Merge tag 'for-5.9/drivers-20200803' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - NVMe:
      - ZNS support (Aravind, Keith, Matias, Niklas)
      - Misc cleanups, optimizations, fixes (Baolin, Chaitanya, David,
        Dongli, Max, Sagi)

 - null_blk zone capacity support (Aravind)

 - MD:
      - raid5/6 fixes (ChangSyun)
      - Warning fixes (Damien)
      - raid5 stripe fixes (Guoqing, Song, Yufen)
      - sysfs deadlock fix (Junxiao)
      - raid10 deadlock fix (Vitaly)

 - struct_size conversions (Gustavo)

 - Set of bcache updates/fixes (Coly)

* tag 'for-5.9/drivers-20200803' of git://git.kernel.dk/linux-block: (117 commits)
  md/raid5: Allow degraded raid6 to do rmw
  md/raid5: Fix Force reconstruct-write io stuck in degraded raid5
  raid5: don't duplicate code for different paths in handle_stripe
  raid5-cache: hold spinlock instead of mutex in r5c_journal_mode_show
  md: print errno in super_written
  md/raid5: remove the redundant setting of STRIPE_HANDLE
  md: register new md sysfs file 'uuid' read-only
  md: fix max sectors calculation for super 1.0
  nvme-loop: remove extra variable in create ctrl
  nvme-loop: set ctrl state connecting after init
  nvme-multipath: do not fall back to __nvme_find_path() for non-optimized paths
  nvme-multipath: fix logic for non-optimized paths
  nvme-rdma: fix controller reset hang during traffic
  nvme-tcp: fix controller reset hang during traffic
  nvmet: introduce the passthru Kconfig option
  nvmet: introduce the passthru configfs interface
  nvmet: Add passthru enable/disable helpers
  nvmet: add passthru code to process commands
  nvme: export nvme_find_get_ns() and nvme_put_ns()
  nvme: introduce nvme_ctrl_get_by_path()
  ...

70 files changed, 3149 insertions, 826 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/admin-guide/md.rst b/Documentation/admin-guide/md.rst
index d973d469ffc4..cc8781b96b4d 100644
--- a/Documentation/admin-guide/md.rst
+++ b/Documentation/admin-guide/md.rst
@@ -426,6 +426,10 @@ All md devices contain:
      The accepted values when writing to this file are ``ppl`` and ``resync``,
      used to enable and disable PPL.
 
+  uuid
+     This indicates the UUID of the array in the following format:
+     xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
+
 
 As component devices are added to an md array, they appear in the ``md``
 directory as new directories named::
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/acpi/property.c b/drivers/acpi/property.c
index 6941062272e0..d04de10a63e4 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -45,6 +45,9 @@ static const guid_t prp_guids[] = {
 	/* Thunderbolt GUID for WAKE_SUPPORTED: 6c501103-c189-4296-ba72-9bf5a26ebe5d */
 	GUID_INIT(0x6c501103, 0xc189, 0x4296,
 		  0xba, 0x72, 0x9b, 0xf5, 0xa2, 0x6e, 0xbe, 0x5d),
+	/* Storage device needs D3 GUID: 5025030f-842f-4ab4-a561-99a5189762d0 */
+	GUID_INIT(0x5025030f, 0x842f, 0x4ab4,
+		  0xa5, 0x61, 0x99, 0xa5, 0x18, 0x97, 0x62, 0xd0),
 };
 
 /* ACPI _DSD data subnodes GUID: dbb8e3e6-5886-4ba6-8795-1319f52a966b */
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/bcache/Kconfig b/drivers/md/bcache/Kconfig
index bf7dd96db9b3..d1ca4d059c20 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -27,7 +27,7 @@ config BCACHE_CLOSURES_DEBUG
 	interface to list them, which makes it possible to see asynchronous
 	operations that get stuck.
 
