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>

73 files changed, 1526 insertions, 951 deletions

diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 9c333d133c30..60e331af9839 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -276,7 +276,6 @@ CONFIG_BRIDGE_EBT_T_NAT=m
 CONFIG_BRIDGE_EBT_ARP=m
 CONFIG_BRIDGE_EBT_IP=m
 CONFIG_BRIDGE_EBT_IP6=m
-CONFIG_BPFILTER=y
 CONFIG_IP_SCTP=m
 CONFIG_RDS=y
 CONFIG_L2TP=m
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 7f0a7b97ef4c..b418333bb086 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -779,7 +779,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
 				 int i, bool extra_pass, u32 stack_depth)
 {
 	struct bpf_insn *insn = &fp->insnsi[i];
-	s16 branch_oc_off = insn->off;
+	s32 branch_oc_off = insn->off;
 	u32 dst_reg = insn->dst_reg;
 	u32 src_reg = insn->src_reg;
 	int last, insn_count = 1;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index bdacbb84456d..fe30b9ebb8de 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -307,6 +307,25 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
 	*pprog = prog;
 }
 
+static void emit_nops(u8 **pprog, int len)
+{
+	u8 *prog = *pprog;
+	int i, noplen;
+
+	while (len > 0) {
+		noplen = len;
+
+		if (noplen > ASM_NOP_MAX)
+			noplen = ASM_NOP_MAX;
+
+		for (i = 0; i < noplen; i++)
+			EMIT1(x86_nops[noplen][i]);
+		len -= noplen;
+	}
+
+	*pprog = prog;
+}
+
 /*
  * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
  * in arch/x86/kernel/alternative.c
@@ -385,8 +404,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
-	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-	prog += X86_PATCH_SIZE;
+	emit_nops(&prog, X86_PATCH_SIZE);
 	if (!ebpf_from_cbpf) {
 		if (tail_call_reachable && !is_subprog)
 			/* When it's the entry of the whole tailcall context,
@@ -692,8 +710,7 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
 
-	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-	prog += X86_PATCH_SIZE;
+	emit_nops(&prog, X86_PATCH_SIZE);
 
 	/* out: */
 	ctx->tail_call_direct_label = prog - start;
@@ -1055,25 +1072,6 @@ static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt,
 	}
 }
 
-static void emit_nops(u8 **pprog, int len)
-{
-	u8 *prog = *pprog;
-	int i, noplen;
-
-	while (len > 0) {
-		noplen = len;
-
-		if (noplen > ASM_NOP_MAX)
-			noplen = ASM_NOP_MAX;
-
-		for (i = 0; i < noplen; i++)
-			EMIT1(x86_nops[noplen][i]);
-		len -= noplen;
-	}
-
-	*pprog = prog;
-}
-
 /* emit the 3-byte VEX prefix
  *
  * r: same as rex.r, extra bit for ModRM reg field
@@ -2700,8 +2698,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 		im->ip_after_call = image + (prog - (u8 *)rw_image);
-		memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
-		prog += X86_PATCH_SIZE;
+		emit_nops(&prog, X86_PATCH_SIZE);
 	}
 
 	if (fmod_ret->nr_links) {
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7671530d6e4e..e30100597d0a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1449,6 +1449,7 @@ struct bpf_prog_aux {
 	bool dev_bound; /* Program is bound to the netdev. */
 	bool offload_requested; /* Program is bound and offloaded to the netdev. */
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	bool attach_tracing_prog; /* true if tracing another tracing program */
 	bool func_proto_unreliable;
 	bool sleepable;
 	bool tail_call_reachable;
diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index bb1223b21308..aaf004d94322 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -11,6 +11,7 @@ struct bpf_mem_caches;
 struct bpf_mem_alloc {
 	struct bpf_mem_caches __percpu *caches;
 	struct bpf_mem_cache __percpu *cache;
+	struct obj_cgroup *objcg;
 	bool percpu;
 	struct work_struct work;
 };
@@ -21,8 +22,15 @@ struct bpf_mem_alloc {
  * 'size = 0' is for bpf_mem_alloc which manages many fixed-size objects.
  * Alloc and free are done with bpf_mem_{alloc,free}() and the size of
  * the returned object is given by the size argument of bpf_mem_alloc().
+ * If percpu equals true, error will be returned in order to avoid
+ * large memory consumption and the below bpf_mem_alloc_percpu_unit_init()
+ * should be used to do on-demand per-cpu allocation for each size.
  */
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu);
+/* Initialize a non-fix-size percpu memory allocator */
+int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg);
+/* The percpu allocation with a specific unit size. */
+int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
 
 /* kmalloc/kfree equivalent: */
diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
deleted file mode 100644
index 736ded4905e0..000000000000
--- a/include/linux/bpfilter.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_BPFILTER_H
-#define _LINUX_BPFILTER_H
-
-#include <uapi/linux/bpfilter.h>
-#include <linux/usermode_driver.h>
-#include <linux/sockptr.h>
-
-struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
-			    unsigned int optlen);
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int __user *optlen);
-
-struct bpfilter_umh_ops {
-	struct umd_info info;
-	/* since ip_getsockopt() can run in parallel, serialize access to umh */
-	struct mutex lock;
-	int (*sockopt)(struct sock *sk, int optname, sockptr_t optval,
-		       unsigned int optlen, bool is_set);
-	int (*start)(void);
-};
-extern struct bpfilter_umh_ops bpfilter_ops;
-#endif
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index c953b8c0d2f4..888a4b217829 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -100,6 +100,11 @@ struct sk_psock {
 	void (*saved_close)(struct sock *sk, long timeout);
 	void (*saved_write_space)(struct sock *sk);
 	void (*saved_data_ready)(struct sock *sk);
+	/* psock_update_sk_prot may be called with restore=false many times
+	 * so the handler must be safe for this case. It will be called
+	 * exactly once with restore=true when the psock is being destroyed
+	 * and psock refcnt is zero, but before an RCU grace period.
+	 */
 	int  (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock,
 				     bool restore);
 	struct proto			*sk_proto;
diff --git a/include/uapi/linux/bpfilter.h b/include/uapi/linux/bpfilter.h
deleted file mode 100644
index cbc1f5813f50..000000000000
--- a/include/uapi/linux/bpfilter.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_BPFILTER_H
-#define _UAPI_LINUX_BPFILTER_H
-
-#include <linux/if.h>
-
-enum {
-	BPFILTER_IPT_SO_SET_REPLACE = 64,
-	BPFILTER_IPT_SO_SET_ADD_COUNTERS = 65,
-	BPFILTER_IPT_SET_MAX,
-};
-
-enum {
-	BPFILTER_IPT_SO_GET_INFO = 64,
-	BPFILTER_IPT_SO_GET_ENTRIES = 65,
-	BPFILTER_IPT_SO_GET_REVISION_MATCH = 66,
-	BPFILTER_IPT_SO_GET_REVISION_TARGET = 67,
-	BPFILTER_IPT_GET_MAX,
-};
-
-#endif /* _UAPI_LINUX_BPFILTER_H */
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index aa0fbf000a12..550f02e2cb13 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -121,6 +121,8 @@ struct bpf_mem_caches {
 	struct bpf_mem_cache cache[NUM_CACHES];
 };
 
+static const u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+
 static struct llist_node notrace *__llist_del_first(struct llist_head *head)
 {
 	struct llist_node *entry, *next;
@@ -462,11 +464,17 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
  * consume ~ 11 Kbyte per cpu.
  * Typical case will be between 11K and 116K closer to 11K.
  * bpf progs can and should share bpf_mem_cache when possible.
+ *
+ * Percpu allocation is typically rare. To avoid potential unnecessary large
+ * memory consumption, set low_mark = 1 and high_mark = 3, resulting in c->batch = 1.
  */
 static void init_refill_work(struct bpf_mem_cache *c)
 {
 	init_irq_work(&c->refill_work, bpf_mem_refill);
-	if (c->unit_size <= 256) {
+	if (c->percpu_size) {
+		c->low_watermark = 1;
+		c->high_watermark = 3;
+	} else if (c->unit_size <= 256) {
 		c->low_watermark = 32;
 		c->high_watermark = 96;
 	} else {
@@ -483,11 +491,16 @@ static void init_refill_work(struct bpf_mem_cache *c)
 
 static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 {
-	/* To avoid consuming memory assume that 1st run of bpf
-	 * prog won't be doing more than 4 map_update_elem from
-	 * irq disabled region
+	int cnt = 1;
+
+	/* To avoid consuming memory, for non-percpu allocation, assume that
+	 * 1st run of bpf prog won't be doing more than 4 map_update_elem from
+	 * irq disabled region if unit size is less than or equal to 256.
+	 * For all other cases, let us just do one allocation.
 	 */
-	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
+	if (!c->percpu_size && c->unit_size <= 256)
+		cnt = 4;
+	alloc_bulk(c, cnt, cpu_to_node(cpu), false);
 }
 
