blk-mq: only apply active queue tag throttling for driver tags

If we have a scheduler attached, we have two sets of tags. We don't
want to apply our active queue throttling for the scheduler side
of tags, that only applies to driver tags since that's the resource
we need to dispatch an IO.

Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index a49ec77..1b156ca 100644 (file)
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -90,9 +90,11 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
        return atomic_read(&hctx->nr_active) < depth;
 }
 
-static int __blk_mq_get_tag(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt)
+static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
+                           struct sbitmap_queue *bt)
 {
-       if (!hctx_may_queue(hctx, bt))
+       if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
+           !hctx_may_queue(data->hctx, bt))
                return -1;
        return __sbitmap_queue_get(bt);
 }
@@ -118,7 +120,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
                tag_offset = tags->nr_reserved_tags;
        }
 
-       tag = __blk_mq_get_tag(data->hctx, bt);
+       tag = __blk_mq_get_tag(data, bt);
        if (tag != -1)
                goto found_tag;
 
@@ -129,7 +131,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
        do {
                prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-               tag = __blk_mq_get_tag(data->hctx, bt);
+               tag = __blk_mq_get_tag(data, bt);
                if (tag != -1)
                        break;
 
@@ -144,7 +146,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
                 * Retry tag allocation after running the hardware queue,
                 * as running the queue may also have found completions.
                 */
-               tag = __blk_mq_get_tag(data->hctx, bt);
+               tag = __blk_mq_get_tag(data, bt);
                if (tag != -1)
                        break;
 

diff --git a/block/blk-mq.c b/block/blk-mq.c
index ee69e5e..dcb5676 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -230,15 +230,14 @@ struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
 
                rq = tags->static_rqs[tag];
 
-               if (blk_mq_tag_busy(data->hctx)) {
-                       rq->rq_flags = RQF_MQ_INFLIGHT;
-                       atomic_inc(&data->hctx->nr_active);
-               }
-
                if (data->flags & BLK_MQ_REQ_INTERNAL) {
                        rq->tag = -1;
                        rq->internal_tag = tag;
                } else {
+                       if (blk_mq_tag_busy(data->hctx)) {
+                               rq->rq_flags = RQF_MQ_INFLIGHT;
+                               atomic_inc(&data->hctx->nr_active);
+                       }
                        rq->tag = tag;
                        rq->internal_tag = -1;
                }
@@ -869,6 +868,10 @@ done:
 
        rq->tag = blk_mq_get_tag(&data);
        if (rq->tag >= 0) {
+               if (blk_mq_tag_busy(data.hctx)) {
+                       rq->rq_flags |= RQF_MQ_INFLIGHT;
+                       atomic_inc(&data.hctx->nr_active);
+               }
                data.hctx->tags->rqs[rq->tag] = rq;
                goto done;
        }