fs/epoll: Remove unnecessary wakeups of nested epoll that in ET mode
PATCH RESEND v3 1/1 fs/epoll: Remove unnecessary wakeups of nested epoll that in ET mode
From: Heiher <[email protected]>
Take the case where we have:
t0
| (ew)
e0
| (et)
e1
| (lt)
s0t0: thread 0
e0: epoll fd 0
e1: epoll fd 1
s0: socket fd 0
ew: epoll_wait
et: edge-trigger
lt: level-trigger
When s0 fires an event, e1 catches the event, and then e0 catches an event from e1. After this, There is a thread t0 do epoll_wait() many times on e0, it should only get one event in total, because e1 is a dded to e0 in edge-triggered mode.
This patch only allows wakeup(&ep->poll_wait) in ep_scan_ready_list if one of the conditions is met:
1. depth == 0.
2. There have event is added to ep->ovflist during processing.
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
--- fs/eventpoll.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)
fs/eventpoll.c +14 -2
@@ -685,6 +685,9 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep,if (!ep_locked)mutex_lock_nested (&ep->mtx, depth); +if (!depth ||list_empty_careful (&ep->rdllist)) + pwake++; +/* * Steal the ready list, and re-init the original one to the * empty list. Also, set ep->ovflist to NULL so that events
@@ -704,12 +707,21 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep, res = (*sproc)(ep, &txlist, priv);write_lock_irq (&ep->lock); + nepi =READ_ONCE (ep->ovflist); +/* +* We only need to wakeup nested epoll fds if something has been queued +* to the overflow list, since the ep_poll() traverses the rdllist +* during recursive poll and thus events on the overflow list may not be +* visible yet. +*/ +if (nepi !=NULL ) + pwake++;/* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ -for (nepi =READ_ONCE (ep->ovflist); (epi = nepi) !=NULL ; +for (; (epi = nepi) !=NULL ; nepi = epi->next, epi->next =EP_UNACTIVE_PTR ) {/* * We need to check if the item is already in the list.
@@ -755,7 +767,7 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep,mutex_unlock (&ep->mtx);/* We have to call this outside the lock */ -if (pwake) +if (pwake ==2 )ep_poll_safewake (&ep->poll_wait);return res;
Signature · 1 line
2.23.0