blk-mq: Record active_queues_shared_sbitmap per tag_set for when using shared sbitmap

For when using a shared sbitmap, no longer should the number of active
request queues per hctx be relied on for when judging how to share the tag
bitmap.

Instead maintain the number of active request queues per tag_set, and make
the judgement based on that.

Originally-from: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

5 files changed, 42 insertions, 11 deletions

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c6d7ebc62bdb..c31c4a0478a5 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -23,9 +23,18 @@
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
-	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
-	    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		atomic_inc(&hctx->tags->active_queues);
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+		struct blk_mq_tag_set *set = q->tag_set;
+
+		if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) &&
+		    !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
+			atomic_inc(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) &&
+		    !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			atomic_inc(&hctx->tags->active_queues);
+	}
 
 	return true;
 }
@@ -47,11 +56,19 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve)
 void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)
 {
 	struct blk_mq_tags *tags = hctx->tags;
-
-	if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		return;
-
-	atomic_dec(&tags->active_queues);
+	struct request_queue *q = hctx->queue;
+	struct blk_mq_tag_set *set = q->tag_set;
+
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE,
+					&q->queue_flags))
+			return;
+		atomic_dec(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			return;
+		atomic_dec(&tags->active_queues);
+	}
 
 	blk_mq_tag_wakeup_all(tags, false);
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ffc5ad0c91b7..eff9d987f85b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3442,6 +3442,8 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 		goto out_free_mq_map;
 
 	if (blk_mq_is_sbitmap_shared(set->flags)) {
+		atomic_set(&set->active_queues_shared_sbitmap, 0);
+
 		if (blk_mq_init_shared_sbitmap(set, set->flags)) {
 			ret = -ENOMEM;
 			goto out_free_mq_rq_maps;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 25ec73078e95..a52703c98b77 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -292,8 +292,6 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 
 	if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED))
 		return true;
-	if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
-		return true;
 
 	/*
 	 * Don't try dividing an ant
@@ -301,7 +299,19 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	if (bt->sb.depth == 1)
 		return true;
 
-	users = atomic_read(&hctx->tags->active_queues);
+	if (blk_mq_is_sbitmap_shared(hctx->flags)) {
+		struct request_queue *q = hctx->queue;
+		struct blk_mq_tag_set *set = q->tag_set;
+
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &q->queue_flags))
+			return true;
+		users = atomic_read(&set->active_queues_shared_sbitmap);
+	} else {
+		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state))
+			return true;
+		users = atomic_read(&hctx->tags->active_queues);
+	}
+
 	if (!users)
 		return true;
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index df7b903ce7ae..8279c807e1f3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -252,6 +252,7 @@ struct blk_mq_tag_set {
 	unsigned int		timeout;
 	unsigned int		flags;
 	void			*driver_data;
+	atomic_t		active_queues_shared_sbitmap;
 
 	struct sbitmap_queue	__bitmap_tags;
 	struct sbitmap_queue	__breserved_tags;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6277aee2aeaa..7d82959e7b86 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -618,6 +618,7 @@ struct request_queue {
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
 #define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
+#define QUEUE_FLAG_HCTX_ACTIVE 28	/* at least one blk-mq hctx is active */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP))