block: directly insert blk-mq request from blk_insert_cloned_request()

commit 157f377beb710e84bd8bc7a3c4475c0674ebebd7 upstream.

A NULL pointer crash was reported for the case of having the BFQ IO
scheduler attached to the underlying blk-mq paths of a DM multipath
device.  The crash occured in blk_mq_sched_insert_request()'s call to
e->type->ops.mq.insert_requests().

Paolo Valente correctly summarized why the crash occured with:
"the call chain (dm_mq_queue_rq -> map_request -> setup_clone ->
blk_rq_prep_clone) creates a cloned request without invoking
e->type->ops.mq.prepare_request for the target elevator e.  The cloned
request is therefore not initialized for the scheduler, but it is
however inserted into the scheduler by blk_mq_sched_insert_request."

All said, a request-based DM multipath device's IO scheduler should be
the only one used -- when the original requests are issued to the
underlying paths as cloned requests they are inserted directly in the
underlying dispatch queue(s) rather than through an additional elevator.

But commit bd166ef18 ("blk-mq-sched: add framework for MQ capable IO
schedulers") switched blk_insert_cloned_request() from using
blk_mq_insert_request() to blk_mq_sched_insert_request().  Which
incorrectly added elevator machinery into a call chain that isn't
supposed to have any.

To fix this introduce a blk-mq private blk_mq_request_bypass_insert()
that blk_insert_cloned_request() calls to insert the request without
involving any elevator that may be attached to the cloned request's
request_queue.

Fixes: bd166ef183c2 ("blk-mq-sched: add framework for MQ capable IO schedulers")
Reported-by: Bart Van Assche <Bart.VanAssche@wdc.com>
Tested-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 23 insertions, 1 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index eeff6d64c6b2..658f67309602 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2330,7 +2330,12 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_sched_insert_request(rq, false, true, false, false);
+		/*
+		 * Since we have a scheduler attached on the top device,
+		 * bypass a potential scheduler on the bottom device for
+		 * insert.
+		 */
+		blk_mq_request_bypass_insert(rq);
 		return BLK_STS_OK;
 	}
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4603b115e234..e0523eb8eee1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1357,6 +1357,22 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
+/*
+ * Should only be used carefully, when the caller knows we want to
+ * bypass a potential IO scheduler on the target device.
+ */
+void blk_mq_request_bypass_insert(struct request *rq)
+{
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, ctx->cpu);
+
+	spin_lock(&hctx->lock);
+	list_add_tail(&rq->queuelist, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
+
+	blk_mq_run_hw_queue(hctx, false);
+}
+
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 			    struct list_head *list)
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 60b01c0309bc..f64747914560 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -54,6 +54,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
  */
 void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 				bool at_head);
+void blk_mq_request_bypass_insert(struct request *rq);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);