Merge tag 'core-process-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull pidfd/waitid updates from Christian Brauner:
 "This contains two features and various tests.

  First, it adds support for waiting on process through pidfds by adding
  the P_PIDFD type to the waitid() syscall. This completes the basic
  functionality of the pidfd api (cf. [1]). In the meantime we also have
  a new adition to the userspace projects that make use of the pidfd
  api. The qt project was nice enough to send a mail pointing out that
  they have a pr up to switch to the pidfd api (cf. [2]).

  Second, this tag contains an extension to the waitid() syscall to make
  it possible to wait on the current process group in a race free manner
  (even though the actual problem is very unlikely) by specifing 0
  together with the P_PGID type. This extension traces back to a
  discussion on the glibc development mailing list.

  There are also a range of tests for the features above. Additionally,
  the test-suite which detected the pidfd-polling race we fixed in [3]
  is included in this tag"

[1] https://lwn.net/Articles/794707/
[2] https://codereview.qt-project.org/c/qt/qtbase/+/108456
[3] commit b191d649 ("pidfd: fix a poll race when setting exit_state")

* tag 'core-process-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  waitid: Add support for waiting for the current process group
  tests: add pidfd poll tests
  tests: move common definitions and functions into pidfd.h
  pidfd: add pidfd_wait tests
  pidfd: add P_PIDFD to waitid()

include/linux/pid.h

@@ -72,6 +72,10 @@ extern struct pid init_struct_pid;
 
 extern const struct file_operations pidfd_fops;
 
+struct file;
+
+extern struct pid *pidfd_pid(const struct file *file);
+
 static inline struct pid *get_pid(struct pid *pid)
 {
 	if (pid)

include/uapi/linux/wait.h

@@ -17,6 +17,7 @@
 #define P_ALL		0
 #define P_PID		1
 #define P_PGID		2
+#define P_PIDFD		3
 
 
 #endif /* _UAPI_LINUX_WAIT_H */

kernel/exit.c

@@ -1554,6 +1554,23 @@ static long do_wait(struct wait_opts *wo)
 	return retval;
 }
 
+static struct pid *pidfd_get_pid(unsigned int fd)
+{
+	struct fd f;
+	struct pid *pid;
+
+	f = fdget(fd);
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	pid = pidfd_pid(f.file);
+	if (!IS_ERR(pid))
+		get_pid(pid);
+
+	fdput(f);
+	return pid;
+}
+
 static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 			  int options, struct rusage *ru)
 {
@@ -1576,19 +1593,32 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 		type = PIDTYPE_PID;
 		if (upid <= 0)
 			return -EINVAL;
+
+		pid = find_get_pid(upid);
 		break;
 	case P_PGID:
 		type = PIDTYPE_PGID;
-		if (upid <= 0)
+		if (upid < 0)
+			return -EINVAL;
+
+		if (upid)
+			pid = find_get_pid(upid);
+		else
+			pid = get_task_pid(current, PIDTYPE_PGID);
+		break;
+	case P_PIDFD:
+		type = PIDTYPE_PID;
+		if (upid < 0)
 			return -EINVAL;
+
+		pid = pidfd_get_pid(upid);
+		if (IS_ERR(pid))
+			return PTR_ERR(pid);
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	if (type < PIDTYPE_MAX)
-		pid = find_get_pid(upid);
-
 	wo.wo_type	= type;
 	wo.wo_pid	= pid;
 	wo.wo_flags	= options;

kernel/fork.c

@@ -1690,6 +1690,14 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
+struct pid *pidfd_pid(const struct file *file)
+{
+	if (file->f_op == &pidfd_fops)
+		return file->private_data;
+
+	return ERR_PTR(-EBADF);
+}
+
 static int pidfd_release(struct inode *inode, struct file *file)
 {
 	struct pid *pid = file->private_data;

kernel/signal.c

@@ -3678,8 +3678,11 @@ static int copy_siginfo_from_user_any(kernel_siginfo_t *kinfo, siginfo_t *info)
 
 static struct pid *pidfd_to_pid(const struct file *file)
 {
-	if (file->f_op == &pidfd_fops)
-		return file->private_data;
+	struct pid *pid;
+
+	pid = pidfd_pid(file);
+	if (!IS_ERR(pid))
+		return pid;
 
 	return tgid_pidfd_to_pid(file);
 }

tools/testing/selftests/pidfd/.gitignore

 pidfd_open_test
+pidfd_poll_test
 pidfd_test
+pidfd_wait

tools/testing/selftests/pidfd/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
 CFLAGS += -g -I../../../../usr/include/ -lpthread
 