 /* When size != 0 bpf_mem_cache for each cpu.
@@ -499,12 +512,14 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
  */
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 {
-	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
 	struct bpf_mem_caches *cc, __percpu *pcc;
 	struct bpf_mem_cache *c, __percpu *pc;
 	struct obj_cgroup *objcg = NULL;
 	int cpu, i, unit_size, percpu_size = 0;
 
+	if (percpu && size == 0)
+		return -EINVAL;
+
 	/* room for llist_node and per-cpu pointer */
 	if (percpu)
 		percpu_size = LLIST_NODE_SZ + sizeof(void *);
@@ -523,6 +538,8 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 		if (memcg_bpf_enabled())
 			objcg = get_obj_cgroup_from_current();
 #endif
+		ma->objcg = objcg;
+
 		for_each_possible_cpu(cpu) {
 			c = per_cpu_ptr(pc, cpu);
 			c->unit_size = unit_size;
@@ -542,6 +559,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 #ifdef CONFIG_MEMCG_KMEM
 	objcg = get_obj_cgroup_from_current();
 #endif
+	ma->objcg = objcg;
 	for_each_possible_cpu(cpu) {
 		cc = per_cpu_ptr(pcc, cpu);
 		for (i = 0; i < NUM_CACHES; i++) {
@@ -560,6 +578,56 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 	return 0;
 }
 
+int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg)
+{
+	struct bpf_mem_caches __percpu *pcc;
+
+	pcc = __alloc_percpu_gfp(sizeof(struct bpf_mem_caches), 8, GFP_KERNEL);
+	if (!pcc)
+		return -ENOMEM;
+
+	ma->caches = pcc;
+	ma->objcg = objcg;
+	ma->percpu = true;
+	return 0;
+}
+
+int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size)
+{
+	struct bpf_mem_caches *cc, __percpu *pcc;
+	int cpu, i, unit_size, percpu_size;
+	struct obj_cgroup *objcg;
+	struct bpf_mem_cache *c;
+
+	i = bpf_mem_cache_idx(size);
+	if (i < 0)
+		return -EINVAL;
+
+	/* room for llist_node and per-cpu pointer */
+	percpu_size = LLIST_NODE_SZ + sizeof(void *);
+
+	unit_size = sizes[i];
+	objcg = ma->objcg;
+	pcc = ma->caches;
+
+	for_each_possible_cpu(cpu) {
+		cc = per_cpu_ptr(pcc, cpu);
+		c = &cc->cache[i];
+		if (c->unit_size)
+			break;
+
+		c->unit_size = unit_size;
+		c->objcg = objcg;
+		c->percpu_size = percpu_size;
+		c->tgt = c;
+
+		init_refill_work(c);
+		prefill_mem_cache(c, cpu);
+	}
+
+	return 0;
+}
+
 static void drain_mem_cache(struct bpf_mem_cache *c)
 {
 	bool percpu = !!c->percpu_size;
@@ -691,9 +759,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 			rcu_in_progress += atomic_read(&c->call_rcu_ttrace_in_progress);
 			rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 		}
-		/* objcg is the same across cpus */
-		if (c->objcg)
-			obj_cgroup_put(c->objcg);
+		if (ma->objcg)
+			obj_cgroup_put(ma->objcg);
 		destroy_mem_alloc(ma, rcu_in_progress);
 	}
 	if (ma->caches) {
@@ -709,8 +776,8 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
 				rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
 			}
 		}
-		if (c->objcg)
-			obj_cgroup_put(c->objcg);
+		if (ma->objcg)
+			obj_cgroup_put(ma->objcg);
 		destroy_mem_alloc(ma, rcu_in_progress);
 	}
 }
@@ -833,7 +900,9 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
 	if (!size)
 		return NULL;
 
-	idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ);
+	if (!ma->percpu)
+		size += LLIST_NODE_SZ;
+	idx = bpf_mem_cache_idx(size);
 	if (idx < 0)
 		return NULL;
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1bf9805ee185..a1f18681721c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2738,6 +2738,22 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size)
 			goto free_prog_sec;
 	}
 
+	/*
+	 * Bookkeeping for managing the program attachment chain.
+	 *
+	 * It might be tempting to set attach_tracing_prog flag at the attachment
+	 * time, but this will not prevent from loading bunch of tracing prog
+	 * first, then attach them one to another.
+	 *
+	 * The flag attach_tracing_prog is set for the whole program lifecycle, and
+	 * doesn't have to be cleared in bpf_tracing_link_release, since tracing
+	 * programs cannot change attachment target.
+	 */
+	if (type == BPF_PROG_TYPE_TRACING && dst_prog &&
+	    dst_prog->type == BPF_PROG_TYPE_TRACING) {
+		prog->aux->attach_tracing_prog = true;
+	}
+
 	/* find program type: socket_filter vs tracing_filter */
 	err = find_prog_type(type, prog);
 	if (err < 0)
@@ -3171,7 +3187,12 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	}
 
 	if (tgt_prog_fd) {
-		/* For now we only allow new targets for BPF_PROG_TYPE_EXT */
+		/*
+		 * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this
+		 * part would be changed to implement the same for
+		 * BPF_PROG_TYPE_TRACING, do not forget to update the way how
+		 * attach_tracing_prog flag is set.
+		 */
 		if (prog->type != BPF_PROG_TYPE_EXT) {
 			err = -EINVAL;
 			goto out_put_prog;
@@ -3216,6 +3237,10 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	 *
 	 * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program
 	 *   was detached and is going for re-attachment.
+	 *
+	 * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf
+	 *   are NULL, then program was already attached and user did not provide
+	 *   tgt_prog_fd so we have no way to find out or create trampoline
 	 */
 	if (!prog->aux->dst_trampoline && !tgt_prog) {
 		/*
@@ -3229,6 +3254,11 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 			err = -EINVAL;
 			goto out_unlock;
 		}
+		/* We can allow re-attach only if we have valid attach_btf. */
+		if (!prog->aux->attach_btf) {
+			err = -EINVAL;
+			goto out_unlock;
+		}
 		btf_id = prog->aux->attach_btf_id;
 		key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id);
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a376eb609c41..adbf330d364b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -195,6 +195,8 @@ struct bpf_verifier_stack_elem {
 					  POISON_POINTER_DELTA))
 #define BPF_MAP_PTR(X)		((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
 
+#define BPF_GLOBAL_PERCPU_MA_MAX_SIZE  512
+
 static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx);
 static int release_reference(struct bpf_verifier_env *env, int ref_obj_id);
 static void invalidate_non_owning_refs(struct bpf_verifier_env *env);
@@ -7279,12 +7281,10 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	if (reg->umin_value == 0) {
-		err = check_helper_mem_access(env, regno - 1, 0,
-					      zero_size_allowed,
-					      meta);
-		if (err)
-			return err;
+	if (reg->umin_value == 0 && !zero_size_allowed) {
+		verbose(env, "R%d invalid zero-sized read: u64=[%lld,%lld]\n",
+			regno, reg->umin_value, reg->umax_value);
+		return -EACCES;
 	}
 
 	if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
@@ -12141,20 +12141,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 				if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl] && !bpf_global_ma_set)
 					return -ENOMEM;
 
-				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
-					if (!bpf_global_percpu_ma_set) {
-						mutex_lock(&bpf_percpu_ma_lock);
-						if (!bpf_global_percpu_ma_set) {
-							err = bpf_mem_alloc_init(&bpf_global_percpu_ma, 0, true);
-							if (!err)
-								bpf_global_percpu_ma_set = true;
-						}
-						mutex_unlock(&bpf_percpu_ma_lock);
-						if (err)
-							return err;
-					}
-				}
-
 				if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) {
 					verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
 					return -EINVAL;
@@ -12175,6 +12161,35 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 					return -EINVAL;
 				}
 
