Merge branch 'for-5.9/drivers' into for-5.9/block-merge

* for-5.9/drivers: (38 commits)
  block: add max_active_zones to blk-sysfs
  block: add max_open_zones to blk-sysfs
  s390/dasd: Use struct_size() helper
  s390/dasd: fix inability to use DASD with DIAG driver
  md-cluster: fix wild pointer of unlock_all_bitmaps()
  md/raid5-cache: clear MD_SB_CHANGE_PENDING before flushing stripes
  md: fix deadlock causing by sysfs_notify
  md: improve io stats accounting
  md: raid0/linear: fix dereference before null check on pointer mddev
  rsxx: switch from 'pci_free_consistent()' to 'dma_free_coherent()'
  nvme: remove ns->disk checks
  nvme-pci: use standard block status symbolic names
  nvme-pci: use the consistent return type of nvme_pci_iod_alloc_size()
  nvme-pci: add a blank line after declarations
  nvme-pci: fix some comments issues
  nvme-pci: remove redundant segment validation
  nvme: document quirked Intel models
  nvme: expose reconnect_delay and ctrl_loss_tmo via sysfs
  nvme: support for zoned namespaces
  nvme: support for multiple Command Sets Supported and Effects log pages
  ...

39 files changed, 1115 insertions, 203 deletions

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index ed8c14f161ee..2322eb748b38 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -273,6 +273,24 @@ Description:
 		device ("host-aware" or "host-managed" zone model). For regular
 		block devices, the value is always 0.
 
+What:		/sys/block/<disk>/queue/max_active_zones
+Date:		July 2020
+Contact:	Niklas Cassel <niklas.cassel@wdc.com>
+Description:
+		For zoned block devices (zoned attribute indicating
+		"host-managed" or "host-aware"), the sum of zones belonging to
+		any of the zone states: EXPLICIT OPEN, IMPLICIT OPEN or CLOSED,
+		is limited by this value. If this value is 0, there is no limit.
+
+What:		/sys/block/<disk>/queue/max_open_zones
+Date:		July 2020
+Contact:	Niklas Cassel <niklas.cassel@wdc.com>
+Description:
+		For zoned block devices (zoned attribute indicating
+		"host-managed" or "host-aware"), the sum of zones belonging to
+		any of the zone states: EXPLICIT OPEN or IMPLICIT OPEN,
+		is limited by this value. If this value is 0, there is no limit.
+
 What:		/sys/block/<disk>/queue/chunk_sectors
 Date:		September 2016
 Contact:	Hannes Reinecke <hare@suse.com>
diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
index 6a8513af9201..f261a5c84170 100644
--- a/Documentation/block/queue-sysfs.rst
+++ b/Documentation/block/queue-sysfs.rst
@@ -117,6 +117,20 @@ Maximum number of elements in a DMA scatter/gather list with integrity
 data that will be submitted by the block layer core to the associated
 block driver.
 
+max_active_zones (RO)
+---------------------
+For zoned block devices (zoned attribute indicating "host-managed" or
+"host-aware"), the sum of zones belonging to any of the zone states:
+EXPLICIT OPEN, IMPLICIT OPEN or CLOSED, is limited by this value.
+If this value is 0, there is no limit.
+
+max_open_zones (RO)
+-------------------
+For zoned block devices (zoned attribute indicating "host-managed" or
+"host-aware"), the sum of zones belonging to any of the zone states:
+EXPLICIT OPEN or IMPLICIT OPEN, is limited by this value.
+If this value is 0, there is no limit.
+
 max_sectors_kb (RW)
 -------------------
 This is the maximum number of kilobytes that the block layer will allow
diff --git a/block/Kconfig b/block/Kconfig
index 9357d7302398..bbad5e8bbffe 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -86,9 +86,10 @@ config BLK_DEV_ZONED
 	select MQ_IOSCHED_DEADLINE
 	help
 	Block layer zoned block device support. This option enables
-	support for ZAC/ZBC host-managed and host-aware zoned block devices.
+	support for ZAC/ZBC/ZNS host-managed and host-aware zoned block
+	devices.
 
