On Thu, Apr 25, 2019 at 11:29:18PM +0200, Christian Brauner wrote:
> On Thu, Apr 25, 2019 at 03:00:10PM -0400, Joel Fernandes (Google) wrote:
> > Other than verifying pidfd based polling, the tests make sure that
> > wait semantics are preserved with the pidfd poll. Notably the 2 cases:
> > 1. If a thread group leader exits while threads still there, then no
> > pidfd poll notifcation should happen.
> > 2. If a non-thread group leader does an execve, then the thread group
> > leader is signaled to exit and is replaced with the execing thread
> > as the new leader, however the parent is not notified in this case.
> >
> > Signed-off-by: Joel Fernandes (Google) <[email protected]>
> > ---
> > tools/testing/selftests/pidfd/Makefile | 2 +-
> > tools/testing/selftests/pidfd/pidfd_test.c | 198 +++++++++++++++++++++
> > 2 files changed, 199 insertions(+), 1 deletion(-)
> >
> > diff --git a/tools/testing/selftests/pidfd/Makefile
> > b/tools/testing/selftests/pidfd/Makefile
> > index deaf8073bc06..4b31c14f273c 100644
> > --- a/tools/testing/selftests/pidfd/Makefile
> > +++ b/tools/testing/selftests/pidfd/Makefile
> > @@ -1,4 +1,4 @@
> > -CFLAGS += -g -I../../../../usr/include/
> > +CFLAGS += -g -I../../../../usr/include/ -lpthread
> >
> > TEST_GEN_PROGS := pidfd_test
> >
> > diff --git a/tools/testing/selftests/pidfd/pidfd_test.c
> > b/tools/testing/selftests/pidfd/pidfd_test.c
> > index d59378a93782..e887f807645e 100644
> > --- a/tools/testing/selftests/pidfd/pidfd_test.c
> > +++ b/tools/testing/selftests/pidfd/pidfd_test.c
> > @@ -4,18 +4,42 @@
> > #include <errno.h>
> > #include <fcntl.h>
> > #include <linux/types.h>
> > +#include <pthread.h>
> > #include <sched.h>
> > #include <signal.h>
> > #include <stdio.h>
> > #include <stdlib.h>
> > #include <string.h>
> > #include <syscall.h>
> > +#include <sys/epoll.h>
> > +#include <sys/mman.h>
> > #include <sys/mount.h>
> > #include <sys/wait.h>
> > +#include <time.h>
> > #include <unistd.h>
> >
> > #include "../kselftest.h"
> >
> > +#define CHILD_THREAD_MIN_WAIT 3 /* seconds */
> > +#define MAX_EVENTS 5
> > +#define __NR_pidfd_send_signal 424
>
> Should probably be ifndefed as well.
done
> > +#ifndef CLONE_PIDFD
> > +#define CLONE_PIDFD 0x00001000
> > +#endif
> > +
> > +static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *))
> > +{
> > + size_t stack_size = 1024;
> > + char *stack[1024] = { 0 };
> > +
> > +#ifdef __ia64__
> > + return __clone2(fn, stack, stack_size, flags | SIGCHLD, NULL, pidfd);
> > +#else
> > + return clone(fn, stack + stack_size, flags | SIGCHLD, NULL, pidfd);
> > +#endif
> > +}
> > +
> > static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t
> > *info,
> > unsigned int flags)
> > {
> > @@ -368,10 +392,184 @@ static int
> > test_pidfd_send_signal_syscall_support(void)
> > return 0;
> > }
> >
> > +void *test_pidfd_poll_exec_thread(void *priv)
> > +{
> > + char waittime[256];
> > +
> > + ksft_print_msg("Child Thread: starting. pid %d tid %d ; and sleeping\n",
> > + getpid(), syscall(SYS_gettid));
> > + ksft_print_msg("Child Thread: doing exec of sleep\n");
> > +
> > + sprintf(waittime, "%d", CHILD_THREAD_MIN_WAIT);
>
> > +#define CHILD_THREAD_MIN_SLEEP "3" /* seconds */
>
> Could also be
>
> #define str(s) _str(s)
> #define _str(s) #s
> #define CHILD_THREAD_MIN_SLEEP 3
>
> execl("/bin/sleep", "sleep", str(CHILD_THREAD_MIN_SLEEP), (char *)NULL);
>
> getting rid of waittime, and snprintf().
yep, much better, thanks.