-TEST_GEN_PROGS := pidfd_test pidfd_open_test
+TEST_GEN_PROGS := pidfd_test pidfd_open_test pidfd_poll_test pidfd_wait
 
 include ../lib.mk
 

tools/testing/selftests/pidfd/pidfd.h

@@ -16,6 +16,26 @@
 
 #include "../kselftest.h"
 
+#ifndef P_PIDFD
+#define P_PIDFD 3
+#endif
+
+#ifndef CLONE_PIDFD
+#define CLONE_PIDFD 0x00001000
+#endif
+
+#ifndef __NR_pidfd_open
+#define __NR_pidfd_open -1
+#endif
+
+#ifndef __NR_pidfd_send_signal
+#define __NR_pidfd_send_signal -1
+#endif
+
+#ifndef __NR_clone3
+#define __NR_clone3 -1
+#endif
+
 /*
  * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c
  * That means, when it wraps around any pid < 300 will be skipped.
@@ -53,5 +73,15 @@ int wait_for_pid(pid_t pid)
 	return WEXITSTATUS(status);
 }
 
+static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
+{
+	return syscall(__NR_pidfd_open, pid, flags);
+}
+
+static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info,
+					unsigned int flags)
+{
+	return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags);
+}
 
 #endif /* __PIDFD_H */

tools/testing/selftests/pidfd/pidfd_open_test.c

@@ -22,11 +22,6 @@
 #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;

tools/testing/selftests/pidfd/pidfd_poll_test.c

+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "pidfd.h"
+#include "../kselftest.h"
+
+static bool timeout;
+
+static void handle_alarm(int sig)
+{
+	timeout = true;
+}
+
+int main(int argc, char **argv)
+{
+	struct pollfd fds;
+	int iter, nevents;
+	int nr_iterations = 10000;
+
+	fds.events = POLLIN;
+
+	if (argc > 2)
+		ksft_exit_fail_msg("Unexpected command line argument\n");
+
+	if (argc == 2) {
+		nr_iterations = atoi(argv[1]);
+		if (nr_iterations <= 0)
+			ksft_exit_fail_msg("invalid input parameter %s\n",
+					argv[1]);
+	}
+
+	ksft_print_msg("running pidfd poll test for %d iterations\n",
+		nr_iterations);
+
+	for (iter = 0; iter < nr_iterations; iter++) {
+		int pidfd;
+		int child_pid = fork();
+
+		if (child_pid < 0) {
+			if (errno == EAGAIN) {
+				iter--;
+				continue;
+			}
+			ksft_exit_fail_msg(
+				"%s - failed to fork a child process\n",
+				strerror(errno));
+		}
+
+		if (child_pid == 0) {
+			/* Child process just sleeps for a min and exits */
+			sleep(60);
+			exit(EXIT_SUCCESS);
+		}
+
+		/* Parent kills the child and waits for its death */
+		pidfd = sys_pidfd_open(child_pid, 0);
+		if (pidfd < 0)
+			ksft_exit_fail_msg("%s - pidfd_open failed\n",
+					strerror(errno));
+
+		/* Setup 3 sec alarm - plenty of time */
+		if (signal(SIGALRM, handle_alarm) == SIG_ERR)
+			ksft_exit_fail_msg("%s - signal failed\n",
+					strerror(errno));
+		alarm(3);
+
+		/* Send SIGKILL to the child */
+		if (sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0))
+			ksft_exit_fail_msg("%s - pidfd_send_signal failed\n",
+					strerror(errno));
+
+		/* Wait for the death notification */
+		fds.fd = pidfd;
+		nevents = poll(&fds, 1, -1);
+
+		/* Check for error conditions */
+		if (nevents < 0)
+			ksft_exit_fail_msg("%s - poll failed\n",
+					strerror(errno));
+
+		if (nevents != 1)
+			ksft_exit_fail_msg("unexpected poll result: %d\n",
+					nevents);
+
+		if (!(fds.revents & POLLIN))
+			ksft_exit_fail_msg(
+				"unexpected event type received: 0x%x\n",
+				fds.revents);
+
+		if (timeout)
+			ksft_exit_fail_msg(
+				"death notification wait timeout\n");
+
+		close(pidfd);
+		/* Wait for child to prevent zombies */
+		if (waitpid(child_pid, NULL, 0) < 0)
+			ksft_exit_fail_msg("%s - waitpid failed\n",
+					strerror(errno));
+
+	}
+
+	ksft_test_result_pass("pidfd poll test: pass\n");
+	return ksft_exit_pass();
+}