-	Say yes here if you have a ZAC or ZBC storage device.
+	Say yes here if you have a ZAC, ZBC, or ZNS storage device.
 
 config BLK_DEV_THROTTLING
 	bool "Block layer bio throttling support"
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index be67952e7be2..7dda709f3ccb 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -306,6 +306,16 @@ static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
 	return queue_var_show(blk_queue_nr_zones(q), page);
 }
 
+static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_max_open_zones(q), page);
+}
+
+static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_max_active_zones(q), page);
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show((blk_queue_nomerges(q) << 1) |
@@ -668,6 +678,16 @@ static struct queue_sysfs_entry queue_nr_zones_entry = {
 	.show = queue_nr_zones_show,
 };
 
+static struct queue_sysfs_entry queue_max_open_zones_entry = {
+	.attr = {.name = "max_open_zones", .mode = 0444 },
+	.show = queue_max_open_zones_show,
+};
+
+static struct queue_sysfs_entry queue_max_active_zones_entry = {
+	.attr = {.name = "max_active_zones", .mode = 0444 },
+	.show = queue_max_active_zones_show,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = 0644 },
 	.show = queue_nomerges_show,
@@ -766,6 +786,8 @@ static struct attribute *queue_attrs[] = {
 	&queue_nonrot_entry.attr,
 	&queue_zoned_entry.attr,
 	&queue_nr_zones_entry.attr,
+	&queue_max_open_zones_entry.attr,
+	&queue_max_active_zones_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
@@ -793,6 +815,11 @@ static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr,
 		(!q->mq_ops || !q->mq_ops->timeout))
 			return 0;
 
+	if ((attr == &queue_max_open_zones_entry.attr ||
+	     attr == &queue_max_active_zones_entry.attr) &&
+	    !blk_queue_is_zoned(q))
+		return 0;
+
 	return attr->mode;
 }
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 23831fa8701d..81152a260354 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -312,6 +312,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 		return ret;
 
 	rep.nr_zones = ret;
+	rep.flags = BLK_ZONE_REP_CAPACITY;
 	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
 		return -EFAULT;
 	return 0;
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index 81b311c9d781..daed4a9c3436 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -49,6 +49,7 @@ struct nullb_device {
 	unsigned long completion_nsec; /* time in ns to complete a request */
 	unsigned long cache_size; /* disk cache size in MB */
 	unsigned long zone_size; /* zone size in MB if device is zoned */
+	unsigned long zone_capacity; /* zone capacity in MB if device is zoned */
 	unsigned int zone_nr_conv; /* number of conventional zones */
 	unsigned int submit_queues; /* number of submission queues */
 	unsigned int home_node; /* home node for the device */
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 907c6858aec0..47a9dad880af 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -200,6 +200,10 @@ static unsigned long g_zone_size = 256;
 module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
 MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
 
+static unsigned long g_zone_capacity;
+module_param_named(zone_capacity, g_zone_capacity, ulong, 0444);
+MODULE_PARM_DESC(zone_capacity, "Zone capacity in MB when block device is zoned. Can be less than or equal to zone size. Default: Zone size");
+
 static unsigned int g_zone_nr_conv;
 module_param_named(zone_nr_conv, g_zone_nr_conv, uint, 0444);
 MODULE_PARM_DESC(zone_nr_conv, "Number of conventional zones when block device is zoned. Default: 0");
@@ -341,6 +345,7 @@ NULLB_DEVICE_ATTR(mbps, uint, NULL);
 NULLB_DEVICE_ATTR(cache_size, ulong, NULL);
 NULLB_DEVICE_ATTR(zoned, bool, NULL);
 NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
+NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
@@ -457,6 +462,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_badblocks,
 	&nullb_device_attr_zoned,
 	&nullb_device_attr_zone_size,
+	&nullb_device_attr_zone_capacity,
 	&nullb_device_attr_zone_nr_conv,
 	NULL,
 };
@@ -510,7 +516,8 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_nr_conv\n");
+	return snprintf(page, PAGE_SIZE,
+			"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -571,6 +578,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->use_per_node_hctx = g_use_per_node_hctx;
 	dev->zoned = g_zoned;
 	dev->zone_size = g_zone_size;
+	dev->zone_capacity = g_zone_capacity;
 	dev->zone_nr_conv = g_zone_nr_conv;
 	return dev;
 }
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index cc47606d8ffe..3d25c9ad2383 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -28,6 +28,15 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 		return -EINVAL;
 	}
 
