diff options
| author | Oleg Nesterov <oleg@redhat.com> | 2025-01-07 17:27:17 +0100 |
|---|---|---|
| committer | Christian Brauner <brauner@kernel.org> | 2025-01-10 11:58:59 +0100 |
| commit | cacd9ae4bf801ff4125d8961bb9a3ba955e51680 (patch) | |
| tree | 7c931c54895633e30d9ea7c3e8725d0a16bd57fc /include | |
| parent | Linux 6.13-rc1 (diff) | |
| download | linux-cacd9ae4bf801ff4125d8961bb9a3ba955e51680.tar.xz linux-cacd9ae4bf801ff4125d8961bb9a3ba955e51680.zip | |
poll_wait: add mb() to fix theoretical race between waitqueue_active() and .poll()
As the comment above waitqueue_active() explains, it can only be used
if both waker and waiter have mb()'s that pair with each other. However
__pollwait() is broken in this respect.
This is not pipe-specific, but let's look at pipe_poll() for example:
poll_wait(...); // -> __pollwait() -> add_wait_queue()
LOAD(pipe->head);
LOAD(pipe->head);
In theory these LOAD()'s can leak into the critical section inside
add_wait_queue() and can happen before list_add(entry, wq_head), in this
case pipe_poll() can race with wakeup_pipe_readers/writers which do
smp_mb();
if (waitqueue_active(wq_head))
wake_up_interruptible(wq_head);
There are more __pollwait()-like functions (grep init_poll_funcptr), and
it seems that at least ep_ptable_queue_proc() has the same problem, so the
patch adds smp_mb() into poll_wait().
Link: https://lore.kernel.org/all/20250102163320.GA17691@redhat.com/
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lore.kernel.org/r/20250107162717.GA18922@redhat.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/poll.h | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/include/linux/poll.h b/include/linux/poll.h index d1ea4f3714a8..fc641b50f129 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -41,8 +41,16 @@ typedef struct poll_table_struct { static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { - if (p && p->_qproc && wait_address) + if (p && p->_qproc && wait_address) { p->_qproc(filp, wait_address, p); + /* + * This memory barrier is paired in the wq_has_sleeper(). + * See the comment above prepare_to_wait(), we need to + * ensure that subsequent tests in this thread can't be + * reordered with __add_wait_queue() in _qproc() paths. + */ + smp_mb(); + } } /* |