Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-01-05

We've added 40 non-merge commits during the last 2 day(s) which contain
a total of 73 files changed, 1526 insertions(+), 951 deletions(-).

The main changes are:

1) Fix a memory leak when streaming AF_UNIX sockets were inserted
   into multiple sockmap slots/maps, from John Fastabend.

2) Fix gotol in s390 BPF JIT with large offsets, from Ilya Leoshkevich.

3) Fix reattachment branch in bpf_tracing_prog_attach() and reject
   the request if there is no valid attach_btf, from Jiri Olsa.

4) Remove deprecated bpfilter kernel leftovers given the project
   is developed in user space (https://github.com/facebook/bpfilter),
   from Quentin Deslandes.

5) Relax tracing BPF program recursive attach rules given right now
   it is not possible to create tracing program call cycles,
   from Dmitrii Dolgov.

6) Fix excessive memory consumption for the bpf_global_percpu_ma
   for systems with a large number of CPUs, from Yonghong Song.

7) Small x86 BPF JIT cleanup to reuse emit_nops instead of open-coding
   memcpy of x86_nops, from Leon Hwang.

8) Follow-up for libbpf to support __arg_ctx global function argument tag
   semantics to complement the merged kernel side, from Andrii Nakryiko.

9) Introduce "volatile compare" macros for BPF selftests in order
   to make the latter more robust against compiler optimization,
   from Alexei Starovoitov.

10) Small simplification in verifier's size checking of helper accesses
    along with additional selftests, from Andrei Matei.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (40 commits)
  selftests/bpf: Test re-attachment fix for bpf_tracing_prog_attach
  bpf: Fix re-attachment branch in bpf_tracing_prog_attach
  selftests/bpf: Add test for recursive attachment of tracing progs
  bpf: Relax tracing prog recursive attach rules
  bpf, x86: Use emit_nops to replace memcpy x86_nops
  selftests/bpf: Test gotol with large offsets
  selftests/bpf: Double the size of test_loader log
  s390/bpf: Fix gotol with large offsets
  bpfilter: remove bpfilter
  bpf: Remove unnecessary cpu == 0 check in memalloc
  selftests/bpf: add __arg_ctx BTF rewrite test
  selftests/bpf: add arg:ctx cases to test_global_funcs tests
  libbpf: implement __arg_ctx fallback logic
  libbpf: move BTF loading step after relocation step
  libbpf: move exception callbacks assignment logic into relocation step
  libbpf: use stable map placeholder FDs
  libbpf: don't rely on map->fd as an indicator of map being created
  libbpf: use explicit map reuse flag to skip map creation steps
  libbpf: make uniform use of btf__fd() accessor inside libbpf
  selftests/bpf: Add a selftest with > 512-byte percpu allocation size
  ...
====================

Link: https://lore.kernel.org/r/20240105170105.21070-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

45 files changed, 855 insertions, 326 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 617ae55c3bb5..fd15017ed3b1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -383,6 +383,7 @@ CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN)	\
 	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR)			\
 	     -I$(abspath $(OUTPUT)/../usr/include)
+# TODO: enable me -Wsign-compare
 
 CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 	       -Wno-compare-distinct-pointer-types
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 1386baf9ae4a..f44875f8b367 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -254,173 +254,97 @@ extern void bpf_throw(u64 cookie) __ksym;
 		}									\
 	 })
 
-/* Description
- *	Assert that a conditional expression is true.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert(cond) if (!(cond)) bpf_throw(0);
-
-/* Description
- *	Assert that a conditional expression is true.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value);
-
-/* Description
- *	Assert that LHS is equal to RHS. This statement updates the known value
- *	of LHS during verification. Note that RHS must be a constant value, and
- *	must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_eq(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, ==, RHS, 0, true);			\
-	})
-
-/* Description
- *	Assert that LHS is equal to RHS. This statement updates the known value
- *	of LHS during verification. Note that RHS must be a constant value, and
- *	must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_eq_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, ==, RHS, value, true);		\
-	})
-
-/* Description
- *	Assert that LHS is less than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_lt(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <, RHS, 0, false);			\
-	})
-
-/* Description
- *	Assert that LHS is less than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_lt_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <, RHS, value, false);		\
-	})
+#define __cmp_cannot_be_signed(x) \
+	__builtin_strcmp(#x, "==") == 0 || __builtin_strcmp(#x, "!=") == 0 || \
+	__builtin_strcmp(#x, "&") == 0
 
-/* Description
- *	Assert that LHS is greater than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_gt(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >, RHS, 0, false);			\
-	})
+#define __is_signed_type(type) (((type)(-1)) < (type)1)
 
-/* Description
- *	Assert that LHS is greater than RHS. This statement updates the known
- *	bounds of LHS during verification. Note that RHS must be a constant
- *	value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
+#define __bpf_cmp(LHS, OP, SIGN, PRED, RHS, DEFAULT)						\
+	({											\
+		__label__ l_true;								\
+		bool ret = DEFAULT;								\
+		asm volatile goto("if %[lhs] " SIGN #OP " %[rhs] goto %l[l_true]"		\
+				  :: [lhs] "r"((short)LHS), [rhs] PRED (RHS) :: l_true);	\
+		ret = !DEFAULT;									\
+l_true:												\
+		ret;										\
+       })
+
+/* C type conversions coupled with comparison operator are tricky.
+ * Make sure BPF program is compiled with -Wsign-compare then
+ * __lhs OP __rhs below will catch the mistake.
+ * Be aware that we check only __lhs to figure out the sign of compare.
  */
-#define bpf_assert_gt_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >, RHS, value, false);		\
-	})
+#define _bpf_cmp(LHS, OP, RHS, NOFLIP)								\
+	({											\
+		typeof(LHS) __lhs = (LHS);							\
+		typeof(RHS) __rhs = (RHS);							\
+		bool ret;									\
+		_Static_assert(sizeof(&(LHS)), "1st argument must be an lvalue expression");	\
+		(void)(__lhs OP __rhs);								\
+		if (__cmp_cannot_be_signed(OP) || !__is_signed_type(typeof(__lhs))) {		\
+			if (sizeof(__rhs) == 8)							\
+				ret = __bpf_cmp(__lhs, OP, "", "r", __rhs, NOFLIP);		\
+			else									\
+				ret = __bpf_cmp(__lhs, OP, "", "i", __rhs, NOFLIP);		\
+		} else {									\
+			if (sizeof(__rhs) == 8)							\
+				ret = __bpf_cmp(__lhs, OP, "s", "r", __rhs, NOFLIP);		\
+			else									\
+				ret = __bpf_cmp(__lhs, OP, "s", "i", __rhs, NOFLIP);		\
+		}										\
+		ret;										\
+       })
+
+#ifndef bpf_cmp_unlikely
+#define bpf_cmp_unlikely(LHS, OP, RHS) _bpf_cmp(LHS, OP, RHS, true)
+#endif
 
-/* Description
- *	Assert that LHS is less than or equal to RHS. This statement updates the
- *	known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the value zero when the assertion fails.
- */
-#define bpf_assert_le(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <=, RHS, 0, false);		\
-	})
+#ifndef bpf_cmp_likely
+#define bpf_cmp_likely(LHS, OP, RHS)								\
+	({											\
+		bool ret;									\
+		if (__builtin_strcmp(#OP, "==") == 0)						\
+			ret = _bpf_cmp(LHS, !=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "!=") == 0)					\
+			ret = _bpf_cmp(LHS, ==, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "<=") == 0)					\
+			ret = _bpf_cmp(LHS, >, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "<") == 0)					\
+			ret = _bpf_cmp(LHS, >=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, ">") == 0)					\
+			ret = _bpf_cmp(LHS, <=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, ">=") == 0)					\
+			ret = _bpf_cmp(LHS, <, RHS, false);					\
+		else										\
+			(void) "bug";								\
+		ret;										\
+       })
+#endif
 
