[PATCH 03/14] blk-mq: introduce blk_mq_dispatch_rq_from_ctxs()

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

This function is introduced for picking up request
from sw queue so that we can dispatch in scheduler's way.

More importantly, for some SCSI devices, driver
tags are host wide, and the number is quite big,
but each lun has very limited queue depth. This
function is introduced for avoiding to take too
many requests from sw queue when queue is busy,
and only try to dispatch request when queue
isn't busy.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq.c | 38 +++++++++++++++++++++++++++++++++++++-
 block/blk-mq.h |  1 +
 2 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 94818f78c099..86b8fdcb8434 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -810,7 +810,11 @@ static void blk_mq_timeout_work(struct work_struct *work)
 
 struct ctx_iter_data {
 	struct blk_mq_hw_ctx *hctx;
-	struct list_head *list;
+
+	union {
+		struct list_head *list;
+		struct request *rq;
+	};
 };
 
 static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
@@ -826,6 +830,26 @@ static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
 	return true;
 }
 
+static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
+{
+	struct ctx_iter_data *dispatch_data = data;
+	struct blk_mq_hw_ctx *hctx = dispatch_data->hctx;
+	struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
+	bool empty = true;
+
+	spin_lock(&ctx->lock);
+	if (unlikely(!list_empty(&ctx->rq_list))) {
+		dispatch_data->rq = list_entry_rq(ctx->rq_list.next);
+		list_del_init(&dispatch_data->rq->queuelist);
+		empty = list_empty(&ctx->rq_list);
+	}
+	spin_unlock(&ctx->lock);
+	if (empty)
+		sbitmap_clear_bit(sb, bitnr);
+
+	return !dispatch_data->rq;
+}
+
 /*
  * Process software queues that have been marked busy, splicing them
  * to the for-dispatch
@@ -841,6 +865,18 @@ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 }
 EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);
 
+struct request *blk_mq_dispatch_rq_from_ctxs(struct blk_mq_hw_ctx *hctx)
+{
+	struct ctx_iter_data data = {
+		.hctx = hctx,
+		.rq   = NULL,
+	};
+
+	sbitmap_for_each_set(&hctx->ctx_map, dispatch_rq_from_ctx, &data);
+
+	return data.rq;
+}
+
 static inline unsigned int queued_to_index(unsigned int queued)
 {
 	if (!queued)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 60b01c0309bc..0c398f29dc4b 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -35,6 +35,7 @@ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
 bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 				bool wait);
+struct request *blk_mq_dispatch_rq_from_ctxs(struct blk_mq_hw_ctx *hctx);
 
 /*
  * Internal helpers for allocating/freeing the request map
-- 
2.9.4