2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-02 19:15:33 +01:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-03-23 03:00:32 -08:00
|
|
|
|
2007-05-10 22:23:21 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2016-12-24 11:46:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-07-26 16:09:06 -07:00
|
|
|
|
2012-12-17 16:05:02 -08:00
|
|
|
|
|
|
|
|
|
2013-02-24 14:52:17 -05:00
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
2017-03-24 10:08:30 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-03-23 03:00:32 -08:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-01-30 23:42:29 +02:00
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-10-31 17:13:14 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-03-23 03:00:32 -08:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-01-20 14:59:24 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
In the current implementation of the EPOLLEXCLUSIVE flag (added for
4.5-rc1), if epoll waiters create different POLL* sets and register them
as exclusive against the same target fd, the current implementation will
stop waking any further waiters once it finds the first idle waiter.
This means that waiters could miss wakeups in certain cases.
For example, when we wake up a pipe for reading we do:
wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); So if
one epoll set or epfd is added to pipe p with POLLIN and a second set
epfd2 is added to pipe p with POLLRDNORM, only epfd may receive the
wakeup since the current implementation will stop after it finds any
intersection of events with a waiter that is blocked in epoll_wait().
We could potentially address this by requiring all epoll waiters that
are added to p be required to pass the same set of POLL* events. IE the
first EPOLL_CTL_ADD that passes EPOLLEXCLUSIVE establishes the set POLL*
flags to be used by any other epfds that are added as EPOLLEXCLUSIVE.
However, I think it might be somewhat confusing interface as we would
have to reference count the number of users for that set, and so
userspace would have to keep track of that count, or we would need a
more involved interface. It also adds some shared state that we'd have
store somewhere. I don't think anybody will want to bloat
__wait_queue_head for this.
I think what we could do instead, is to simply restrict EPOLLEXCLUSIVE
such that it can only be specified with EPOLLIN and/or EPOLLOUT. So
that way if the wakeup includes 'POLLIN' and not 'POLLOUT', we can stop
once we hit the first idle waiter that specifies the EPOLLIN bit, since
any remaining waiters that only have 'POLLOUT' set wouldn't need to be
woken. Likewise, we can do the same thing if 'POLLOUT' is in the wakeup
bit set and not 'POLLIN'. If both 'POLLOUT' and 'POLLIN' are set in the
wake bit set (there is at least one example of this I saw in fs/pipe.c),
then we just wake the entire exclusive list. Having both 'POLLOUT' and
'POLLIN' both set should not be on any performance critical path, so I
think that's ok (in fs/pipe.c its in pipe_release()). We also continue
to include EPOLLERR and EPOLLHUP by default in any exclusive set. Thus,
the user can specify EPOLLERR and/or EPOLLHUP but is not required to do
so.
Since epoll waiters may be interested in other events as well besides
EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP, these can still be added by
doing a 'dup' call on the target fd and adding that as one normally
would with EPOLL_CTL_ADD. Since I think that the POLLIN and POLLOUT
events are what we are interest in balancing, I think that the 'dup'
thing could perhaps be added to only one of the waiter threads.
However, I think that EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP should be
sufficient for the majority of use-cases.
Since EPOLLEXCLUSIVE is intended to be used with a target fd shared
among multiple epfds, where between 1 and n of the epfds may receive an
event, it does not satisfy the semantics of EPOLLONESHOT where only 1
epfd would get an event. Thus, it is not allowed to be specified in
conjunction with EPOLLEXCLUSIVE.
EPOLL_CTL_MOD is also not allowed if the fd was previously added as
EPOLLEXCLUSIVE. It seems with the limited number of flags to not be as
interesting, but this could be relaxed at some further point.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Tested-by: Madars Vitolins <m@silodev.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-05 15:37:04 -08:00
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
In the current implementation of the EPOLLEXCLUSIVE flag (added for
4.5-rc1), if epoll waiters create different POLL* sets and register them
as exclusive against the same target fd, the current implementation will
stop waking any further waiters once it finds the first idle waiter.
This means that waiters could miss wakeups in certain cases.
For example, when we wake up a pipe for reading we do:
wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); So if
one epoll set or epfd is added to pipe p with POLLIN and a second set
epfd2 is added to pipe p with POLLRDNORM, only epfd may receive the
wakeup since the current implementation will stop after it finds any
intersection of events with a waiter that is blocked in epoll_wait().
We could potentially address this by requiring all epoll waiters that
are added to p be required to pass the same set of POLL* events. IE the
first EPOLL_CTL_ADD that passes EPOLLEXCLUSIVE establishes the set POLL*
flags to be used by any other epfds that are added as EPOLLEXCLUSIVE.
However, I think it might be somewhat confusing interface as we would
have to reference count the number of users for that set, and so
userspace would have to keep track of that count, or we would need a
more involved interface. It also adds some shared state that we'd have
store somewhere. I don't think anybody will want to bloat
__wait_queue_head for this.
I think what we could do instead, is to simply restrict EPOLLEXCLUSIVE
such that it can only be specified with EPOLLIN and/or EPOLLOUT. So
that way if the wakeup includes 'POLLIN' and not 'POLLOUT', we can stop
once we hit the first idle waiter that specifies the EPOLLIN bit, since
any remaining waiters that only have 'POLLOUT' set wouldn't need to be
woken. Likewise, we can do the same thing if 'POLLOUT' is in the wakeup
bit set and not 'POLLIN'. If both 'POLLOUT' and 'POLLIN' are set in the
wake bit set (there is at least one example of this I saw in fs/pipe.c),
then we just wake the entire exclusive list. Having both 'POLLOUT' and
'POLLIN' both set should not be on any performance critical path, so I
think that's ok (in fs/pipe.c its in pipe_release()). We also continue
to include EPOLLERR and EPOLLHUP by default in any exclusive set. Thus,
the user can specify EPOLLERR and/or EPOLLHUP but is not required to do
so.
Since epoll waiters may be interested in other events as well besides
EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP, these can still be added by
doing a 'dup' call on the target fd and adding that as one normally
would with EPOLL_CTL_ADD. Since I think that the POLLIN and POLLOUT
events are what we are interest in balancing, I think that the 'dup'
thing could perhaps be added to only one of the waiter threads.
However, I think that EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP should be
sufficient for the majority of use-cases.
Since EPOLLEXCLUSIVE is intended to be used with a target fd shared
among multiple epfds, where between 1 and n of the epfds may receive an
event, it does not satisfy the semantics of EPOLLONESHOT where only 1
epfd would get an event. Thus, it is not allowed to be specified in
conjunction with EPOLLEXCLUSIVE.
EPOLL_CTL_MOD is also not allowed if the fd was previously added as
EPOLLEXCLUSIVE. It seems with the limited number of flags to not be as
interesting, but this could be relaxed at some further point.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Tested-by: Madars Vitolins <m@silodev.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-05 15:37:04 -08:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-10-11 01:21:44 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:38 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2009-06-17 16:25:58 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:38 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-01-30 23:42:29 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-30 23:42:29 +02:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:52 -07:00
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-30 22:57:33 -03:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-24 10:08:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:16 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-20 12:06:13 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-02-01 15:21:13 -05:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2006-12-06 20:33:20 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2006-12-06 20:33:20 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2014-06-06 14:38:05 -07:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2009-11-05 14:25:10 -08:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
2007-05-15 01:40:52 -07:00
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:52 -07:00
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-06-20 12:06:13 +02:00
|
|
|
|
2012-02-24 20:07:29 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
2017-06-20 12:06:13 +02:00
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-04-29 00:58:34 -07:00
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: optimizations and cleanups
Epoll is doing multiple passes over the ready set at the moment, because of
the constraints over the f_op->poll() call. Looking at the code again, I
noticed that we already hold the epoll semaphore in read, and this
(together with other locking conditions that hold while doing an
epoll_wait()) can lead to a smarter way [1] to "ship" events to userspace
(in a single pass).
This is a stress application that can be used to test the new code. It
spwans multiple thread and call epoll_wait() and epoll_ctl() from many
threads. Stress tested on my dual Opteron 254 w/out any problems.
http://www.xmailserver.org/totalmess.c
This is not a benchmark, just something that tries to stress and exploit
possible problems with the new code.
Also, I made a stupid micro-benchmark:
http://www.xmailserver.org/epwbench.c
[1] Considering that epoll must be thread-safe, there are five ways we can
be hit during an epoll_wait() transfer loop (ep_send_events()):
1) The epoll fd going away and calling ep_free
This just can't happen, since we did an fget() in sys_epoll_wait
2) An epoll_ctl(EPOLL_CTL_DEL)
This can't happen because epoll_ctl() gets ep->sem in write, and
we're holding it in read during ep_send_events()
3) An fd stored inside the epoll fd going away
This can't happen because in eventpoll_release_file() we get
ep->sem in write, and we're holding it in read during
ep_send_events()
4) Another epoll_wait() happening on another thread
They both can be inside ep_send_events() at the same time, we get
(splice) the ready-list under the spinlock, so each one will get
its own ready list. Note that an fd cannot be at the same time
inside more than one ready list, because ep_poll_callback() will
not re-queue it if it sees it already linked:
if (ep_is_linked(&epi->rdllink))
goto is_linked;
Another case that can happen, is two concurrent epoll_wait(),
coming in with a userspace event buffer of size, say, ten.
Suppose there are 50 event ready in the list. The first
epoll_wait() will "steal" the whole list, while the second, seeing
no events, will go to sleep. But at the end of ep_send_events() in
the first epoll_wait(), we will re-inject surplus ready fds, and we
will trigger the proper wake_up to the second epoll_wait().
5) ep_poll_callback() hitting us asyncronously
This is the tricky part. As I said above, the ep_is_linked() test
done inside ep_poll_callback(), will guarantee us that until the
item will result linked to a list, ep_poll_callback() will not try
to re-queue it again (read, write data on any of its members). When
we do a list_del() in ep_send_events(), the item will still satisfy
the ep_is_linked() test (whatever data is written in prev/next,
it'll never be its own pointer), so ep_poll_callback() will still
leave us alone. It's only after the eventual smp_mb()+INIT_LIST_HEAD(&epi->rdllink)
that it'll become visible to ep_poll_callback(), but at the point
we're already past it.