-/* Description
- *	Assert that LHS is less than or equal to RHS. This statement updates the
- *	known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
- * Returns
- *	Void.
- * Throws
- *	An exception with the specified value when the assertion fails.
- */
-#define bpf_assert_le_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, <=, RHS, value, false);		\
-	})
+#ifndef bpf_nop_mov
+#define bpf_nop_mov(var) \
+	asm volatile("%[reg]=%[reg]"::[reg]"r"((short)var))
+#endif
 
 /* Description
- *	Assert that LHS is greater than or equal to RHS. This statement updates
- *	the known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
+ *	Assert that a conditional expression is true.
  * Returns
  *	Void.
  * Throws
  *	An exception with the value zero when the assertion fails.
  */
-#define bpf_assert_ge(LHS, RHS)						\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >=, RHS, 0, false);		\
-	})
+#define bpf_assert(cond) if (!(cond)) bpf_throw(0);
 
 /* Description
- *	Assert that LHS is greater than or equal to RHS. This statement updates
- *	the known bounds of LHS during verification. Note that RHS must be a
- *	constant value, and must fit within the data type of LHS.
+ *	Assert that a conditional expression is true.
  * Returns
  *	Void.
  * Throws
  *	An exception with the specified value when the assertion fails.
  */
-#define bpf_assert_ge_with(LHS, RHS, value)				\
-	({								\
-		barrier_var(LHS);					\
-		__bpf_assert_op(LHS, >=, RHS, value, false);		\
-	})
+#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value);
 
 /* Description
  *	Assert that LHS is in the range [BEG, END] (inclusive of both). This
diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64
index 29c8635c5722..3720b7611523 100644
--- a/tools/testing/selftests/bpf/config.aarch64
+++ b/tools/testing/selftests/bpf/config.aarch64
@@ -11,7 +11,6 @@ CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BONDING=y
-CONFIG_BPFILTER=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD_UMD=y
diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x
index e93330382849..706931a8c2c6 100644
--- a/tools/testing/selftests/bpf/config.s390x
+++ b/tools/testing/selftests/bpf/config.s390x
@@ -9,7 +9,6 @@ CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_FREEZER=y
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index b946088017f1..5680befae8c6 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -19,7 +19,6 @@ CONFIG_BOOTTIME_TRACING=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_CFS_BANDWIDTH=y
diff --git a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
new file mode 100644
index 000000000000..8100509e561b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <test_progs.h>
+#include "fentry_recursive.skel.h"
+#include "fentry_recursive_target.skel.h"
+#include <bpf/btf.h>
+#include "bpf/libbpf_internal.h"
+
+/* Test recursive attachment of tracing progs with more than one nesting level
+ * is not possible. Create a chain of attachment, verify that the last prog
+ * will fail. Depending on the arguments, following cases are tested:
+ *
+ * - Recursive loading of tracing progs, without attaching (attach = false,
+ *   detach = false). The chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       load fentry2 -> fentry1 (fail)
+ *
+ * - Recursive attach of tracing progs (attach = true, detach = false). The
+ *   chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       attach fentry1 -> target
+ *       load fentry2 -> fentry1 (fail)
+ *
+ * - Recursive attach and detach of tracing progs (attach = true, detach =
+ *   true). This validates that attach_tracing_prog flag will be set throughout
+ *   the whole lifecycle of an fentry prog, independently from whether it's
+ *   detached. The chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       attach fentry1 -> target
+ *       detach fentry1
+ *       load fentry2 -> fentry1 (fail)
+ */
+static void test_recursive_fentry_chain(bool attach, bool detach)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_chain[2] = {};
+	struct bpf_program *prog;
+	int prev_fd, err;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel, "fentry_recursive_target__open_and_load"))
+		return;
+
+	/* Create an attachment chain with two fentry progs */
+	for (int i = 0; i < 2; i++) {
+		tracing_chain[i] = fentry_recursive__open();
+		if (!ASSERT_OK_PTR(tracing_chain[i], "fentry_recursive__open"))
+			goto close_prog;
+
+		/* The first prog in the chain is going to be attached to the target
+		 * fentry program, the second one to the previous in the chain.
+		 */
+		prog = tracing_chain[i]->progs.recursive_attach;
+		if (i == 0) {
+			prev_fd = bpf_program__fd(target_skel->progs.test1);
+			err = bpf_program__set_attach_target(prog, prev_fd, "test1");
+		} else {
+			prev_fd = bpf_program__fd(tracing_chain[i-1]->progs.recursive_attach);
+			err = bpf_program__set_attach_target(prog, prev_fd, "recursive_attach");
+		}
+
+		if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+			goto close_prog;
+
+		err = fentry_recursive__load(tracing_chain[i]);
+		/* The first attach should succeed, the second fail */
+		if (i == 0) {
+			if (!ASSERT_OK(err, "fentry_recursive__load"))
+				goto close_prog;
+
+			if (attach) {
+				err = fentry_recursive__attach(tracing_chain[i]);
+				if (!ASSERT_OK(err, "fentry_recursive__attach"))
+					goto close_prog;
+			}
+
+			if (detach) {
+				/* Flag attach_tracing_prog should still be set, preventing
+				 * attachment of the following prog.
+				 */
+				fentry_recursive__detach(tracing_chain[i]);
+			}
+		} else {
+			if (!ASSERT_ERR(err, "fentry_recursive__load"))
+				goto close_prog;
+		}
+	}
+
+close_prog:
+	fentry_recursive_target__destroy(target_skel);
+	for (int i = 0; i < 2; i++) {
+		fentry_recursive__destroy(tracing_chain[i]);
+	}
+}
+
+void test_recursive_fentry(void)
+{
+	if (test__start_subtest("attach"))
+		test_recursive_fentry_chain(true, false);
+	if (test__start_subtest("load"))
+		test_recursive_fentry_chain(false, false);
+	if (test__start_subtest("detach"))
+		test_recursive_fentry_chain(true, true);
+}
+
+/* Test that a tracing prog reattachment (when we land in
+ * "prog->aux->dst_trampoline and tgt_prog is NULL" branch in
+ * bpf_tracing_prog_attach) does not lead to a crash due to missing attach_btf
+ */
+void test_fentry_attach_btf_presence(void)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_skel = NULL;
+	struct bpf_program *prog;
+	int err, link_fd, tgt_prog_fd;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel, "fentry_recursive_target__open_and_load"))
+		goto close_prog;
+
+	tracing_skel = fentry_recursive__open();
+	if (!ASSERT_OK_PTR(tracing_skel, "fentry_recursive__open"))
+		goto close_prog;
+
+	prog = tracing_skel->progs.recursive_attach;
+	tgt_prog_fd = bpf_program__fd(target_skel->progs.fentry_target);
+	err = bpf_program__set_attach_target(prog, tgt_prog_fd, "fentry_target");
+	if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+		goto close_prog;
+
+	err = fentry_recursive__load(tracing_skel);
+	if (!ASSERT_OK(err, "fentry_recursive__load"))
+		goto close_prog;
+
+	tgt_prog_fd = bpf_program__fd(tracing_skel->progs.recursive_attach);
+	link_fd = bpf_link_create(tgt_prog_fd, 0, BPF_TRACE_FENTRY, NULL);
+	if (!ASSERT_GE(link_fd, 0, "link_fd"))
+		goto close_prog;
+
+	fentry_recursive__detach(tracing_skel);
+
+	err = fentry_recursive__attach(tracing_skel);
+	ASSERT_ERR(err, "fentry_recursive__attach");
+
+close_prog:
+	fentry_recursive_target__destroy(target_skel);
+	fentry_recursive__destroy(tracing_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 7c2241fae19a..77e26ecffa9d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -555,6 +555,213 @@ static void test_sockmap_unconnected_unix(void)
 	close(dgram);
 }
 
