diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 133b6454b287..8d772bd6894d 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -15,6 +15,13 @@
 #include <linux/sched/task.h>
 #include <linux/static_key.h>
 
+enum tp_func_state {
+	TP_FUNC_0,
+	TP_FUNC_1,
+	TP_FUNC_2,
+	TP_FUNC_N,
+};
+
 extern tracepoint_ptr_t __start___tracepoints_ptrs[];
 extern tracepoint_ptr_t __stop___tracepoints_ptrs[];
 
@@ -246,26 +253,29 @@ static void *func_remove(struct tracepoint_func **funcs,
 	return old;
 }
 
-static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs, bool sync)
+/*
+ * Count the number of functions (enum tp_func_state) in a tp_funcs array.
+ */
+static enum tp_func_state nr_func_state(const struct tracepoint_func *tp_funcs)
+{
+	if (!tp_funcs)
+		return TP_FUNC_0;
+	if (!tp_funcs[1].func)
+		return TP_FUNC_1;
+	if (!tp_funcs[2].func)
+		return TP_FUNC_2;
+	return TP_FUNC_N;	/* 3 or more */
+}
+
+static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs)
 {
 	void *func = tp->iterator;
 
 	/* Synthetic events do not have static call sites */
 	if (!tp->static_call_key)
 		return;
-
-	if (!tp_funcs[1].func) {
+	if (nr_func_state(tp_funcs) == TP_FUNC_1)
 		func = tp_funcs[0].func;
-		/*
-		 * If going from the iterator back to a single caller,
-		 * we need to synchronize with __DO_TRACE to make sure
-		 * that the data passed to the callback is the one that
-		 * belongs to that callback.
-		 */
-		if (sync)
-			tracepoint_synchronize_unregister();
-	}
-
 	__static_call_update(tp->static_call_key, tp->static_call_tramp, func);
 }
 
@@ -299,9 +309,31 @@ static int tracepoint_add_func(struct tracepoint *tp,
 	 * a pointer to it.  This array is referenced by __DO_TRACE from
 	 * include/linux/tracepoint.h using rcu_dereference_sched().
 	 */
-	tracepoint_update_call(tp, tp_funcs, false);
-	rcu_assign_pointer(tp->funcs, tp_funcs);
-	static_key_enable(&tp->key);
+	switch (nr_func_state(tp_funcs)) {
+	case TP_FUNC_1:		/* 0->1 */
+		/* Set static call to first function */
+		tracepoint_update_call(tp, tp_funcs);
+		/* Both iterator and static call handle NULL tp->funcs */
+		rcu_assign_pointer(tp->funcs, tp_funcs);
+		static_key_enable(&tp->key);
+		break;
+	case TP_FUNC_2:		/* 1->2 */
+		/* Set iterator static call */
+		tracepoint_update_call(tp, tp_funcs);
+		/*
+		 * Iterator callback installed before updating tp->funcs.
+		 * Requires ordering between RCU assign/dereference and
+		 * static call update/call.
+		 */
+		rcu_assign_pointer(tp->funcs, tp_funcs);
+		break;
+	case TP_FUNC_N:		/* N->N+1 (N>1) */
+		rcu_assign_pointer(tp->funcs, tp_funcs);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
 
 	release_probes(old);
 	return 0;
@@ -328,17 +360,47 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 		/* Failed allocating new tp_funcs, replaced func with stub */
 		return 0;
 
-	if (!tp_funcs) {
+	switch (nr_func_state(tp_funcs)) {
+	case TP_FUNC_0:		/* 1->0 */
 		/* Removed last function */
 		if (tp->unregfunc && static_key_enabled(&tp->key))
 			tp->unregfunc();
 
 		static_key_disable(&tp->key);
+		/* Set iterator static call */
+		tracepoint_update_call(tp, tp_funcs);
+		/* Both iterator and static call handle NULL tp->funcs */
+		rcu_assign_pointer(tp->funcs, NULL);
+		/*
+		 * Make sure new func never uses old data after a 1->0->1
+		 * transition sequence.
+		 * Considering that transition 0->1 is the common case
+		 * and don't have rcu-sync, issue rcu-sync after
+		 * transition 1->0 to break that sequence by waiting for
+		 * readers to be quiescent.
+		 */
+		tracepoint_synchronize_unregister();
+		break;
+	case TP_FUNC_1:		/* 2->1 */
 		rcu_assign_pointer(tp->funcs, tp_funcs);
-	} else {
+		/*
+		 * On 2->1 transition, RCU sync is needed before setting
+		 * static call to first callback, because the observer
+		 * may have loaded any prior tp->funcs after the last one
+		 * associated with an rcu-sync.
+		 */
+		tracepoint_synchronize_unregister();
+		/* Set static call to first function */
+		tracepoint_update_call(tp, tp_funcs);
+		break;
+	case TP_FUNC_2:		/* N->N-1 (N>2) */
+		fallthrough;
+	case TP_FUNC_N:
 		rcu_assign_pointer(tp->funcs, tp_funcs);
-		tracepoint_update_call(tp, tp_funcs,
-				       tp_funcs[0].data != old[0].data);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
 	}
 	release_probes(old);
 	return 0;