123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377 |
- /*
- * Copyright 2000-2003 Niels Provos <provos@citi.umich.edu>
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. The name of the author may not be used to endorse or promote products
- * derived from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
- * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
- * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
- * IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
- #ifdef HAVE_CONFIG_H
- #include "config.h"
- #endif
- #include <stdint.h>
- #include <sys/types.h>
- #include <sys/resource.h>
- #ifdef HAVE_SYS_TIME_H
- #include <sys/time.h>
- #else
- #include <sys/_libevent_time.h>
- #endif
- #include <sys/queue.h>
- #include <sys/epoll.h>
- #include <signal.h>
- #include <stdio.h>
- #include <stdlib.h>
- #include <string.h>
- #include <unistd.h>
- #include <errno.h>
- #ifdef HAVE_FCNTL_H
- #include <fcntl.h>
- #endif
- #include "event.h"
- #include "event-internal.h"
- #include "evsignal.h"
- #include "log.h"
- /* due to limitations in the epoll interface, we need to keep track of
- * all file descriptors outself.
- */
- struct evepoll {
- struct event *evread;
- struct event *evwrite;
- };
- struct epollop {
- struct evepoll *fds;
- int nfds;
- struct epoll_event *events;
- int nevents;
- int epfd;
- };
- static void *epoll_init (struct event_base *);
- static int epoll_add (void *, struct event *);
- static int epoll_del (void *, struct event *);
- static int epoll_dispatch (struct event_base *, void *, struct timeval *);
- static void epoll_dealloc (struct event_base *, void *);
- const struct eventop epollops = {
- "epoll",
- epoll_init,
- epoll_add,
- epoll_del,
- epoll_dispatch,
- epoll_dealloc,
- 1 /* need reinit */
- };
- #ifdef HAVE_SETFD
- #define FD_CLOSEONEXEC(x) do { \
- if (fcntl(x, F_SETFD, 1) == -1) \
- event_warn("fcntl(%d, F_SETFD)", x); \
- } while (0)
- #else
- #define FD_CLOSEONEXEC(x)
- #endif
- /* On Linux kernels at least up to 2.6.24.4, epoll can't handle timeout
- * values bigger than (LONG_MAX - 999ULL)/HZ. HZ in the wild can be
- * as big as 1000, and LONG_MAX can be as small as (1<<31)-1, so the
- * largest number of msec we can support here is 2147482. Let's
- * round that down by 47 seconds.
- */
- #define MAX_EPOLL_TIMEOUT_MSEC (35*60*1000)
- #define INITIAL_NFILES 32
- #define INITIAL_NEVENTS 32
- #define MAX_NEVENTS 4096
- static void *
- epoll_init(struct event_base *base)
- {
- int epfd;
- struct epollop *epollop;
- /* Disable epollueue when this environment variable is set */
- if (evutil_getenv("EVENT_NOEPOLL"))
- return (NULL);
- /* Initalize the kernel queue */
- if ((epfd = epoll_create(32000)) == -1) {
- if (errno != ENOSYS)
- event_warn("epoll_create");
- return (NULL);
- }
- FD_CLOSEONEXEC(epfd);
- if (!(epollop = calloc(1, sizeof(struct epollop))))
- return (NULL);
- epollop->epfd = epfd;
- /* Initalize fields */
- epollop->events = malloc(INITIAL_NEVENTS * sizeof(struct epoll_event));
- if (epollop->events == NULL) {
- free(epollop);
- return (NULL);
- }
- epollop->nevents = INITIAL_NEVENTS;
- epollop->fds = calloc(INITIAL_NFILES, sizeof(struct evepoll));
- if (epollop->fds == NULL) {
- free(epollop->events);
- free(epollop);
- return (NULL);
- }
- epollop->nfds = INITIAL_NFILES;
- evsignal_init(base);
- return (epollop);
- }
- static int
- epoll_recalc(struct event_base *base, void *arg, int max)
- {
- struct epollop *epollop = arg;
- if (max >= epollop->nfds) {
- struct evepoll *fds;
- int nfds;
- nfds = epollop->nfds;
- while (nfds <= max)
- nfds <<= 1;
- fds = realloc(epollop->fds, nfds * sizeof(struct evepoll));
- if (fds == NULL) {
- event_warn("realloc");
- return (-1);
- }
- epollop->fds = fds;
- memset(fds + epollop->nfds, 0,
- (nfds - epollop->nfds) * sizeof(struct evepoll));
- epollop->nfds = nfds;
- }
- return (0);
- }
- static int
- epoll_dispatch(struct event_base *base, void *arg, struct timeval *tv)
- {
- struct epollop *epollop = arg;
- struct epoll_event *events = epollop->events;
- struct evepoll *evep;