+				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
+					if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) {
+						verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n",
+							ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE);
+						return -EINVAL;
+					}
+
+					if (!bpf_global_percpu_ma_set) {
+						mutex_lock(&bpf_percpu_ma_lock);
+						if (!bpf_global_percpu_ma_set) {
+							/* Charge memory allocated with bpf_global_percpu_ma to
+							 * root memcg. The obj_cgroup for root memcg is NULL.
+							 */
+							err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL);
+							if (!err)
+								bpf_global_percpu_ma_set = true;
+						}
+						mutex_unlock(&bpf_percpu_ma_lock);
+						if (err)
+							return err;
+					}
+
+					mutex_lock(&bpf_percpu_ma_lock);
+					err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size);
+					mutex_unlock(&bpf_percpu_ma_lock);
+					if (err)
+						return err;
+				}
+
 				struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
 				if (meta.func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl]) {
 					if (!__btf_type_is_scalar_struct(env, ret_btf, ret_t, 0)) {
@@ -20302,6 +20317,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			    struct bpf_attach_target_info *tgt_info)
 {
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
+	bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING;
 	const char prefix[] = "btf_trace_";
 	int ret = 0, subprog = -1, i;
 	const struct btf_type *t;
@@ -20372,10 +20388,21 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			bpf_log(log, "Can attach to only JITed progs\n");
 			return -EINVAL;
 		}
-		if (tgt_prog->type == prog->type) {
-			/* Cannot fentry/fexit another fentry/fexit program.
-			 * Cannot attach program extension to another extension.
-			 * It's ok to attach fentry/fexit to extension program.
+		if (prog_tracing) {
+			if (aux->attach_tracing_prog) {
+				/*
+				 * Target program is an fentry/fexit which is already attached
+				 * to another tracing program. More levels of nesting
+				 * attachment are not allowed.
+				 */
+				bpf_log(log, "Cannot nest tracing program attach more than once\n");
+				return -EINVAL;
+			}
+		} else if (tgt_prog->type == prog->type) {
+			/*
+			 * To avoid potential call chain cycles, prevent attaching of a
+			 * program extension to another extension. It's ok to attach
+			 * fentry/fexit to extension program.
 			 */
 			bpf_log(log, "Cannot recursively attach\n");
 			return -EINVAL;
@@ -20388,16 +20415,15 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			 * except fentry/fexit. The reason is the following.
 			 * The fentry/fexit programs are used for performance
 			 * analysis, stats and can be attached to any program
-			 * type except themselves. When extension program is
-			 * replacing XDP function it is necessary to allow
-			 * performance analysis of all functions. Both original
-			 * XDP program and its program extension. Hence
-			 * attaching fentry/fexit to BPF_PROG_TYPE_EXT is
-			 * allowed. If extending of fentry/fexit was allowed it
-			 * would be possible to create long call chain
-			 * fentry->extension->fentry->extension beyond
-			 * reasonable stack size. Hence extending fentry is not
-			 * allowed.
+			 * type. When extension program is replacing XDP function
+			 * it is necessary to allow performance analysis of all
+			 * functions. Both original XDP program and its program
+			 * extension. Hence attaching fentry/fexit to
+			 * BPF_PROG_TYPE_EXT is allowed. If extending of
+			 * fentry/fexit was allowed it would be possible to create
+			 * long call chain fentry->extension->fentry->extension
+			 * beyond reasonable stack size. Hence extending fentry
+			 * is not allowed.
 			 */
 			bpf_log(log, "Cannot extend fentry/fexit\n");
 			return -EINVAL;
diff --git a/net/Kconfig b/net/Kconfig
index 3ec6bc98fa05..4adc47d0c9c2 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -233,8 +233,6 @@ source "net/bridge/netfilter/Kconfig"
 
 endif
 
-source "net/bpfilter/Kconfig"
-
 source "net/dccp/Kconfig"
 source "net/sctp/Kconfig"
 source "net/rds/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index 4c4dc535453d..b06b5539e7a6 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_TLS)		+= tls/
 obj-$(CONFIG_XFRM)		+= xfrm/
 obj-$(CONFIG_UNIX_SCM)		+= unix/
 obj-y				+= ipv6/
-obj-$(CONFIG_BPFILTER)		+= bpfilter/
 obj-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
diff --git a/net/bpfilter/.gitignore b/net/bpfilter/.gitignore
deleted file mode 100644
index f34e85ee8204..000000000000
--- a/net/bpfilter/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-bpfilter_umh
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
deleted file mode 100644
index 3d4a21462458..000000000000
--- a/net/bpfilter/Kconfig
+++ /dev/null
@@ -1,23 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-menuconfig BPFILTER
-	bool "BPF based packet filtering framework (BPFILTER)"
-	depends on BPF && INET
-	select USERMODE_DRIVER
-	help
-	  This builds experimental bpfilter framework that is aiming to
-	  provide netfilter compatible functionality via BPF
-
-if BPFILTER
-config BPFILTER_UMH
-	tristate "bpfilter kernel module with user mode helper"
-	depends on CC_CAN_LINK
-	depends on m || CC_CAN_LINK_STATIC
-	default m
-	help
-	  This builds bpfilter kernel module with embedded user mode helper
-
-	  Note: To compile this as built-in, your toolchain must support
-	  building static binaries, since rootfs isn't mounted at the time
-	  when __init functions are called and do_execv won't be able to find
-	  the elf interpreter.
-endif
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
deleted file mode 100644
index cdac82b8c53a..000000000000
--- a/net/bpfilter/Makefile
+++ /dev/null
@@ -1,20 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-#
-# Makefile for the Linux BPFILTER layer.
-#
-
-userprogs := bpfilter_umh
-bpfilter_umh-objs := main.o
-userccflags += -I $(srctree)/tools/include/ -I $(srctree)/tools/include/uapi
-
-ifeq ($(CONFIG_BPFILTER_UMH), y)
-# builtin bpfilter_umh should be linked with -static
-# since rootfs isn't mounted at the time of __init
-# function is called and do_execv won't find elf interpreter
-userldflags += -static
-endif
-
-$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
-
-obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
deleted file mode 100644
index 97e129e3f31c..000000000000
--- a/net/bpfilter/bpfilter_kern.c
+++ /dev/null
@@ -1,136 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/umh.h>
-#include <linux/bpfilter.h>
-#include <linux/sched.h>
-#include <linux/sched/signal.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include "msgfmt.h"
-
-extern char bpfilter_umh_start;
-extern char bpfilter_umh_end;
-
-static void shutdown_umh(void)
-{
-	struct umd_info *info = &bpfilter_ops.info;
-	struct pid *tgid = info->tgid;
-
-	if (tgid) {
-		kill_pid(tgid, SIGKILL, 1);
-		wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
-		umd_cleanup_helper(info);
-	}
-}
-
-static void __stop_umh(void)
-{
-	if (IS_ENABLED(CONFIG_INET))
-		shutdown_umh();
-}
-
-static int bpfilter_send_req(struct mbox_request *req)
-{
-	struct mbox_reply reply;
-	loff_t pos = 0;
-	ssize_t n;
-
-	if (!bpfilter_ops.info.tgid)
-		return -EFAULT;
-	pos = 0;
-	n = kernel_write(bpfilter_ops.info.pipe_to_umh, req, sizeof(*req),
-			   &pos);
-	if (n != sizeof(*req)) {
-		pr_err("write fail %zd\n", n);
-		goto stop;
-	}
-	pos = 0;
-	n = kernel_read(bpfilter_ops.info.pipe_from_umh, &reply, sizeof(reply),
-			&pos);
-	if (n != sizeof(reply)) {
-		pr_err("read fail %zd\n", n);
-		goto stop;
-	}
-	return reply.status;
-stop:
-	__stop_umh();
-	return -EFAULT;
-}
-
-static int bpfilter_process_sockopt(struct sock *sk, int optname,
-				    sockptr_t optval, unsigned int optlen,
-				    bool is_set)
-{
-	struct mbox_request req = {
-		.is_set		= is_set,
-		.pid		= current->pid,
-		.cmd		= optname,
-		.addr		= (uintptr_t)optval.user,
-		.len		= optlen,
-	};
-	if (sockptr_is_kernel(optval)) {
-		pr_err("kernel access not supported\n");
-		return -EFAULT;
-	}
-	return bpfilter_send_req(&req);
-}
-
-static int start_umh(void)
-{
-	struct mbox_request req = { .pid = current->pid };
-	int err;
-
-	/* fork usermode process */
-	err = fork_usermode_driver(&bpfilter_ops.info);
-	if (err)
-		return err;
-	pr_info("Loaded bpfilter_umh pid %d\n", pid_nr(bpfilter_ops.info.tgid));
-
-	/* health check that usermode process started correctly */
-	if (bpfilter_send_req(&req) != 0) {
-		shutdown_umh();
-		return -EFAULT;
-	}
-
-	return 0;
-}
-
-static int __init load_umh(void)
-{
-	int err;
-
-	err = umd_load_blob(&bpfilter_ops.info,
-			    &bpfilter_umh_start,
-			    &bpfilter_umh_end - &bpfilter_umh_start);
-	if (err)
-		return err;
-
-	mutex_lock(&bpfilter_ops.lock);
-	err = start_umh();
-	if (!err && IS_ENABLED(CONFIG_INET)) {
-		bpfilter_ops.sockopt = &bpfilter_process_sockopt;
-		bpfilter_ops.start = &start_umh;
-	}
-	mutex_unlock(&bpfilter_ops.lock);
-	if (err)
-		umd_unload_blob(&bpfilter_ops.info);
-	return err;
-}
-
-static void __exit fini_umh(void)
-{
-	mutex_lock(&bpfilter_ops.lock);
-	if (IS_ENABLED(CONFIG_INET)) {
-		shutdown_umh();
-		bpfilter_ops.start = NULL;
-		bpfilter_ops.sockopt = NULL;
-	}
-	mutex_unlock(&bpfilter_ops.lock);
-
-	umd_unload_blob(&bpfilter_ops.info);
-}
-module_init(load_umh);
-module_exit(fini_umh);
-MODULE_LICENSE("GPL");
diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S
deleted file mode 100644
index 40311d10d2f2..000000000000
--- a/net/bpfilter/bpfilter_umh_blob.S
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-	.section .init.rodata, "a"
-	.global bpfilter_umh_start
-bpfilter_umh_start:
-	.incbin "net/bpfilter/bpfilter_umh"
-	.global bpfilter_umh_end
-bpfilter_umh_end:
diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c
deleted file mode 100644
index 291a92546246..000000000000
--- a/net/bpfilter/main.c
+++ /dev/null
@@ -1,64 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#define _GNU_SOURCE
-#include <sys/uio.h>
-#include <errno.h>
-#include <stdio.h>
-#include <sys/socket.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include "../../include/uapi/linux/bpf.h"
-#include <asm/unistd.h>
-#include "msgfmt.h"
-
-FILE *debug_f;
-
-static int handle_get_cmd(struct mbox_request *cmd)
-{
-	switch (cmd->cmd) {
-	case 0:
-		return 0;
-	default:
-		break;
-	}
-	return -ENOPROTOOPT;
-}
-
-static int handle_set_cmd(struct mbox_request *cmd)
-{
-	return -ENOPROTOOPT;
-}
-
-static void loop(void)
-{
-	while (1) {
-		struct mbox_request req;
-		struct mbox_reply reply;
-		int n;
-
-		n = read(0, &req, sizeof(req));
-		if (n != sizeof(req)) {
-			fprintf(debug_f, "invalid request %d\n", n);
-			return;
-		}
-
-		reply.status = req.is_set ?
-			handle_set_cmd(&req) :
-			handle_get_cmd(&req);
-
-		n = write(1, &reply, sizeof(reply));
-		if (n != sizeof(reply)) {
-			fprintf(debug_f, "reply failed %d\n", n);
-			return;
-		}
-	}
-}
-
-int main(void)
-{
-	debug_f = fopen("/dev/kmsg", "w");
-	setvbuf(debug_f, 0, _IOLBF, 0);
-	fprintf(debug_f, "<5>Started bpfilter\n");
-	loop();
-	fclose(debug_f);
-	return 0;
-}
diff --git a/net/bpfilter/msgfmt.h b/net/bpfilter/msgfmt.h
deleted file mode 100644
index 98d121c62945..000000000000
--- a/net/bpfilter/msgfmt.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NET_BPFILTER_MSGFMT_H
-#define _NET_BPFILTER_MSGFMT_H
-
-struct mbox_request {
-	__u64 addr;
-	__u32 len;
-	__u32 is_set;
-	__u32 cmd;
-	__u32 pid;
-};
-
-struct mbox_reply {
-	__u32 status;
-};
-
-#endif
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index e144a02a6a61..ec36d2ec059e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -16,8 +16,6 @@ obj-y     := route.o inetpeer.o protocol.o \
 	     inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
 	     metrics.o netlink.o nexthop.o udp_tunnel_stub.o
 
