Merge tag 'for-5.14/drivers-2021-06-29' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
"Pretty calm round, mostly just NVMe and a bit of MD:

- NVMe updates (via Christoph)
- improve the APST configuration algorithm (Alexey Bogoslavsky)
- look for StorageD3Enable on companion ACPI device
(Mario Limonciello)
- allow selecting the network interface for TCP connections
(Martin Belanger)
- misc cleanups (Amit Engel, Chaitanya Kulkarni, Colin Ian King,
Christoph)
- move the ACPI StorageD3 code to drivers/acpi/ and add quirks
for certain AMD CPUs (Mario Limonciello)
- zoned device support for nvmet (Chaitanya Kulkarni)
- fix the rules for changing the serial number in nvmet
(Noam Gottlieb)
- various small fixes and cleanups (Dan Carpenter, JK Kim,
Chaitanya Kulkarni, Hannes Reinecke, Wesley Sheng, Geert
Uytterhoeven, Daniel Wagner)

- MD updates (Via Song)
- iostats rewrite (Guoqing Jiang)
- raid5 lock contention optimization (Gal Ofri)

- Fall through warning fix (Gustavo)

- Misc fixes (Gustavo, Jiapeng)"

* tag 'for-5.14/drivers-2021-06-29' of git://git.kernel.dk/linux-block: (78 commits)
nvmet: use NVMET_MAX_NAMESPACES to set nn value
loop: Fix missing discard support when using LOOP_CONFIGURE
nvme.h: add missing nvme_lba_range_type endianness annotations
nvme: remove zeroout memset call for struct
nvme-pci: remove zeroout memset call for struct
nvmet: remove zeroout memset call for struct
nvmet: add ZBD over ZNS backend support
nvmet: add Command Set Identifier support
nvmet: add nvmet_req_bio put helper for backends
nvmet: add req cns error complete helper
block: export blk_next_bio()
nvmet: remove local variable
nvmet: use nvme status value directly
nvmet: use u32 type for the local variable nsid
nvmet: use u32 for nvmet_subsys max_nsid
nvmet: use req->cmd directly in file-ns fast path
nvmet: use req->cmd directly in bdev-ns fast path
nvmet: make ver stable once connection established
nvmet: allow mn change if subsys not discovered
nvmet: make sn stable once connection was established
...

block/blk-lib.c

···
 
 	return new;
 }
+EXPORT_SYMBOL_GPL(blk_next_bio);
 
 int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, int flags,

drivers/acpi/device_pm.c

···
 	return 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
+
+/**
+ * acpi_storage_d3 - Check if D3 should be used in the suspend path
+ * @dev: Device to check
+ *
+ * Return %true if the platform firmware wants @dev to be programmed
+ * into D3hot or D3cold (if supported) in the suspend path, or %false
+ * when there is no specific preference. On some platforms, if this
+ * hint is ignored, @dev may remain unresponsive after suspending the
+ * platform as a whole.
+ *
+ * Although the property has storage in the name it actually is
+ * applied to the PCIe slot and plugging in a non-storage device the
+ * same platform restrictions will likely apply.
+ */
+bool acpi_storage_d3(struct device *dev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	u8 val;
+
+	if (force_storage_d3())
+		return true;
+
+	if (!adev)
+		return false;
+	if (fwnode_property_read_u8(acpi_fwnode_handle(adev), "StorageD3Enable",
+			&val))
+		return false;
+	return val == 1;
+}
+EXPORT_SYMBOL_GPL(acpi_storage_d3);
+
 #endif /* CONFIG_PM */

drivers/acpi/internal.h

···
 static inline void suspend_nvs_restore(void) {}
 #endif
 
+#ifdef CONFIG_X86
+bool force_storage_d3(void);
+#else
+static inline bool force_storage_d3(void)
+{
+	return false;
+}
+#endif
+
 /*--------------------------------------------------------------------------
 				Device properties
   -------------------------------------------------------------------------- */

drivers/acpi/x86/utils.c

···
 
 	return ret;
 }
+
+/*
+ * AMD systems from Renoir and Lucienne *require* that the NVME controller
+ * is put into D3 over a Modern Standby / suspend-to-idle cycle.
+ *
+ * This is "typically" accomplished using the `StorageD3Enable`
+ * property in the _DSD that is checked via the `acpi_storage_d3` function
+ * but this property was introduced after many of these systems launched
+ * and most OEM systems don't have it in their BIOS.
+ *
+ * The Microsoft documentation for StorageD3Enable mentioned that Windows has
+ * a hardcoded allowlist for D3 support, which was used for these platforms.
+ *
+ * This allows quirking on Linux in a similar fashion.
+ */
+static const struct x86_cpu_id storage_d3_cpu_ids[] = {
+	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL),	/* Renoir */
+	X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL),	/* Lucienne */
+	{}
+};
+
+bool force_storage_d3(void)
+{
+	return x86_match_cpu(storage_d3_cpu_ids);
+}

drivers/block/aoe/aoechr.c

···
 	}
 
 	mp = kmemdup(msg, n, GFP_ATOMIC);
-	if (mp == NULL) {
-		printk(KERN_ERR "aoe: allocation failure, len=%ld\n", n);
+	if (!mp)
 		goto bail;
-	}
 
 	em->msg = mp;
 	em->flags |= EMFL_VALID;

drivers/block/drbd/drbd_receiver.c

···
 	}
 
 	new_net_conf = kmalloc(sizeof(struct net_conf), GFP_KERNEL);
-	if (!new_net_conf) {
-		drbd_err(connection, "Allocation of new net_conf failed\n");
+	if (!new_net_conf)
 		goto disconnect;
-	}
 
 	mutex_lock(&connection->data.mutex);
 	mutex_lock(&connection->resource->conf_update);
···
 
 		if (verify_tfm || csums_tfm) {
 			new_net_conf = kzalloc(sizeof(struct net_conf), GFP_KERNEL);
-			if (!new_net_conf) {
-				drbd_err(device, "Allocation of new net_conf failed\n");
+			if (!new_net_conf)
 				goto disconnect;
-			}
 
 			*new_net_conf = *old_net_conf;
 