[akpm@osdl.org: 80 cols]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 00:25:41 -07:00
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
revert "epoll: support for disabling items, and a self-test app"
Revert commit 03a7beb55b9f ("epoll: support for disabling items, and a
self-test app") pending resolution of the issues identified by Michael
Kerrisk, copied below.
We'll revisit this for 3.8.
: I've taken a look at this patch as it currently stands in 3.7-rc1, and
: done a bit of testing. (By the way, the test program
: tools/testing/selftests/epoll/test_epoll.c does not compile...)
:
: There are one or two places where the behavior seems a little strange,
: so I have a question or two at the end of this mail. But other than
: that, I want to check my understanding so that the interface can be
: correctly documented.
:
: Just to go though my understanding, the problem is the following
: scenario in a multithreaded application:
:
: 1. Multiple threads are performing epoll_wait() operations,
: and maintaining a user-space cache that contains information
: corresponding to each file descriptor being monitored by
: epoll_wait().
:
: 2. At some point, a thread wants to delete (EPOLL_CTL_DEL)
: a file descriptor from the epoll interest list, and
: delete the corresponding record from the user-space cache.
:
: 3. The problem with (2) is that some other thread may have
: previously done an epoll_wait() that retrieved information
: about the fd in question, and may be in the middle of using
: information in the cache that relates to that fd. Thus,
: there is a potential race.
:
: 4. The race can't solved purely in user space, because doing
: so would require applying a mutex across the epoll_wait()
: call, which would of course blow thread concurrency.
:
: Right?
:
: Your solution is the EPOLL_CTL_DISABLE operation. I want to
: confirm my understanding about how to use this flag, since
: the description that has accompanied the patches so far
: has been a bit sparse
:
: 0. In the scenario you're concerned about, deleting a file
: descriptor means (safely) doing the following:
: (a) Deleting the file descriptor from the epoll interest list
: using EPOLL_CTL_DEL
: (b) Deleting the corresponding record in the user-space cache
:
: 1. It's only meaningful to use this EPOLL_CTL_DISABLE in
: conjunction with EPOLLONESHOT.
:
: 2. Using EPOLL_CTL_DISABLE without using EPOLLONESHOT in
: conjunction is a logical error.
:
: 3. The correct way to code multithreaded applications using
: EPOLL_CTL_DISABLE and EPOLLONESHOT is as follows:
:
: a. All EPOLL_CTL_ADD and EPOLL_CTL_MOD operations should
: should EPOLLONESHOT.
:
: b. When a thread wants to delete a file descriptor, it
: should do the following:
:
: [1] Call epoll_ctl(EPOLL_CTL_DISABLE)
: [2] If the return status from epoll_ctl(EPOLL_CTL_DISABLE)
: was zero, then the file descriptor can be safely
: deleted by the thread that made this call.
: [3] If the epoll_ctl(EPOLL_CTL_DISABLE) fails with EBUSY,
: then the descriptor is in use. In this case, the calling
: thread should set a flag in the user-space cache to
: indicate that the thread that is using the descriptor
: should perform the deletion operation.
:
: Is all of the above correct?
:
: The implementation depends on checking on whether
: (events & ~EP_PRIVATE_BITS) == 0
: This replies on the fact that EPOLL_CTL_AD and EPOLL_CTL_MOD always
: set EPOLLHUP and EPOLLERR in the 'events' mask, and EPOLLONESHOT
: causes those flags (as well as all others in ~EP_PRIVATE_BITS) to be
: cleared.
:
: A corollary to the previous paragraph is that using EPOLL_CTL_DISABLE
: is only useful in conjunction with EPOLLONESHOT. However, as things
: stand, one can use EPOLL_CTL_DISABLE on a file descriptor that does
: not have EPOLLONESHOT set in 'events' This results in the following
: (slightly surprising) behavior:
:
: (a) The first call to epoll_ctl(EPOLL_CTL_DISABLE) returns 0
: (the indicator that the file descriptor can be safely deleted).
: (b) The next call to epoll_ctl(EPOLL_CTL_DISABLE) fails with EBUSY.
:
: This doesn't seem particularly useful, and in fact is probably an
: indication that the user made a logic error: they should only be using
: epoll_ctl(EPOLL_CTL_DISABLE) on a file descriptor for which
: EPOLLONESHOT was set in 'events'. If that is correct, then would it
: not make sense to return an error to user space for this case?
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paton J. Lewis" <palewis@adobe.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-11-08 15:53:35 -08:00
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2011-03-22 16:34:46 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-24 10:08:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-06-17 16:25:58 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2009-06-17 16:25:58 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-10-18 23:39:56 -07:00
|
|
|
|
2009-06-17 16:25:58 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:13 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2009-06-17 16:25:58 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-06-17 16:25:58 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: comment the funky #ifdef
Looking for a bug in -rt, I stumbled across this code here from: commit
2dfa4eeab0fc ("epoll keyed wakeups: teach epoll about hints coming with
the wakeup key"), specifically:
#ifdef CONFIG_DEBUG_LOCK_ALLOC
static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
unsigned long events, int subclass)
{
unsigned long flags;
spin_lock_irqsave_nested(&wqueue->lock, flags, subclass);
wake_up_locked_poll(wqueue, events);
spin_unlock_irqrestore(&wqueue->lock, flags);
}
#else
static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
unsigned long events, int subclass)
{
wake_up_poll(wqueue, events);
}
#endif
You change the function of ep_wake_up_nested() depending on whether
CONFIG_DEBUG_LOCK_ALLOC is set or not. This looks awfully suspicious,
and there's no comment to explain why. I initially thought that this
was trying to fool lockdep, and hiding a real bug.
Investigating it, I found the creation of wake_up_nested() (which no
longer exists) but was created for the sole purpose of epoll and its
strange wake ups, as explained in commit 0ccf831cbee9 ("lockdep:
annotate epoll")
Although the commit message says "annotate epoll" the change log is much
better at explaining what is happening than what is in the actual code.
Thus a comment is really necessary here. And to save the time of other
developers from having to go trudging through the git logs trying to
figure out why this code exists.
I took parts of the change log and placed it into a comment above the
affected code. This will make the description of what is happening more
visible to new developers that have to look at this code for the first
time.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-23 15:02:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:22 -07:00
|
|
|
|
epoll: avoid calling ep_call_nested() from ep_poll_safewake()
ep_poll_safewake() is used to wakeup potentially nested epoll file
descriptors. The function uses ep_call_nested() to prevent entering the
same wake up queue more than once, and to prevent excessively deep
wakeup paths (deeper than EP_MAX_NESTS). However, this is not necessary
since we are already preventing these conditions during EPOLL_CTL_ADD.
This saves extra function calls, and avoids taking a global lock during
the ep_call_nested() calls.
I have, however, left ep_call_nested() for the CONFIG_DEBUG_LOCK_ALLOC
case, since ep_call_nested() keeps track of the nesting level, and this
is required by the call to spin_lock_irqsave_nested(). It would be nice
to remove the ep_call_nested() calls for the CONFIG_DEBUG_LOCK_ALLOC
case as well, however its not clear how to simply pass the nesting level
through multiple wake_up() levels without more surgery. In any case, I
don't think CONFIG_DEBUG_LOCK_ALLOC is generally used for production.
This patch, also apparently fixes a workload at Google that Salman Qazi
reported by completely removing the poll_safewake_ncalls->lock from
wakeup paths.
Link: http://lkml.kernel.org/r/1507920533-8812-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:22 -07:00
|
|
|
|
|
|
|
|
|
epoll: avoid calling ep_call_nested() from ep_poll_safewake()
ep_poll_safewake() is used to wakeup potentially nested epoll file
descriptors. The function uses ep_call_nested() to prevent entering the
same wake up queue more than once, and to prevent excessively deep
wakeup paths (deeper than EP_MAX_NESTS). However, this is not necessary
since we are already preventing these conditions during EPOLL_CTL_ADD.
This saves extra function calls, and avoids taking a global lock during
the ep_call_nested() calls.
I have, however, left ep_call_nested() for the CONFIG_DEBUG_LOCK_ALLOC
case, since ep_call_nested() keeps track of the nesting level, and this
is required by the call to spin_lock_irqsave_nested(). It would be nice
to remove the ep_call_nested() calls for the CONFIG_DEBUG_LOCK_ALLOC
case as well, however its not clear how to simply pass the nesting level
through multiple wake_up() levels without more surgery. In any case, I
don't think CONFIG_DEBUG_LOCK_ALLOC is generally used for production.
This patch, also apparently fixes a workload at Google that Salman Qazi
reported by completely removing the poll_safewake_ncalls->lock from
wakeup paths.
Link: http://lkml.kernel.org/r/1507920533-8812-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:02 -08:00
|
|
|
|
2009-03-31 15:24:22 -07:00
|
|
|
|
epoll: avoid calling ep_call_nested() from ep_poll_safewake()
ep_poll_safewake() is used to wakeup potentially nested epoll file
descriptors. The function uses ep_call_nested() to prevent entering the
same wake up queue more than once, and to prevent excessively deep
wakeup paths (deeper than EP_MAX_NESTS). However, this is not necessary
since we are already preventing these conditions during EPOLL_CTL_ADD.
This saves extra function calls, and avoids taking a global lock during
the ep_call_nested() calls.
I have, however, left ep_call_nested() for the CONFIG_DEBUG_LOCK_ALLOC
case, since ep_call_nested() keeps track of the nesting level, and this
is required by the call to spin_lock_irqsave_nested(). It would be nice
to remove the ep_call_nested() calls for the CONFIG_DEBUG_LOCK_ALLOC
case as well, however its not clear how to simply pass the nesting level
through multiple wake_up() levels without more surgery. In any case, I
don't think CONFIG_DEBUG_LOCK_ALLOC is generally used for production.
This patch, also apparently fixes a workload at Google that Salman Qazi
reported by completely removing the poll_safewake_ncalls->lock from
wakeup paths.
Link: http://lkml.kernel.org/r/1507920533-8812-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:02 -08:00
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
2009-03-31 15:24:22 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-06-17 16:25:58 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2009-06-17 16:25:58 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
epoll: avoid calling ep_call_nested() from ep_poll_safewake()
ep_poll_safewake() is used to wakeup potentially nested epoll file
descriptors. The function uses ep_call_nested() to prevent entering the
same wake up queue more than once, and to prevent excessively deep
wakeup paths (deeper than EP_MAX_NESTS). However, this is not necessary
since we are already preventing these conditions during EPOLL_CTL_ADD.
