Merge tag 'threads-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux

Pull pidfd updates from Christian Brauner:
 "This introduces a new extension to the pidfd_open() syscall. Users can
  now raise the new PIDFD_NONBLOCK flag to support non-blocking pidfd
  file descriptors. This has been requested for uses in async process
  management libraries such as async-pidfd in Rust.

  Ever since the introduction of pidfds and more advanced async io
  various programming languages such as Rust have grown support for
  async event libraries. These libraries are created to help build
  epoll-based event loops around file descriptors. A common pattern is
  to automatically make all file descriptors they manage to O_NONBLOCK.

  For such libraries the EAGAIN error code is treated specially. When a
  function is called that returns EAGAIN the function isn't called again
  until the event loop indicates the the file descriptor is ready.
  Supporting EAGAIN when waiting on pidfds makes such libraries just
  work with little effort.

  This introduces a new flag PIDFD_NONBLOCK that is equivalent to
  O_NONBLOCK. This follows the same patterns we have for other (anon
  inode) file descriptors such as EFD_NONBLOCK, IN_NONBLOCK,
  SFD_NONBLOCK, TFD_NONBLOCK and the same for close-on-exec flags.

  Passing a non-blocking pidfd to waitid() currently has no effect, i.e.
  is not supported. There are users which would like to use waitid() on
  pidfds that are O_NONBLOCK and mix it with pidfds that are blocking
  and both pass them to waitid().

  The expected behavior is to have waitid() return -EAGAIN for
  non-blocking pidfds and to block for blocking pidfds without needing
  to perform any additional checks for flags set on the pidfd before
  passing it to waitid(). Non-blocking pidfds will return EAGAIN from
  waitid() when no child process is ready yet. Returning -EAGAIN for
  non-blocking pidfds makes it easier for event loops that handle EAGAIN
  specially.

  It also makes the API more consistent and uniform. In essence,
  waitid() is treated like a read on a non-blocking pidfd or a recvmsg()
  on a non-blocking socket.

  With the addition of support for non-blocking pidfds we support the
  same functionality that sockets do. For sockets() recvmsg() supports
  MSG_DONTWAIT for pidfds waitid() supports WNOHANG. Both flags are
  per-call options. In contrast non-blocking pidfds and non-blocking
  sockets are a setting on an open file description affecting all
  threads in the calling process as well as other processes that hold
  file descriptors referring to the same open file description. Both
  behaviors, per call and per open file description, have genuine
  use-cases.

  The interaction with the WNOHANG flag is documented as follows:

   - If a non-blocking pidfd is passed and WNOHANG is not raised we
     simply raise the WNOHANG flag internally. When do_wait() returns
     indicating that there are eligible child processes but none have
     exited yet we set EAGAIN. If no child process exists we continue
     returning ECHILD.

   - If a non-blocking pidfd is passed and WNOHANG is raised waitid()
     will continue returning 0, i.e. it will not set EAGAIN. This ensure
     backwards compatibility with applications passing WNOHANG
     explicitly with pidfds"

* tag 'threads-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux:
  tests: remove O_NONBLOCK before waiting for WSTOPPED
  tests: add waitid() tests for non-blocking pidfds
  tests: port pidfd_wait to kselftest harness
  pidfd: support PIDFD_NONBLOCK in pidfd_open()
  exit: support non-blocking pidfds

2 files changed, 133 insertions, 175 deletions

diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index a2c80914e3dc..01f8d3c0cf2c 100644
--- a/tools/testing/selftests/pidfd/pidfd.h
+++ b/tools/testing/selftests/pidfd/pidfd.h
@@ -46,6 +46,10 @@
 #define __NR_pidfd_getfd -1
 #endif
 
+#ifndef PIDFD_NONBLOCK
+#define PIDFD_NONBLOCK O_NONBLOCK
+#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.
diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c
index 7079f8eef792..be2943f072f6 100644
--- a/tools/testing/selftests/pidfd/pidfd_wait.c
+++ b/tools/testing/selftests/pidfd/pidfd_wait.c
@@ -17,10 +17,15 @@
 #include <unistd.h>
 
 #include "pidfd.h"
-#include "../kselftest.h"
+#include "../kselftest_harness.h"
 
 #define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
 
+/* Attempt to de-conflict with the selftests tree. */
+#ifndef SKIP
+#define SKIP(s, ...)	XFAIL(s, ##__VA_ARGS__)
+#endif
+
 static pid_t sys_clone3(struct clone_args *args)
 {
 	return syscall(__NR_clone3, args, sizeof(struct clone_args));
@@ -32,9 +37,8 @@ static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options,
 	return syscall(__NR_waitid, which, pid, info, options, ru);
 }
 
-static int test_pidfd_wait_simple(void)
+TEST(wait_simple)
 {
-	const char *test_name = "pidfd wait simple";
 	int pidfd = -1, status = 0;
 	pid_t parent_tid = -1;
 	struct clone_args args = {
@@ -50,76 +54,40 @@ static int test_pidfd_wait_simple(void)
 	};
 
 	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));
+	ASSERT_GE(pidfd, 0);
 
 	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);
+	ASSERT_NE(pid, 0);
+	EXPECT_EQ(close(pidfd), 0);
 	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));
+	ASSERT_GE(pidfd, 0);
 
 	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);
+	ASSERT_NE(pid, 0);
+	EXPECT_EQ(close(pidfd), 0);
 	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));
+	ASSERT_GE(pid, 0);
 