- int i, res, timeout = -1;
- if (tv != NULL)
- timeout = tv->tv_sec * 1000 + (tv->tv_usec + 999) / 1000;
- if (timeout > MAX_EPOLL_TIMEOUT_MSEC) {
- /* Linux kernels can wait forever if the timeout is too big;
- * see comment on MAX_EPOLL_TIMEOUT_MSEC. */
- timeout = MAX_EPOLL_TIMEOUT_MSEC;
- }
- res = epoll_wait(epollop->epfd, events, epollop->nevents, timeout);
- if (res == -1) {
- if (errno != EINTR) {
- event_warn("epoll_wait");
- return (-1);
- }
- evsignal_process(base);
- return (0);
- } else if (base->sig.evsignal_caught) {
- evsignal_process(base);
- }
- event_debug(("%s: epoll_wait reports %d", __func__, res));
- for (i = 0; i < res; i++) {
- int what = events[i].events;
- struct event *evread = NULL, *evwrite = NULL;
- int fd = events[i].data.fd;
- if (fd < 0 || fd >= epollop->nfds)
- continue;
- evep = &epollop->fds[fd];
- if (what & (EPOLLHUP|EPOLLERR)) {
- evread = evep->evread;
- evwrite = evep->evwrite;
- } else {
- if (what & EPOLLIN) {
- evread = evep->evread;
- }
- if (what & EPOLLOUT) {
- evwrite = evep->evwrite;
- }
- }
- if (!(evread||evwrite))
- continue;
- if (evread != NULL)
- event_active(evread, EV_READ, 1);
- if (evwrite != NULL)
- event_active(evwrite, EV_WRITE, 1);
- }
- if (res == epollop->nevents && epollop->nevents < MAX_NEVENTS) {
- /* We used all of the event space this time. We should
- be ready for more events next time. */
- int new_nevents = epollop->nevents * 2;
- struct epoll_event *new_events;
- new_events = realloc(epollop->events,
- new_nevents * sizeof(struct epoll_event));
- if (new_events) {
- epollop->events = new_events;
- epollop->nevents = new_nevents;
- }
- }
- return (0);
- }
- static int
- epoll_add(void *arg, struct event *ev)
- {
- struct epollop *epollop = arg;
- struct epoll_event epev = {0, {0}};
- struct evepoll *evep;
- int fd, op, events;
- if (ev->ev_events & EV_SIGNAL)
- return (evsignal_add(ev));
- fd = ev->ev_fd;
- if (fd >= epollop->nfds) {
- /* Extent the file descriptor array as necessary */
- if (epoll_recalc(ev->ev_base, epollop, fd) == -1)
- return (-1);
- }
- evep = &epollop->fds[fd];
- op = EPOLL_CTL_ADD;
- events = 0;
- if (evep->evread != NULL) {
- events |= EPOLLIN;
- op = EPOLL_CTL_MOD;
- }
- if (evep->evwrite != NULL) {
- events |= EPOLLOUT;
- op = EPOLL_CTL_MOD;
- }
- if (ev->ev_events & EV_READ)
- events |= EPOLLIN;
- if (ev->ev_events & EV_WRITE)
- events |= EPOLLOUT;
- epev.data.fd = fd;
- epev.events = events;
- if (epoll_ctl(epollop->epfd, op, ev->ev_fd, &epev) == -1)
- return (-1);
- /* Update events responsible */
- if (ev->ev_events & EV_READ)
- evep->evread = ev;
- if (ev->ev_events & EV_WRITE)
- evep->evwrite = ev;
- return (0);
- }
- static int
- epoll_del(void *arg, struct event *ev)
- {
- struct epollop *epollop = arg;
- struct epoll_event epev = {0, {0}};
- struct evepoll *evep;
- int fd, events, op;
- int needwritedelete = 1, needreaddelete = 1;
- if (ev->ev_events & EV_SIGNAL)
- return (evsignal_del(ev));
- fd = ev->ev_fd;
- if (fd >= epollop->nfds)
- return (0);
- evep = &epollop->fds[fd];
- op = EPOLL_CTL_DEL;
- events = 0;
- if (ev->ev_events & EV_READ)
- events |= EPOLLIN;
- if (ev->ev_events & EV_WRITE)
- events |= EPOLLOUT;
- if ((events & (EPOLLIN|EPOLLOUT)) != (EPOLLIN|EPOLLOUT)) {
- if ((events & EPOLLIN) && evep->evwrite != NULL) {
- needwritedelete = 0;
- events = EPOLLOUT;
- op = EPOLL_CTL_MOD;
- } else if ((events & EPOLLOUT) && evep->evread != NULL) {
- needreaddelete = 0;
- events = EPOLLIN;
- op = EPOLL_CTL_MOD;
- }
- }
- epev.events = events;
- epev.data.fd = fd;
- if (needreaddelete)
- evep->evread = NULL;
- if (needwritedelete)
- evep->evwrite = NULL;
- if (epoll_ctl(epollop->epfd, op, fd, &epev) == -1)
- return (-1);
- return (0);
- }
- static void
- epoll_dealloc(struct event_base *base, void *arg)
- {
- struct epollop *epollop = arg;
- evsignal_dealloc(base);
- if (epollop->fds)
- free(epollop->fds);
- if (epollop->events)
- free(epollop->events);
- if (epollop->epfd >= 0)
- close(epollop->epfd);
- memset(epollop, 0, sizeof(struct epollop));
- free(epollop);
- }
|