This saves extra function calls, and avoids taking a global lock during
the ep_call_nested() calls.
I have, however, left ep_call_nested() for the CONFIG_DEBUG_LOCK_ALLOC
case, since ep_call_nested() keeps track of the nesting level, and this
is required by the call to spin_lock_irqsave_nested(). It would be nice
to remove the ep_call_nested() calls for the CONFIG_DEBUG_LOCK_ALLOC
case as well, however its not clear how to simply pass the nesting level
through multiple wake_up() levels without more surgery. In any case, I
don't think CONFIG_DEBUG_LOCK_ALLOC is generally used for production.
This patch, also apparently fixes a workload at Google that Salman Qazi
reported by completely removing the poll_safewake_ncalls->lock from
wakeup paths.
Link: http://lkml.kernel.org/r/1507920533-8812-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
epoll: avoid calling ep_call_nested() from ep_poll_safewake()
ep_poll_safewake() is used to wakeup potentially nested epoll file
descriptors. The function uses ep_call_nested() to prevent entering the
same wake up queue more than once, and to prevent excessively deep
wakeup paths (deeper than EP_MAX_NESTS). However, this is not necessary
since we are already preventing these conditions during EPOLL_CTL_ADD.
This saves extra function calls, and avoids taking a global lock during
the ep_call_nested() calls.
I have, however, left ep_call_nested() for the CONFIG_DEBUG_LOCK_ALLOC
case, since ep_call_nested() keeps track of the nesting level, and this
is required by the call to spin_lock_irqsave_nested(). It would be nice
to remove the ep_call_nested() calls for the CONFIG_DEBUG_LOCK_ALLOC
case as well, however its not clear how to simply pass the nesting level
through multiple wake_up() levels without more surgery. In any case, I
don't think CONFIG_DEBUG_LOCK_ALLOC is generally used for production.
This patch, also apparently fixes a workload at Google that Salman Qazi
reported by completely removing the poll_safewake_ncalls->lock from
wakeup paths.
Link: http://lkml.kernel.org/r/1507920533-8812-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-02-24 20:07:29 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-01 18:55:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-02-24 20:07:29 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
2012-02-24 20:07:29 +01:00
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-10-31 17:13:14 -07:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2009-02-06 13:52:43 -07:00
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
2009-02-06 13:52:43 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2011-03-30 22:57:33 -03:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-09-11 14:24:06 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2013-04-30 15:27:40 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-04-30 15:27:40 -07:00
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2013-09-11 14:24:06 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2013-04-30 15:27:40 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2007-05-15 01:40:57 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:57 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
2017-11-28 19:43:33 -05:00
|
|
|
|
2013-04-30 15:27:42 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:42 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:42 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:42 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:42 -07:00
|
|
|
|
|
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
poll: add poll_requested_events() and poll_does_not_wait() functions
In some cases the poll() implementation in a driver has to do different
things depending on the events the caller wants to poll for. An example
is when a driver needs to start a DMA engine if the caller polls for
POLLIN, but doesn't want to do that if POLLIN is not requested but instead
only POLLOUT or POLLPRI is requested. This is something that can happen
in the video4linux subsystem among others.
Unfortunately, the current epoll/poll/select implementation doesn't
provide that information reliably. The poll_table_struct does have it: it
has a key field with the event mask. But once a poll() call matches one
or more bits of that mask any following poll() calls are passed a NULL
poll_table pointer.
Also, the eventpoll implementation always left the key field at ~0 instead
of using the requested events mask.
This was changed in eventpoll.c so the key field now contains the actual
events that should be polled for as set by the caller.
The solution to the NULL poll_table pointer is to set the qproc field to
NULL in poll_table once poll() matches the events, not the poll_table
pointer itself. That way drivers can obtain the mask through a new
poll_requested_events inline.
The poll_table_struct can still be NULL since some kernel code calls it
internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In
that case poll_requested_events() returns ~0 (i.e. all events).
Very rarely drivers might want to know whether poll_wait will actually
wait. If another earlier file descriptor in the set already matched the
events the caller wanted to wait for, then the kernel will return from the
select() call without waiting. This might be useful information in order
to avoid doing expensive work.
A new helper function poll_does_not_wait() is added that drivers can use
to detect this situation. This is now used in sock_poll_wait() in
include/net/sock.h. This was the only place in the kernel that needed
this information.
Drivers should no longer access any of the poll_table internals, but use
the poll_requested_events() and poll_does_not_wait() access functions
instead. In order to enforce that the poll_table fields are now prepended
with an underscore and a comment was added warning against using them
directly.
This required a change in unix_dgram_poll() in unix/af_unix.c which used
the key field to get the requested events. It's been replaced by a call
to poll_requested_events().
For qproc it was especially important to change its name since the
behavior of that field changes with this patch since this function pointer
can now be NULL when that wasn't possible in the past.
Any driver accessing the qproc or key fields directly will now fail to compile.
Some notes regarding the correctness of this patch: the driver's poll()
function is called with a 'struct poll_table_struct *wait' argument. This
pointer may or may not be NULL, drivers can never rely on it being one or
the other as that depends on whether or not an earlier file descriptor in
the select()'s fdset matched the requested events.
There are only three things a driver can do with the wait argument:
1) obtain the key field:
events = wait ? wait->key : ~0;
This will still work although it should be replaced with the new
poll_requested_events() function (which does exactly the same).
This will now even work better, since wait is no longer set to NULL
unnecessarily.
2) use the qproc callback. This could be deadly since qproc can now be
NULL. Renaming qproc should prevent this from happening. There are no
kernel drivers that actually access this callback directly, BTW.
3) test whether wait == NULL to determine whether poll would return without
waiting. This is no longer sufficient as the correct test is now
wait == NULL || wait->_qproc == NULL.
However, the worst that can happen here is a slight performance hit in
the case where wait != NULL and wait->_qproc == NULL. In that case the
driver will assume that poll_wait() will actually add the fd to the set
of waiting file descriptors. Of course, poll_wait() will not do that
since it tests for wait->_qproc. This will not break anything, though.
There is only one place in the whole kernel where this happens
(sock_poll_wait() in include/net/sock.h) and that code will be replaced
by a call to poll_does_not_wait() in the next patch.
Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait()
actually waiting. The next file descriptor from the set might match the
event mask and thus any possible waits will never happen.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-23 15:02:27 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
poll: add poll_requested_events() and poll_does_not_wait() functions
In some cases the poll() implementation in a driver has to do different
things depending on the events the caller wants to poll for. An example
is when a driver needs to start a DMA engine if the caller polls for
POLLIN, but doesn't want to do that if POLLIN is not requested but instead
only POLLOUT or POLLPRI is requested. This is something that can happen
in the video4linux subsystem among others.
Unfortunately, the current epoll/poll/select implementation doesn't
provide that information reliably. The poll_table_struct does have it: it
has a key field with the event mask. But once a poll() call matches one
or more bits of that mask any following poll() calls are passed a NULL
poll_table pointer.
Also, the eventpoll implementation always left the key field at ~0 instead
of using the requested events mask.
This was changed in eventpoll.c so the key field now contains the actual
events that should be polled for as set by the caller.
The solution to the NULL poll_table pointer is to set the qproc field to
NULL in poll_table once poll() matches the events, not the poll_table
pointer itself. That way drivers can obtain the mask through a new
poll_requested_events inline.
The poll_table_struct can still be NULL since some kernel code calls it
internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In
that case poll_requested_events() returns ~0 (i.e. all events).
Very rarely drivers might want to know whether poll_wait will actually
wait. If another earlier file descriptor in the set already matched the
events the caller wanted to wait for, then the kernel will return from the
select() call without waiting. This might be useful information in order
to avoid doing expensive work.
A new helper function poll_does_not_wait() is added that drivers can use
to detect this situation. This is now used in sock_poll_wait() in
include/net/sock.h. This was the only place in the kernel that needed
this information.
Drivers should no longer access any of the poll_table internals, but use
the poll_requested_events() and poll_does_not_wait() access functions
instead. In order to enforce that the poll_table fields are now prepended
with an underscore and a comment was added warning against using them
directly.
This required a change in unix_dgram_poll() in unix/af_unix.c which used
the key field to get the requested events. It's been replaced by a call
to poll_requested_events().
For qproc it was especially important to change its name since the
behavior of that field changes with this patch since this function pointer
can now be NULL when that wasn't possible in the past.
Any driver accessing the qproc or key fields directly will now fail to compile.
Some notes regarding the correctness of this patch: the driver's poll()
function is called with a 'struct poll_table_struct *wait' argument. This
pointer may or may not be NULL, drivers can never rely on it being one or
the other as that depends on whether or not an earlier file descriptor in
the select()'s fdset matched the requested events.
There are only three things a driver can do with the wait argument:
1) obtain the key field:
events = wait ? wait->key : ~0;
This will still work although it should be replaced with the new
poll_requested_events() function (which does exactly the same).
This will now even work better, since wait is no longer set to NULL
unnecessarily.
2) use the qproc callback. This could be deadly since qproc can now be
NULL. Renaming qproc should prevent this from happening. There are no
kernel drivers that actually access this callback directly, BTW.
3) test whether wait == NULL to determine whether poll would return without
waiting. This is no longer sufficient as the correct test is now
wait == NULL || wait->_qproc == NULL.
However, the worst that can happen here is a slight performance hit in
the case where wait != NULL and wait->_qproc == NULL. In that case the
driver will assume that poll_wait() will actually add the fd to the set
of waiting file descriptors. Of course, poll_wait() will not do that
since it tests for wait->_qproc. This will not break anything, though.
There is only one place in the whole kernel where this happens
(sock_poll_wait() in include/net/sock.h) and that code will be replaced
by a call to poll_does_not_wait() in the next patch.
Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait()
actually waiting. The next file descriptor from the set might match the
event mask and thus any possible waits will never happen.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-23 15:02:27 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
2013-04-30 15:27:42 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-03 01:02:18 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2012-12-17 16:05:02 -08:00
|
|
|
|
2014-09-29 16:08:25 -07:00
|
|
|
|
2012-12-17 16:05:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2012-12-17 16:05:02 -08:00
|
|
|
|
2017-07-12 14:34:25 -07:00
|
|
|
|
2012-12-17 16:05:02 -08:00
|
|
|
|
2017-07-12 14:34:25 -07:00
|
|
|
|
|
|
|
|
|
2014-09-29 16:08:25 -07:00
|
|
|
|
2017-07-12 14:34:25 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2014-09-29 16:08:25 -07:00
|
|
|
|
2012-12-17 16:05:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2012-12-17 16:05:02 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 18:52:59 +02:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2006-10-11 01:21:44 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-10-11 01:21:44 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2006-10-11 01:21:44 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2014-06-17 06:58:05 +04:00
|
|
|
|
2006-10-11 01:21:44 -07:00
|
|
|
|
|
|
|
|
|
2009-02-06 13:52:43 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2011-03-30 22:57:33 -03:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2007-05-15 01:40:52 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2009-02-06 13:52:43 -07:00
|
|
|
|
|
|
|
|
|
2006-10-11 01:21:44 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2014-06-17 06:58:05 +04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2011-10-31 17:13:14 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2006-10-11 01:21:44 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2006-10-11 01:21:44 -07:00
|
|
|
|
|
|
|
|
|
2005-09-16 19:28:06 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2005-09-16 19:28:06 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-12 14:34:31 -07:00
|
|
|
|
2017-07-12 14:34:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2017-07-12 14:34:28 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-12 14:34:31 -07:00
|
|
|
|
2017-07-12 14:34:28 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2011-01-30 23:42:29 +02:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-06-20 12:06:13 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-03 20:14:56 -04:00
|
|
|
|
2016-01-20 14:59:24 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-03-24 10:08:30 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:22 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-03 20:14:56 -04:00
|
|
|
|
2009-03-31 15:24:22 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2011-01-30 23:42:29 +02:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2011-01-30 23:42:29 +02:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-01-20 14:59:24 -08:00
|
|
|
|
epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
In the current implementation of the EPOLLEXCLUSIVE flag (added for
4.5-rc1), if epoll waiters create different POLL* sets and register them
as exclusive against the same target fd, the current implementation will
stop waking any further waiters once it finds the first idle waiter.
This means that waiters could miss wakeups in certain cases.
For example, when we wake up a pipe for reading we do:
wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); So if
one epoll set or epfd is added to pipe p with POLLIN and a second set
epfd2 is added to pipe p with POLLRDNORM, only epfd may receive the
wakeup since the current implementation will stop after it finds any
intersection of events with a waiter that is blocked in epoll_wait().
We could potentially address this by requiring all epoll waiters that
are added to p be required to pass the same set of POLL* events. IE the
first EPOLL_CTL_ADD that passes EPOLLEXCLUSIVE establishes the set POLL*
flags to be used by any other epfds that are added as EPOLLEXCLUSIVE.
However, I think it might be somewhat confusing interface as we would
have to reference count the number of users for that set, and so
userspace would have to keep track of that count, or we would need a
more involved interface. It also adds some shared state that we'd have
store somewhere. I don't think anybody will want to bloat
__wait_queue_head for this.
I think what we could do instead, is to simply restrict EPOLLEXCLUSIVE
such that it can only be specified with EPOLLIN and/or EPOLLOUT. So
that way if the wakeup includes 'POLLIN' and not 'POLLOUT', we can stop
once we hit the first idle waiter that specifies the EPOLLIN bit, since
any remaining waiters that only have 'POLLOUT' set wouldn't need to be
woken. Likewise, we can do the same thing if 'POLLOUT' is in the wakeup
bit set and not 'POLLIN'. If both 'POLLOUT' and 'POLLIN' are set in the
wake bit set (there is at least one example of this I saw in fs/pipe.c),
then we just wake the entire exclusive list. Having both 'POLLOUT' and
'POLLIN' both set should not be on any performance critical path, so I
think that's ok (in fs/pipe.c its in pipe_release()). We also continue
to include EPOLLERR and EPOLLHUP by default in any exclusive set. Thus,
the user can specify EPOLLERR and/or EPOLLHUP but is not required to do
so.
Since epoll waiters may be interested in other events as well besides
EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP, these can still be added by
doing a 'dup' call on the target fd and adding that as one normally
would with EPOLL_CTL_ADD. Since I think that the POLLIN and POLLOUT
events are what we are interest in balancing, I think that the 'dup'
thing could perhaps be added to only one of the waiter threads.
However, I think that EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP should be
sufficient for the majority of use-cases.
Since EPOLLEXCLUSIVE is intended to be used with a target fd shared
among multiple epfds, where between 1 and n of the epfds may receive an
event, it does not satisfy the semantics of EPOLLONESHOT where only 1
epfd would get an event. Thus, it is not allowed to be specified in
conjunction with EPOLLEXCLUSIVE.
EPOLL_CTL_MOD is also not allowed if the fd was previously added as
EPOLLEXCLUSIVE. It seems with the limited number of flags to not be as
interesting, but this could be relaxed at some further point.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Tested-by: Madars Vitolins <m@silodev.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-05 15:37:04 -08:00
|
|
|
|
2017-07-03 20:14:56 -04:00
|
|
|
|
|
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
|
|
|
|
|
epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
In the current implementation of the EPOLLEXCLUSIVE flag (added for
4.5-rc1), if epoll waiters create different POLL* sets and register them
as exclusive against the same target fd, the current implementation will
stop waking any further waiters once it finds the first idle waiter.
This means that waiters could miss wakeups in certain cases.
For example, when we wake up a pipe for reading we do:
wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); So if
one epoll set or epfd is added to pipe p with POLLIN and a second set
epfd2 is added to pipe p with POLLRDNORM, only epfd may receive the
wakeup since the current implementation will stop after it finds any
intersection of events with a waiter that is blocked in epoll_wait().
We could potentially address this by requiring all epoll waiters that
are added to p be required to pass the same set of POLL* events. IE the
first EPOLL_CTL_ADD that passes EPOLLEXCLUSIVE establishes the set POLL*
flags to be used by any other epfds that are added as EPOLLEXCLUSIVE.
However, I think it might be somewhat confusing interface as we would
have to reference count the number of users for that set, and so
userspace would have to keep track of that count, or we would need a
more involved interface. It also adds some shared state that we'd have
store somewhere. I don't think anybody will want to bloat
__wait_queue_head for this.
I think what we could do instead, is to simply restrict EPOLLEXCLUSIVE
such that it can only be specified with EPOLLIN and/or EPOLLOUT. So
that way if the wakeup includes 'POLLIN' and not 'POLLOUT', we can stop
once we hit the first idle waiter that specifies the EPOLLIN bit, since
any remaining waiters that only have 'POLLOUT' set wouldn't need to be
woken. Likewise, we can do the same thing if 'POLLOUT' is in the wakeup
bit set and not 'POLLIN'. If both 'POLLOUT' and 'POLLIN' are set in the
wake bit set (there is at least one example of this I saw in fs/pipe.c),
then we just wake the entire exclusive list. Having both 'POLLOUT' and
'POLLIN' both set should not be on any performance critical path, so I
think that's ok (in fs/pipe.c its in pipe_release()). We also continue
to include EPOLLERR and EPOLLHUP by default in any exclusive set. Thus,
the user can specify EPOLLERR and/or EPOLLHUP but is not required to do
so.
Since epoll waiters may be interested in other events as well besides
EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP, these can still be added by
doing a 'dup' call on the target fd and adding that as one normally
would with EPOLL_CTL_ADD. Since I think that the POLLIN and POLLOUT
events are what we are interest in balancing, I think that the 'dup'
thing could perhaps be added to only one of the waiter threads.
However, I think that EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP should be
sufficient for the majority of use-cases.
Since EPOLLEXCLUSIVE is intended to be used with a target fd shared
among multiple epfds, where between 1 and n of the epfds may receive an
event, it does not satisfy the semantics of EPOLLONESHOT where only 1
epfd would get an event. Thus, it is not allowed to be specified in
conjunction with EPOLLEXCLUSIVE.
EPOLL_CTL_MOD is also not allowed if the fd was previously added as
EPOLLEXCLUSIVE. It seems with the limited number of flags to not be as
interesting, but this could be relaxed at some further point.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Tested-by: Madars Vitolins <m@silodev.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-05 15:37:04 -08:00
|
|
|
|
|
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
|
|
|
|
|
epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
In the current implementation of the EPOLLEXCLUSIVE flag (added for
4.5-rc1), if epoll waiters create different POLL* sets and register them
as exclusive against the same target fd, the current implementation will
stop waking any further waiters once it finds the first idle waiter.
This means that waiters could miss wakeups in certain cases.
For example, when we wake up a pipe for reading we do:
wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); So if
one epoll set or epfd is added to pipe p with POLLIN and a second set
epfd2 is added to pipe p with POLLRDNORM, only epfd may receive the
wakeup since the current implementation will stop after it finds any
intersection of events with a waiter that is blocked in epoll_wait().
We could potentially address this by requiring all epoll waiters that
are added to p be required to pass the same set of POLL* events. IE the
first EPOLL_CTL_ADD that passes EPOLLEXCLUSIVE establishes the set POLL*
flags to be used by any other epfds that are added as EPOLLEXCLUSIVE.
However, I think it might be somewhat confusing interface as we would
have to reference count the number of users for that set, and so
userspace would have to keep track of that count, or we would need a
more involved interface. It also adds some shared state that we'd have
store somewhere. I don't think anybody will want to bloat
__wait_queue_head for this.
I think what we could do instead, is to simply restrict EPOLLEXCLUSIVE
such that it can only be specified with EPOLLIN and/or EPOLLOUT. So
that way if the wakeup includes 'POLLIN' and not 'POLLOUT', we can stop
once we hit the first idle waiter that specifies the EPOLLIN bit, since
any remaining waiters that only have 'POLLOUT' set wouldn't need to be
woken. Likewise, we can do the same thing if 'POLLOUT' is in the wakeup
bit set and not 'POLLIN'. If both 'POLLOUT' and 'POLLIN' are set in the
wake bit set (there is at least one example of this I saw in fs/pipe.c),
then we just wake the entire exclusive list. Having both 'POLLOUT' and
'POLLIN' both set should not be on any performance critical path, so I
think that's ok (in fs/pipe.c its in pipe_release()). We also continue
to include EPOLLERR and EPOLLHUP by default in any exclusive set. Thus,
the user can specify EPOLLERR and/or EPOLLHUP but is not required to do
so.