-obj-$(CONFIG_BPFILTER) += bpfilter/
-
 obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
 obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
 obj-$(CONFIG_PROC_FS) += proc.o
diff --git a/net/ipv4/bpfilter/Makefile b/net/ipv4/bpfilter/Makefile
deleted file mode 100644
index 00af5305e05a..000000000000
--- a/net/ipv4/bpfilter/Makefile
+++ /dev/null
@@ -1,2 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_BPFILTER) += sockopt.o
diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c
deleted file mode 100644
index 193bcc2acccc..000000000000
--- a/net/ipv4/bpfilter/sockopt.c
+++ /dev/null
@@ -1,71 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/uaccess.h>
-#include <linux/bpfilter.h>
-#include <uapi/linux/bpf.h>
-#include <linux/wait.h>
-#include <linux/kmod.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-
-struct bpfilter_umh_ops bpfilter_ops;
-EXPORT_SYMBOL_GPL(bpfilter_ops);
-
-static int bpfilter_mbox_request(struct sock *sk, int optname, sockptr_t optval,
-				 unsigned int optlen, bool is_set)
-{
-	int err;
-	mutex_lock(&bpfilter_ops.lock);
-	if (!bpfilter_ops.sockopt) {
-		mutex_unlock(&bpfilter_ops.lock);
-		request_module("bpfilter");
-		mutex_lock(&bpfilter_ops.lock);
-
-		if (!bpfilter_ops.sockopt) {
-			err = -ENOPROTOOPT;
-			goto out;
-		}
-	}
-	if (bpfilter_ops.info.tgid &&
-	    thread_group_exited(bpfilter_ops.info.tgid))
-		umd_cleanup_helper(&bpfilter_ops.info);
-
-	if (!bpfilter_ops.info.tgid) {
-		err = bpfilter_ops.start();
-		if (err)
-			goto out;
-	}
-	err = bpfilter_ops.sockopt(sk, optname, optval, optlen, is_set);
-out:
-	mutex_unlock(&bpfilter_ops.lock);
-	return err;
-}
-
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
-			    unsigned int optlen)
-{
-	return bpfilter_mbox_request(sk, optname, optval, optlen, true);
-}
-
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int __user *optlen)
-{
-	int len;
-
-	if (get_user(len, optlen))
-		return -EFAULT;
-
-	return bpfilter_mbox_request(sk, optname, USER_SOCKPTR(optval), len,
-				     false);
-}
-
-static int __init bpfilter_sockopt_init(void)
-{
-	mutex_init(&bpfilter_ops.lock);
-	bpfilter_ops.info.tgid = NULL;
-	bpfilter_ops.info.driver_name = "bpfilter_umh";
-
-	return 0;
-}
-device_initcall(bpfilter_sockopt_init);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 66247e8b429e..7aa9dc0e6760 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -47,8 +47,6 @@
 #include <linux/errqueue.h>
 #include <linux/uaccess.h>
 
-#include <linux/bpfilter.h>
-
 /*
  *	SOL_IP control messages.
  */
@@ -1411,11 +1409,6 @@ int ip_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		return -ENOPROTOOPT;
 
 	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
-#if IS_ENABLED(CONFIG_BPFILTER_UMH)
-	if (optname >= BPFILTER_IPT_SO_SET_REPLACE &&
-	    optname < BPFILTER_IPT_SET_MAX)
-		err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen);
-#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
@@ -1763,11 +1756,6 @@ int ip_getsockopt(struct sock *sk, int level,
 	err = do_ip_getsockopt(sk, level, optname,
 			       USER_SOCKPTR(optval), USER_SOCKPTR(optlen));
 
-#if IS_ENABLED(CONFIG_BPFILTER_UMH)
-	if (optname >= BPFILTER_IPT_SO_GET_INFO &&
-	    optname < BPFILTER_IPT_GET_MAX)
-		err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
-#endif
 #ifdef CONFIG_NETFILTER
 	/* we need to exclude all possible ENOPROTOOPTs except default case */
 	if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 7ea7c3a0d0d0..bd84785bf8d6 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -161,15 +161,30 @@ int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool r
 {
 	struct sock *sk_pair;
 
+	/* Restore does not decrement the sk_pair reference yet because we must
+	 * keep the a reference to the socket until after an RCU grace period
+	 * and any pending sends have completed.
+	 */
 	if (restore) {
 		sk->sk_write_space = psock->saved_write_space;
 		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
 
