diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 14134fd34ff7..0ce5f13eabb1 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1655,13 +1655,8 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
 	struct bpf_prog *p = l->link.prog;
 	int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
 
-	if (p->aux->sleepable) {
-		enter_prog = (u64)__bpf_prog_enter_sleepable;
-		exit_prog = (u64)__bpf_prog_exit_sleepable;
-	} else {
-		enter_prog = (u64)__bpf_prog_enter;
-		exit_prog = (u64)__bpf_prog_exit;
-	}
+	enter_prog = (u64)bpf_trampoline_enter(p);
+	exit_prog = (u64)bpf_trampoline_exit(p);
 
 	if (l->cookie == 0) {
 		/* if cookie is zero, one instruction is enough to store it */
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index db6053a22e86..5e680e039d0e 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1813,10 +1813,6 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			   struct bpf_tramp_link *l, int stack_size,
 			   int run_ctx_off, bool save_ret)
 {
-	void (*exit)(struct bpf_prog *prog, u64 start,
-		     struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit;
-	u64 (*enter)(struct bpf_prog *prog,
-		     struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter;
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
 	int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
@@ -1835,23 +1831,12 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	 */
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off);
 
-	if (p->aux->sleepable) {
-		enter = __bpf_prog_enter_sleepable;
-		exit = __bpf_prog_exit_sleepable;
-	} else if (p->type == BPF_PROG_TYPE_STRUCT_OPS) {
-		enter = __bpf_prog_enter_struct_ops;
-		exit = __bpf_prog_exit_struct_ops;
-	} else if (p->expected_attach_type == BPF_LSM_CGROUP) {
-		enter = __bpf_prog_enter_lsm_cgroup;
-		exit = __bpf_prog_exit_lsm_cgroup;
-	}
-
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
 	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
 	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
 
-	if (emit_call(&prog, enter, prog))
+	if (emit_call(&prog, bpf_trampoline_enter(p), prog))
 		return -EINVAL;
 	/* remember prog start time returned by __bpf_prog_enter */
 	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
@@ -1896,7 +1881,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
 	/* arg3: lea rdx, [rbp - run_ctx_off] */
 	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
-	if (emit_call(&prog, exit, prog))
+	if (emit_call(&prog, bpf_trampoline_exit(p), prog))
 		return -EINVAL;
 
 	*pprog = prog;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8cef9ec3a89c..b3d3aa8437dc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -862,22 +862,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_links *tlinks,
 				void *orig_call);
-/* these two functions are called from generated trampoline */
-u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx);
-u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
-void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
-				       struct bpf_tramp_run_ctx *run_ctx);
-u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
-					struct bpf_tramp_run_ctx *run_ctx);
-void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
-					struct bpf_tramp_run_ctx *run_ctx);
-u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog,
-					struct bpf_tramp_run_ctx *run_ctx);
-void notrace __bpf_prog_exit_struct_ops(struct bpf_prog *prog, u64 start,
-					struct bpf_tramp_run_ctx *run_ctx);
+u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
+					     struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
+					     struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
 void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
+typedef u64 (*bpf_trampoline_enter_t)(struct bpf_prog *prog,
+				      struct bpf_tramp_run_ctx *run_ctx);
+typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start,
+				      struct bpf_tramp_run_ctx *run_ctx);
+bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog);
+bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog);
 
 struct bpf_ksym {
 	unsigned long		 start;
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 0eb8f035b3d9..1a32baa78ce2 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -648,4 +648,17 @@ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog)
 		prog->aux->dst_prog->type : prog->type;
 }
 
+static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
+{
+	switch (resolve_prog_type(prog)) {
+	case BPF_PROG_TYPE_TRACING:
+		return prog->expected_attach_type != BPF_TRACE_ITER;
+	case BPF_PROG_TYPE_STRUCT_OPS:
+	case BPF_PROG_TYPE_LSM:
+		return false;
+	default:
+		return true;
+	}
+}
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0c44a716f0a2..7afec961c572 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5136,13 +5136,14 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
 
 		run_ctx.bpf_cookie = 0;
 		run_ctx.saved_run_ctx = NULL;
-		if (!__bpf_prog_enter_sleepable(prog, &run_ctx)) {
+		if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) {
 			/* recursion detected */
 			bpf_prog_put(prog);
 			return -EBUSY;
 		}
 		attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in);
-		__bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx);
+		__bpf_prog_exit_sleepable_recur(prog, 0 /* bpf_prog_run does runtime stats */,
+						&run_ctx);
 		bpf_prog_put(prog);
 		return 0;
 #endif
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 30af8f66e17b..88841e352dcd 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -874,7 +874,7 @@ static __always_inline u64 notrace bpf_prog_start_time(void)
  * [2..MAX_U64] - execute bpf prog and record execution time.
  *     This is start time.
  */
-u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
+static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
 	__acquires(RCU)
 {
 	rcu_read_lock();
@@ -911,7 +911,8 @@ static void notrace update_prog_stats(struct bpf_prog *prog,
 	}
 }
 