Since epoll waiters may be interested in other events as well besides
EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP, these can still be added by
doing a 'dup' call on the target fd and adding that as one normally
would with EPOLL_CTL_ADD. Since I think that the POLLIN and POLLOUT
events are what we are interest in balancing, I think that the 'dup'
thing could perhaps be added to only one of the waiter threads.
However, I think that EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP should be
sufficient for the majority of use-cases.
Since EPOLLEXCLUSIVE is intended to be used with a target fd shared
among multiple epfds, where between 1 and n of the epfds may receive an
event, it does not satisfy the semantics of EPOLLONESHOT where only 1
epfd would get an event. Thus, it is not allowed to be specified in
conjunction with EPOLLEXCLUSIVE.
EPOLL_CTL_MOD is also not allowed if the fd was previously added as
EPOLLEXCLUSIVE. It seems with the limited number of flags to not be as
interesting, but this could be relaxed at some further point.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Tested-by: Madars Vitolins <m@silodev.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-05 15:37:04 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-08-30 16:10:22 -04:00
|
|
|
|
2016-01-20 14:59:24 -08:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2017-09-01 18:55:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-03 20:14:56 -04:00
|
|
|
|
2017-09-01 18:55:33 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-01-20 14:59:24 -08:00
|
|
|
|
2017-09-01 18:55:33 +02:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2006-12-06 20:33:17 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-01-20 14:59:24 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
revert "epoll: support for disabling items, and a self-test app"
Revert commit 03a7beb55b9f ("epoll: support for disabling items, and a
self-test app") pending resolution of the issues identified by Michael
Kerrisk, copied below.
We'll revisit this for 3.8.
: I've taken a look at this patch as it currently stands in 3.7-rc1, and
: done a bit of testing. (By the way, the test program
: tools/testing/selftests/epoll/test_epoll.c does not compile...)
:
: There are one or two places where the behavior seems a little strange,
: so I have a question or two at the end of this mail. But other than
: that, I want to check my understanding so that the interface can be
: correctly documented.
:
: Just to go though my understanding, the problem is the following
: scenario in a multithreaded application:
:
: 1. Multiple threads are performing epoll_wait() operations,
: and maintaining a user-space cache that contains information
: corresponding to each file descriptor being monitored by
: epoll_wait().
:
: 2. At some point, a thread wants to delete (EPOLL_CTL_DEL)
: a file descriptor from the epoll interest list, and
: delete the corresponding record from the user-space cache.
:
: 3. The problem with (2) is that some other thread may have
: previously done an epoll_wait() that retrieved information
: about the fd in question, and may be in the middle of using
: information in the cache that relates to that fd. Thus,
: there is a potential race.
:
: 4. The race can't solved purely in user space, because doing
: so would require applying a mutex across the epoll_wait()
: call, which would of course blow thread concurrency.
:
: Right?
:
: Your solution is the EPOLL_CTL_DISABLE operation. I want to
: confirm my understanding about how to use this flag, since
: the description that has accompanied the patches so far
: has been a bit sparse
:
: 0. In the scenario you're concerned about, deleting a file
: descriptor means (safely) doing the following:
: (a) Deleting the file descriptor from the epoll interest list
: using EPOLL_CTL_DEL
: (b) Deleting the corresponding record in the user-space cache
:
: 1. It's only meaningful to use this EPOLL_CTL_DISABLE in
: conjunction with EPOLLONESHOT.
:
: 2. Using EPOLL_CTL_DISABLE without using EPOLLONESHOT in
: conjunction is a logical error.
:
: 3. The correct way to code multithreaded applications using
: EPOLL_CTL_DISABLE and EPOLLONESHOT is as follows:
:
: a. All EPOLL_CTL_ADD and EPOLL_CTL_MOD operations should
: should EPOLLONESHOT.
:
: b. When a thread wants to delete a file descriptor, it
: should do the following:
:
: [1] Call epoll_ctl(EPOLL_CTL_DISABLE)
: [2] If the return status from epoll_ctl(EPOLL_CTL_DISABLE)
: was zero, then the file descriptor can be safely
: deleted by the thread that made this call.
: [3] If the epoll_ctl(EPOLL_CTL_DISABLE) fails with EBUSY,
: then the descriptor is in use. In this case, the calling
: thread should set a flag in the user-space cache to
: indicate that the thread that is using the descriptor
: should perform the deletion operation.
:
: Is all of the above correct?
:
: The implementation depends on checking on whether
: (events & ~EP_PRIVATE_BITS) == 0
: This replies on the fact that EPOLL_CTL_AD and EPOLL_CTL_MOD always
: set EPOLLHUP and EPOLLERR in the 'events' mask, and EPOLLONESHOT
: causes those flags (as well as all others in ~EP_PRIVATE_BITS) to be
: cleared.
:
: A corollary to the previous paragraph is that using EPOLL_CTL_DISABLE
: is only useful in conjunction with EPOLLONESHOT. However, as things
: stand, one can use EPOLL_CTL_DISABLE on a file descriptor that does
: not have EPOLLONESHOT set in 'events' This results in the following
: (slightly surprising) behavior:
:
: (a) The first call to epoll_ctl(EPOLL_CTL_DISABLE) returns 0
: (the indicator that the file descriptor can be safely deleted).
: (b) The next call to epoll_ctl(EPOLL_CTL_DISABLE) fails with EBUSY.
:
: This doesn't seem particularly useful, and in fact is probably an
: indication that the user made a logic error: they should only be using
: epoll_ctl(EPOLL_CTL_DISABLE) on a file descriptor for which
: EPOLLONESHOT was set in 'events'. If that is correct, then would it
: not make sense to return an error to user space for this case?
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: "Paton J. Lewis" <palewis@adobe.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-11-08 15:53:35 -08:00
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-03-16 16:34:03 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:43 -07:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-11-28 19:43:33 -05:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2006-12-06 20:33:17 -08:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2009-02-06 13:52:43 -07:00
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
2009-02-06 13:52:43 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-03-24 10:08:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-11-28 19:56:15 -05:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-08-30 16:10:22 -04:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:16 -08:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:52 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
epoll: optimizations and cleanups
Epoll is doing multiple passes over the ready set at the moment, because of
the constraints over the f_op->poll() call. Looking at the code again, I
noticed that we already hold the epoll semaphore in read, and this
(together with other locking conditions that hold while doing an
epoll_wait()) can lead to a smarter way [1] to "ship" events to userspace
(in a single pass).
This is a stress application that can be used to test the new code. It
spwans multiple thread and call epoll_wait() and epoll_ctl() from many
threads. Stress tested on my dual Opteron 254 w/out any problems.
http://www.xmailserver.org/totalmess.c
This is not a benchmark, just something that tries to stress and exploit
possible problems with the new code.
Also, I made a stupid micro-benchmark:
http://www.xmailserver.org/epwbench.c
[1] Considering that epoll must be thread-safe, there are five ways we can
be hit during an epoll_wait() transfer loop (ep_send_events()):
1) The epoll fd going away and calling ep_free
This just can't happen, since we did an fget() in sys_epoll_wait
2) An epoll_ctl(EPOLL_CTL_DEL)
This can't happen because epoll_ctl() gets ep->sem in write, and
we're holding it in read during ep_send_events()
3) An fd stored inside the epoll fd going away
This can't happen because in eventpoll_release_file() we get
ep->sem in write, and we're holding it in read during
ep_send_events()
4) Another epoll_wait() happening on another thread
They both can be inside ep_send_events() at the same time, we get
(splice) the ready-list under the spinlock, so each one will get
its own ready list. Note that an fd cannot be at the same time
inside more than one ready list, because ep_poll_callback() will
not re-queue it if it sees it already linked:
if (ep_is_linked(&epi->rdllink))
goto is_linked;
Another case that can happen, is two concurrent epoll_wait(),
coming in with a userspace event buffer of size, say, ten.
Suppose there are 50 event ready in the list. The first
epoll_wait() will "steal" the whole list, while the second, seeing
no events, will go to sleep. But at the end of ep_send_events() in
the first epoll_wait(), we will re-inject surplus ready fds, and we
will trigger the proper wake_up to the second epoll_wait().
5) ep_poll_callback() hitting us asyncronously
This is the tricky part. As I said above, the ep_is_linked() test
done inside ep_poll_callback(), will guarantee us that until the
item will result linked to a list, ep_poll_callback() will not try
to re-queue it again (read, write data on any of its members). When
we do a list_del() in ep_send_events(), the item will still satisfy
the ep_is_linked() test (whatever data is written in prev/next,
it'll never be its own pointer), so ep_poll_callback() will still
leave us alone. It's only after the eventual smp_mb()+INIT_LIST_HEAD(&epi->rdllink)
that it'll become visible to ep_poll_callback(), but at the point
we're already past it.
[akpm@osdl.org: 80 cols]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 00:25:41 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
2005-06-23 00:10:03 -07:00
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-11-28 19:43:33 -05:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
poll: add poll_requested_events() and poll_does_not_wait() functions
In some cases the poll() implementation in a driver has to do different
things depending on the events the caller wants to poll for. An example
is when a driver needs to start a DMA engine if the caller polls for
POLLIN, but doesn't want to do that if POLLIN is not requested but instead
only POLLOUT or POLLPRI is requested. This is something that can happen
in the video4linux subsystem among others.
Unfortunately, the current epoll/poll/select implementation doesn't
provide that information reliably. The poll_table_struct does have it: it
has a key field with the event mask. But once a poll() call matches one
or more bits of that mask any following poll() calls are passed a NULL
poll_table pointer.
Also, the eventpoll implementation always left the key field at ~0 instead
of using the requested events mask.
This was changed in eventpoll.c so the key field now contains the actual
events that should be polled for as set by the caller.
The solution to the NULL poll_table pointer is to set the qproc field to
NULL in poll_table once poll() matches the events, not the poll_table
pointer itself. That way drivers can obtain the mask through a new
poll_requested_events inline.
The poll_table_struct can still be NULL since some kernel code calls it
internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In
that case poll_requested_events() returns ~0 (i.e. all events).
