linux-sg2042/fs/eventpoll.c

1441 lines
39 KiB
C
Raw Normal View History

/*
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>
2009-04-01 06:24:10 +08:00
* fs/eventpoll.c (Efficient event retrieval implementation)
* Copyright (C) 2001,...,2009 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.
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
#include <linux/rbtree.h>
#include <linux/wait.h>
#include <linux/eventpoll.h>
#include <linux/mount.h>
#include <linux/bitops.h>
#include <linux/mutex.h>
#include <linux/anon_inodes.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/mman.h>
#include <asm/atomic.h>
/*
* LOCKING:
* There are three level of locking required by epoll :
*
* 1) epmutex (mutex)
* 2) ep->mtx (mutex)
* 3) ep->lock (spinlock)
*
* The acquire order is the one listed above, from 1 to 3.
* We need a spinlock (ep->lock) because we manipulate objects
* from inside the poll callback, that might be triggered from
* a wake_up() that in turn might be called from IRQ context.
* So we can't sleep inside the poll callback and hence we need
* a spinlock. During the event transfer loop (from kernel to
* user space) we could end up sleeping due a copy_to_user(), so
* we need a lock that will allow us to sleep. This lock is a
* mutex (ep->mtx). It is acquired during the event transfer loop,
* during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file().
* Then we also need a global mutex to serialize eventpoll_release_file()
* and ep_free().
* This mutex is acquired by ep_free() during the epoll file
* cleanup path and it is also acquired by eventpoll_release_file()
* if a file has been pushed inside an epoll set and it is then
* close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL).
* It is possible to drop the "ep->mtx" and to use the global
* mutex "epmutex" (together with "ep->lock") to have it working,
* but having "ep->mtx" will make the interface more scalable.
* Events that require holding "epmutex" are very rare, while for
* normal operations the epoll private "ep->mtx" will guarantee
* a better scalability.
*/
/* Epoll private bits inside the event mask */
#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET)
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>
2009-04-01 06:24:10 +08:00
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
/* Maximum msec timeout value storeable in a long int */
#define EP_MAX_MSTIMEO min(1000ULL * MAX_SCHEDULE_TIMEOUT / HZ, (LONG_MAX - 999ULL) / HZ)
#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
#define EP_UNACTIVE_PTR ((void *) -1L)
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>
2008-12-02 05:13:55 +08:00
#define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry))
struct epoll_filefd {
struct file *file;
int fd;
};
/*
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>
2009-04-01 06:24:10 +08:00
* Structure used to track possible nested calls, for too deep recursions
* and loop cycles.
*/
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>
2009-04-01 06:24:10 +08:00
struct nested_call_node {
struct list_head llink;
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>
2009-04-01 06:24:10 +08:00
void *cookie;
int cpu;
};
/*
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>
2009-04-01 06:24:10 +08:00
* This structure is used as collector for nested calls, to check for
* maximum recursion dept and loop cycles.
*/
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>
2009-04-01 06:24:10 +08:00
struct nested_calls {
struct list_head tasks_call_list;
spinlock_t lock;
};
/*
* Each file descriptor added to the eventpoll interface will
* have an entry of this type linked to the "rbr" RB tree.
*/
struct epitem {
/* RB tree node used to link this structure to the eventpoll RB tree */
struct rb_node rbn;
/* List header used to link this structure to the eventpoll ready list */
struct list_head rdllink;
/*
* Works together "struct eventpoll"->ovflist in keeping the
* single linked chain of items.
*/
struct epitem *next;
/* The file descriptor information this item refers to */
struct epoll_filefd ffd;
/* Number of active wait queue attached to poll operations */
int nwait;
/* List containing poll wait queues */
struct list_head pwqlist;
/* The "container" of this item */
struct eventpoll *ep;
/* List header used to link this item to the "struct file" items list */
struct list_head fllink;
/* The structure that describe the interested events and the source fd */
struct epoll_event event;
};
/*
* This structure is stored inside the "private_data" member of the file
* structure and rapresent the main data sructure for the eventpoll
* interface.
*/
struct eventpoll {
/* Protect the this structure access */
spinlock_t lock;
/*
* This mutex is used to ensure that files are not removed
* while epoll is using them. This is held during the event
* collection loop, the file cleanup path, the epoll file exit
* code and the ctl operations.
*/
struct mutex mtx;
/* Wait queue used by sys_epoll_wait() */
wait_queue_head_t wq;
/* Wait queue used by file->poll() */
wait_queue_head_t poll_wait;
/* List of ready file descriptors */
struct list_head rdllist;
/* RB tree root used to store monitored fd structs */
struct rb_root rbr;
/*
* This is a single linked list that chains all the "struct epitem" that
* happened while transfering ready events to userspace w/out
* holding ->lock.
*/
struct epitem *ovflist;
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>
2008-12-02 05:13:55 +08:00
/* The user that created the eventpoll descriptor */
struct user_struct *user;
};
/* Wait structure used by the poll hooks */
struct eppoll_entry {
/* List header used to link this structure to the "struct epitem" */
struct list_head llink;
/* The "base" pointer is set to the container "struct epitem" */
struct epitem *base;
/*
* Wait queue item that will be linked to the target file wait
* queue head.