···
 
 			new_disk_conf = kzalloc(sizeof(struct disk_conf), GFP_KERNEL);
 			if (!new_disk_conf) {
-				drbd_err(device, "Allocation of new disk_conf failed\n");
 				put_ldev(device);
 				return -ENOMEM;
 			}
···
 	device = peer_device->device;
 
 	p_uuid = kmalloc_array(UI_EXTENDED_SIZE, sizeof(*p_uuid), GFP_NOIO);
-	if (!p_uuid) {
-		drbd_err(device, "kmalloc of p_uuid failed\n");
+	if (!p_uuid)
 		return false;
-	}
 
 	for (i = UI_CURRENT; i < UI_EXTENDED_SIZE; i++)
 		p_uuid[i] = be64_to_cpu(p->uuid[i]);
···
 	}
 
 	peers_ch = kmalloc(pi.size, GFP_NOIO);
-	if (peers_ch == NULL) {
-		drbd_err(connection, "kmalloc of peers_ch failed\n");
+	if (!peers_ch) {
 		rv = -1;
 		goto fail;
 	}
···
 
 	resp_size = crypto_shash_digestsize(connection->cram_hmac_tfm);
 	response = kmalloc(resp_size, GFP_NOIO);
-	if (response == NULL) {
-		drbd_err(connection, "kmalloc of response failed\n");
+	if (!response) {
 		rv = -1;
 		goto fail;
 	}
···
 	}
 
 	right_response = kmalloc(resp_size, GFP_NOIO);
-	if (right_response == NULL) {
-		drbd_err(connection, "kmalloc of right_response failed\n");
+	if (!right_response) {
 		rv = -1;
 		goto fail;
 	}

drivers/block/floppy.c

···
 	switch (interpret_errors()) {
 	case 1:
 		cont->error();
+		break;
 	case 2:
 		break;
 	case 0:
···
 	if (!drive_state[current_drive].first_read_date)
 		drive_state[current_drive].first_read_date = jiffies;
 
-	nr_sectors = 0;
 	ssize = DIV_ROUND_UP(1 << raw_cmd->cmd[SIZECODE], 4);
 
 	if (reply_buffer[ST1] & ST1_EOC)

drivers/block/loop.c

···
 	blk_queue_physical_block_size(lo->lo_queue, bsize);
 	blk_queue_io_min(lo->lo_queue, bsize);
 
+	loop_config_discard(lo);
 	loop_update_rotational(lo);
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);

drivers/block/mtip32xx/mtip32xx.c

···
 static ssize_t mtip_hw_read_device_status(struct file *f, char __user *ubuf,
 						size_t len, loff_t *offset)
 {
-	struct driver_data *dd =  (struct driver_data *)f->private_data;
 	int size = *offset;
 	char *buf;
 	int rv = 0;
···
 		return 0;
 
 	buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL);
-	if (!buf) {
-		dev_err(&dd->pdev->dev,
-			"Memory allocation: status buffer\n");
+	if (!buf)
 		return -ENOMEM;
-	}
 
 	size += show_device_status(NULL, buf);
 
···
 		return 0;
 
 	buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL);
-	if (!buf) {
-		dev_err(&dd->pdev->dev,
-			"Memory allocation: register buffer\n");
+	if (!buf)
 		return -ENOMEM;
-	}
 
 	size += sprintf(&buf[size], "H/ S ACTive      : [ 0x");
 
···
 		return 0;
 
 	buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL);
-	if (!buf) {
-		dev_err(&dd->pdev->dev,
-			"Memory allocation: flag buffer\n");
+	if (!buf)
 		return -ENOMEM;
-	}
 
 	size += sprintf(&buf[size], "Flag-port : [ %08lX ]\n",
 							dd->port->flags);
···
 
 	dd->port = kzalloc_node(sizeof(struct mtip_port), GFP_KERNEL,
 				dd->numa_node);
-	if (!dd->port) {
-		dev_err(&dd->pdev->dev,
-			"Memory allocation: port structure\n");
+	if (!dd->port)
 		return -ENOMEM;
-	}
 
 	/* Continue workqueue setup */
 	for (i = 0; i < MTIP_MAX_SLOT_GROUPS; i++)
···
 		cpu_to_node(raw_smp_processor_id()), raw_smp_processor_id());
 
 	dd = kzalloc_node(sizeof(struct driver_data), GFP_KERNEL, my_node);
-	if (dd == NULL) {
-		dev_err(&pdev->dev,
-			"Unable to allocate memory for driver data\n");
+	if (!dd)
 		return -ENOMEM;
-	}
 
 	/* Attach the private data to this PCI device.  */
 	pci_set_drvdata(pdev, dd);

drivers/block/rsxx/dma.c

···
 	struct rsxx_dma	*dma;
 };
 
-#define DMA_TRACKER_LIST_SIZE8 (sizeof(struct dma_tracker_list) + \
-		(sizeof(struct dma_tracker) * RSXX_MAX_OUTSTANDING_CMDS))
-
 struct dma_tracker_list {
 	spinlock_t		lock;
 	int			head;
···
 
 	memset(&ctrl->stats, 0, sizeof(ctrl->stats));
 
-	ctrl->trackers = vmalloc(DMA_TRACKER_LIST_SIZE8);
+	ctrl->trackers = vmalloc(struct_size(ctrl->trackers, list,
+					     RSXX_MAX_OUTSTANDING_CMDS));
 	if (!ctrl->trackers)
 		return -ENOMEM;
 

drivers/block/sunvdc.c

···
 	}
 
 	port = kzalloc(sizeof(*port), GFP_KERNEL);
-	err = -ENOMEM;
 	if (!port) {
-		printk(KERN_ERR PFX "Cannot allocate vdc_port.\n");
+		err = -ENOMEM;
 		goto err_out_release_mdesc;
 	}
 

drivers/block/sx8.c

···
 
 	host = kzalloc(sizeof(*host), GFP_KERNEL);
 	if (!host) {
-		printk(KERN_ERR DRV_NAME "(%s): memory alloc failure\n",
-		       pci_name(pdev));
 		rc = -ENOMEM;
 		goto err_out_regions;
 	}

drivers/block/z2ram.c

···
 
 			case Z2MINOR_Z2ONLY:
 				z2ram_map = kmalloc(max_z2_map, GFP_KERNEL);
-				if (z2ram_map == NULL) {
-					printk(KERN_ERR DEVICE_NAME
-					       ": cannot get mem for z2ram_map\n");
+				if (!z2ram_map)
 					goto err_out;
-				}
 
 				get_z2ram();
 
···
 
 			case Z2MINOR_CHIPONLY:
 				z2ram_map = kmalloc(max_chip_map, GFP_KERNEL);
-				if (z2ram_map == NULL) {
-					printk(KERN_ERR DEVICE_NAME
-					       ": cannot get mem for z2ram_map\n");
+				if (!z2ram_map)
 					goto err_out;
-				}
 
 				get_chipram();
 

drivers/md/Kconfig

···
 	  If unsure, say Y.
 
 config MD_LINEAR
-	tristate "Linear (append) mode"
+	tristate "Linear (append) mode (deprecated)"
 	depends on BLK_DEV_MD
 	help
 	  If you say Y here, then your multiple devices driver will be able to
···
 	  If unsure, say Y.
 
 config MD_MULTIPATH
-	tristate "Multipath I/O support"
+	tristate "Multipath I/O support (deprecated)"
 	depends on BLK_DEV_MD
 	help
 	  MD_MULTIPATH provides a simple multi-path personality for use
···
 	  If unsure, say N.
 
