Message-ID: <20190425212917.yotnir4uqgpnh764@brauner.io>
Date:   Thu, 25 Apr 2019 23:29:18 +0200
From:   Christian Brauner <christian@...uner.io>
To:     "Joel Fernandes (Google)" <joel@...lfernandes.org>
Cc:     linux-kernel@...r.kernel.org,
        Andrew Morton <akpm@...ux-foundation.org>,
        Arnd Bergmann <arnd@...db.de>, dancol@...gle.com,
        "Eric W. Biederman" <ebiederm@...ssion.com>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Ingo Molnar <mingo@...nel.org>, jannh@...gle.com,
        Jann Horn <jann@...jh.net>,
        Jonathan Kowalski <bl0pbl33p@...il.com>,
        kernel-team@...roid.com, linux-kselftest@...r.kernel.org,
        luto@...capital.net, Michal Hocko <mhocko@...e.com>,
        "Peter Zijlstra (Intel)" <peterz@...radead.org>,
        rostedt@...dmis.org, Serge Hallyn <serge@...lyn.com>,
        Shuah Khan <shuah@...nel.org>, sspatil@...gle.com,
        Stephen Rothwell <sfr@...b.auug.org.au>, surenb@...gle.com,
        Thomas Gleixner <tglx@...utronix.de>, timmurray@...gle.com,
        torvalds@...ux-foundation.org, Tycho Andersen <tycho@...ho.ws>
Subject: Re: [PATCH v1 2/2] Add selftests for pidfd polling

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) <joel@...lfernandes.org>
> ---
>  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.

> +
> +#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().

> +	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);

> +	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. 

> +		_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?

> +	}
> +
> +	c = epoll_wait(epoll_fd, events, MAX_EVENTS, 5000);

Uhm 5000 timeout? Either do a -1 or something that is noticeably
shorter, please. :)

> +	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. 

> +
> +	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?

> +}
> +
> +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.

> +
> +	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.

> +	}
> +
> +	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?

> +		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

> +
> +	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

> +{
> +	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)

> +
> +	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)

> +
> +	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.

> +	}
> +
> +	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.

> +		ksft_exit_fail_msg("%s test: Failed\n", test_name);
> +	else
> +		ksft_test_result_pass("%s test: Passed\n", test_name);
> +}
> +
>  int main(int argc, char **argv)
>  {
>  	ksft_print_header();
>  
> +	test_pidfd_poll_exec(0);
> +	test_pidfd_poll_exec(1);
> +	test_pidfd_poll_leader_exit(0);
> +	test_pidfd_poll_leader_exit(1);
>  	test_pidfd_send_signal_syscall_support();
>  	test_pidfd_send_signal_simple_success();
>  	test_pidfd_send_signal_exited_fail();
> -- 
> 2.21.0.593.g511ec345e18-goog
> 

Powered by blists - more mailing lists