blk-mq: fix tag_get wait task can't be awakened

In case of shared tags, there might be more than one hctx which
allocates from the same tags, and each hctx is limited to allocate at
most:
        hctx_max_depth = max((bt->sb.depth + users - 1) / users, 4U);

tag idle detection is lazy, and may be delayed for 30sec, so there
could be just one real active hctx(queue) but all others are actually
idle and still accounted as active because of the lazy idle detection.
Then if wake_batch is > hctx_max_depth, driver tag allocation may wait
forever on this real active hctx.

Fix this by recalculating wake_batch when inc or dec active_queues.

Fixes: 0d2602ca30e41 ("blk-mq: improve support for shared tags maps")
Suggested-by: Ming Lei <[email protected]>
Suggested-by: John Garry <[email protected]>
Signed-off-by: Laibin Qiu <[email protected]>
Reviewed-by: Andy Shevchenko <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jens Axboe <[email protected]>
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 2709ab8..6220fa6 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -457,10 +457,9 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);
 
-static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
-					    unsigned int depth)
+static inline void __sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
+					    unsigned int wake_batch)
 {
-	unsigned int wake_batch = sbq_calc_wake_batch(sbq, depth);
 	int i;
 
 	if (sbq->wake_batch != wake_batch) {
@@ -476,6 +475,26 @@ static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
 	}
 }
 
+static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq,
+					    unsigned int depth)
+{
+	unsigned int wake_batch;
+
+	wake_batch = sbq_calc_wake_batch(sbq, depth);
+	__sbitmap_queue_update_wake_batch(sbq, wake_batch);
+}
+
+void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq,
+					    unsigned int users)
+{
+	unsigned int wake_batch;
+
+	wake_batch = clamp_val((sbq->sb.depth + users - 1) /
+			users, 4, SBQ_WAKE_BATCH);
+	__sbitmap_queue_update_wake_batch(sbq, wake_batch);
+}
+EXPORT_SYMBOL_GPL(sbitmap_queue_recalculate_wake_batch);
+
 void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
 {
 	sbitmap_queue_update_wake_batch(sbq, depth);