+	if (!dev->zone_capacity)
+		dev->zone_capacity = dev->zone_size;
+
+	if (dev->zone_capacity > dev->zone_size) {
+		pr_err("null_blk: zone capacity (%lu MB) larger than zone size (%lu MB)\n",
+					dev->zone_capacity, dev->zone_size);
+		return -EINVAL;
+	}
+
 	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
 	dev->nr_zones = dev_size >>
 				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
@@ -47,6 +56,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 
 		zone->start = sector;
 		zone->len = dev->zone_size_sects;
+		zone->capacity = zone->len;
 		zone->wp = zone->start + zone->len;
 		zone->type = BLK_ZONE_TYPE_CONVENTIONAL;
 		zone->cond = BLK_ZONE_COND_NOT_WP;
@@ -59,6 +69,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 
 		zone->start = zone->wp = sector;
 		zone->len = dev->zone_size_sects;
+		zone->capacity = dev->zone_capacity << ZONE_SIZE_SHIFT;
 		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
 		zone->cond = BLK_ZONE_COND_EMPTY;
 
@@ -185,6 +196,9 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 			return BLK_STS_IOERR;
 		}
 
+		if (zone->wp + nr_sectors > zone->start + zone->capacity)
+			return BLK_STS_IOERR;
+
 		if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
 			zone->cond = BLK_ZONE_COND_IMP_OPEN;
 
@@ -193,7 +207,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 			return ret;
 
 		zone->wp += nr_sectors;
-		if (zone->wp == zone->start + zone->len)
+		if (zone->wp == zone->start + zone->capacity)
 			zone->cond = BLK_ZONE_COND_FULL;
 		return BLK_STS_OK;
 	default:
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 10f6368117d8..01333af13bbb 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -562,13 +562,15 @@ static int rsxx_eeh_frozen(struct pci_dev *dev)
 
 	for (i = 0; i < card->n_targets; i++) {
 		if (card->ctrl[i].status.buf)
-			pci_free_consistent(card->dev, STATUS_BUFFER_SIZE8,
-					    card->ctrl[i].status.buf,
-					    card->ctrl[i].status.dma_addr);
+			dma_free_coherent(&card->dev->dev,
+					  STATUS_BUFFER_SIZE8,
+					  card->ctrl[i].status.buf,
+					  card->ctrl[i].status.dma_addr);
 		if (card->ctrl[i].cmd.buf)
-			pci_free_consistent(card->dev, COMMAND_BUFFER_SIZE8,
-					    card->ctrl[i].cmd.buf,
-					    card->ctrl[i].cmd.dma_addr);
+			dma_free_coherent(&card->dev->dev,
+					  COMMAND_BUFFER_SIZE8,
+					  card->ctrl[i].cmd.buf,
+					  card->ctrl[i].cmd.dma_addr);
 	}
 
 	return 0;
@@ -711,15 +713,15 @@ static pci_ers_result_t rsxx_slot_reset(struct pci_dev *dev)
 failed_hw_buffers_init:
 	for (i = 0; i < card->n_targets; i++) {
 		if (card->ctrl[i].status.buf)
-			pci_free_consistent(card->dev,
-					STATUS_BUFFER_SIZE8,
-					card->ctrl[i].status.buf,
-					card->ctrl[i].status.dma_addr);
+			dma_free_coherent(&card->dev->dev,
+					  STATUS_BUFFER_SIZE8,
+					  card->ctrl[i].status.buf,
+					  card->ctrl[i].status.dma_addr);
 		if (card->ctrl[i].cmd.buf)
-			pci_free_consistent(card->dev,
-					COMMAND_BUFFER_SIZE8,
-					card->ctrl[i].cmd.buf,
-					card->ctrl[i].cmd.dma_addr);
+			dma_free_coherent(&card->dev->dev,
+					  COMMAND_BUFFER_SIZE8,
+					  card->ctrl[i].cmd.buf,
+					  card->ctrl[i].cmd.dma_addr);
 	}
 failed_hw_setup:
 	rsxx_eeh_failure(dev);
diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index 95a5f3757fa3..d61b524ae440 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -1631,7 +1631,7 @@ void md_bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force)
 		s += blocks;
 	}
 	bitmap->last_end_sync = jiffies;
-	sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed");
+	sysfs_notify_dirent_safe(bitmap->mddev->sysfs_completed);
 }
 EXPORT_SYMBOL(md_bitmap_cond_end_sync);
 
