diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h
new file mode 100644
index 0000000000000000000000000000000000000000..5406fbc1307489e2083a5c9136cf00c3844506ca
--- /dev/null
+++ b/include/uapi/linux/pidfd.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_LINUX_PIDFD_H
+#define _UAPI_LINUX_PIDFD_H
+
+#include <linux/types.h>
+#include <linux/fcntl.h>
+
+/* Flags for pidfd_open(). */
+#define PIDFD_NONBLOCK O_NONBLOCK
+
+#endif /* _UAPI_LINUX_PIDFD_H */
diff --git a/kernel/exit.c b/kernel/exit.c
index 733e80f334e71174420c4267a203203cc61ffbd7..1f51c27bae59341c7f7f45be479bd9735efb1a59 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1474,7 +1474,7 @@ static long do_wait(struct wait_opts *wo)
return retval;
}
-static struct pid *pidfd_get_pid(unsigned int fd)
+static struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags)
{
struct fd f;
struct pid *pid;
@@ -1484,8 +1484,10 @@ static struct pid *pidfd_get_pid(unsigned int fd)
return ERR_PTR(-EBADF);
pid = pidfd_pid(f.file);
- if (!IS_ERR(pid))
+ if (!IS_ERR(pid)) {
get_pid(pid);
+ *flags = f.file->f_flags;
+ }
fdput(f);
return pid;
@@ -1498,6 +1500,7 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
struct pid *pid = NULL;
enum pid_type type;
long ret;
+ unsigned int f_flags = 0;
if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
__WNOTHREAD|__WCLONE|__WALL))
@@ -1531,9 +1534,10 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
if (upid < 0)
return -EINVAL;
- pid = pidfd_get_pid(upid);
+ pid = pidfd_get_pid(upid, &f_flags);
if (IS_ERR(pid))
return PTR_ERR(pid);
+
break;
default:
return -EINVAL;
@@ -1544,7 +1548,12 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
wo.wo_flags = options;
wo.wo_info = infop;
wo.wo_rusage = ru;
+ if (f_flags & O_NONBLOCK)
+ wo.wo_flags |= WNOHANG;
+
ret = do_wait(&wo);
+ if (!ret && !(options & WNOHANG) && (f_flags & O_NONBLOCK))
+ ret = -EAGAIN;
put_pid(pid);
return ret;
diff --git a/kernel/pid.c b/kernel/pid.c
index b2562a7ce5258577c985f68e94ca9068ee518b00..74ddbff1a6ba754dd780568ca14429160d0a852c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -43,6 +43,7 @@
#include <linux/sched/task.h>
#include <linux/idr.h>
#include <net/sock.h>
+#include <uapi/linux/pidfd.h>
struct pid init_struct_pid = {
.count = REFCOUNT_INIT(1),
@@ -522,7 +523,8 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
/**
* pidfd_create() - Create a new pid file descriptor.
*
- * @pid: struct pid that the pidfd will reference
+ * @pid: struct pid that the pidfd will reference
+ * @flags: flags to pass
*
* This creates a new pid file descriptor with the O_CLOEXEC flag set.
*
@@ -532,12 +534,12 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
* Return: On success, a cloexec pidfd is returned.
* On error, a negative errno number will be returned.
*/
-static int pidfd_create(struct pid *pid)
+static int pidfd_create(struct pid *pid, unsigned int flags)
{
int fd;
fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
- O_RDWR | O_CLOEXEC);
+ flags | O_RDWR | O_CLOEXEC);
if (fd < 0)
put_pid(pid);
@@ -565,7 +567,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
int fd;
struct pid *p;
- if (flags)
+ if (flags & ~PIDFD_NONBLOCK)
return -EINVAL;
if (pid <= 0)
@@ -576,7 +578,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
return -ESRCH;
if (pid_has_task(p, PIDTYPE_TGID))
- fd = pidfd_create(p);
+ fd = pidfd_create(p, flags);
else
fd = -EINVAL;
diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h
index a2c80914e3dc3d146775ec70da712890b0af412a..01f8d3c0cf2cb844ecc233e5cc1f6b7fa1a42c0f 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 7079f8eef792ec2c9c03e9f93491af6c17f4974f..be2943f072f6088ba77df89ba2b7c942b9534465 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