Rainer Weikusat <rweiku...@mobileactivedefense.com> writes:
> Mathias Krause <mini...@googlemail.com> writes:
>> On 2 October 2015 at 22:43, Jason Baron <jba...@akamai.com> wrote:
>>> The unix_dgram_poll() routine calls sock_poll_wait() not only for the wait
>>> queue associated with the socket s that we are poll'ing against, but also
>>> calls
>
> [useless full-quote removed]
>
>> My reproducer runs on this patch for more than 3 days now without
>> triggering anything anymore.
>
> Since the behaviour of your program is random, using it to "test"
> anything doesn't really provide any insight: It could have been
> executing the same codepath which doesn't happen to trigger any problems
> for all of these three days. Nobody can tell.
Since this "strangely" seems to have been lost in the thread: Here's the
test program showing that the reconnect while in epoll actually causes a
problem (at least I think so):
--------
#include <fcntl.h>
#include <pthread.h>
#include <string.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <sys/epoll.h>
#include <signal.h>
#include <unistd.h>
static int sk, tg0, tg1;
static void *epoller(void *unused)
{
struct epoll_event epev;
int epfd;
epfd = epoll_create(1);
if (epfd == -1) exit(0);
epev.events = EPOLLOUT;
epoll_ctl(epfd, EPOLL_CTL_ADD, sk, &epev);
epoll_wait(epfd, &epev, 1, 5000);
close(sk);
execl("./a.out", "./a.out", (void *)0);
return NULL;
}
int main(void)
{
struct sockaddr_un sun;
pthread_t tid;
int rc;
sun.sun_family = AF_UNIX;
tg0 = socket(AF_UNIX, SOCK_DGRAM, 0);
strncpy(sun.sun_path, "/tmp/tg0", sizeof(sun.sun_path));
unlink(sun.sun_path);
bind(tg0, (struct sockaddr *)&sun, sizeof(sun));
tg1 = socket(AF_UNIX, SOCK_DGRAM, 0);
strncpy(sun.sun_path, "/tmp/tg1", sizeof(sun.sun_path));
unlink(sun.sun_path);
bind(tg1, (struct sockaddr *)&sun, sizeof(sun));
sk = socket(AF_UNIX, SOCK_DGRAM, 0);
connect(sk, (struct sockaddr *)&sun, sizeof(sun));
fcntl(sk, F_SETFL, fcntl(sk, F_GETFL) | O_NONBLOCK);
while ((rc = write(sk, "bla", 3)) != -1);
pthread_create(&tid, NULL, epoller, NULL);
usleep(5);
strncpy(sun.sun_path, "/tmp/tg0", sizeof(sun.sun_path));
connect(sk, (struct sockaddr *)&sun, sizeof(sun));
close(tg1);
pause();
return 0;
}
----------
And here the other demonstrating the poller not being woken up despite
it could write something:
----------
#include <fcntl.h>
#include <stdio.h>
#include <string.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <sys/poll.h>
#include <sys/wait.h>
#include <unistd.h>
int main(void)
{
struct sockaddr_un sun;
struct pollfd pfd;
int tg, sk0, sk1, rc;
char buf[16];
sun.sun_family = AF_UNIX;
tg = socket(AF_UNIX, SOCK_DGRAM, 0);
strncpy(sun.sun_path, "/tmp/tg", sizeof(sun.sun_path));
unlink(sun.sun_path);
bind(tg, (struct sockaddr *)&sun, sizeof(sun));
sk0 = socket(AF_UNIX, SOCK_DGRAM, 0);
connect(sk0, (struct sockaddr *)&sun, sizeof(sun));
sk1 = socket(AF_UNIX, SOCK_DGRAM, 0);
connect(sk1, (struct sockaddr *)&sun, sizeof(sun));
fcntl(sk0, F_SETFL, fcntl(sk0, F_GETFL) | O_NONBLOCK);
fcntl(sk1, F_SETFL, fcntl(sk1, F_GETFL) | O_NONBLOCK);
while (write(sk0, "bla", 3) != -1);
if (fork() == 0) {
pfd.fd = sk1;
pfd.events = POLLOUT;
rc = poll(&pfd, 1, -1);
_exit(0);
}
sleep(3);
read(tg, buf, sizeof(buf));
wait(&rc);
return 0;
}
-----------
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