tools/testing/selftests/pidfd/pidfd_test.c

@@ -21,20 +21,12 @@
 #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;
@@ -47,12 +39,6 @@ static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *))
 #endif
 }
 
-static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info,
-					unsigned int flags)
-{
-	return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags);
-}
-
 static int signal_received;
 
 static void set_signal_received_on_sigusr1(int sig)

tools/testing/selftests/pidfd/pidfd_wait.c

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <signal.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sched.h>
+#include <string.h>
+#include <sys/resource.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "pidfd.h"
+#include "../kselftest.h"
+
+#define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
+
+static pid_t sys_clone3(struct clone_args *args)
+{
+	return syscall(__NR_clone3, args, sizeof(struct clone_args));
+}
+
+static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options,
+		      struct rusage *ru)
+{
+	return syscall(__NR_waitid, which, pid, info, options, ru);
+}
+
+static int test_pidfd_wait_simple(void)
+{
+	const char *test_name = "pidfd wait simple";
+	int pidfd = -1, status = 0;
+	pid_t parent_tid = -1;
+	struct clone_args args = {
+		.parent_tid = ptr_to_u64(&parent_tid),
+		.pidfd = ptr_to_u64(&pidfd),
+		.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
+		.exit_signal = SIGCHLD,
+	};
+	int ret;
+	pid_t pid;
+	siginfo_t info = {
+		.si_signo = 0,
+	};
+
+	pidfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC);
+	if (pidfd < 0)
+		ksft_exit_fail_msg("%s test: failed to open /proc/self %s\n",
+				   test_name, strerror(errno));
+
+	pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+	if (pid == 0)
+		ksft_exit_fail_msg(
+			"%s test: succeeded to wait on invalid pidfd %s\n",
+			test_name, strerror(errno));
+	close(pidfd);
+	pidfd = -1;
+
+	pidfd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+	if (pidfd == 0)
+		ksft_exit_fail_msg("%s test: failed to open /dev/null %s\n",
+				   test_name, strerror(errno));
+
+	pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+	if (pid == 0)
+		ksft_exit_fail_msg(
+			"%s test: succeeded to wait on invalid pidfd %s\n",
+			test_name, strerror(errno));
+	close(pidfd);
+	pidfd = -1;
+
+	pid = sys_clone3(&args);
+	if (pid < 0)
+		ksft_exit_fail_msg("%s test: failed to create new process %s\n",
+				   test_name, strerror(errno));
+
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+
+	pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+	if (pid < 0)
+		ksft_exit_fail_msg(
+			"%s test: failed to wait on process with pid %d and pidfd %d: %s\n",
+			test_name, parent_tid, pidfd, strerror(errno));
+
+	if (!WIFEXITED(info.si_status) || WEXITSTATUS(info.si_status))
+		ksft_exit_fail_msg(
+			"%s test: unexpected status received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, parent_tid, pidfd, strerror(errno));
+	close(pidfd);
+
+	if (info.si_signo != SIGCHLD)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_signo, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_code != CLD_EXITED)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_code, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_pid != parent_tid)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_pid, parent_tid, pidfd,
+			strerror(errno));
+
+	ksft_test_result_pass("%s test: Passed\n", test_name);
+	return 0;
+}
+
+static int test_pidfd_wait_states(void)
+{
+	const char *test_name = "pidfd wait states";
+	int pidfd = -1, status = 0;
+	pid_t parent_tid = -1;
+	struct clone_args args = {
+		.parent_tid = ptr_to_u64(&parent_tid),
+		.pidfd = ptr_to_u64(&pidfd),
