Merge tag 'pidfd-updates-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull pidfd updates from Christian Brauner:
 "This adds two main features.

   - First, it adds polling support for pidfds. This allows process
     managers to know when a (non-parent) process dies in a race-free
     way.

     The notification mechanism used follows the same logic that is
     currently used when the parent of a task is notified of a child's
     death. With this patchset it is possible to put pidfds in an
     {e}poll loop and get reliable notifications for process (i.e.
     thread-group) exit.

   - The second feature compliments the first one by making it possible
     to retrieve pollable pidfds for processes that were not created
     using CLONE_PIDFD.

     A lot of processes get created with traditional PID-based calls
     such as fork() or clone() (without CLONE_PIDFD). For these
     processes a caller can currently not create a pollable pidfd. This
     is a problem for Android's low memory killer (LMK) and service
     managers such as systemd.

  Both patchsets are accompanied by selftests.

  It's perhaps worth noting that the work done so far and the work done
  in this branch for pidfd_open() and polling support do already see
  some adoption:

   - Android is in the process of backporting this work to all their LTS
     kernels [1]

   - Service managers make use of pidfd_send_signal but will need to
     wait until we enable waiting on pidfds for full adoption.

   - And projects I maintain make use of both pidfd_send_signal and
     CLONE_PIDFD [2] and will use polling support and pidfd_open() too"

[1] https://android-review.googlesource.com/q/topic:%22pidfd+polling+support+4.9+backport%22
    https://android-review.googlesource.com/q/topic:%22pidfd+polling+support+4.14+backport%22
    https://android-review.googlesource.com/q/topic:%22pidfd+polling+support+4.19+backport%22

[2] https://github.com/lxc/lxc/blob/aab6e3eb73c343231cdde775db938994fc6f2803/src/lxc/start.c#L1753

* tag 'pidfd-updates-v5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  tests: add pidfd_open() tests
  arch: wire-up pidfd_open()
  pid: add pidfd_open()
  pidfd: add polling selftests
  pidfd: add polling support

5 files changed, 437 insertions, 42 deletions

diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore
index 822a1e63d045..16d84d117bc0 100644
--- a/tools/testing/selftests/pidfd/.gitignore
+++ b/tools/testing/selftests/pidfd/.gitignore
@@ -1 +1,2 @@
+pidfd_open_test
 pidfd_test
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index 443fedbd6231..720b2d884b3c 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
-CFLAGS += -g -I../../../../usr/include/
+CFLAGS += -g -I../../../../usr/include/ -lpthread
 
