diff options
| author | Stefano Garzarella <sgarzare@redhat.com> | 2020-02-21 16:42:16 +0100 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2020-02-21 17:16:10 +0100 |
| commit | 7143b5ac5750f404ff3a594b34fdf3fc2f99f828 (patch) | |
| tree | d6bf0edaaf6f0f994d2043d91a91644b2e6ca461 /fs/io_uring.c | |
| parent | io_uring: fix use-after-free by io_cleanup_req() (diff) | |
| download | linux-7143b5ac5750f404ff3a594b34fdf3fc2f99f828.tar.xz linux-7143b5ac5750f404ff3a594b34fdf3fc2f99f828.zip | |
io_uring: prevent sq_thread from spinning when it should stop
This patch drops 'cur_mm' before calling cond_resched(), to prevent
the sq_thread from spinning even when the user process is finished.
Before this patch, if the user process ended without closing the
io_uring fd, the sq_thread continues to spin until the
'sq_thread_idle' timeout ends.
In the worst case where the 'sq_thread_idle' parameter is bigger than
INT_MAX, the sq_thread will spin forever.
Fixes: 6c271ce2f1d5 ("io_uring: add submission polling")
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to '')
| -rw-r--r-- | fs/io_uring.c | 24 |
1 files changed, 12 insertions, 12 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c index 6e249aa97ba3..b43467b3a8dc 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5143,6 +5143,18 @@ static int io_sq_thread(void *data) */ if (!to_submit || ret == -EBUSY) { /* + * Drop cur_mm before scheduling, we can't hold it for + * long periods (or over schedule()). Do this before + * adding ourselves to the waitqueue, as the unuse/drop + * may sleep. + */ + if (cur_mm) { + unuse_mm(cur_mm); + mmput(cur_mm); + cur_mm = NULL; + } + + /* * We're polling. If we're within the defined idle * period, then let us spin without work before going * to sleep. The exception is if we got EBUSY doing @@ -5156,18 +5168,6 @@ static int io_sq_thread(void *data) continue; } - /* - * Drop cur_mm before scheduling, we can't hold it for - * long periods (or over schedule()). Do this before - * adding ourselves to the waitqueue, as the unuse/drop - * may sleep. - */ - if (cur_mm) { - unuse_mm(cur_mm); - mmput(cur_mm); - cur_mm = NULL; - } - prepare_to_wait(&ctx->sqo_wait, &wait, TASK_INTERRUPTIBLE); |