 config MD_FAULTY
-	tristate "Faulty test module for MD"
+	tristate "Faulty test module for MD (deprecated)"
 	depends on BLK_DEV_MD
 	help
 	  The "faulty" module allows for a block device that occasionally returns

drivers/md/md-bitmap.c

···
 	&max_backlog_used.attr,
 	NULL
 };
-struct attribute_group md_bitmap_group = {
+const struct attribute_group md_bitmap_group = {
 	.name = "bitmap",
 	.attrs = md_bitmap_attrs,
 };

drivers/md/md-faulty.c

···
 module_init(raid_init);
 module_exit(raid_exit);
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Fault injection personality for MD");
+MODULE_DESCRIPTION("Fault injection personality for MD (deprecated)");
 MODULE_ALIAS("md-personality-10"); /* faulty */
 MODULE_ALIAS("md-faulty");
 MODULE_ALIAS("md-level--5");

drivers/md/md-linear.c

···
 module_init(linear_init);
 module_exit(linear_exit);
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Linear device concatenation personality for MD");
+MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)");
 MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/
 MODULE_ALIAS("md-linear");
 MODULE_ALIAS("md-level--1");

drivers/md/md-multipath.c

···
 module_init(multipath_init);
 module_exit(multipath_exit);
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("simple multi-path personality for MD");
+MODULE_DESCRIPTION("simple multi-path personality for MD (deprecated)");
 MODULE_ALIAS("md-personality-7"); /* MULTIPATH */
 MODULE_ALIAS("md-multipath");
 MODULE_ALIAS("md-level--4");

drivers/md/md.c

···
 }
 EXPORT_SYMBOL(md_handle_request);
 
-struct md_io {
-	struct mddev *mddev;
-	bio_end_io_t *orig_bi_end_io;
-	void *orig_bi_private;
-	struct block_device *orig_bi_bdev;
-	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;
-
-	bio_end_io_acct_remapped(bio, md_io->start_time, md_io->orig_bi_bdev);
-
-	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);
···
 			bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
 		return BLK_QC_T_NONE;
-	}
-
-	if (bio->bi_end_io != md_end_io) {
-		struct md_io *md_io;
-
-		md_io = mempool_alloc(&mddev->md_io_pool, GFP_NOIO);
-		md_io->mddev = mddev;
-		md_io->orig_bi_end_io = bio->bi_end_io;
-		md_io->orig_bi_private = bio->bi_private;
-		md_io->orig_bi_bdev = bio->bi_bdev;
-
-		bio->bi_end_io = md_end_io;
-		bio->bi_private = md_io;
-
-		md_io->start_time = bio_start_io_acct(bio);
 	}
 
 	/* bio could be mergeable after passing to underlayer */
···
 	return ERR_PTR(error);
 }
 
-static struct attribute_group md_redundancy_group;
+static const struct attribute_group md_redundancy_group;
 
 void mddev_unlock(struct mddev *mddev)
 {
···
 		 * test it under the same mutex to ensure its correct value
 		 * is seen.
 		 */
-		struct attribute_group *to_remove = mddev->to_remove;
+		const struct attribute_group *to_remove = mddev->to_remove;
 		mddev->to_remove = NULL;
 		mddev->sysfs_active = 1;
 		mutex_unlock(&mddev->reconfig_mutex);
···
 			       bdev_get_integrity(reference->bdev));
 
 	pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
-	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) {
+	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) ||
+	    (mddev->level != 1 && mddev->level != 10 &&
+	     bioset_integrity_create(&mddev->io_acct_set, BIO_POOL_SIZE))) {
+		/*
+		 * No need to handle the failure of bioset_integrity_create,
+		 * because the function is called by md_run() -> pers->run(),
+		 * md_run calls bioset_exit -> bioset_integrity_free in case
+		 * of failure case.
+		 */
 		pr_err("md: failed to create integrity pool for %s\n",
 		       mdname(mddev));
 		return -EINVAL;
···
 	&md_degraded.attr,
 	NULL,
 };
-static struct attribute_group md_redundancy_group = {
+static const struct attribute_group md_redundancy_group = {
 	.name = NULL,
 	.attrs = md_redundancy_attrs,
 };
···
 
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
-	mempool_exit(&mddev->md_io_pool);
+	if (mddev->level != 1 && mddev->level != 10)
+		bioset_exit(&mddev->io_acct_set);
 	kfree(mddev);
 }
 
···
 		 * Creating /dev/mdNNN via "newarray", so adjust hold_active.
 		 */
 		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;
 	disk = blk_alloc_disk(NUMA_NO_NODE);
···
 	if (!bioset_initialized(&mddev->sync_set)) {
 		err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 		if (err)
-			return err;
+			goto exit_bio_set;
+	}
+	if (mddev->level != 1 && mddev->level != 10 &&
+	    !bioset_initialized(&mddev->io_acct_set)) {
+		err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE,
+				  offsetof(struct md_io_acct, bio_clone), 0);
+		if (err)
+			goto exit_sync_set;
 	}
 
 	spin_lock(&pers_lock);
···
 			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
 		else
 			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
+		blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue);
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
···
 	module_put(pers->owner);
 	md_bitmap_destroy(mddev);
 abort:
-	bioset_exit(&mddev->bio_set);
+	if (mddev->level != 1 && mddev->level != 10)
+		bioset_exit(&mddev->io_acct_set);
+exit_sync_set:
 	bioset_exit(&mddev->sync_set);
+exit_bio_set:
+	bioset_exit(&mddev->bio_set);
 	return err;
 }
 EXPORT_SYMBOL_GPL(md_run);
···
 	__md_stop(mddev);
 	bioset_exit(&mddev->bio_set);
 	bioset_exit(&mddev->sync_set);
+	if (mddev->level != 1 && mddev->level != 10)
+		bioset_exit(&mddev->io_acct_set);
 }
 
 EXPORT_SYMBOL_GPL(md_stop);
···
 	submit_bio_noacct(discard_bio);
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
+
+static void md_end_io_acct(struct bio *bio)
+{
+	struct md_io_acct *md_io_acct = bio->bi_private;
+	struct bio *orig_bio = md_io_acct->orig_bio;
+
+	orig_bio->bi_status = bio->bi_status;
+
+	bio_end_io_acct(orig_bio, md_io_acct->start_time);
+	bio_put(bio);
+	bio_endio(orig_bio);
+}
+
+/*
+ * Used by personalities that don't already clone the bio and thus can't
+ * easily add the timestamp to their extended bio structure.
+ */
+void md_account_bio(struct mddev *mddev, struct bio **bio)
+{
+	struct md_io_acct *md_io_acct;
+	struct bio *clone;
+
+	if (!blk_queue_io_stat((*bio)->bi_bdev->bd_disk->queue))
+		return;
+
+	clone = bio_clone_fast(*bio, GFP_NOIO, &mddev->io_acct_set);
+	md_io_acct = container_of(clone, struct md_io_acct, bio_clone);
+	md_io_acct->orig_bio = *bio;
+	md_io_acct->start_time = bio_start_io_acct(*bio);
+
+	clone->bi_end_io = md_end_io_acct;
+	clone->bi_private = md_io_acct;
+	*bio = clone;
+}
+EXPORT_SYMBOL_GPL(md_account_bio);
 