-TEST_GEN_PROGS := pidfd_test
+TEST_GEN_PROGS := pidfd_test pidfd_open_test
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
new file mode 100644
index 000000000000..8452e910463f
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __PIDFD_H
+#define __PIDFD_H
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/mount.h>
+
+#include "../kselftest.h"
+
+/*
+ * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c
+ * That means, when it wraps around any pid < 300 will be skipped.
+ * So we need to use a pid > 300 in order to test recycling.
+ */
+#define PID_RECYCLE 1000
+
+/*
+ * Define a few custom error codes for the child process to clearly indicate
+ * what is happening. This way we can tell the difference between a system
+ * error, a test error, etc.
+ */
+#define PIDFD_PASS 0
+#define PIDFD_FAIL 1
+#define PIDFD_ERROR 2
+#define PIDFD_SKIP 3
+#define PIDFD_XFAIL 4
+
+int wait_for_pid(pid_t pid)
+{
+	int status, ret;
+
+again:
+	ret = waitpid(pid, &status, 0);
+	if (ret == -1) {
+		if (errno == EINTR)
+			goto again;
+
+		return -1;
+	}
+
+	if (!WIFEXITED(status))
+		return -1;
+
+	return WEXITSTATUS(status);
+}
+
+
+#endif /* __PIDFD_H */
diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c
new file mode 100644
index 000000000000..0377133dd6dc
--- /dev/null
+++ b/tools/testing/selftests/pidfd/pidfd_open_test.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/mount.h>
+#include <sys/prctl.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "pidfd.h"
+#include "../kselftest.h"
+
+static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
+{
+	return syscall(__NR_pidfd_open, pid, flags);
+}
+
+static int safe_int(const char *numstr, int *converted)
+{
+	char *err = NULL;
+	long sli;
+
+	errno = 0;
+	sli = strtol(numstr, &err, 0);
+	if (errno == ERANGE && (sli == LONG_MAX || sli == LONG_MIN))
+		return -ERANGE;
+
+	if (errno != 0 && sli == 0)
+		return -EINVAL;
+
+	if (err == numstr || *err != '\0')
+		return -EINVAL;
+
+	if (sli > INT_MAX || sli < INT_MIN)
+		return -ERANGE;
+
+	*converted = (int)sli;
+	return 0;
+}
+
+static int char_left_gc(const char *buffer, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++) {
+		if (buffer[i] == ' ' ||
+		    buffer[i] == '\t')
+			continue;
+
+		return i;
+	}
+
+	return 0;
+}
+
+static int char_right_gc(const char *buffer, size_t len)
+{
+	int i;
+
+	for (i = len - 1; i >= 0; i--) {
+		if (buffer[i] == ' '  ||
+		    buffer[i] == '\t' ||
+		    buffer[i] == '\n' ||
+		    buffer[i] == '\0')
+			continue;
+
+		return i + 1;
+	}
+
+	return 0;
+}
+
+static char *trim_whitespace_in_place(char *buffer)
+{
+	buffer += char_left_gc(buffer, strlen(buffer));
+	buffer[char_right_gc(buffer, strlen(buffer))] = '\0';
+	return buffer;
+}
+
+static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen)
+{
+	int ret;
+	char path[512];
+	FILE *f;
+	size_t n = 0;
+	pid_t result = -1;
+	char *line = NULL;
+
+	snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", pidfd);
+
+	f = fopen(path, "re");
+	if (!f)
+		return -1;
+
+	while (getline(&line, &n, f) != -1) {
+		char *numstr;
+
+		if (strncmp(line, key, keylen))
+			continue;
+
+		numstr = trim_whitespace_in_place(line + 4);
+		ret = safe_int(numstr, &result);
+		if (ret < 0)
+			goto out;
+
+		break;
+	}
+
+out:
+	free(line);
+	fclose(f);
+	return result;
+}
+
+int main(int argc, char **argv)
+{
+	int pidfd = -1, ret = 1;
+	pid_t pid;
+
+	ksft_set_plan(3);
+
+	pidfd = sys_pidfd_open(-1, 0);
+	if (pidfd >= 0) {
+		ksft_print_msg(
+			"%s - succeeded to open pidfd for invalid pid -1\n",
+			strerror(errno));
+		goto on_error;
+	}
+	ksft_test_result_pass("do not allow invalid pid test: passed\n");
+
+	pidfd = sys_pidfd_open(getpid(), 1);
+	if (pidfd >= 0) {
+		ksft_print_msg(
+			"%s - succeeded to open pidfd with invalid flag value specified\n",
+			strerror(errno));
+		goto on_error;
+	}
+	ksft_test_result_pass("do not allow invalid flag test: passed\n");
+
+	pidfd = sys_pidfd_open(getpid(), 0);
+	if (pidfd < 0) {
+		ksft_print_msg("%s - failed to open pidfd\n", strerror(errno));
+		goto on_error;
+	}
+	ksft_test_result_pass("open a new pidfd test: passed\n");
+
+	pid = get_pid_from_fdinfo_file(pidfd, "Pid:", sizeof("Pid:") - 1);
+	ksft_print_msg("pidfd %d refers to process with pid %d\n", pidfd, pid);
+
+	ret = 0;
+
+on_error:
+	if (pidfd >= 0)
+		close(pidfd);
+
+	return !ret ? ksft_exit_pass() : ksft_exit_fail();
+}
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index 104c75a33882..7eaa8a3de262 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -4,22 +4,49 @@
 #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 "pidfd.h"
 #include "../kselftest.h"
 
 #ifndef __NR_pidfd_send_signal
 #define __NR_pidfd_send_signal -1
 #endif
 
+#define str(s) _str(s)
+#define _str(s) #s
+#define CHILD_THREAD_MIN_WAIT 3 /* seconds */
+
+#define MAX_EVENTS 5
+
+#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)
 {
@@ -66,28 +93,6 @@ static int test_pidfd_send_signal_simple_success(void)
 	return 0;
 }
 
