The patch titled
Subject: epoll: simplify signal handling
has been added to the -mm tree. Its filename is
epoll-simplify-signal-handling.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/epoll-simplify-signal-handling.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/epoll-simplify-signal-handling.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Soheil Hassas Yeganeh <soheil@xxxxxxxxxx>
Subject: epoll: simplify signal handling
Check signals before locking ep->lock, and immediately return -EINTR if
there is any signal pending.
This saves a few loads, stores, and branches from the hot path and
simplifies the loop structure for follow up patches.
Link: https://lkml.kernel.org/r/20201106231635.3528496-3-soheil.kdev@xxxxxxxxx
Signed-off-by: Soheil Hassas Yeganeh <soheil@xxxxxxxxxx>
Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Reviewed-by: Willem de Bruijn <willemb@xxxxxxxxxx>
Reviewed-by: Khazhismel Kumykov <khazhy@xxxxxxxxxx>
Cc: Guantao Liu <guantaol@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/eventpoll.c | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
--- a/fs/eventpoll.c~epoll-simplify-signal-handling
+++ a/fs/eventpoll.c
@@ -1818,7 +1818,7 @@ static inline struct timespec64 ep_set_m
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
- int res = 0, eavail, timed_out = 0;
+ int res, eavail, timed_out = 0;
u64 slack = 0;
wait_queue_entry_t wait;
ktime_t expires, *to = NULL;
@@ -1865,6 +1865,9 @@ fetch_events:
ep_reset_busy_poll_napi_id(ep);
do {
+ if (signal_pending(current))
+ return -EINTR;
+
/*
* Internally init_wait() uses autoremove_wake_function(),
* thus wait entry is removed from the wait queue on each
@@ -1894,15 +1897,12 @@ fetch_events:
* important.
*/
eavail = ep_events_available(ep);
- if (!eavail) {
- if (signal_pending(current))
- res = -EINTR;
- else
- __add_wait_queue_exclusive(&ep->wq, &wait);
- }
+ if (!eavail)
+ __add_wait_queue_exclusive(&ep->wq, &wait);
+
write_unlock_irq(&ep->lock);
- if (!eavail && !res)
+ if (!eavail)
timed_out = !schedule_hrtimeout_range(to, slack,
HRTIMER_MODE_ABS);
@@ -1938,14 +1938,14 @@ send_events:
* finding more events available and fetching
* repeatedly.
*/
- res = -EINTR;
+ return -EINTR;
}
/*
* Try to transfer events to user space. In case we get 0 events and
* there's still timeout left over, we go trying again in search of
* more luck.
*/
- if (!res && eavail &&
+ if (eavail &&
!(res = ep_send_events(ep, events, maxevents)) && !timed_out)
goto fetch_events;
_
Patches currently in -mm which might be from soheil@xxxxxxxxxx are
epoll-check-for-events-when-removing-a-timed-out-thread-from-the-wait-queue.patch
epoll-simplify-signal-handling.patch
epoll-pull-fatal-signal-checks-into-ep_send_events.patch
epoll-move-eavail-next-to-the-list_empty_careful-check.patch
epoll-simplify-and-optimize-busy-loop-logic.patch
epoll-pull-all-code-between-fetch_events-and-send_event-into-the-loop.patch
epoll-replace-gotos-with-a-proper-loop.patch
epoll-eliminate-unnecessary-lock-for-zero-timeout.patch