*/
wait_queue_t wait;
/* The wait queue head that linked the "wait" wait queue item */
wait_queue_head_t *whead;
};
/* Wrapper struct used by poll queueing */
struct ep_pqueue {
poll_table pt;
struct epitem *epi;
};
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>
2009-04-01 06:24:10 +08:00
/* Used by the ep_send_events() function as callback private data */
struct ep_send_events_data {
int maxevents;
struct epoll_event __user *events;
};
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>
2008-12-02 05:13:55 +08:00
/*
* Configuration options available inside /proc/sys/fs/epoll/
*/
/* Maximum number of epoll watched descriptors, per user */
static int max_user_watches __read_mostly;
/*
* This mutex is used to serialize ep_free() and eventpoll_release_file().
*/
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>
2008-12-02 05:13:55 +08:00
static DEFINE_MUTEX(epmutex);
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>
2009-04-01 06:24:10 +08:00
/* Used for safe wake up implementation */
static struct nested_calls poll_safewake_ncalls;
/* Used to call file's f_op->poll() under the nested calls boundaries */
static struct nested_calls poll_readywalk_ncalls;
/* Slab cache used to allocate "struct epitem" */
static struct kmem_cache *epi_cache __read_mostly;
/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __read_mostly;
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>
2008-12-02 05:13:55 +08:00
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
static int zero;
ctl_table epoll_table[] = {
{
.procname = "max_user_watches",
.data = &max_user_watches,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = &proc_dointvec_minmax,
.extra1 = &zero,
},
{ .ctl_name = 0 }
};
#endif /* CONFIG_SYSCTL */
/* Setup the structure that is used as key for the RB tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
struct file *file, int fd)
{
ffd->file = file;
ffd->fd = fd;
}
/* Compare RB tree keys */
static inline int ep_cmp_ffd(struct epoll_filefd *p1,
struct epoll_filefd *p2)
{
return (p1->file > p2->file ? +1:
(p1->file < p2->file ? -1 : p1->fd - p2->fd));
}
/* Tells us if the item is currently linked */
static inline int ep_is_linked(struct list_head *p)
{
return !list_empty(p);
}
/* Get the "struct epitem" from a wait queue pointer */
static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
{
return container_of(p, struct eppoll_entry, wait)->base;
}
/* Get the "struct epitem" from an epoll queue wrapper */
static inline struct epitem *ep_item_from_epqueue(poll_table *p)
{
return container_of(p, struct ep_pqueue, pt)->epi;
}
/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
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 15:25:41 +08:00
static inline int ep_op_has_event(int op)
{
return op != EPOLL_CTL_DEL;
}
/* Initialize the poll safe wake up structure */
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>
2009-04-01 06:24:10 +08:00
static void ep_nested_calls_init(struct nested_calls *ncalls)
{
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>
2009-04-01 06:24:10 +08:00
INIT_LIST_HEAD(&ncalls->tasks_call_list);
spin_lock_init(&ncalls->lock);
}
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>
2009-04-01 06:24:10 +08:00
/**
* ep_call_nested - Perform a bound (possibly) nested call, by checking
* that the recursion limit is not exceeded, and that
* the same nested call (by the meaning of same cookie) is
* no re-entered.
*
* @ncalls: Pointer to the nested_calls structure to be used for this call.
* @max_nests: Maximum number of allowed nesting calls.
* @nproc: Nested call core function pointer.
* @priv: Opaque data to be passed to the @nproc callback.
* @cookie: Cookie to be used to identify this nested call.
*
* Returns: Returns the code returned by the @nproc callback, or -1 if
* the maximum recursion limit has been exceeded.
*/
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>
2009-04-01 06:24:10 +08:00
static int ep_call_nested(struct nested_calls *ncalls, int max_nests,
int (*nproc)(void *, void *, int), void *priv,
void *cookie)
{
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>
2009-04-01 06:24:10 +08:00
int error, call_nests = 0;
unsigned long flags;
int this_cpu = get_cpu();
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>
2009-04-01 06:24:10 +08:00
struct list_head *lsthead = &ncalls->tasks_call_list;
struct nested_call_node *tncur;
struct nested_call_node tnode;
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>
2009-04-01 06:24:10 +08:00
spin_lock_irqsave(&ncalls->lock, flags);
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>
2009-04-01 06:24:10 +08:00
/*
* Try to see if the current task is already inside this wakeup call.
* We use a list here, since the population inside this set is always
* very much limited.
*/
list_for_each_entry(tncur, lsthead, llink) {
if (tncur->cpu == this_cpu &&
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>
2009-04-01 06:24:10 +08:00
(tncur->cookie == cookie || ++call_nests > max_nests)) {
/*
* Ops ... loop detected or maximum nest level reached.
* We abort this wake by breaking the cycle itself.