 /* md_allow_write(mddev)
  * Calling this ensures that the array is marked 'active' so that writes

drivers/md/md.h

···
 	atomic_t			max_corr_read_errors; /* max read retries */
 	struct list_head		all_mddevs;
 
-	struct attribute_group		*to_remove;
+	const struct attribute_group	*to_remove;
 
 	struct bio_set			bio_set;
 	struct bio_set			sync_set; /* for sync operations like
 						   * metadata and bitmap writes
 						   */
-	mempool_t			md_io_pool;
+	struct bio_set			io_acct_set; /* for raid0 and raid5 io accounting */
 
 	/* Generic flush handling.
 	 * The last to finish preflush schedules a worker to submit
···
 	ssize_t (*show)(struct mddev *, char *);
 	ssize_t (*store)(struct mddev *, const char *, size_t);
 };
-extern struct attribute_group md_bitmap_group;
+extern const struct attribute_group md_bitmap_group;
 
 static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name)
 {
···
 	void			*private;
 };
 
+struct md_io_acct {
+	struct bio *orig_bio;
+	unsigned long start_time;
+	struct bio bio_clone;
+};
+
 #define THREAD_WAKEUP  0
 
 static inline void safe_put_page(struct page *p)
···
 extern void md_finish_reshape(struct mddev *mddev);
 void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev,
 			struct bio *bio, sector_t start, sector_t size);
+void md_account_bio(struct mddev *mddev, struct bio **bio);
 
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,

drivers/md/raid0.c

···
 		bio = split;
 	}
 
+	if (bio->bi_pool != &mddev->bio_set)
+		md_account_bio(mddev, &bio);
+
 	orig_sector = sector;
 	zone = find_zone(mddev->private, &sector);
 	switch (conf->layout) {

drivers/md/raid1.c

···
 	if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
 		bio->bi_status = BLK_STS_IOERR;
 
+	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
+		bio_end_io_acct(bio, r1_bio->start_time);
 	bio_endio(bio);
 }
 
···
 	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
 	int max_sectors;
 	int rdisk;
-	bool print_msg = !!r1_bio;
+	bool r1bio_existed = !!r1_bio;
 	char b[BDEVNAME_SIZE];
 
 	/*
···
 	 */
 	gfp_t gfp = r1_bio ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO;
 
-	if (print_msg) {
+	if (r1bio_existed) {
 		/* Need to get the block device name carefully */
 		struct md_rdev *rdev;
 		rcu_read_lock();
···
 
 	if (rdisk < 0) {
 		/* couldn't find anywhere to read from */
-		if (print_msg) {
+		if (r1bio_existed) {
 			pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
 					    mdname(mddev),
 					    b,
···
 	}
 	mirror = conf->mirrors + rdisk;
 
-	if (print_msg)
+	if (r1bio_existed)
 		pr_info_ratelimited("md/raid1:%s: redirecting sector %llu to other mirror: %s\n",
 				    mdname(mddev),
 				    (unsigned long long)r1_bio->sector,
···
 	}
 
 	r1_bio->read_disk = rdisk;
+
+	if (!r1bio_existed && blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
+		r1_bio->start_time = bio_start_io_acct(bio);
 
 	read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
 
···
 		r1_bio->sectors = max_sectors;
 	}
 
+	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
+		r1_bio->start_time = bio_start_io_acct(bio);
 	atomic_set(&r1_bio->remaining, 1);
 	atomic_set(&r1_bio->behind_remaining, 0);
 

drivers/md/raid1.h

···
 	sector_t		sector;
 	int			sectors;
 	unsigned long		state;
+	unsigned long		start_time;
 	struct mddev		*mddev;
 	/*
 	 * original bio going to /dev/mdx

drivers/md/raid10.c

···
 	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
 		bio->bi_status = BLK_STS_IOERR;
 
+	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
+		bio_end_io_acct(bio, r10_bio->start_time);
 	bio_endio(bio);
 	/*
 	 * Wake up any possible resync thread that waits for the device
···
 	}
 	slot = r10_bio->read_slot;
 
+	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
+		r10_bio->start_time = bio_start_io_acct(bio);
 	read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
 
 	r10_bio->devs[slot].bio = read_bio;
···
 		r10_bio->master_bio = bio;
 	}
 
+	if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue))
+		r10_bio->start_time = bio_start_io_acct(bio);
 	atomic_set(&r10_bio->remaining, 1);
 	md_bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0);
 

drivers/md/raid10.h

···
 	sector_t		sector;	/* virtual sector number */
 	int			sectors;
 	unsigned long		state;
+	unsigned long		start_time;
 	struct mddev		*mddev;
 	/*
 	 * original bio going to /dev/mdx

drivers/md/raid5.c

···
  */
 static void raid5_align_endio(struct bio *bi)
 {
-	struct bio* raid_bi  = bi->bi_private;
+	struct md_io_acct *md_io_acct = bi->bi_private;
+	struct bio *raid_bi = md_io_acct->orig_bio;
 	struct mddev *mddev;
 	struct r5conf *conf;
 	struct md_rdev *rdev;
 	blk_status_t error = bi->bi_status;
+	unsigned long start_time = md_io_acct->start_time;
 
 	bio_put(bi);
 
···
 	rdev_dec_pending(rdev, conf->mddev);
 
 	if (!error) {
+		if (blk_queue_io_stat(raid_bi->bi_bdev->bd_disk->queue))
+			bio_end_io_acct(raid_bi, start_time);
 		bio_endio(raid_bi);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
 			wake_up(&conf->wait_for_quiescent);
···
 	struct md_rdev *rdev;
 	sector_t sector, end_sector, first_bad;
 	int bad_sectors, dd_idx;
+	struct md_io_acct *md_io_acct;
+	bool did_inc;
 
 	if (!in_chunk_boundary(mddev, raid_bio)) {
 		pr_debug("%s: non aligned\n", __func__);
···
 	atomic_inc(&rdev->nr_pending);
 	rcu_read_unlock();
 
-	align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set);
-	bio_set_dev(align_bio, rdev->bdev);
-	align_bio->bi_end_io = raid5_align_endio;
-	align_bio->bi_private = raid_bio;
-	align_bio->bi_iter.bi_sector = sector;
-
-	raid_bio->bi_next = (void *)rdev;
-
-	if (is_badblock(rdev, sector, bio_sectors(align_bio), &first_bad,
+	if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad,
 			&bad_sectors)) {
-		bio_put(align_bio);
+		bio_put(raid_bio);
 		rdev_dec_pending(rdev, mddev);
 		return 0;
 	}
 
