[RFC PATCH v2 1/7] block: Extand commit_rqs() to do batch processing

[Baolin Wang <baolin.wang7@gmail.com>]

From: Ming Lei <ming.lei@redhat.com>

Now some SD/MMC host controllers can support packed command or packed request,
that means we can package several requests to host controller at one time
to improve performence.

But the blk-mq always takes one request from the scheduler and dispatch it to
the device, regardless of the driver or the scheduler, so there should only
ever be one request in the local list in blk_mq_dispatch_rq_list(), that means
the bd.last is always true and the driver can not use bd.last to decide if
there are requests are pending now in hardware queue to help to package
requests.

Thus this patch introduces a new 'BLK_MQ_F_FORCE_COMMIT_RQS' flag to call
.commit_rqs() to do batch processing if necessary.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Baolin Wang <baolin.wang7@gmail.com>
Signed-off-by: Baolin Wang <baolin.wang7@gmail.com>
---
 block/blk-mq-sched.c   | 29 ++++++++++++++++++++---------
 block/blk-mq.c         | 15 ++++++++++-----
 include/linux/blk-mq.h |  1 +
 3 files changed, 31 insertions(+), 14 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 74cedea56034..3429a71a7364 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -85,11 +85,12 @@ void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
  * its queue by itself in its completion handler, so we don't need to
  * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
  */
-static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
 	struct elevator_queue *e = q->elevator;
 	LIST_HEAD(rq_list);
+	bool ret = false;
 
 	do {
 		struct request *rq;
@@ -112,7 +113,10 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 		 * in blk_mq_dispatch_rq_list().
 		 */
 		list_add(&rq->queuelist, &rq_list);
-	} while (blk_mq_dispatch_rq_list(q, &rq_list, true));
+		ret = blk_mq_dispatch_rq_list(q, &rq_list, true);
+	} while (ret);
+
+	return ret;
 }
 
 static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
@@ -131,11 +135,12 @@ static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
  * its queue by itself in its completion handler, so we don't need to
  * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE.
  */
-static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
 	LIST_HEAD(rq_list);
 	struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from);
+	bool ret = false;
 
 	do {
 		struct request *rq;
@@ -161,10 +166,11 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)
 
 		/* round robin for fair dispatch */
 		ctx = blk_mq_next_ctx(hctx, rq->mq_ctx);
-
-	} while (blk_mq_dispatch_rq_list(q, &rq_list, true));
+		ret = blk_mq_dispatch_rq_list(q, &rq_list, true);
+	} while (ret);
 
 	WRITE_ONCE(hctx->dispatch_from, ctx);
+	return ret;
 }
 
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
@@ -173,6 +179,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	struct elevator_queue *e = q->elevator;
 	const bool has_sched_dispatch = e && e->type->ops.dispatch_request;
 	LIST_HEAD(rq_list);
+	bool dispatch_ret;
 
 	/* RCU or SRCU read lock is needed before checking quiesced flag */
 	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
@@ -206,21 +213,25 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 */
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
-		if (blk_mq_dispatch_rq_list(q, &rq_list, false)) {
+		dispatch_ret = blk_mq_dispatch_rq_list(q, &rq_list, false);
+		if (dispatch_ret) {
 			if (has_sched_dispatch)
 				blk_mq_do_dispatch_sched(hctx);
 			else
 				blk_mq_do_dispatch_ctx(hctx);
 		}
 	} else if (has_sched_dispatch) {
-		blk_mq_do_dispatch_sched(hctx);
+		dispatch_ret = blk_mq_do_dispatch_sched(hctx);
 	} else if (hctx->dispatch_busy) {
 		/* dequeue request one by one from sw queue if queue is busy */
-		blk_mq_do_dispatch_ctx(hctx);
+		dispatch_ret = blk_mq_do_dispatch_ctx(hctx);
 	} else {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
-		blk_mq_dispatch_rq_list(q, &rq_list, false);
+		dispatch_ret = blk_mq_dispatch_rq_list(q, &rq_list, false);
 	}
+
+	if (dispatch_ret && (hctx->flags & BLK_MQ_F_FORCE_COMMIT_RQS))
+		hctx->queue->mq_ops->commit_rqs(hctx);
 }
 
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 8e56884fd2e9..bde122feef01 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1253,11 +1253,16 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		 * Flag last if we have no more requests, or if we have more
 		 * but can't assign a driver tag to it.
 		 */
-		if (list_empty(list))
-			bd.last = true;
-		else {
-			nxt = list_first_entry(list, struct request, queuelist);
-			bd.last = !blk_mq_get_driver_tag(nxt);
+		if (!(hctx->flags & BLK_MQ_F_FORCE_COMMIT_RQS)) {
+			if (list_empty(list)) {
+				bd.last = true;
+			} else {
+				nxt = list_first_entry(list, struct request,
+						       queuelist);
+				bd.last = !blk_mq_get_driver_tag(nxt);
+			}
+		} else {
+			bd.last = false;
 		}
 
 		ret = q->mq_ops->queue_rq(hctx, &bd);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index f389d7c724bd..6a20f8e8eb85 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -391,6 +391,7 @@ struct blk_mq_ops {
 enum {
 	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
 	BLK_MQ_F_TAG_SHARED	= 1 << 1,
+	BLK_MQ_F_FORCE_COMMIT_RQS = 1 << 3,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
 	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
-- 
2.17.1