Very rarely drivers might want to know whether poll_wait will actually
wait. If another earlier file descriptor in the set already matched the
events the caller wanted to wait for, then the kernel will return from the
select() call without waiting. This might be useful information in order
to avoid doing expensive work.
A new helper function poll_does_not_wait() is added that drivers can use
to detect this situation. This is now used in sock_poll_wait() in
include/net/sock.h. This was the only place in the kernel that needed
this information.
Drivers should no longer access any of the poll_table internals, but use
the poll_requested_events() and poll_does_not_wait() access functions
instead. In order to enforce that the poll_table fields are now prepended
with an underscore and a comment was added warning against using them
directly.
This required a change in unix_dgram_poll() in unix/af_unix.c which used
the key field to get the requested events. It's been replaced by a call
to poll_requested_events().
For qproc it was especially important to change its name since the
behavior of that field changes with this patch since this function pointer
can now be NULL when that wasn't possible in the past.
Any driver accessing the qproc or key fields directly will now fail to compile.
Some notes regarding the correctness of this patch: the driver's poll()
function is called with a 'struct poll_table_struct *wait' argument. This
pointer may or may not be NULL, drivers can never rely on it being one or
the other as that depends on whether or not an earlier file descriptor in
the select()'s fdset matched the requested events.
There are only three things a driver can do with the wait argument:
1) obtain the key field:
events = wait ? wait->key : ~0;
This will still work although it should be replaced with the new
poll_requested_events() function (which does exactly the same).
This will now even work better, since wait is no longer set to NULL
unnecessarily.
2) use the qproc callback. This could be deadly since qproc can now be
NULL. Renaming qproc should prevent this from happening. There are no
kernel drivers that actually access this callback directly, BTW.
3) test whether wait == NULL to determine whether poll would return without
waiting. This is no longer sufficient as the correct test is now
wait == NULL || wait->_qproc == NULL.
However, the worst that can happen here is a slight performance hit in
the case where wait != NULL and wait->_qproc == NULL. In that case the
driver will assume that poll_wait() will actually add the fd to the set
of waiting file descriptors. Of course, poll_wait() will not do that
since it tests for wait->_qproc. This will not break anything, though.
There is only one place in the whole kernel where this happens
(sock_poll_wait() in include/net/sock.h) and that code will be replaced
by a call to poll_does_not_wait() in the next patch.
Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait()
actually waiting. The next file descriptor from the set might match the
event mask and thus any possible waits will never happen.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-23 15:02:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-01-01 21:20:27 +00:00
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-01-01 21:20:27 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2007-05-15 01:40:52 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2017-11-28 19:56:15 -05:00
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-08-30 16:10:22 -04:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2009-03-31 15:24:15 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2018-02-01 15:24:58 -05:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
poll: add poll_requested_events() and poll_does_not_wait() functions
In some cases the poll() implementation in a driver has to do different
things depending on the events the caller wants to poll for. An example
is when a driver needs to start a DMA engine if the caller polls for
POLLIN, but doesn't want to do that if POLLIN is not requested but instead
only POLLOUT or POLLPRI is requested. This is something that can happen
in the video4linux subsystem among others.
Unfortunately, the current epoll/poll/select implementation doesn't
provide that information reliably. The poll_table_struct does have it: it
has a key field with the event mask. But once a poll() call matches one
or more bits of that mask any following poll() calls are passed a NULL
poll_table pointer.
Also, the eventpoll implementation always left the key field at ~0 instead
of using the requested events mask.
This was changed in eventpoll.c so the key field now contains the actual
events that should be polled for as set by the caller.
The solution to the NULL poll_table pointer is to set the qproc field to
NULL in poll_table once poll() matches the events, not the poll_table
pointer itself. That way drivers can obtain the mask through a new
poll_requested_events inline.
The poll_table_struct can still be NULL since some kernel code calls it
internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In
that case poll_requested_events() returns ~0 (i.e. all events).
Very rarely drivers might want to know whether poll_wait will actually
wait. If another earlier file descriptor in the set already matched the
events the caller wanted to wait for, then the kernel will return from the
select() call without waiting. This might be useful information in order
to avoid doing expensive work.
A new helper function poll_does_not_wait() is added that drivers can use
to detect this situation. This is now used in sock_poll_wait() in
include/net/sock.h. This was the only place in the kernel that needed
this information.
Drivers should no longer access any of the poll_table internals, but use
the poll_requested_events() and poll_does_not_wait() access functions
instead. In order to enforce that the poll_table fields are now prepended
with an underscore and a comment was added warning against using them
directly.
This required a change in unix_dgram_poll() in unix/af_unix.c which used
the key field to get the requested events. It's been replaced by a call
to poll_requested_events().
For qproc it was especially important to change its name since the
behavior of that field changes with this patch since this function pointer
can now be NULL when that wasn't possible in the past.
Any driver accessing the qproc or key fields directly will now fail to compile.
Some notes regarding the correctness of this patch: the driver's poll()
function is called with a 'struct poll_table_struct *wait' argument. This
pointer may or may not be NULL, drivers can never rely on it being one or
the other as that depends on whether or not an earlier file descriptor in
the select()'s fdset matched the requested events.
There are only three things a driver can do with the wait argument:
1) obtain the key field:
events = wait ? wait->key : ~0;
This will still work although it should be replaced with the new
poll_requested_events() function (which does exactly the same).
This will now even work better, since wait is no longer set to NULL
unnecessarily.
2) use the qproc callback. This could be deadly since qproc can now be
NULL. Renaming qproc should prevent this from happening. There are no
kernel drivers that actually access this callback directly, BTW.
3) test whether wait == NULL to determine whether poll would return without
waiting. This is no longer sufficient as the correct test is now
wait == NULL || wait->_qproc == NULL.
However, the worst that can happen here is a slight performance hit in
the case where wait != NULL and wait->_qproc == NULL. In that case the
driver will assume that poll_wait() will actually add the fd to the set
of waiting file descriptors. Of course, poll_wait() will not do that
since it tests for wait->_qproc. This will not break anything, though.
There is only one place in the whole kernel where this happens
(sock_poll_wait() in include/net/sock.h) and that code will be replaced
by a call to poll_does_not_wait() in the next patch.
Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait()
actually waiting. The next file descriptor from the set might match the
event mask and thus any possible waits will never happen.
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jonathan Corbet <corbet@lwn.net>
Reviewed-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Cc: David Miller <davem@davemloft.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-23 15:02:27 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
2018-02-01 15:21:13 -05:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: remove ep_call_nested() from ep_eventpoll_poll()
The use of ep_call_nested() in ep_eventpoll_poll(), which is the .poll
routine for an epoll fd, is used to prevent excessively deep epoll
nesting, and to prevent circular paths.
However, we are already preventing these conditions during
EPOLL_CTL_ADD. In terms of too deep epoll chains, we do in fact allow
deep nesting of the epoll fds themselves (deeper than EP_MAX_NESTS),
however we don't allow more than EP_MAX_NESTS when an epoll file
descriptor is actually connected to a wakeup source. Thus, we do not
require the use of ep_call_nested(), since ep_eventpoll_poll(), which is
called via ep_scan_ready_list() only continues nesting if there are
events available.
Since ep_call_nested() is implemented using a global lock, applications
that make use of nested epoll can see large performance improvements
with this change.
Davidlohr said:
: Improvements are quite obscene actually, such as for the following
: epoll_wait() benchmark with 2 level nesting on a 80 core IvyBridge:
:
: ncpus vanilla dirty delta
: 1 2447092 3028315 +23.75%
: 4 231265 2986954 +1191.57%
: 8 121631 2898796 +2283.27%
: 16 59749 2902056 +4757.07%
: 32 26837 2326314 +8568.30%
: 64 12926 1341281 +10276.61%
:
: (http://linux-scalability.org/epoll/epoll-test.c)
Link: http://lkml.kernel.org/r/1509430214-5599-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Cc: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:06 -08:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2009-03-31 15:24:14 -07:00
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2018-02-01 15:21:13 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:14 -07:00
|
|
|
|
2018-02-01 15:21:13 -05:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-30 22:57:33 -03:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-04-30 15:27:39 -07:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2018-02-01 15:21:13 -05:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
|
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
|
|
|
|
|
epoll: optimizations and cleanups
Epoll is doing multiple passes over the ready set at the moment, because of
the constraints over the f_op->poll() call. Looking at the code again, I
noticed that we already hold the epoll semaphore in read, and this
(together with other locking conditions that hold while doing an
epoll_wait()) can lead to a smarter way [1] to "ship" events to userspace
(in a single pass).
This is a stress application that can be used to test the new code. It
spwans multiple thread and call epoll_wait() and epoll_ctl() from many
threads. Stress tested on my dual Opteron 254 w/out any problems.
http://www.xmailserver.org/totalmess.c
This is not a benchmark, just something that tries to stress and exploit
possible problems with the new code.
Also, I made a stupid micro-benchmark:
http://www.xmailserver.org/epwbench.c
[1] Considering that epoll must be thread-safe, there are five ways we can
be hit during an epoll_wait() transfer loop (ep_send_events()):
1) The epoll fd going away and calling ep_free
This just can't happen, since we did an fget() in sys_epoll_wait
2) An epoll_ctl(EPOLL_CTL_DEL)
This can't happen because epoll_ctl() gets ep->sem in write, and
we're holding it in read during ep_send_events()
3) An fd stored inside the epoll fd going away
This can't happen because in eventpoll_release_file() we get
ep->sem in write, and we're holding it in read during
ep_send_events()
4) Another epoll_wait() happening on another thread
They both can be inside ep_send_events() at the same time, we get
(splice) the ready-list under the spinlock, so each one will get
its own ready list. Note that an fd cannot be at the same time
inside more than one ready list, because ep_poll_callback() will
not re-queue it if it sees it already linked:
if (ep_is_linked(&epi->rdllink))
goto is_linked;
Another case that can happen, is two concurrent epoll_wait(),
coming in with a userspace event buffer of size, say, ten.
Suppose there are 50 event ready in the list. The first
epoll_wait() will "steal" the whole list, while the second, seeing
no events, will go to sleep. But at the end of ep_send_events() in
the first epoll_wait(), we will re-inject surplus ready fds, and we
will trigger the proper wake_up to the second epoll_wait().
