Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull bpf fixes from Daniel Borkmann:

 - Fix a bug in the BPF verifier to track changes to packet data
   property for global functions (Eduard Zingerman)

 - Fix a theoretical BPF prog_array use-after-free in RCU handling of
   __uprobe_perf_func (Jann Horn)

 - Fix BPF tracing to have an explicit list of tracepoints and their
   arguments which need to be annotated as PTR_MAYBE_NULL (Kumar
   Kartikeya Dwivedi)

 - Fix a logic bug in the bpf_remove_insns code where a potential error
   would have been wrongly propagated (Anton Protopopov)

 - Avoid deadlock scenarios caused by nested kprobe and fentry BPF
   programs (Priya Bala Govindasamy)

 - Fix a bug in BPF verifier which was missing a size check for
   BTF-based context access (Kumar Kartikeya Dwivedi)

 - Fix a crash found by syzbot through an invalid BPF prog_array access
   in perf_event_detach_bpf_prog (Jiri Olsa)

 - Fix several BPF sockmap bugs including a race causing a refcount
   imbalance upon element replace (Michal Luczaj)

 - Fix a use-after-free from mismatching BPF program/attachment RCU
   flavors (Jann Horn)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf: (23 commits)
  bpf: Avoid deadlock caused by nested kprobe and fentry bpf programs
  selftests/bpf: Add tests for raw_tp NULL args
  bpf: Augment raw_tp arguments with PTR_MAYBE_NULL
  bpf: Revert "bpf: Mark raw_tp arguments with PTR_MAYBE_NULL"
  selftests/bpf: Add test for narrow ctx load for pointer args
  bpf: Check size for BTF-based ctx access of pointer members
  selftests/bpf: extend changes_pkt_data with cases w/o subprograms
  bpf: fix null dereference when computing changes_pkt_data of prog w/o subprogs
  bpf: Fix theoretical prog_array UAF in __uprobe_perf_func()
  bpf: fix potential error return
  selftests/bpf: validate that tail call invalidates packet pointers
  bpf: consider that tail calls invalidate packet pointers
  selftests/bpf: freplace tests for tracking of changes_packet_data
  bpf: check changes_pkt_data property for extension programs
  selftests/bpf: test for changing packet data from global functions
  bpf: track changes_pkt_data property for global functions
  bpf: refactor bpf_helper_changes_pkt_data to use helper number
  bpf: add find_containing_subprog() utility function
  bpf,perf: Fix invalid prog_array access in perf_event_detach_bpf_prog
  bpf: Fix UAF via mismatching bpf_prog/attachment RCU flavors
  ...

23 files changed, 596 insertions, 164 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index eaee2a819f4c..6e63dd3443b9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1527,6 +1527,7 @@ struct bpf_prog_aux {
 	bool is_extended; /* true if extended by freplace program */
 	bool jits_use_priv_stack;
 	bool priv_stack_requested;
+	bool changes_pkt_data;
 	u64 prog_array_member_cnt; /* counts how many times as member of prog_array */
 	struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */
 	struct bpf_arena *arena;
@@ -2193,26 +2194,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
  * rcu-protected dynamically sized maps.
  */
 static __always_inline u32
-bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
+bpf_prog_run_array_uprobe(const struct bpf_prog_array *array,
 			  const void *ctx, bpf_prog_run_fn run_prog)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
-	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_trace_run_ctx run_ctx;
 	u32 ret = 1;
 
 	might_fault();
+	RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held");
+
+	if (unlikely(!array))
+		return ret;
 
-	rcu_read_lock_trace();
 	migrate_disable();
 
 	run_ctx.is_uprobe = true;
 
-	array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
-	if (unlikely(!array))
-		goto out;
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	item = &array->items[0];
 	while ((prog = READ_ONCE(item->prog))) {
@@ -2227,9 +2227,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu,
 			rcu_read_unlock();
 	}
 	bpf_reset_run_ctx(old_run_ctx);
-out:
 	migrate_enable();
-	rcu_read_unlock_trace();
 	return ret;
 }
 
@@ -3516,10 +3514,4 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog)
 	return prog->aux->func_idx != 0;
 }
 
-static inline bool bpf_prog_is_raw_tp(const struct bpf_prog *prog)
-{
-	return prog->type == BPF_PROG_TYPE_TRACING &&
-	       prog->expected_attach_type == BPF_TRACE_RAW_TP;
-}
-
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index f4290c179bee..48b7b2eeb7e2 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -659,6 +659,7 @@ struct bpf_subprog_info {
 	bool args_cached: 1;
 	/* true if bpf_fastcall stack region is used by functions that can't be inlined */
 	bool keep_fastcall_stack: 1;
+	bool changes_pkt_data: 1;
 
 	enum priv_stack_mode priv_stack_mode;
 	u8 arg_cnt;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 3a21947f2fd4..0477254bc2d3 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1122,7 +1122,7 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena);
 bool bpf_jit_supports_private_stack(void);
 u64 bpf_arch_uaddress_limit(void);
 void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);
-bool bpf_helper_changes_pkt_data(void *func);
+bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id);
 
 static inline bool bpf_dump_raw_ok(const struct cred *cred)
 {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 9762bdddf1de..410028633621 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -53,3 +53,9 @@ obj-$(CONFIG_BPF_SYSCALL) += relo_core.o
 obj-$(CONFIG_BPF_SYSCALL) += btf_iter.o
 obj-$(CONFIG_BPF_SYSCALL) += btf_relocate.o
 obj-$(CONFIG_BPF_SYSCALL) += kmem_cache_iter.o
+
+CFLAGS_REMOVE_percpu_freelist.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_queue_stack_maps.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_lpm_trie.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_ringbuf.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e7a59e6462a9..e5a5f023cedd 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6439,6 +6439,101 @@ int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto,
 	return off;
 }
 