*/
error = -1;
goto out_unlock;
}
}
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>
2009-04-01 06:24:10 +08:00
/* Add the current task and cookie to the list */
tnode.cpu = this_cpu;
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>
2009-04-01 06:24:10 +08:00
tnode.cookie = cookie;
list_add(&tnode.llink, lsthead);
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>
2009-04-01 06:24:10 +08:00
spin_unlock_irqrestore(&ncalls->lock, flags);
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>
2009-04-01 06:24:10 +08:00
/* Call the nested function */
error = (*nproc)(priv, cookie, call_nests);
/* Remove the current task from the list */
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>
2009-04-01 06:24:10 +08:00
spin_lock_irqsave(&ncalls->lock, flags);
list_del(&tnode.llink);
out_unlock:
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>
2009-04-01 06:24:10 +08:00
spin_unlock_irqrestore(&ncalls->lock, flags);
put_cpu();
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>
2009-04-01 06:24:10 +08:00
return error;
}
#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
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>
2009-04-01 06:24:10 +08:00
static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
{
ep_wake_up_nested((wait_queue_head_t *) cookie, POLLIN,
1 + call_nests);
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>
2009-04-01 06:24:10 +08:00
return 0;
}
/*
* Perform a safe wake up of the poll wait list. The problem is that
* with the new callback'd wake up system, it is possible that the
* poll callback is reentered from inside the call to wake_up() done
* on the poll wait queue head. The rule is that we cannot reenter the
* wake up code from the same task more than EP_MAX_NESTS times,
* and we cannot reenter the same wait queue head at all. This will
* enable to have a hierarchy of epoll file descriptor of no more than
* EP_MAX_NESTS deep.
*/
static void ep_poll_safewake(wait_queue_head_t *wq)
{
ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
ep_poll_wakeup_proc, NULL, wq);
}
/*
* This function unregisters poll callbacks from the associated file
* descriptor. Must be called with "mtx" held (or "epmutex" if called from
* ep_free).
*/
static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
{
struct list_head *lsthead = &epi->pwqlist;
struct eppoll_entry *pwq;
while (!list_empty(lsthead)) {
pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
list_del(&pwq->llink);
remove_wait_queue(pwq->whead, &pwq->wait);
kmem_cache_free(pwq_cache, pwq);
}
}
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>
2009-04-01 06:24:10 +08:00
/**
* ep_scan_ready_list - Scans the ready list in a way that makes possible for
* the scan code, to call f_op->poll(). Also allows for
* O(NumReady) performance.
*
* @ep: Pointer to the epoll private data structure.
* @sproc: Pointer to the scan callback.
* @priv: Private opaque data passed to the @sproc callback.
*
* Returns: The same integer error code returned by the @sproc callback.
*/
static int ep_scan_ready_list(struct eventpoll *ep,
int (*sproc)(struct eventpoll *,
struct list_head *, void *),
void *priv)
{
int error, pwake = 0;
unsigned long flags;
struct epitem *epi, *nepi;
LIST_HEAD(txlist);
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>
2009-04-01 06:24:10 +08:00
/*
* We need to lock this because we could be hit by
* eventpoll_release_file() and epoll_ctl().
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>
2009-04-01 06:24:10 +08:00
*/
mutex_lock(&ep->mtx);
/*
* Steal the ready list, and re-init the original one to the
* empty list. Also, set ep->ovflist to NULL so that events
* happening while looping w/out locks, are not lost. We cannot
* have the poll callback to queue directly on ep->rdllist,
* because we want the "sproc" callback to be able to do it
* in a lockless way.
*/
spin_lock_irqsave(&ep->lock, flags);
list_splice_init(&ep->rdllist, &txlist);
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>
2009-04-01 06:24:10 +08:00
ep->ovflist = NULL;
spin_unlock_irqrestore(&ep->lock, flags);
/*
* Now call the callback function.
*/
error = (*sproc)(ep, &txlist, priv);
spin_lock_irqsave(&ep->lock, flags);
/*
* During the time we spent inside the "sproc" callback, some
* other events might have been queued by the poll callback.
* We re-insert them inside the main ready-list here.
*/
for (nepi = ep->ovflist; (epi = nepi) != NULL;
nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
/*
* We need to check if the item is already in the list.
* During the "sproc" callback execution time, items are
* queued into ->ovflist but the "txlist" might already
* contain them, and the list_splice() below takes care of them.
*/
if (!ep_is_linked(&epi->rdllink))
list_add_tail(&epi->rdllink, &ep->rdllist);
}
/*
* We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
* releasing the lock, events will be queued in the normal way inside
* ep->rdllist.
*/
ep->ovflist = EP_UNACTIVE_PTR;
/*
* Quickly re-inject items left on "txlist".
*/
list_splice(&txlist, &ep->rdllist);
if (!list_empty(&ep->rdllist)) {
/*
* Wake up (if active) both the eventpoll wait list and
* the ->poll() wait list (delayed after we release the lock).
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>
2009-04-01 06:24:10 +08:00
*/
if (waitqueue_active(&ep->wq))
wake_up_locked(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
spin_unlock_irqrestore(&ep->lock, flags);
mutex_unlock(&ep->mtx);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&ep->poll_wait);
return error;
}
/*
* Removes a "struct epitem" from the eventpoll RB tree and deallocates
* all the associated resources. Must be called with "mtx" held.
