blk-mq: allow blk_mq_make_request to consume the q_usage_counter reference

blk_mq_make_request currently needs to grab an q_usage_counter
reference when allocating a request.  This is because the block layer
grabs one before calling blk_mq_make_request, but also releases it as
soon as blk_mq_make_request returns.  Remove the blk_queue_exit call
after blk_mq_make_request returns, and instead let it consume the
reference.  This works perfectly fine for the block layer caller, just
device mapper needs an extra reference as the old problem still
persists there.  Open code blk_queue_enter_live in device mapper,
as there should be no other callers and this allows better documenting
why we do a non-try get.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-core.c

@@ -1066,6 +1066,20 @@ generic_make_request_checks(struct bio *bio)
 	return false;
 }
 
+static blk_qc_t do_make_request(struct bio *bio)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+	blk_qc_t ret = BLK_QC_T_NONE;
+
+	if (blk_crypto_bio_prep(&bio)) {
+		if (!q->make_request_fn)
+			return blk_mq_make_request(q, bio);
+		ret = q->make_request_fn(q, bio);
+	}
+	blk_queue_exit(q);
+	return ret;
+}
+
 /**
  * generic_make_request - re-submit a bio to the block device layer for I/O
  * @bio:  The bio describing the location in memory and on the device.
@@ -1131,14 +1145,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 			/* Create a fresh bio_list for all subordinate requests */
 			bio_list_on_stack[1] = bio_list_on_stack[0];
 			bio_list_init(&bio_list_on_stack[0]);
-			if (blk_crypto_bio_prep(&bio)) {
-				if (q->make_request_fn)
-					ret = q->make_request_fn(q, bio);
-				else
-					ret = blk_mq_make_request(q, bio);
-			}
-
-			blk_queue_exit(q);
+			ret = do_make_request(bio);
 
 			/* sort new bios into those for a lower level
 			 * and those for the same level
@@ -1175,7 +1182,6 @@ EXPORT_SYMBOL(generic_make_request);
 blk_qc_t direct_make_request(struct bio *bio)
 {
 	struct request_queue *q = bio->bi_disk->queue;
-	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (WARN_ON_ONCE(q->make_request_fn)) {
 		bio_io_error(bio);
@@ -1185,10 +1191,11 @@ blk_qc_t direct_make_request(struct bio *bio)
 		return BLK_QC_T_NONE;
 	if (unlikely(bio_queue_enter(bio)))
 		return BLK_QC_T_NONE;
-	if (blk_crypto_bio_prep(&bio))
-		ret = blk_mq_make_request(q, bio);
-	blk_queue_exit(q);
-	return ret;
+	if (!blk_crypto_bio_prep(&bio)) {
+		blk_queue_exit(q);
+		return BLK_QC_T_NONE;
+	}
+	return blk_mq_make_request(q, bio);
 }
 EXPORT_SYMBOL_GPL(direct_make_request);
 

block/blk-mq.c

@@ -2028,26 +2028,24 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	__blk_queue_split(q, &bio, &nr_segs);
 
 	if (!bio_integrity_prep(bio))
-		return BLK_QC_T_NONE;
+		goto queue_exit;
 
 	if (!is_flush_fua && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq))
-		return BLK_QC_T_NONE;
+		goto queue_exit;
 
 	if (blk_mq_sched_bio_merge(q, bio, nr_segs))
-		return BLK_QC_T_NONE;
+		goto queue_exit;
 
 	rq_qos_throttle(q, bio);
 
 	data.cmd_flags = bio->bi_opf;
-	blk_queue_enter_live(q);
 	rq = blk_mq_get_request(q, bio, &data);
 	if (unlikely(!rq)) {
-		blk_queue_exit(q);
 		rq_qos_cleanup(q, bio);
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
-		return BLK_QC_T_NONE;
+		goto queue_exit;
 	}
 
 	trace_block_getrq(q, bio, bio->bi_opf);
@@ -2134,6 +2132,9 @@ blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	}
 
 	return cookie;
+queue_exit:
+	blk_queue_exit(q);
+	return BLK_QC_T_NONE;
 }
 EXPORT_SYMBOL_GPL(blk_mq_make_request); /* only for request based dm */
 

block/blk.h

@@ -64,17 +64,6 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
 
 void blk_freeze_queue(struct request_queue *q);
 
-static inline void blk_queue_enter_live(struct request_queue *q)
-{
-	/*
-	 * Given that running in generic_make_request() context
-	 * guarantees that a live reference against q_usage_counter has
-	 * been established, further references under that same context
-	 * need not check that the queue has been frozen (marked dead).
-	 */
-	percpu_ref_get(&q->q_usage_counter);
-}
-
 static inline bool biovec_phys_mergeable(struct request_queue *q,
 		struct bio_vec *vec1, struct bio_vec *vec2)
 {

drivers/md/dm.c

@@ -1791,8 +1791,17 @@ static blk_qc_t dm_make_request(struct request_queue *q, struct bio *bio)
 	int srcu_idx;
 	struct dm_table *map;
 
-	if (dm_get_md_type(md) == DM_TYPE_REQUEST_BASED)
+	if (dm_get_md_type(md) == DM_TYPE_REQUEST_BASED) {
+		/*
+		 * We are called with a live reference on q_usage_counter, but
+		 * that one will be released as soon as we return.  Grab an
+		 * extra one as blk_mq_make_request expects to be able to
+		 * consume a reference (which lives until the request is freed
+		 * in case a request is allocated).
+		 */
+		percpu_ref_get(&q->q_usage_counter);
 		return blk_mq_make_request(q, bio);
+	}
 
 	map = dm_get_live_table(md, &srcu_idx);