+	align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->io_acct_set);
+	md_io_acct = container_of(align_bio, struct md_io_acct, bio_clone);
+	raid_bio->bi_next = (void *)rdev;
+	if (blk_queue_io_stat(raid_bio->bi_bdev->bd_disk->queue))
+		md_io_acct->start_time = bio_start_io_acct(raid_bio);
+	md_io_acct->orig_bio = raid_bio;
+
+	bio_set_dev(align_bio, rdev->bdev);
+	align_bio->bi_end_io = raid5_align_endio;
+	align_bio->bi_private = md_io_acct;
+	align_bio->bi_iter.bi_sector = sector;
+
 	/* No reshape active, so we can trust rdev->data_offset */
 	align_bio->bi_iter.bi_sector += rdev->data_offset;
 
-	spin_lock_irq(&conf->device_lock);
-	wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0,
-			    conf->device_lock);
-	atomic_inc(&conf->active_aligned_reads);
-	spin_unlock_irq(&conf->device_lock);
+	did_inc = false;
+	if (conf->quiesce == 0) {
+		atomic_inc(&conf->active_aligned_reads);
+		did_inc = true;
+	}
+	/* need a memory barrier to detect the race with raid5_quiesce() */
+	if (!did_inc || smp_load_acquire(&conf->quiesce) != 0) {
+		/* quiesce is in progress, so we need to undo io activation and wait
+		 * for it to finish
+		 */
+		if (did_inc && atomic_dec_and_test(&conf->active_aligned_reads))
+			wake_up(&conf->wait_for_quiescent);
+		spin_lock_irq(&conf->device_lock);
+		wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0,
+				    conf->device_lock);
+		atomic_inc(&conf->active_aligned_reads);
+		spin_unlock_irq(&conf->device_lock);
+	}
 
 	if (mddev->gendisk)
 		trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk),
···
 	last_sector = bio_end_sector(bi);
 	bi->bi_next = NULL;
 
+	md_account_bio(mddev, &bi);
 	prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
 	for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) {
 		int previous;
···
 	&ppl_write_hint.attr,
 	NULL,
 };
-static struct attribute_group raid5_attrs_group = {
+static const struct attribute_group raid5_attrs_group = {
 	.name = NULL,
 	.attrs = raid5_attrs,
 };
···
 		 * active stripes can drain
 		 */
 		r5c_flush_cache(conf, INT_MAX);
-		conf->quiesce = 2;
+		/* need a memory barrier to make sure read_one_chunk() sees
+		 * quiesce started and reverts to slow (locked) path.
+		 */
+		smp_store_release(&conf->quiesce, 2);
 		wait_event_cmd(conf->wait_for_quiescent,
 				    atomic_read(&conf->active_stripes) == 0 &&
 				    atomic_read(&conf->active_aligned_reads) == 0,

drivers/nvme/host/Kconfig

···
 	help
 	   This option enables support for multipath access to NVMe
 	   subsystems.  If this option is enabled only a single
-	   /dev/nvmeXnY device will show up for each NVMe namespaces,
+	   /dev/nvmeXnY device will show up for each NVMe namespace,
 	   even if it is accessible through multiple controllers.
 
 config NVME_HWMON

drivers/nvme/host/core.c

···
 module_param(force_apst, bool, 0644);
 MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off");
 
+static unsigned long apst_primary_timeout_ms = 100;
+module_param(apst_primary_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(apst_primary_timeout_ms,
+	"primary APST timeout in ms");
+
+static unsigned long apst_secondary_timeout_ms = 2000;
+module_param(apst_secondary_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(apst_secondary_timeout_ms,
+	"secondary APST timeout in ms");
+
+static unsigned long apst_primary_latency_tol_us = 15000;
+module_param(apst_primary_latency_tol_us, ulong, 0644);
+MODULE_PARM_DESC(apst_primary_latency_tol_us,
+	"primary APST latency tolerance in us");
+
+static unsigned long apst_secondary_latency_tol_us = 100000;
+module_param(apst_secondary_latency_tol_us, ulong, 0644);
+MODULE_PARM_DESC(apst_secondary_latency_tol_us,
+	"secondary APST latency tolerance in us");
+
 static bool streams;
 module_param(streams, bool, 0644);
 MODULE_PARM_DESC(streams, "turn on support for Streams write directives");
···
 
 static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
 {
-	struct nvme_command c;
-
-	memset(&c, 0, sizeof(c));
+	struct nvme_command c = { };
 
 	c.directive.opcode = nvme_admin_directive_send;
 	c.directive.nsid = cpu_to_le32(NVME_NSID_ALL);
···
 static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
 				  struct streams_directive_params *s, u32 nsid)
 {
-	struct nvme_command c;
+	struct nvme_command c = { };
 
-	memset(&c, 0, sizeof(c));
 	memset(s, 0, sizeof(*s));
 
 	c.directive.opcode = nvme_admin_directive_recv;
···
 		unsigned int dword11, void *buffer, size_t buflen, u32 *result)
 {
 	union nvme_result res = { 0 };
-	struct nvme_command c;
+	struct nvme_command c = { };
 	int ret;
 
-	memset(&c, 0, sizeof(c));
 	c.features.opcode = op;
 	c.features.fid = cpu_to_le32(fid);
 	c.features.dword11 = cpu_to_le32(dword11);
···
 	queue_work(nvme_wq, &ctrl->async_event_work);
 }
 
-/*
- * Issue ioctl requests on the first available path.  Note that unlike normal
- * block layer requests we will not retry failed request on another controller.
- */
-struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk,
-		struct nvme_ns_head **head, int *srcu_idx)
-{
-#ifdef CONFIG_NVME_MULTIPATH
-	if (disk->fops == &nvme_ns_head_ops) {
-		struct nvme_ns *ns;
-
-		*head = disk->private_data;
-		*srcu_idx = srcu_read_lock(&(*head)->srcu);
-		ns = nvme_find_path(*head);
-		if (!ns)
-			srcu_read_unlock(&(*head)->srcu, *srcu_idx);
-		return ns;
-	}
-#endif
-	*head = NULL;
-	*srcu_idx = -1;
-	return disk->private_data;
-}
-
-void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
-{
-	if (head)
-		srcu_read_unlock(&head->srcu, idx);
-}
-
 static int nvme_ns_open(struct nvme_ns *ns)
 {
 
···
 static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type,
 				u32 max_integrity_segments)
 {
-	struct blk_integrity integrity;
+	struct blk_integrity integrity = { };
 
-	memset(&integrity, 0, sizeof(integrity));
 	switch (pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
 		integrity.profile = &t10_pi_type3_crc;
···
 	}
 };
 
