diff mbox series

[v2,2/4] epoll: loosen irq safety in ep_poll_callback()

Message ID 20190103150104.17128-3-rpenyaev@suse.de (mailing list archive)
State New, archived
Headers show
Series use rwlock in order to reduce ep_poll_callback() contention | expand

Commit Message

Roman Penyaev Jan. 3, 2019, 3:01 p.m. UTC 
Callers of the ep_poll_callback() (all set of wake_up_*poll()) disable
interrupts, so no need to save/restore irq flags.

Signed-off-by: Roman Penyaev <rpenyaev@suse.de>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 fs/eventpoll.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3627c2e07149..3c373a510f65 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1124,13 +1124,18 @@  struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
 static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	int pwake = 0;
-	unsigned long flags;
 	struct epitem *epi = ep_item_from_wait(wait);
 	struct eventpoll *ep = epi->ep;
 	__poll_t pollflags = key_to_poll(key);
 	int ewake = 0;
 
-	spin_lock_irqsave(&ep->wq.lock, flags);
+	/*
+	 * Called by irq context or interrupts are disabled by the wake_up_*poll
+	 * callers.
+	 */
+	lockdep_assert_irqs_disabled();
+
+	spin_lock(&ep->wq.lock);
 
 	ep_set_busy_poll_napi_id(epi);
 
@@ -1207,7 +1212,7 @@  static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 		pwake++;
 
 out_unlock:
-	spin_unlock_irqrestore(&ep->wq.lock, flags);
+	spin_unlock(&ep->wq.lock);
 
 	/* We have to call this outside the lock */
 	if (pwake)