02292f131a
o The polling mechanism for I/O readiness was changed from
select() to poll(). In additon, a wrapped version of poll()
is now provided.
o The wrapped select routine now converts each fd_set to a
poll array so that the thread scheduler doesn't have to
perform a bitwise search for selected fds each time file
descriptors are polled for I/O readiness.
o The thread scheduler was modified to use a new queue (_workq)
for threads that need work. Threads waiting for I/O readiness
and spinblocks are added to the work queue in addition to the
waiting queue. This reduces the time spent forming/searching
the array of file descriptors being polled.
o The waiting queue (_waitingq) is now maintained in order of
thread wakeup time. This allows the thread scheduler to
find the nearest wakeup time by looking at the first thread
in the queue instead of searching the entire queue.
o Removed file descriptor locking for select/poll routines. An
application should not rely on the threads library for providing
this locking; if necessary, the application should use mutexes
to protect selecting/polling of file descriptors.
o Retrieve and use the kernel clock rate/resolution at startup
instead of hardcoding the clock resolution to 10 msec (tested
with kernel running at 1000 HZ).
o All queues have been changed to use queue.h macros. These
include the queues of all threads, dead threads, and threads
waiting for file descriptor locks.
o Added reinitialization of the GC mutex and condition variable
after a fork. Also prevented reallocation of the ready queue
after a fork.
o Prevented the wrapped close routine from closing the thread
kernel pipes.
o Initialized file descriptor table for stdio entries at thread
init.
o Provided additional flags to indicate to what queues threads
belong.
o Moved TAILQ initialization for statically allocated mutex and
condition variables to after the spinlock.
o Added dispatching of signals to pthread_kill. Removing the
dispatching of signals from thread activation broke sigsuspend
when pthread_kill was used to send a signal to a thread.
o Temporarily set the state of a thread to PS_SUSPENDED when it
is first created and placed in the list of threads so that it
will not be accidentally scheduled before becoming a member
of one of the scheduling queues.
o Change the signal handler to queue signals to the thread kernel
pipe if the scheduling queues are protected. When scheduling
queues are unprotected, signals are then dequeued and handled.
o Ensured that all installed signal handlers block the scheduling
signal and that the scheduling signal handler blocks all
other signals. This ensures that the signal handler is only
interruptible for and by non-scheduling signals. An atomic
lock is used to decide which instance of the signal handler
will handle pending signals.
o Removed _lock_thread_list and _unlock_thread_list as they are
no longer used to protect the thread list.
o Added missing RCS IDs to modified files.
o Added checks for appropriate queue membership and activity when
adding, removing, and searching the scheduling queues. These
checks add very little overhead and are enabled when compiled
with _PTHREADS_INVARIANTS defined. Suggested and implemented
by Tor Egge with some modification by me.
o Close a race condition in uthread_close. (Tor Egge)
o Protect the scheduling queues while modifying them in
pthread_cond_signal and _thread_fd_unlock. (Tor Egge)
o Ensure that when a thread gets a mutex, the mutex is on that
threads list of owned mutexes. (Tor Egge)
o Set the kernel-in-scheduler flag in _thread_kern_sched_state
and _thread_kern_sched_state_unlock to prevent a scheduling
signal from calling the scheduler again. (Tor Egge)
o Don't use TAILQ_FOREACH macro while searching the waiting
queue for threads in a sigwait state, because a change of
state destroys the TAILQ link. It is actually safe to do
so, though, because once a sigwaiting thread is found, the
loop ends and the function returns. (Tor Egge)
o When dispatching signals to threads, make the thread inherit
the signal deferral flag of the currently running thread.
(Tor Egge)
Submitted by: Daniel Eischen <eischen@vigrid.com> and
Tor Egge <Tor.Egge@fast.no>
200 lines
5.8 KiB
C
200 lines
5.8 KiB
C
/*
|
|
* Copyright (c) 1995-1998 John Birrell <jb@cimlogic.com.au>
|
|
* 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. All advertising materials mentioning features or use of this software
|
|
* must display the following acknowledgement:
|
|
* This product includes software developed by John Birrell.
|
|
* 4. Neither the name of the author nor the names of any co-contributors
|
|
* may be used to endorse or promote products derived from this software
|
|
* without specific prior written permission.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY JOHN BIRRELL AND CONTRIBUTORS ``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 REGENTS OR CONTRIBUTORS 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.
|
|
*
|
|
* $Id$
|
|
*/
|
|
#include <unistd.h>
|
|
#include <errno.h>
|
|
#include <poll.h>
|
|
#include <string.h>
|
|
#include <sys/param.h>
|
|
#include <sys/types.h>
|
|
#include <sys/time.h>
|
|
#include <sys/fcntl.h>
|
|
#ifdef _THREAD_SAFE
|
|
#include <pthread.h>
|
|
#include "pthread_private.h"
|
|
|
|
int
|
|
select(int numfds, fd_set * readfds, fd_set * writefds,
|
|
fd_set * exceptfds, struct timeval * timeout)
|
|
{
|
|
struct timespec ts;
|
|
int i, ret = 0, f_wait = 1;
|
|
int pfd_index, got_one = 0, fd_count = 0;
|
|
struct pthread_poll_data data;
|
|
|
|
if (numfds > _thread_dtablesize) {
|
|
numfds = _thread_dtablesize;
|
|
}
|
|
/* Check if a timeout was specified: */
|
|
if (timeout) {
|
|
/* Convert the timeval to a timespec: */
|
|
TIMEVAL_TO_TIMESPEC(timeout, &ts);
|
|
|
|
/* Set the wake up time: */
|
|
_thread_kern_set_timeout(&ts);
|
|
if (ts.tv_sec == 0 && ts.tv_nsec == 0)
|
|
f_wait = 0;
|
|
} else {
|
|
/* Wait for ever: */
|
|
_thread_kern_set_timeout(NULL);
|
|
}
|
|
|
|
/* Count the number of file descriptors to be polled: */
|
|
if (readfds || writefds || exceptfds) {
|
|
for (i = 0; i < numfds; i++) {
|
|
if ((readfds && FD_ISSET(i, readfds)) ||
|
|
(exceptfds && FD_ISSET(i, exceptfds)) ||
|
|
(writefds && FD_ISSET(i, writefds))) {
|
|
fd_count++;
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Allocate memory for poll data if it hasn't already been
|
|
* allocated or if previously allocated memory is insufficient.