+static void test_sockmap_many_socket(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map, entry = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+	for (entry--; entry >= 0; entry--) {
+		err = bpf_map_delete_elem(map, &entry);
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	}
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_many_maps(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map[2], entry = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map[0] = bpf_map__fd(skel->maps.sock_map_rx);
+	map[1] = bpf_map__fd(skel->maps.sock_map_tx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+	for (entry--; entry >= 0; entry--) {
+		err = bpf_map_delete_elem(map[1], &entry);
+		entry--;
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+		err = bpf_map_delete_elem(map[0], &entry);
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	}
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_same_sock(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map, zero = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+
+	err = bpf_map_delete_elem(map, &zero);
+	ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -597,7 +804,12 @@ void test_sockmap_basic(void)
 		test_sockmap_skb_verdict_fionread(false);
 	if (test__start_subtest("sockmap skb_verdict msg_f_peek"))
 		test_sockmap_skb_verdict_peek();
-
 	if (test__start_subtest("sockmap unconnected af_unix"))
 		test_sockmap_unconnected_unix();
+	if (test__start_subtest("sockmap one socket to many map entries"))
+		test_sockmap_many_socket();
+	if (test__start_subtest("sockmap one socket to many maps"))
+		test_sockmap_many_maps();
+	if (test__start_subtest("sockmap same socket replace"))
+		test_sockmap_same_sock();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
index d3491a84b3b9..ccae0b31ac6c 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
@@ -14,7 +14,8 @@ static void do_bpf_ma_test(const char *name)
 	struct test_bpf_ma *skel;
 	struct bpf_program *prog;
 	struct btf *btf;
-	int i, err;
+	int i, err, id;
+	char tname[32];
 
 	skel = test_bpf_ma__open();
 	if (!ASSERT_OK_PTR(skel, "open"))
@@ -25,16 +26,21 @@ static void do_bpf_ma_test(const char *name)
 		goto out;
 
 	for (i = 0; i < ARRAY_SIZE(skel->rodata->data_sizes); i++) {
-		char name[32];
-		int id;
-
-		snprintf(name, sizeof(name), "bin_data_%u", skel->rodata->data_sizes[i]);
-		id = btf__find_by_name_kind(btf, name, BTF_KIND_STRUCT);
-		if (!ASSERT_GT(id, 0, "bin_data"))
+		snprintf(tname, sizeof(tname), "bin_data_%u", skel->rodata->data_sizes[i]);
+		id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, tname))
 			goto out;
 		skel->rodata->data_btf_ids[i] = id;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(skel->rodata->percpu_data_sizes); i++) {
+		snprintf(tname, sizeof(tname), "percpu_bin_data_%u", skel->rodata->percpu_data_sizes[i]);
+		id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, tname))
+			goto out;
+		skel->rodata->percpu_data_btf_ids[i] = id;
+	}
+
 	prog = bpf_object__find_program_by_name(skel->obj, name);
 	if (!ASSERT_OK_PTR(prog, "invalid prog name"))
 		goto out;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index e0879df38639..67d4ef9e62b3 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -20,6 +20,109 @@
 #include "test_global_func17.skel.h"
 #include "test_global_func_ctx_args.skel.h"
 
+#include "bpf/libbpf_internal.h"
+#include "btf_helpers.h"
+
+static void check_ctx_arg_type(const struct btf *btf, const struct btf_param *p)
+{
+	const struct btf_type *t;
+	const char *s;
+
+	t = btf__type_by_id(btf, p->type);
+	if (!ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_t"))
+		return;
+
+	s = btf_type_raw_dump(btf, t->type);
+	if (!ASSERT_HAS_SUBSTR(s, "STRUCT 'bpf_perf_event_data' size=0 vlen=0",
+			       "ctx_struct_t"))
+		return;
+}
+
+static void subtest_ctx_arg_rewrite(void)
+{
+	struct test_global_func_ctx_args *skel = NULL;
+	struct bpf_prog_info info;
+	char func_info_buf[1024] __attribute__((aligned(8)));
+	struct bpf_func_info_min *rec;
+	struct btf *btf = NULL;
+	__u32 info_len = sizeof(info);
+	int err, fd, i;
+
+	skel = test_global_func_ctx_args__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.arg_tag_ctx_perf, true);
+
+	err = test_global_func_ctx_args__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto out;
+
+	memset(&info, 0, sizeof(info));
+	info.func_info = ptr_to_u64(&func_info_buf);
+	info.nr_func_info = 3;
+	info.func_info_rec_size = sizeof(struct bpf_func_info_min);
+
+	fd = bpf_program__fd(skel->progs.arg_tag_ctx_perf);
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "prog_info"))
+		goto out;
+
+	if (!ASSERT_EQ(info.nr_func_info, 3, "nr_func_info"))
+		goto out;
+
+	btf = btf__load_from_kernel_by_id(info.btf_id);
+	if (!ASSERT_OK_PTR(btf, "obj_kern_btf"))
+		goto out;
+
+	rec = (struct bpf_func_info_min *)func_info_buf;
+	for (i = 0; i < info.nr_func_info; i++, rec = (void *)rec + info.func_info_rec_size) {
+		const struct btf_type *fn_t, *proto_t;
+		const char *name;
+
+		if (rec->insn_off == 0)
+			continue; /* main prog, skip */
+
+		fn_t = btf__type_by_id(btf, rec->type_id);
+		if (!ASSERT_OK_PTR(fn_t, "fn_type"))
+			goto out;
+		if (!ASSERT_EQ(btf_kind(fn_t), BTF_KIND_FUNC, "fn_type_kind"))
+			goto out;
+		proto_t = btf__type_by_id(btf, fn_t->type);
+		if (!ASSERT_OK_PTR(proto_t, "proto_type"))
+			goto out;
+
+		name = btf__name_by_offset(btf, fn_t->name_off);
+		if (strcmp(name, "subprog_ctx_tag") == 0) {
+			/* int subprog_ctx_tag(void *ctx __arg_ctx) */
+			if (!ASSERT_EQ(btf_vlen(proto_t), 1, "arg_cnt"))
+				goto out;
+
+			/* arg 0 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[0]);
+		} else if (strcmp(name, "subprog_multi_ctx_tags") == 0) {
+			/* int subprog_multi_ctx_tags(void *ctx1 __arg_ctx,
+			 *			      struct my_struct *mem,
+			 *			      void *ctx2 __arg_ctx)
+			 */
+			if (!ASSERT_EQ(btf_vlen(proto_t), 3, "arg_cnt"))
+				goto out;
+
+			/* arg 0 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[0]);
+			/* arg 2 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[2]);
+		} else {
+			ASSERT_FAIL("unexpected subprog %s", name);
+			goto out;
+		}
+	}
+
+out:
+	btf__free(btf);
+	test_global_func_ctx_args__destroy(skel);
+}
+
 void test_test_global_funcs(void)
 {
 	RUN_TESTS(test_global_func1);
@@ -40,4 +143,7 @@ void test_test_global_funcs(void)
 	RUN_TESTS(test_global_func16);
 	RUN_TESTS(test_global_func17);
 	RUN_TESTS(test_global_func_ctx_args);
+
+	if (test__start_subtest("ctx_arg_rewrite"))
+		subtest_ctx_arg_rewrite();
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
index feaaa2b89c57..5014a17d6c02 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
@@ -20,7 +20,7 @@ struct {
 } hashmap1 SEC(".maps");
 
