summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2022-09-08 15:09:37 +0200
committerJens Axboe <axboe@kernel.dk>2022-09-08 08:39:04 -0600
commit48c033314f372478548203c583529f53080fd078 (patch)
tree75c41982aac9bd59c1964c1fd1c9da8cd29afdc2
parent8807707df7ef09d679df2b21894d49a06fd8ba7e (diff)
sbitmap: Avoid leaving waitqueue in invalid state in __sbq_wake_up()
When __sbq_wake_up() decrements wait_cnt to 0 but races with someone else waking the waiter on the waitqueue (so the waitqueue becomes empty), it exits without reseting wait_cnt to wake_batch number. Once wait_cnt is 0, nobody will ever reset the wait_cnt or wake the new waiters resulting in possible deadlocks or busyloops. Fix the problem by making sure we reset wait_cnt even if we didn't wake up anybody in the end. Fixes: 040b83fcecfb ("sbitmap: fix possible io hung due to lost wakeup") Reported-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Jan Kara <jack@suse.cz> Link: https://lore.kernel.org/r/20220908130937.2795-1-jack@suse.cz Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--lib/sbitmap.c18
1 files changed, 15 insertions, 3 deletions
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index a39b1a877366..47cd8fb894ba 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -604,6 +604,7 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq)
struct sbq_wait_state *ws;
unsigned int wake_batch;
int wait_cnt;
+ bool ret;
ws = sbq_wake_ptr(sbq);
if (!ws)
@@ -614,12 +615,23 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq)
* For concurrent callers of this, callers should call this function
* again to wakeup a new batch on a different 'ws'.
*/
- if (wait_cnt < 0 || !waitqueue_active(&ws->wait))
+ if (wait_cnt < 0)
return true;
+ /*
+ * If we decremented queue without waiters, retry to avoid lost
+ * wakeups.
+ */
if (wait_cnt > 0)
- return false;
+ return !waitqueue_active(&ws->wait);
+ /*
+ * When wait_cnt == 0, we have to be particularly careful as we are
+ * responsible to reset wait_cnt regardless whether we've actually
+ * woken up anybody. But in case we didn't wakeup anybody, we still
+ * need to retry.
+ */
+ ret = !waitqueue_active(&ws->wait);
wake_batch = READ_ONCE(sbq->wake_batch);
/*
@@ -648,7 +660,7 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq)
sbq_index_atomic_inc(&sbq->wake_index);
atomic_set(&ws->wait_cnt, wake_batch);
- return false;
+ return ret;
}
void sbitmap_queue_wake_up(struct sbitmap_queue *sbq)