*/
static int ep_remove(struct eventpoll *ep, struct epitem *epi)
{
unsigned long flags;
struct file *file = epi->ffd.file;
/*
* Removes poll wait queue hooks. We _have_ to do this without holding
* the "ep->lock" otherwise a deadlock might occur. This because of the
* sequence of the lock acquisition. Here we do "ep->lock" then the wait
* queue head lock when unregistering the wait queue. The wakeup callback
* will run by holding the wait queue head lock and will call our callback
* that will try to get "ep->lock".
*/
ep_unregister_pollwait(ep, epi);
/* Remove the current item from the list of epoll hooks */
spin_lock(&file->f_lock);
if (ep_is_linked(&epi->fllink))
list_del_init(&epi->fllink);
spin_unlock(&file->f_lock);
rb_erase(&epi->rbn, &ep->rbr);
spin_lock_irqsave(&ep->lock, flags);
if (ep_is_linked(&epi->rdllink))
list_del_init(&epi->rdllink);
spin_unlock_irqrestore(&ep->lock, flags);
/* At this point it is safe to free the eventpoll item */
kmem_cache_free(epi_cache, epi);
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>
2008-12-02 05:13:55 +08:00
atomic_dec(&ep->user->epoll_watches);
return 0;
}
static void ep_free(struct eventpoll *ep)
{
struct rb_node *rbp;
struct epitem *epi;
/* We need to release all tasks waiting for these file */
if (waitqueue_active(&ep->poll_wait))
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>
2009-04-01 06:24:10 +08:00
ep_poll_safewake(&ep->poll_wait);
/*
* We need to lock this because we could be hit by
* eventpoll_release_file() while we're freeing the "struct eventpoll".
* We do not need to hold "ep->mtx" here because the epoll file
* is on the way to be removed and no one has references to it
* anymore. The only hit might come from eventpoll_release_file() but
* holding "epmutex" is sufficent here.
*/
mutex_lock(&epmutex);
/*
* Walks through the whole tree by unregistering poll callbacks.
*/
for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
epi = rb_entry(rbp, struct epitem, rbn);
ep_unregister_pollwait(ep, epi);
}
/*
* Walks through the whole tree by freeing each "struct epitem". At this
* point we are sure no poll callbacks will be lingering around, and also by
* holding "epmutex" we can be sure that no file cleanup code will hit
* us during this operation. So we can avoid the lock on "ep->lock".
*/
while ((rbp = rb_first(&ep->rbr)) != NULL) {
epi = rb_entry(rbp, struct epitem, rbn);
ep_remove(ep, epi);
}
mutex_unlock(&epmutex);
mutex_destroy(&ep->mtx);
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>
2008-12-02 05:13:55 +08:00
free_uid(ep->user);
kfree(ep);
}
static int ep_eventpoll_release(struct inode *inode, struct file *file)
{
struct eventpoll *ep = file->private_data;
if (ep)
ep_free(ep);
return 0;
}
static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
void *priv)
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>
2009-04-01 06:24:10 +08:00
{
struct epitem *epi, *tmp;
list_for_each_entry_safe(epi, tmp, head, rdllink) {
if (epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
epi->event.events)
return POLLIN | POLLRDNORM;
else {
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>
2009-04-01 06:24:10 +08:00
/*
* Item has been dropped into the ready list by the poll
* callback, but it's not actually ready, as far as
* caller requested events goes. We can remove it here.
*/
list_del_init(&epi->rdllink);
}
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>
2009-04-01 06:24:10 +08:00
}
return 0;
}
static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
{
return ep_scan_ready_list(priv, ep_read_events_proc, NULL);
}
static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
{
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>
2009-04-01 06:24:10 +08:00
int pollflags;
struct eventpoll *ep = file->private_data;
/* Insert inside our poll wait queue */
poll_wait(file, &ep->poll_wait, wait);
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>
2009-04-01 06:24:10 +08:00
/*
* Proceed to find out if wanted events are really available inside
* the ready list. This need to be done under ep_call_nested()
* supervision, since the call to f_op->poll() done on listed files
* could re-enter here.
*/
pollflags = ep_call_nested(&poll_readywalk_ncalls, EP_MAX_NESTS,
ep_poll_readyevents_proc, ep, ep);
return pollflags != -1 ? pollflags : 0;
}
/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
.release = ep_eventpoll_release,
.poll = ep_eventpoll_poll
};
/* Fast test to see if the file is an evenpoll file */
static inline int is_file_epoll(struct file *f)
{
return f->f_op == &eventpoll_fops;
}
/*
* This is called from eventpoll_release() to unlink files from the eventpoll
* interface. We need to have this facility to cleanup correctly files that are
* closed without being removed from the eventpoll interface.
*/
void eventpoll_release_file(struct file *file)
{
struct list_head *lsthead = &file->f_ep_links;
struct eventpoll *ep;
struct epitem *epi;
/*
* We don't want to get "file->f_lock" because it is not
* necessary. It is not necessary because we're in the "struct file"
* cleanup path, and this means that noone is using this file anymore.
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>
2009-04-01 06:24:10 +08:00
* So, for example, epoll_ctl() cannot hit here since if we reach this
* point, the file counter already went to zero and fget() would fail.