+static int nvme_send_ns_head_pr_command(struct block_device *bdev,
+		struct nvme_command *c, u8 data[16])
+{
+	struct nvme_ns_head *head = bdev->bd_disk->private_data;
+	int srcu_idx = srcu_read_lock(&head->srcu);
+	struct nvme_ns *ns = nvme_find_path(head);
+	int ret = -EWOULDBLOCK;
+
+	if (ns) {
+		c->common.nsid = cpu_to_le32(ns->head->ns_id);
+		ret = nvme_submit_sync_cmd(ns->queue, c, data, 16);
+	}
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+	
+static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
+		u8 data[16])
+{
+	c->common.nsid = cpu_to_le32(ns->head->ns_id);
+	return nvme_submit_sync_cmd(ns->queue, c, data, 16);
+}
+
 static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
 				u64 key, u64 sa_key, u8 op)
 {
-	struct nvme_ns_head *head = NULL;
-	struct nvme_ns *ns;
-	struct nvme_command c;
-	int srcu_idx, ret;
+	struct nvme_command c = { };
 	u8 data[16] = { 0, };
-
-	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
-	if (unlikely(!ns))
-		return -EWOULDBLOCK;
 
 	put_unaligned_le64(key, &data[0]);
 	put_unaligned_le64(sa_key, &data[8]);
 
-	memset(&c, 0, sizeof(c));
 	c.common.opcode = op;
-	c.common.nsid = cpu_to_le32(ns->head->ns_id);
 	c.common.cdw10 = cpu_to_le32(cdw10);
 
-	ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16);
-	nvme_put_ns_from_disk(head, srcu_idx);
-	return ret;
+	if (IS_ENABLED(CONFIG_NVME_MULTIPATH) &&
+	    bdev->bd_disk->fops == &nvme_ns_head_ops)
+		return nvme_send_ns_head_pr_command(bdev, &c, data);
+	return nvme_send_ns_pr_command(bdev->bd_disk->private_data, &c, data);
 }
 
 static int nvme_pr_register(struct block_device *bdev, u64 old,
···
 		bool send)
 {
 	struct nvme_ctrl *ctrl = data;
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 
-	memset(&cmd, 0, sizeof(cmd));
 	if (send)
 		cmd.common.opcode = nvme_admin_security_send;
 	else
···
 }
 EXPORT_SYMBOL_GPL(nvme_sec_submit);
 #endif /* CONFIG_BLK_SED_OPAL */
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static int nvme_report_zones(struct gendisk *disk, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	return nvme_ns_report_zones(disk->private_data, sector, nr_zones, cb,
+			data);
+}
+#else
+#define nvme_report_zones	NULL
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static const struct block_device_operations nvme_bdev_ops = {
 	.owner		= THIS_MODULE,
···
 }
 
 /*
+ * The function checks whether the given total (exlat + enlat) latency of
+ * a power state allows the latter to be used as an APST transition target.
+ * It does so by comparing the latency to the primary and secondary latency
+ * tolerances defined by module params. If there's a match, the corresponding
+ * timeout value is returned and the matching tolerance index (1 or 2) is
+ * reported.
+ */
+static bool nvme_apst_get_transition_time(u64 total_latency,
+		u64 *transition_time, unsigned *last_index)
+{
+	if (total_latency <= apst_primary_latency_tol_us) {
+		if (*last_index == 1)
+			return false;
+		*last_index = 1;
+		*transition_time = apst_primary_timeout_ms;
+		return true;
+	}
+	if (apst_secondary_timeout_ms &&
+		total_latency <= apst_secondary_latency_tol_us) {
+		if (*last_index <= 2)
+			return false;
+		*last_index = 2;
+		*transition_time = apst_secondary_timeout_ms;
+		return true;
+	}
+	return false;
+}
+
+/*
  * APST (Autonomous Power State Transition) lets us program a table of power
  * state transitions that the controller will perform automatically.
- * We configure it with a simple heuristic: we are willing to spend at most 2%
- * of the time transitioning between power states.  Therefore, when running in
- * any given state, we will enter the next lower-power non-operational state
- * after waiting 50 * (enlat + exlat) microseconds, as long as that state's exit
- * latency is under the requested maximum latency.
+ *
+ * Depending on module params, one of the two supported techniques will be used:
+ *
+ * - If the parameters provide explicit timeouts and tolerances, they will be
+ *   used to build a table with up to 2 non-operational states to transition to.
+ *   The default parameter values were selected based on the values used by
+ *   Microsoft's and Intel's NVMe drivers. Yet, since we don't implement dynamic
+ *   regeneration of the APST table in the event of switching between external
+ *   and battery power, the timeouts and tolerances reflect a compromise
+ *   between values used by Microsoft for AC and battery scenarios.
+ * - If not, we'll configure the table with a simple heuristic: we are willing
+ *   to spend at most 2% of the time transitioning between power states.
+ *   Therefore, when running in any given state, we will enter the next
+ *   lower-power non-operational state after waiting 50 * (enlat + exlat)
+ *   microseconds, as long as that state's exit latency is under the requested
+ *   maximum latency.
  *
  * We will not autonomously enter any non-operational state for which the total
  * latency exceeds ps_max_latency_us.
···
 	int max_ps = -1;
 	int state;
 	int ret;
+	unsigned last_lt_index = UINT_MAX;
 
 	/*
 	 * If APST isn't supported or if we haven't been initialized yet,
···
 			le32_to_cpu(ctrl->psd[state].entry_lat);
 
 		/*
-		 * This state is good.  Use it as the APST idle target for
-		 * higher power states.
+		 * This state is good. It can be used as the APST idle target
+		 * for higher power states.
 		 */
-		transition_ms = total_latency_us + 19;
-		do_div(transition_ms, 20);
-		if (transition_ms > (1 << 24) - 1)
-			transition_ms = (1 << 24) - 1;
+		if (apst_primary_timeout_ms && apst_primary_latency_tol_us) {
+			if (!nvme_apst_get_transition_time(total_latency_us,
+					&transition_ms, &last_lt_index))
+				continue;
+		} else {
+			transition_ms = total_latency_us + 19;
+			do_div(transition_ms, 20);
+			if (transition_ms > (1 << 24) - 1)
+				transition_ms = (1 << 24) - 1;
+		}
 
 		target = cpu_to_le64((state << 3) | (transition_ms << 8));
 		if (max_ps == -1)
···
 
 		ret = add_uevent_var(env, "NVME_HOST_TRADDR=%s",
 				opts->host_traddr ?: "none");
+		if (ret)
+			return ret;
+
+		ret = add_uevent_var(env, "NVME_HOST_IFACE=%s",
+				opts->host_iface ?: "none");
 	}
 	return ret;
 }

drivers/nvme/host/fabrics.c

···
 	if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR)
 		len += scnprintf(buf + len, size - len, "%shost_traddr=%s",
 				(len) ? "," : "", ctrl->opts->host_traddr);
+	if (ctrl->opts->mask & NVMF_OPT_HOST_IFACE)
+		len += scnprintf(buf + len, size - len, "%shost_iface=%s",
+				(len) ? "," : "", ctrl->opts->host_iface);
 	len += scnprintf(buf + len, size - len, "\n");
 
 	return len;
···
  */
 int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	union nvme_result res;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.prop_get.opcode = nvme_fabrics_command;
 	cmd.prop_get.fctype = nvme_fabrics_type_property_get;
 	cmd.prop_get.attrib = 1;
···
  */
 int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.prop_set.opcode = nvme_fabrics_command;
 	cmd.prop_set.fctype = nvme_fabrics_type_property_set;
 	cmd.prop_set.attrib = 0;
···
 EXPORT_SYMBOL_GPL(nvmf_reg_write32);
 
