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
  ...

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>

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,
+			dma_free_coherent(&card->dev->dev,
-					    card->ctrl[i].status.buf,
+					  STATUS_BUFFER_SIZE8,
-					    card->ctrl[i].status.dma_addr);
+					  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,
+			dma_free_coherent(&card->dev->dev,
-					    card->ctrl[i].cmd.buf,
+					  COMMAND_BUFFER_SIZE8,
-					    card->ctrl[i].cmd.dma_addr);
+					  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,
+			dma_free_coherent(&card->dev->dev,
-					STATUS_BUFFER_SIZE8,
+					  STATUS_BUFFER_SIZE8,
-					card->ctrl[i].status.buf,
+					  card->ctrl[i].status.buf,
-					card->ctrl[i].status.dma_addr);
+					  card->ctrl[i].status.dma_addr);
 		if (card->ctrl[i].cmd.buf)
-			pci_free_consistent(card->dev,
+			dma_free_coherent(&card->dev->dev,
-					COMMAND_BUFFER_SIZE8,
+					  COMMAND_BUFFER_SIZE8,
-					card->ctrl[i].cmd.buf,
+					  card->ctrl[i].cmd.buf,
-					card->ctrl[i].cmd.dma_addr);
+					  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);
 

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;
 	}
 }
 

drivers/md/md.c

@@ -463,12 +463,38 @@ 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 (mddev == NULL || mddev->pers == NULL) {
+		bio_io_error(bio);
+		return BLK_QC_T_NONE;
+	}
 
 	if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) {
 		bio_io_error(bio);
@@ -477,10 +503,6 @@ static blk_qc_t md_submit_bio(struct bio *bio)
 
 	blk_queue_split(&bio);
 
-	if (mddev == NULL || mddev->pers == NULL) {
-		bio_io_error(bio);
-		return BLK_QC_T_NONE;
-	}
 	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;
 	}
 
-	/*
+	if (bio->bi_end_io != md_end_io) {
-	 * save the sectors now since our bio can
+		struct md_io *md_io;
-	 * go away inside make_request
+
-	 */
+		md_io = mempool_alloc(&mddev->md_io_pool, GFP_NOIO);
-	sectors = bio_sectors(bio);
+		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,
+			sysfs_notify_dirent_safe(mddev->sysfs_degraded);
-				     "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,
+			sysfs_notify_dirent_safe(rdev->sysfs_unack_badblocks);
-				     "unacknowledged_bad_blocks");
 		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;

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

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;
 		}

drivers/md/raid5-cache.c

@@ -2430,10 +2430,15 @@ static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
 	struct mddev *mddev = log->rdev->mddev;
 	struct r5conf *conf = mddev->private;
 	struct stripe_head *sh, *next;
+	bool cleared_pending = false;
 
 	if (ctx->data_only_stripes == 0)
 		return;
 
+	if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
+		cleared_pending = true;
+		clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
+	}
 	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_BACK;
 
 	list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
@@ -2448,6 +2453,8 @@ static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
 		   atomic_read(&conf->active_stripes) == 0);
 
 	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
+	if (cleared_pending)
+		set_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
 }
 
 static int r5l_recovery_log(struct r5l_log *log)

drivers/md/raid5.c

@@ -5777,7 +5777,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 		sector_div(sector_nr, new_data_disks);
 		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;
 			retn = sector_nr;
 			goto finish;
@@ -5891,7 +5891,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 		conf->reshape_safe = mddev->reshape_position;
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
-		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+		sysfs_notify_dirent_safe(mddev->sysfs_completed);
 	}
 
 	INIT_LIST_HEAD(&stripes);
@@ -5998,7 +5998,7 @@ finish:
 		conf->reshape_safe = mddev->reshape_position;
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
-		sysfs_notify(&mddev->kobj, NULL, "sync_completed");
+		sysfs_notify_dirent_safe(mddev->sysfs_completed);
 	}
 ret:
 	return retn;

drivers/nvme/host/Makefile

@@ -13,6 +13,7 @@ nvme-core-y				:= core.o
 nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
 nvme-core-$(CONFIG_NVM)			+= lightnvm.o
+nvme-core-$(CONFIG_BLK_DEV_ZONED)	+= zns.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
 nvme-core-$(CONFIG_NVME_HWMON)		+= hwmon.o
 

drivers/nvme/host/core.c

@@ -89,7 +89,7 @@ static dev_t nvme_chr_devt;
 static struct class *nvme_class;
 static struct class *nvme_subsys_class;
 
-static int nvme_revalidate_disk(struct gendisk *disk);
+static int _nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
@@ -100,7 +100,7 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
 	 * Revalidating a dead namespace sets capacity to 0. This will end
 	 * buffered writers dirtying pages that can't be synced.
 	 */
-	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+	if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
 		return;
 	blk_set_queue_dying(ns->queue);
 	/* Forcibly unquiesce queues to avoid blocking dispatch */
@@ -287,6 +287,10 @@ void nvme_complete_rq(struct request *req)
 			nvme_retry_req(req);
 			return;
 		}
+	} else if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+		   req_op(req) == REQ_OP_ZONE_APPEND) {
+		req->__sector = nvme_lba_to_sect(req->q->queuedata,
+			le64_to_cpu(nvme_req(req)->result.u64));
 	}
 
 	nvme_trace_bio_complete(req, status);
@@ -555,7 +559,7 @@ static int nvme_configure_directives(struct nvme_ctrl *ctrl)
 		goto out_disable_stream;
 	}
 
-	ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
+	ctrl->nr_streams = min_t(u16, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
 	dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
 	return 0;
 
@@ -673,7 +677,8 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 }
 
 static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
-		struct request *req, struct nvme_command *cmnd)
+		struct request *req, struct nvme_command *cmnd,
+		enum nvme_opcode op)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	u16 control = 0;
@@ -687,7 +692,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	if (req->cmd_flags & REQ_RAHEAD)
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
-	cmnd->rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
+	cmnd->rw.opcode = op;
 	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
 	cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
 	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
@@ -716,6 +721,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
+			if (op == nvme_cmd_zone_append)
+				control |= NVME_RW_APPEND_PIREMAP;
 			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 			break;
 		}
@@ -756,6 +763,19 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 	case REQ_OP_FLUSH:
 		nvme_setup_flush(ns, cmd);
 		break;
+	case REQ_OP_ZONE_RESET_ALL:
+	case REQ_OP_ZONE_RESET:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_RESET);
+		break;
+	case REQ_OP_ZONE_OPEN:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_OPEN);
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_CLOSE);
+		break;
+	case REQ_OP_ZONE_FINISH:
+		ret = nvme_setup_zone_mgmt_send(ns, req, cmd, NVME_ZONE_FINISH);
+		break;
 	case REQ_OP_WRITE_ZEROES:
 		ret = nvme_setup_write_zeroes(ns, req, cmd);
 		break;
@@ -763,8 +783,13 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		ret = nvme_setup_discard(ns, req, cmd);
 		break;
 	case REQ_OP_READ:
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_read);
+		break;
 	case REQ_OP_WRITE:
-		ret = nvme_setup_rw(ns, req, cmd);
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_write);
+		break;
+	case REQ_OP_ZONE_APPEND:
+		ret = nvme_setup_rw(ns, req, cmd, nvme_cmd_zone_append);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1056,8 +1081,13 @@ static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
 	return error;
 }
 
+static bool nvme_multi_css(struct nvme_ctrl *ctrl)
+{
+	return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
+}
+
 static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
-		struct nvme_ns_id_desc *cur)
+		struct nvme_ns_id_desc *cur, bool *csi_seen)
 {
 	const char *warn_str = "ctrl returned bogus length:";
 	void *data = cur;
@@ -1087,6 +1117,15 @@ static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
 		}
 		uuid_copy(&ids->uuid, data + sizeof(*cur));
 		return NVME_NIDT_UUID_LEN;
+	case NVME_NIDT_CSI:
+		if (cur->nidl != NVME_NIDT_CSI_LEN) {
+			dev_warn(ctrl->device, "%s %d for NVME_NIDT_CSI\n",
+				 warn_str, cur->nidl);
+			return -1;
+		}
+		memcpy(&ids->csi, data + sizeof(*cur), NVME_NIDT_CSI_LEN);
+		*csi_seen = true;
+		return NVME_NIDT_CSI_LEN;
 	default:
 		/* Skip unknown types */
 		return cur->nidl;
@@ -1097,10 +1136,9 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		struct nvme_ns_ids *ids)
 {
 	struct nvme_command c = { };
-	int status;
+	bool csi_seen = false;
+	int status, pos, len;
 	void *data;
-	int pos;
-	int len;
 
 	c.identify.opcode = nvme_admin_identify;
 	c.identify.nsid = cpu_to_le32(nsid);
@@ -1125,7 +1163,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		  * device just because of a temporal retry-able error (such
 		  * as path of transport errors).
 		  */
-		if (status > 0 && (status & NVME_SC_DNR))
+		if (status > 0 && (status & NVME_SC_DNR) && !nvme_multi_css(ctrl))
 			status = 0;
 		goto free_data;
 	}
@@ -1136,12 +1174,19 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid,
 		if (cur->nidl == 0)
 			break;
 