+struct bpf_raw_tp_null_args {
+	const char *func;
+	u64 mask;
+};
+
+static const struct bpf_raw_tp_null_args raw_tp_null_args[] = {
+	/* sched */
+	{ "sched_pi_setprio", 0x10 },
+	/* ... from sched_numa_pair_template event class */
+	{ "sched_stick_numa", 0x100 },
+	{ "sched_swap_numa", 0x100 },
+	/* afs */
+	{ "afs_make_fs_call", 0x10 },
+	{ "afs_make_fs_calli", 0x10 },
+	{ "afs_make_fs_call1", 0x10 },
+	{ "afs_make_fs_call2", 0x10 },
+	{ "afs_protocol_error", 0x1 },
+	{ "afs_flock_ev", 0x10 },
+	/* cachefiles */
+	{ "cachefiles_lookup", 0x1 | 0x200 },
+	{ "cachefiles_unlink", 0x1 },
+	{ "cachefiles_rename", 0x1 },
+	{ "cachefiles_prep_read", 0x1 },
+	{ "cachefiles_mark_active", 0x1 },
+	{ "cachefiles_mark_failed", 0x1 },
+	{ "cachefiles_mark_inactive", 0x1 },
+	{ "cachefiles_vfs_error", 0x1 },
+	{ "cachefiles_io_error", 0x1 },
+	{ "cachefiles_ondemand_open", 0x1 },
+	{ "cachefiles_ondemand_copen", 0x1 },
+	{ "cachefiles_ondemand_close", 0x1 },
+	{ "cachefiles_ondemand_read", 0x1 },
+	{ "cachefiles_ondemand_cread", 0x1 },
+	{ "cachefiles_ondemand_fd_write", 0x1 },
+	{ "cachefiles_ondemand_fd_release", 0x1 },
+	/* ext4, from ext4__mballoc event class */
+	{ "ext4_mballoc_discard", 0x10 },
+	{ "ext4_mballoc_free", 0x10 },
+	/* fib */
+	{ "fib_table_lookup", 0x100 },
+	/* filelock */
+	/* ... from filelock_lock event class */
+	{ "posix_lock_inode", 0x10 },
+	{ "fcntl_setlk", 0x10 },
+	{ "locks_remove_posix", 0x10 },
+	{ "flock_lock_inode", 0x10 },
+	/* ... from filelock_lease event class */
+	{ "break_lease_noblock", 0x10 },
+	{ "break_lease_block", 0x10 },
+	{ "break_lease_unblock", 0x10 },
+	{ "generic_delete_lease", 0x10 },
+	{ "time_out_leases", 0x10 },
+	/* host1x */
+	{ "host1x_cdma_push_gather", 0x10000 },
+	/* huge_memory */
+	{ "mm_khugepaged_scan_pmd", 0x10 },
+	{ "mm_collapse_huge_page_isolate", 0x1 },
+	{ "mm_khugepaged_scan_file", 0x10 },
+	{ "mm_khugepaged_collapse_file", 0x10 },
+	/* kmem */
+	{ "mm_page_alloc", 0x1 },
+	{ "mm_page_pcpu_drain", 0x1 },
+	/* .. from mm_page event class */
+	{ "mm_page_alloc_zone_locked", 0x1 },
+	/* netfs */
+	{ "netfs_failure", 0x10 },
+	/* power */
+	{ "device_pm_callback_start", 0x10 },
+	/* qdisc */
+	{ "qdisc_dequeue", 0x1000 },
+	/* rxrpc */
+	{ "rxrpc_recvdata", 0x1 },
+	{ "rxrpc_resend", 0x10 },
+	/* sunrpc */
+	{ "xs_stream_read_data", 0x1 },
+	/* ... from xprt_cong_event event class */
+	{ "xprt_reserve_cong", 0x10 },
+	{ "xprt_release_cong", 0x10 },
+	{ "xprt_get_cong", 0x10 },
+	{ "xprt_put_cong", 0x10 },
+	/* tcp */
+	{ "tcp_send_reset", 0x11 },
+	/* tegra_apb_dma */
+	{ "tegra_dma_tx_status", 0x100 },
+	/* timer_migration */
+	{ "tmigr_update_events", 0x1 },
+	/* writeback, from writeback_folio_template event class */
+	{ "writeback_dirty_folio", 0x10 },
+	{ "folio_wait_writeback", 0x10 },
+	/* rdma */
+	{ "mr_integ_alloc", 0x2000 },
+	/* bpf_testmod */
+	{ "bpf_testmod_test_read", 0x0 },
+};
+
 bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		    const struct bpf_prog *prog,
 		    struct bpf_insn_access_aux *info)
@@ -6449,6 +6544,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	const char *tname = prog->aux->attach_func_name;
 	struct bpf_verifier_log *log = info->log;
 	const struct btf_param *args;
+	bool ptr_err_raw_tp = false;
 	const char *tag_value;
 	u32 nr_args, arg;
 	int i, ret;
@@ -6543,6 +6639,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		return false;
 	}
 
+	if (size != sizeof(u64)) {
+		bpf_log(log, "func '%s' size %d must be 8\n",
+			tname, size);
+		return false;
+	}
+
 	/* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */
 	for (i = 0; i < prog->aux->ctx_arg_info_size; i++) {
 		const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i];
@@ -6588,12 +6690,42 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	if (prog_args_trusted(prog))
 		info->reg_type |= PTR_TRUSTED;
 
-	/* Raw tracepoint arguments always get marked as maybe NULL */
-	if (bpf_prog_is_raw_tp(prog))
-		info->reg_type |= PTR_MAYBE_NULL;
-	else if (btf_param_match_suffix(btf, &args[arg], "__nullable"))
+	if (btf_param_match_suffix(btf, &args[arg], "__nullable"))
 		info->reg_type |= PTR_MAYBE_NULL;
 
