Merge tag 'block-5.11-2021-01-29' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "All over the place fixes for this release:

   - blk-cgroup iteration teardown resched fix (Baolin)

   - NVMe pull request from Christoph:
        - add another Write Zeroes quirk (Chaitanya Kulkarni)
        - handle a no path available corner case (Daniel Wagner)
        - use the proper RCU aware list_add helper (Chao Leng)

   - bcache regression fix (Coly)

   - bdev->bd_size_lock IRQ fix. This will be fixed in drivers for 5.12,
     but for now, we'll make it IRQ safe (Damien)

   - null_blk zoned init fix (Damien)

   - add_partition() error handling fix (Dinghao)

   - s390 dasd kobject fix (Jan)

   - nbd fix for freezing queue while adding connections (Josef)

   - tag queueing regression fix (Ming)

   - revert of a patch that inadvertently meant that we regressed write
     performance on raid (Maxim)"

* tag 'block-5.11-2021-01-29' of git://git.kernel.dk/linux-block:
  null_blk: cleanup zoned mode initialization
  nvme-core: use list_add_tail_rcu instead of list_add_tail for nvme_init_ns_head
  nvme-multipath: Early exit if no path is available
  nvme-pci: add the DISABLE_WRITE_ZEROES quirk for a SPCC device
  bcache: only check feature sets when sb->version >= BCACHE_SB_VERSION_CDEV_WITH_FEATURES
  block: fix bd_size_lock use
  blk-cgroup: Use cond_resched() when destroy blkgs
  Revert "block: simplify set_init_blocksize" to regain lost performance
  nbd: freeze the queue while we're adding connections
  s390/dasd: Fix inconsistent kobject removal
  block: Fix an error handling in add_partition
  blk-mq: test QUEUE_FLAG_HCTX_ACTIVE for sbitmap_shared in hctx_may_queue

4 files changed, 22 insertions, 11 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 031114d454a6..4221a1539391 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1016,6 +1016,8 @@ static void blkcg_css_offline(struct cgroup_subsys_state *css)
  */
 void blkcg_destroy_blkgs(struct blkcg *blkcg)
 {
+	might_sleep();
+
 	spin_lock_irq(&blkcg->lock);
 
 	while (!hlist_empty(&blkcg->blkg_list)) {
@@ -1023,14 +1025,20 @@ void blkcg_destroy_blkgs(struct blkcg *blkcg)
 						struct blkcg_gq, blkcg_node);
 		struct request_queue *q = blkg->q;
 
-		if (spin_trylock(&q->queue_lock)) {
-			blkg_destroy(blkg);
-			spin_unlock(&q->queue_lock);
-		} else {
+		if (need_resched() || !spin_trylock(&q->queue_lock)) {
+			/*
+			 * Given that the system can accumulate a huge number
+			 * of blkgs in pathological cases, check to see if we
+			 * need to rescheduling to avoid softlockup.
+			 */
 			spin_unlock_irq(&blkcg->lock);
-			cpu_relax();
+			cond_resched();
 			spin_lock_irq(&blkcg->lock);
+			continue;
 		}
+
+		blkg_destroy(blkg);
+		spin_unlock(&q->queue_lock);
 	}
 
 	spin_unlock_irq(&blkcg->lock);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index c1458d9502f1..3616453ca28c 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -304,7 +304,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 		struct request_queue *q = hctx->queue;
 		struct blk_mq_tag_set *set = q->tag_set;
 
-		if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &q->queue_flags))
+		if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags))
 			return true;
 		users = atomic_read(&set->active_queues_shared_sbitmap);
 	} else {
diff --git a/block/genhd.c b/block/genhd.c
index 419548e92d82..9e741a4f351b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -45,10 +45,11 @@ static void disk_release_events(struct gendisk *disk);
 void set_capacity(struct gendisk *disk, sector_t sectors)
 {
 	struct block_device *bdev = disk->part0;
+	unsigned long flags;
 
-	spin_lock(&bdev->bd_size_lock);
+	spin_lock_irqsave(&bdev->bd_size_lock, flags);
 	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
-	spin_unlock(&bdev->bd_size_lock);
+	spin_unlock_irqrestore(&bdev->bd_size_lock, flags);
 }
 EXPORT_SYMBOL(set_capacity);
 
diff --git a/block/partitions/core.c b/block/partitions/core.c
index e7d776db803b..4601a845cd79 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -88,9 +88,11 @@ static int (*check_part[])(struct parsed_partitions *) = {
 
 static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
 {
-	spin_lock(&bdev->bd_size_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&bdev->bd_size_lock, flags);
 	i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
-	spin_unlock(&bdev->bd_size_lock);
+	spin_unlock_irqrestore(&bdev->bd_size_lock, flags);
 }
 
 static struct parsed_partitions *allocate_partitions(struct gendisk *hd)
@@ -384,7 +386,7 @@ static struct block_device *add_partition(struct gendisk *disk, int partno,
 
 	err = blk_alloc_devt(bdev, &devt);
 	if (err)
-		goto out_bdput;
+		goto out_put;
 	pdev->devt = devt;
 
 	/* delay uevent until 'holders' subdir is created */