-		len = nvme_process_ns_desc(ctrl, ids, cur);
+		len = nvme_process_ns_desc(ctrl, ids, cur, &csi_seen);
 		if (len < 0)
-			goto free_data;
+			break;
 
 		len += sizeof(*cur);
 	}
+
+	if (nvme_multi_css(ctrl) && !csi_seen) {
+		dev_warn(ctrl->device, "Command set not reported for nsid:%d\n",
+			 nsid);
+		status = -EINVAL;
+	}
+
 free_data:
 	kfree(data);
 	return status;
@@ -1350,8 +1395,8 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	u32 effects = 0;
 
 	if (ns) {
-		if (ctrl->effects)
+		if (ns->head->effects)
-			effects = le32_to_cpu(ctrl->effects->iocs[opcode]);
+			effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
 		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
 			dev_warn(ctrl->device,
 				 "IO command:%02x has unhandled effects:%08x\n",
@@ -1378,14 +1423,23 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return effects;
 }
 
-static void nvme_update_formats(struct nvme_ctrl *ctrl)
+static void nvme_update_formats(struct nvme_ctrl *ctrl, u32 *effects)
 {
 	struct nvme_ns *ns;
 
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list)
-		if (ns->disk && nvme_revalidate_disk(ns->disk))
+		if (_nvme_revalidate_disk(ns->disk))
 			nvme_set_queue_dying(ns);
+		else if (blk_queue_is_zoned(ns->disk->queue)) {
+			/*
+			 * IO commands are required to fully revalidate a zoned
+			 * device. Force the command effects to trigger rescan
+			 * work so report zones can run in a context with
+			 * unfrozen IO queues.
+			 */
+			*effects |= NVME_CMD_EFFECTS_NCC;
+		}
 	up_read(&ctrl->namespaces_rwsem);
 }
 
@@ -1397,7 +1451,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 	 * this command.
 	 */
 	if (effects & NVME_CMD_EFFECTS_LBCC)
-		nvme_update_formats(ctrl);
+		nvme_update_formats(ctrl, &effects);
 	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
 		nvme_unfreeze(ctrl);
 		nvme_mpath_unfreeze(ctrl->subsys);
@@ -1512,7 +1566,7 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
  * Issue ioctl requests on the first available path.  Note that unlike normal
  * block layer requests we will not retry failed request on another controller.
  */
-static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
+struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 		struct nvme_ns_head **head, int *srcu_idx)
 {
 #ifdef CONFIG_NVME_MULTIPATH
@@ -1532,7 +1586,7 @@ static struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
 	return disk->private_data;
 }
 
-static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
+void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 {
 	if (head)
 		srcu_read_unlock(&head->srcu, idx);
@@ -1798,7 +1852,7 @@ static int nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid,
 		memcpy(ids->eui64, id->eui64, sizeof(id->eui64));
 	if (ctrl->vs >= NVME_VS(1, 2, 0))
 		memcpy(ids->nguid, id->nguid, sizeof(id->nguid));
-	if (ctrl->vs >= NVME_VS(1, 3, 0))
+	if (ctrl->vs >= NVME_VS(1, 3, 0) || nvme_multi_css(ctrl))
 		return nvme_identify_ns_descs(ctrl, nsid, ids);
 	return 0;
 }
@@ -1814,7 +1868,8 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b)
 {
 	return uuid_equal(&a->uuid, &b->uuid) &&
 		memcmp(&a->nguid, &b->nguid, sizeof(a->nguid)) == 0 &&
-		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0;
+		memcmp(&a->eui64, &b->eui64, sizeof(a->eui64)) == 0 &&
+		a->csi == b->csi;
 }
 
 static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
@@ -1924,18 +1979,38 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
+	unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_ctrl *ctrl = ns->ctrl;
+	int ret;
 	u32 iob;
 
 	/*
 	 * If identify namespace failed, use default 512 byte block size so
 	 * block layer can use before failing read/write for 0 capacity.
 	 */
-	ns->lba_shift = id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ds;
+	ns->lba_shift = id->lbaf[lbaf].ds;
 	if (ns->lba_shift == 0)
 		ns->lba_shift = 9;
 
+	switch (ns->head->ids.csi) {
+	case NVME_CSI_NVM:
+		break;
+	case NVME_CSI_ZNS:
+		ret = nvme_update_zone_info(disk, ns, lbaf);
+		if (ret) {
+			dev_warn(ctrl->device,
+				"failed to add zoned namespace:%u ret:%d\n",
+				ns->head->ns_id, ret);
+			return ret;
+		}
+		break;
+	default:
+		dev_warn(ctrl->device, "unknown csi:%u ns:%u\n",
+			ns->head->ids.csi, ns->head->ns_id);
+		return -ENODEV;
+	}
+
 	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
 	    is_power_of_2(ctrl->max_hw_sectors))
 		iob = ctrl->max_hw_sectors;
@@ -1943,7 +2018,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
 
 	ns->features = 0;
-	ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
 	/* the PI implementation requires metadata equal t10 pi tuple size */
 	if (ns->ms == sizeof(struct t10_pi_tuple))
 		ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
@@ -1986,7 +2061,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	return 0;
 }
 
-static int nvme_revalidate_disk(struct gendisk *disk)
+static int _nvme_revalidate_disk(struct gendisk *disk)
 {
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_ctrl *ctrl = ns->ctrl;
@@ -2034,6 +2109,28 @@ out:
 	return ret;
 }
 
+static int nvme_revalidate_disk(struct gendisk *disk)
+{
+	int ret;
+
+	ret = _nvme_revalidate_disk(disk);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	if (blk_queue_is_zoned(disk->queue)) {
+		struct nvme_ns *ns = disk->private_data;
+		struct nvme_ctrl *ctrl = ns->ctrl;
+
+		ret = blk_revalidate_disk_zones(disk, NULL);
+		if (!ret)
+			blk_queue_max_zone_append_sectors(disk->queue,
+							  ctrl->max_zone_append);
+	}
+#endif
+	return ret;
+}
+
 static char nvme_pr_type(enum pr_type type)
 {
 	switch (type) {
@@ -2164,6 +2261,7 @@ static const struct block_device_operations nvme_fops = {
 	.release	= nvme_release,
 	.getgeo		= nvme_getgeo,
 	.revalidate_disk= nvme_revalidate_disk,
+	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 
@@ -2190,6 +2288,7 @@ const struct block_device_operations nvme_ns_head_ops = {
 	.ioctl		= nvme_ioctl,
 	.compat_ioctl	= nvme_compat_ioctl,
 	.getgeo		= nvme_getgeo,
+	.report_zones	= nvme_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 #endif /* CONFIG_NVME_MULTIPATH */
@@ -2271,7 +2370,10 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 
 	ctrl->page_size = 1 << page_shift;
 
-	ctrl->ctrl_config = NVME_CC_CSS_NVM;
+	if (NVME_CAP_CSS(ctrl->cap) & NVME_CAP_CSS_CSI)
+		ctrl->ctrl_config = NVME_CC_CSS_CSI;
+	else
+		ctrl->ctrl_config = NVME_CC_CSS_NVM;
 	ctrl->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
 	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
 	ctrl->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
@@ -2819,7 +2921,7 @@ out_unlock:
 	return ret;
 }
 
-int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
@@ -2833,27 +2935,55 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
 	c.get_log_page.lpou = cpu_to_le32(upper_32_bits(offset));
+	c.get_log_page.csi = csi;
 
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
+static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
 {
+	struct nvme_cel *cel, *ret = NULL;
+
+	spin_lock(&ctrl->lock);
+	list_for_each_entry(cel, &ctrl->cels, entry) {
+		if (cel->csi == csi) {
+			ret = cel;
+			break;
+		}
+	}
+	spin_unlock(&ctrl->lock);
+
+	return ret;
+}
+
+static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
+				struct nvme_effects_log **log)
+{
+	struct nvme_cel *cel = nvme_find_cel(ctrl, csi);
 	int ret;
 
-	if (!ctrl->effects)
+	if (cel)
-		ctrl->effects = kzalloc(sizeof(*ctrl->effects), GFP_KERNEL);
+		goto out;
 
-	if (!ctrl->effects)
+	cel = kzalloc(sizeof(*cel), GFP_KERNEL);
-		return 0;
+	if (!cel)
+		return -ENOMEM;
 
-	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
+	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0, csi,
-			ctrl->effects, sizeof(*ctrl->effects), 0);
+			&cel->log, sizeof(cel->log), 0);
 	if (ret) {
-		kfree(ctrl->effects);
+		kfree(cel);
-		ctrl->effects = NULL;
+		return ret;
 	}
-	return ret;
+
+	cel->csi = csi;
+
+	spin_lock(&ctrl->lock);
+	list_add_tail(&cel->entry, &ctrl->cels);
+	spin_unlock(&ctrl->lock);
+out:
+	*log = &cel->log;
+	return 0;
 }
 