+	if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
+		struct btf *btf = prog->aux->attach_btf;
+		const struct btf_type *t;
+		const char *tname;
+
+		/* BTF lookups cannot fail, return false on error */
+		t = btf_type_by_id(btf, prog->aux->attach_btf_id);
+		if (!t)
+			return false;
+		tname = btf_name_by_offset(btf, t->name_off);
+		if (!tname)
+			return false;
+		/* Checked by bpf_check_attach_target */
+		tname += sizeof("btf_trace_") - 1;
+		for (i = 0; i < ARRAY_SIZE(raw_tp_null_args); i++) {
+			/* Is this a func with potential NULL args? */
+			if (strcmp(tname, raw_tp_null_args[i].func))
+				continue;
+			if (raw_tp_null_args[i].mask & (0x1 << (arg * 4)))
+				info->reg_type |= PTR_MAYBE_NULL;
+			/* Is the current arg IS_ERR? */
+			if (raw_tp_null_args[i].mask & (0x2 << (arg * 4)))
+				ptr_err_raw_tp = true;
+			break;
+		}
+		/* If we don't know NULL-ness specification and the tracepoint
+		 * is coming from a loadable module, be conservative and mark
+		 * argument as PTR_MAYBE_NULL.
+		 */
+		if (i == ARRAY_SIZE(raw_tp_null_args) && btf_is_module(btf))
+			info->reg_type |= PTR_MAYBE_NULL;
+	}
+
 	if (tgt_prog) {
 		enum bpf_prog_type tgt_type;
 
@@ -6638,6 +6770,15 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n",
 		tname, arg, info->btf_id, btf_type_str(t),
 		__btf_name_by_offset(btf, t->name_off));
+
+	/* Perform all checks on the validity of type for this argument, but if
+	 * we know it can be IS_ERR at runtime, scrub pointer type and mark as
+	 * scalar.
+	 */
+	if (ptr_err_raw_tp) {
+		bpf_log(log, "marking pointer arg%d as scalar as it may encode error", arg);
+		info->reg_type = SCALAR_VALUE;
+	}
 	return true;
 }
 EXPORT_SYMBOL_GPL(btf_ctx_access);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a2327c4fdc8b..da729cbbaeb9 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -539,6 +539,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 
 int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
 {
+	int err;
+
 	/* Branch offsets can't overflow when program is shrinking, no need
 	 * to call bpf_adj_branches(..., true) here
 	 */
@@ -546,7 +548,9 @@ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
 		sizeof(struct bpf_insn) * (prog->len - off - cnt));
 	prog->len -= cnt;
 
-	return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
+	err = bpf_adj_branches(prog, off, off + cnt, off, false);
+	WARN_ON_ONCE(err);
+	return err;
 }
 
 static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
@@ -2936,7 +2940,7 @@ void __weak bpf_jit_compile(struct bpf_prog *prog)
 {
 }
 
-bool __weak bpf_helper_changes_pkt_data(void *func)
+bool __weak bpf_helper_changes_pkt_data(enum bpf_func_id func_id)
 {
 	return false;
 }
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 01fbef9576e0..f7f892a52a37 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -420,25 +420,6 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
 	return rec;
 }
 
-static bool mask_raw_tp_reg_cond(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) {
-	return reg->type == (PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL) &&
-	       bpf_prog_is_raw_tp(env->prog) && !reg->ref_obj_id;
-}
-
-static bool mask_raw_tp_reg(const struct bpf_verifier_env *env, struct bpf_reg_state *reg)
-{
-	if (!mask_raw_tp_reg_cond(env, reg))
-		return false;
-	reg->type &= ~PTR_MAYBE_NULL;
-	return true;
-}
-
-static void unmask_raw_tp_reg(struct bpf_reg_state *reg, bool result)
-{
-	if (result)
-		reg->type |= PTR_MAYBE_NULL;
-}
-
 static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog)
 {
 	struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux;
@@ -2597,16 +2578,36 @@ static int cmp_subprogs(const void *a, const void *b)
 	       ((struct bpf_subprog_info *)b)->start;
 }
 
+/* Find subprogram that contains instruction at 'off' */
+static struct bpf_subprog_info *find_containing_subprog(struct bpf_verifier_env *env, int off)
+{
+	struct bpf_subprog_info *vals = env->subprog_info;
+	int l, r, m;
+
+	if (off >= env->prog->len || off < 0 || env->subprog_cnt == 0)
+		return NULL;
+
+	l = 0;
+	r = env->subprog_cnt - 1;
+	while (l < r) {
+		m = l + (r - l + 1) / 2;
+		if (vals[m].start <= off)
+			l = m;
+		else
+			r = m - 1;
+	}
+	return &vals[l];
+}
+
+/* Find subprogram that starts exactly at 'off' */
 static int find_subprog(struct bpf_verifier_env *env, int off)
 {
 	struct bpf_subprog_info *p;
 
-	p = bsearch(&off, env->subprog_info, env->subprog_cnt,
-		    sizeof(env->subprog_info[0]), cmp_subprogs);
-	if (!p)
+	p = find_containing_subprog(env, off);
+	if (!p || p->start != off)
 		return -ENOENT;
 	return p - env->subprog_info;
-
 }
 
 static int add_subprog(struct bpf_verifier_env *env, int off)
@@ -6781,7 +6782,6 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 	const char *field_name = NULL;
 	enum bpf_type_flag flag = 0;
 	u32 btf_id = 0;
-	bool mask;
 	int ret;
 
 	if (!env->allow_ptr_leaks) {
@@ -6853,21 +6853,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 
 	if (ret < 0)
 		return ret;
-	/* For raw_tp progs, we allow dereference of PTR_MAYBE_NULL
-	 * trusted PTR_TO_BTF_ID, these are the ones that are possibly
-	 * arguments to the raw_tp. Since internal checks in for trusted
-	 * reg in check_ptr_to_btf_access would consider PTR_MAYBE_NULL
-	 * modifier as problematic, mask it out temporarily for the
-	 * check. Don't apply this to pointers with ref_obj_id > 0, as
-	 * those won't be raw_tp args.
-	 *
-	 * We may end up applying this relaxation to other trusted
-	 * PTR_TO_BTF_ID with maybe null flag, since we cannot
-	 * distinguish PTR_MAYBE_NULL tagged for arguments vs normal
-	 * tagging, but that should expand allowed behavior, and not
-	 * cause regression for existing behavior.
-	 */
-	mask = mask_raw_tp_reg(env, reg);
+
 	if (ret != PTR_TO_BTF_ID) {
 		/* just mark; */
 
