selftests/pidfd: add seventh PIDFD_INFO_EXIT selftest

Add a selftest for PIDFD_INFO_EXIT behavior.

Link: https://lore.kernel.org/r/20250305-work-pidfs-kill_on_last_close-v3-16-c8c3d8361705@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

Author: brauner

tools/testing/selftests/pidfd/.gitignore

@@ -9,3 +9,4 @@ pidfd_setns_test
 pidfd_file_handle_test
 pidfd_bind_mount
 pidfd_info_test
+pidfd_exec_helper

tools/testing/selftests/pidfd/Makefile

@@ -5,5 +5,7 @@ TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \
 	pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test \
 	pidfd_file_handle_test pidfd_bind_mount pidfd_info_test
 
+TEST_GEN_PROGS_EXTENDED := pidfd_exec_helper
+
 include ../lib.mk
 

tools/testing/selftests/pidfd/pidfd.h

@@ -254,4 +254,11 @@ static inline ssize_t write_nointr(int fd, const void *buf, size_t count)
 	return ret;
 }
 
+static inline int sys_execveat(int dirfd, const char *pathname,
+			       char *const argv[], char *const envp[],
+			       int flags)
+{
+        return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags);
+}
+
 #endif /* __PIDFD_H */

tools/testing/selftests/pidfd/pidfd_exec_helper.c

@@ -0,0 +1,12 @@
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+int main(int argc, char *argv[])
+{
+	if (pause())
+		_exit(EXIT_FAILURE);
+
+	_exit(EXIT_SUCCESS);
+}

tools/testing/selftests/pidfd/pidfd_info_test.c

@@ -369,4 +369,129 @@ TEST_F(pidfd_info, thread_group)
 	EXPECT_EQ(close(pidfd_thread), 0);
 }
 
+static void *pidfd_info_thread_exec(void *arg)
+{
+	pid_t pid_thread = gettid();
+	int ipc_socket = *(int *)arg;
+
+	/* Inform the grand-parent what the tid of this thread is. */
+	if (write_nointr(ipc_socket, &pid_thread, sizeof(pid_thread)) != sizeof(pid_thread))
+		return NULL;
+
+	if (read_nointr(ipc_socket, &pid_thread, sizeof(pid_thread)) != sizeof(pid_thread))
+		return NULL;
+
+	close(ipc_socket);
+
+	sys_execveat(AT_FDCWD, "pidfd_exec_helper", NULL, NULL, 0);
+	return NULL;
+}
+
+TEST_F(pidfd_info, thread_group_exec)
+{
+	pid_t pid_leader, pid_thread;
+	pthread_t thread;
+	int nevents, pidfd_leader, pidfd_leader_thread, pidfd_thread, ret;
+	int ipc_sockets[2];
+	struct pollfd fds = {};
+	struct pidfd_info info = {
+		.mask = PIDFD_INFO_CGROUPID | PIDFD_INFO_EXIT,
+	};
+
+	ret = socketpair(AF_LOCAL, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	EXPECT_EQ(ret, 0);
+
+	pid_leader = create_child(&pidfd_leader, 0);
+	EXPECT_GE(pid_leader, 0);
+
+	if (pid_leader == 0) {
+		close(ipc_sockets[0]);
+
+		/* The thread will outlive the thread-group leader. */
+		if (pthread_create(&thread, NULL, pidfd_info_thread_exec, &ipc_sockets[1]))
+			syscall(__NR_exit, EXIT_FAILURE);
+
+		/* Make the thread-group leader exit prematurely. */
+		syscall(__NR_exit, EXIT_SUCCESS);
+	}
+
+	/* Retrieve the tid of the thread. */
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &pid_thread, sizeof(pid_thread)), sizeof(pid_thread));
+
+	/* Opening a thread as a PIDFD_THREAD must succeed. */
+	pidfd_thread = sys_pidfd_open(pid_thread, PIDFD_THREAD);
+	ASSERT_GE(pidfd_thread, 0);
+
+	/* Open a thread-specific pidfd for the thread-group leader. */
+	pidfd_leader_thread = sys_pidfd_open(pid_leader, PIDFD_THREAD);
+	ASSERT_GE(pidfd_leader_thread, 0);
+
+	/*
+	 * We can poll and wait for the old thread-group leader to exit
+	 * using a thread-specific pidfd.
+	 *
+	 * This only works until the thread has execed. When the thread
+	 * has execed it will have taken over the old thread-group
+	 * leaders struct pid. Calling poll after the thread execed will
+	 * thus block again because a new thread-group has started (Yes,
+	 * it's fscked.).
+	 */
+	fds.events = POLLIN;
+	fds.fd = pidfd_leader_thread;
+	nevents = poll(&fds, 1, -1);
+	ASSERT_EQ(nevents, 1);
+	/* The thread-group leader has exited. */
+	ASSERT_TRUE(!!(fds.revents & POLLIN));
+	/* The thread-group leader hasn't been reaped. */
+	ASSERT_FALSE(!!(fds.revents & POLLHUP));
+
+	/* Now that we've opened a thread-specific pidfd the thread can exec. */
+	ASSERT_EQ(write_nointr(ipc_sockets[0], &pid_thread, sizeof(pid_thread)), sizeof(pid_thread));
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	/* Wait until the kernel has SIGKILLed the thread. */
+	fds.events = POLLHUP;
+	fds.fd = pidfd_thread;
+	nevents = poll(&fds, 1, -1);
+	ASSERT_EQ(nevents, 1);
+	/* The thread has been reaped. */
+	ASSERT_TRUE(!!(fds.revents & POLLHUP));
+
+	/* Retrieve thread-specific exit info from pidfd. */
+	ASSERT_EQ(ioctl(pidfd_thread, PIDFD_GET_INFO, &info), 0);
+	ASSERT_FALSE(!!(info.mask & PIDFD_INFO_CREDS));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_EXIT));
+	/*
+	 * While the kernel will have SIGKILLed the whole thread-group
+	 * during exec it will cause the individual threads to exit
+	 * cleanly.
+	 */
+	ASSERT_TRUE(WIFEXITED(info.exit_code));
+	ASSERT_EQ(WEXITSTATUS(info.exit_code), 0);
+
+	/*
+	 * The thread-group leader is still alive, the thread has taken
+	 * over its struct pid and thus its pid number.
+	 */
+	info.mask = PIDFD_INFO_CGROUPID | PIDFD_INFO_EXIT;
+	ASSERT_EQ(ioctl(pidfd_leader, PIDFD_GET_INFO, &info), 0);
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_CREDS));
+	ASSERT_FALSE(!!(info.mask & PIDFD_INFO_EXIT));
+	ASSERT_EQ(info.pid, pid_leader);
+
+	/* Take down the thread-group leader. */
+	EXPECT_EQ(sys_pidfd_send_signal(pidfd_leader, SIGKILL, NULL, 0), 0);
+	EXPECT_EQ(sys_waitid(P_PIDFD, pidfd_leader, NULL, WEXITED), 0);
+
+	/* Retrieve exit information for the thread-group leader. */
+	info.mask = PIDFD_INFO_CGROUPID | PIDFD_INFO_EXIT;
+	ASSERT_EQ(ioctl(pidfd_leader, PIDFD_GET_INFO, &info), 0);
+	ASSERT_FALSE(!!(info.mask & PIDFD_INFO_CREDS));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_EXIT));
+
+	EXPECT_EQ(close(pidfd_leader), 0);
+	EXPECT_EQ(close(pidfd_thread), 0);
+}
+
 TEST_HARNESS_MAIN