-	sk_pair = unix_peer(sk);
-	sock_hold(sk_pair);
-	psock->sk_pair = sk_pair;
+	/* psock_update_sk_prot can be called multiple times if psock is
+	 * added to multiple maps and/or slots in the same map. There is
+	 * also an edge case where replacing a psock with itself can trigger
+	 * an extra psock_update_sk_prot during the insert process. So it
+	 * must be safe to do multiple calls. Here we need to ensure we don't
+	 * increment the refcnt through sock_hold many times. There will only
+	 * be a single matching destroy operation.
+	 */
+	if (!psock->sk_pair) {
+		sk_pair = unix_peer(sk);
+		sock_hold(sk_pair);
+		psock->sk_pair = sk_pair;
+	}
+
 	unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
 	sock_replace_proto(sk, &unix_stream_bpf_prot);
 	return 0;
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index edda4fc2c4d0..708733b0ea06 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -426,10 +426,6 @@ static void probe_kernel_image_config(const char *define_prefix)
 		{ "CONFIG_BPF_STREAM_PARSER", },
 		/* xt_bpf module for passing BPF programs to netfilter  */
 		{ "CONFIG_NETFILTER_XT_MATCH_BPF", },
-		/* bpfilter back-end for iptables */
-		{ "CONFIG_BPFILTER", },
-		/* bpftilter module with "user mode helper" */
-		{ "CONFIG_BPFILTER_UMH", },
 
 		/* test_bpf module for BPF tests */
 		{ "CONFIG_TEST_BPF", },
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ebcfb2147fbd..c5a42ac309fd 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1503,6 +1503,16 @@ static Elf64_Sym *find_elf_var_sym(const struct bpf_object *obj, const char *nam
 	return ERR_PTR(-ENOENT);
 }
 
+static int create_placeholder_fd(void)
+{
+	int fd;
+
+	fd = ensure_good_fd(memfd_create("libbpf-placeholder-fd", MFD_CLOEXEC));
+	if (fd < 0)
+		return -errno;
+	return fd;
+}
+
 static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 {
 	struct bpf_map *map;
@@ -1515,7 +1525,21 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj)
 
 	map = &obj->maps[obj->nr_maps++];
 	map->obj = obj;
-	map->fd = -1;
+	/* Preallocate map FD without actually creating BPF map just yet.
+	 * These map FD "placeholders" will be reused later without changing
+	 * FD value when map is actually created in the kernel.
+	 *
+	 * This is useful to be able to perform BPF program relocations
+	 * without having to create BPF maps before that step. This allows us
+	 * to finalize and load BTF very late in BPF object's loading phase,
+	 * right before BPF maps have to be created and BPF programs have to
+	 * be loaded. By having these map FD placeholders we can perform all
+	 * the sanitizations, relocations, and any other adjustments before we
+	 * start creating actual BPF kernel objects (BTF, maps, progs).
+	 */
+	map->fd = create_placeholder_fd();
+	if (map->fd < 0)
+		return ERR_PTR(map->fd);
 	map->inner_map_fd = -1;
 	map->autocreate = true;
 
@@ -2607,7 +2631,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj,
 		map->inner_map = calloc(1, sizeof(*map->inner_map));
 		if (!map->inner_map)
 			return -ENOMEM;
-		map->inner_map->fd = -1;
+		map->inner_map->fd = create_placeholder_fd();
+		if (map->inner_map->fd < 0)
+			return map->inner_map->fd;
 		map->inner_map->sec_idx = sec_idx;
 		map->inner_map->name = malloc(strlen(map_name) + sizeof(".inner") + 1);
 		if (!map->inner_map->name)
@@ -3166,86 +3192,6 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		}
 	}
 
-	if (!kernel_supports(obj, FEAT_BTF_DECL_TAG))
-		goto skip_exception_cb;
-	for (i = 0; i < obj->nr_programs; i++) {
-		struct bpf_program *prog = &obj->programs[i];
-		int j, k, n;
-
-		if (prog_is_subprog(obj, prog))
-			continue;
-		n = btf__type_cnt(obj->btf);
-		for (j = 1; j < n; j++) {
-			const char *str = "exception_callback:", *name;
-			size_t len = strlen(str);
-			struct btf_type *t;
-
-			t = btf_type_by_id(obj->btf, j);
-			if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1)
-				continue;
-
-			name = btf__str_by_offset(obj->btf, t->name_off);
-			if (strncmp(name, str, len))
-				continue;
-
-			t = btf_type_by_id(obj->btf, t->type);
-			if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
-				pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n",
-					prog->name);
-				return -EINVAL;
-			}
-			if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)))
-				continue;
-			/* Multiple callbacks are specified for the same prog,
-			 * the verifier will eventually return an error for this
-			 * case, hence simply skip appending a subprog.
-			 */
-			if (prog->exception_cb_idx >= 0) {
-				prog->exception_cb_idx = -1;
-				break;
-			}
-
-			name += len;
-			if (str_is_empty(name)) {
-				pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n",
-					prog->name);
-				return -EINVAL;
-			}
-
-			for (k = 0; k < obj->nr_programs; k++) {
-				struct bpf_program *subprog = &obj->programs[k];
-
-				if (!prog_is_subprog(obj, subprog))
-					continue;
-				if (strcmp(name, subprog->name))
-					continue;
-				/* Enforce non-hidden, as from verifier point of
-				 * view it expects global functions, whereas the
-				 * mark_btf_static fixes up linkage as static.
-				 */
-				if (!subprog->sym_global || subprog->mark_btf_static) {
-					pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n",
-						prog->name, subprog->name);
-					return -EINVAL;
-				}
-				/* Let's see if we already saw a static exception callback with the same name */
-				if (prog->exception_cb_idx >= 0) {
-					pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n",
-					        prog->name, subprog->name);
-					return -EINVAL;
-				}
-				prog->exception_cb_idx = k;
-				break;
-			}
-
-			if (prog->exception_cb_idx >= 0)
-				continue;
-			pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name);
-			return -ENOENT;
-		}
-	}
-skip_exception_cb:
-
 	sanitize = btf_needs_sanitization(obj);
 	if (sanitize) {
 		const void *raw_data;
@@ -4549,14 +4495,12 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 		goto err_free_new_name;
 	}
 
-	err = zclose(map->fd);
-	if (err) {
-		err = -errno;
-		goto err_close_new_fd;
-	}
+	err = reuse_fd(map->fd, new_fd);
+	if (err)
+		goto err_free_new_name;
+
 	free(map->name);
 
-	map->fd = new_fd;
 	map->name = new_name;
 	map->def.type = info.type;
 	map->def.key_size = info.key_size;
@@ -4570,8 +4514,6 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 
 	return 0;
 
-err_close_new_fd:
-	close(new_fd);
 err_free_new_name:
 	free(new_name);
 	return libbpf_err(err);
@@ -5200,12 +5142,17 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
 
 static void bpf_map__destroy(struct bpf_map *map);
 
+static bool map_is_created(const struct bpf_map *map)
+{
+	return map->obj->loaded || map->reused;
+}
+
 static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, create_attr);
 	struct bpf_map_def *def = &map->def;
 	const char *map_name = NULL;
-	int err = 0;
+	int err = 0, map_fd;
 
 	if (kernel_supports(obj, FEAT_PROG_NAME))
 		map_name = map->name;
@@ -5231,7 +5178,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 					map->name, err);
 				return err;
 			}
-			map->inner_map_fd = bpf_map__fd(map->inner_map);
+			map->inner_map_fd = map->inner_map->fd;
 		}
 		if (map->inner_map_fd >= 0)
 			create_attr.inner_map_fd = map->inner_map_fd;
@@ -5264,17 +5211,19 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		bpf_gen__map_create(obj->gen_loader, def->type, map_name,
 				    def->key_size, def->value_size, def->max_entries,
 				    &create_attr, is_inner ? -1 : map - obj->maps);
-		/* Pretend to have valid FD to pass various fd >= 0 checks.
-		 * This fd == 0 will not be used with any syscall and will be reset to -1 eventually.
+		/* We keep pretenting we have valid FD to pass various fd >= 0
+		 * checks by just keeping original placeholder FDs in place.
+		 * See bpf_object__add_map() comment.
+		 * This placeholder fd will not be used with any syscall and
+		 * will be reset to -1 eventually.
 		 */
-		map->fd = 0;
+		map_fd = map->fd;
 	} else {
-		map->fd = bpf_map_create(def->type, map_name,
-					 def->key_size, def->value_size,
-					 def->max_entries, &create_attr);
+		map_fd = bpf_map_create(def->type, map_name,
+					def->key_size, def->value_size,
+					def->max_entries, &create_attr);
 	}
-	if (map->fd < 0 && (create_attr.btf_key_type_id ||
-			    create_attr.btf_value_type_id)) {
+	if (map_fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) {
 		char *cp, errmsg[STRERR_BUFSIZE];
 
 		err = -errno;
@@ -5286,13 +5235,11 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		create_attr.btf_value_type_id = 0;
 		map->btf_key_type_id = 0;
 		map->btf_value_type_id = 0;
-		map->fd = bpf_map_create(def->type, map_name,
-					 def->key_size, def->value_size,
-					 def->max_entries, &create_attr);
+		map_fd = bpf_map_create(def->type, map_name,
+					def->key_size, def->value_size,
+					def->max_entries, &create_attr);
 	}
 