@@ -6928,13 +6914,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
 		clear_trusted_flags(&flag);
 	}
 
-	if (atype == BPF_READ && value_regno >= 0) {
+	if (atype == BPF_READ && value_regno >= 0)
 		mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag);
-		/* We've assigned a new type to regno, so don't undo masking. */
-		if (regno == value_regno)
-			mask = false;
-	}
-	unmask_raw_tp_reg(reg, mask);
 
 	return 0;
 }
@@ -7309,7 +7290,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else if (base_type(reg->type) == PTR_TO_BTF_ID &&
-		   (mask_raw_tp_reg_cond(env, reg) || !type_may_be_null(reg->type))) {
+		   !type_may_be_null(reg->type)) {
 		err = check_ptr_to_btf_access(env, regs, regno, off, size, t,
 					      value_regno);
 	} else if (reg->type == CONST_PTR_TO_MAP) {
@@ -9012,7 +8993,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	enum bpf_reg_type type = reg->type;
 	u32 *arg_btf_id = NULL;
 	int err = 0;
-	bool mask;
 
 	if (arg_type == ARG_DONTCARE)
 		return 0;
@@ -9053,11 +9033,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 	    base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK)
 		arg_btf_id = fn->arg_btf_id[arg];
 
-	mask = mask_raw_tp_reg(env, reg);
 	err = check_reg_type(env, regno, arg_type, arg_btf_id, meta);
+	if (err)
+		return err;
 
-	err = err ?: check_func_arg_reg_off(env, reg, regno, arg_type);
-	unmask_raw_tp_reg(reg, mask);
+	err = check_func_arg_reg_off(env, reg, regno, arg_type);
 	if (err)
 		return err;
 
@@ -9852,17 +9832,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 				return ret;
 		} else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) {
 			struct bpf_call_arg_meta meta;
-			bool mask;
 			int err;
 
 			if (register_is_null(reg) && type_may_be_null(arg->arg_type))
 				continue;
 
 			memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */
-			mask = mask_raw_tp_reg(env, reg);
 			err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta);
 			err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type);
-			unmask_raw_tp_reg(reg, mask);
 			if (err)
 				return err;
 		} else {
@@ -10022,6 +9999,8 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 
 		verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
 			subprog, sub_name);
+		if (env->subprog_info[subprog].changes_pkt_data)
+			clear_all_pkt_pointers(env);
 		/* mark global subprog for verifying after main prog */
 		subprog_aux(env, subprog)->called = true;
 		clear_caller_saved_regs(env, caller->regs);
@@ -10708,7 +10687,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	}
 
 	/* With LD_ABS/IND some JITs save/restore skb from r1. */
-	changes_data = bpf_helper_changes_pkt_data(fn->func);
+	changes_data = bpf_helper_changes_pkt_data(func_id);
 	if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
 		verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
 			func_id_name(func_id), func_id);
@@ -12183,7 +12162,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 		enum bpf_arg_type arg_type = ARG_DONTCARE;
 		u32 regno = i + 1, ref_id, type_size;
 		bool is_ret_buf_sz = false;
-		bool mask = false;
 		int kf_arg_type;
 
 		t = btf_type_skip_modifiers(btf, args[i].type, NULL);
@@ -12242,15 +12220,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			return -EINVAL;
 		}
 
-		mask = mask_raw_tp_reg(env, reg);
 		if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) &&
 		    (register_is_null(reg) || type_may_be_null(reg->type)) &&
 			!is_kfunc_arg_nullable(meta->btf, &args[i])) {
 			verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i);
-			unmask_raw_tp_reg(reg, mask);
 			return -EACCES;
 		}
-		unmask_raw_tp_reg(reg, mask);
 
 		if (reg->ref_obj_id) {
 			if (is_kfunc_release(meta) && meta->ref_obj_id) {
@@ -12308,24 +12283,16 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta))
 				break;
 
-			/* Allow passing maybe NULL raw_tp arguments to
-			 * kfuncs for compatibility. Don't apply this to
-			 * arguments with ref_obj_id > 0.
-			 */
-			mask = mask_raw_tp_reg(env, reg);
 			if (!is_trusted_reg(reg)) {
 				if (!is_kfunc_rcu(meta)) {
 					verbose(env, "R%d must be referenced or trusted\n", regno);
-					unmask_raw_tp_reg(reg, mask);
 					return -EINVAL;
 				}
 				if (!is_rcu_reg(reg)) {
 					verbose(env, "R%d must be a rcu pointer\n", regno);
-					unmask_raw_tp_reg(reg, mask);
 					return -EINVAL;
 				}
 			}
-			unmask_raw_tp_reg(reg, mask);
 			fallthrough;
 		case KF_ARG_PTR_TO_CTX:
 		case KF_ARG_PTR_TO_DYNPTR:
@@ -12348,9 +12315,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 
 		if (is_kfunc_release(meta) && reg->ref_obj_id)
 			arg_type |= OBJ_RELEASE;
-		mask = mask_raw_tp_reg(env, reg);
 		ret = check_func_arg_reg_off(env, reg, regno, arg_type);
-		unmask_raw_tp_reg(reg, mask);
 		if (ret < 0)
 			return ret;
 
@@ -12527,7 +12492,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			ref_tname = btf_name_by_offset(btf, ref_t->name_off);
 			fallthrough;
 		case KF_ARG_PTR_TO_BTF_ID:
-			mask = mask_raw_tp_reg(env, reg);
 			/* Only base_type is checked, further checks are done here */
 			if ((base_type(reg->type) != PTR_TO_BTF_ID ||
 			     (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) &&
@@ -12536,11 +12500,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 				verbose(env, "expected %s or socket\n",
 					reg_type_str(env, base_type(reg->type) |
 							  (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS)));
-				unmask_raw_tp_reg(reg, mask);
 				return -EINVAL;
 			}
 			ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i);
-			unmask_raw_tp_reg(reg, mask);
 			if (ret < 0)
 				return ret;
 			break;
@@ -13513,7 +13475,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env,
  */
 static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 				   struct bpf_insn *insn,
-				   struct bpf_reg_state *ptr_reg,
+				   const struct bpf_reg_state *ptr_reg,
 				   const struct bpf_reg_state *off_reg)
 {
 	struct bpf_verifier_state *vstate = env->cur_state;
@@ -13527,7 +13489,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	struct bpf_sanitize_info info = {};
 	u8 opcode = BPF_OP(insn->code);
 	u32 dst = insn->dst_reg;
-	bool mask;
 	int ret;
 
 	dst_reg = &regs[dst];
@@ -13554,14 +13515,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 		return -EACCES;
 	}
 