 /*
@@ -2874,7 +3004,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		return ret;
 	}
 	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
-	ctrl->sqsize = min_t(int, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
+	ctrl->sqsize = min_t(u16, NVME_CAP_MQES(ctrl->cap), ctrl->sqsize);
 
 	if (ctrl->vs >= NVME_VS(1, 1, 0))
 		ctrl->subsystem = NVME_CAP_NSSRC(ctrl->cap);
@@ -2886,7 +3016,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	}
 
 	if (id->lpa & NVME_CTRL_LPA_CMD_EFFECTS_LOG) {
-		ret = nvme_get_effects_log(ctrl);
+		ret = nvme_get_effects_log(ctrl, NVME_CSI_NVM, &ctrl->effects);
 		if (ret < 0)
 			goto out_free;
 	}
@@ -2948,7 +3078,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 
 	if (id->rtd3e) {
 		/* us -> s */
-		u32 transition_time = le32_to_cpu(id->rtd3e) / 1000000;
+		u32 transition_time = le32_to_cpu(id->rtd3e) / USEC_PER_SEC;
 
 		ctrl->shutdown_timeout = clamp_t(unsigned int, transition_time,
 						 shutdown_timeout, 60);
@@ -3406,6 +3536,66 @@ static ssize_t nvme_sysfs_show_address(struct device *dev,
 }
 static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL);
 
+static ssize_t nvme_ctrl_loss_tmo_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+
+	if (ctrl->opts->max_reconnects == -1)
+		return sprintf(buf, "off\n");
+	return sprintf(buf, "%d\n",
+			opts->max_reconnects * opts->reconnect_delay);
+}
+
+static ssize_t nvme_ctrl_loss_tmo_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	struct nvmf_ctrl_options *opts = ctrl->opts;
+	int ctrl_loss_tmo, err;
+
+	err = kstrtoint(buf, 10, &ctrl_loss_tmo);
+	if (err)
+		return -EINVAL;
+
+	else if (ctrl_loss_tmo < 0)
+		opts->max_reconnects = -1;
+	else
+		opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
+						opts->reconnect_delay);
+	return count;
+}
+static DEVICE_ATTR(ctrl_loss_tmo, S_IRUGO | S_IWUSR,
+	nvme_ctrl_loss_tmo_show, nvme_ctrl_loss_tmo_store);
+
+static ssize_t nvme_ctrl_reconnect_delay_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+
+	if (ctrl->opts->reconnect_delay == -1)
+		return sprintf(buf, "off\n");
+	return sprintf(buf, "%d\n", ctrl->opts->reconnect_delay);
+}
+
+static ssize_t nvme_ctrl_reconnect_delay_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
+	unsigned int v;
+	int err;
+
+	err = kstrtou32(buf, 10, &v);
+	if (err || v > UINT_MAX)
+		return -EINVAL;
+
+	ctrl->opts->reconnect_delay = v;
+	return count;
+}
+static DEVICE_ATTR(reconnect_delay, S_IRUGO | S_IWUSR,
+	nvme_ctrl_reconnect_delay_show, nvme_ctrl_reconnect_delay_store);
+
 static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_reset_controller.attr,
 	&dev_attr_rescan_controller.attr,
@@ -3423,6 +3613,8 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_sqsize.attr,
 	&dev_attr_hostnqn.attr,
 	&dev_attr_hostid.attr,
+	&dev_attr_ctrl_loss_tmo.attr,
+	&dev_attr_reconnect_delay.attr,
 	NULL
 };
 
@@ -3519,6 +3711,13 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 		goto out_cleanup_srcu;
 	}
 
+	if (head->ids.csi) {
+		ret = nvme_get_effects_log(ctrl, head->ids.csi, &head->effects);
+		if (ret)
+			goto out_cleanup_srcu;
+	} else
+		head->effects = ctrl->effects;
+
 	ret = nvme_mpath_alloc_disk(ctrl, head);
 	if (ret)
 		goto out_cleanup_srcu;
@@ -3735,7 +3934,7 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	nvme_mpath_clear_current_path(ns);
 	synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
 
-	if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
+	if (ns->disk->flags & GENHD_FL_UP) {
 		del_gendisk(ns->disk);
 		blk_cleanup_queue(ns->queue);
 		if (blk_get_integrity(ns->disk))
@@ -3766,7 +3965,7 @@ static void nvme_validate_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	ns = nvme_find_get_ns(ctrl, nsid);
 	if (ns) {
-		if (ns->disk && revalidate_disk(ns->disk))
+		if (revalidate_disk(ns->disk))
 			nvme_ns_remove(ns);
 		nvme_put_ns(ns);
 	} else
@@ -3859,8 +4058,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0,
-			log_size, 0);
+			NVME_CSI_NVM, log, log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -4004,8 +4203,8 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, log,
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_FW_SLOT, 0, NVME_CSI_NVM,
-			sizeof(*log), 0))
+			log, sizeof(*log), 0))
 		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
@@ -4142,11 +4341,16 @@ static void nvme_free_ctrl(struct device *dev)
 	struct nvme_ctrl *ctrl =
 		container_of(dev, struct nvme_ctrl, ctrl_device);
 	struct nvme_subsystem *subsys = ctrl->subsys;
+	struct nvme_cel *cel, *next;
 
 	if (subsys && ctrl->instance != subsys->instance)
 		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 
-	kfree(ctrl->effects);
+	list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
+		list_del(&cel->entry);
+		kfree(cel);
+	}
+
 	nvme_mpath_uninit(ctrl);
 	__free_page(ctrl->discard_page);
 
@@ -4177,6 +4381,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
+	INIT_LIST_HEAD(&ctrl->cels);
 	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->dev = dev;
 	ctrl->ops = ops;
@@ -4373,6 +4578,8 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ns_zns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl_zns) != NVME_IDENTIFY_DATA_SIZE);
 	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
 	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
 	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);

drivers/nvme/host/hwmon.c

@@ -62,7 +62,7 @@ static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
 	int ret;
 
 	ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
-			   &data->log, sizeof(data->log), 0);
+			   NVME_CSI_NVM, &data->log, sizeof(data->log), 0);
 
 	return ret <= 0 ? ret : -EIO;
 }

drivers/nvme/host/lightnvm.c

@@ -593,8 +593,8 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 		dev_meta_off = dev_meta;
 
 		ret = nvme_get_log(ctrl, ns->head->ns_id,
-				NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
+				NVME_NVM_LOG_REPORT_CHUNK, 0, NVME_CSI_NVM,
-				offset);
+				dev_meta, len, offset);
 		if (ret) {
 			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
 			break;

drivers/nvme/host/multipath.c

@@ -527,7 +527,7 @@ static int nvme_read_ana_log(struct nvme_ctrl *ctrl)
 	int error;
 
 	mutex_lock(&ctrl->ana_lock);
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0,
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0, NVME_CSI_NVM,
 			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
 	if (error) {
 		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);

drivers/nvme/host/nvme.h

@@ -191,6 +191,12 @@ struct nvme_fault_inject {
 #endif
 };
 
+struct nvme_cel {
+	struct list_head	entry;
+	struct nvme_effects_log	log;
+	u8			csi;
+};
+
 struct nvme_ctrl {
 	bool comp_seen;
 	enum nvme_ctrl_state state;
@@ -232,6 +238,9 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u32 max_segments;
 	u32 max_integrity_segments;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u32 max_zone_append;
+#endif
 	u16 crdt[3];
 	u16 oncs;
 	u16 oacs;
@@ -257,6 +266,7 @@ struct nvme_ctrl {
 	unsigned long quirks;
 	struct nvme_id_power_state psd[32];
 	struct nvme_effects_log *effects;
+	struct list_head cels;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
@@ -339,6 +349,7 @@ struct nvme_ns_ids {
 	u8	eui64[8];
 	u8	nguid[16];
 	uuid_t	uuid;
+	u8	csi;
 };
 
 /*
@@ -358,6 +369,7 @@ struct nvme_ns_head {
 	struct kref		ref;
 	bool			shared;
 	int			instance;
+	struct nvme_effects_log *effects;
 #ifdef CONFIG_NVME_MULTIPATH
 	struct gendisk		*disk;
 	struct bio_list		requeue_list;
@@ -395,6 +407,9 @@ struct nvme_ns {
 	u16 sgs;
 	u32 sws;
 	u8 pi_type;
+#ifdef CONFIG_BLK_DEV_ZONED
+	u64 zsze;
+#endif
 	unsigned long features;
 	unsigned long flags;
 #define NVME_NS_REMOVING	0
@@ -560,8 +575,11 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 
-int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 		void *log, size_t size, u64 offset);
+struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
+		struct nvme_ns_head **head, int *srcu_idx);
+void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx);
 
 extern const struct attribute_group *nvme_ns_id_attr_groups[];
 extern const struct block_device_operations nvme_ns_head_ops;
@@ -697,6 +715,36 @@ static inline void nvme_mpath_update_disk_size(struct gendisk *disk)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
+#ifdef CONFIG_BLK_DEV_ZONED
+int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
+			  unsigned lbaf);
+
+int nvme_report_zones(struct gendisk *disk, sector_t sector,
+		      unsigned int nr_zones, report_zones_cb cb, void *data);
+
+blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
+				       struct nvme_command *cmnd,
+				       enum nvme_zone_mgmt_action action);
+#else
+#define nvme_report_zones NULL
+
+static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns,
+		struct request *req, struct nvme_command *cmnd,
+		enum nvme_zone_mgmt_action action)
+{
+	return BLK_STS_NOTSUPP;
+}
+
+static inline int nvme_update_zone_info(struct gendisk *disk,
+					struct nvme_ns *ns,
+					unsigned lbaf)
+{
+	dev_warn(ns->ctrl->device,
+		 "Please enable CONFIG_BLK_DEV_ZONED to support ZNS devices\n");
+	return -EPROTONOSUPPORT;
+}
+#endif
+
 #ifdef CONFIG_NVM
 int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
 void nvme_nvm_unregister(struct nvme_ns *ns);

drivers/nvme/host/pci.c

@@ -61,10 +61,10 @@ MODULE_PARM_DESC(sgl_threshold,
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
 static const struct kernel_param_ops io_queue_depth_ops = {
 	.set = io_queue_depth_set,
-	.get = param_get_int,
+	.get = param_get_uint,
 };
 
