epoll: eliminate unnecessary lock for zero timeout
We call ep_events_available() under lock when timeout is 0, and then call
it without locks in the loop for the other cases.
Instead, call ep_events_available() without lock for all cases. For
non-zero timeouts, we will recheck after adding the thread to the wait
queue. For zero timeout cases, by definition, user is opportunistically
polling and will have to call epoll_wait again in the future.
Note that this lock was kept in c5a282e9635e9 because the whole loop was
historically under lock.
This patch results in a 1% CPU/RPC reduction in RPC benchmarks.
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Soheil Hassas Yeganeh <[email protected]>
Suggested-by: Eric Dumazet <[email protected]>
Reviewed-by: Eric Dumazet <[email protected]>
Reviewed-by: Willem de Bruijn <[email protected]>
Reviewed-by: Khazhismel Kumykov <[email protected]>
Cc: Guantao Liu <[email protected]>
Cc: Linus Torvalds <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1e0030c..9efb553 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1743,7 +1743,7 @@ static inline struct timespec64 ep_set_mstimeout(long ms)
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
- int res, eavail = 0, timed_out = 0;
+ int res, eavail, timed_out = 0;
u64 slack = 0;
wait_queue_entry_t wait;
ktime_t expires, *to = NULL;
@@ -1759,18 +1759,21 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
} else if (timeout == 0) {
/*
* Avoid the unnecessary trip to the wait queue loop, if the
- * caller specified a non blocking operation. We still need
- * lock because we could race and not see an epi being added
- * to the ready list while in irq callback. Thus incorrectly
- * returning 0 back to userspace.
+ * caller specified a non blocking operation.
*/
timed_out = 1;
-
- write_lock_irq(&ep->lock);
- eavail = ep_events_available(ep);
- write_unlock_irq(&ep->lock);
}
+ /*
+ * This call is racy: We may or may not see events that are being added
+ * to the ready list under the lock (e.g., in IRQ callbacks). For, cases
+ * with a non-zero timeout, this thread will check the ready list under
+ * lock and will added to the wait queue. For, cases with a zero
+ * timeout, the user by definition should not care and will have to
+ * recheck again.
+ */
+ eavail = ep_events_available(ep);
+
while (1) {
if (eavail) {
/*
@@ -1786,10 +1789,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
if (timed_out)
return 0;
- eavail = ep_events_available(ep);
- if (eavail)
- continue;
-
eavail = ep_busy_loop(ep, timed_out);
if (eavail)
continue;