-	mask = mask_raw_tp_reg(env, ptr_reg);
 	if (ptr_reg->type & PTR_MAYBE_NULL) {
 		verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
 			dst, reg_type_str(env, ptr_reg->type));
-		unmask_raw_tp_reg(ptr_reg, mask);
 		return -EACCES;
 	}
-	unmask_raw_tp_reg(ptr_reg, mask);
 
 	switch (base_type(ptr_reg->type)) {
 	case PTR_TO_CTX:
@@ -16226,6 +16184,29 @@ enforce_retval:
 	return 0;
 }
 
+static void mark_subprog_changes_pkt_data(struct bpf_verifier_env *env, int off)
+{
+	struct bpf_subprog_info *subprog;
+
+	subprog = find_containing_subprog(env, off);
+	subprog->changes_pkt_data = true;
+}
+
+/* 't' is an index of a call-site.
+ * 'w' is a callee entry point.
+ * Eventually this function would be called when env->cfg.insn_state[w] == EXPLORED.
+ * Rely on DFS traversal order and absence of recursive calls to guarantee that
+ * callee's change_pkt_data marks would be correct at that moment.
+ */
+static void merge_callee_effects(struct bpf_verifier_env *env, int t, int w)
+{
+	struct bpf_subprog_info *caller, *callee;
+
+	caller = find_containing_subprog(env, t);
+	callee = find_containing_subprog(env, w);
+	caller->changes_pkt_data |= callee->changes_pkt_data;
+}
+
 /* non-recursive DFS pseudo code
  * 1  procedure DFS-iterative(G,v):
  * 2      label v as discovered
@@ -16359,6 +16340,7 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 				bool visit_callee)
 {
 	int ret, insn_sz;
+	int w;
 
 	insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1;
 	ret = push_insn(t, t + insn_sz, FALLTHROUGH, env);
@@ -16370,8 +16352,10 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
 	mark_jmp_point(env, t + insn_sz);
 
 	if (visit_callee) {
+		w = t + insns[t].imm + 1;
 		mark_prune_point(env, t);
-		ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
+		merge_callee_effects(env, t, w);
+		ret = push_insn(t, w, BRANCH, env);
 	}
 	return ret;
 }
@@ -16688,6 +16672,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
 			mark_prune_point(env, t);
 			mark_jmp_point(env, t);
 		}
+		if (bpf_helper_call(insn) && bpf_helper_changes_pkt_data(insn->imm))
+			mark_subprog_changes_pkt_data(env, t);
 		if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
 			struct bpf_kfunc_call_arg_meta meta;
 
@@ -16822,6 +16808,7 @@ walk_cfg:
 		}
 	}
 	ret = 0; /* cfg looks good */
+	env->prog->aux->changes_pkt_data = env->subprog_info[0].changes_pkt_data;
 
 err_free:
 	kvfree(insn_state);
@@ -20075,7 +20062,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		 * for this case.
 		 */
 		case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
-		case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL:
 			if (type == BPF_READ) {
 				if (BPF_MODE(insn->code) == BPF_MEM)
 					insn->code = BPF_LDX | BPF_PROBE_MEM |
@@ -20311,6 +20297,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->num_exentries = num_exentries;
 		func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
 		func[i]->aux->exception_cb = env->subprog_info[i].is_exception_cb;
+		func[i]->aux->changes_pkt_data = env->subprog_info[i].changes_pkt_data;
 		if (!i)
 			func[i]->aux->exception_boundary = env->seen_exception;
 		func[i] = bpf_int_jit_compile(func[i]);
@@ -22141,6 +22128,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 	}
 	if (tgt_prog) {
 		struct bpf_prog_aux *aux = tgt_prog->aux;
+		bool tgt_changes_pkt_data;
 
 		if (bpf_prog_is_dev_bound(prog->aux) &&
 		    !bpf_prog_dev_bound_match(prog, tgt_prog)) {
@@ -22175,6 +22163,14 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 					"Extension programs should be JITed\n");
 				return -EINVAL;
 			}
+			tgt_changes_pkt_data = aux->func
+					       ? aux->func[subprog]->aux->changes_pkt_data
+					       : aux->changes_pkt_data;
+			if (prog->aux->changes_pkt_data && !tgt_changes_pkt_data) {
+				bpf_log(log,
+					"Extension program changes packet data, while original does not\n");
+				return -EINVAL;
+			}
 		}
 		if (!tgt_prog->jited) {
 			bpf_log(log, "Can attach to only JITed progs\n");
@@ -22640,10 +22636,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (ret < 0)
 		goto skip_full_check;
 
-	ret = check_attach_btf_id(env);
-	if (ret)
-		goto skip_full_check;
-
 	ret = resolve_pseudo_ldimm64(env);
 	if (ret < 0)
 		goto skip_full_check;
@@ -22658,6 +22650,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (ret < 0)
 		goto skip_full_check;
 
+	ret = check_attach_btf_id(env);
+	if (ret)
+		goto skip_full_check;
+
 	ret = mark_fastcall_patterns(env);
 	if (ret < 0)
 		goto skip_full_check;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 949a3870946c..1b8db5aee9d3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2250,6 +2250,9 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 		goto unlock;
 
 	old_array = bpf_event_rcu_dereference(event->tp_event->prog_array);
+	if (!old_array)
+		goto put;
+
 	ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array);
 	if (ret < 0) {
 		bpf_prog_array_delete_safe(old_array, event->prog);
@@ -2258,6 +2261,14 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 		bpf_prog_array_free_sleepable(old_array);
 	}
 
+put:
+	/*
+	 * It could be that the bpf_prog is not sleepable (and will be freed
+	 * via normal RCU), but is called from a point that supports sleepable
+	 * programs and uses tasks-trace-RCU.
+	 */
+	synchronize_rcu_tasks_trace();
+
 	bpf_prog_put(event->prog);
 	event->prog = NULL;
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index fed382b7881b..4875e7f5de3d 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1402,9 +1402,13 @@ static void __uprobe_perf_func(struct trace_uprobe *tu,
 
 #ifdef CONFIG_BPF_EVENTS
 	if (bpf_prog_array_valid(call)) {
+		const struct bpf_prog_array *array;
 		u32 ret;
 
-		ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run);
+		rcu_read_lock_trace();
+		array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held());
+		ret = bpf_prog_run_array_uprobe(array, regs, bpf_prog_run);
+		rcu_read_unlock_trace();
 		if (!ret)
 			return;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index 6625b3f563a4..21131ec25f24 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7899,42 +7899,37 @@ static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = {
 
 #endif /* CONFIG_INET */
 
-bool bpf_helper_changes_pkt_data(void *func)
-{
-	if (func == bpf_skb_vlan_push ||
-	    func == bpf_skb_vlan_pop ||
-	    func == bpf_skb_store_bytes ||
-	    func == bpf_skb_change_proto ||
-	    func == bpf_skb_change_head ||
-	    func == sk_skb_change_head ||
-	    func == bpf_skb_change_tail ||
-	    func == sk_skb_change_tail ||
-	    func == bpf_skb_adjust_room ||
-	    func == sk_skb_adjust_room ||
-	    func == bpf_skb_pull_data ||
-	    func == sk_skb_pull_data ||
-	    func == bpf_clone_redirect ||
-	    func == bpf_l3_csum_replace ||
-	    func == bpf_l4_csum_replace ||
-	    func == bpf_xdp_adjust_head ||
-	    func == bpf_xdp_adjust_meta ||
-	    func == bpf_msg_pull_data ||
-	    func == bpf_msg_push_data ||
-	    func == bpf_msg_pop_data ||
-	    func == bpf_xdp_adjust_tail ||
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
-	    func == bpf_lwt_seg6_store_bytes ||
-	    func == bpf_lwt_seg6_adjust_srh ||
-	    func == bpf_lwt_seg6_action ||
-#endif
-#ifdef CONFIG_INET
-	    func == bpf_sock_ops_store_hdr_opt ||
-#endif
-	    func == bpf_lwt_in_push_encap ||
-	    func == bpf_lwt_xmit_push_encap)
+bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_clone_redirect:
+	case BPF_FUNC_l3_csum_replace:
+	case BPF_FUNC_l4_csum_replace:
+	case BPF_FUNC_lwt_push_encap:
+	case BPF_FUNC_lwt_seg6_action:
+	case BPF_FUNC_lwt_seg6_adjust_srh:
+	case BPF_FUNC_lwt_seg6_store_bytes:
+	case BPF_FUNC_msg_pop_data:
+	case BPF_FUNC_msg_pull_data:
+	case BPF_FUNC_msg_push_data:
+	case BPF_FUNC_skb_adjust_room:
+	case BPF_FUNC_skb_change_head:
+	case BPF_FUNC_skb_change_proto:
+	case BPF_FUNC_skb_change_tail:
+	case BPF_FUNC_skb_pull_data:
+	case BPF_FUNC_skb_store_bytes:
+	case BPF_FUNC_skb_vlan_pop:
+	case BPF_FUNC_skb_vlan_push:
+	case BPF_FUNC_store_hdr_opt:
+	case BPF_FUNC_xdp_adjust_head:
+	case BPF_FUNC_xdp_adjust_meta:
+	case BPF_FUNC_xdp_adjust_tail:
+	/* tail-called program could call any of the above */
+	case BPF_FUNC_tail_call:
 		return true;
-
-	return false;
+	default:
+		return false;
+	}
 }
 
 const struct bpf_func_proto bpf_event_output_data_proto __weak;
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 78347d7d25ef..f1b9b3958792 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -159,6 +159,7 @@ static void sock_map_del_link(struct sock *sk,
 				verdict_stop = true;
 			list_del(&link->list);
 			sk_psock_free_link(link);
+			break;
 		}
 	}
 	spin_unlock_bh(&psock->link_lock);
@@ -411,12 +412,11 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key)
 static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test,
 			     struct sock **psk)
 {
-	struct sock *sk;
+	struct sock *sk = NULL;
 	int err = 0;
 
 	spin_lock_bh(&stab->lock);
-	sk = *psk;
-	if (!sk_test || sk_test == sk)
+	if (!sk_test || sk_test == *psk)
 		sk = xchg(psk, NULL);
 