* The only hit might come from ep_free() but by holding the mutex
* will correctly serialize the operation. We do need to acquire
* "ep->mtx" after "epmutex" because ep_remove() requires it when called
* from anywhere but ep_free().
*
* Besides, ep_remove() acquires the lock, so we can't hold it here.
*/
mutex_lock(&epmutex);
while (!list_empty(lsthead)) {
epi = list_first_entry(lsthead, struct epitem, fllink);
ep = epi->ep;
list_del_init(&epi->fllink);
mutex_lock(&ep->mtx);
ep_remove(ep, epi);
mutex_unlock(&ep->mtx);
}
mutex_unlock(&epmutex);
}
static int ep_alloc(struct eventpoll **pep)
{
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>
2008-12-02 05:13:55 +08:00
int error;
struct user_struct *user;
struct eventpoll *ep;
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>
2008-12-02 05:13:55 +08:00
user = get_current_user();
error = -ENOMEM;
ep = kzalloc(sizeof(*ep), GFP_KERNEL);
if (unlikely(!ep))
goto free_uid;
spin_lock_init(&ep->lock);
mutex_init(&ep->mtx);
init_waitqueue_head(&ep->wq);
init_waitqueue_head(&ep->poll_wait);
INIT_LIST_HEAD(&ep->rdllist);
ep->rbr = RB_ROOT;
ep->ovflist = EP_UNACTIVE_PTR;
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>
2008-12-02 05:13:55 +08:00
ep->user = user;
*pep = ep;
return 0;
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>
2008-12-02 05:13:55 +08:00
free_uid:
free_uid(user);
return error;
}
/*
* Search the file inside the eventpoll tree. The RB tree operations
* are protected by the "mtx" mutex, and ep_find() must be called with
* "mtx" held.
*/
static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
{
int kcmp;
struct rb_node *rbp;
struct epitem *epi, *epir = NULL;
struct epoll_filefd ffd;
ep_set_ffd(&ffd, file, fd);
for (rbp = ep->rbr.rb_node; rbp; ) {
epi = rb_entry(rbp, struct epitem, rbn);
kcmp = ep_cmp_ffd(&ffd, &epi->ffd);
if (kcmp > 0)
rbp = rbp->rb_right;
else if (kcmp < 0)
rbp = rbp->rb_left;
else {
epir = epi;
break;
}
}
return epir;
}
/*
* This is the callback that is passed to the wait queue wakeup
* machanism. It is called by the stored file descriptors when they
* have events to report.
*/
static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
int pwake = 0;
unsigned long flags;
struct epitem *epi = ep_item_from_wait(wait);
struct eventpoll *ep = epi->ep;
spin_lock_irqsave(&ep->lock, flags);
/*
* If the event mask does not contain any poll(2) event, we consider the
* descriptor to be disabled. This condition is likely the effect of the
* EPOLLONESHOT bit that disables the descriptor when an event is received,
* until the next EPOLL_CTL_MOD will be issued.
*/
if (!(epi->event.events & ~EP_PRIVATE_BITS))
goto out_unlock;
/*
* Check the events coming with the callback. At this stage, not
* every device reports the events in the "key" parameter of the
* callback. We need to be able to handle both cases here, hence the
* test for "key" != NULL before the event match test.
*/
if (key && !((unsigned long) key & epi->event.events))
goto out_unlock;
/*
* If we are trasfering events to userspace, we can hold no locks
* (because we're accessing user memory, and because of linux f_op->poll()
* semantics). All the events that happens during that period of time are
* chained in ep->ovflist and requeued later on.
*/
if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) {
if (epi->next == EP_UNACTIVE_PTR) {
epi->next = ep->ovflist;
ep->ovflist = epi;
}
goto out_unlock;
}
/* If this file is already in the ready list we exit soon */
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>
2009-04-01 06:24:10 +08:00
if (!ep_is_linked(&epi->rdllink))
list_add_tail(&epi->rdllink, &ep->rdllist);
/*
* Wake up ( if active ) both the eventpoll wait list and the ->poll()
* wait list.
*/
if (waitqueue_active(&ep->wq))
wake_up_locked(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
out_unlock:
spin_unlock_irqrestore(&ep->lock, flags);
/* We have to call this outside the lock */
if (pwake)
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>
2009-04-01 06:24:10 +08:00
ep_poll_safewake(&ep->poll_wait);
return 1;
}
/*
* This is the callback that is used to add our wait queue to the
* target file wakeup lists.
*/
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
poll_table *pt)
{
struct epitem *epi = ep_item_from_epqueue(pt);
struct eppoll_entry *pwq;
if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) {
init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
pwq->whead = whead;
pwq->base = epi;
add_wait_queue(whead, &pwq->wait);
list_add_tail(&pwq->llink, &epi->pwqlist);
epi->nwait++;
} else {
/* We have to signal that an error occurred */
epi->nwait = -1;
}
}
static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
{
int kcmp;
struct rb_node **p = &ep->rbr.rb_node, *parent = NULL;
struct epitem *epic;
while (*p) {
parent = *p;
epic = rb_entry(parent, struct epitem, rbn);
kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd);
if (kcmp > 0)
p = &parent->rb_right;
else
p = &parent->rb_left;
}
rb_link_node(&epi->rbn, parent, p);
rb_insert_color(&epi->rbn, &ep->rbr);
}
/*
* Must be called with "mtx" held.
