diff options
| author | Jens Axboe | 2018-11-26 08:24:43 -0700 |
|---|---|---|
| committer | Jens Axboe | 2018-11-26 08:25:53 -0700 |
| commit | 0a1b8b87d064a47fad9ec475316002da28559207 (patch) | |
| tree | 9bc87a52b3fcc1f476d52ae94d6bb7e69e2bfd94 /fs/direct-io.c | |
| parent | e7d943910719b44738e86f91a26a64e3b61ae419 (diff) | |
block: make blk_poll() take a parameter on whether to spin or not
blk_poll() has always kept spinning until it found an IO. This is
fine for SYNC polling, since we need to find one request we have
pending, but in preparation for ASYNC polling it can be beneficial
to just check if we have any entries available or not.
Existing callers are converted to pass in 'spin == true', to retain
the old behavior.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'fs/direct-io.c')
| -rw-r--r-- | fs/direct-io.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/direct-io.c b/fs/direct-io.c index ea07d5a34317..a5a4e5a1423e 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -518,7 +518,7 @@ static struct bio *dio_await_one(struct dio *dio) dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); if (!(dio->iocb->ki_flags & IOCB_HIPRI) || - !blk_poll(dio->bio_disk->queue, dio->bio_cookie)) + !blk_poll(dio->bio_disk->queue, dio->bio_cookie, true)) io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); |