diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e57af902560c..1d2676782d70 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1651,8 +1651,9 @@ static inline void bpf_trampoline_set_flags(struct bpf_trampoline *tr, u32 flags
 struct bpf_func_info_aux {
 	u16 linkage;
 	bool unreliable;
-	bool called : 1;
-	bool verified : 1;
+	/* Indexed by in_sleepable. */
+	bool called[2];
+	bool verified[2];
 };
 
 enum bpf_jit_poke_reason {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ddba53eaa333..5d7080c260d8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9931,6 +9931,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	if (err == -EFAULT)
 		return err;
 	if (bpf_subprog_is_global(env, subprog)) {
+		struct bpf_func_info_aux *sub_aux = subprog_aux(env, subprog);
 		const char *sub_name = bpf_subprog_name(env, subprog);
 		const char *operation;
 		bool returns_void;
@@ -9962,11 +9963,10 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		if (env->log.level & BPF_LOG_LEVEL)
 			verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
 				subprog, sub_name);
+		sub_aux->called[in_sleepable_context(env)] = true;
 		returns_void = subprog_returns_void(env, subprog);
 		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;
 		if (returns_void)
 			bpf_diag_record_scrub(env, &caller->regs[BPF_REG_0], BPF_DIAG_MOD_CALLER_SAVED);
 		else
@@ -10784,11 +10784,7 @@ int bpf_get_helper_proto(struct bpf_verifier_env *env, int func_id,
 /* Check if we're in a sleepable context. */
 static inline bool in_sleepable_context(struct bpf_verifier_env *env)
 {
-	return !env->cur_state->active_rcu_locks &&
-	       !env->cur_state->active_preempt_locks &&
-	       !env->cur_state->active_locks &&
-	       !env->cur_state->active_irq_id &&
-	       in_sleepable(env);
+	return !in_rcu_cs(env);
 }
 
 static const char *non_sleepable_context_description(struct bpf_verifier_env *env)
@@ -19447,13 +19443,14 @@ static void free_states(struct bpf_verifier_env *env)
 	}
 }
 
-static int do_check_common(struct bpf_verifier_env *env, int subprog)
+static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_sleepable)
 {
 	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
 	struct bpf_subprog_info *sub = subprog_info(env, subprog);
 	struct bpf_prog_aux *aux = env->prog->aux;
 	struct bpf_verifier_state *state;
 	struct bpf_reg_state *regs;
+	u32 old_insns_total = sub->insns_total;
 	u32 insn_processed = env->insn_processed;
 	int ret, i;
 
@@ -19466,7 +19463,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 	state->curframe = 0;
 	state->speculative = false;
 	state->branches = 1;
-	state->in_sleepable = env->prog->sleepable;
+	state->in_sleepable = is_sleepable;
 	state->frame[0] = kzalloc_obj(struct bpf_func_state, GFP_KERNEL_ACCOUNT);
 	if (!state->frame[0]) {
 		kfree(state);
@@ -19607,8 +19604,10 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 	 * not accounted as callees by account_current_path().
 	 * Accumulate their total counts as total counts of the main or
 	 * global subprog hosting the async call.
+	 * Start from the saved total of earlier contexts: adding to the current
+	 * total would count this pass's synchronous paths twice.
 	 */
-	env->subprog_info[subprog].insns_total = env->insn_processed - insn_processed;
+	sub->insns_total = old_insns_total + (env->insn_processed - insn_processed);
 	return ret;
 }
 
@@ -19636,14 +19635,19 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
 {
 	struct bpf_prog_aux *aux = env->prog->aux;
 	struct bpf_func_info_aux *sub_aux;
-	int i, ret, new_cnt;
+	int context, i, ret, new_cnt;
 
 	if (!aux->func_info)
 		return 0;
 
-	/* exception callback is presumed to be always called */
-	if (env->exception_callback_subprog)
-		subprog_aux(env, env->exception_callback_subprog)->called = true;
+	/*
+	 * Callbacks cannot throw, so the exception callback always runs in the
+	 * main program's context. It is presumed to be always called.
+	 */
+	if (env->exception_callback_subprog) {
+		sub_aux = subprog_aux(env, env->exception_callback_subprog);
+		sub_aux->called[env->prog->sleepable] = true;
+	}
 
 again:
 	new_cnt = 0;
@@ -19652,29 +19656,28 @@ static int do_check_subprogs(struct bpf_verifier_env *env)
 			continue;
 
 		sub_aux = subprog_aux(env, i);
-		if (!sub_aux->called || sub_aux->verified)
-			continue;
+		for (context = 0; context < ARRAY_SIZE(sub_aux->called); context++) {
+			if (!sub_aux->called[context] || sub_aux->verified[context])
+				continue;
 
