blk-mq: split out a __blk_mq_get_driver_tag helper

Allocation of the driver tag in the case of using a scheduler shares very
little code with the "normal" tag allocation.  Split out a new helper to
streamline this path, and untangle it from the complex normal tag
allocation.

This way also avoids to fail driver tag allocation because of inactive hctx
during cpu hotplug, and fixes potential hang risk.

Fixes: bf0beec0 ("blk-mq: drain I/O when all CPUs in a hctx are offline")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: John Garry <john.garry@huawei.com>
Cc: Dongli Zhang <dongli.zhang@oracle.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-mq-tag.c

@@ -191,6 +191,33 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 	return tag + tag_offset;
 }
 
+bool __blk_mq_get_driver_tag(struct request *rq)
+{
+	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
+	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
+	bool shared = blk_mq_tag_busy(rq->mq_hctx);
+	int tag;
+
+	if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) {
+		bt = &rq->mq_hctx->tags->breserved_tags;
+		tag_offset = 0;
+	}
+
+	if (!hctx_may_queue(rq->mq_hctx, bt))
+		return false;
+	tag = __sbitmap_queue_get(bt);
+	if (tag == BLK_MQ_NO_TAG)
+		return false;
+
+	rq->tag = tag + tag_offset;
+	if (shared) {
+		rq->rq_flags |= RQF_MQ_INFLIGHT;
+		atomic_inc(&rq->mq_hctx->nr_active);
+	}
+	rq->mq_hctx->tags->rqs[rq->tag] = rq;
+	return true;
+}
+
 void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx,
 		    unsigned int tag)
 {

block/blk-mq-tag.h

@@ -51,6 +51,14 @@ enum {
 	BLK_MQ_TAG_MAX		= BLK_MQ_NO_TAG - 1,
 };
 
+bool __blk_mq_get_driver_tag(struct request *rq);
+static inline bool blk_mq_get_driver_tag(struct request *rq)
+{
+	if (rq->tag != BLK_MQ_NO_TAG)
+		return true;
+	return __blk_mq_get_driver_tag(rq);
+}
+
 extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *);
 extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *);
 

block/blk-mq.c

@@ -1052,35 +1052,6 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
-bool blk_mq_get_driver_tag(struct request *rq)
-{
-	struct blk_mq_alloc_data data = {
-		.q = rq->q,
-		.hctx = rq->mq_hctx,
-		.flags = BLK_MQ_REQ_NOWAIT,
-		.cmd_flags = rq->cmd_flags,
-	};
-	bool shared;
-
-	if (rq->tag != BLK_MQ_NO_TAG)
-		return true;
-
-	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
-		data.flags |= BLK_MQ_REQ_RESERVED;
-
-	shared = blk_mq_tag_busy(data.hctx);
-	rq->tag = blk_mq_get_tag(&data);
-	if (rq->tag >= 0) {
-		if (shared) {
-			rq->rq_flags |= RQF_MQ_INFLIGHT;
-			atomic_inc(&data.hctx->nr_active);
-		}
-		data.hctx->tags->rqs[rq->tag] = rq;
-	}
-
-	return rq->tag != BLK_MQ_NO_TAG;
-}
-
 static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 				int flags, void *key)
 {

block/blk-mq.h

@@ -44,7 +44,6 @@ bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
 void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
 				bool kick_requeue_list);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
-bool blk_mq_get_driver_tag(struct request *rq);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);