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

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);

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 {

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);
 

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 */

drivers/block/nbd.c

@@ -1022,6 +1022,12 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	if (!sock)
 		return err;
 
+	/*
+	 * We need to make sure we don't get any errant requests while we're
+	 * reallocating the ->socks array.
+	 */
+	blk_mq_freeze_queue(nbd->disk->queue);
+
 	if (!netlink && !nbd->task_setup &&
 	    !test_bit(NBD_RT_BOUND, &config->runtime_flags))
 		nbd->task_setup = current;
@@ -1060,10 +1066,12 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	nsock->cookie = 0;
 	socks[config->num_connections++] = nsock;
 	atomic_inc(&config->live_connections);
+	blk_mq_unfreeze_queue(nbd->disk->queue);
 
 	return 0;
 
 put_socket:
+	blk_mq_unfreeze_queue(nbd->disk->queue);
 	sockfd_put(sock);
 	return err;
 }

drivers/block/null_blk/zoned.c

@@ -6,7 +6,10 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-#define MB_TO_SECTS(mb) (((sector_t)mb * SZ_1M) >> SECTOR_SHIFT)
+static inline sector_t mb_to_sects(unsigned long mb)
+{
+	return ((sector_t)mb * SZ_1M) >> SECTOR_SHIFT;
+}
 
 static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
 {
@@ -77,12 +80,11 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 		return -EINVAL;
 	}
 
-	zone_capacity_sects = MB_TO_SECTS(dev->zone_capacity);
-	dev_capacity_sects = MB_TO_SECTS(dev->size);
-	dev->zone_size_sects = MB_TO_SECTS(dev->zone_size);
-	dev->nr_zones = dev_capacity_sects >> ilog2(dev->zone_size_sects);
-	if (dev_capacity_sects & (dev->zone_size_sects - 1))
-		dev->nr_zones++;
+	zone_capacity_sects = mb_to_sects(dev->zone_capacity);
+	dev_capacity_sects = mb_to_sects(dev->size);
+	dev->zone_size_sects = mb_to_sects(dev->zone_size);
+	dev->nr_zones = round_up(dev_capacity_sects, dev->zone_size_sects)
+		>> ilog2(dev->zone_size_sects);
 
 	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct nullb_zone),
 				    GFP_KERNEL | __GFP_ZERO);

drivers/md/bcache/features.h

@@ -33,6 +33,8 @@
 #define BCH_FEATURE_COMPAT_FUNCS(name, flagname) \
 static inline int bch_has_feature_##name(struct cache_sb *sb) \
 { \
+	if (sb->version < BCACHE_SB_VERSION_CDEV_WITH_FEATURES) \
+		return 0; \
 	return (((sb)->feature_compat & \
 		BCH##_FEATURE_COMPAT_##flagname) != 0); \
 } \
@@ -50,6 +52,8 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \
 #define BCH_FEATURE_RO_COMPAT_FUNCS(name, flagname) \
 static inline int bch_has_feature_##name(struct cache_sb *sb) \
 { \
+	if (sb->version < BCACHE_SB_VERSION_CDEV_WITH_FEATURES) \
+		return 0; \
 	return (((sb)->feature_ro_compat & \
 		BCH##_FEATURE_RO_COMPAT_##flagname) != 0); \
 } \
@@ -67,6 +71,8 @@ static inline void bch_clear_feature_##name(struct cache_sb *sb) \
 #define BCH_FEATURE_INCOMPAT_FUNCS(name, flagname) \
 static inline int bch_has_feature_##name(struct cache_sb *sb) \
 { \
+	if (sb->version < BCACHE_SB_VERSION_CDEV_WITH_FEATURES) \
+		return 0; \
 	return (((sb)->feature_incompat & \
 		BCH##_FEATURE_INCOMPAT_##flagname) != 0); \
 } \

drivers/nvme/host/core.c

@@ -3829,7 +3829,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, unsigned nsid,
 		}
 	}
 