-static int io_queue_depth = 1024;
+static unsigned int io_queue_depth = 1024;
 module_param_cb(io_queue_depth, &io_queue_depth_ops, &io_queue_depth, 0644);
 MODULE_PARM_DESC(io_queue_depth, "set io queue depth, should >= 2");
 
@@ -115,7 +115,7 @@ struct nvme_dev {
 	unsigned max_qid;
 	unsigned io_queues[HCTX_MAX_TYPES];
 	unsigned int num_vecs;
-	int q_depth;
+	u16 q_depth;
 	int io_sqes;
 	u32 db_stride;
 	void __iomem *bar;
@@ -151,13 +151,14 @@ struct nvme_dev {
 
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
 {
-	int n = 0, ret;
+	int ret;
+	u16 n;
 
-	ret = kstrtoint(val, 10, &n);
+	ret = kstrtou16(val, 10, &n);
 	if (ret != 0 || n < 2)
 		return -EINVAL;
 
-	return param_set_int(val, kp);
+	return param_set_ushort(val, kp);
 }
 
 static inline unsigned int sq_idx(unsigned int qid, u32 stride)
@@ -361,7 +362,7 @@ static int nvme_pci_npages_sgl(unsigned int num_seg)
 	return DIV_ROUND_UP(num_seg * sizeof(struct nvme_sgl_desc), PAGE_SIZE);
 }
 
-static unsigned int nvme_pci_iod_alloc_size(struct nvme_dev *dev,
+static size_t nvme_pci_iod_alloc_size(struct nvme_dev *dev,
 		unsigned int size, unsigned int nseg, bool use_sgl)
 {
 	size_t alloc_size;
@@ -500,9 +501,6 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req)
 	int nseg = blk_rq_nr_phys_segments(req);
 	unsigned int avg_seg_size;
 
-	if (nseg == 0)
-		return false;
-
 	avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg);
 
 	if (!(dev->ctrl.sgls & ((1 << 0) | (1 << 1))))
@@ -764,7 +762,7 @@ static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
 	cmnd->dptr.prp1 = cpu_to_le64(iod->first_dma);
 	if (bv->bv_len > first_prp_len)
 		cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma + first_prp_len);
-	return 0;
+	return BLK_STS_OK;
 }
 
 static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
@@ -782,7 +780,7 @@ static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
 	cmnd->dptr.sgl.addr = cpu_to_le64(iod->first_dma);
 	cmnd->dptr.sgl.length = cpu_to_le32(iod->dma_len);
 	cmnd->dptr.sgl.type = NVME_SGL_FMT_DATA_DESC << 4;
-	return 0;
+	return BLK_STS_OK;
 }
 
 static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
@@ -846,7 +844,7 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
 	if (dma_mapping_error(dev->dev, iod->meta_dma))
 		return BLK_STS_IOERR;
 	cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
-	return 0;
+	return BLK_STS_OK;
 }
 
 /*
@@ -1019,6 +1017,7 @@ static irqreturn_t nvme_irq(int irq, void *data)
 static irqreturn_t nvme_irq_check(int irq, void *data)
 {
 	struct nvme_queue *nvmeq = data;
+
 	if (nvme_cqe_pending(nvmeq))
 		return IRQ_WAKE_THREAD;
 	return IRQ_NONE;
@@ -1154,7 +1153,6 @@ static void abort_endio(struct request *req, blk_status_t error)
 
 static bool nvme_should_reset(struct nvme_dev *dev, u32 csts)
 {
-
 	/* If true, indicates loss of adapter communication, possibly by a
 	 * NVMe Subsystem reset.
 	 */
@@ -1261,9 +1259,9 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	}
 
 	/*
- 	 * Shutdown the controller immediately and schedule a reset if the
+	 * Shutdown the controller immediately and schedule a reset if the
- 	 * command was already aborted once before and still hasn't been
+	 * command was already aborted once before and still hasn't been
- 	 * returned to the driver, or if this is the admin queue.
+	 * returned to the driver, or if this is the admin queue.
 	 */
 	if (!nvmeq->qid || iod->aborted) {
 		dev_warn(dev->ctrl.device,
@@ -1402,6 +1400,7 @@ static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
 
 	if (q_size_aligned * nr_io_queues > dev->cmb_size) {
 		u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
+
 		mem_per_q = round_down(mem_per_q, dev->ctrl.page_size);
 		q_depth = div_u64(mem_per_q, entry_size);
 
@@ -1932,12 +1931,12 @@ out:
 
 static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred)
 {
-	u32 chunk_size;
+	u64 min_chunk = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
+	u64 hmminds = max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
+	u64 chunk_size;
 
 	/* start big and work our way down */
-	for (chunk_size = min_t(u64, preferred, PAGE_SIZE * MAX_ORDER_NR_PAGES);
+	for (chunk_size = min_chunk; chunk_size >= hmminds; chunk_size /= 2) {
-	     chunk_size >= max_t(u32, dev->ctrl.hmminds * 4096, PAGE_SIZE * 2);
-	     chunk_size /= 2) {
 		if (!__nvme_alloc_host_mem(dev, preferred, chunk_size)) {
 			if (!min || dev->host_mem_size >= min)
 				return 0;
@@ -2003,7 +2002,7 @@ static void nvme_calc_irq_sets(struct irq_affinity *affd, unsigned int nrirqs)
 	unsigned int nr_read_queues, nr_write_queues = dev->nr_write_queues;
 
 	/*
-	 * If there is no interupt available for queues, ensure that
+	 * If there is no interrupt available for queues, ensure that
 	 * the default queue is set to 1. The affinity set size is
 	 * also set to one, but the irq core ignores it for this case.
 	 *
@@ -2261,8 +2260,8 @@ static void nvme_dev_add(struct nvme_dev *dev)
 			dev->tagset.nr_maps++;
 		dev->tagset.timeout = NVME_IO_TIMEOUT;
 		dev->tagset.numa_node = dev->ctrl.numa_node;
-		dev->tagset.queue_depth =
+		dev->tagset.queue_depth = min_t(unsigned int, dev->q_depth,
-				min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
+						BLK_MQ_MAX_DEPTH) - 1;
 		dev->tagset.cmd_size = sizeof(struct nvme_iod);
 		dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
 		dev->tagset.driver_data = dev;
@@ -2321,7 +2320,7 @@ static int nvme_pci_enable(struct nvme_dev *dev)
 
 	dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP);
 
-	dev->q_depth = min_t(int, NVME_CAP_MQES(dev->ctrl.cap) + 1,
+	dev->q_depth = min_t(u16, NVME_CAP_MQES(dev->ctrl.cap) + 1,
 				io_queue_depth);
 	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
@@ -2876,6 +2875,7 @@ static void nvme_reset_done(struct pci_dev *pdev)
 static void nvme_shutdown(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
+
 	nvme_disable_prepare_reset(dev, true);
 }
 
@@ -3006,6 +3006,7 @@ unfreeze:
 static int nvme_simple_suspend(struct device *dev)
 {
 	struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
+
 	return nvme_disable_prepare_reset(ndev, true);
 }
 
@@ -3079,16 +3080,16 @@ static const struct pci_error_handlers nvme_err_handler = {
 };
 
 static const struct pci_device_id nvme_id_table[] = {
-	{ PCI_VDEVICE(INTEL, 0x0953),
+	{ PCI_VDEVICE(INTEL, 0x0953),	/* Intel 750/P3500/P3600/P3700 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
-	{ PCI_VDEVICE(INTEL, 0x0a53),
+	{ PCI_VDEVICE(INTEL, 0x0a53),	/* Intel P3520 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
-	{ PCI_VDEVICE(INTEL, 0x0a54),
+	{ PCI_VDEVICE(INTEL, 0x0a54),	/* Intel P4500/P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
-	{ PCI_VDEVICE(INTEL, 0x0a55),
+	{ PCI_VDEVICE(INTEL, 0x0a55),	/* Dell Express Flash P4600 */
 		.driver_data = NVME_QUIRK_STRIPE_SIZE |
 				NVME_QUIRK_DEALLOCATE_ZEROES, },
 	{ PCI_VDEVICE(INTEL, 0xf1a5),	/* Intel 600P/P3100 */

drivers/nvme/host/tcp.c

@@ -46,6 +46,7 @@ struct nvme_tcp_request {
 	u32			pdu_sent;
 	u16			ttag;
 	struct list_head	entry;
+	struct llist_node	lentry;
 	__le32			ddgst;
 
 	struct bio		*curr_bio;
@@ -75,9 +76,10 @@ struct nvme_tcp_queue {
 	struct work_struct	io_work;
 	int			io_cpu;
 
-	spinlock_t		lock;
 	struct mutex		send_mutex;
+	struct llist_head	req_list;
 	struct list_head	send_list;
+	bool			more_requests;
 