 	if (likely(sk))
diff --git a/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c
new file mode 100644
index 000000000000..7526de379081
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "bpf/libbpf.h"
+#include "changes_pkt_data_freplace.skel.h"
+#include "changes_pkt_data.skel.h"
+#include <test_progs.h>
+
+static void print_verifier_log(const char *log)
+{
+	if (env.verbosity >= VERBOSE_VERY)
+		fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log);
+}
+
+static void test_aux(const char *main_prog_name,
+		     const char *to_be_replaced,
+		     const char *replacement,
+		     bool expect_load)
+{
+	struct changes_pkt_data_freplace *freplace = NULL;
+	struct bpf_program *freplace_prog = NULL;
+	struct bpf_program *main_prog = NULL;
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	struct changes_pkt_data *main = NULL;
+	char log[16*1024];
+	int err;
+
+	opts.kernel_log_buf = log;
+	opts.kernel_log_size = sizeof(log);
+	if (env.verbosity >= VERBOSE_SUPER)
+		opts.kernel_log_level = 1 | 2 | 4;
+	main = changes_pkt_data__open_opts(&opts);
+	if (!ASSERT_OK_PTR(main, "changes_pkt_data__open"))
+		goto out;
+	main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name);
+	if (!ASSERT_OK_PTR(main_prog, "main_prog"))
+		goto out;
+	bpf_program__set_autoload(main_prog, true);
+	err = changes_pkt_data__load(main);
+	print_verifier_log(log);
+	if (!ASSERT_OK(err, "changes_pkt_data__load"))
+		goto out;
+	freplace = changes_pkt_data_freplace__open_opts(&opts);
+	if (!ASSERT_OK_PTR(freplace, "changes_pkt_data_freplace__open"))
+		goto out;
+	freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement);
+	if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog"))
+		goto out;
+	bpf_program__set_autoload(freplace_prog, true);
+	bpf_program__set_autoattach(freplace_prog, true);
+	bpf_program__set_attach_target(freplace_prog,
+				       bpf_program__fd(main_prog),
+				       to_be_replaced);
+	err = changes_pkt_data_freplace__load(freplace);
+	print_verifier_log(log);
+	if (expect_load) {
+		ASSERT_OK(err, "changes_pkt_data_freplace__load");
+	} else {
+		ASSERT_ERR(err, "changes_pkt_data_freplace__load");
+		ASSERT_HAS_SUBSTR(log, "Extension program changes packet data", "error log");
+	}
+
+out:
+	changes_pkt_data_freplace__destroy(freplace);
+	changes_pkt_data__destroy(main);
+}
+
+/* There are two global subprograms in both changes_pkt_data.skel.h:
+ * - one changes packet data;
+ * - another does not.
+ * It is ok to freplace subprograms that change packet data with those
+ * that either do or do not. It is only ok to freplace subprograms
+ * that do not change packet data with those that do not as well.
+ * The below tests check outcomes for each combination of such freplace.
+ * Also test a case when main subprogram itself is replaced and is a single
+ * subprogram in a program.
+ */
+void test_changes_pkt_data_freplace(void)
+{
+	struct {
+		const char *main;
+		const char *to_be_replaced;
+		bool changes;
+	} mains[] = {
+		{ "main_with_subprogs",   "changes_pkt_data",         true },
+		{ "main_with_subprogs",   "does_not_change_pkt_data", false },
+		{ "main_changes",         "main_changes",             true },
+		{ "main_does_not_change", "main_does_not_change",     false },
+	};
+	struct {
+		const char *func;
+		bool changes;
+	} replacements[] = {
+		{ "changes_pkt_data",         true },
+		{ "does_not_change_pkt_data", false }
+	};
+	char buf[64];
+
+	for (int i = 0; i < ARRAY_SIZE(mains); ++i) {
+		for (int j = 0; j < ARRAY_SIZE(replacements); ++j) {
+			snprintf(buf, sizeof(buf), "%s_with_%s",
+				 mains[i].to_be_replaced, replacements[j].func);
+			if (!test__start_subtest(buf))
+				continue;
+			test_aux(mains[i].main, mains[i].to_be_replaced, replacements[j].func,
+				 mains[i].changes || !replacements[j].changes);
+		}
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
index 6fa19449297e..43676a9922dc 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
@@ -3,11 +3,14 @@
 
 #include <test_progs.h>
 #include "raw_tp_null.skel.h"
+#include "raw_tp_null_fail.skel.h"
 
 void test_raw_tp_null(void)
 {
 	struct raw_tp_null *skel;
 
+	RUN_TESTS(raw_tp_null_fail);
+
 	skel = raw_tp_null__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "raw_tp_null__open_and_load"))
 		return;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index fdff0652d7ef..248754296d97 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -934,8 +934,10 @@ static void test_sockmap_same_sock(void)
 
 	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
 	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
-	if (err)
+	if (err) {
+		close(tcp);
 		goto out;
+	}
 
 	for (i = 0; i < 2; i++) {
 		err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY);
@@ -954,14 +956,14 @@ static void test_sockmap_same_sock(void)
 		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
 	}
 
+	close(tcp);
 	err = bpf_map_delete_elem(map, &zero);
-	ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	ASSERT_ERR(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);
 }
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data.c b/tools/testing/selftests/bpf/progs/changes_pkt_data.c
new file mode 100644
index 000000000000..43cada48b28a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/changes_pkt_data.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__noinline
+long changes_pkt_data(struct __sk_buff *sk)
+{
+	return bpf_skb_pull_data(sk, 0);
+}
+
+__noinline __weak
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+SEC("?tc")
+int main_with_subprogs(struct __sk_buff *sk)
+{
+	changes_pkt_data(sk);
+	does_not_change_pkt_data(sk);
+	return 0;
+}
+
+SEC("?tc")
+int main_changes(struct __sk_buff *sk)
+{
+	bpf_skb_pull_data(sk, 0);
+	return 0;
+}
+
+SEC("?tc")
+int main_does_not_change(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c
new file mode 100644
index 000000000000..f9a622705f1b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("?freplace")
+long changes_pkt_data(struct __sk_buff *sk)
+{
+	return bpf_skb_pull_data(sk, 0);
+}
+
+SEC("?freplace")
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null.c b/tools/testing/selftests/bpf/progs/raw_tp_null.c
index 457f34c151e3..5927054b6dd9 100644
--- a/tools/testing/selftests/bpf/progs/raw_tp_null.c
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null.c
@@ -3,6 +3,7 @@
 
 #include <vmlinux.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -17,16 +18,14 @@ int BPF_PROG(test_raw_tp_null, struct sk_buff *skb)
 	if (task->pid != tid)
 		return 0;
 