 /**
- * nvmf_log_connect_error() - Error-parsing-diagnostic print
- * out function for connect() errors.
- *
- * @ctrl: the specific /dev/nvmeX device that had the error.
- *
- * @errval: Error code to be decoded in a more human-friendly
- *	    printout.
- *
- * @offset: For use with the NVMe error code NVME_SC_CONNECT_INVALID_PARAM.
- *
- * @cmd: This is the SQE portion of a submission capsule.
- *
- * @data: This is the "Data" portion of a submission capsule.
+ * nvmf_log_connect_error() - Error-parsing-diagnostic print out function for
+ * 				connect() errors.
+ * @ctrl:	The specific /dev/nvmeX device that had the error.
+ * @errval:	Error code to be decoded in a more human-friendly
+ * 		printout.
+ * @offset:	For use with the NVMe error code
+ * 		NVME_SC_CONNECT_INVALID_PARAM.
+ * @cmd:	This is the SQE portion of a submission capsule.
+ * @data:	This is the "Data" portion of a submission capsule.
  */
 static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
 		int errval, int offset, struct nvme_command *cmd,
 		struct nvmf_connect_data *data)
 {
-	int err_sctype = errval & (~NVME_SC_DNR);
+	int err_sctype = errval & ~NVME_SC_DNR;
 
 	switch (err_sctype) {
-
 	case (NVME_SC_CONNECT_INVALID_PARAM):
 		if (offset >> 16) {
 			char *inv_data = "Connect Invalid Data Parameter";
···
 			}
 		}
 		break;
-
 	case NVME_SC_CONNECT_INVALID_HOST:
 		dev_err(ctrl->device,
 			"Connect for subsystem %s is not allowed, hostnqn: %s\n",
 			data->subsysnqn, data->hostnqn);
 		break;
-
 	case NVME_SC_CONNECT_CTRL_BUSY:
 		dev_err(ctrl->device,
 			"Connect command failed: controller is busy or not available\n");
 		break;
-
 	case NVME_SC_CONNECT_FORMAT:
 		dev_err(ctrl->device,
 			"Connect incompatible format: %d",
 			cmd->connect.recfmt);
 		break;
-
 	case NVME_SC_HOST_PATH_ERROR:
 		dev_err(ctrl->device,
 			"Connect command failed: host path error\n");
 		break;
-
 	default:
 		dev_err(ctrl->device,
 			"Connect command failed, error wo/DNR bit: %d\n",
 			err_sctype);
 		break;
-	} /* switch (err_sctype) */
+	}
 }
 
 /**
···
  */
 int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	union nvme_result res;
 	struct nvmf_connect_data *data;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.connect.opcode = nvme_fabrics_command;
 	cmd.connect.fctype = nvme_fabrics_type_connect;
 	cmd.connect.qid = 0;
···
  */
 int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll)
 {
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	struct nvmf_connect_data *data;
 	union nvme_result res;
 	int ret;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.connect.opcode = nvme_fabrics_command;
 	cmd.connect.fctype = nvme_fabrics_type_connect;
 	cmd.connect.qid = cpu_to_le16(qid);
···
 	{ NVMF_OPT_KATO,		"keep_alive_tmo=%d"	},
 	{ NVMF_OPT_HOSTNQN,		"hostnqn=%s"		},
 	{ NVMF_OPT_HOST_TRADDR,		"host_traddr=%s"	},
+	{ NVMF_OPT_HOST_IFACE,		"host_iface=%s"		},
 	{ NVMF_OPT_HOST_ID,		"hostid=%s"		},
 	{ NVMF_OPT_DUP_CONNECT,		"duplicate_connect"	},
 	{ NVMF_OPT_DISABLE_SQFLOW,	"disable_sqflow"	},
···
 			kfree(opts->host_traddr);
 			opts->host_traddr = p;
 			break;
+		case NVMF_OPT_HOST_IFACE:
+			p = match_strdup(args);
+			if (!p) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			kfree(opts->host_iface);
+			opts->host_iface = p;
+			break;
 		case NVMF_OPT_HOST_ID:
 			p = match_strdup(args);
 			if (!p) {
···
 	kfree(opts->trsvcid);
 	kfree(opts->subsysnqn);
 	kfree(opts->host_traddr);
+	kfree(opts->host_iface);
 	kfree(opts);
 }
 EXPORT_SYMBOL_GPL(nvmf_free_options);

drivers/nvme/host/fabrics.h

···
 	NVMF_OPT_NR_POLL_QUEUES = 1 << 18,
 	NVMF_OPT_TOS		= 1 << 19,
 	NVMF_OPT_FAIL_FAST_TMO	= 1 << 20,
+	NVMF_OPT_HOST_IFACE	= 1 << 21,
 };
 
 /**
···
  * @trsvcid:	The transport-specific TRSVCID field for a port on the
  *              subsystem which is adding a controller.
  * @host_traddr: A transport-specific field identifying the NVME host port
- *              to use for the connection to the controller.
+ *     to use for the connection to the controller.
+ * @host_iface: A transport-specific field identifying the NVME host
+ *     interface to use for the connection to the controller.
  * @queue_size: Number of IO queue elements.
  * @nr_io_queues: Number of controller IO queues that will be established.
  * @reconnect_delay: Time between two consecutive reconnect attempts.
···
 	char			*traddr;
 	char			*trsvcid;
 	char			*host_traddr;
+	char			*host_iface;
 	size_t			queue_size;
 	unsigned int		nr_io_queues;
 	unsigned int		reconnect_delay;

drivers/nvme/host/fc.c

···
 	}
 
 	/* FC-NVME supports normal SGL Data Block Descriptors */
-	if (!(ctrl->ctrl.sgls & ((1 << 0) | (1 << 1)))) {
+	if (!nvme_ctrl_sgl_supported(&ctrl->ctrl)) {
 		dev_err(ctrl->ctrl.device,
 			"Mandatory sgls are not supported!\n");
 		ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;