> > + execl("/bin/sleep", "sleep", waittime, (char *)NULL);
> > +
> > + ksft_print_msg("Child Thread: DONE. pid %d tid %d\n",
> > + getpid(), syscall(SYS_gettid));
> > + return NULL;
> > +}
> > +
> > +static int poll_pidfd(const char *test_name, int pidfd)
> > +{
> > + int c;
> > + int epoll_fd = epoll_create1(0);
>
> You probably don't need the epoll_fd after an exec, so:
> int epoll_fd = epoll_create1(EPOLL_CLOEXEC);
done
> > + struct epoll_event event, events[MAX_EVENTS];
> > +
> > + if (epoll_fd == -1)
> > + ksft_exit_fail_msg("%s test: Failed to create epoll file
> > descriptor\n",
> > + test_name);
>
> I think logging the errno is helpful here.
>
> > +
> > + event.events = EPOLLIN;
> > + event.data.fd = pidfd;
> > +
> > + if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, pidfd, &event)) {
> > + ksft_print_msg("%s test: Failed to add epoll file descriptor:
> > Skipping\n",
> > + test_name);
>
> I think logging the errno is helpful here.
no where else in other tests are we logging this. I don't have a preference.
Should ksft_exit_fail_msg() do this automatically? Although it could be
logging a stale errno if it did. Anyway I added logging of errno here, as
you suggest.
> > + _exit(PIDFD_SKIP);
>
> Why do you skip when you can't add the pidfd to the epoll loop? Why
> shouldn't this be a test failure?
The original approach was to do this for proc pidfd, which means older
kernels could get a pidfd but couldn't do poll, in this case I wanted the
test to be skipped. Since we are now basing this on CLONE_PIDFD, there is
less of a reason for that. So I will just do ksft_exit_fail_msg() here.
> > + }
> > +
> > + c = epoll_wait(epoll_fd, events, MAX_EVENTS, 5000);
>
> Uhm 5000 timeout? Either do a -1 or something that is noticeably
> shorter, please. :)
I want a timeout for the case where epoll_wait blocks indefinitely, in which
case it should be a test failure.
> > + if (c != 1 || !(events[0].events & EPOLLIN))
> > + ksft_exit_fail_msg("%s test: Unexpected epoll_wait result
> > (c=%d, events=%x)\n",
> > + test_name, c, events[0].events);
>
> I think logging the errno is helpful here.
Ok, done.
> > +
> > + close(epoll_fd);
> > + return events[0].events;
> > +
> > +}
> > +
> > +static int child_poll_exec_test(void *args)
> > +{
> > + pthread_t t1;
> > +
> > + ksft_print_msg("Child (pidfd): starting. pid %d tid %d\n", getpid(),
> > + syscall(SYS_gettid));
> > + pthread_create(&t1, NULL, test_pidfd_poll_exec_thread, NULL);
> > + /*
> > + * Exec in the non-leader thread will destroy the leader immediately.
> > + * If the wait in the parent returns too soon, the test fails.
> > + */
> > + while (1)
> > + ;
>
> Wouldn't sleep(<some-value>) be better here or at least a:
>
> while (true)
> sleep(<some-sensible-value);
>
> instead of a busy loop?
Good catch, I will do sleep(1);
> > +}
> > +
> > +int test_pidfd_poll_exec(int use_waitpid)
> > +{
> > + int pid, pidfd = 0;
> > + int status, ret;
> > + pthread_t t1;
> > + time_t prog_start = time(NULL);
> > + const char *test_name = "pidfd_poll check for premature notification on
> > child thread exec";
> > +
> > + ksft_print_msg("Parent: pid: %d\n", getpid());
> > + pid = pidfd_clone(CLONE_PIDFD, &pidfd, child_poll_exec_test);
>
> That needs to check for error aka
> if (pid < 0)
> I think Tycho mentioned this already.
fixed, thanks to Tycho as well!
