Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:
 "This is a followup for block changes, that didn't make the initial
  pull request. It's a bit of a mixed bag, this contains:

   - A followup pull request from Sagi for NVMe. Outside of fixups for
     NVMe, it also includes a series for ensuring that we properly
     quiesce hardware queues when browsing live tags.

   - Set of integrity fixes from Dmitry (mostly), fixing various issues
     for folks using DIF/DIX.

   - Fix for a bug introduced in cciss, with the req init changes. From
     Christoph.

   - Fix for a bug in BFQ, from Paolo.

   - Two followup fixes for lightnvm/pblk from Javier.

   - Depth fix from Ming for blk-mq-sched.

   - Also from Ming, performance fix for mtip32xx that was introduced
     with the dynamic initialization of commands"

* 'for-linus' of git://git.kernel.dk/linux-block: (44 commits)
  block: call bio_uninit in bio_endio
  nvmet: avoid unneeded assignment of submit_bio return value
  nvme-pci: add module parameter for io queue depth
  nvme-pci: compile warnings in nvme_alloc_host_mem()
  nvmet_fc: Accept variable pad lengths on Create Association LS
  nvme_fc/nvmet_fc: revise Create Association descriptor length
  lightnvm: pblk: remove unnecessary checks
  lightnvm: pblk: control I/O flow also on tear down
  cciss: initialize struct scsi_req
  null_blk: fix error flow for shared tags during module_init
  block: Fix __blkdev_issue_zeroout loop
  nvme-rdma: unconditionally recycle the request mr
  nvme: split nvme_uninit_ctrl into stop and uninit
  virtio_blk: quiesce/unquiesce live IO when entering PM states
  mtip32xx: quiesce request queues to make sure no submissions are inflight
  nbd: quiesce request queues to make sure no submissions are inflight
  nvme: kick requeue list when requeueing a request instead of when starting the queues
  nvme-pci: quiesce/unquiesce admin_q instead of start/stop its hw queues
  nvme-loop: quiesce/unquiesce admin_q instead of start/stop its hw queues
  nvme-fc: quiesce/unquiesce admin_q instead of start/stop its hw queues
  ...

1 files changed, 34 insertions, 5 deletions

diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 8726ede19eef..5ec05cd42b80 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -694,10 +694,28 @@ struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity)
 	return sched_data->service_tree + idx;
 }
 
-
+/*
+ * Update weight and priority of entity. If update_class_too is true,
+ * then update the ioprio_class of entity too.
+ *
+ * The reason why the update of ioprio_class is controlled through the
+ * last parameter is as follows. Changing the ioprio class of an
+ * entity implies changing the destination service trees for that
+ * entity. If such a change occurred when the entity is already on one
+ * of the service trees for its previous class, then the state of the
+ * entity would become more complex: none of the new possible service
+ * trees for the entity, according to bfq_entity_service_tree(), would
+ * match any of the possible service trees on which the entity
+ * is. Complex operations involving these trees, such as entity
+ * activations and deactivations, should take into account this
+ * additional complexity.  To avoid this issue, this function is
+ * invoked with update_class_too unset in the points in the code where
+ * entity may happen to be on some tree.
+ */
 struct bfq_service_tree *
 __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
-				struct bfq_entity *entity)
+				struct bfq_entity *entity,
+				bool update_class_too)
 {
 	struct bfq_service_tree *new_st = old_st;
 
@@ -739,9 +757,15 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 				  bfq_weight_to_ioprio(entity->orig_weight);
 		}
 
-		if (bfqq)
+		if (bfqq && update_class_too)
 			bfqq->ioprio_class = bfqq->new_ioprio_class;
-		entity->prio_changed = 0;
+
+		/*
+		 * Reset prio_changed only if the ioprio_class change
+		 * is not pending any longer.
+		 */
+		if (!bfqq || bfqq->ioprio_class == bfqq->new_ioprio_class)
+			entity->prio_changed = 0;
 
 		/*
 		 * NOTE: here we may be changing the weight too early,
@@ -867,7 +891,12 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
 {
 	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
 
-	st = __bfq_entity_update_weight_prio(st, entity);
+	/*
+	 * When this function is invoked, entity is not in any service
+	 * tree, then it is safe to invoke next function with the last
+	 * parameter set (see the comments on the function).
+	 */
+	st = __bfq_entity_update_weight_prio(st, entity, true);
 	bfq_calc_finish(entity, entity->budget);
 
 	/*