[PATCH] blk-mq: fix sbitmap ws_active for shared tags

[Jens Axboe <axboe@kernel.dk>]

We now wrap sbitmap waitqueues in an active counter, so we can avoid
iterating wakeups unless we have waiters there. This works as long as
everyone that's manipulating the waitqueues use the proper helpers. For
the tag wait case for shared tags, however, we add ourselves to the
waitqueue without incrementing/decrementing the ->ws_active count. This
means that wakeups can take a long time to happen.

Fix this by manually doing the inc/dec as needed for the wait queue
handling.

Fixes: 5d2ee7122c73 ("sbitmap: optimize wakeup check")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

---

Got a bug report on raid5 on 4 USB-3 attached drives which is slow with
5.0, but works fine with the ->ws_active check bypassed. Waiting for
confirmation that this patch fixes it, but I think it will.

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 28080b0235f0..3ff3d7b49969 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1072,7 +1072,13 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
 
 	spin_lock(&hctx->dispatch_wait_lock);
-	list_del_init(&wait->entry);
+	if (!list_empty(&wait->entry)) {
+		struct sbitmap_queue *sbq;
+
+		list_del_init(&wait->entry);
+		sbq = &hctx->tags->bitmap_tags;
+		atomic_dec(&sbq->ws_active);
+	}
 	spin_unlock(&hctx->dispatch_wait_lock);
 
 	blk_mq_run_hw_queue(hctx, true);
@@ -1088,6 +1094,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
+	struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags;
 	struct wait_queue_head *wq;
 	wait_queue_entry_t *wait;
 	bool ret;
@@ -1110,7 +1117,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	if (!list_empty_careful(&wait->entry))
 		return false;
 
-	wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait;
+	wq = &bt_wait_ptr(sbq, hctx)->wait;
 
 	spin_lock_irq(&wq->lock);
 	spin_lock(&hctx->dispatch_wait_lock);
@@ -1120,6 +1127,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 		return false;
 	}
 
+	atomic_inc(&sbq->ws_active);
 	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
 	__add_wait_queue(wq, wait);
 
@@ -1140,6 +1148,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	 * someone else gets the wakeup.
 	 */
 	list_del_init(&wait->entry);
+	atomic_dec(&sbq->ws_active);
 	spin_unlock(&hctx->dispatch_wait_lock);
 	spin_unlock_irq(&wq->lock);
 

-- 
Jens Axboe