 /* will set before prog run */
-volatile const __u32 num_cpus = 0;
+volatile const __s32 num_cpus = 0;
 
 /* will collect results during prog run */
 __u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
index dd923dc637d5..423b39e60b6f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
@@ -35,7 +35,7 @@ SEC("iter/task_vma") int proc_maps(struct bpf_iter__task_vma *ctx)
 		return 0;
 
 	file = vma->vm_file;
-	if (task->tgid != pid) {
+	if (task->tgid != (pid_t)pid) {
 		if (one_task)
 			one_task_error = 1;
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
index 96131b9a1caa..6cbb3393f243 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
@@ -22,7 +22,7 @@ int dump_task(struct bpf_iter__task *ctx)
 		return 0;
 	}
 
-	if (task->pid != tid)
+	if (task->pid != (pid_t)tid)
 		num_unknown_tid++;
 	else
 		num_known_tid++;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
index 400fdf8d6233..dbf61c44acac 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
@@ -45,7 +45,7 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 	}
 
 	/* fill seq_file buffer */
-	for (i = 0; i < print_len; i++)
+	for (i = 0; i < (int)print_len; i++)
 		bpf_seq_write(seq, &seq_num, sizeof(seq_num));
 
 	return ret;
diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
index b7fa8804e19d..45a0e9f492a9 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
@@ -11,7 +11,7 @@
 __u32 invocations = 0;
 __u32 assertion_error = 0;
 __u32 retval_value = 0;
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/setsockopt")
 int get_retval(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
index facedd8b8250..5e282c16eadc 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
@@ -15,7 +15,7 @@ struct {
 	__type(value, long);
 } map_a SEC(".maps");
 
-__u32 target_pid;
+__s32 target_pid;
 __u64 cgroup_id;
 int target_hid;
 bool is_cgroup1;
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
index fc3666edf456..7a1e64c6c065 100644
--- a/tools/testing/selftests/bpf/progs/cpumask_success.c
+++ b/tools/testing/selftests/bpf/progs/cpumask_success.c
@@ -332,7 +332,7 @@ SEC("tp_btf/task_newtask")
 int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags)
 {
 	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
-	u32 cpu;
+	int cpu;
 
 	if (!is_test_task())
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/exceptions.c b/tools/testing/selftests/bpf/progs/exceptions.c
index 2811ee842b01..f09cd14d8e04 100644
--- a/tools/testing/selftests/bpf/progs/exceptions.c
+++ b/tools/testing/selftests/bpf/progs/exceptions.c
@@ -210,7 +210,7 @@ __noinline int assert_zero_gfunc(u64 c)
 {
 	volatile u64 cookie = c;
 
-	bpf_assert_eq(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, ==, 0));
 	return 0;
 }
 
@@ -218,7 +218,7 @@ __noinline int assert_neg_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_lt(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, <, 0));
 	return 0;
 }
 
@@ -226,7 +226,7 @@ __noinline int assert_pos_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_gt(cookie, 0);
+	bpf_assert(bpf_cmp_unlikely(cookie, >, 0));
 	return 0;
 }
 
@@ -234,7 +234,7 @@ __noinline int assert_negeq_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_le(cookie, -1);
+	bpf_assert(bpf_cmp_unlikely(cookie, <=, -1));
 	return 0;
 }
 
@@ -242,7 +242,7 @@ __noinline int assert_poseq_gfunc(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_ge(cookie, 1);
+	bpf_assert(bpf_cmp_unlikely(cookie, >=, 1));
 	return 0;
 }
 
@@ -258,7 +258,7 @@ __noinline int assert_zero_gfunc_with(u64 c)
 {
 	volatile u64 cookie = c;
 
-	bpf_assert_eq_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, ==, 0), cookie + 100);
 	return 0;
 }
 
@@ -266,7 +266,7 @@ __noinline int assert_neg_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_lt_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, <, 0), cookie + 100);
 	return 0;
 }
 
@@ -274,7 +274,7 @@ __noinline int assert_pos_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_gt_with(cookie, 0, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, >, 0), cookie + 100);
 	return 0;
 }
 
@@ -282,7 +282,7 @@ __noinline int assert_negeq_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_le_with(cookie, -1, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, <=, -1), cookie + 100);
 	return 0;
 }
 
@@ -290,7 +290,7 @@ __noinline int assert_poseq_gfunc_with(s64 c)
 {
 	volatile s64 cookie = c;
 
-	bpf_assert_ge_with(cookie, 1, cookie + 100);
+	bpf_assert_with(bpf_cmp_unlikely(cookie, >=, 1), cookie + 100);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
index 0ef81040da59..5e0a1ca96d4e 100644
--- a/tools/testing/selftests/bpf/progs/exceptions_assert.c
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -11,51 +11,51 @@
 #define check_assert(type, op, name, value)				\
 	SEC("?tc")							\
 	__log_level(2) __failure					\
-	int check_assert_##op##_##name(void *ctx)			\
+	int check_assert_##name(void *ctx)				\
 	{								\
 		type num = bpf_ktime_get_ns();				\
-		bpf_assert_##op(num, value);				\
+		bpf_assert(bpf_cmp_unlikely(num, op, value));		\
 		return *(u64 *)num;					\
 	}
 
