[PATCH 2/3] cgroup: add lockless fast-path checks to cgroup_file_notify()

[Shakeel Butt]

Add two lockless checks before acquiring the lock:

1. READ_ONCE(cfile->kn) NULL check to skip torn-down files.
2. READ_ONCE(cfile->notified_at) check to skip when within the
   rate-limit window (~10ms).

Both checks have safe error directions -- a stale read can only cause
unnecessary lock acquisition, never a missed notification.  Annotate
all write sites with WRITE_ONCE() to pair with the lockless readers.

The trade-off is that trailing timer_reduce() calls during bursts are
skipped, so the deferred notification that delivers the final state
may be lost.  This is acceptable for the primary callers like
__memcg_memory_event() where events keep arriving.

Signed-off-by: Shakeel Butt <shakeel.butt@xxxxxxxxx>
Reported-by: Jakub Kicinski <kuba@xxxxxxxxxx>
---
 kernel/cgroup/cgroup.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 33282c7d71e4..5473ebd0f6c1 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1749,7 +1749,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 		struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
 		spin_lock_irq(&cgroup_file_kn_lock);
-		cfile->kn = NULL;
+		WRITE_ONCE(cfile->kn, NULL);
 		spin_unlock_irq(&cgroup_file_kn_lock);
 
 		timer_delete_sync(&cfile->notify_timer);
@@ -4430,7 +4430,7 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 		timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0);
 
 		spin_lock_irq(&cgroup_file_kn_lock);
-		cfile->kn = kn;
+		WRITE_ONCE(cfile->kn, kn);
 		spin_unlock_irq(&cgroup_file_kn_lock);
 	}
 
@@ -4686,20 +4686,27 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
  */
 void cgroup_file_notify(struct cgroup_file *cfile)
 {
-	unsigned long flags;
+	unsigned long flags, last, next;
 	struct kernfs_node *kn = NULL;
 
+	if (!READ_ONCE(cfile->kn))
+		return;
+
+	last = READ_ONCE(cfile->notified_at);
+	if (time_before_eq(jiffies, last + CGROUP_FILE_NOTIFY_MIN_INTV))
+		return;
+
 	spin_lock_irqsave(&cgroup_file_kn_lock, flags);
 	if (cfile->kn) {
-		unsigned long last = cfile->notified_at;
-		unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV;
+		last = cfile->notified_at;
+		next = last + CGROUP_FILE_NOTIFY_MIN_INTV;
 
-		if (time_in_range(jiffies, last, next)) {
+		if (time_before_eq(jiffies, next)) {
 			timer_reduce(&cfile->notify_timer, next);
 		} else {
 			kn = cfile->kn;
 			kernfs_get(kn);
-			cfile->notified_at = jiffies;
+			WRITE_ONCE(cfile->notified_at, jiffies);
 		}
 	}
 	spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
-- 
2.47.3