*/
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
struct file *tfile, int fd)
{
int error, revents, pwake = 0;
unsigned long flags;
struct epitem *epi;
struct ep_pqueue epq;
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>
2008-12-02 05:13:55 +08:00
if (unlikely(atomic_read(&ep->user->epoll_watches) >=
max_user_watches))
return -ENOSPC;
if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
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>
2008-12-02 05:13:55 +08:00
return -ENOMEM;
/* Item initialization follow here ... */
INIT_LIST_HEAD(&epi->rdllink);
INIT_LIST_HEAD(&epi->fllink);
INIT_LIST_HEAD(&epi->pwqlist);
epi->ep = ep;
ep_set_ffd(&epi->ffd, tfile, fd);
epi->event = *event;
epi->nwait = 0;
epi->next = EP_UNACTIVE_PTR;
/* Initialize the poll table using the queue callback */
epq.epi = epi;
init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);
/*
* Attach the item to the poll hooks and get current event bits.
* We can safely use the file* here because its usage count has
* been increased by the caller of this function. Note that after
* this operation completes, the poll callback can start hitting
* the new item.
*/
revents = tfile->f_op->poll(tfile, &epq.pt);
/*
* We have to check if something went wrong during the poll wait queue
* install process. Namely an allocation for a wait queue failed due
* high memory pressure.
*/
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>
2008-12-02 05:13:55 +08:00
error = -ENOMEM;
if (epi->nwait < 0)
goto error_unregister;
/* Add the current item to the list of active epoll hook for this file */
spin_lock(&tfile->f_lock);
list_add_tail(&epi->fllink, &tfile->f_ep_links);
spin_unlock(&tfile->f_lock);
/*
* Add the current item to the RB tree. All RB tree operations are
* protected by "mtx", and ep_insert() is called with "mtx" held.
*/
ep_rbtree_insert(ep, epi);
/* We have to drop the new item inside our item list to keep track of it */
spin_lock_irqsave(&ep->lock, flags);
/* If the file is already "ready" we drop it inside the ready list */
if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
/* Notify waiting tasks that events are available */
if (waitqueue_active(&ep->wq))
wake_up_locked(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
spin_unlock_irqrestore(&ep->lock, flags);
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>
2008-12-02 05:13:55 +08:00
atomic_inc(&ep->user->epoll_watches);
/* We have to call this outside the lock */
if (pwake)
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>
2009-04-01 06:24:10 +08:00
ep_poll_safewake(&ep->poll_wait);
return 0;
error_unregister:
ep_unregister_pollwait(ep, epi);
/*
* We need to do this because an event could have been arrived on some
* allocated wait queue. Note that we don't care about the ep->ovflist
* list, since that is used/cleaned only inside a section bound by "mtx".
* And ep_insert() is called with "mtx" held.
*/
spin_lock_irqsave(&ep->lock, flags);
if (ep_is_linked(&epi->rdllink))
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 15:25:41 +08:00
list_del_init(&epi->rdllink);
spin_unlock_irqrestore(&ep->lock, flags);
kmem_cache_free(epi_cache, epi);
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>
2008-12-02 05:13:55 +08:00
return error;
}
/*
* Modify the interest event mask by dropping an event if the new mask
* has a match in the current file status. Must be called with "mtx" held.
*/
static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_event *event)
{
int pwake = 0;
unsigned int revents;
/*
* Set the new event interest mask before calling f_op->poll();
* otherwise we might miss an event that happens between the
* f_op->poll() call and the new event set registering.
*/
epi->event.events = event->events;
epi->event.data = event->data; /* protected by mtx */
/*
* Get current event bits. We can safely use the file* here because
* its usage count has been increased by the caller of this function.
*/
revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);
/*
* If the item is "hot" and it is not registered inside the ready
* list, push it inside.
*/
if (revents & event->events) {
spin_lock_irq(&ep->lock);
if (!ep_is_linked(&epi->rdllink)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
/* Notify waiting tasks that events are available */
if (waitqueue_active(&ep->wq))
wake_up_locked(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
spin_unlock_irq(&ep->lock);
}
/* We have to call this outside the lock */
if (pwake)
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>
2009-04-01 06:24:10 +08:00
ep_poll_safewake(&ep->poll_wait);
return 0;
}
static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
void *priv)
{
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>
2009-04-01 06:24:10 +08:00
struct ep_send_events_data *esed = priv;
int eventcnt;
unsigned int revents;
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>
2009-04-01 06:24:10 +08:00
struct epitem *epi;
struct epoll_event __user *uevent;
/*
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>
2009-04-01 06:24:10 +08:00
* We can loop without lock because we are passed a task private list.
* Items cannot vanish during the loop because ep_scan_ready_list() is
* holding "mtx" during this call.
