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 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.
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 <v...@zeniv.linux.org.uk>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: Davide Libenzi <davi...@xmailserver.org>
Cc: Davidlohr Bueso <d...@stgolabs.net>
Cc: Dominik Brodowski <li...@dominikbrodowski.net>
Cc: Eric Wong <e...@80x24.org>
Cc: Jason Baron <jba...@akamai.com>
Cc: Linus Torvalds <torva...@linux-foundation.org>
Cc: Roman Penyaev <rpeny...@suse.de>
Cc: Sridhar Samudrala <sridhar.samudr...@intel.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-fsde...@vger.kernel.org
Signed-off-by: hev <r...@hev.cc>
---
fs/eventpoll.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index c4159bcc05d9..a0c07f6653c6 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -704,12 +704,21 @@ 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 +764,7 @@ 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;
--
2.23.0
