diff options
| author |   Christian Brauner <brauner@kernel.org> | 2025-03-04 09:46:14 +0100 |
|---|---|---|
| committer | Christian Brauner <brauner@kernel.org> | 2025-03-04 09:46:14 +0100 |
| commit | 3d5b9f3702f16e683047d0647117a5a297d1e284 (patch) | |
| tree | bf96414d0dd23cbd85a3f69cf7a3ec4da747005c /fs/pidfs.c | |
| parent | pipe: change pipe_write() to never add a zero-sized buffer (diff) | |
| parent | wait: avoid spurious calls to prepare_to_wait_event() in ___wait_event() (diff) | |
| download | wireguard-linux-3d5b9f3702f16e683047d0647117a5a297d1e284.tar.xz wireguard-linux-3d5b9f3702f16e683047d0647117a5a297d1e284.zip | |
Merge patch series "some pipe + wait stuff"
Mateusz Guzik <mjguzik@gmail.com> says:
As a side effect of looking at the pipe hang I came up with 3 changes to
consider for -next.
The first one is a trivial clean up which I wont mind if it merely gets
folded into someone else's change for pipes.
The second one reduces page alloc/free calls for the backing area (60%
less during a kernel build in my testing). I already posted this, but
the cc list was not proper.
The last one concerns the wait/wakeup mechanism and drops one lock trip
in the common case after waking up.
* patches from https://lore.kernel.org/r/20250303230409.452687-1-mjguzik@gmail.com:
wait: avoid spurious calls to prepare_to_wait_event() in ___wait_event()
pipe: cache 2 pages instead of 1
pipe: drop an always true check in anon_pipe_write()
Link: https://lore.kernel.org/r/20250303230409.452687-1-mjguzik@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to 'fs/pidfs.c')
0 files changed, 0 insertions, 0 deletions