-	err = map->fd < 0 ? -errno : 0;
-
 	if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) {
 		if (obj->gen_loader)
 			map->inner_map->fd = -1;
@@ -5300,7 +5247,19 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		zfree(&map->inner_map);
 	}
 
-	return err;
+	if (map_fd < 0)
+		return map_fd;
+
+	/* obj->gen_loader case, prevent reuse_fd() from closing map_fd */
+	if (map->fd == map_fd)
+		return 0;
+
+	/* Keep placeholder FD value but now point it to the BPF map object.
+	 * This way everything that relied on this map's FD (e.g., relocated
+	 * ldimm64 instructions) will stay valid and won't need adjustments.
+	 * map->fd stays valid but now point to what map_fd points to.
+	 */
+	return reuse_fd(map->fd, map_fd);
 }
 
 static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map)
@@ -5314,7 +5273,7 @@ static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map)
 			continue;
 
 		targ_map = map->init_slots[i];
-		fd = bpf_map__fd(targ_map);
+		fd = targ_map->fd;
 
 		if (obj->gen_loader) {
 			bpf_gen__populate_outer_map(obj->gen_loader,
@@ -5384,10 +5343,8 @@ static int bpf_object_init_prog_arrays(struct bpf_object *obj)
 			continue;
 
 		err = init_prog_array_slots(obj, map);
-		if (err < 0) {
-			zclose(map->fd);
+		if (err < 0)
 			return err;
-		}
 	}
 	return 0;
 }
@@ -5465,7 +5422,7 @@ retry:
 			}
 		}
 
-		if (map->fd >= 0) {
+		if (map->reused) {
 			pr_debug("map '%s': skipping creation (preset fd=%d)\n",
 				 map->name, map->fd);
 		} else {
@@ -5478,25 +5435,20 @@ retry:
 
 			if (bpf_map__is_internal(map)) {
 				err = bpf_object__populate_internal_map(obj, map);
-				if (err < 0) {
-					zclose(map->fd);
+				if (err < 0)
 					goto err_out;
-				}
 			}
 
 			if (map->init_slots_sz && map->def.type != BPF_MAP_TYPE_PROG_ARRAY) {
 				err = init_map_in_map_slots(obj, map);
-				if (err < 0) {
-					zclose(map->fd);
+				if (err < 0)
 					goto err_out;
-				}
 			}
 		}
 
 		if (map->pin_path && !map->pinned) {
 			err = bpf_map__pin(map, NULL);
 			if (err) {
-				zclose(map->fd);
 				if (!retried && err == -EEXIST) {
 					retried = true;
 					goto retry;
@@ -6229,7 +6181,7 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj,
 	int err;
 
 	/* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't
-	 * supprot func/line info
+	 * support func/line info
 	 */
 	if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC))
 		return 0;
@@ -6629,8 +6581,329 @@ static void bpf_object__sort_relos(struct bpf_object *obj)
 	}
 }
 
