From 339ddb53d373baee6e7946aec17c739c4924d6d9 Mon Sep 17 00:00:00 2001
From: Heiher <r@hev.cc>
Date: Wed, 4 Dec 2019 16:52:15 -0800
Subject: [PATCH] fs/epoll: remove unnecessary wakeups of nested epoll
Git-commit: 339ddb53d373baee6e7946aec17c739c4924d6d9
Patch-mainline: v5.5-rc1
References: bsc#1159867
Take the case where we have:
t0
| (ew)
e0
| (et)
e1
| (lt)
s0
T0: thread 0
E0: epoll fd 0
E1: epoll fd 1
S0: socket fd 0
Ew: epoll_wait
Et: edge-trigger
Lt: level-trigger
We remove unnecessary wakeups to prevent the nested epoll that working in edge-
triggered mode to waking up continuously.
Test code:
#include <unistd.h>
#include <sys/epoll.h>
#include <sys/socket.h>
int main(int argc, char *argv[])
{
int sfd[2];
int efd[2];
struct epoll_event e;
if (socketpair(AF_UNIX, SOCK_STREAM, 0, sfd) < 0)
goto out;
efd[0] = epoll_create(1);
if (efd[0] < 0)
goto out;
efd[1] = epoll_create(1);
if (efd[1] < 0)
goto out;
e.events = EPOLLIN;
if (epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e) < 0)
goto out;
e.events = EPOLLIN | EPOLLET;
if (epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e) < 0)
goto out;
if (write(sfd[1], "w", 1) != 1)
goto out;
if (epoll_wait(efd[0], &e, 1, 0) != 1)
goto out;
if (epoll_wait(efd[0], &e, 1, 0) != 0)
goto out;
close(efd[0]);
close(efd[1]);
close(sfd[0]);
close(sfd[1]);
return 0;
out:
return -1;
}
More tests:
https://github.com/heiher/epoll-wakeup
Link: http://lkml.kernel.org/r/20191009060516.3577-1-r@hev.cc
Signed-off-by: hev <r@hev.cc>
Reviewed-by: Roman Penyaev <rpenyaev@suse.de>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Eric Wong <e@80x24.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Sridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
fs/eventpoll.c | 16 ----------------
1 file changed, 16 deletions(-)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 98ef0e2f1b5c..67a395039268 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -666,7 +666,6 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep,
void *priv, int depth, bool ep_locked)
{
__poll_t res;
- int pwake = 0;
struct epitem *epi, *nepi;
LIST_HEAD(txlist);
@@ -733,26 +732,11 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep,
*/
list_splice(&txlist, &ep->rdllist);
__pm_relax(ep->ws);
-
- if (!list_empty(&ep->rdllist)) {
- /*
- * Wake up (if active) both the eventpoll wait list and
- * the ->poll() wait list (delayed after we release the lock).
- */
- if (waitqueue_active(&ep->wq))
- wake_up(&ep->wq);
- if (waitqueue_active(&ep->poll_wait))
- pwake++;
- }
write_unlock_irq(&ep->lock);
if (!ep_locked)
mutex_unlock(&ep->mtx);
- /* We have to call this outside the lock */
- if (pwake)
- ep_poll_safewake(&ep->poll_wait);
-
return res;
}
--
2.16.4