tracepoint: Use rcu get state and cond sync for static call updates

State transitions from 1->0->1 and N->2->1 callbacks require RCU
synchronization. Rather than performing the RCU synchronization every
time the state change occurs, which is quite slow when many tracepoints
are registered in batch, instead keep a snapshot of the RCU state on the
most recent transitions which belong to a chain, and conditionally wait
for a grace period on the last transition of the chain if one g.p. has
not elapsed since the last snapshot.

This applies to both RCU and SRCU.

This brings the performance regression caused by commit 231264d
("Fix: tracepoint: static call function vs data state mismatch") back to
what it was originally.

Before this commit:

  # trace-cmd start -e all
  # time trace-cmd start -p nop

  real	0m10.593s
  user	0m0.017s
  sys	0m0.259s

After this commit:

  # trace-cmd start -e all
  # time trace-cmd start -p nop

  real	0m0.878s
  user	0m0.000s
  sys	0m0.103s

Link: https://lkml.kernel.org/r/[email protected]
Link: https://lore.kernel.org/io-uring/[email protected]/

Cc: [email protected]
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: "Paul E. McKenney" <[email protected]>
Cc: Stefan Metzmacher <[email protected]>
Fixes: 231264d ("Fix: tracepoint: static call function vs data state mismatch")
Signed-off-by: Mathieu Desnoyers <[email protected]>
Reviewed-by: Paul E. McKenney <[email protected]>
Signed-off-by: Steven Rostedt (VMware) <[email protected]>

kernel/tracepoint.c

@@ -28,6 +28,44 @@ extern tracepoint_ptr_t __stop___tracepoints_ptrs[];
 DEFINE_SRCU(tracepoint_srcu);
 EXPORT_SYMBOL_GPL(tracepoint_srcu);
 
+enum tp_transition_sync {
+	TP_TRANSITION_SYNC_1_0_1,
+	TP_TRANSITION_SYNC_N_2_1,
+
+	_NR_TP_TRANSITION_SYNC,
+};
+
+struct tp_transition_snapshot {
+	unsigned long rcu;
+	unsigned long srcu;
+	bool ongoing;
+};
+
+/* Protected by tracepoints_mutex */
+static struct tp_transition_snapshot tp_transition_snapshot[_NR_TP_TRANSITION_SYNC];
+
+static void tp_rcu_get_state(enum tp_transition_sync sync)
+{
+	struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync];
+
+	/* Keep the latest get_state snapshot. */
+	snapshot->rcu = get_state_synchronize_rcu();
+	snapshot->srcu = start_poll_synchronize_srcu(&tracepoint_srcu);
+	snapshot->ongoing = true;
+}
+
+static void tp_rcu_cond_sync(enum tp_transition_sync sync)
+{
+	struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync];
+
+	if (!snapshot->ongoing)
+		return;
+	cond_synchronize_rcu(snapshot->rcu);
+	if (!poll_state_synchronize_srcu(&tracepoint_srcu, snapshot->srcu))
+		synchronize_srcu(&tracepoint_srcu);
+	snapshot->ongoing = false;
+}
+
 /* Set to 1 to enable tracepoint debug output */
 static const int tracepoint_debug;
 
@@ -311,6 +349,11 @@ static int tracepoint_add_func(struct tracepoint *tp,
 	 */
 	switch (nr_func_state(tp_funcs)) {
 	case TP_FUNC_1:		/* 0->1 */
+		/*
+		 * Make sure new static func never uses old data after a
+		 * 1->0->1 transition sequence.
+		 */
+		tp_rcu_cond_sync(TP_TRANSITION_SYNC_1_0_1);
 		/* Set static call to first function */
 		tracepoint_update_call(tp, tp_funcs);
 		/* Both iterator and static call handle NULL tp->funcs */
@@ -325,10 +368,15 @@ static int tracepoint_add_func(struct tracepoint *tp,
 		 * Requires ordering between RCU assign/dereference and
 		 * static call update/call.
 		 */
-		rcu_assign_pointer(tp->funcs, tp_funcs);
-		break;
+		fallthrough;
 	case TP_FUNC_N:		/* N->N+1 (N>1) */
 		rcu_assign_pointer(tp->funcs, tp_funcs);
+		/*
+		 * Make sure static func never uses incorrect data after a
+		 * N->...->2->1 (N>1) transition sequence.
+		 */
+		if (tp_funcs[0].data != old[0].data)
+			tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -372,31 +420,36 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 		/* 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.
+		 * Make sure new static func never uses old data after a
+		 * 1->0->1 transition sequence.
 		 */
-		tracepoint_synchronize_unregister();
+		tp_rcu_get_state(TP_TRANSITION_SYNC_1_0_1);
 		break;
 	case TP_FUNC_1:		/* 2->1 */
 		rcu_assign_pointer(tp->funcs, tp_funcs);
 		/*
-		 * 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.
+		 * Make sure static func never uses incorrect data after a
+		 * N->...->2->1 (N>2) transition sequence. If the first
+		 * element's data has changed, then force the synchronization
+		 * to prevent current readers that have loaded the old data
+		 * from calling the new function.
 		 */
-		tracepoint_synchronize_unregister();
+		if (tp_funcs[0].data != old[0].data)
+			tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+		tp_rcu_cond_sync(TP_TRANSITION_SYNC_N_2_1);
 		/* 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);
+		/*
+		 * Make sure static func never uses incorrect data after a
+		 * N->...->2->1 (N>2) transition sequence.
+		 */
+		if (tp_funcs[0].data != old[0].data)
+			tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
 		break;
 	default:
 		WARN_ON_ONCE(1);