/* * Copyright 2000-2007 Niels Provos <provos@citi.umich.edu> * Copyright 2007-2012 Niels Provos, Nick Mathewson * * 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.
*/ #include"event2/event-config.h" #include"evconfig-private.h"
/* Since Linux 2.6.17, epoll is able to report about peer half-closed connection using special EPOLLRDHUP flag on a read event.
*/ #if !defined(EPOLLRDHUP) #define EPOLLRDHUP 0 #define EARLY_CLOSE_IF_HAVE_RDHUP 0 #else #define EARLY_CLOSE_IF_HAVE_RDHUP EV_FEATURE_EARLY_CLOSE #endif
#include"epolltable-internal.h"
#ifdefined(EVENT__HAVE_SYS_TIMERFD_H) && \ defined(EVENT__HAVE_TIMERFD_CREATE) && \ defined(HAVE_POSIX_MONOTONIC) && defined(TFD_NONBLOCK) && \ defined(TFD_CLOEXEC) /* Note that we only use timerfd if TFD_NONBLOCK and TFD_CLOEXEC are available and working. This means that we can't support it on 2.6.25 (where timerfd was introduced) or 2.6.26, since 2.6.27 introduced those flags.
*/ #define USING_TIMERFD #endif
struct epollop { struct epoll_event *events; int nevents; int epfd; #ifdef USING_TIMERFD int timerfd; #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)
#ifdef EVENT__HAVE_EPOLL_CREATE1 /* First, try the shiny new epoll_create1 interface, if we have it. */
epfd = epoll_create1(EPOLL_CLOEXEC); #endif if (epfd == -1) { /* Initialize the kernel queue using the old interface. (The
size field is ignored since 2.6.8.) */ if ((epfd = epoll_create(32000)) == -1) { if (errno != ENOSYS)
event_warn("epoll_create"); return (NULL);
}
evutil_make_socket_closeonexec(epfd);
}
#ifdef USING_TIMERFD /* The epoll interface ordinarily gives us one-millisecond precision, so on Linux it makes perfect sense to use the CLOCK_MONOTONIC_COARSE timer. But when the user has set the new PRECISE_TIMER flag for an event_base, we can try to use timerfd to give them finer granularity.
*/ if ((base->flags & EVENT_BASE_FLAG_PRECISE_TIMER) &&
base->monotonic_timer.monotonic_clock == CLOCK_MONOTONIC) { int fd;
fd = epollop->timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK|TFD_CLOEXEC); if (epollop->timerfd >= 0) { struct epoll_event epev;
memset(&epev, 0, sizeof(epev));
epev.data.fd = epollop->timerfd;
epev.events = EPOLLIN; if (epoll_ctl(epollop->epfd, EPOLL_CTL_ADD, fd, &epev) < 0) {
event_warn("epoll_ctl(timerfd)");
close(fd);
epollop->timerfd = -1;
}
} else { if (errno != EINVAL && errno != ENOSYS) { /* These errors probably mean that we were * compiled with timerfd/TFD_* support, but * we're running on a kernel that lacks those.
*/
event_warn("timerfd_create");
}
epollop->timerfd = -1;
}
} else {
epollop->timerfd = -1;
} #endif
switch (op) { case EPOLL_CTL_MOD: if (errno == ENOENT) { /* If a MOD operation fails with ENOENT, the * fd was probably closed and re-opened. We * should retry the operation as an ADD.
*/ if (epoll_ctl(epollop->epfd, EPOLL_CTL_ADD, ch->fd, &epev) == -1) {
event_warn("Epoll MOD(%d) on %d retried as ADD; that failed too",
(int)epev.events, ch->fd); return -1;
} else {
event_debug(("Epoll MOD(%d) on %d retried as ADD; succeeded.",
(int)epev.events,
ch->fd)); return 0;
}
} break; case EPOLL_CTL_ADD: if (errno == EEXIST) { /* If an ADD operation fails with EEXIST, * either the operation was redundant (as with a * precautionary add), or we ran into a fun * kernel bug where using dup*() to duplicate the * same file into the same fd gives you the same epitem * rather than a fresh one. For the second case,
* we must retry with MOD. */ if (epoll_ctl(epollop->epfd, EPOLL_CTL_MOD, ch->fd, &epev) == -1) {
event_warn("Epoll ADD(%d) on %d retried as MOD; that failed too",
(int)epev.events, ch->fd); return -1;
} else {
event_debug(("Epoll ADD(%d) on %d retried as MOD; succeeded.",
(int)epev.events,
ch->fd)); return 0;
}
} break; case EPOLL_CTL_DEL: if (errno == ENOENT || errno == EBADF || errno == EPERM) { /* If a delete fails with one of these errors, * that's fine too: we closed the fd before we
* got around to calling epoll_dispatch. */
event_debug(("Epoll DEL(%d) on fd %d gave %s: DEL was unnecessary.",
(int)epev.events,
ch->fd,
strerror(errno))); return 0;
} break; default: break;
}
staticint
epoll_dispatch(struct event_base *base, struct timeval *tv)
{ struct epollop *epollop = base->evbase; struct epoll_event *events = epollop->events; int i, res; long timeout = -1;
#ifdef USING_TIMERFD if (epollop->timerfd >= 0) { struct itimerspec is;
is.it_interval.tv_sec = 0;
is.it_interval.tv_nsec = 0; if (tv == NULL) { /* No timeout; disarm the timer. */
is.it_value.tv_sec = 0;
is.it_value.tv_nsec = 0;
} else { if (tv->tv_sec == 0 && tv->tv_usec == 0) { /* we need to exit immediately; timerfd can't
* do that. */
timeout = 0;
}
is.it_value.tv_sec = tv->tv_sec;
is.it_value.tv_nsec = tv->tv_usec * 1000;
} /* TODO: we could avoid unnecessary syscalls here by only calling timerfd_settime when the top timeout changes, or when we're called with a different timeval.
*/ if (timerfd_settime(epollop->timerfd, 0, &is, NULL) < 0) {
event_warn("timerfd_settime");
}
} else #endif if (tv != NULL) {
timeout = evutil_tv_to_msec_(tv); if (timeout < 0 || 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;
}
}
for (i = 0; i < res; i++) { int what = events[i].events; short ev = 0; #ifdef USING_TIMERFD if (events[i].data.fd == epollop->timerfd) continue; #endif
if (what & EPOLLERR) {
ev = EV_READ | EV_WRITE;
} elseif ((what & EPOLLHUP) && !(what & EPOLLRDHUP)) {
ev = EV_READ | EV_WRITE;
} else { if (what & EPOLLIN)
ev |= EV_READ; if (what & EPOLLOUT)
ev |= EV_WRITE; if (what & EPOLLRDHUP)
ev |= EV_CLOSED;
}
if (!ev) continue;
evmap_io_active_(base, events[i].data.fd, ev | EV_ET);
}
if (res == epollop->nevents && epollop->nevents < MAX_NEVENT) { /* 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;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.