-__msg(": R0_w=0xffffffff80000000 R10=fp0")
-check_assert(s64, eq, int_min, INT_MIN);
-__msg(": R0_w=0x7fffffff R10=fp0")
-check_assert(s64, eq, int_max, INT_MAX);
-__msg(": R0_w=0 R10=fp0")
-check_assert(s64, eq, zero, 0);
-__msg(": R0_w=0x8000000000000000 R1_w=0x8000000000000000 R10=fp0")
-check_assert(s64, eq, llong_min, LLONG_MIN);
-__msg(": R0_w=0x7fffffffffffffff R1_w=0x7fffffffffffffff R10=fp0")
-check_assert(s64, eq, llong_max, LLONG_MAX);
-
-__msg(": R0_w=scalar(smax=0x7ffffffe) R10=fp0")
-check_assert(s64, lt, pos, INT_MAX);
-__msg(": R0_w=scalar(smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, lt, zero, 0);
-__msg(": R0_w=scalar(smax=0xffffffff7fffffff,umin=0x8000000000000000,umax=0xffffffff7fffffff,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, lt, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smax=0x7fffffff) R10=fp0")
-check_assert(s64, le, pos, INT_MAX);
-__msg(": R0_w=scalar(smax=0) R10=fp0")
-check_assert(s64, le, zero, 0);
-__msg(": R0_w=scalar(smax=0xffffffff80000000,umin=0x8000000000000000,umax=0xffffffff80000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
-check_assert(s64, le, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, gt, pos, INT_MAX);
-__msg(": R0_w=scalar(smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, gt, zero, 0);
-__msg(": R0_w=scalar(smin=0xffffffff80000001) R10=fp0")
-check_assert(s64, gt, neg, INT_MIN);
-
-__msg(": R0_w=scalar(smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
-check_assert(s64, ge, pos, INT_MAX);
-__msg(": R0_w=scalar(smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff)) R10=fp0")
-check_assert(s64, ge, zero, 0);
-__msg(": R0_w=scalar(smin=0xffffffff80000000) R10=fp0")
-check_assert(s64, ge, neg, INT_MIN);
+__msg(": R0_w=0xffffffff80000000")
+check_assert(s64, ==, eq_int_min, INT_MIN);
+__msg(": R0_w=0x7fffffff")
+check_assert(s64, ==, eq_int_max, INT_MAX);
+__msg(": R0_w=0")
+check_assert(s64, ==, eq_zero, 0);
+__msg(": R0_w=0x8000000000000000 R1_w=0x8000000000000000")
+check_assert(s64, ==, eq_llong_min, LLONG_MIN);
+__msg(": R0_w=0x7fffffffffffffff R1_w=0x7fffffffffffffff")
+check_assert(s64, ==, eq_llong_max, LLONG_MAX);
+
+__msg(": R0_w=scalar(id=1,smax=0x7ffffffe)")
+check_assert(s64, <, lt_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+check_assert(s64, <, lt_zero, 0);
+__msg(": R0_w=scalar(id=1,smax=0xffffffff7fffffff")
+check_assert(s64, <, lt_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smax=0x7fffffff)")
+check_assert(s64, <=, le_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smax=0)")
+check_assert(s64, <=, le_zero, 0);
+__msg(": R0_w=scalar(id=1,smax=0xffffffff80000000")
+check_assert(s64, <=, le_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >, gt_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >, gt_zero, 0);
+__msg(": R0_w=scalar(id=1,smin=0xffffffff80000001")
+check_assert(s64, >, gt_neg, INT_MIN);
+
+__msg(": R0_w=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >=, ge_pos, INT_MAX);
+__msg(": R0_w=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >=, ge_zero, 0);
+__msg(": R0_w=scalar(id=1,smin=0xffffffff80000000")
+check_assert(s64, >=, ge_neg, INT_MIN);
 
 SEC("?tc")
 __log_level(2) __failure
diff --git a/tools/testing/selftests/bpf/progs/fentry_recursive.c b/tools/testing/selftests/bpf/progs/fentry_recursive.c
new file mode 100644
index 000000000000..2c9fb5ac42b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_recursive.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Dummy fentry bpf prog for testing fentry attachment chains */
+SEC("fentry/XXX")
+int BPF_PROG(recursive_attach, int a)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fentry_recursive_target.c b/tools/testing/selftests/bpf/progs/fentry_recursive_target.c
new file mode 100644
index 000000000000..267c876d0aba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_recursive_target.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Dummy fentry bpf prog for testing fentry attachment chains. It's going to be
+ * a start of the chain.
+ */
+SEC("fentry/bpf_testmod_fentry_test1")
+int BPF_PROG(test1, int a)
+{
+	return 0;
+}
+
+/* Dummy bpf prog for testing attach_btf presence when attaching an fentry
+ * program.
+ */
+SEC("raw_tp/sys_enter")
+int BPF_PROG(fentry_target, struct pt_regs *regs, long id)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 3aca3dc145b5..fe971992e635 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -6,7 +6,7 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#define ARRAY_SIZE(x) (int)(sizeof(x) / sizeof((x)[0]))
 
 static volatile int zero = 0;
 
@@ -676,7 +676,7 @@ static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n)
 
 	while ((t = bpf_iter_num_next(it))) {
 		i = *t;
-		if (i >= n)
+		if ((__u32)i >= n)
 			break;
 		sum += arr[i];
 	}
diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c
index e085a51d153e..dc0c3691dcc2 100644
--- a/tools/testing/selftests/bpf/progs/iters_task_vma.c
+++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c
@@ -28,9 +28,8 @@ int iter_task_vma_for_each(const void *ctx)
 		return 0;
 
 	bpf_for_each(task_vma, vma, task, 0) {
-		if (seen >= 1000)
+		if (bpf_cmp_unlikely(seen, >=, 1000))
 			break;
-		barrier_var(seen);
 
 		vm_ranges[seen].vm_start = vma->vm_start;
 		vm_ranges[seen].vm_end = vma->vm_end;
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs1.c b/tools/testing/selftests/bpf/progs/linked_funcs1.c
index c4b49ceea967..cc79dddac182 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs1.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs1.c
@@ -8,7 +8,7 @@
 #include "bpf_misc.h"
 
 /* weak and shared between two files */
-const volatile int my_tid __weak;
+const volatile __u32 my_tid __weak;
 long syscall_id __weak;
 
 int output_val1;
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs2.c b/tools/testing/selftests/bpf/progs/linked_funcs2.c
index 013ff0645f0c..942cc5526ddf 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs2.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs2.c
@@ -68,7 +68,7 @@ int BPF_PROG(handler2, struct pt_regs *regs, long id)
 {
 	static volatile int whatever;
 
-	if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
+	if (my_tid != (s32)bpf_get_current_pid_tgid() || id != syscall_id)
 		return 0;
 
 	/* make sure we have CO-RE relocations in main program */
diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c
index 84d1777a9e6c..26205ca80679 100644
--- a/tools/testing/selftests/bpf/progs/linked_list.c
+++ b/tools/testing/selftests/bpf/progs/linked_list.c
@@ -6,7 +6,7 @@
 #include "bpf_experimental.h"
 
 #ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#define ARRAY_SIZE(x) (int)(sizeof(x) / sizeof((x)[0]))
 #endif
 
 #include "linked_list.h"
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index bc8ea56671a1..e5e3a8b8dd07 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -13,7 +13,7 @@ char _license[] SEC("license") = "GPL";
 
 #define DUMMY_STORAGE_VALUE 0xdeadbeef
 
-int monitored_pid = 0;
+__u32 monitored_pid = 0;
 int inode_storage_result = -1;
 int sk_storage_result = -1;
 int task_storage_result = -1;
diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c
index fadfdd98707c..0c13b7409947 100644
--- a/tools/testing/selftests/bpf/progs/lsm.c
+++ b/tools/testing/selftests/bpf/progs/lsm.c
@@ -92,7 +92,7 @@ int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
 	if (ret != 0)
 		return ret;
 
-	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+	__s32 pid = bpf_get_current_pid_tgid() >> 32;
 	int is_stack = 0;
 
 	is_stack = (vma->vm_start <= vma->vm_mm->start_stack &&
diff --git a/tools/testing/selftests/bpf/progs/normal_map_btf.c b/tools/testing/selftests/bpf/progs/normal_map_btf.c
index 66cde82aa86d..a45c9299552c 100644
--- a/tools/testing/selftests/bpf/progs/normal_map_btf.c
+++ b/tools/testing/selftests/bpf/progs/normal_map_btf.c
@@ -36,7 +36,7 @@ int add_to_list_in_array(void *ctx)
 	struct node_data *new;
 	int zero = 0;
 
-	if (done || (u32)bpf_get_current_pid_tgid() != pid)
+	if (done || (int)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
 	value = bpf_map_lookup_elem(&array, &zero);
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
index 1a891d30f1fe..f2b8eb2ff76f 100644
--- a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
@@ -17,6 +17,10 @@ struct val_with_rb_root_t {
 	struct bpf_spin_lock lock;
 };
 
+struct val_600b_t {
+	char b[600];
+};
+
 struct elem {
 	long sum;
 	struct val_t __percpu_kptr *pc;
@@ -161,4 +165,18 @@ int BPF_PROG(test_array_map_7)
 	return 0;
 }
 