5) ep_poll_callback() hitting us asyncronously
This is the tricky part. As I said above, the ep_is_linked() test
done inside ep_poll_callback(), will guarantee us that until the
item will result linked to a list, ep_poll_callback() will not try
to re-queue it again (read, write data on any of its members). When
we do a list_del() in ep_send_events(), the item will still satisfy
the ep_is_linked() test (whatever data is written in prev/next,
it'll never be its own pointer), so ep_poll_callback() will still
leave us alone. It's only after the eventual smp_mb()+INIT_LIST_HEAD(&epi->rdllink)
that it'll become visible to ep_poll_callback(), but at the point
we're already past it.
[akpm@osdl.org: 80 cols]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 00:25:41 -07:00
|
|
|
|
2018-02-01 15:21:13 -05:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2016-05-19 17:09:05 -07:00
|
|
|
|
2011-02-01 15:52:35 -08:00
|
|
|
|
2016-05-19 17:09:05 -07:00
|
|
|
|
2011-02-01 15:52:35 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-19 17:09:05 -07:00
|
|
|
|
|
|
|
|
|
2011-02-01 15:52:35 -08:00
|
|
|
|
|
|
|
|
|
2011-03-22 16:34:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-22 16:34:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
timer: convert timer_slack_ns from unsigned long to u64
This patchset introduces a /proc/<pid>/timerslack_ns interface which
would allow controlling processes to be able to set the timerslack value
on other processes in order to save power by avoiding wakeups (Something
Android currently does via out-of-tree patches).
The first patch tries to fix the internal timer_slack_ns usage which was
defined as a long, which limits the slack range to ~4 seconds on 32bit
systems. It converts it to a u64, which provides the same basically
unlimited slack (500 years) on both 32bit and 64bit machines.
The second patch introduces the /proc/<pid>/timerslack_ns interface
which allows the full 64bit slack range for a task to be read or set on
both 32bit and 64bit machines.
With these two patches, on a 32bit machine, after setting the slack on
bash to 10 seconds:
$ time sleep 1
real 0m10.747s
user 0m0.001s
sys 0m0.005s
The first patch is a little ugly, since I had to chase the slack delta
arguments through a number of functions converting them to u64s. Let me
know if it makes sense to break that up more or not.
Other than that things are fairly straightforward.
This patch (of 2):
The timer_slack_ns value in the task struct is currently a unsigned
long. This means that on 32bit applications, the maximum slack is just
over 4 seconds. However, on 64bit machines, its much much larger (~500
years).
This disparity could make application development a little (as well as
the default_slack) to a u64. This means both 32bit and 64bit systems
have the same effective internal slack range.
Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify
the interface as a unsigned long, so we preserve that limitation on
32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned
long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is
actually larger then what can be stored by an unsigned long.
This patch also modifies hrtimer functions which specified the slack
delta as a unsigned long.
Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Oren Laadan <orenl@cellrox.com>
Cc: Ruchi Kandoi <kandoiruchi@google.com>
Cc: Rom Lemarchand <romlem@android.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Android Kernel Team <kernel-team@android.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-17 14:20:51 -07:00
|
|
|
|
2017-06-20 12:06:13 +02:00
|
|
|
|
2010-10-27 15:34:54 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-05-19 17:09:05 -07:00
|
|
|
|
2011-02-01 15:52:35 -08:00
|
|
|
|
2010-10-27 15:34:54 -07:00
|
|
|
|
|
|
|
|
|
2016-05-19 17:09:05 -07:00
|
|
|
|
2010-10-27 15:34:54 -07:00
|
|
|
|
2011-03-22 16:34:47 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-27 15:34:54 -07:00
|
|
|
|
2011-03-22 16:34:47 -07:00
|
|
|
|
|
|
|
|
|
2010-10-27 15:34:54 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-22 16:34:47 -07:00
|
|
|
|
2017-03-24 10:08:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-22 16:34:46 -07:00
|
|
|
|
2017-03-24 10:08:30 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-05-07 14:33:26 +08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-07-10 15:52:33 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-03-22 16:34:46 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2013-10-29 13:12:56 +01:00
|
|
|
|
2010-10-27 15:34:54 -07:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2015-02-13 14:39:08 -08:00
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-22 16:34:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2011-03-22 16:34:46 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2010-10-27 15:34:54 -07:00
|
|
|
|
2011-03-22 16:34:47 -07:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2011-10-31 17:13:14 -07:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
2017-09-08 16:15:18 -07:00
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2008-08-12 15:09:01 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2009-01-14 14:14:25 +01:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
2009-03-31 15:24:12 -07:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2008-07-23 21:29:42 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:11 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2009-03-31 15:24:12 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2008-07-23 21:29:43 -07:00
|
|
|
|
2009-03-31 15:24:12 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2008-02-23 06:46:49 -05:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-12-18 09:41:24 -08:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-17 22:42:36 -04:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-03-31 15:24:12 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2009-01-14 14:14:25 +01:00
|
|
|
|
2008-07-23 21:29:27 -07:00
|
|
|
|
2009-05-12 13:19:44 -07:00
|
|
|
|
2008-07-23 21:29:43 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2008-07-23 21:29:27 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:52 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2009-01-14 14:14:25 +01:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
2013-08-30 12:47:21 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-08-30 12:47:21 -04:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-08-30 12:47:21 -04:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-09-22 16:27:52 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2014-09-09 14:50:51 -07:00
|
|
|
|
|
|
|
|
|
2012-05-01 21:33:34 +02:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-08-30 12:47:21 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2016-01-20 14:59:24 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-02-27 14:27:40 -08:00
|
|
|
|
epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
In the current implementation of the EPOLLEXCLUSIVE flag (added for
4.5-rc1), if epoll waiters create different POLL* sets and register them
as exclusive against the same target fd, the current implementation will
stop waking any further waiters once it finds the first idle waiter.
This means that waiters could miss wakeups in certain cases.
For example, when we wake up a pipe for reading we do:
wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); So if
one epoll set or epfd is added to pipe p with POLLIN and a second set
epfd2 is added to pipe p with POLLRDNORM, only epfd may receive the
wakeup since the current implementation will stop after it finds any
intersection of events with a waiter that is blocked in epoll_wait().
We could potentially address this by requiring all epoll waiters that
are added to p be required to pass the same set of POLL* events. IE the
first EPOLL_CTL_ADD that passes EPOLLEXCLUSIVE establishes the set POLL*
flags to be used by any other epfds that are added as EPOLLEXCLUSIVE.
However, I think it might be somewhat confusing interface as we would
have to reference count the number of users for that set, and so
userspace would have to keep track of that count, or we would need a
more involved interface. It also adds some shared state that we'd have
store somewhere. I don't think anybody will want to bloat
__wait_queue_head for this.
I think what we could do instead, is to simply restrict EPOLLEXCLUSIVE
such that it can only be specified with EPOLLIN and/or EPOLLOUT. So
that way if the wakeup includes 'POLLIN' and not 'POLLOUT', we can stop
once we hit the first idle waiter that specifies the EPOLLIN bit, since
any remaining waiters that only have 'POLLOUT' set wouldn't need to be
woken. Likewise, we can do the same thing if 'POLLOUT' is in the wakeup
bit set and not 'POLLIN'. If both 'POLLOUT' and 'POLLIN' are set in the
wake bit set (there is at least one example of this I saw in fs/pipe.c),
then we just wake the entire exclusive list. Having both 'POLLOUT' and
'POLLIN' both set should not be on any performance critical path, so I
think that's ok (in fs/pipe.c its in pipe_release()). We also continue
to include EPOLLERR and EPOLLHUP by default in any exclusive set. Thus,
the user can specify EPOLLERR and/or EPOLLHUP but is not required to do
so.
Since epoll waiters may be interested in other events as well besides
EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP, these can still be added by
doing a 'dup' call on the target fd and adding that as one normally
would with EPOLL_CTL_ADD. Since I think that the POLLIN and POLLOUT
events are what we are interest in balancing, I think that the 'dup'
thing could perhaps be added to only one of the waiter threads.
However, I think that EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP should be
sufficient for the majority of use-cases.
Since EPOLLEXCLUSIVE is intended to be used with a target fd shared
among multiple epfds, where between 1 and n of the epfds may receive an
event, it does not satisfy the semantics of EPOLLONESHOT where only 1
epfd would get an event. Thus, it is not allowed to be specified in
conjunction with EPOLLEXCLUSIVE.
EPOLL_CTL_MOD is also not allowed if the fd was previously added as
EPOLLEXCLUSIVE. It seems with the limited number of flags to not be as
interesting, but this could be relaxed at some further point.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Tested-by: Madars Vitolins <m@silodev.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-05 15:37:04 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2016-01-20 14:59:24 -08:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-08-30 12:47:21 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-12 17:17:43 -08:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-04-25 16:01:47 -07:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2007-05-15 01:40:52 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-08-30 12:47:21 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
In the current implementation of the EPOLLEXCLUSIVE flag (added for
4.5-rc1), if epoll waiters create different POLL* sets and register them
as exclusive against the same target fd, the current implementation will
stop waking any further waiters once it finds the first idle waiter.
This means that waiters could miss wakeups in certain cases.
For example, when we wake up a pipe for reading we do:
wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); So if
one epoll set or epfd is added to pipe p with POLLIN and a second set
epfd2 is added to pipe p with POLLRDNORM, only epfd may receive the
wakeup since the current implementation will stop after it finds any
intersection of events with a waiter that is blocked in epoll_wait().
We could potentially address this by requiring all epoll waiters that
are added to p be required to pass the same set of POLL* events. IE the
first EPOLL_CTL_ADD that passes EPOLLEXCLUSIVE establishes the set POLL*
flags to be used by any other epfds that are added as EPOLLEXCLUSIVE.