-	i = i + skb->mark + 1;
-	/* The compiler may move the NULL check before this deref, which causes
-	 * the load to fail as deref of scalar. Prevent that by using a barrier.
+	/* If dead code elimination kicks in, the increment +=2 will be
+	 * removed. For raw_tp programs attaching to tracepoints in kernel
+	 * modules, we mark input arguments as PTR_MAYBE_NULL, so branch
+	 * prediction should never kick in.
 	 */
-	barrier();
-	/* If dead code elimination kicks in, the increment below will
-	 * be removed. For raw_tp programs, we mark input arguments as
-	 * PTR_MAYBE_NULL, so branch prediction should never kick in.
-	 */
-	if (!skb)
-		i += 2;
+	asm volatile ("%[i] += 1; if %[ctx] != 0 goto +1; %[i] += 2;"
+			: [i]"+r"(i)
+			: [ctx]"r"(skb)
+			: "memory");
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
new file mode 100644
index 000000000000..38d669957bf1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Ensure module parameter has PTR_MAYBE_NULL */
+SEC("tp_btf/bpf_testmod_test_raw_tp_null")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_bpf_testmod_test_raw_tp_null_arg_1(void *ctx) {
+    asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
+    return 0;
+}
+
+/* Check NULL marking */
+SEC("tp_btf/sched_pi_setprio")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_sched_pi_setprio_arg_2(void *ctx) {
+    asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
+    return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
index d1a57f7d09bd..fe6249d99b31 100644
--- a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
@@ -11,6 +11,8 @@ int subprog_tc(struct __sk_buff *skb)
 
 	__sink(skb);
 	__sink(ret);
+	/* let verifier know that 'subprog_tc' can change pointers to skb->data */
+	bpf_skb_change_proto(skb, 0, 0);
 	return ret;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
index 5aaf2b065f86..bba3e37f749b 100644
--- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
+++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
@@ -7,11 +7,7 @@
 #include "bpf_misc.h"
 
 SEC("tp_btf/bpf_testmod_test_nullable_bare")
-/* This used to be a failure test, but raw_tp nullable arguments can now
- * directly be dereferenced, whether they have nullable annotation or not,
- * and don't need to be explicitly checked.
- */
-__success
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
 int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx)
 {
 	return nullable_ctx->len;
diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
index a570e48b917a..28b939572cda 100644
--- a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
@@ -11,7 +11,7 @@ __success __retval(0)
 __naked void btf_ctx_access_accept(void)
 {
 	asm volatile ("					\
-	r2 = *(u32*)(r1 + 8);		/* load 2nd argument value (int pointer) */\
+	r2 = *(u64 *)(r1 + 8);		/* load 2nd argument value (int pointer) */\
 	r0 = 0;						\
 	exit;						\
 "	::: __clobber_all);
@@ -23,7 +23,43 @@ __success __retval(0)
 __naked void ctx_access_u32_pointer_accept(void)
 {
 	asm volatile ("					\
-	r2 = *(u32*)(r1 + 0);		/* load 1nd argument value (u32 pointer) */\
+	r2 = *(u64 *)(r1 + 0);		/* load 1nd argument value (u32 pointer) */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u32")
+__failure __msg("size 4 must be 8")
+__naked void ctx_access_u32_pointer_reject_32(void)
+{
+	asm volatile ("					\
+	r2 = *(u32 *)(r1 + 0);		/* load 1st argument with narrow load */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u16")
+__failure __msg("size 2 must be 8")
+__naked void ctx_access_u32_pointer_reject_16(void)
+{
+	asm volatile ("					\
+	r2 = *(u16 *)(r1 + 0);		/* load 1st argument with narrow load */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u8")
+__failure __msg("size 1 must be 8")
+__naked void ctx_access_u32_pointer_reject_8(void)
+{
+	asm volatile ("					\
+	r2 = *(u8 *)(r1 + 0);		/* load 1st argument with narrow load */\
 	r0 = 0;						\
 	exit;						\
 "	::: __clobber_all);
diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c
index ec79cbcfde91..87e51a215558 100644
--- a/tools/testing/selftests/bpf/progs/verifier_d_path.c
+++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c
@@ -11,7 +11,7 @@ __success __retval(0)
 __naked void d_path_accept(void)
 {
 	asm volatile ("					\
-	r1 = *(u32*)(r1 + 0);				\
+	r1 = *(u64 *)(r1 + 0);				\
 	r2 = r10;					\
 	r2 += -8;					\
 	r6 = 0;						\
@@ -31,7 +31,7 @@ __failure __msg("helper call is not allowed in probe")
 __naked void d_path_reject(void)
 {
 	asm volatile ("					\
-	r1 = *(u32*)(r1 + 0);				\
+	r1 = *(u64 *)(r1 + 0);				\
 	r2 = r10;					\
 	r2 += -8;					\
 	r6 = 0;						\
diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c
index d3e70e38e442..0d5e56dffabb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sock.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sock.c
@@ -50,6 +50,13 @@ struct {
 	__uint(map_flags, BPF_F_NO_PREALLOC);
 } sk_storage_map SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
 SEC("cgroup/skb")
 __description("skb->sk: no NULL check")
 __failure __msg("invalid mem access 'sock_common_or_null'")
@@ -1037,4 +1044,53 @@ __naked void sock_create_read_src_port(void)
 	: __clobber_all);
 }
 
+__noinline
+long skb_pull_data2(struct __sk_buff *sk, __u32 len)
+{
+	return bpf_skb_pull_data(sk, len);
+}
+
+__noinline
+long skb_pull_data1(struct __sk_buff *sk, __u32 len)
+{
+	return skb_pull_data2(sk, len);
+}
+
+/* global function calls bpf_skb_pull_data(), which invalidates packet
+ * pointers established before global function call.
+ */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_from_global_func(struct __sk_buff *sk)
+{
+	int *p = (void *)(long)sk->data;
+
+	if ((void *)(p + 1) > (void *)(long)sk->data_end)
+		return TCX_DROP;
+	skb_pull_data1(sk, 0);
+	*p = 42; /* this is unsafe */
+	return TCX_PASS;
+}
+
+__noinline
+int tail_call(struct __sk_buff *sk)
+{
+	bpf_tail_call_static(sk, &jmp_table, 0);
+	return 0;
+}
+
+/* Tail calls invalidate packet pointers. */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk)
+{
+	int *p = (void *)(long)sk->data;
+
+	if ((void *)(p + 1) > (void *)(long)sk->data_end)
+		return TCX_DROP;
+	tail_call(sk);
+	*p = 42; /* this is unsafe */
+	return TCX_PASS;
+}
+
 char _license[] SEC("license") = "GPL";