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("bpf_percpu_obj_new type size (600) is greater than 512")
+int BPF_PROG(test_array_map_8)
+{
+	struct val_600b_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_600b_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 897061930cb7..de3b6e4e4d0a 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -7,6 +7,7 @@
 
 #include "profiler.h"
 #include "err.h"
+#include "bpf_experimental.h"
 
 #ifndef NULL
 #define NULL 0
@@ -132,7 +133,7 @@ struct {
 } disallowed_exec_inodes SEC(".maps");
 
 #ifndef ARRAY_SIZE
-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
+#define ARRAY_SIZE(arr) (int)(sizeof(arr) / sizeof(arr[0]))
 #endif
 
 static INLINE bool IS_ERR(const void* ptr)
@@ -221,8 +222,7 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node,
 			return payload;
 		if (cgroup_node == cgroup_root_node)
 			*root_pos = payload - payload_start;
-		if (filepart_length <= MAX_PATH) {
-			barrier_var(filepart_length);
+		if (bpf_cmp_likely(filepart_length, <=, MAX_PATH)) {
 			payload += filepart_length;
 		}
 		cgroup_node = BPF_CORE_READ(cgroup_node, parent);
@@ -305,9 +305,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 	size_t cgroup_root_length =
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(root_kernfs, name));
-	barrier_var(cgroup_root_length);
-	if (cgroup_root_length <= MAX_PATH) {
-		barrier_var(cgroup_root_length);
+	if (bpf_cmp_likely(cgroup_root_length, <=, MAX_PATH)) {
 		cgroup_data->cgroup_root_length = cgroup_root_length;
 		payload += cgroup_root_length;
 	}
@@ -315,9 +313,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 	size_t cgroup_proc_length =
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(proc_kernfs, name));
-	barrier_var(cgroup_proc_length);
-	if (cgroup_proc_length <= MAX_PATH) {
-		barrier_var(cgroup_proc_length);
+	if (bpf_cmp_likely(cgroup_proc_length, <=, MAX_PATH)) {
 		cgroup_data->cgroup_proc_length = cgroup_proc_length;
 		payload += cgroup_proc_length;
 	}
@@ -347,9 +343,7 @@ static INLINE void* populate_var_metadata(struct var_metadata_t* metadata,
 	metadata->comm_length = 0;
 
 	size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
-	barrier_var(comm_length);
-	if (comm_length <= TASK_COMM_LEN) {
-		barrier_var(comm_length);
+	if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
 		metadata->comm_length = comm_length;
 		payload += comm_length;
 	}
@@ -494,10 +488,9 @@ read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload)
 		filepart_length =
 			bpf_probe_read_kernel_str(payload, MAX_PATH,
 						  BPF_CORE_READ(filp_dentry, d_name.name));
-		barrier_var(filepart_length);
-		if (filepart_length > MAX_PATH)
+		bpf_nop_mov(filepart_length);
+		if (bpf_cmp_unlikely(filepart_length, >, MAX_PATH))
 			break;
-		barrier_var(filepart_length);
 		payload += filepart_length;
 		length += filepart_length;
 
@@ -579,9 +572,7 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write,
 
 	size_t sysctl_val_length = bpf_probe_read_kernel_str(payload,
 							     CTL_MAXNAME, buf);
-	barrier_var(sysctl_val_length);
-	if (sysctl_val_length <= CTL_MAXNAME) {
-		barrier_var(sysctl_val_length);
+	if (bpf_cmp_likely(sysctl_val_length, <=, CTL_MAXNAME)) {
 		sysctl_data->sysctl_val_length = sysctl_val_length;
 		payload += sysctl_val_length;
 	}
@@ -590,9 +581,7 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write,
 		bpf_probe_read_kernel_str(payload, MAX_PATH,
 					  BPF_CORE_READ(filp, f_path.dentry,
 							d_name.name));
-	barrier_var(sysctl_path_length);
-	if (sysctl_path_length <= MAX_PATH) {
-		barrier_var(sysctl_path_length);
+	if (bpf_cmp_likely(sysctl_path_length, <=, MAX_PATH)) {
 		sysctl_data->sysctl_path_length = sysctl_path_length;
 		payload += sysctl_path_length;
 	}
@@ -645,7 +634,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) {
 		struct var_kill_data_t* past_kill_data = &arr_struct->array[i];
 
-		if (past_kill_data != NULL && past_kill_data->kill_target_pid == tpid) {
+		if (past_kill_data != NULL && past_kill_data->kill_target_pid == (pid_t)tpid) {
 			bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data),
 					      past_kill_data);
 			void* payload = kill_data->payload;
@@ -658,9 +647,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 			kill_data->kill_target_cgroup_proc_length = 0;
 
 			size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
-			barrier_var(comm_length);
-			if (comm_length <= TASK_COMM_LEN) {
-				barrier_var(comm_length);
+			if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
 				kill_data->kill_target_name_length = comm_length;
 				payload += comm_length;
 			}
@@ -669,9 +656,7 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 				bpf_probe_read_kernel_str(payload,
 							  KILL_TARGET_LEN,
 							  BPF_CORE_READ(proc_kernfs, name));
-			barrier_var(cgroup_proc_length);
-			if (cgroup_proc_length <= KILL_TARGET_LEN) {
-				barrier_var(cgroup_proc_length);
+			if (bpf_cmp_likely(cgroup_proc_length, <=, KILL_TARGET_LEN)) {
 				kill_data->kill_target_cgroup_proc_length = cgroup_proc_length;
 				payload += cgroup_proc_length;
 			}
@@ -731,9 +716,7 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
 	const char* filename = BPF_CORE_READ(bprm, filename);
 	size_t bin_path_length =
 		bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename);
-	barrier_var(bin_path_length);
-	if (bin_path_length <= MAX_FILENAME_LEN) {
-		barrier_var(bin_path_length);
+	if (bpf_cmp_likely(bin_path_length, <=, MAX_FILENAME_LEN)) {
 		proc_exec_data->bin_path_length = bin_path_length;
 		payload += bin_path_length;
 	}
@@ -743,8 +726,7 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
 	unsigned int cmdline_length = probe_read_lim(payload, arg_start,
 						     arg_end - arg_start, MAX_ARGS_LEN);
 
-	if (cmdline_length <= MAX_ARGS_LEN) {
-		barrier_var(cmdline_length);
+	if (bpf_cmp_likely(cmdline_length, <=, MAX_ARGS_LEN)) {
 		proc_exec_data->cmdline_length = cmdline_length;
 		payload += cmdline_length;
 	}
@@ -821,9 +803,7 @@ int kprobe_ret__do_filp_open(struct pt_regs* ctx)
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
 	size_t len = read_absolute_file_path_from_dentry(filp_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
@@ -876,17 +856,13 @@ int BPF_KPROBE(kprobe__vfs_link,
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
 	size_t len = read_absolute_file_path_from_dentry(old_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->src_filepath_length = len;
 	}
 
 	len = read_absolute_file_path_from_dentry(new_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
@@ -936,16 +912,12 @@ int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry,
 
 	size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH,
 					       oldname);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->src_filepath_length = len;
 	}
 	len = read_absolute_file_path_from_dentry(dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
index c8f59caa4639..a3434b840928 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
@@ -9,7 +9,7 @@ char _license[] SEC("license") = "GPL";
 #define CUSTOM_INHERIT2			1
 #define CUSTOM_LISTENER			2
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 struct sockopt_inherit {
 	__u8 val;
diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c
index 96f29fce050b..db67278e12d4 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c
@@ -5,7 +5,7 @@
 
 char _license[] SEC("license") = "GPL";
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/getsockopt")
 int _getsockopt_child(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
index dbe235ede7f3..83753b00a556 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
@@ -9,7 +9,7 @@
 
 char _license[] SEC("license") = "GPL";
 