> > +
> > + ksft_print_msg("Parent: Waiting for Child (%d) to complete.\n", pid);
> > +
> > + if (use_waitpid) {
> > + ret = waitpid(pid, &status, 0);
> > + if (ret == -1)
> > + ksft_print_msg("Parent: error\n");
> > +
> > + if (ret == pid)
> > + ksft_print_msg("Parent: Child process waited for.\n");
> > + } else {
> > + poll_pidfd(test_name, pidfd);
>
> Either make poll_pidfd() void or check the error value. One of the two.
done
> > + }
> > +
> > + time_t prog_time = time(NULL) - prog_start;
> > +
> > + ksft_print_msg("Time waited for child: %lu\n", prog_time);
> > +
> > + close(pidfd);
> > +
> > + if (prog_time < CHILD_THREAD_MIN_WAIT || prog_time >
> > CHILD_THREAD_MIN_WAIT + 2)
>
> This timing-based testing seems kinda odd to be honest. Can't we do
> something better than this?
will try..
> > + ksft_exit_fail_msg("%s test: Failed\n", test_name);
> > + else
> > + ksft_test_result_pass("%s test: Passed\n", test_name);
> > +}
> > +
> > +void *test_pidfd_poll_leader_exit_thread(void *priv)
> > +{
> > + char waittime[256];
>
> Unused variable
ouch, fixed
> > +
> > + ksft_print_msg("Child Thread: starting. pid %d tid %d ; and sleeping\n",
> > + getpid(), syscall(SYS_gettid));
> > + sleep(CHILD_THREAD_MIN_WAIT);
> > + ksft_print_msg("Child Thread: DONE. pid %d tid %d\n", getpid(),
> > syscall(SYS_gettid));
> > + return NULL;
> > +}
> > +
> > +static time_t *child_exit_secs;
> > +static int child_poll_leader_exit_test(void *args)
> > +{
> > + pthread_t t1, t2;
> > +
> > + ksft_print_msg("Child: starting. pid %d tid %d\n", getpid(),
> > syscall(SYS_gettid));
> > + pthread_create(&t1, NULL, test_pidfd_poll_leader_exit_thread, NULL);
> > + pthread_create(&t2, NULL, test_pidfd_poll_leader_exit_thread, NULL);
> > +
> > + /*
> > + * glibc exit calls exit_group syscall, so explicity call exit only
> > + * so that only the group leader exits, leaving the threads alone.
> > + */
> > + *child_exit_secs = time(NULL);
> > + syscall(SYS_exit, 0);
> > +}
> > +
> > +int test_pidfd_poll_leader_exit(int use_waitpid)
>
> static
fixed
> > +{
> > + int pid, pidfd = 0;
> > + int status, ret;
> > + time_t prog_start = time(NULL);
> > + const char *test_name = "pidfd_poll check for premature notification on
> > non-empty"
> > + "group leader exit";
> > +
> > + child_exit_secs = mmap(NULL, sizeof *child_exit_secs, PROT_READ |
> > PROT_WRITE,
> > + MAP_SHARED | MAP_ANONYMOUS, -1, 0);
>
> Error checking, please:
>
> if (child_exit_secs == MAP_FAILED)
done
> > +
> > + ksft_print_msg("Parent: pid: %d\n", getpid());
> > + pid = pidfd_clone(CLONE_PIDFD, &pidfd, child_poll_leader_exit_test);
>
> Error checking, please:
>
> if (pid < 0)
done
> > +
> > + ksft_print_msg("Parent: Waiting for Child (%d) to complete.\n", pid);
> > +
> > + if (use_waitpid) {
> > + ret = waitpid(pid, &status, 0);
> > + if (ret == -1)
> > + ksft_print_msg("Parent: error\n");
> > + } else {
> > + /*
> > + * This sleep tests for the case where if the child exits, and
> > is in
> > + * EXIT_ZOMBIE, but the thread group leader is non-empty, then
> > the poll
> > + * doesn't prematurely return even though there are active
> > threads
> > + */
> > + sleep(1);
> > + poll_pidfd(test_name, pidfd);
>
> Make poll_pidfd() void or check error, please.
done, made void
> > + }
> > +
> > + if (ret == pid)
> > + ksft_print_msg("Parent: Child process waited for.\n");
> > +
> > + time_t since_child_exit = time(NULL) - *child_exit_secs;
> > +
> > + ksft_print_msg("Time since child exit: %lu\n", since_child_exit);
> > +
> > + close(pidfd);
> > +
> > + if (since_child_exit < CHILD_THREAD_MIN_WAIT ||
> > + since_child_exit > CHILD_THREAD_MIN_WAIT + 2)
>
> This looks very magical. Especially without a comment. Now you add
> random +2. Please comment it or better, come up with a non-timing
> based test.
Will try a non-timing test, need to plan it out. Other comments are addressed
and will post again soon, thanks!
- Joel