 	/* recv state */
 	void			*pdu;
@@ -261,15 +263,13 @@ static inline void nvme_tcp_advance_req(struct nvme_tcp_request *req,
 }
 
 static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
-		bool sync)
+		bool sync, bool last)
 {
 	struct nvme_tcp_queue *queue = req->queue;
 	bool empty;
 
-	spin_lock(&queue->lock);
+	empty = llist_add(&req->lentry, &queue->req_list) &&
-	empty = list_empty(&queue->send_list) && !queue->request;
+		list_empty(&queue->send_list) && !queue->request;
-	list_add_tail(&req->entry, &queue->send_list);
-	spin_unlock(&queue->lock);
 
 	/*
 	 * if we're the first on the send_list and we can try to send
@@ -278,25 +278,42 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 	 */
 	if (queue->io_cpu == smp_processor_id() &&
 	    sync && empty && mutex_trylock(&queue->send_mutex)) {
+		queue->more_requests = !last;
 		nvme_tcp_try_send(queue);
+		queue->more_requests = false;
 		mutex_unlock(&queue->send_mutex);
-	} else {
+	} else if (last) {
 		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 	}
 }
 
+static void nvme_tcp_process_req_list(struct nvme_tcp_queue *queue)
+{
+	struct nvme_tcp_request *req;
+	struct llist_node *node;
+
+	for (node = llist_del_all(&queue->req_list); node; node = node->next) {
+		req = llist_entry(node, struct nvme_tcp_request, lentry);
+		list_add(&req->entry, &queue->send_list);
+	}
+}
+
 static inline struct nvme_tcp_request *
 nvme_tcp_fetch_request(struct nvme_tcp_queue *queue)
 {
 	struct nvme_tcp_request *req;
 
-	spin_lock(&queue->lock);
 	req = list_first_entry_or_null(&queue->send_list,
 			struct nvme_tcp_request, entry);
-	if (req)
+	if (!req) {
-		list_del(&req->entry);
+		nvme_tcp_process_req_list(queue);
-	spin_unlock(&queue->lock);
+		req = list_first_entry_or_null(&queue->send_list,
+				struct nvme_tcp_request, entry);
+		if (unlikely(!req))
+			return NULL;
+	}
 
+	list_del(&req->entry);
 	return req;
 }
 
@@ -596,7 +613,7 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 	req->state = NVME_TCP_SEND_H2C_PDU;
 	req->offset = 0;
 
-	nvme_tcp_queue_request(req, false);
+	nvme_tcp_queue_request(req, false, true);
 
 	return 0;
 }
@@ -863,6 +880,12 @@ done:
 	read_unlock(&sk->sk_callback_lock);
 }
 
+static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+{
+	return !list_empty(&queue->send_list) ||
+		!llist_empty(&queue->req_list) || queue->more_requests;
+}
+
 static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue)
 {
 	queue->request = NULL;
@@ -884,7 +907,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 		bool last = nvme_tcp_pdu_last_send(req, len);
 		int ret, flags = MSG_DONTWAIT;
 
-		if (last && !queue->data_digest)
+		if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
 			flags |= MSG_EOR;
 		else
 			flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
@@ -931,7 +954,7 @@ static int nvme_tcp_try_send_cmd_pdu(struct nvme_tcp_request *req)
 	int flags = MSG_DONTWAIT;
 	int ret;
 
-	if (inline_data)
+	if (inline_data || nvme_tcp_queue_more(queue))
 		flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST;
 	else
 		flags |= MSG_EOR;
@@ -996,12 +1019,17 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
 {
 	struct nvme_tcp_queue *queue = req->queue;
 	int ret;
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_EOR };
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
 	struct kvec iov = {
 		.iov_base = &req->ddgst + req->offset,
 		.iov_len = NVME_TCP_DIGEST_LENGTH - req->offset
 	};
 
+	if (nvme_tcp_queue_more(queue))
+		msg.msg_flags |= MSG_MORE;
+	else
+		msg.msg_flags |= MSG_EOR;
+
 	ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len);
 	if (unlikely(ret <= 0))
 		return ret;
@@ -1344,8 +1372,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	int ret, rcv_pdu_size;
 
 	queue->ctrl = ctrl;
+	init_llist_head(&queue->req_list);
 	INIT_LIST_HEAD(&queue->send_list);
-	spin_lock_init(&queue->lock);
 	mutex_init(&queue->send_mutex);
 	INIT_WORK(&queue->io_work, nvme_tcp_io_work);
 	queue->queue_size = queue_size;
@@ -2106,7 +2134,7 @@ static void nvme_tcp_submit_async_event(struct nvme_ctrl *arg)
 	ctrl->async_req.curr_bio = NULL;
 	ctrl->async_req.data_len = 0;
 
-	nvme_tcp_queue_request(&ctrl->async_req, true);
+	nvme_tcp_queue_request(&ctrl->async_req, true, true);
 }
 
 static enum blk_eh_timer_return
@@ -2218,6 +2246,14 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 	return 0;
 }
 
+static void nvme_tcp_commit_rqs(struct blk_mq_hw_ctx *hctx)
+{
+	struct nvme_tcp_queue *queue = hctx->driver_data;
+
+	if (!llist_empty(&queue->req_list))
+		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
+}
+
 static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
@@ -2237,7 +2273,7 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(rq);
 
-	nvme_tcp_queue_request(req, true);
+	nvme_tcp_queue_request(req, true, bd->last);
 
 	return BLK_STS_OK;
 }
@@ -2305,6 +2341,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
 
 static const struct blk_mq_ops nvme_tcp_mq_ops = {
 	.queue_rq	= nvme_tcp_queue_rq,
+	.commit_rqs	= nvme_tcp_commit_rqs,
 	.complete	= nvme_complete_rq,
 	.init_request	= nvme_tcp_init_request,
 	.exit_request	= nvme_tcp_exit_request,

drivers/nvme/host/zns.c

@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/blkdev.h>
+#include <linux/vmalloc.h>
+#include "nvme.h"
+
+static int nvme_set_max_append(struct nvme_ctrl *ctrl)
+{
+	struct nvme_command c = { };
+	struct nvme_id_ctrl_zns *id;
+	int status;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return -ENOMEM;
+
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.cns = NVME_ID_CNS_CS_CTRL;
+	c.identify.csi = NVME_CSI_ZNS;
+
+	status = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
+	if (status) {
+		kfree(id);
+		return status;
+	}
+
+	if (id->zasl)
+		ctrl->max_zone_append = 1 << (id->zasl + 3);
+	else
+		ctrl->max_zone_append = ctrl->max_hw_sectors;
+	kfree(id);
+	return 0;
+}
+
+int nvme_update_zone_info(struct gendisk *disk, struct nvme_ns *ns,
+			  unsigned lbaf)
+{
+	struct nvme_effects_log *log = ns->head->effects;
+	struct request_queue *q = disk->queue;
+	struct nvme_command c = { };
+	struct nvme_id_ns_zns *id;
+	int status;
+
+	/* Driver requires zone append support */
+	if (!(le32_to_cpu(log->iocs[nvme_cmd_zone_append]) &
+			NVME_CMD_EFFECTS_CSUPP)) {
+		dev_warn(ns->ctrl->device,
+			"append not supported for zoned namespace:%d\n",
+			ns->head->ns_id);
+		return -EINVAL;
+	}
+
+	/* Lazily query controller append limit for the first zoned namespace */
+	if (!ns->ctrl->max_zone_append) {
+		status = nvme_set_max_append(ns->ctrl);
+		if (status)
+			return status;
+	}
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id)
+		return -ENOMEM;
+
+	c.identify.opcode = nvme_admin_identify;
+	c.identify.nsid = cpu_to_le32(ns->head->ns_id);
+	c.identify.cns = NVME_ID_CNS_CS_NS;
+	c.identify.csi = NVME_CSI_ZNS;
+
+	status = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, id, sizeof(*id));
+	if (status)
+		goto free_data;
+
+	/*
+	 * We currently do not handle devices requiring any of the zoned
+	 * operation characteristics.
+	 */
+	if (id->zoc) {
+		dev_warn(ns->ctrl->device,
+			"zone operations:%x not supported for namespace:%u\n",
+			le16_to_cpu(id->zoc), ns->head->ns_id);
+		status = -EINVAL;
+		goto free_data;
+	}
+
+	ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze));
+	if (!is_power_of_2(ns->zsze)) {
+		dev_warn(ns->ctrl->device,
+			"invalid zone size:%llu for namespace:%u\n",
+			ns->zsze, ns->head->ns_id);
+		status = -EINVAL;
+		goto free_data;
+	}
+
+	q->limits.zoned = BLK_ZONED_HM;
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+	blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
+	blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
+free_data:
+	kfree(id);
+	return status;
+}
+
+static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
+					  unsigned int nr_zones, size_t *buflen)
+{
+	struct request_queue *q = ns->disk->queue;
+	size_t bufsize;
+	void *buf;
+
+	const size_t min_bufsize = sizeof(struct nvme_zone_report) +
+				   sizeof(struct nvme_zone_descriptor);
+
+	nr_zones = min_t(unsigned int, nr_zones,
+			 get_capacity(ns->disk) >> ilog2(ns->zsze));
+
+	bufsize = sizeof(struct nvme_zone_report) +
+		nr_zones * sizeof(struct nvme_zone_descriptor);
+	bufsize = min_t(size_t, bufsize,
+			queue_max_hw_sectors(q) << SECTOR_SHIFT);
+	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);
+
+	while (bufsize >= min_bufsize) {
+		buf = __vmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
+		if (buf) {
+			*buflen = bufsize;
+			return buf;
+		}
+		bufsize >>= 1;
+	}
+	return NULL;
+}
+
+static int __nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
+				  struct nvme_zone_report *report,
+				  size_t buflen)
+{
+	struct nvme_command c = { };
+	int ret;
+
+	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
+	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
+	c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
+	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
+	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
+	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
+	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
+
+	ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
+	if (ret)
+		return ret;
+
+	return le64_to_cpu(report->nr_zones);
+}
+
+static int nvme_zone_parse_entry(struct nvme_ns *ns,
+				 struct nvme_zone_descriptor *entry,
+				 unsigned int idx, report_zones_cb cb,
+				 void *data)
+{
+	struct blk_zone zone = { };
+
+	if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) {
+		dev_err(ns->ctrl->device, "invalid zone type %#x\n",
+				entry->zt);
+		return -EINVAL;
+	}
+
+	zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ;
+	zone.cond = entry->zs >> 4;
+	zone.len = ns->zsze;
+	zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
+	zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
+	zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+
+	return cb(&zone, idx, data);
+}
+
+static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
+			unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	struct nvme_zone_report *report;
+	int ret, zone_idx = 0;
+	unsigned int nz, i;
+	size_t buflen;
+
+	report = nvme_zns_alloc_report_buffer(ns, nr_zones, &buflen);
+	if (!report)
+		return -ENOMEM;
+
+	sector &= ~(ns->zsze - 1);
+	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
+		memset(report, 0, buflen);
+		ret = __nvme_ns_report_zones(ns, sector, report, buflen);
+		if (ret < 0)
+			goto out_free;
+
+		nz = min_t(unsigned int, ret, nr_zones);
+		if (!nz)
+			break;
+
+		for (i = 0; i < nz && zone_idx < nr_zones; i++) {
+			ret = nvme_zone_parse_entry(ns, &report->entries[i],
+						    zone_idx, cb, data);
+			if (ret)
+				goto out_free;
+			zone_idx++;
+		}
+
+		sector += ns->zsze * nz;
+	}
+
+	if (zone_idx > 0)
+		ret = zone_idx;
+	else
+		ret = -EINVAL;
+out_free:
+	kvfree(report);
+	return ret;
+}
+
+int nvme_report_zones(struct gendisk *disk, sector_t sector,
+		      unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	struct nvme_ns_head *head = NULL;
+	struct nvme_ns *ns;
+	int srcu_idx, ret;
+
+	ns = nvme_get_ns_from_disk(disk, &head, &srcu_idx);
+	if (unlikely(!ns))
+		return -EWOULDBLOCK;
+
+	if (ns->head->ids.csi == NVME_CSI_ZNS)
+		ret = nvme_ns_report_zones(ns, sector, nr_zones, cb, data);
+	else
+		ret = -EINVAL;
+	nvme_put_ns_from_disk(head, srcu_idx);
+
+	return ret;
+}
+
+blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
+		struct nvme_command *c, enum nvme_zone_mgmt_action action)
+{
+	c->zms.opcode = nvme_cmd_zone_mgmt_send;
+	c->zms.nsid = cpu_to_le32(ns->head->ns_id);
+	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
+	c->zms.zsa = action;
+
+	if (req_op(req) == REQ_OP_ZONE_RESET_ALL)
+		c->zms.select_all = 1;
+
+	return BLK_STS_OK;
+}