-__u32 page_size = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/setsockopt")
 int sockopt_qos_to_cc(struct bpf_sockopt *ctx)
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
index 069db9085e78..3494ca30fa7f 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
@@ -20,17 +20,20 @@ char _license[] SEC("license") = "GPL";
 const unsigned int data_sizes[] = {16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096};
 const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
 
+const unsigned int percpu_data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512};
+const volatile unsigned int percpu_data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
+
 int err = 0;
-int pid = 0;
+u32 pid = 0;
 
 #define DEFINE_ARRAY_WITH_KPTR(_size) \
 	struct bin_data_##_size { \
 		char data[_size - sizeof(void *)]; \
 	}; \
+	/* See Commit 5d8d6634ccc, force btf generation for type bin_data_##_size */	\
+	struct bin_data_##_size *__bin_data_##_size; \
 	struct map_value_##_size { \
 		struct bin_data_##_size __kptr * data; \
-		/* To emit BTF info for bin_data_xx */ \
-		struct bin_data_##_size not_used; \
 	}; \
 	struct { \
 		__uint(type, BPF_MAP_TYPE_ARRAY); \
@@ -40,8 +43,12 @@ int pid = 0;
 	} array_##_size SEC(".maps")
 
 #define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \
+	struct percpu_bin_data_##_size { \
+		char data[_size]; \
+	}; \
+	struct percpu_bin_data_##_size *__percpu_bin_data_##_size; \
 	struct map_value_percpu_##_size { \
-		struct bin_data_##_size __percpu_kptr * data; \
+		struct percpu_bin_data_##_size __percpu_kptr * data; \
 	}; \
 	struct { \
 		__uint(type, BPF_MAP_TYPE_ARRAY); \
@@ -114,7 +121,7 @@ static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int
 			return;
 		}
 		/* per-cpu allocator may not be able to refill in time */
-		new = bpf_percpu_obj_new_impl(data_btf_ids[idx], NULL);
+		new = bpf_percpu_obj_new_impl(percpu_data_btf_ids[idx], NULL);
 		if (!new)
 			continue;
 
@@ -179,7 +186,7 @@ DEFINE_ARRAY_WITH_KPTR(1024);
 DEFINE_ARRAY_WITH_KPTR(2048);
 DEFINE_ARRAY_WITH_KPTR(4096);
 
-/* per-cpu kptr doesn't support bin_data_8 which is a zero-sized array */
+DEFINE_ARRAY_WITH_PERCPU_KPTR(8);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(16);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(32);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(64);
@@ -188,9 +195,6 @@ DEFINE_ARRAY_WITH_PERCPU_KPTR(128);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(192);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(256);
 DEFINE_ARRAY_WITH_PERCPU_KPTR(512);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(1024);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(2048);
-DEFINE_ARRAY_WITH_PERCPU_KPTR(4096);
 
 SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
 int test_batch_alloc_free(void *ctx)
@@ -246,20 +250,18 @@ int test_batch_percpu_alloc_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
-	 * then free 128 16-bytes per-cpu objects in batch to trigger freeing.
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
+	 * then free 128 8-bytes per-cpu objects in batch to trigger freeing.
 	 */
-	CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 0);
-	CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 1);
-	CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 2);
-	CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 3);
-	CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 4);
-	CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 5);
-	CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 6);
-	CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 7);
-	CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 8);
-	CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 9);
-	CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 10);
+	CALL_BATCH_PERCPU_ALLOC_FREE(8, 128, 0);
+	CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1);
+	CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2);
+	CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3);
+	CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 4);
+	CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 5);
+	CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6);
+	CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7);
+	CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8);
 
 	return 0;
 }
@@ -270,20 +272,18 @@ int test_percpu_free_through_map_free(void *ctx)
 	if ((u32)bpf_get_current_pid_tgid() != pid)
 		return 0;
 
-	/* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling,
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
 	 * then free these object through map free.
 	 */
-	CALL_BATCH_PERCPU_ALLOC(16, 128, 0);
-	CALL_BATCH_PERCPU_ALLOC(32, 128, 1);
-	CALL_BATCH_PERCPU_ALLOC(64, 128, 2);
-	CALL_BATCH_PERCPU_ALLOC(96, 128, 3);
-	CALL_BATCH_PERCPU_ALLOC(128, 128, 4);
-	CALL_BATCH_PERCPU_ALLOC(192, 128, 5);
-	CALL_BATCH_PERCPU_ALLOC(256, 128, 6);
-	CALL_BATCH_PERCPU_ALLOC(512, 64, 7);
-	CALL_BATCH_PERCPU_ALLOC(1024, 32, 8);
-	CALL_BATCH_PERCPU_ALLOC(2048, 16, 9);
-	CALL_BATCH_PERCPU_ALLOC(4096, 8, 10);
+	CALL_BATCH_PERCPU_ALLOC(8, 128, 0);
+	CALL_BATCH_PERCPU_ALLOC(16, 128, 1);
+	CALL_BATCH_PERCPU_ALLOC(32, 128, 2);
+	CALL_BATCH_PERCPU_ALLOC(64, 128, 3);
+	CALL_BATCH_PERCPU_ALLOC(96, 128, 4);
+	CALL_BATCH_PERCPU_ALLOC(128, 128, 5);
+	CALL_BATCH_PERCPU_ALLOC(192, 128, 6);
+	CALL_BATCH_PERCPU_ALLOC(256, 128, 7);
+	CALL_BATCH_PERCPU_ALLOC(512, 64, 8);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
index a17dd83eae67..ee4a601dcb06 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
@@ -53,7 +53,7 @@ int test_core_kernel(void *ctx)
 	struct task_struct *task = (void *)bpf_get_current_task();
 	struct core_reloc_kernel_output *out = (void *)&data.out;
 	uint64_t pid_tgid = bpf_get_current_pid_tgid();
-	uint32_t real_tgid = (uint32_t)pid_tgid;
+	int32_t real_tgid = (int32_t)pid_tgid;
 	int pid, tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
index f59f175c7baf..bcb31ff92dcc 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
@@ -43,8 +43,8 @@ int BPF_PROG(test_core_module_probed,
 #if __has_builtin(__builtin_preserve_enum_value)
 	struct core_reloc_module_output *out = (void *)&data.out;
 	__u64 pid_tgid = bpf_get_current_pid_tgid();
-	__u32 real_tgid = (__u32)(pid_tgid >> 32);
-	__u32 real_pid = (__u32)pid_tgid;
+	__s32 real_tgid = (__s32)(pid_tgid >> 32);
+	__s32 real_pid = (__s32)pid_tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
 		return 0;
@@ -77,8 +77,8 @@ int BPF_PROG(test_core_module_direct,
 #if __has_builtin(__builtin_preserve_enum_value)
 	struct core_reloc_module_output *out = (void *)&data.out;
 	__u64 pid_tgid = bpf_get_current_pid_tgid();
-	__u32 real_tgid = (__u32)(pid_tgid >> 32);
-	__u32 real_pid = (__u32)pid_tgid;
+	__s32 real_tgid = (__s32)(pid_tgid >> 32);
+	__s32 real_pid = (__s32)pid_tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_fsverity.c b/tools/testing/selftests/bpf/progs/test_fsverity.c
index 3975495b75c8..9e0f73e8189c 100644
--- a/tools/testing/selftests/bpf/progs/test_fsverity.c
+++ b/tools/testing/selftests/bpf/progs/test_fsverity.c
@@ -38,7 +38,7 @@ int BPF_PROG(test_file_open, struct file *f)
 		return 0;
 	got_fsverity = 1;
 
