diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a1435b019aca..edd43edb27d6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2042,6 +2042,8 @@ static inline bool has_current_bpf_ctx(void)
 {
 	return !!current->bpf_ctx;
 }
+
+void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog);
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -2264,6 +2266,10 @@ static inline bool has_current_bpf_ctx(void)
 {
 	return false;
 }
+
+static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog)
+{
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index dab156f09f8d..372fad5ef3d3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2093,6 +2093,17 @@ struct bpf_prog_kstats {
 	u64 misses;
 };
 
+void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog)
+{
+	struct bpf_prog_stats *stats;
+	unsigned int flags;
+
+	stats = this_cpu_ptr(prog->stats);
+	flags = u64_stats_update_begin_irqsave(&stats->syncp);
+	u64_stats_inc(&stats->misses);
+	u64_stats_update_end_irqrestore(&stats->syncp, flags);
+}
+
 static void bpf_prog_get_stats(const struct bpf_prog *prog,
 			       struct bpf_prog_kstats *stats)
 {
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index ad76940b02cc..41b67eb83ab3 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -863,17 +863,6 @@ static __always_inline u64 notrace bpf_prog_start_time(void)
 	return start;
 }
 
-static void notrace inc_misses_counter(struct bpf_prog *prog)
-{
-	struct bpf_prog_stats *stats;
-	unsigned int flags;
-
-	stats = this_cpu_ptr(prog->stats);
-	flags = u64_stats_update_begin_irqsave(&stats->syncp);
-	u64_stats_inc(&stats->misses);
-	u64_stats_update_end_irqrestore(&stats->syncp, flags);
-}
-
 /* The logic is similar to bpf_prog_run(), but with an explicit
  * rcu_read_lock() and migrate_disable() which are required
  * for the trampoline. The macro is split into
@@ -896,7 +885,7 @@ u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *ru
 	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
 
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
-		inc_misses_counter(prog);
+		bpf_prog_inc_misses_counter(prog);
 		return 0;
 	}
 	return bpf_prog_start_time();
@@ -967,7 +956,7 @@ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_r
 	might_fault();
 
 	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
-		inc_misses_counter(prog);
+		bpf_prog_inc_misses_counter(prog);
 		return 0;
 	}
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 9df53c40cffd..b05f0310dbd3 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2222,9 +2222,15 @@ static __always_inline
 void __bpf_trace_run(struct bpf_prog *prog, u64 *args)
 {
 	cant_sleep();
+	if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
+		bpf_prog_inc_misses_counter(prog);
+		goto out;
+	}
 	rcu_read_lock();
 	(void) bpf_prog_run(prog, args);
 	rcu_read_unlock();
+out:
+	this_cpu_dec(*(prog->active));
 }
 
 #define UNPACK(...)			__VA_ARGS__