[RESEND,v5] fs/epoll: Remove unnecessary wakeups of nested epoll
diff mbox series

Message ID 20191009060516.3577-1-r@hev.cc
State New
Headers show
Series
  • [RESEND,v5] fs/epoll: Remove unnecessary wakeups of nested epoll
Related show

Commit Message

Heiher Oct. 9, 2019, 6:05 a.m. UTC
From: Heiher <r@hev.cc>

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

Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
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: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Roman Penyaev <rpenyaev@suse.de>
Cc: Sridhar Samudrala <sridhar.samudrala@intel.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: hev <r@hev.cc>
---
 fs/eventpoll.c | 16 ----------------
 1 file changed, 16 deletions(-)

Comments

Roman Penyaev Oct. 9, 2019, 9:21 a.m. UTC | #1
On 2019-10-09 08:05, hev wrote:
> From: Heiher <r@hev.cc>
> 
> 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
> 
> Cc: Al Viro <viro@ZenIV.linux.org.uk>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> 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: Linus Torvalds <torvalds@linux-foundation.org>
> Cc: Roman Penyaev <rpenyaev@suse.de>
> Cc: Sridhar Samudrala <sridhar.samudrala@intel.com>
> Cc: linux-kernel@vger.kernel.org
> Cc: linux-fsdevel@vger.kernel.org
> Signed-off-by: hev <r@hev.cc>
> ---
>  fs/eventpoll.c | 16 ----------------
>  1 file changed, 16 deletions(-)
> 
> diff --git a/fs/eventpoll.c b/fs/eventpoll.c
> index c4159bcc05d9..75fccae100b5 100644
> --- a/fs/eventpoll.c
> +++ b/fs/eventpoll.c
> @@ -671,7 +671,6 @@ 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);
> 
> @@ -738,26 +737,11 @@ 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;
>  }

This looks good to me.  Heiher, mind to make kselftest out of your test 
suite?

Reviewed-by: Roman Penyaev <rpenyaev@suse.de>

--
Roman
Heiher Oct. 28, 2019, 12:58 a.m. UTC | #2
Hi,

On Wed, Oct 9, 2019 at 5:21 PM Roman Penyaev <rpenyaev@suse.de> wrote:
>
> On 2019-10-09 08:05, hev wrote:
> > From: Heiher <r@hev.cc>
> >
> > 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
> >
> > Cc: Al Viro <viro@ZenIV.linux.org.uk>
> > Cc: Andrew Morton <akpm@linux-foundation.org>
> > 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: Linus Torvalds <torvalds@linux-foundation.org>
> > Cc: Roman Penyaev <rpenyaev@suse.de>
> > Cc: Sridhar Samudrala <sridhar.samudrala@intel.com>
> > Cc: linux-kernel@vger.kernel.org
> > Cc: linux-fsdevel@vger.kernel.org
> > Signed-off-by: hev <r@hev.cc>
> > ---
> >  fs/eventpoll.c | 16 ----------------
> >  1 file changed, 16 deletions(-)
> >
> > diff --git a/fs/eventpoll.c b/fs/eventpoll.c
> > index c4159bcc05d9..75fccae100b5 100644
> > --- a/fs/eventpoll.c
> > +++ b/fs/eventpoll.c
> > @@ -671,7 +671,6 @@ 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);
> >
> > @@ -738,26 +737,11 @@ 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;
> >  }
>
> This looks good to me.  Heiher, mind to make kselftest out of your test
> suite?
>
> Reviewed-by: Roman Penyaev <rpenyaev@suse.de>
>
> --
> Roman
>
>
>

Need to back port this patch to stable branches?

Patch
diff mbox series

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index c4159bcc05d9..75fccae100b5 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -671,7 +671,6 @@  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);
 
@@ -738,26 +737,11 @@  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;
 }