[PATCH V2 09/20] blk-mq: introduce BLK_MQ_F_SHARED_DEPTH

[Ming Lei <ming.lei@redhat.com>]

SCSI devices often provides one per-request_queue depth via
q->queue_depth(.cmd_per_lun), which is a global limit on all
hw queues. After the pending I/O submitted to one rquest queue
reaches this limit, BLK_STS_RESOURCE will be returned to all
dispatch path. That means when one hw queue is stuck, actually
all hctxs are stuck too.

This flag is introduced for improving blk-mq IO scheduling
on this kind of device.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq-debugfs.c |  1 +
 block/blk-mq-sched.c   |  2 +-
 block/blk-mq.c         | 25 ++++++++++++++++++++++---
 include/linux/blk-mq.h |  1 +
 4 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 7932782c4614..febcaa7bfc82 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -210,6 +210,7 @@ static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(SG_MERGE),
 	HCTX_FLAG_NAME(BLOCKING),
 	HCTX_FLAG_NAME(NO_SCHED),
+	HCTX_FLAG_NAME(SHARED_DEPTH),
 };
 #undef HCTX_FLAG_NAME
 
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 2eda942357c3..18d997679d7d 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -201,7 +201,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 		 * is busy, which can be triggeredd easily by
 		 * limit of of request_queue's queue depth
 		 */
-		if (!q->queue_depth) {
+		if (!(hctx->flags & BLK_MQ_F_SHARED_DEPTH)) {
 			blk_mq_flush_busy_ctxs(hctx, &rq_list);
 			blk_mq_dispatch_rq_list(q, &rq_list);
 		} else {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index da2fa175d78f..b535587570b8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2656,12 +2656,31 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 int blk_mq_update_sched_queue_depth(struct request_queue *q)
 {
 	unsigned nr;
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+	int ret = 0;
 
-	if (!q->mq_ops || !q->elevator)
-		return 0;
+	if (!q->mq_ops)
+		return ret;
+
+	blk_mq_freeze_queue(q);
+	/*
+	 * if there is q->queue_depth, all hw queues share
+	 * this queue depth limit
+	 */
+	if (q->queue_depth) {
+		queue_for_each_hw_ctx(q, hctx, i)
+			hctx->flags |= BLK_MQ_F_SHARED_DEPTH;
+	}
+
+	if (!q->elevator)
+		goto exit;
 
 	nr = blk_mq_sched_queue_depth(q);
-	return __blk_mq_update_nr_requests(q, true, nr);
+	ret = __blk_mq_update_nr_requests(q, true, nr);
+ exit:
+	blk_mq_unfreeze_queue(q);
+	return ret;
 }
 
 static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index cae063482b82..1197e5dee015 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -164,6 +164,7 @@ enum {
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
 	BLK_MQ_F_NO_SCHED	= 1 << 6,
+	BLK_MQ_F_SHARED_DEPTH	= 1 << 7,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
 	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
 
-- 
2.9.4