*/
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>
2009-04-01 06:24:10 +08:00
for (eventcnt = 0, uevent = esed->events;
!list_empty(head) && eventcnt < esed->maxevents;) {
epi = list_first_entry(head, struct epitem, rdllink);
list_del_init(&epi->rdllink);
revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
epi->event.events;
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>
2009-04-01 06:24:10 +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>
2009-04-01 06:24:10 +08:00
* If the event mask intersect the caller-requested one,
* deliver the event to userspace. Again, ep_scan_ready_list()
* is holding "mtx", so no operations coming from userspace
* can change the item.
*/
if (revents) {
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>
2009-04-01 06:24:10 +08:00
if (__put_user(revents, &uevent->events) ||
__put_user(epi->event.data, &uevent->data)) {
list_add(&epi->rdllink, head);
return eventcnt ? eventcnt : -EFAULT;
}
eventcnt++;
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>
2009-04-01 06:24:10 +08:00
uevent++;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
else if (!(epi->event.events & EPOLLET)) {
/*
* If this file has been added with Level
* Trigger mode, we need to insert back inside
* the ready list, so that the next call to
* epoll_wait() will check again the events
* availability. At this point, noone can insert
* into ep->rdllist besides us. The epoll_ctl()
* callers are locked out by
* ep_scan_ready_list() holding "mtx" and the
* poll callback will queue them in ep->ovflist.
*/
list_add_tail(&epi->rdllink, &ep->rdllist);
}
}
}
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>
2009-04-01 06:24:10 +08:00
return eventcnt;
}
static int ep_send_events(struct eventpoll *ep,
struct epoll_event __user *events, int maxevents)
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>
2009-04-01 06:24:10 +08:00
{
struct ep_send_events_data esed;
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>
2009-04-01 06:24:10 +08:00
esed.maxevents = maxevents;
esed.events = events;
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 15:25:41 +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>
2009-04-01 06:24:10 +08:00
return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
}
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
int res, eavail;
unsigned long flags;
long jtimeout;
wait_queue_t wait;
/*
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>
2009-04-01 06:24:10 +08:00
* Calculate the timeout by checking for the "infinite" value (-1)
* and the overflow condition. The passed timeout is in milliseconds,
* that why (t * HZ) / 1000.
*/
jtimeout = (timeout < 0 || timeout >= EP_MAX_MSTIMEO) ?
MAX_SCHEDULE_TIMEOUT : (timeout * HZ + 999) / 1000;
retry:
spin_lock_irqsave(&ep->lock, flags);
res = 0;
if (list_empty(&ep->rdllist)) {
/*
* We don't have any available event to return to the caller.
* We need to sleep here, and we will be wake up by
* ep_poll_callback() when events will become available.
*/
init_waitqueue_entry(&wait, current);
wait.flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue(&ep->wq, &wait);
for (;;) {
/*
* We don't want to sleep if the ep_poll_callback() sends us
* a wakeup in between. That's why we set the task state
* to TASK_INTERRUPTIBLE before doing the checks.
*/
set_current_state(TASK_INTERRUPTIBLE);
if (!list_empty(&ep->rdllist) || !jtimeout)
break;
if (signal_pending(current)) {
res = -EINTR;
break;
}
spin_unlock_irqrestore(&ep->lock, flags);
jtimeout = schedule_timeout(jtimeout);
spin_lock_irqsave(&ep->lock, flags);
}
__remove_wait_queue(&ep->wq, &wait);
set_current_state(TASK_RUNNING);
}
/* Is it worth to try to dig for events ? */
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>
2009-04-01 06:24:10 +08:00
eavail = !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
spin_unlock_irqrestore(&ep->lock, flags);
/*
* Try to transfer events to user space. In case we get 0 events and
* there's still timeout left over, we go trying again in search of
* more luck.
*/
if (!res && eavail &&
!(res = ep_send_events(ep, events, maxevents)) && jtimeout)
goto retry;
return res;
}
/*
* Open an eventpoll file descriptor.
*/
SYSCALL_DEFINE1(epoll_create1, int, flags)
{
int error;
struct eventpoll *ep = NULL;
/* Check the EPOLL_* constant for consistency. */
BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
if (flags & ~EPOLL_CLOEXEC)
return -EINVAL;
/*
* Create the internal data structure ("struct eventpoll").
*/
flag parameters add-on: remove epoll_create size param Remove the size parameter from the new epoll_create syscall and renames the syscall itself. The updated test program follows. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <time.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:43 +08:00
error = ep_alloc(&ep);
if (error < 0)
return error;
/*
* Creates all the items needed to setup an eventpoll file. That is,
* a file structure and a free file descriptor.
*/
error = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
flags & O_CLOEXEC);
if (error < 0)
ep_free(ep);
return error;
}
SYSCALL_DEFINE1(epoll_create, int, size)
flag parameters: epoll_create This patch adds the new epoll_create2 syscall. It extends the old epoll_create syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EPOLL_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EPOLL_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <time.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 1, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, 1, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:27 +08:00
{
if (size <= 0)
flag parameters add-on: remove epoll_create size param Remove the size parameter from the new epoll_create syscall and renames the syscall itself. The updated test program follows. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <time.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:43 +08:00
return -EINVAL;
return sys_epoll_create1(0);
flag parameters: epoll_create This patch adds the new epoll_create2 syscall. It extends the old epoll_create syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EPOLL_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EPOLL_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <time.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 1, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, 1, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:27 +08:00
}
/*
* The following function implements the controller interface for
* the eventpoll file that enables the insertion/removal/change of
* file descriptors inside the interest set.