-	for (i = 0; i < sizeof(digest); i++) {
+	for (i = 0; i < (int)sizeof(digest); i++) {
 		if (digest[i] != expected_digest[i])
 			return 0;
 	}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
index 7faa8eef0598..9a06e5eb1fbe 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
@@ -102,3 +102,52 @@ int perf_event_ctx(void *ctx)
 {
 	return perf_event_ctx_subprog(ctx);
 }
+
+/* this global subprog can be now called from many types of entry progs, each
+ * with different context type
+ */
+__weak int subprog_ctx_tag(void *ctx __arg_ctx)
+{
+	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
+}
+
+struct my_struct { int x; };
+
+__weak int subprog_multi_ctx_tags(void *ctx1 __arg_ctx,
+				  struct my_struct *mem,
+				  void *ctx2 __arg_ctx)
+{
+	if (!mem)
+		return 0;
+
+	return bpf_get_stack(ctx1, stack, sizeof(stack), 0) +
+	       mem->x +
+	       bpf_get_stack(ctx2, stack, sizeof(stack), 0);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
+
+SEC("?perf_event")
+__success __log_level(2)
+int arg_tag_ctx_perf(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+int arg_tag_ctx_kprobe(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
index eacda9fe07eb..4cfa42aa9436 100644
--- a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
+++ b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
@@ -29,7 +29,7 @@ int BPF_PROG(unix_listen, struct socket *sock, int backlog)
 	len = unix_sk->addr->len - sizeof(short);
 	path[0] = '@';
 	for (i = 1; i < len; i++) {
-		if (i >= sizeof(struct sockaddr_un))
+		if (i >= (int)sizeof(struct sockaddr_un))
 			break;
 
 		path[i] = unix_sk->addr->name->sun_path[i];
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
index 5baaafed0d2d..3abf068b8446 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
@@ -38,7 +38,7 @@ int xdp_redirect(struct xdp_md *xdp)
 	if (payload + 1 > data_end)
 		return XDP_ABORTED;
 
-	if (xdp->ingress_ifindex != ifindex_in)
+	if (xdp->ingress_ifindex != (__u32)ifindex_in)
 		return XDP_ABORTED;
 
 	if (metadata + 1 > data)
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index d1edbcff9a18..05a329ee45ee 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -33,6 +33,25 @@ l3_%=:							\
 	: __clobber_all);
 }
 
+SEC("socket")
+__description("gotol, large_imm")
+__success __failure_unpriv __retval(40000)
+__naked void gotol_large_imm(void)
+{
+	asm volatile ("					\
+	gotol 1f;					\
+0:							\
+	r0 = 0;						\
+	.rept 40000;					\
+	r0 += 1;					\
+	.endr;						\
+	exit;						\
+1:	gotol 0b;					\
+"	:
+	:
+	: __clobber_all);
+}
+
 #else
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
index 692216c0ad3d..886498b5e6f3 100644
--- a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
@@ -89,9 +89,14 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+/* Call a function taking a pointer and a size which doesn't allow the size to
+ * be zero (i.e. bpf_trace_printk() declares the second argument to be
+ * ARG_CONST_SIZE, not ARG_CONST_SIZE_OR_ZERO). We attempt to pass zero for the
+ * size and expect to fail.
+ */
 SEC("tracepoint")
 __description("helper access to map: empty range")
-__failure __msg("invalid access to map value, value_size=48 off=0 size=0")
+__failure __msg("R2 invalid zero-sized read: u64=[0,0]")
 __naked void access_to_map_empty_range(void)
 {
 	asm volatile ("					\
@@ -113,6 +118,38 @@ l0_%=:	exit;						\
 	: __clobber_all);
 }
 
+/* Like the test above, but this time the size register is not known to be zero;
+ * its lower-bound is zero though, which is still unacceptable.
+ */
+SEC("tracepoint")
+__description("helper access to map: possibly-empty ange")
+__failure __msg("R2 invalid zero-sized read: u64=[0,4]")
+__naked void access_to_map_possibly_empty_range(void)
+{
+	asm volatile ("                                         \
+	r2 = r10;                                               \
+	r2 += -8;                                               \
+	r1 = 0;                                                 \
+	*(u64*)(r2 + 0) = r1;                                   \
+	r1 = %[map_hash_48b] ll;                                \
+	call %[bpf_map_lookup_elem];                            \
+	if r0 == 0 goto l0_%=;                                  \
+	r1 = r0;                                                \
+	/* Read an unknown value */                             \
+	r7 = *(u64*)(r0 + 0);                                   \
+	/* Make it small and positive, to avoid other errors */ \
+	r7 &= 4;                                                \
+	r2 = 0;                                                 \
+	r2 += r7;                                               \
+	call %[bpf_trace_printk];                               \
+l0_%=:	exit;                                               \
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_trace_printk),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
 SEC("tracepoint")
 __description("helper access to map: out-of-bound range")
 __failure __msg("invalid access to map value, value_size=48 off=0 size=56")
@@ -221,7 +258,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via const imm): empty range")
-__failure __msg("invalid access to map value, value_size=48 off=4 size=0")
+__failure __msg("R2 invalid zero-sized read")
 __naked void via_const_imm_empty_range(void)
 {
 	asm volatile ("					\
@@ -386,7 +423,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via const reg): empty range")
-__failure __msg("R1 min value is outside of the allowed memory range")
+__failure __msg("R2 invalid zero-sized read")
 __naked void via_const_reg_empty_range(void)
 {
 	asm volatile ("					\
@@ -556,7 +593,7 @@ l0_%=:	exit;						\
 
 SEC("tracepoint")
 __description("helper access to adjusted map (via variable): empty range")
-__failure __msg("R1 min value is outside of the allowed memory range")
+__failure __msg("R2 invalid zero-sized read")
 __naked void map_via_variable_empty_range(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
index f67390224a9c..7cc83acac727 100644
--- a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
+++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
@@ -64,7 +64,7 @@ __naked void load_bytes_negative_len_2(void)
 
 SEC("tc")
 __description("raw_stack: skb_load_bytes, zero len")
-__failure __msg("invalid zero-sized read")
+__failure __msg("R4 invalid zero-sized read: u64=[0,0]")
 __naked void skb_load_bytes_zero_len(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 74ceb7877ae2..f01391021218 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -12,7 +12,7 @@
 #define str_has_pfx(str, pfx) \
 	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
 
-#define TEST_LOADER_LOG_BUF_SZ 1048576
+#define TEST_LOADER_LOG_BUF_SZ 2097152
 
 #define TEST_TAG_EXPECT_FAILURE "comment:test_expect_failure"
 #define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success"
diff --git a/tools/testing/selftests/hid/config b/tools/testing/selftests/hid/config
index 4f425178b56f..1758b055f295 100644
--- a/tools/testing/selftests/hid/config
+++ b/tools/testing/selftests/hid/config
@@ -1,5 +1,4 @@
 CONFIG_BPF_EVENTS=y
-CONFIG_BPFILTER=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT=y
 CONFIG_BPF_KPROBE_OVERRIDE=y