-config BCACHE_ASYNC_REGISTRAION
+config BCACHE_ASYNC_REGISTRATION
 	bool "Asynchronous device registration (EXPERIMENTAL)"
 	depends on BCACHE
 	help
diff --git a/drivers/md/bcache/Makefile b/drivers/md/bcache/Makefile
index fd714628da6a..5b87e59676b8 100644
--- a/drivers/md/bcache/Makefile
+++ b/drivers/md/bcache/Makefile
@@ -4,4 +4,4 @@ obj-$(CONFIG_BCACHE)	+= bcache.o
 
 bcache-y		:= alloc.o bset.o btree.o closure.o debug.o extents.o\
 	io.o journal.o movinggc.o request.o stats.o super.o sysfs.o trace.o\
-	util.o writeback.o
+	util.o writeback.o features.o
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index a1df0d95151c..52035a78d836 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -87,7 +87,7 @@ void bch_rescale_priorities(struct cache_set *c, int sectors)
 {
 	struct cache *ca;
 	struct bucket *b;
-	unsigned int next = c->nbuckets * c->sb.bucket_size / 1024;
+	unsigned long next = c->nbuckets * c->sb.bucket_size / 1024;
 	unsigned int i;
 	int r;
 
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 3c708e8b5e2d..4fd03d2496d8 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -264,7 +264,7 @@ struct bcache_device {
 #define BCACHE_DEV_UNLINK_DONE		2
 #define BCACHE_DEV_WB_RUNNING		3
 #define BCACHE_DEV_RATE_DW_RUNNING	4
-	unsigned int		nr_stripes;
+	int			nr_stripes;
 	unsigned int		stripe_size;
 	atomic_t		*stripe_sectors_dirty;
 	unsigned long		*full_dirty_stripes;
@@ -762,11 +762,32 @@ struct bbio {
 #define bucket_bytes(c)		((c)->sb.bucket_size << 9)
 #define block_bytes(c)		((c)->sb.block_size << 9)
 
-#define prios_per_bucket(c)				\
-	((bucket_bytes(c) - sizeof(struct prio_set)) /	\
+static inline unsigned int meta_bucket_pages(struct cache_sb *sb)
+{
+	unsigned int n, max_pages;
+
+	max_pages = min_t(unsigned int,
+			  __rounddown_pow_of_two(USHRT_MAX) / PAGE_SECTORS,
+			  MAX_ORDER_NR_PAGES);
+
+	n = sb->bucket_size / PAGE_SECTORS;
+	if (n > max_pages)
+		n = max_pages;
+
+	return n;
+}
+
+static inline unsigned int meta_bucket_bytes(struct cache_sb *sb)
+{
+	return meta_bucket_pages(sb) << PAGE_SHIFT;
+}
+
+#define prios_per_bucket(ca)						\
+	((meta_bucket_bytes(&(ca)->sb) - sizeof(struct prio_set)) /	\
 	 sizeof(struct bucket_disk))
-#define prio_buckets(c)					\
-	DIV_ROUND_UP((size_t) (c)->sb.nbuckets, prios_per_bucket(c))
+
+#define prio_buckets(ca)						\
+	DIV_ROUND_UP((size_t) (ca)->sb.nbuckets, prios_per_bucket(ca))
 
 static inline size_t sector_to_bucket(struct cache_set *c, sector_t s)
 {
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 4995fcaefe29..67a2c47f4201 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -322,7 +322,7 @@ int bch_btree_keys_alloc(struct btree_keys *b,
 
 	b->page_order = page_order;
 
-	t->data = (void *) __get_free_pages(gfp, b->page_order);
+	t->data = (void *) __get_free_pages(__GFP_COMP|gfp, b->page_order);
 	if (!t->data)
 		goto err;
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index d5c51e332046..3d8bd0692af3 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -738,7 +738,7 @@ void bch_btree_cache_free(struct cache_set *c)
 	if (c->verify_data)
 		list_move(&c->verify_data->list, &c->btree_cache);
 
-	free_pages((unsigned long) c->verify_ondisk, ilog2(bucket_pages(c)));<