Merge tag 'for-6.1/block-2022-10-03' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Christoph:
      - handle number of queue changes in the TCP and RDMA drivers
        (Daniel Wagner)
      - allow changing the number of queues in nvmet (Daniel Wagner)
      - also consider host_iface when checking ip options (Daniel
        Wagner)
      - don't map pages which can't come from HIGHMEM (Fabio M. De
        Francesco)
      - avoid unnecessary flush bios in nvmet (Guixin Liu)
      - shrink and better pack the nvme_iod structure (Keith Busch)
      - add comment for unaligned "fake" nqn (Linjun Bao)
      - print actual source IP address through sysfs "address" attr
        (Martin Belanger)
      - various cleanups (Jackie Liu, Wolfram Sang, Genjian Zhang)
      - handle effects after freeing the request (Keith Busch)
      - copy firmware_rev on each init (Keith Busch)
      - restrict management ioctls to admin (Keith Busch)
      - ensure subsystem reset is single threaded (Keith Busch)
      - report the actual number of tagset maps in nvme-pci (Keith
        Busch)
      - small fabrics authentication fixups (Christoph Hellwig)
      - add common code for tagset allocation and freeing (Christoph
        Hellwig)
      - stop using the request_queue in nvmet (Christoph Hellwig)
      - set min_align_mask before calculating max_hw_sectors (Rishabh
        Bhatnagar)
      - send a rediscover uevent when a persistent discovery controller
        reconnects (Sagi Grimberg)
      - misc nvmet-tcp fixes (Varun Prakash, zhenwei pi)

 - MD pull request via Song:
      - Various raid5 fix and clean up, by Logan Gunthorpe and David
        Sloan.
      - Raid10 performance optimization, by Yu Kuai.

 - sbitmap wakeup hang fixes (Hugh, Keith, Jan, Yu)

 - IO scheduler switching quisce fix (Keith)

 - s390/dasd block driver updates (Stefan)

 - support for recovery for the ublk driver (ZiyangZhang)

 - rnbd drivers fixes and updates (Guoqing, Santosh, ye, Christoph)

 - blk-mq and null_blk map fixes (Bart)

 - various bcache fixes (Coly, Jilin, Jules)

 - nbd signal hang fix (Shigeru)

 - block writeback throttling fix (Yu)

 - optimize the passthrough mapping handling (me)

 - prepare block cgroups to being gendisk based (Christoph)

 - get rid of an old PSI hack in the block layer, moving it to the
   callers instead where it belongs (Christoph)

 - blk-throttle fixes and cleanups (Yu)

 - misc fixes and cleanups (Liu Shixin, Liu Song, Miaohe, Pankaj,
   Ping-Xiang, Wolfram, Saurabh, Li Jinlin, Li Lei, Lin, Li zeming,
   Miaohe, Bart, Coly, Gaosheng

* tag 'for-6.1/block-2022-10-03' of git://git.kernel.dk/linux: (162 commits)
  sbitmap: fix lockup while swapping
  block: add rationale for not using blk_mq_plug() when applicable
  block: adapt blk_mq_plug() to not plug for writes that require a zone lock
  s390/dasd: use blk_mq_alloc_disk
  blk-cgroup: don't update the blkg lookup hint in blkg_conf_prep
  nvmet: don't look at the request_queue in nvmet_bdev_set_limits
  nvmet: don't look at the request_queue in nvmet_bdev_zone_mgmt_emulate_all
  blk-mq: use quiesced elevator switch when reinitializing queues
  block: replace blk_queue_nowait with bdev_nowait
  nvme: remove nvme_ctrl_init_connect_q
  nvme-loop: use the tagset alloc/free helpers
  nvme-loop: store the generic nvme_ctrl in set->driver_data
  nvme-loop: initialize sqsize later
  nvme-fc: use the tagset alloc/free helpers
  nvme-fc: store the generic nvme_ctrl in set->driver_data
  nvme-fc: keep ctrl->sqsize in sync with opts->queue_size
  nvme-rdma: use the tagset alloc/free helpers
  nvme-rdma: store the generic nvme_ctrl in set->driver_data
  nvme-tcp: use the tagset alloc/free helpers
  nvme-tcp: store the generic nvme_ctrl in set->driver_data
  ...