-static int wait_for_pid(pid_t pid)
-{
-	int status, ret;
-
-again:
-	ret = waitpid(pid, &status, 0);
-	if (ret == -1) {
-		if (errno == EINTR)
-			goto again;
-
-		return -1;
-	}
-
-	if (ret != pid)
-		goto again;
-
-	if (!WIFEXITED(status))
-		return -1;
-
-	return WEXITSTATUS(status);
-}
-
 static int test_pidfd_send_signal_exited_fail(void)
 {
 	int pidfd, ret, saved_errno;
@@ -133,13 +138,6 @@ static int test_pidfd_send_signal_exited_fail(void)
 }
 
 /*
- * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c
- * That means, when it wraps around any pid < 300 will be skipped.
- * So we need to use a pid > 300 in order to test recycling.
- */
-#define PID_RECYCLE 1000
-
-/*
  * Maximum number of cycles we allow. This is equivalent to PID_MAX_DEFAULT.
  * If users set a higher limit or we have cycled PIDFD_MAX_DEFAULT number of
  * times then we skip the test to not go into an infinite loop or block for a
@@ -147,17 +145,6 @@ static int test_pidfd_send_signal_exited_fail(void)
  */
 #define PIDFD_MAX_DEFAULT 0x8000
 
-/*
- * Define a few custom error codes for the child process to clearly indicate
- * what is happening. This way we can tell the difference between a system
- * error, a test error, etc.
- */
-#define PIDFD_PASS 0
-#define PIDFD_FAIL 1
-#define PIDFD_ERROR 2
-#define PIDFD_SKIP 3
-#define PIDFD_XFAIL 4
-
 static int test_pidfd_send_signal_recycled_pid_fail(void)
 {
 	int i, ret;
@@ -372,11 +359,192 @@ static int test_pidfd_send_signal_syscall_support(void)
 	return 0;
 }
 
+static void *test_pidfd_poll_exec_thread(void *priv)
+{
+	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");
+
+	execl("/bin/sleep", "sleep", str(CHILD_THREAD_MIN_WAIT), (char *)NULL);
+
+	ksft_print_msg("Child Thread: DONE. pid %d tid %d\n",
+			getpid(), syscall(SYS_gettid));
+	return NULL;
+}
+
+static void poll_pidfd(const char *test_name, int pidfd)
+{
+	int c;
+	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 "
+				   "(errno %d)\n",
+				   test_name, errno);
+
+	event.events = EPOLLIN;
+	event.data.fd = pidfd;
+
+	if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, pidfd, &event)) {
+		ksft_exit_fail_msg("%s test: Failed to add epoll file descriptor "
+				   "(errno %d)\n",
+				   test_name, errno);
+	}
+
+	c = epoll_wait(epoll_fd, events, MAX_EVENTS, 5000);
+	if (c != 1 || !(events[0].events & EPOLLIN))
+		ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) ",
+				   "(errno %d)\n",
+				   test_name, c, events[0].events, errno);
+
+	close(epoll_fd);
+	return;
+
+}
+
+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)
+		sleep(1);
+}
+
+static void 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);
+	if (pid < 0)
+		ksft_exit_fail_msg("%s test: pidfd_clone failed (ret %d, errno %d)\n",
+				   test_name, pid, errno);
+
+	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);
+	}
+
+	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)
+		ksft_exit_fail_msg("%s test: Failed\n", test_name);
+	else
+		ksft_test_result_pass("%s test: Passed\n", test_name);
+}
+
+static void *test_pidfd_poll_leader_exit_thread(void *priv)
+{
+	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);
+}
+
+static void test_pidfd_poll_leader_exit(int use_waitpid)
+{
+	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);
+
+	if (child_exit_secs == MAP_FAILED)
+		ksft_exit_fail_msg("%s test: mmap failed (errno %d)\n",
+				   test_name, errno);
+
+	ksft_print_msg("Parent: pid: %d\n", getpid());
+	pid = pidfd_clone(CLONE_PIDFD, &pidfd, child_poll_leader_exit_test);
+	if (pid < 0)
+		ksft_exit_fail_msg("%s test: pidfd_clone failed (ret %d, errno %d)\n",
+				   test_name, pid, errno);
+
+	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);
+	}
+
+	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)
+		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();
 	ksft_set_plan(4);
 
+	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();