drivers/nvme/target/admin-cmd.c

@@ -427,7 +427,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->awupf = 0;
 
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
-	if (ctrl->ops->has_keyed_sgls)
+	if (ctrl->ops->flags & NVMF_KEYED_SGLS)
 		id->sgls |= cpu_to_le32(1 << 2);
 	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);

drivers/nvme/target/configfs.c

@@ -862,14 +862,14 @@ static ssize_t nvmet_subsys_attr_version_show(struct config_item *item,
 	struct nvmet_subsys *subsys = to_subsys(item);
 
 	if (NVME_TERTIARY(subsys->ver))
-		return snprintf(page, PAGE_SIZE, "%d.%d.%d\n",
+		return snprintf(page, PAGE_SIZE, "%llu.%llu.%llu\n",
-				(int)NVME_MAJOR(subsys->ver),
+				NVME_MAJOR(subsys->ver),
-				(int)NVME_MINOR(subsys->ver),
+				NVME_MINOR(subsys->ver),
-				(int)NVME_TERTIARY(subsys->ver));
+				NVME_TERTIARY(subsys->ver));
 
-	return snprintf(page, PAGE_SIZE, "%d.%d\n",
+	return snprintf(page, PAGE_SIZE, "%llu.%llu\n",
-			(int)NVME_MAJOR(subsys->ver),
+			NVME_MAJOR(subsys->ver),
-			(int)NVME_MINOR(subsys->ver));
+			NVME_MINOR(subsys->ver));
 }
 
 static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,

drivers/nvme/target/core.c

@@ -336,7 +336,7 @@ int nvmet_enable_port(struct nvmet_port *port)
 	 * If the user requested PI support and the transport isn't pi capable,
 	 * don't enable the port.
 	 */
-	if (port->pi_enable && !ops->metadata_support) {
+	if (port->pi_enable && !(ops->flags & NVMF_METADATA_SUPPORTED)) {
 		pr_err("T10-PI is not supported by transport type %d\n",
 		       port->disc_addr.trtype);
 		ret = -EINVAL;

drivers/nvme/target/discovery.c

@@ -277,7 +277,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
 	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
 
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
-	if (ctrl->ops->has_keyed_sgls)
+	if (ctrl->ops->flags & NVMF_KEYED_SGLS)
 		id->sgls |= cpu_to_le32(1 << 2);
 	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);

drivers/nvme/target/fcloop.c

@@ -43,6 +43,17 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_ERR,		NULL		}
 };
 
+static int fcloop_verify_addr(substring_t *s)
+{
+	size_t blen = s->to - s->from + 1;
+
+	if (strnlen(s->from, blen) != NVME_FC_TRADDR_HEXNAMELEN + 2 ||
+	    strncmp(s->from, "0x", 2))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int
 fcloop_parse_options(struct fcloop_ctrl_options *opts,
 		const char *buf)
@@ -64,14 +75,16 @@ fcloop_parse_options(struct fcloop_ctrl_options *opts,
 		opts->mask |= token;
 		switch (token) {
 		case NVMF_OPT_WWNN:
-			if (match_u64(args, &token64)) {
+			if (fcloop_verify_addr(args) ||
+			    match_u64(args, &token64)) {
 				ret = -EINVAL;
 				goto out_free_options;
 			}
 			opts->wwnn = token64;
 			break;
 		case NVMF_OPT_WWPN:
-			if (match_u64(args, &token64)) {
+			if (fcloop_verify_addr(args) ||
+			    match_u64(args, &token64)) {
 				ret = -EINVAL;
 				goto out_free_options;
 			}
@@ -92,14 +105,16 @@ fcloop_parse_options(struct fcloop_ctrl_options *opts,
 			opts->fcaddr = token;
 			break;
 		case NVMF_OPT_LPWWNN:
-			if (match_u64(args, &token64)) {
+			if (fcloop_verify_addr(args) ||
+			    match_u64(args, &token64)) {
 				ret = -EINVAL;
 				goto out_free_options;
 			}
 			opts->lpwwnn = token64;
 			break;
 		case NVMF_OPT_LPWWPN:
-			if (match_u64(args, &token64)) {
+			if (fcloop_verify_addr(args) ||
+			    match_u64(args, &token64)) {
 				ret = -EINVAL;
 				goto out_free_options;
 			}
@@ -141,14 +156,16 @@ fcloop_parse_nm_options(struct device *dev, u64 *nname, u64 *pname,
 		token = match_token(p, opt_tokens, args);
 		switch (token) {
 		case NVMF_OPT_WWNN:
-			if (match_u64(args, &token64)) {
+			if (fcloop_verify_addr(args) ||
+			    match_u64(args, &token64)) {
 				ret = -EINVAL;
 				goto out_free_options;
 			}
 			*nname = token64;
 			break;
 		case NVMF_OPT_WWPN:
-			if (match_u64(args, &token64)) {
+			if (fcloop_verify_addr(args) ||
+			    match_u64(args, &token64)) {
 				ret = -EINVAL;
 				goto out_free_options;
 			}

drivers/nvme/target/loop.c

@@ -36,7 +36,6 @@ struct nvme_loop_ctrl {
 	struct nvme_loop_iod	async_event_iod;
 	struct nvme_ctrl	ctrl;
 