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 813a99ffa86f..73fd50e77975 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -1518,6 +1518,7 @@ static void unlock_all_bitmaps(struct mddev *mddev)
 			}
 		}
 		kfree(cinfo->other_bitmap_lockres);
+		cinfo->other_bitmap_lockres = NULL;
 	}
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 96b28f6d025c..bc06f046d9e7 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -463,24 +463,46 @@ check_suspended:
 }
 EXPORT_SYMBOL(md_handle_request);
 
+struct md_io {
+	struct mddev *mddev;
+	bio_end_io_t *orig_bi_end_io;
+	void *orig_bi_private;
+	unsigned long start_time;
+};
+
+static void md_end_io(struct bio *bio)
+{
+	struct md_io *md_io = bio->bi_private;
+	struct mddev *mddev = md_io->mddev;
+
+	disk_end_io_acct(mddev->gendisk, bio_op(bio), md_io->start_time);
+
+	bio->bi_end_io = md_io->orig_bi_end_io;
+	bio->bi_private = md_io->orig_bi_private;
+
+	mempool_free(md_io, &mddev->md_io_pool);
+
+	if (bio->bi_end_io)
+		bio->bi_end_io(bio);
+}
+
 static blk_qc_t md_submit_bio(struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
-	const int sgrp = op_stat_group(bio_op(bio));
 	struct mddev *mddev = bio->bi_disk->private_data;
-	unsigned int sectors;
 
-	if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
+	if (mddev == NULL || mddev->pers == NULL) {
 		bio_io_error(bio);
 		return BLK_QC_T_NONE;
 	}
 
-	blk_queue_split(&bio);
-
-	if (mddev == NULL || mddev->pers == NULL) {
+	if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
 		bio_io_error(bio);
 		return BLK_QC_T_NONE;
 	}
+
+	blk_queue_split(&bio);
+
 	if (mddev->ro == 1 && unlikely(rw == WRITE)) {
 		if (bio_sectors(bio) != 0)
 			bio->bi_status = BLK_STS_IOERR;
@@ -488,21 +510,27 @@ static blk_qc_t md_submit_bio(struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	/*
-	 * save the sectors now since our bio can
-	 * go away inside make_request
-	 */
-	sectors = bio_sectors(bio);
+	if (bio->bi_end_io != md_end_io) {
+		struct md_io *md_io;
+
+		md_io = mempool_alloc(&mddev->md_io_pool, GFP_NOIO);
+		md_io->mddev = mddev;
+		md_io->orig_bi_end_io = bio->bi_end_io;
+		md_io->orig_bi_private = bio->bi_private;
+
+		bio->bi_end_io = md_end_io;
+		bio->bi_private = md_io;
+
+		md_io->start_time = disk_start_io_acct(mddev->gendisk,
+						       bio_sectors(bio),
+						       bio_op(bio));
+	}
+
 	/* bio could be mergeable after passing to underlayer */
 	bio->bi_opf &= ~REQ_NOMERGE;
 
 	md_handle_request(mddev, bio);
 
-	part_stat_lock();
-	part_stat_inc(&mddev->gendisk->part0, ios[sgrp]);
-	part_stat_add(&mddev->gendisk->part0, sectors[sgrp], sectors);
-	part_stat_unlock();
-
 	return BLK_QC_T_NONE;
 }
 
@@ -2424,6 +2452,10 @@ static int bind_rdev_to_array(struct md_rdev *rdev, struct mddev *mddev)
 	if (sysfs_create_link(&rdev->kobj, ko, "block"))
 		/* failure here is OK */;
 	rdev->sysfs_state = sysfs_get_dirent_safe(rdev->kobj.sd, "state");
+	rdev->sysfs_unack_badblocks =
+		sysfs_get_dirent_safe(rdev->kobj.sd, "unacknowledged_bad_blocks");
+	rdev->sysfs_badblocks =
+		sysfs_get_dirent_safe(rdev->kobj.sd, "bad_blocks");
 
 	list_add_rcu(&rdev->same_set, &mddev->disks);
 	bd_link_disk_holder(rdev->bdev, mddev->gendisk);
@@ -2457,7 +2489,11 @@ static void unbind_rdev_from_array(struct md_rdev *rdev)
 	rdev->mddev = NULL;
 	sysfs_remove_link(&rdev->kobj, "block");
 	sysfs_put(rdev->sysfs_state);
+	sysfs_put(rdev->sysfs_unack_badblocks);
+	sysfs_put(rdev->sysfs_badblocks);
 	rdev->sysfs_state = NULL;
+	rdev->sysfs_unack_badblocks = NULL;
+	rdev->sysfs_badblocks = NULL;
 	rdev->badblocks.count = 0;
 	/* We need to delay this, otherwise we can deadlock when
 	 * writing to 'remove' to "dev/state".  We also need
@@ -2802,7 +2838,7 @@ rewrite:
 		goto repeat;
 	wake_up(&mddev->sb_wait);
 	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+		sysfs_notify_dirent_safe(mddev->sysfs_completed);
 