-static int
-bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
+static int bpf_prog_assign_exc_cb(struct bpf_object *obj, struct bpf_program *prog)
+{
+	const char *str = "exception_callback:";
+	size_t pfx_len = strlen(str);
+	int i, j, n;
+
+	if (!obj->btf || !kernel_supports(obj, FEAT_BTF_DECL_TAG))
+		return 0;
+
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
+		const char *name;
+		struct btf_type *t;
+
+		t = btf_type_by_id(obj->btf, i);
+		if (!btf_is_decl_tag(t) || btf_decl_tag(t)->component_idx != -1)
+			continue;
+
+		name = btf__str_by_offset(obj->btf, t->name_off);
+		if (strncmp(name, str, pfx_len) != 0)
+			continue;
+
+		t = btf_type_by_id(obj->btf, t->type);
+		if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
+			pr_warn("prog '%s': exception_callback:<value> decl tag not applied to the main program\n",
+				prog->name);
+			return -EINVAL;
+		}
+		if (strcmp(prog->name, btf__str_by_offset(obj->btf, t->name_off)) != 0)
+			continue;
+		/* Multiple callbacks are specified for the same prog,
+		 * the verifier will eventually return an error for this
+		 * case, hence simply skip appending a subprog.
+		 */
+		if (prog->exception_cb_idx >= 0) {
+			prog->exception_cb_idx = -1;
+			break;
+		}
+
+		name += pfx_len;
+		if (str_is_empty(name)) {
+			pr_warn("prog '%s': exception_callback:<value> decl tag contains empty value\n",
+				prog->name);
+			return -EINVAL;
+		}
+
+		for (j = 0; j < obj->nr_programs; j++) {
+			struct bpf_program *subprog = &obj->programs[j];
+
+			if (!prog_is_subprog(obj, subprog))
+				continue;
+			if (strcmp(name, subprog->name) != 0)
+				continue;
+			/* Enforce non-hidden, as from verifier point of
+			 * view it expects global functions, whereas the
+			 * mark_btf_static fixes up linkage as static.
+			 */
+			if (!subprog->sym_global || subprog->mark_btf_static) {
+				pr_warn("prog '%s': exception callback %s must be a global non-hidden function\n",
+					prog->name, subprog->name);
+				return -EINVAL;
+			}
+			/* Let's see if we already saw a static exception callback with the same name */
+			if (prog->exception_cb_idx >= 0) {
+				pr_warn("prog '%s': multiple subprogs with same name as exception callback '%s'\n",
+					prog->name, subprog->name);
+				return -EINVAL;
+			}
+			prog->exception_cb_idx = j;
+			break;
+		}
+
+		if (prog->exception_cb_idx >= 0)
+			continue;
+
+		pr_warn("prog '%s': cannot find exception callback '%s'\n", prog->name, name);
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
+static struct {
+	enum bpf_prog_type prog_type;
+	const char *ctx_name;
+} global_ctx_map[] = {
+	{ BPF_PROG_TYPE_CGROUP_DEVICE,           "bpf_cgroup_dev_ctx" },
+	{ BPF_PROG_TYPE_CGROUP_SKB,              "__sk_buff" },
+	{ BPF_PROG_TYPE_CGROUP_SOCK,             "bpf_sock" },
+	{ BPF_PROG_TYPE_CGROUP_SOCK_ADDR,        "bpf_sock_addr" },
+	{ BPF_PROG_TYPE_CGROUP_SOCKOPT,          "bpf_sockopt" },
+	{ BPF_PROG_TYPE_CGROUP_SYSCTL,           "bpf_sysctl" },
+	{ BPF_PROG_TYPE_FLOW_DISSECTOR,          "__sk_buff" },
+	{ BPF_PROG_TYPE_KPROBE,                  "bpf_user_pt_regs_t" },
+	{ BPF_PROG_TYPE_LWT_IN,                  "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_OUT,                 "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_SEG6LOCAL,           "__sk_buff" },
+	{ BPF_PROG_TYPE_LWT_XMIT,                "__sk_buff" },
+	{ BPF_PROG_TYPE_NETFILTER,               "bpf_nf_ctx" },
+	{ BPF_PROG_TYPE_PERF_EVENT,              "bpf_perf_event_data" },
+	{ BPF_PROG_TYPE_RAW_TRACEPOINT,          "bpf_raw_tracepoint_args" },
+	{ BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, "bpf_raw_tracepoint_args" },
+	{ BPF_PROG_TYPE_SCHED_ACT,               "__sk_buff" },
+	{ BPF_PROG_TYPE_SCHED_CLS,               "__sk_buff" },
+	{ BPF_PROG_TYPE_SK_LOOKUP,               "bpf_sk_lookup" },
+	{ BPF_PROG_TYPE_SK_MSG,                  "sk_msg_md" },
+	{ BPF_PROG_TYPE_SK_REUSEPORT,            "sk_reuseport_md" },
+	{ BPF_PROG_TYPE_SK_SKB,                  "__sk_buff" },
+	{ BPF_PROG_TYPE_SOCK_OPS,                "bpf_sock_ops" },
+	{ BPF_PROG_TYPE_SOCKET_FILTER,           "__sk_buff" },
+	{ BPF_PROG_TYPE_XDP,                     "xdp_md" },
+	/* all other program types don't have "named" context structs */
+};
+
+static int clone_func_btf_info(struct btf *btf, int orig_fn_id, struct bpf_program *prog)
+{
+	int fn_id, fn_proto_id, ret_type_id, orig_proto_id;
+	int i, err, arg_cnt, fn_name_off, linkage;
+	struct btf_type *fn_t, *fn_proto_t, *t;
+	struct btf_param *p;
+
+	/* caller already validated FUNC -> FUNC_PROTO validity */
+	fn_t = btf_type_by_id(btf, orig_fn_id);
+	fn_proto_t = btf_type_by_id(btf, fn_t->type);
+
+	/* Note that each btf__add_xxx() operation invalidates
+	 * all btf_type and string pointers, so we need to be
+	 * very careful when cloning BTF types. BTF type
+	 * pointers have to be always refetched. And to avoid
+	 * problems with invalidated string pointers, we
+	 * add empty strings initially, then just fix up
+	 * name_off offsets in place. Offsets are stable for
+	 * existing strings, so that works out.
+	 */
+	fn_name_off = fn_t->name_off; /* we are about to invalidate fn_t */
+	linkage = btf_func_linkage(fn_t);
+	orig_proto_id = fn_t->type; /* original FUNC_PROTO ID */
+	ret_type_id = fn_proto_t->type; /* fn_proto_t will be invalidated */
+	arg_cnt = btf_vlen(fn_proto_t);
+
+	/* clone FUNC_PROTO and its params */
+	fn_proto_id = btf__add_func_proto(btf, ret_type_id);
+	if (fn_proto_id < 0)
+		return -EINVAL;
+
+	for (i = 0; i < arg_cnt; i++) {
+		int name_off;
+
+		/* copy original parameter data */
+		t = btf_type_by_id(btf, orig_proto_id);
+		p = &btf_params(t)[i];
+		name_off = p->name_off;
+
+		err = btf__add_func_param(btf, "", p->type);
+		if (err)
+			return err;
+
+		fn_proto_t = btf_type_by_id(btf, fn_proto_id);
+		p = &btf_params(fn_proto_t)[i];
+		p->name_off = name_off; /* use remembered str offset */
+	}
+
+	/* clone FUNC now, btf__add_func() enforces non-empty name, so use
+	 * entry program's name as a placeholder, which we replace immediately
+	 * with original name_off
+	 */
+	fn_id = btf__add_func(btf, prog->name, linkage, fn_proto_id);
+	if (fn_id < 0)
+		return -EINVAL;
+
+	fn_t = btf_type_by_id(btf, fn_id);
+	fn_t->name_off = fn_name_off; /* reuse original string */
+
+	return fn_id;
+}
+
+/* Check if main program or global subprog's function prototype has `arg:ctx`
+ * argument tags, and, if necessary, substitute correct type to match what BPF
+ * verifier would expect, taking into account specific program type. This
+ * allows to support __arg_ctx tag transparently on old kernels that don't yet
+ * have a native support for it in the verifier, making user's life much
+ * easier.
+ */
+static int bpf_program_fixup_func_info(struct bpf_object *obj, struct bpf_program *prog)
+{
+	const char *ctx_name = NULL, *ctx_tag = "arg:ctx";
+	struct bpf_func_info_min *func_rec;
+	struct btf_type *fn_t, *fn_proto_t;
+	struct btf *btf = obj->btf;
+	const struct btf_type *t;
+	struct btf_param *p;
+	int ptr_id = 0, struct_id, tag_id, orig_fn_id;
+	int i, n, arg_idx, arg_cnt, err, rec_idx;
+	int *orig_ids;
+
+	/* no .BTF.ext, no problem */
+	if (!obj->btf_ext || !prog->func_info)
+		return 0;
+
+	/* some BPF program types just don't have named context structs, so
+	 * this fallback mechanism doesn't work for them
+	 */
+	for (i = 0; i < ARRAY_SIZE(global_ctx_map); i++) {
+		if (global_ctx_map[i].prog_type != prog->type)
+			continue;
+		ctx_name = global_ctx_map[i].ctx_name;
+		break;
+	}
+	if (!ctx_name)
+		return 0;
+
+	/* remember original func BTF IDs to detect if we already cloned them */
+	orig_ids = calloc(prog->func_info_cnt, sizeof(*orig_ids));
+	if (!orig_ids)
+		return -ENOMEM;
+	for (i = 0; i < prog->func_info_cnt; i++) {
+		func_rec = prog->func_info + prog->func_info_rec_size * i;
+		orig_ids[i] = func_rec->type_id;
+	}
+
+	/* go through each DECL_TAG with "arg:ctx" and see if it points to one
+	 * of our subprogs; if yes and subprog is global and needs adjustment,
+	 * clone and adjust FUNC -> FUNC_PROTO combo
+	 */
+	for (i = 1, n = btf__type_cnt(btf); i < n; i++) {
+		/* only DECL_TAG with "arg:ctx" value are interesting */
+		t = btf__type_by_id(btf, i);
+		if (!btf_is_decl_tag(t))
+			continue;
+		if (strcmp(btf__str_by_offset(btf, t->name_off), ctx_tag) != 0)
+			continue;
+
+		/* only global funcs need adjustment, if at all */
+		orig_fn_id = t->type;
+		fn_t = btf_type_by_id(btf, orig_fn_id);
+		if (!btf_is_func(fn_t) || btf_func_linkage(fn_t) != BTF_FUNC_GLOBAL)
+			continue;
+
+		/* sanity check FUNC -> FUNC_PROTO chain, just in case */
+		fn_proto_t = btf_type_by_id(btf, fn_t->type);
+		if (!fn_proto_t || !btf_is_func_proto(fn_proto_t))
+			continue;
+
+		/* find corresponding func_info record */
+		func_rec = NULL;
+		for (rec_idx = 0; rec_idx < prog->func_info_cnt; rec_idx++) {
+			if (orig_ids[rec_idx] == t->type) {
+				func_rec = prog->func_info + prog->func_info_rec_size * rec_idx;
+				break;
+			}
+		}
+		/* current main program doesn't call into this subprog */
+		if (!func_rec)
+			continue;
+
+		/* some more sanity checking of DECL_TAG */
+		arg_cnt = btf_vlen(fn_proto_t);
+		arg_idx = btf_decl_tag(t)->component_idx;
+		if (arg_idx < 0 || arg_idx >= arg_cnt)
+			continue;
+
+		/* check if existing parameter already matches verifier expectations */
+		p = &btf_params(fn_proto_t)[arg_idx];
+		t = skip_mods_and_typedefs(btf, p->type, NULL);
+		if (btf_is_ptr(t) &&
+		    (t = skip_mods_and_typedefs(btf, t->type, NULL)) &&
+		    btf_is_struct(t) &&
+		    strcmp(btf__str_by_offset(btf, t->name_off), ctx_name) == 0) {
+			continue; /* no need for fix up */
+		}
+
+		/* clone fn/fn_proto, unless we already did it for another arg */
+		if (func_rec->type_id == orig_fn_id) {
+			int fn_id;
+
+			fn_id = clone_func_btf_info(btf, orig_fn_id, prog);
+			if (fn_id < 0) {
+				err = fn_id;
+				goto err_out;
+			}
+
+			/* point func_info record to a cloned FUNC type */
+			func_rec->type_id = fn_id;
+		}
+
+		/* create PTR -> STRUCT type chain to mark PTR_TO_CTX argument;
+		 * we do it just once per main BPF program, as all global
+		 * funcs share the same program type, so need only PTR ->
+		 * STRUCT type chain
+		 */
+		if (ptr_id == 0) {
+			struct_id = btf__add_struct(btf, ctx_name, 0);
+			ptr_id = btf__add_ptr(btf, struct_id);
+			if (ptr_id < 0 || struct_id < 0) {
+				err = -EINVAL;
+				goto err_out;
+			}
+		}
+
+		/* for completeness, clone DECL_TAG and point it to cloned param */
+		tag_id = btf__add_decl_tag(btf, ctx_tag, func_rec->type_id, arg_idx);
+		if (tag_id < 0) {
+			err = -EINVAL;
+			goto err_out;
+		}
+
+		/* all the BTF manipulations invalidated pointers, refetch them */
+		fn_t = btf_type_by_id(btf, func_rec->type_id);
+		fn_proto_t = btf_type_by_id(btf, fn_t->type);
+
+		/* fix up type ID pointed to by param */
+		p = &btf_params(fn_proto_t)[arg_idx];
+		p->type = ptr_id;
+	}
+
+	free(orig_ids);
+	return 0;
+err_out:
+	free(orig_ids);
+	return err;
+}
+
+static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 {
 	struct bpf_program *prog;
 	size_t i, j;
@@ -6689,6 +6962,9 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			return err;
 		}
 