-		env->insn_idx = env->subprog_info[i].start;
-		WARN_ON_ONCE(env->insn_idx == 0);
-		ret = do_check_common(env, i);
-		if (ret) {
-			return ret;
-		} else if (env->log.level & BPF_LOG_LEVEL) {
-			verbose(env, "Func#%d ('%s') is safe for any args that match its prototype\n",
-				i, bpf_subprog_name(env, i));
+			env->insn_idx = env->subprog_info[i].start;
+			WARN_ON_ONCE(env->insn_idx == 0);
+			ret = do_check_common(env, i, context);
+			if (ret)
+				return ret;
+			if (env->log.level & BPF_LOG_LEVEL)
+				verbose(env, "Func#%d ('%s') is safe for any args "
+					"that match its prototype\n",
+					i, bpf_subprog_name(env, i));
+
+			sub_aux->verified[context] = true;
+			new_cnt++;
 		}
-
-		/* We verified new global subprog, it might have called some
-		 * more global subprogs that we haven't verified yet, so we
-		 * need to do another pass over subprogs to verify those.
-		 */
-		sub_aux->verified = true;
-		new_cnt++;
 	}
 
-	/* We can't loop forever as we verify at least one global subprog on
-	 * each pass.
+	/*
+	 * We can't loop forever as each pass verifies at least one new context,
+	 * and there are only two contexts per global subprog.
 	 */
 	if (new_cnt)
 		goto again;
@@ -19687,7 +19690,7 @@ static int do_check_main(struct bpf_verifier_env *env)
 	int ret;
 
 	env->insn_idx = 0;
-	ret = do_check_common(env, 0);
+	ret = do_check_common(env, 0, env->prog->sleepable);
 	if (!ret)
 		env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return ret;
diff --git a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
index e0926767bbd3..1b653bfb63eb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
+++ b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
@@ -9,6 +9,11 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
 /* Timer tests */
 
 struct timer_elem {
@@ -164,6 +169,7 @@ int syscall_btf_find_prog(void *ctx)
 
 struct wq_elem {
 	struct bpf_wq w;
+	struct task_struct __kptr *task;
 };
 
 struct {
@@ -217,6 +223,106 @@ int wq_sleepable_prog(void *ctx)
 	return 0;
 }
 
+__noinline int wq_global_acquire(void)
+{
+	struct task_struct *task, *acquired;
+	struct wq_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	task = val->task;
+	if (!task)
+		return 0;
+
+	acquired = bpf_task_acquire(task);
+	if (acquired)
+		bpf_task_release(acquired);
+	return 0;
+}
+
+static int wq_global_rcu_cb(void *map, int *key, void *value)
+{
+	wq_global_acquire();
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__failure __msg("R1 must be a rcu pointer")
+int wq_global_rcu_prog(void *ctx)
+{
+	struct wq_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_wq_init(&val->w, &wq_map, 0);
+	bpf_wq_set_callback(&val->w, wq_global_rcu_cb, 0);
+	return 0;
+}
+
+static int wq_global_rcu_lock_cb(void *map, int *key, void *value)
+{
+	bpf_rcu_read_lock();
+	wq_global_acquire();
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__success
+int wq_global_rcu_lock_prog(void *ctx)
+{
+	struct wq_elem *val;
+	int key = 0;
+
+	/* Verify the same global subprog in non-sleepable and protected contexts. */
+	wq_global_acquire();
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_wq_init(&val->w, &wq_map, 0);
+	bpf_wq_set_callback(&val->w, wq_global_rcu_lock_cb, 0);
+	return 0;
+}
+
+__weak __noinline int wq_global_no_rcu(void)
+{
+	return 0;
+}
+
+static int wq_global_no_rcu_cb(void *map, int *key, void *value)
+{
+	wq_global_no_rcu();
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__success __log_level(4)
+__msg("subprog {{[0-9]+}} (wq_global_no_rcu) global insns_self 4 insns_total 4 stack 0")
+int wq_global_no_rcu_prog(void *ctx)
+{
+	struct wq_elem *val;
+	int key = 0;
+
+	/* Verify the same global in non-sleepable and unprotected contexts. */
+	wq_global_no_rcu();
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_wq_init(&val->w, &wq_map, 0);
+	bpf_wq_set_callback(&val->w, wq_global_no_rcu_cb, 0);
+	return 0;
+}
+
 /* Task work tests */
 
 struct task_work_elem {