 	rdev_for_each(rdev, mddev) {
 		if (test_and_clear_bit(FaultRecorded, &rdev->flags))
@@ -4055,7 +4091,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
 	mddev_resume(mddev);
 	if (!mddev->thread)
 		md_update_sb(mddev, 1);
-	sysfs_notify(&mddev->kobj, NULL, "level");
+	sysfs_notify_dirent_safe(mddev->sysfs_level);
 	md_new_event(mddev);
 	rv = len;
 out_unlock:
@@ -4808,7 +4844,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 		}
 		if (err)
 			return err;
-		sysfs_notify(&mddev->kobj, NULL, "degraded");
+		sysfs_notify_dirent_safe(mddev->sysfs_degraded);
 	} else {
 		if (cmd_match(page, "check"))
 			set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
@@ -5514,6 +5550,13 @@ static void md_free(struct kobject *ko)
 
 	if (mddev->sysfs_state)
 		sysfs_put(mddev->sysfs_state);
+	if (mddev->sysfs_completed)
+		sysfs_put(mddev->sysfs_completed);
+	if (mddev->sysfs_degraded)
+		sysfs_put(mddev->sysfs_degraded);
+	if (mddev->sysfs_level)
+		sysfs_put(mddev->sysfs_level);
+
 
 	if (mddev->gendisk)
 		del_gendisk(mddev->gendisk);
@@ -5525,6 +5568,7 @@ static void md_free(struct kobject *ko)
 
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
+	mempool_exit(&mddev->md_io_pool);
 	kfree(mddev);
 }
 
@@ -5620,6 +5664,11 @@ static int md_alloc(dev_t dev, char *name)
 		 */
 		mddev->hold_active = UNTIL_STOP;
 
+	error = mempool_init_kmalloc_pool(&mddev->md_io_pool, BIO_POOL_SIZE,
+					  sizeof(struct md_io));
+	if (error)
+		goto abort;
+
 	error = -ENOMEM;
 	mddev->queue = blk_alloc_queue(NUMA_NO_NODE);
 	if (!mddev->queue)
@@ -5676,6 +5725,9 @@ static int md_alloc(dev_t dev, char *name)
 	if (!error && mddev->kobj.sd) {
 		kobject_uevent(&mddev->kobj, KOBJ_ADD);
 		mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
+		mddev->sysfs_completed = sysfs_get_dirent_safe(mddev->kobj.sd, "sync_completed");
+		mddev->sysfs_degraded = sysfs_get_dirent_safe(mddev->kobj.sd, "degraded");
+		mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level");
 	}
 	mddev_put(mddev);
 	return error;
@@ -6028,7 +6080,7 @@ static int do_md_run(struct mddev *mddev)
 	kobject_uevent(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE);
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	sysfs_notify_dirent_safe(mddev->sysfs_action);
-	sysfs_notify(&mddev->kobj, NULL, "degraded");
+	sysfs_notify_dirent_safe(mddev->sysfs_degraded);
 out:
 	clear_bit(MD_NOT_READY, &mddev->flags);
 	return err;
@@ -8742,7 +8794,7 @@ void md_do_sync(struct md_thread *thread)
 	} else
 		mddev->curr_resync = 3; /* no longer delayed */
 	mddev->curr_resync_completed = j;
-	sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+	sysfs_notify_dirent_safe(mddev->sysfs_completed);
 	md_new_event(mddev);
 	update_time = jiffies;
 
@@ -8770,7 +8822,7 @@ void md_do_sync(struct md_thread *thread)
 				mddev->recovery_cp = j;
 			update_time = jiffies;
 			set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
-			sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+			sysfs_notify_dirent_safe(mddev->sysfs_completed);
 		}
 
 		while (j >= mddev->resync_max &&
@@ -8877,7 +8929,7 @@ void md_do_sync(struct md_thread *thread)
 	    !test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
 	    mddev->curr_resync > 3) {
 		mddev->curr_resync_completed = mddev->curr_resync;
-		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+		sysfs_notify_dirent_safe(mddev->sysfs_completed);
 	}
 	mddev->pers->sync_request(mddev, max_sectors, &skipped);
 