 	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;
+	ASSERT_GE(pid, 0);
+	ASSERT_EQ(WIFEXITED(info.si_status), true);
+	ASSERT_EQ(WEXITSTATUS(info.si_status), 0);
+	EXPECT_EQ(close(pidfd), 0);
+
+	ASSERT_EQ(info.si_signo, SIGCHLD);
+	ASSERT_EQ(info.si_code, CLD_EXITED);
+	ASSERT_EQ(info.si_pid, parent_tid);
 }
 
-static int test_pidfd_wait_states(void)
+TEST(wait_states)
 {
-	const char *test_name = "pidfd wait states";
 	int pidfd = -1, status = 0;
 	pid_t parent_tid = -1;
 	struct clone_args args = {
@@ -135,9 +103,7 @@ static int test_pidfd_wait_states(void)
 	};
 
 	pid = sys_clone3(&args);
-	if (pid < 0)
-		ksft_exit_fail_msg("%s test: failed to create new process %s\n",
-				   test_name, strerror(errno));
+	ASSERT_GE(pid, 0);
 
 	if (pid == 0) {
 		kill(getpid(), SIGSTOP);
@@ -145,127 +111,115 @@ static int test_pidfd_wait_states(void)
 		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));
+	ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0);
+	ASSERT_EQ(info.si_signo, SIGCHLD);
+	ASSERT_EQ(info.si_code, CLD_STOPPED);
+	ASSERT_EQ(info.si_pid, parent_tid);
 
-	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;
+	ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0);
+
+	ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL), 0);
+	ASSERT_EQ(info.si_signo, SIGCHLD);
+	ASSERT_EQ(info.si_code, CLD_CONTINUED);
+	ASSERT_EQ(info.si_pid, parent_tid);
+
+	ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED, NULL), 0);
+	ASSERT_EQ(info.si_signo, SIGCHLD);
+	ASSERT_EQ(info.si_code, CLD_STOPPED);
+	ASSERT_EQ(info.si_pid, parent_tid);
+
+	ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0), 0);
+
+	ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL), 0);
+	ASSERT_EQ(info.si_signo, SIGCHLD);
+	ASSERT_EQ(info.si_code, CLD_KILLED);
+	ASSERT_EQ(info.si_pid, parent_tid);
+
+	EXPECT_EQ(close(pidfd), 0);
 }
 
-int main(int argc, char **argv)
+TEST(wait_nonblock)
 {
-	ksft_print_header();
-	ksft_set_plan(2);
+	int pidfd, status = 0;
+	unsigned int flags = 0;
+	pid_t parent_tid = -1;
+	struct clone_args args = {
+		.parent_tid = ptr_to_u64(&parent_tid),
+		.flags = CLONE_PARENT_SETTID,
+		.exit_signal = SIGCHLD,
+	};
+	int ret;
+	pid_t pid;
+	siginfo_t info = {
+		.si_signo = 0,
+	};
+
+	/*
+	 * Callers need to see ECHILD with non-blocking pidfds when no child
+	 * processes exists.
+	 */
+	pidfd = sys_pidfd_open(getpid(), PIDFD_NONBLOCK);
+	EXPECT_GE(pidfd, 0) {
+		/* pidfd_open() doesn't support PIDFD_NONBLOCK. */
+		ASSERT_EQ(errno, EINVAL);
+		SKIP(return, "Skipping PIDFD_NONBLOCK test");
+	}
+
+	ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+	ASSERT_LT(ret, 0);
+	ASSERT_EQ(errno, ECHILD);
+	EXPECT_EQ(close(pidfd), 0);
+
+	pid = sys_clone3(&args);
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		kill(getpid(), SIGSTOP);
+		exit(EXIT_SUCCESS);
+	}
 
-	test_pidfd_wait_simple();
-	test_pidfd_wait_states();
+	pidfd = sys_pidfd_open(pid, PIDFD_NONBLOCK);
+	EXPECT_GE(pidfd, 0) {
+		/* pidfd_open() doesn't support PIDFD_NONBLOCK. */
+		ASSERT_EQ(errno, EINVAL);
+		SKIP(return, "Skipping PIDFD_NONBLOCK test");
+	}
+
+	flags = fcntl(pidfd, F_GETFL, 0);
+	ASSERT_GT(flags, 0);
+	ASSERT_GT((flags & O_NONBLOCK), 0);
+
+	/*
+	 * Callers need to see EAGAIN/EWOULDBLOCK with non-blocking pidfd when
+	 * child processes exist but none have exited.
+	 */
+	ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL);
+	ASSERT_LT(ret, 0);
+	ASSERT_EQ(errno, EAGAIN);
+
+	/*
+	 * Callers need to continue seeing 0 with non-blocking pidfd and
+	 * WNOHANG raised explicitly when child processes exist but none have
+	 * exited.
+	 */
+	ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED | WNOHANG, NULL);
+	ASSERT_EQ(ret, 0);
 
-	return ksft_exit_pass();
+	ASSERT_EQ(fcntl(pidfd, F_SETFL, (flags & ~O_NONBLOCK)), 0);
+
+	ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0);
+	ASSERT_EQ(info.si_signo, SIGCHLD);
+	ASSERT_EQ(info.si_code, CLD_STOPPED);
+	ASSERT_EQ(info.si_pid, parent_tid);
+
+	ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0);
+
+	ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL), 0);
+	ASSERT_EQ(info.si_signo, SIGCHLD);
+	ASSERT_EQ(info.si_code, CLD_EXITED);
+	ASSERT_EQ(info.si_pid, parent_tid);
+
+	EXPECT_EQ(close(pidfd), 0);
 }
+
+TEST_HARNESS_MAIN