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx)
+static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start,
+					  struct bpf_tramp_run_ctx *run_ctx)
 	__releases(RCU)
 {
 	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
@@ -922,8 +923,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_
 	rcu_read_unlock();
 }
 
-u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
-					struct bpf_tramp_run_ctx *run_ctx)
+static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
+					       struct bpf_tramp_run_ctx *run_ctx)
 	__acquires(RCU)
 {
 	/* Runtime stats are exported via actual BPF_LSM_CGROUP
@@ -937,8 +938,8 @@ u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
 	return NO_START_TIME;
 }
 
-void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
-					struct bpf_tramp_run_ctx *run_ctx)
+static void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
+					       struct bpf_tramp_run_ctx *run_ctx)
 	__releases(RCU)
 {
 	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
@@ -947,7 +948,8 @@ void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
 	rcu_read_unlock();
 }
 
-u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx)
+u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
+					     struct bpf_tramp_run_ctx *run_ctx)
 {
 	rcu_read_lock_trace();
 	migrate_disable();
@@ -963,8 +965,8 @@ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_r
 	return bpf_prog_start_time();
 }
 
-void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
-				       struct bpf_tramp_run_ctx *run_ctx)
+void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
+					     struct bpf_tramp_run_ctx *run_ctx)
 {
 	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
 
@@ -974,8 +976,30 @@ void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
 	rcu_read_unlock_trace();
 }
 
-u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog,
-					struct bpf_tramp_run_ctx *run_ctx)
+static u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog,
+					      struct bpf_tramp_run_ctx *run_ctx)
+{
+	rcu_read_lock_trace();
+	migrate_disable();
+	might_fault();
+
+	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
+	return bpf_prog_start_time();
+}
+
+static void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
+					      struct bpf_tramp_run_ctx *run_ctx)
+{
+	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
+	update_prog_stats(prog, start);
+	migrate_enable();
+	rcu_read_unlock_trace();
+}
+
+static u64 notrace __bpf_prog_enter(struct bpf_prog *prog,
+				    struct bpf_tramp_run_ctx *run_ctx)
 	__acquires(RCU)
 {
 	rcu_read_lock();
@@ -986,8 +1010,8 @@ u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog,
 	return bpf_prog_start_time();
 }
 
-void notrace __bpf_prog_exit_struct_ops(struct bpf_prog *prog, u64 start,
-					struct bpf_tramp_run_ctx *run_ctx)
+static void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start,
+				    struct bpf_tramp_run_ctx *run_ctx)
 	__releases(RCU)
 {
 	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
@@ -1007,6 +1031,36 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr)
 	percpu_ref_put(&tr->pcref);
 }
 
+bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog)
+{
+	bool sleepable = prog->aux->sleepable;
+
+	if (bpf_prog_check_recur(prog))
+		return sleepable ? __bpf_prog_enter_sleepable_recur :
+			__bpf_prog_enter_recur;
+
+	if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM &&
+	    prog->expected_attach_type == BPF_LSM_CGROUP)
+		return __bpf_prog_enter_lsm_cgroup;
+
+	return sleepable ? __bpf_prog_enter_sleepable : __bpf_prog_enter;
+}
+
+bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog)
+{
+	bool sleepable = prog->aux->sleepable;
+
+	if (bpf_prog_check_recur(prog))
+		return sleepable ? __bpf_prog_exit_sleepable_recur :
+			__bpf_prog_exit_recur;
+
+	if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM &&
+	    prog->expected_attach_type == BPF_LSM_CGROUP)
+		return __bpf_prog_exit_lsm_cgroup;
+
+	return sleepable ? __bpf_prog_exit_sleepable : __bpf_prog_exit;
+}
+
 int __weak
 arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
 			    const struct btf_func_model *m, u32 flags,