1 files changed, 19 insertions, 13 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 0df20184cc3e..83492d942348 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1093,10 +1093,12 @@ bool blk_mq_complete_request_remote(struct request *rq)
 	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
 
 	/*
-	 * For a polled request, always complete locally, it's pointless
-	 * to redirect the completion.
+	 * For request which hctx has only one ctx mapping,
+	 * or a polled request, always complete locally,
+	 * it's pointless to redirect the completion.
 	 */
-	if (rq->cmd_flags & REQ_POLLED)
+	if (rq->mq_hctx->nr_ctx == 1 ||
+		rq->cmd_flags & REQ_POLLED)
 		return false;
 
 	if (blk_mq_complete_need_ipi(rq)) {
@@ -1213,6 +1215,12 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head)
 	WARN_ON(!blk_rq_is_passthrough(rq));
 
 	blk_account_io_start(rq);
+
+	/*
+	 * As plugging can be enabled for passthrough requests on a zoned
+	 * device, directly accessing the plug instead of using blk_mq_plug()
+	 * should not have any consequences.
+	 */
 	if (current->plug)
 		blk_add_rq_to_plug(current->plug, rq);
 	else
@@ -1993,7 +2001,7 @@ out:
 		if (!needs_restart ||
 		    (no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
 			blk_mq_run_hw_queue(hctx, true);
-		else if (needs_restart && needs_resource)
+		else if (needs_resource)
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
 
 		blk_mq_update_dispatch_busy(hctx, true);
@@ -4192,7 +4200,7 @@ static int blk_mq_alloc_set_map_and_rqs(struct blk_mq_tag_set *set)
 	return 0;
 }
 
-static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
+static void blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 {
 	/*
 	 * blk_mq_map_queues() and multiple .map_queues() implementations
@@ -4222,10 +4230,10 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 		for (i = 0; i < set->nr_maps; i++)
 			blk_mq_clear_mq_map(&set->map[i]);
 
-		return set->ops->map_queues(set);
+		set->ops->map_queues(set);
 	} else {
 		BUG_ON(set->nr_maps > 1);
-		return blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
+		blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]);
 	}
 }
 
@@ -4324,9 +4332,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 		set->map[i].nr_queues = is_kdump_kernel() ? 1 : set->nr_hw_queues;
 	}
 
-	ret = blk_mq_update_queue_map(set);
-	if (ret)
-		goto out_free_mq_map;
+	blk_mq_update_queue_map(set);
 
 	ret = blk_mq_alloc_set_map_and_rqs(set);
 	if (ret)
@@ -4474,14 +4480,14 @@ static bool blk_mq_elv_switch_none(struct list_head *head,
 	list_add(&qe->node, head);
 
 	/*
-	 * After elevator_switch_mq, the previous elevator_queue will be
+	 * After elevator_switch, the previous elevator_queue will be
 	 * released by elevator_release. The reference of the io scheduler
 	 * module get by elevator_get will also be put. So we need to get
 	 * a reference of the io scheduler module here to prevent it to be
 	 * removed.
 	 */
 	__module_get(qe->type->elevator_owner);
-	elevator_switch_mq(q, NULL);
+	elevator_switch(q, NULL);
 	mutex_unlock(&q->sysfs_lock);
 
 	return true;
@@ -4513,7 +4519,7 @@ static void blk_mq_elv_switch_back(struct list_head *head,
 	kfree(qe);
 
 	mutex_lock(&q->sysfs_lock);
-	elevator_switch_mq(q, t);
+	elevator_switch(q, t);
 	mutex_unlock(&q->sysfs_lock);
 }