blk-mq: count the hctx as active before allocating tag

BugLink: https://bugs.launchpad.net/bugs/1835972
[ Upstream commit d263ed9926823c462f99a7679e18f0c9e5b8550d ]

Currently, we count the hctx as active after allocate driver tag
successfully. If a previously inactive hctx try to get tag first
time, it may fails and need to wait. However, due to the stale tag
->active_queues, the other shared-tags users are still able to
occupy all driver tags while there is someone waiting for tag.
Consequently, even if the previously inactive hctx is waked up, it
still may not be able to get a tag and could be starved.

To fix it, we count the hctx as active before try to allocate driver
tag, then when it is waiting the tag, the other shared-tag users
will reserve budget for it.

Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Kleber Sacilotto de Souza <kleber.souza@canonical.com>

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c81b40ecd3f11e90596cf25887269f4341f227d6..a546f9a44f315656d44df25e1821f79e49b2a9eb 100644 (file)
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -23,6 +23,9 @@ bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
 
 /*
  * If a previously inactive queue goes active, bump the active user count.
+ * We need to do this before try to allocate driver tag, then even if fail
+ * to get tag when first time, the other shared-tag users could reserve
+ * budget for it.
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 67a80fd597e1405133ea3b4b27e3a69877d9bc47..be342d0aca34cebb2da25f9d6abb48c852d184d5 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -298,7 +298,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
                rq->tag = -1;
                rq->internal_tag = tag;
        } else {
-               if (blk_mq_tag_busy(data->hctx)) {
+               if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
                        rq->rq_flags = RQF_MQ_INFLIGHT;
                        atomic_inc(&data->hctx->nr_active);
                }
@@ -376,6 +376,8 @@ static struct request *blk_mq_get_request(struct request_queue *q,
                 */
                if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
                        e->type->ops.mq.limit_depth(op, data);
+       } else {
+               blk_mq_tag_busy(data->hctx);
        }
 
        tag = blk_mq_get_tag(data);
@@ -993,6 +995,7 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
                .hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
                .flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
        };
+       bool shared;
 
        might_sleep_if(wait);
 
@@ -1002,9 +1005,10 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
        if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
                data.flags |= BLK_MQ_REQ_RESERVED;
 
+       shared = blk_mq_tag_busy(data.hctx);
        rq->tag = blk_mq_get_tag(&data);
        if (rq->tag >= 0) {
-               if (blk_mq_tag_busy(data.hctx)) {
+               if (shared) {
                        rq->rq_flags |= RQF_MQ_INFLIGHT;
                        atomic_inc(&data.hctx->nr_active);
                }