@@ -9007,7 +9059,7 @@ static int remove_and_add_spares(struct mddev *mddev,
 	}
 
 	if (removed && mddev->kobj.sd)
-		sysfs_notify(&mddev->kobj, NULL, "degraded");
+		sysfs_notify_dirent_safe(mddev->sysfs_degraded);
 
 	if (this && removed)
 		goto no_add;
@@ -9290,8 +9342,7 @@ void md_reap_sync_thread(struct mddev *mddev)
 		/* success...*/
 		/* activate any spares */
 		if (mddev->pers->spare_active(mddev)) {
-			sysfs_notify(&mddev->kobj, NULL,
-				     "degraded");
+			sysfs_notify_dirent_safe(mddev->sysfs_degraded);
 			set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		}
 	}
@@ -9381,8 +9432,7 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 	if (rv == 0) {
 		/* Make sure they get written out promptly */
 		if (test_bit(ExternalBbl, &rdev->flags))
-			sysfs_notify(&rdev->kobj, NULL,
-				     "unacknowledged_bad_blocks");
+			sysfs_notify_dirent_safe(rdev->sysfs_unack_badblocks);
 		sysfs_notify_dirent_safe(rdev->sysfs_state);
 		set_mask_bits(&mddev->sb_flags, 0,
 			      BIT(MD_SB_CHANGE_CLEAN) | BIT(MD_SB_CHANGE_PENDING));
@@ -9403,7 +9453,7 @@ int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 		s += rdev->data_offset;
 	rv = badblocks_clear(&rdev->badblocks, s, sectors);
 	if ((rv == 0) && test_bit(ExternalBbl, &rdev->flags))
-		sysfs_notify(&rdev->kobj, NULL, "bad_blocks");
+		sysfs_notify_dirent_safe(rdev->sysfs_badblocks);
 	return rv;
 }
 EXPORT_SYMBOL_GPL(rdev_clear_badblocks);
@@ -9633,7 +9683,7 @@ static int read_rdev(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->recovery_offset == MaxSector &&
 	    !test_bit(In_sync, &rdev->flags) &&
 	    mddev->pers->spare_active(mddev))
-		sysfs_notify(&mddev->kobj, NULL, "degraded");
+		sysfs_notify_dirent_safe(mddev->sysfs_degraded);
 
 	put_page(swapout);
 	return 0;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index e2f1ad9afc48..f79b5b4101ef 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -126,7 +126,10 @@ struct md_rdev {
 
 	struct kernfs_node *sysfs_state; /* handle for 'state'
 					   * sysfs entry */
-
+	/* handle for 'unacknowledged_bad_blocks' sysfs dentry */
+	struct kernfs_node *sysfs_unack_badblocks;
+	/* handle for 'bad_blocks' sysfs dentry */
+	struct kernfs_node *sysfs_badblocks;
 	struct badblocks badblocks;
 
 	struct {
@@ -420,6 +423,9 @@ struct mddev {
 							 * file in sysfs.
 							 */
 	struct kernfs_node		*sysfs_action;  /* handle for 'sync_action' */
+	struct kernfs_node		*sysfs_completed;	/*handle for 'sync_completed' */
+	struct kernfs_node		*sysfs_degraded;	/*handle for 'degraded' */
+	struct kernfs_node		*sysfs_level;		/*handle for 'level' */
 
 	struct work_struct del_work;	/* used for delayed sysfs removal */
 
@@ -481,6 +487,7 @@ struct mddev {
 	struct bio_set			sync_set; /* for sync operations like
 						   * metadata and bitmap writes
 						   */
+	mempool_t			md_io_pool;
 
 	/* Generic flush handling.
 	 * The last to finish preflush schedules a worker to submit
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 353288bc4cb7..b1d0c9d4ef77 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4429,7 +4429,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 			sector_nr = conf->reshape_progress;
 		if (sector_nr) {
 			mddev->curr_resync_completed = sector_nr;
-			sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+			sysfs_notify_dirent_safe(mddev->sysfs_completed);
 			*skipped = 1;
 			return sector_nr;
 		}
diff --git a/drivers/md/raid5-c