However, I think it might be somewhat confusing interface as we would
have to reference count the number of users for that set, and so
userspace would have to keep track of that count, or we would need a
more involved interface. It also adds some shared state that we'd have
store somewhere. I don't think anybody will want to bloat
__wait_queue_head for this.
I think what we could do instead, is to simply restrict EPOLLEXCLUSIVE
such that it can only be specified with EPOLLIN and/or EPOLLOUT. So
that way if the wakeup includes 'POLLIN' and not 'POLLOUT', we can stop
once we hit the first idle waiter that specifies the EPOLLIN bit, since
any remaining waiters that only have 'POLLOUT' set wouldn't need to be
woken. Likewise, we can do the same thing if 'POLLOUT' is in the wakeup
bit set and not 'POLLIN'. If both 'POLLOUT' and 'POLLIN' are set in the
wake bit set (there is at least one example of this I saw in fs/pipe.c),
then we just wake the entire exclusive list. Having both 'POLLOUT' and
'POLLIN' both set should not be on any performance critical path, so I
think that's ok (in fs/pipe.c its in pipe_release()). We also continue
to include EPOLLERR and EPOLLHUP by default in any exclusive set. Thus,
the user can specify EPOLLERR and/or EPOLLHUP but is not required to do
so.
Since epoll waiters may be interested in other events as well besides
EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP, these can still be added by
doing a 'dup' call on the target fd and adding that as one normally
would with EPOLL_CTL_ADD. Since I think that the POLLIN and POLLOUT
events are what we are interest in balancing, I think that the 'dup'
thing could perhaps be added to only one of the waiter threads.
However, I think that EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP should be
sufficient for the majority of use-cases.
Since EPOLLEXCLUSIVE is intended to be used with a target fd shared
among multiple epfds, where between 1 and n of the epfds may receive an
event, it does not satisfy the semantics of EPOLLONESHOT where only 1
epfd would get an event. Thus, it is not allowed to be specified in
conjunction with EPOLLEXCLUSIVE.
EPOLL_CTL_MOD is also not allowed if the fd was previously added as
EPOLLEXCLUSIVE. It seems with the limited number of flags to not be as
interesting, but this could be relaxed at some further point.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Tested-by: Madars Vitolins <m@silodev.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-05 15:37:04 -08:00
|
|
|
|
2018-02-11 14:34:03 -08:00
|
|
|
|
epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
In the current implementation of the EPOLLEXCLUSIVE flag (added for
4.5-rc1), if epoll waiters create different POLL* sets and register them
as exclusive against the same target fd, the current implementation will
stop waking any further waiters once it finds the first idle waiter.
This means that waiters could miss wakeups in certain cases.
For example, when we wake up a pipe for reading we do:
wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); So if
one epoll set or epfd is added to pipe p with POLLIN and a second set
epfd2 is added to pipe p with POLLRDNORM, only epfd may receive the
wakeup since the current implementation will stop after it finds any
intersection of events with a waiter that is blocked in epoll_wait().
We could potentially address this by requiring all epoll waiters that
are added to p be required to pass the same set of POLL* events. IE the
first EPOLL_CTL_ADD that passes EPOLLEXCLUSIVE establishes the set POLL*
flags to be used by any other epfds that are added as EPOLLEXCLUSIVE.
However, I think it might be somewhat confusing interface as we would
have to reference count the number of users for that set, and so
userspace would have to keep track of that count, or we would need a
more involved interface. It also adds some shared state that we'd have
store somewhere. I don't think anybody will want to bloat
__wait_queue_head for this.
I think what we could do instead, is to simply restrict EPOLLEXCLUSIVE
such that it can only be specified with EPOLLIN and/or EPOLLOUT. So
that way if the wakeup includes 'POLLIN' and not 'POLLOUT', we can stop
once we hit the first idle waiter that specifies the EPOLLIN bit, since
any remaining waiters that only have 'POLLOUT' set wouldn't need to be
woken. Likewise, we can do the same thing if 'POLLOUT' is in the wakeup
bit set and not 'POLLIN'. If both 'POLLOUT' and 'POLLIN' are set in the
wake bit set (there is at least one example of this I saw in fs/pipe.c),
then we just wake the entire exclusive list. Having both 'POLLOUT' and
'POLLIN' both set should not be on any performance critical path, so I
think that's ok (in fs/pipe.c its in pipe_release()). We also continue
to include EPOLLERR and EPOLLHUP by default in any exclusive set. Thus,
the user can specify EPOLLERR and/or EPOLLHUP but is not required to do
so.
Since epoll waiters may be interested in other events as well besides
EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP, these can still be added by
doing a 'dup' call on the target fd and adding that as one normally
would with EPOLL_CTL_ADD. Since I think that the POLLIN and POLLOUT
events are what we are interest in balancing, I think that the 'dup'
thing could perhaps be added to only one of the waiter threads.
However, I think that EPOLLIN, EPOLLOUT, EPOLLERR and EPOLLHUP should be
sufficient for the majority of use-cases.
Since EPOLLEXCLUSIVE is intended to be used with a target fd shared
among multiple epfds, where between 1 and n of the epfds may receive an
event, it does not satisfy the semantics of EPOLLONESHOT where only 1
epfd would get an event. Thus, it is not allowed to be specified in
conjunction with EPOLLEXCLUSIVE.
EPOLL_CTL_MOD is also not allowed if the fd was previously added as
EPOLLEXCLUSIVE. It seems with the limited number of flags to not be as
interesting, but this could be relaxed at some further point.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Tested-by: Madars Vitolins <m@silodev.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-05 15:37:04 -08:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:41 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2013-11-12 15:10:18 -08:00
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
2013-08-30 12:47:21 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2013-08-30 12:47:21 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-01-14 14:14:25 +01:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2012-08-28 12:52:22 -04:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-28 12:52:22 -04:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
2012-08-28 12:52:22 -04:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-28 12:52:22 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-28 12:52:22 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2012-08-28 12:52:22 -04:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-01-14 14:14:25 +01:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-07-03 15:08:14 -07:00
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-15 01:40:47 -07:00
|
|
|
|
2008-04-30 00:53:06 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
2013-07-03 15:08:14 -07:00
|
|
|
|
2007-05-10 22:23:23 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-02-24 14:52:17 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-09-03 21:45:17 -04:00
|
|
|
|
2013-02-24 14:52:17 -05:00
|
|
|
|
2013-07-03 15:08:14 -07:00
|
|
|
|
|
|
|
|
|
2013-02-24 14:52:17 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2013-07-03 15:08:14 -07:00
|
|
|
|
2013-02-24 14:52:17 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2009-01-29 14:25:26 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: introduce resource usage limits
It has been thought that the per-user file descriptors limit would also
limit the resources that a normal user can request via the epoll
interface. Vegard Nossum reported a very simple program (a modified
version attached) that can make a normal user to request a pretty large
amount of kernel memory, well within the its maximum number of fds. To
solve such problem, default limits are now imposed, and /proc based
configuration has been introduced. A new directory has been created,
named /proc/sys/fs/epoll/ and inside there, there are two configuration
points:
max_user_instances = Maximum number of devices - per user
max_user_watches = Maximum number of "watched" fds - per user
The current default for "max_user_watches" limits the memory used by epoll
to store "watches", to 1/32 of the amount of the low RAM. As example, a
256MB 32bit machine, will have "max_user_watches" set to roughly 90000.
That should be enough to not break existing heavy epoll users. The
default value for "max_user_instances" is set to 128, that should be
enough too.
This also changes the userspace, because a new error code can now come out
from EPOLL_CTL_ADD (-ENOSPC). The EMFILE from epoll_create() was already
listed, so that should be ok.
[akpm@linux-foundation.org: use get_current_user()]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <stable@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Vegard Nossum <vegardno@ifi.uio.no>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 13:13:55 -08:00
|
|
|
|
2011-01-12 17:00:01 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: prevent creating circular epoll structures
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-25 14:44:12 -08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
epoll: avoid calling ep_call_nested() from ep_poll_safewake()
ep_poll_safewake() is used to wakeup potentially nested epoll file
descriptors. The function uses ep_call_nested() to prevent entering the
same wake up queue more than once, and to prevent excessively deep
wakeup paths (deeper than EP_MAX_NESTS). However, this is not necessary
since we are already preventing these conditions during EPOLL_CTL_ADD.
This saves extra function calls, and avoids taking a global lock during
the ep_call_nested() calls.
I have, however, left ep_call_nested() for the CONFIG_DEBUG_LOCK_ALLOC
case, since ep_call_nested() keeps track of the nesting level, and this
is required by the call to spin_lock_irqsave_nested(). It would be nice
to remove the ep_call_nested() calls for the CONFIG_DEBUG_LOCK_ALLOC
case as well, however its not clear how to simply pass the nesting level
through multiple wake_up() levels without more surgery. In any case, I
don't think CONFIG_DEBUG_LOCK_ALLOC is generally used for production.
This patch, also apparently fixes a workload at Google that Salman Qazi
reported by completely removing the poll_safewake_ncalls->lock from
wakeup paths.
Link: http://lkml.kernel.org/r/1507920533-8812-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:02 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
epoll: fix epoll's own poll
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-03-31 15:24:10 -07:00
|
|
|
|
epoll: avoid calling ep_call_nested() from ep_poll_safewake()
ep_poll_safewake() is used to wakeup potentially nested epoll file
descriptors. The function uses ep_call_nested() to prevent entering the
same wake up queue more than once, and to prevent excessively deep
wakeup paths (deeper than EP_MAX_NESTS). However, this is not necessary
since we are already preventing these conditions during EPOLL_CTL_ADD.
This saves extra function calls, and avoids taking a global lock during
the ep_call_nested() calls.
I have, however, left ep_call_nested() for the CONFIG_DEBUG_LOCK_ALLOC
case, since ep_call_nested() keeps track of the nesting level, and this
is required by the call to spin_lock_irqsave_nested(). It would be nice
to remove the ep_call_nested() calls for the CONFIG_DEBUG_LOCK_ALLOC
case as well, however its not clear how to simply pass the nesting level
through multiple wake_up() levels without more surgery. In any case, I
don't think CONFIG_DEBUG_LOCK_ALLOC is generally used for production.
This patch, also apparently fixes a workload at Google that Salman Qazi
reported by completely removing the poll_safewake_ncalls->lock from
wakeup paths.
Link: http://lkml.kernel.org/r/1507920533-8812-1-git-send-email-jbaron@akamai.com
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Salman Qazi <sqazi@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 15:29:02 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
2013-04-30 15:27:38 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
2017-11-17 15:28:59 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2017-11-17 15:28:59 -08:00
|
|
|
|
2005-04-16 15:20:36 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2007-05-10 22:23:22 -07:00
|
|
|
|
