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
  ...

Author: axboe

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 <[email protected]>
+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 <[email protected]>
+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 <[email protected]>

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

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"

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;
 }
 

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;

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 */

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;
 }

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:

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);

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);