-	struct nvmet_ctrl	*target_ctrl;
 	struct nvmet_port	*port;
 };
 

drivers/nvme/target/nvmet.h

@@ -286,8 +286,9 @@ struct nvmet_fabrics_ops {
 	struct module *owner;
 	unsigned int type;
 	unsigned int msdbd;
-	bool has_keyed_sgls : 1;
+	unsigned int flags;
-	bool metadata_support : 1;
+#define NVMF_KEYED_SGLS			(1 << 0)
+#define NVMF_METADATA_SUPPORTED		(1 << 1)
 	void (*queue_response)(struct nvmet_req *req);
 	int (*add_port)(struct nvmet_port *port);
 	void (*remove_port)(struct nvmet_port *port);

drivers/nvme/target/rdma.c

@@ -1970,8 +1970,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_RDMA,
 	.msdbd			= 1,
-	.has_keyed_sgls		= 1,
+	.flags			= NVMF_KEYED_SGLS | NVMF_METADATA_SUPPORTED,
-	.metadata_support	= 1,
 	.add_port		= nvmet_rdma_add_port,
 	.remove_port		= nvmet_rdma_remove_port,
 	.queue_response		= nvmet_rdma_queue_response,

drivers/nvme/target/tcp.c

@@ -459,17 +459,11 @@ static void nvmet_setup_response_pdu(struct nvmet_tcp_cmd *cmd)
 static void nvmet_tcp_process_resp_list(struct nvmet_tcp_queue *queue)
 {
 	struct llist_node *node;
+	struct nvmet_tcp_cmd *cmd;
 
-	node = llist_del_all(&queue->resp_list);
+	for (node = llist_del_all(&queue->resp_list); node; node = node->next) {
-	if (!node)
+		cmd = llist_entry(node, struct nvmet_tcp_cmd, lentry);
-		return;
-
-	while (node) {
-		struct nvmet_tcp_cmd *cmd = llist_entry(node,
-					struct nvmet_tcp_cmd, lentry);
-
 		list_add(&cmd->entry, &queue->resp_send_list);
-		node = node->next;
 		queue->send_list_len++;
 	}
 }
@@ -1717,7 +1711,6 @@ static const struct nvmet_fabrics_ops nvmet_tcp_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_TCP,
 	.msdbd			= 1,
-	.has_keyed_sgls		= 0,
 	.add_port		= nvmet_tcp_add_port,
 	.remove_port		= nvmet_tcp_remove_port,
 	.queue_response		= nvmet_tcp_queue_response,

drivers/s390/block/dasd_diag.c

@@ -319,7 +319,7 @@ dasd_diag_check_device(struct dasd_device *device)
 	struct dasd_diag_characteristics *rdc_data;
 	struct vtoc_cms_label *label;
 	struct dasd_block *block;
-	struct dasd_diag_bio bio;
+	struct dasd_diag_bio *bio;
 	unsigned int sb, bsize;
 	blocknum_t end_block;
 	int rc;
@@ -395,29 +395,36 @@ dasd_diag_check_device(struct dasd_device *device)
 		rc = -ENOMEM;
 		goto out;
 	}
+	bio = kzalloc(sizeof(*bio), GFP_KERNEL);
+	if (bio == NULL)  {
+		DBF_DEV_EVENT(DBF_WARNING, device, "%s",
+			      "No memory to allocate initialization bio");
+		rc = -ENOMEM;
+		goto out_label;
+	}
 	rc = 0;
 	end_block = 0;
 	/* try all sizes - needed for ECKD devices */
 	for (bsize = 512; bsize <= PAGE_SIZE; bsize <<= 1) {
 		mdsk_init_io(device, bsize, 0, &end_block);
-		memset(&bio, 0, sizeof (struct dasd_diag_bio));
+		memset(bio, 0, sizeof(*bio));
-		bio.type = MDSK_READ_REQ;
+		bio->type = MDSK_READ_REQ;
-		bio.block_number = private->pt_block + 1;
+		bio->block_number = private->pt_block + 1;
-		bio.buffer = label;
+		bio->buffer = label;
 		memset(&private->iob, 0, sizeof (struct dasd_diag_rw_io));
 		private->iob.dev_nr = rdc_data->dev_nr;
 		private->iob.key = 0;
 		private->iob.flags = 0;	/* do synchronous io */
 		private->iob.block_count = 1;
 		private->iob.interrupt_params = 0;
-		private->iob.bio_list = &bio;
+		private->iob.bio_list = bio;
 		private->iob.flaga = DASD_DIAG_FLAGA_DEFAULT;
 		rc = dia250(&private->iob, RW_BIO);
 		if (rc == 3) {
 			pr_warn("%s: A 64-bit DIAG call failed\n",
 				dev_name(&device->cdev->dev));
 			rc = -EOPNOTSUPP;
-			goto out_label;
+			goto out_bio;
 		}
 		mdsk_term_io(device);
 		if (rc == 0)
@@ -427,7 +434,7 @@ dasd_diag_check_device(struct dasd_device *device)
 		pr_warn("%s: Accessing the DASD failed because of an incorrect format (rc=%d)\n",
 			dev_name(&device->cdev->dev), rc);
 		rc = -EIO;
-		goto out_label;
+		goto out_bio;
 	}
 	/* check for label block */
 	if (memcmp(label->label_id, DASD_DIAG_CMS1,
@@ -457,6 +464,8 @@ dasd_diag_check_device(struct dasd_device *device)
 			(rc == 4) ? ", read-only device" : "");
 		rc = 0;
 	}
+out_bio:
+	kfree(bio);
 out_label:
 	free_page((long) label);
 out:
@@ -506,7 +515,7 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 	struct req_iterator iter;
 	struct bio_vec bv;
 	char *dst;
-	unsigned int count, datasize;
+	unsigned int count;
 	sector_t recid, first_rec, last_rec;
 	unsigned int blksize, off;
 	unsigned char rw_cmd;
@@ -534,10 +543,8 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 	if (count != last_rec - first_rec + 1)
 		return ERR_PTR(-EINVAL);
 	/* Build the request */
-	datasize = sizeof(struct dasd_diag_req) +
+	cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, struct_size(dreq, bio, count),
-		count*sizeof(struct dasd_diag_bio);
+				   memdev, blk_mq_rq_to_pdu(req));
-	cqr = dasd_smalloc_request(DASD_DIAG_MAGIC, 0, datasize, memdev,
-				   blk_mq_rq_to_pdu(req));
 	if (IS_ERR(cqr))
 		return cqr;
 

drivers/scsi/sd_zbc.c

@@ -59,6 +59,7 @@ static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
 		zone.non_seq = 1;
 
 	zone.len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8]));
+	zone.capacity = zone.len;
 	zone.start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16]));
 	zone.wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24]));
 	if (zone.type != ZBC_ZONE_TYPE_CONV &&
@@ -716,6 +717,11 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	/* The drive satisfies the kernel restrictions: set it up */
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
 	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
+	if (sdkp->zones_max_open == U32_MAX)
+		blk_queue_max_open_zones(q, 0);
+	else
+		blk_queue_max_open_zones(q, sdkp->zones_max_open);
+	blk_queue_max_active_zones(q, 0);
 	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
 
 	/* READ16/WRITE16 is mandatory for ZBC disks */

include/linux/blkdev.h

@@ -513,6 +513,8 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
@@ -722,6 +724,28 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return true;
 	return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap);
 }
+
+static inline void blk_queue_max_open_zones(struct request_queue *q,
+		unsigned int max_open_zones)
+{
+	q->max_open_zones = max_open_zones;
+}
+
+static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+{
+	return q->max_open_zones;
+}
+
+static inline void blk_queue_max_active_zones(struct request_queue *q,
+		unsigned int max_active_zones)
+{
+	q->max_active_zones = max_active_zones;
+}
+
+static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+{
+	return q->max_active_zones;
+}
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
 {
@@ -737,6 +761,14 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 {
 	return 0;
 }
+static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+{
+	return 0;
+}
+static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+{
+	return 0;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
@@ -1519,6 +1551,24 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
+static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return queue_max_open_zones(q);
+	return 0;
+}
+
+static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return queue_max_active_zones(q);
+	return 0;
+}
+
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;

include/linux/nvme.h

@@ -132,6 +132,7 @@ enum {
 #define NVME_CAP_TIMEOUT(cap)	(((cap) >> 24) & 0xff)
 #define NVME_CAP_STRIDE(cap)	(((cap) >> 32) & 0xf)
 #define NVME_CAP_NSSRC(cap)	(((cap) >> 36) & 0x1)
+#define NVME_CAP_CSS(cap)	(((cap) >> 37) & 0xff)
 #define NVME_CAP_MPSMIN(cap)	(((cap) >> 48) & 0xf)
 #define NVME_CAP_MPSMAX(cap)	(((cap) >> 52) & 0xf)
 
@@ -162,7 +163,6 @@ enum {
 
 enum {
 	NVME_CC_ENABLE		= 1 << 0,
-	NVME_CC_CSS_NVM		= 0 << 4,
 	NVME_CC_EN_SHIFT	= 0,
 	NVME_CC_CSS_SHIFT	= 4,
 	NVME_CC_MPS_SHIFT	= 7,
@@ -170,6 +170,9 @@ enum {
 	NVME_CC_SHN_SHIFT	= 14,
 	NVME_CC_IOSQES_SHIFT	= 16,
 	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_CSS_NVM		= 0 << NVME_CC_CSS_SHIFT,
+	NVME_CC_CSS_CSI		= 6 << NVME_CC_CSS_SHIFT,
+	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
 	NVME_CC_AMS_RR		= 0 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_WRRU	= 1 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_VS		= 7 << NVME_CC_AMS_SHIFT,
@@ -179,6 +182,8 @@ enum {
 	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
 	NVME_CC_IOSQES		= NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
 	NVME_CC_IOCQES		= NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
+	NVME_CAP_CSS_NVM	= 1 << 0,
+	NVME_CAP_CSS_CSI	= 1 << 6,
 	NVME_CSTS_RDY		= 1 << 0,
 	NVME_CSTS_CFS		= 1 << 1,
 	NVME_CSTS_NSSRO		= 1 << 4,
@@ -369,11 +374,37 @@ struct nvme_id_ns {
 	__u8			vs[3712];
 };
 
