summaryrefslogtreecommitdiffstats
path: root/kernel/exit.c
diff options
context:
space:
mode:
authorChristian Brauner <christian.brauner@ubuntu.com>2020-09-02 12:21:28 +0200
committerChristian Brauner <christian.brauner@ubuntu.com>2020-09-04 12:31:30 +0200
commitba7d25f3dff6adc03b669fea87e356b8dc04575e (patch)
treea1f745bc61f5875da9153f1d92f13732464e4d04 /kernel/exit.c
parentLinux 5.9-rc2 (diff)
downloadlinux-ba7d25f3dff6adc03b669fea87e356b8dc04575e.tar.xz
linux-ba7d25f3dff6adc03b669fea87e356b8dc04575e.zip
exit: support non-blocking pidfds
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 implementation should be straightforward: - 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. A concrete use-case that was brought on-list was Josh's async pidfd library. 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. Suggested-by: Josh Triplett <josh@joshtriplett.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Sargun Dhillon <sargun@sargun.me> Cc: Jann Horn <jannh@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Link: https://lore.kernel.org/lkml/20200811181236.GA18763@localhost/ Link: https://github.com/joshtriplett/async-pidfd Link: https://lore.kernel.org/r/20200902102130.147672-3-christian.brauner@ubuntu.com
Diffstat (limited to 'kernel/exit.c')
-rw-r--r--kernel/exit.c15
1 files changed, 12 insertions, 3 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index 733e80f334e7..1f51c27bae59 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1474,7 +1474,7 @@ end:
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;