Merge tag 'for-linus-20180929' of git://git.kernel.dk/linux-block

Jens writes:
  "Block fixes for 4.19-rc6

   A set of fixes that should go into this release. This pull request
   contains:

   - A fix (hopefully) for the persistent grants for xen-blkfront. A
     previous fix from this series wasn't complete, hence reverted, and
     this one should hopefully be it. (Boris Ostrovsky)

   - Fix for an elevator drain warning with SMR devices, which is
     triggered when you switch schedulers (Damien)

   - bcache deadlock fix (Guoju Fang)

   - Fix for the block unplug tracepoint, which has had the
     timer/explicit flag reverted since 4.11 (Ilya)

   - Fix a regression in this series where the blk-mq timeout hook is
     invoked with the RCU read lock held, hence preventing it from
     blocking (Keith)

   - NVMe pull from Christoph, with a single multipath fix (Susobhan Dey)"

* tag 'for-linus-20180929' of git://git.kernel.dk/linux-block:
  xen/blkfront: correct purging of persistent grants
  Revert "xen/blkfront: When purging persistent grants, keep them in the buffer"
  blk-mq: I/O and timer unplugs are inverted in blktrace
  bcache: add separate workqueue for journal_write to avoid deadlock
  xen/blkfront: When purging persistent grants, keep them in the buffer
  block: fix deadline elevator drain for zoned block devices
  blk-mq: Allow blocking queue tag iter callbacks
  nvme: properly propagate errors in nvme_mpath_init

8 files changed, 25 insertions, 19 deletions

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 94e1ed667b6e..41317c50a446 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -322,16 +322,11 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 
 	/*
 	 * __blk_mq_update_nr_hw_queues will update the nr_hw_queues and
-	 * queue_hw_ctx after freeze the queue. So we could use q_usage_counter
-	 * to avoid race with it. __blk_mq_update_nr_hw_queues will users
-	 * synchronize_rcu to ensure all of the users go out of the critical
-	 * section below and see zeroed q_usage_counter.
+	 * queue_hw_ctx after freeze the queue, so we use q_usage_counter
+	 * to avoid race with it.
 	 */
-	rcu_read_lock();
-	if (percpu_ref_is_zero(&q->q_usage_counter)) {
-		rcu_read_unlock();
+	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
-	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		struct blk_mq_tags *tags = hctx->tags;
@@ -347,7 +342,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
 		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
 	}
-	rcu_read_unlock();
+	blk_queue_exit(q);
 }
 
 static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 85a1c1a59c72..e3c39ea8e17b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1628,7 +1628,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		BUG_ON(!rq->q);
 		if (rq->mq_ctx != this_ctx) {
 			if (this_ctx) {
-				trace_block_unplug(this_q, depth, from_schedule);
+				trace_block_unplug(this_q, depth, !from_schedule);
 				blk_mq_sched_insert_requests(this_q, this_ctx,
 								&ctx_list,
 								from_schedule);
@@ -1648,7 +1648,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	 * on 'ctx_list'. Do those.
 	 */
 	if (this_ctx) {
-		trace_block_unplug(this_q, depth, from_schedule);
+		trace_block_unplug(this_q, depth, !from_schedule);
 		blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
 						from_schedule);
 	}
diff --git a/block/elevator.c b/block/elevator.c
index 6a06b5d040e5..fae58b2f906f 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -609,7 +609,7 @@ void elv_drain_elevator(struct request_queue *q)
 
 	while (e->type->ops.sq.elevator_dispatch_fn(q, 1))
 		;
-	if (q->nr_sorted && printed++ < 10) {
+	if (q->nr_sorted && !blk_queue_is_zoned(q) && printed++ < 10 ) {
 		printk(KERN_ERR "%s: forced dispatching is broken "
 		       "(nr_sorted=%u), please report this\n",
 		       q->elevator->type->elevator_name, q->nr_sorted);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index a71d817e900d..429d20131c7e 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2670,8 +2670,8 @@ static void purge_persistent_grants(struct blkfront_info *info)
 			list_del(&gnt_list_entry->node);
 			gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL);
 			rinfo->persistent_gnts_c--;
-			__free_page(gnt_list_entry->page);
-			kfree(gnt_list_entry);
+			gnt_list_entry->gref = GRANT_INVALID_REF;
+			list_add_tail(&gnt_list_entry->node, &rinfo->grants);
 		}
 
 		spin_unlock_irqrestore(&rinfo->ring_lock, flags);
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 83504dd8100a..954dad29e6e8 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -965,6 +965,7 @@ void bch_prio_write(struct cache *ca);
 void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
 
 extern struct workqueue_struct *bcache_wq;
+extern struct workqueue_struct *bch_journal_wq;
 extern struct mutex bch_register_lock;
 extern struct list_head bch_cache_sets;
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 6116bbf870d8..522c7426f3a0 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -485,7 +485,7 @@ static void do_journal_discard(struct cache *ca)
 
 		closure_get(&ca->set->cl);
 		INIT_WORK(&ja->discard_work, journal_discard_work);
-		schedule_work(&ja->discard_work);
+		queue_work(bch_journal_wq, &ja->discard_work);
 	}
 }
 
@@ -592,7 +592,7 @@ static void journal_write_done(struct closure *cl)
 		: &j->w[0];
 
 	__closure_wake_up(&w->wait);
-	continue_at_nobarrier(cl, journal_write, system_wq);
+	continue_at_nobarrier(cl, journal_write, bch_journal_wq);
 }
 
 static void journal_write_unlock(struct closure *cl)
@@ -627,7 +627,7 @@ static void journal_write_unlocked(struct closure *cl)
 		spin_unlock(&c->journal.lock);
 
 		btree_flush_write(c);
-		continue_at(cl, journal_write, system_wq);
+		continue_at(cl, journal_write, bch_journal_wq);
 		return;
 	}
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 94c756c66bd7..30ba9aeb5ee8 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -47,6 +47,7 @@ static int bcache_major;
 static DEFINE_IDA(bcache_device_idx);
 static wait_queue_head_t unregister_wait;
 struct workqueue_struct *bcache_wq;
+struct workqueue_struct *bch_journal_wq;
 
 #define BTREE_MAX_PAGES		(256 * 1024 / PAGE_SIZE)
 /* limitation of partitions number on single bcache device */
@@ -2341,6 +2342,9 @@ static void bcache_exit(void)
 		kobject_put(bcache_kobj);
 	if (bcache_wq)
 		destroy_workqueue(bcache_wq);
+	if (bch_journal_wq)
+		destroy_workqueue(bch_journal_wq);
+
 	if (bcache_major)
 		unregister_blkdev(bcache_major, "bcache");
 	unregister_reboot_notifier(&reboot);
@@ -2370,6 +2374,10 @@ static int __init bcache_init(void)
 	if (!bcache_wq)
 		goto err;
 
+	bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
+	if (!bch_journal_wq)
+		goto err;
+
 	bcache_kobj = kobject_create_and_add("bcache", fs_kobj);
 	if (!bcache_kobj)
 		goto err;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5a9562881d4e..9fe3fff818b8 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -537,8 +537,10 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 
 	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
 	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
-	if (!ctrl->ana_log_buf)
+	if (!ctrl->ana_log_buf) {
+		error = -ENOMEM;
 		goto out;
+	}
 
 	error = nvme_read_ana_log(ctrl, true);
 	if (error)
@@ -547,7 +549,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 out_free_ana_log_buf:
 	kfree(ctrl->ana_log_buf);
 out:
-	return -ENOMEM;
+	return error;
 }
 
 void nvme_mpath_uninit(struct nvme_ctrl *ctrl)