+struct nvme_zns_lbafe {
+	__le64			zsze;
+	__u8			zdes;
+	__u8			rsvd9[7];
+};
+
+struct nvme_id_ns_zns {
+	__le16			zoc;
+	__le16			ozcs;
+	__le32			mar;
+	__le32			mor;
+	__le32			rrl;
+	__le32			frl;
+	__u8			rsvd20[2796];
+	struct nvme_zns_lbafe	lbafe[16];
+	__u8			rsvd3072[768];
+	__u8			vs[256];
+};
+
+struct nvme_id_ctrl_zns {
+	__u8	zasl;
+	__u8	rsvd1[4095];
+};
+
 enum {
 	NVME_ID_CNS_NS			= 0x00,
 	NVME_ID_CNS_CTRL		= 0x01,
 	NVME_ID_CNS_NS_ACTIVE_LIST	= 0x02,
 	NVME_ID_CNS_NS_DESC_LIST	= 0x03,
+	NVME_ID_CNS_CS_NS		= 0x05,
+	NVME_ID_CNS_CS_CTRL		= 0x06,
 	NVME_ID_CNS_NS_PRESENT_LIST	= 0x10,
 	NVME_ID_CNS_NS_PRESENT		= 0x11,
 	NVME_ID_CNS_CTRL_NS_LIST	= 0x12,
@@ -383,6 +414,11 @@ enum {
 	NVME_ID_CNS_UUID_LIST		= 0x17,
 };
 
+enum {
+	NVME_CSI_NVM			= 0,
+	NVME_CSI_ZNS			= 2,
+};
+
 enum {
 	NVME_DIR_IDENTIFY		= 0x00,
 	NVME_DIR_STREAMS		= 0x01,
@@ -435,11 +471,13 @@ struct nvme_ns_id_desc {
 #define NVME_NIDT_EUI64_LEN	8
 #define NVME_NIDT_NGUID_LEN	16
 #define NVME_NIDT_UUID_LEN	16
+#define NVME_NIDT_CSI_LEN	1
 
 enum {
 	NVME_NIDT_EUI64		= 0x01,
 	NVME_NIDT_NGUID		= 0x02,
 	NVME_NIDT_UUID		= 0x03,
+	NVME_NIDT_CSI		= 0x04,
 };
 
 struct nvme_smart_log {
@@ -519,6 +557,27 @@ struct nvme_ana_rsp_hdr {
 	__le16	rsvd10[3];
 };
 
+struct nvme_zone_descriptor {
+	__u8		zt;
+	__u8		zs;
+	__u8		za;
+	__u8		rsvd3[5];
+	__le64		zcap;
+	__le64		zslba;
+	__le64		wp;
+	__u8		rsvd32[32];
+};
+
+enum {
+	NVME_ZONE_TYPE_SEQWRITE_REQ	= 0x2,
+};
+
+struct nvme_zone_report {
+	__le64		nr_zones;
+	__u8		resv8[56];
+	struct nvme_zone_descriptor entries[];
+};
+
 enum {
 	NVME_SMART_CRIT_SPARE		= 1 << 0,
 	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
@@ -613,6 +672,9 @@ enum nvme_opcode {
 	nvme_cmd_resv_report	= 0x0e,
 	nvme_cmd_resv_acquire	= 0x11,
 	nvme_cmd_resv_release	= 0x15,
+	nvme_cmd_zone_mgmt_send	= 0x79,
+	nvme_cmd_zone_mgmt_recv	= 0x7a,
+	nvme_cmd_zone_append	= 0x7d,
 };
 
 #define nvme_opcode_name(opcode)	{ opcode, #opcode }
@@ -751,6 +813,7 @@ struct nvme_rw_command {
 enum {
 	NVME_RW_LR			= 1 << 15,
 	NVME_RW_FUA			= 1 << 14,
+	NVME_RW_APPEND_PIREMAP		= 1 << 9,
 	NVME_RW_DSM_FREQ_UNSPEC		= 0,
 	NVME_RW_DSM_FREQ_TYPICAL	= 1,
 	NVME_RW_DSM_FREQ_RARE		= 2,
@@ -816,6 +879,53 @@ struct nvme_write_zeroes_cmd {
 	__le16			appmask;
 };
 
+enum nvme_zone_mgmt_action {
+	NVME_ZONE_CLOSE		= 0x1,
+	NVME_ZONE_FINISH	= 0x2,
+	NVME_ZONE_OPEN		= 0x3,
+	NVME_ZONE_RESET		= 0x4,
+	NVME_ZONE_OFFLINE	= 0x5,
+	NVME_ZONE_SET_DESC_EXT	= 0x10,
+};
+
+struct nvme_zone_mgmt_send_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le32			cdw2[2];
+	__le64			metadata;
+	union nvme_data_ptr	dptr;
+	__le64			slba;
+	__le32			cdw12;
+	__u8			zsa;
+	__u8			select_all;
+	__u8			rsvd13[2];
+	__le32			cdw14[2];
+};
+
+struct nvme_zone_mgmt_recv_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le64			rsvd2[2];
+	union nvme_data_ptr	dptr;
+	__le64			slba;
+	__le32			numd;
+	__u8			zra;
+	__u8			zrasf;
+	__u8			pr;
+	__u8			rsvd13;
+	__le32			cdw14[2];
+};
+
+enum {
+	NVME_ZRA_ZONE_REPORT		= 0,
+	NVME_ZRASF_ZONE_REPORT_ALL	= 0,
+	NVME_REPORT_ZONE_PARTIAL	= 1,
+};
+
 /* Features */
 
 enum {
@@ -972,7 +1082,9 @@ struct nvme_identify {
 	__u8			cns;
 	__u8			rsvd3;
 	__le16			ctrlid;
-	__u32			rsvd11[5];
+	__u8			rsvd11[3];
+	__u8			csi;
+	__u32			rsvd12[4];
 };
 
 #define NVME_IDENTIFY_DATA_SIZE 4096
@@ -1086,7 +1198,9 @@ struct nvme_get_log_page_command {
 		};
 		__le64 lpo;
 	};
-	__u32			rsvd14[2];
+	__u8			rsvd14[3];
+	__u8			csi;
+	__u32			rsvd15;
 };
 
 struct nvme_directive_cmd {
@@ -1283,6 +1397,8 @@ struct nvme_command {
 		struct nvme_format_cmd format;
 		struct nvme_dsm_cmd dsm;
 		struct nvme_write_zeroes_cmd write_zeroes;
+		struct nvme_zone_mgmt_send_cmd zms;
+		struct nvme_zone_mgmt_recv_cmd zmr;
 		struct nvme_abort_cmd abort;
 		struct nvme_get_log_page_command get_log_page;
 		struct nvmf_common_command fabrics;
@@ -1416,6 +1532,18 @@ enum {
 	NVME_SC_DISCOVERY_RESTART	= 0x190,
 	NVME_SC_AUTH_REQUIRED		= 0x191,
 
+	/*
+	 * I/O Command Set Specific - Zoned commands:
+	 */
+	NVME_SC_ZONE_BOUNDARY_ERROR	= 0x1b8,
+	NVME_SC_ZONE_FULL		= 0x1b9,
+	NVME_SC_ZONE_READ_ONLY		= 0x1ba,
+	NVME_SC_ZONE_OFFLINE		= 0x1bb,
+	NVME_SC_ZONE_INVALID_WRITE	= 0x1bc,
+	NVME_SC_ZONE_TOO_MANY_ACTIVE	= 0x1bd,
+	NVME_SC_ZONE_TOO_MANY_OPEN	= 0x1be,
+	NVME_SC_ZONE_INVALID_TRANSITION	= 0x1bf,
+
 	/*
 	 * Media and Data Integrity Errors:
 	 */

include/uapi/linux/blkzoned.h

@@ -73,6 +73,15 @@ enum blk_zone_cond {
 	BLK_ZONE_COND_OFFLINE	= 0xF,
 };
 
+/**
+ * enum blk_zone_report_flags - Feature flags of reported zone descriptors.
+ *
+ * @BLK_ZONE_REP_CAPACITY: Zone descriptor has capacity field.
+ */
+enum blk_zone_report_flags {
+	BLK_ZONE_REP_CAPACITY	= (1 << 0),
+};
+
 /**
  * struct blk_zone - Zone descriptor for BLKREPORTZONE ioctl.
  *
@@ -99,7 +108,9 @@ struct blk_zone {
 	__u8	cond;		/* Zone condition */
 	__u8	non_seq;	/* Non-sequential write resources active */
 	__u8	reset;		/* Reset write pointer recommended */
-	__u8	reserved[36];
+	__u8	resv[4];
+	__u64	capacity;	/* Zone capacity in number of sectors */
+	__u8	reserved[24];
 };
 
 /**
@@ -115,7 +126,7 @@ struct blk_zone {
 struct blk_zone_report {
 	__u64		sector;
 	__u32		nr_zones;
-	__u8		reserved[4];
+	__u32		flags;
 	struct blk_zone zones[0];
 };