|
|
*/
|
|
if ((_thread_run->poll_data.fds == NULL) ||
|
|
(_thread_run->poll_data.nfds < fd_count)) {
|
|
data.fds = (struct pollfd *) realloc(_thread_run->poll_data.fds,
|
|
sizeof(struct pollfd) * MAX(128, fd_count));
|
|
if (data.fds == NULL) {
|
|
errno = ENOMEM;
|
|
ret = -1;
|
|
}
|
|
else {
|
|
/*
|
|
* Note that the threads poll data always
|
|
* indicates what is allocated, not what is
|
|
* currently being polled.
|
|
*/
|
|
_thread_run->poll_data.fds = data.fds;
|
|
_thread_run->poll_data.nfds = MAX(128, fd_count);
|
|
}
|
|
}
|
|
if (ret == 0) {
|
|
/* Setup the wait data. */
|
|
data.fds = _thread_run->poll_data.fds;
|
|
data.nfds = fd_count;
|
|
|
|
/*
|
|
* Setup the array of pollfds. Optimize this by
|
|
* running the loop in reverse and stopping when
|
|
* the number of selected file descriptors is reached.
|
|
*/
|
|
for (i = numfds - 1, pfd_index = fd_count - 1;
|
|
(i >= 0) && (pfd_index >= 0); i--) {
|
|
data.fds[pfd_index].events = 0;
|
|
if (readfds && FD_ISSET(i, readfds)) {
|
|
data.fds[pfd_index].events = POLLRDNORM;
|
|
}
|
|
if (exceptfds && FD_ISSET(i, exceptfds)) {
|
|
data.fds[pfd_index].events |= POLLRDBAND;
|
|
}
|
|
if (writefds && FD_ISSET(i, writefds)) {
|
|
data.fds[pfd_index].events |= POLLWRNORM;
|
|
}
|
|
if (data.fds[pfd_index].events != 0) {
|
|
/*
|
|
* Set the file descriptor to be polled and
|
|
* clear revents in case of a timeout which
|
|
* leaves fds unchanged:
|
|
*/
|
|
data.fds[pfd_index].fd = i;
|
|
data.fds[pfd_index].revents = 0;
|
|
pfd_index--;
|
|
}
|
|
}
|
|
if (((ret = _thread_sys_poll(data.fds, data.nfds, 0)) == 0) &&
|
|
(f_wait != 0)) {
|
|
_thread_run->data.poll_data = &data;
|
|
_thread_run->interrupted = 0;
|
|
_thread_kern_sched_state(PS_SELECT_WAIT, __FILE__, __LINE__);
|
|
if (_thread_run->interrupted) {
|
|
errno = EINTR;
|
|
data.nfds = 0;
|
|
ret = -1;
|
|
} else
|
|
ret = data.nfds;
|
|
}
|
|
}
|
|
|
|
if (ret >= 0) {
|
|
numfds = 0;
|
|
for (i = 0; i < fd_count; i++) {
|
|
/*
|
|
* Check the results of the poll and clear
|
|
* this file descriptor from the fdset if
|
|
* the requested event wasn't ready.
|
|
*/
|
|
got_one = 0;
|
|
if (readfds != NULL) {
|
|
if (FD_ISSET(data.fds[i].fd, readfds)) {
|
|
if (data.fds[i].revents & (POLLIN |
|
|
POLLRDNORM))
|
|
got_one = 1;
|
|
else
|
|
FD_CLR(data.fds[i].fd, readfds);
|
|
}
|
|
}
|
|
if (writefds != NULL) {
|
|
if (FD_ISSET(data.fds[i].fd, writefds)) {
|
|
if (data.fds[i].revents & (POLLOUT |
|
|
POLLWRNORM | POLLWRBAND))
|
|
got_one = 1;
|
|
else
|
|
FD_CLR(data.fds[i].fd,
|
|
writefds);
|
|
}
|
|
}
|
|
if (exceptfds != NULL) {
|
|
if (FD_ISSET(data.fds[i].fd, exceptfds)) {
|
|
if (data.fds[i].revents & (POLLRDBAND |
|
|
POLLPRI | POLLHUP | POLLERR |
|
|
POLLNVAL))
|
|
got_one = 1;
|
|
else
|
|
FD_CLR(data.fds[i].fd,
|
|
exceptfds);
|
|
}
|
|
}
|
|
if (got_one)
|
|
numfds++;
|
|
}
|
|
ret = numfds;
|
|
}
|
|
|
|
return (ret);
|
|
}
|
|
#endif
|