-	list_add_tail(&ns->siblings, &head->list);
+	list_add_tail_rcu(&ns->siblings, &head->list);
 	ns->head = head;
 	mutex_unlock(&ctrl->subsys->lock);
 	return 0;

drivers/nvme/host/multipath.c

@@ -221,7 +221,7 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head,
 	}
 
 	for (ns = nvme_next_ns(head, old);
-	     ns != old;
+	     ns && ns != old;
 	     ns = nvme_next_ns(head, ns)) {
 		if (nvme_path_is_disabled(ns))
 			continue;

drivers/nvme/host/pci.c

@@ -3257,6 +3257,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x15b7, 0x2001),   /*  Sandisk Skyhawk */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x1d97, 0x2263),   /* SPCC */
+		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },

drivers/s390/block/dasd_devmap.c

@@ -1874,18 +1874,26 @@ void dasd_path_create_kobjects(struct dasd_device *device)
 }
 EXPORT_SYMBOL(dasd_path_create_kobjects);
 
-/*
- * As we keep kobjects for the lifetime of a device, this function must not be
- * called anywhere but in the context of offlining a device.
- */
-void dasd_path_remove_kobj(struct dasd_device *device, int chp)
+static void dasd_path_remove_kobj(struct dasd_device *device, int chp)
 {
 	if (device->path[chp].in_sysfs) {
 		kobject_put(&device->path[chp].kobj);
 		device->path[chp].in_sysfs = false;
 	}
 }
-EXPORT_SYMBOL(dasd_path_remove_kobj);
+
+/*
+ * As we keep kobjects for the lifetime of a device, this function must not be
+ * called anywhere but in the context of offlining a device.
+ */
+void dasd_path_remove_kobjects(struct dasd_device *device)
+{
+	int i;
+
+	for (i = 0; i < 8; i++)
+		dasd_path_remove_kobj(device, i);
+}
+EXPORT_SYMBOL(dasd_path_remove_kobjects);
 
 int dasd_add_sysfs_files(struct ccw_device *cdev)
 {

drivers/s390/block/dasd_eckd.c

@@ -1036,7 +1036,6 @@ static void dasd_eckd_clear_conf_data(struct dasd_device *device)
 		device->path[i].ssid = 0;
 		device->path[i].chpid = 0;
 		dasd_path_notoper(device, i);
-		dasd_path_remove_kobj(device, i);
 	}
 }
 
@@ -2173,6 +2172,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
 	device->block = NULL;
 out_err1:
 	dasd_eckd_clear_conf_data(device);
+	dasd_path_remove_kobjects(device);
 	kfree(device->private);
 	device->private = NULL;
 	return rc;
@@ -2191,6 +2191,7 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
 	private->vdsneq = NULL;
 	private->gneq = NULL;
 	dasd_eckd_clear_conf_data(device);
+	dasd_path_remove_kobjects(device);
 }
 
 static struct dasd_ccw_req *

drivers/s390/block/dasd_int.h

@@ -858,7 +858,7 @@ int dasd_add_sysfs_files(struct ccw_device *);
 void dasd_remove_sysfs_files(struct ccw_device *);
 void dasd_path_create_kobj(struct dasd_device *, int);
 void dasd_path_create_kobjects(struct dasd_device *);
-void dasd_path_remove_kobj(struct dasd_device *, int);
+void dasd_path_remove_kobjects(struct dasd_device *);
 
 struct dasd_device *dasd_device_from_cdev(struct ccw_device *);
 struct dasd_device *dasd_device_from_cdev_locked(struct ccw_device *);

fs/block_dev.c

@@ -130,7 +130,15 @@ EXPORT_SYMBOL(truncate_bdev_range);
 
 static void set_init_blocksize(struct block_device *bdev)
 {
-	bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
+	unsigned int bsize = bdev_logical_block_size(bdev);
+	loff_t size = i_size_read(bdev->bd_inode);
+
+	while (bsize < PAGE_SIZE) {
+		if (size & bsize)
+			break;
+		bsize <<= 1;
+	}
+	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
 }
 
 int set_blocksize(struct block_device *bdev, int size)