fs/pipe: use spinlock in pipe_read() only if there is a watch_queue

Browse source

If there is no watch_queue, holding the pipe mutex is enough to
prevent concurrent writes, and we can avoid the spinlock.

O_NOTIFICATION_QUEUE is an exotic and rarely used feature, and of all
the pipes that exist at any given time, only very few actually have a
watch_queue, therefore it appears worthwile to optimize the common
case.

This patch does not optimize pipe_resize_ring() where the spinlocks
could be avoided as well; that does not seem like a worthwile
optimization because this function is not called often.

Related commits:

- commit 8df441294d ("pipe: Check for ring full inside of the
  spinlock in pipe_write()")
- commit b667b86734 ("pipe: Advance tail pointer inside of wait
  spinlock in pipe_read()")
- commit 189b0ddc24 ("pipe: Fix missing lock in pipe_resize_ring()")

Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
Message-Id: <20230921075755.1378787-4-max.kellermann@ionos.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

...

This commit is contained in:

Max Kellermann 2023-09-21 09:57:55 +02:00 • committed by Christian Brauner

parent dfaabf916b

commit 478dbf1217

No known key found for this signature in database

GPG key ID: 91C61BC06578DCA2

1 changed files with 32 additions and 11 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

43

fs/pipe.c

View file