+		.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
+		.exit_signal = SIGCHLD,
+	};
+	int ret;
+	pid_t pid;
+	siginfo_t info = {
+		.si_signo = 0,
+	};
+
+	pid = sys_clone3(&args);
+	if (pid < 0)
+		ksft_exit_fail_msg("%s test: failed to create new process %s\n",
+				   test_name, strerror(errno));
+
+	if (pid == 0) {
+		kill(getpid(), SIGSTOP);
+		kill(getpid(), SIGSTOP);
+		exit(EXIT_SUCCESS);
+	}
+
+	ret = sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL);
+	if (ret < 0)
+		ksft_exit_fail_msg(
+			"%s test: failed to wait on WSTOPPED process with pid %d and pidfd %d: %s\n",
+			test_name, parent_tid, pidfd, strerror(errno));
+
+	if (info.si_signo != SIGCHLD)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_signo, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_code != CLD_STOPPED)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_code, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_pid != parent_tid)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_pid, parent_tid, pidfd,
+			strerror(errno));
+
+	ret = sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0);
+	if (ret < 0)
+		ksft_exit_fail_msg(
+			"%s test: failed to send signal to process with pid %d and pidfd %d: %s\n",
+			test_name, parent_tid, pidfd, strerror(errno));
+
+	ret = sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL);
+	if (ret < 0)
+		ksft_exit_fail_msg(
+			"%s test: failed to wait WCONTINUED on process with pid %d and pidfd %d: %s\n",
+			test_name, parent_tid, pidfd, strerror(errno));
+
+	if (info.si_signo != SIGCHLD)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_signo, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_code != CLD_CONTINUED)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_code, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_pid != parent_tid)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_pid, parent_tid, pidfd,
+			strerror(errno));
+
+	ret = sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED, NULL);
+	if (ret < 0)
+		ksft_exit_fail_msg(
+			"%s test: failed to wait on WUNTRACED process with pid %d and pidfd %d: %s\n",
+			test_name, parent_tid, pidfd, strerror(errno));
+
+	if (info.si_signo != SIGCHLD)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_signo, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_code != CLD_STOPPED)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_code, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_pid != parent_tid)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_pid, parent_tid, pidfd,
+			strerror(errno));
+
+	ret = sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0);
+	if (ret < 0)
+		ksft_exit_fail_msg(
+			"%s test: failed to send SIGKILL to process with pid %d and pidfd %d: %s\n",
+			test_name, parent_tid, pidfd, strerror(errno));
+
+	ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+	if (ret < 0)
+		ksft_exit_fail_msg(
+			"%s test: failed to wait on WEXITED process with pid %d and pidfd %d: %s\n",
+			test_name, parent_tid, pidfd, strerror(errno));
+
+	if (info.si_signo != SIGCHLD)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_signo, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_code != CLD_KILLED)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_code, parent_tid, pidfd,
+			strerror(errno));
+
+	if (info.si_pid != parent_tid)
+		ksft_exit_fail_msg(
+			"%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n",
+			test_name, info.si_pid, parent_tid, pidfd,
+			strerror(errno));
+
+	close(pidfd);
+
+	ksft_test_result_pass("%s test: Passed\n", test_name);
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	ksft_print_header();
+	ksft_set_plan(2);
+
+	test_pidfd_wait_simple();
+	test_pidfd_wait_states();
+
+	return ksft_exit_pass();
+}