*/
SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
struct epoll_event __user *, event)
{
int error;
struct file *file, *tfile;
struct eventpoll *ep;
struct epitem *epi;
struct epoll_event epds;
error = -EFAULT;
if (ep_op_has_event(op) &&
copy_from_user(&epds, event, sizeof(struct epoll_event)))
goto error_return;
/* Get the "struct file *" for the eventpoll file */
error = -EBADF;
file = fget(epfd);
if (!file)
goto error_return;
/* Get the "struct file *" for the target file */
tfile = fget(fd);
if (!tfile)
goto error_fput;
/* The target file descriptor must support poll */
error = -EPERM;
if (!tfile->f_op || !tfile->f_op->poll)
goto error_tgt_fput;
/*
* We have to check that the file structure underneath the file descriptor
* the user passed to us _is_ an eventpoll file. And also we do not permit
* adding an epoll file descriptor inside itself.
*/
error = -EINVAL;
if (file == tfile || !is_file_epoll(file))
goto error_tgt_fput;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
ep = file->private_data;
mutex_lock(&ep->mtx);
/*
* Try to lookup the file inside our RB tree, Since we grabbed "mtx"
* above, we can be sure to be able to use the item looked up by
* ep_find() till we release the mutex.
*/
epi = ep_find(ep, tfile, fd);
error = -EINVAL;
switch (op) {
case EPOLL_CTL_ADD:
if (!epi) {
epds.events |= POLLERR | POLLHUP;
error = ep_insert(ep, &epds, tfile, fd);
} else
error = -EEXIST;
break;
case EPOLL_CTL_DEL:
if (epi)
error = ep_remove(ep, epi);
else
error = -ENOENT;
break;
case EPOLL_CTL_MOD:
if (epi) {
epds.events |= POLLERR | POLLHUP;
error = ep_modify(ep, epi, &epds);
} else
error = -ENOENT;
break;
}
mutex_unlock(&ep->mtx);
error_tgt_fput:
fput(tfile);
error_fput:
fput(file);
error_return:
return error;
}
/*
* Implement the event wait interface for the eventpoll file. It is the kernel
* part of the user space epoll_wait(2).
*/
SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
int, maxevents, int, timeout)
{
int error;
struct file *file;
struct eventpoll *ep;
/* The maximum number of event must be greater than zero */
if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
return -EINVAL;
/* Verify that the area passed by the user is writeable */
if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
error = -EFAULT;
goto error_return;
}
/* Get the "struct file *" for the eventpoll file */
error = -EBADF;
file = fget(epfd);
if (!file)
goto error_return;
/*
* We have to check that the file structure underneath the fd
* the user passed to us _is_ an eventpoll file.
*/
error = -EINVAL;
if (!is_file_epoll(file))
goto error_fput;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
ep = file->private_data;
/* Time to fish for events ... */
error = ep_poll(ep, events, maxevents, timeout);
error_fput:
fput(file);
error_return:
return error;
}
#ifdef HAVE_SET_RESTORE_SIGMASK
/*
* Implement the event wait interface for the eventpoll file. It is the kernel
* part of the user space epoll_pwait(2).
*/
SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
int, maxevents, int, timeout, const sigset_t __user *, sigmask,
size_t, sigsetsize)
{
int error;
sigset_t ksigmask, sigsaved;
/*
* If the caller wants a certain signal mask to be set during the wait,
* we apply it here.
*/
if (sigmask) {
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
return -EFAULT;
sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
error = sys_epoll_wait(epfd, events, maxevents, timeout);
/*
* If we changed the signal mask, we need to restore the original one.
* In case we've got a signal while waiting, we do not restore the
* signal mask yet, and we allow do_signal() to deliver the signal on
* the way back to userspace, before the signal mask is restored.
*/
if (sigmask) {
if (error == -EINTR) {
memcpy(&current->saved_sigmask, &sigsaved,
sizeof(sigsaved));
set_restore_sigmask();
} else
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
}
return error;
}
#endif /* HAVE_SET_RESTORE_SIGMASK */
static int __init eventpoll_init(void)
{
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>
2008-12-02 05:13:55 +08:00
struct sysinfo si;
si_meminfo(&si);
/*
* Allows top 4% of lomem to be allocated for epoll watches (per user).
*/
max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
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>
2008-12-02 05:13:55 +08:00
EP_ITEM_COST;
/* Initialize the structure used to perform safe poll wait head wake ups */
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>
2009-04-01 06:24:10 +08:00
ep_nested_calls_init(&poll_safewake_ncalls);
/* Initialize the structure used to perform file's f_op->poll() calls */
ep_nested_calls_init(&poll_readywalk_ncalls);
/* Allocates slab cache used to allocate "struct epitem" items */
epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
/* Allocates slab cache used to allocate "struct eppoll_entry" */
pwq_cache = kmem_cache_create("eventpoll_pwq",
sizeof(struct eppoll_entry), 0, SLAB_PANIC, NULL);
return 0;
}
fs_initcall(eventpoll_init);