pidfd: support PIDFD_NONBLOCK in pidfd_open()

Introduce PIDFD_NONBLOCK to support non-blocking pidfd file descriptors.

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. In the
following patch we will extend waitid() internally to support non-blocking
pidfds.

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.

Suggested-by: Josh Triplett <[email protected]>
Signed-off-by: Christian Brauner <[email protected]>
Reviewed-by: Josh Triplett <[email protected]>
Reviewed-by: Oleg Nesterov <[email protected]>
Cc: Kees Cook <[email protected]>
Cc: Sargun Dhillon <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Link: https://lore.kernel.org/lkml/20200811181236.GA18763@localhost/
Link: https://github.com/joshtriplett/async-pidfd
Link: https://lore.kernel.org/r/[email protected]

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 */

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;