+		err = bpf_prog_assign_exc_cb(obj, prog);
+		if (err)
+			return err;
 		/* Now, also append exception callback if it has not been done already. */
 		if (prog->exception_cb_idx >= 0) {
 			struct bpf_program *subprog = &obj->programs[prog->exception_cb_idx];
@@ -6708,19 +6984,28 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 			}
 		}
 	}
-	/* Process data relos for main programs */
 	for (i = 0; i < obj->nr_programs; i++) {
 		prog = &obj->programs[i];
 		if (prog_is_subprog(obj, prog))
 			continue;
 		if (!prog->autoload)
 			continue;
+
+		/* Process data relos for main programs */
 		err = bpf_object__relocate_data(obj, prog);
 		if (err) {
 			pr_warn("prog '%s': failed to relocate data references: %d\n",
 				prog->name, err);
 			return err;
 		}
+
+		/* Fix up .BTF.ext information, if necessary */
+		err = bpf_program_fixup_func_info(obj, prog);
+		if (err) {
+			pr_warn("prog '%s': failed to perform .BTF.ext fix ups: %d\n",
+				prog->name, err);
+			return err;
+		}
 	}
 
 	return 0;
@@ -7050,7 +7335,7 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog
 	load_attr.prog_ifindex = prog->prog_ifindex;
 
 	/* specify func_info/line_info only if kernel supports them */
-	btf_fd = bpf_object__btf_fd(obj);
+	btf_fd = btf__fd(obj->btf);
 	if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
 		load_attr.prog_btf_fd = btf_fd;
 		load_attr.func_info = prog->func_info;
@@ -7135,7 +7420,7 @@ retry_load:
 				if (map->libbpf_type != LIBBPF_MAP_RODATA)
 					continue;
 
-				if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) {
+				if (bpf_prog_bind_map(ret, map->fd, NULL)) {
 					cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 					pr_warn("prog '%s': failed to bind map '%s': %s\n",
 						prog->name, map->real_name, cp);
@@ -8067,11 +8352,11 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 	err = bpf_object__probe_loading(obj);
 	err = err ? : bpf_object__load_vmlinux_btf(obj, false);
 	err = err ? : bpf_object__resolve_externs(obj, obj->kconfig);
-	err = err ? : bpf_object__sanitize_and_load_btf(obj);
 	err = err ? : bpf_object__sanitize_maps(obj);
 	err = err ? : bpf_object__init_kern_struct_ops_maps(obj);
-	err = err ? : bpf_object__create_maps(obj);
 	err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path);
+	err = err ? : bpf_object__sanitize_and_load_btf(obj);
+	err = err ? : bpf_object__create_maps(obj);
 	err = err ? : bpf_object__load_progs(obj, extra_log_level);
 	err = err ? : bpf_object_init_prog_arrays(obj);
 	err = err ? : bpf_object_prepare_struct_ops(obj);
@@ -8080,8 +8365,6 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch
 		/* reset FDs */
 		if (obj->btf)
 			btf__set_fd(obj->btf, -1);
-		for (i = 0; i < obj->nr_maps; i++)
-			obj->maps[i].fd = -1;
 		if (!err)
 			err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps);
 	}
@@ -9601,7 +9884,11 @@ int libbpf_attach_type_by_name(const char *name,
 
 int bpf_map__fd(const struct bpf_map *map)
 {
-	return map ? map->fd : libbpf_err(-EINVAL);
+	if (!map)
+		return libbpf_err(-EINVAL);
+	if (!map_is_created(map))
+		return -1;
+	return map->fd;
 }
 
 static bool map_uses_real_name(const struct bpf_map *map)
@@ -9637,7 +9924,7 @@ enum bpf_map_type bpf_map__type(const struct bpf_map *map)
 
 int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.type = type;
 	return 0;
@@ -9650,7 +9937,7 @@ __u32 bpf_map__map_flags(const struct bpf_map *map)
 
 int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.map_flags = flags;
 	return 0;
@@ -9663,7 +9950,7 @@ __u64 bpf_map__map_extra(const struct bpf_map *map)
 
 int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->map_extra = map_extra;
 	return 0;
@@ -9676,7 +9963,7 @@ __u32 bpf_map__numa_node(const struct bpf_map *map)
 
 int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->numa_node = numa_node;
 	return 0;
@@ -9689,7 +9976,7 @@ __u32 bpf_map__key_size(const struct bpf_map *map)
 
 int bpf_map__set_key_size(struct bpf_map *map, __u32 size)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->def.key_size = size;
 	return 0;
@@ -9773,7 +10060,7 @@ static int map_btf_datasec_resize(struct bpf_map *map, __u32 size)
 
 int bpf_map__set_value_size(struct bpf_map *map, __u32 size)
 {
-	if (map->fd >= 0)
+	if (map->obj->loaded || map->reused)
 		return libbpf_err(-EBUSY);
 
 	if (map->mmaped) {
@@ -9814,8 +10101,11 @@ __u32 bpf_map__btf_value_type_id(const struct bpf_map *map)
 int bpf_map__set_initial_value(struct bpf_map *map,
 			       const void *data, size_t size)
 {
+	if (map->obj->loaded || map->reused)
+		return libbpf_err(-EBUSY);
+
 	if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG ||
-	    size != map->def.value_size || map->fd >= 0)
+	    size != map->def.value_size)
 		return libbpf_err(-EINVAL);
 
 	memcpy(map->mmaped, data, size);
@@ -9842,7 +10132,7 @@ __u32 bpf_map__ifindex(const struct bpf_map *map)
 
 int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 {
-	if (map->fd >= 0)
+	if (map_is_created(map))
 		return libbpf_err(-EBUSY);
 	map->map_ifindex = ifindex;
 	return 0;
@@ -9947,7 +10237,7 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name)
 static int validate_map_op(const struct bpf_map *map, size_t key_sz,
 			   size_t value_sz, bool check_value_sz)
 {
-	if (map->fd <= 0)
+	if (!map_is_created(map)) /* map is not yet created */
 		return -ENOENT;
 
 	if (map->def.key_size != key_sz) {
@@ -12400,7 +12690,7 @@ int bpf_link__update_map(struct bpf_link *link, const struct bpf_map *map)
 	__u32 zero = 0;
 	int err;
 
-	if (!bpf_map__is_struct_ops(map) || map->fd < 0)
+	if (!bpf_map__is_struct_ops(map) || !map_is_created(map))
 		return -EINVAL;
 
 	st_ops_link = container_of(link, struct bpf_link_struct_ops, link);
@@ -13304,7 +13594,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s)
 	for (i = 0; i < s->map_cnt; i++) {
 		struct bpf_map *map = *s->maps[i].map;
 		size_t mmap_sz = bpf_map_mmap_sz(map->def.value_size, map->def.max_entries);
-		int prot, map_fd = bpf_map__fd(map);
+		int prot, map_fd = map->fd;
 		void **mmaped = s->maps[i].mmaped;
 
 		if (!mmaped)
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index b5d334754e5d..27e4e320e1a6 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -555,6 +555,20 @@ static inline int ensure_good_fd(int fd)
 	return fd;
 }
 
+/* Point *fixed_fd* to the same file that *tmp_fd* points to.
+ * Regardless of success, *tmp_fd* is closed.
+ * Whatever *fixed_fd* pointed to is closed silently.
+ */
+static inline int reuse_fd(int fixed_fd, int tmp_fd)
+{
+	int err;
+
+	err = dup2(tmp_fd, fixed_fd);
+	err = err < 0 ? -errno : 0;
+	close(tmp_fd); /* clean up temporary FD */
+	return err;
+}
+
 /* The following two functions are exposed to bpftool */
 int bpf_core_add_cands(struct bpf_core_cand *local_cand,
 		       size_t local_essent_len,
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