drivers/nvme/host/ioctl.c

···
 			metadata, meta_len, lower_32_bits(io.slba), NULL, 0);
 }
 
+static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
+					struct nvme_ns *ns, __u32 nsid)
+{
+	if (ns && nsid != ns->head->ns_id) {
+		dev_err(ctrl->device,
+			"%s: nsid (%u) in cmd does not match nsid (%u)"
+			"of namespace\n",
+			current->comm, nsid, ns->head->ns_id);
+		return false;
+	}
+
+	return true;
+}
+
 static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			struct nvme_passthru_cmd __user *ucmd)
 {
···
 		return -EFAULT;
 	if (cmd.flags)
 		return -EINVAL;
-	if (ns && cmd.nsid != ns->head->ns_id) {
-		dev_err(ctrl->device,
-			"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
-			current->comm, cmd.nsid, ns->head->ns_id);
+	if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
 		return -EINVAL;
-	}
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = cmd.opcode;
···
 		return -EFAULT;
 	if (cmd.flags)
 		return -EINVAL;
-	if (ns && cmd.nsid != ns->head->ns_id) {
-		dev_err(ctrl->device,
-			"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
-			current->comm, cmd.nsid, ns->head->ns_id);
+	if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid))
 		return -EINVAL;
-	}
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = cmd.opcode;
···
 #ifdef CONFIG_NVME_MULTIPATH
 static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
 		void __user *argp, struct nvme_ns_head *head, int srcu_idx)
+	__releases(&head->srcu)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
 
 	nvme_get_ctrl(ns->ctrl);
-	nvme_put_ns_from_disk(head, srcu_idx);
+	srcu_read_unlock(&head->srcu, srcu_idx);
 	ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp);
 
 	nvme_put_ctrl(ctrl);
···
 int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, unsigned long arg)
 {
-	struct nvme_ns_head *head = NULL;
+	struct nvme_ns_head *head = bdev->bd_disk->private_data;
 	void __user *argp = (void __user *)arg;
 	struct nvme_ns *ns;
-	int srcu_idx, ret;
+	int srcu_idx, ret = -EWOULDBLOCK;
 
-	ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx);
-	if (unlikely(!ns))
-		return -EWOULDBLOCK;
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (!ns)
+		goto out_unlock;
 
 	/*
 	 * Handle ioctls that apply to the controller instead of the namespace
···
 	 * deadlock when deleting namespaces using the passthrough interface.
 	 */
 	if (is_ctrl_ioctl(cmd))
-		ret = nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
-	else {
-		ret = nvme_ns_ioctl(ns, cmd, argp);
-		nvme_put_ns_from_disk(head, srcu_idx);
-	}
+		return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
 
+	ret = nvme_ns_ioctl(ns, cmd, argp);
+out_unlock:
+	srcu_read_unlock(&head->srcu, srcu_idx);
 	return ret;
 }
 
···
 		container_of(cdev, struct nvme_ns_head, cdev);
 	void __user *argp = (void __user *)arg;
 	struct nvme_ns *ns;
-	int srcu_idx, ret;
+	int srcu_idx, ret = -EWOULDBLOCK;
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);
-	if (!ns) {
-		srcu_read_unlock(&head->srcu, srcu_idx);
-		return -EWOULDBLOCK;
-	}
+	if (!ns)
+		goto out_unlock;
 
 	if (is_ctrl_ioctl(cmd))
 		return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
 
 	ret = nvme_ns_ioctl(ns, cmd, argp);
-	nvme_put_ns_from_disk(head, srcu_idx);
-
+out_unlock:
+	srcu_read_unlock(&head->srcu, srcu_idx);
 	return ret;
 }
 #endif /* CONFIG_NVME_MULTIPATH */

drivers/nvme/host/multipath.c

···
 	nvme_put_ns_head(disk->private_data);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int nvme_ns_head_report_zones(struct gendisk *disk, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data)
+{
+	struct nvme_ns_head *head = disk->private_data;
+	struct nvme_ns *ns;
+	int srcu_idx, ret = -EWOULDBLOCK;
+
+	srcu_idx = srcu_read_lock(&head->srcu);
+	ns = nvme_find_path(head);
+	if (ns)
+		ret = nvme_ns_report_zones(ns, sector, nr_zones, cb, data);
+	srcu_read_unlock(&head->srcu, srcu_idx);
+	return ret;
+}
+#else
+#define nvme_ns_head_report_zones	NULL
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 const struct block_device_operations nvme_ns_head_ops = {
 	.owner		= THIS_MODULE,
 	.submit_bio	= nvme_ns_head_submit_bio,
···
 	.release	= nvme_ns_head_release,
 	.ioctl		= nvme_ns_head_ioctl,
 	.getgeo		= nvme_getgeo,
-	.report_zones	= nvme_report_zones,
+	.report_zones	= nvme_ns_head_report_zones,
 	.pr_ops		= &nvme_pr_ops,
 };
 
···
 		next = bio->bi_next;
 		bio->bi_next = NULL;
 
-		/*
-		 * Reset disk to the mpath node and resubmit to select a new
-		 * path.
-		 */
-		bio_set_dev(bio, head->disk->part0);
 		submit_bio_noacct(bio);
 	}
 }
···
 	if (!multipath || !ctrl->subsys ||
 	    !(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA))
 		return 0;
+
+	if (!ctrl->max_namespaces ||
+	    ctrl->max_namespaces > le32_to_cpu(id->nn)) {
+		dev_err(ctrl->device,
+			"Invalid MNAN value %u\n", ctrl->max_namespaces);
+		return -EINVAL;
+	}
 
 	ctrl->anacap = id->anacap;
 	ctrl->anatt = id->anatt;

drivers/nvme/host/nvme.h

···
 void nvme_queue_scan(struct nvme_ctrl *ctrl);
 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);
 bool nvme_tryget_ns_head(struct nvme_ns_head *head);
 void nvme_put_ns_head(struct nvme_ns_head *head);
 int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
···
 extern const struct pr_ops nvme_pr_ops;
 extern const struct block_device_operations nvme_ns_head_ops;
 
+struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
 #ifdef CONFIG_NVME_MULTIPATH
 static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
 {
···
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
-struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
 
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
···
 #endif /* CONFIG_NVME_MULTIPATH */
 
 int nvme_revalidate_zones(struct nvme_ns *ns);
+int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data);
 #ifdef CONFIG_BLK_DEV_ZONED
 int nvme_update_zone_info(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)
···
 {
 }
 #endif
+
+static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl)
+{
+	return ctrl->sgls & ((1 << 0) | (1 << 1));
+}
 
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			 u8 opcode);

drivers/nvme/host/pci.c

···
 
 static void nvme_dbbuf_set(struct nvme_dev *dev)
 {
-	struct nvme_command c;
+	struct nvme_command c = { };
 	unsigned int i;
 
 	if (!dev->dbbuf_dbs)
 		return;
 
-	memset(&c, 0, sizeof(c));
 	c.dbbuf.opcode = nvme_admin_dbbuf;
 	c.dbbuf.prp1 = cpu_to_le64(dev->dbbuf_dbs_dma_addr);
 	c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
···
 
 	avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg);
 
-	if (!(dev->ctrl.sgls & ((1 << 0) | (1 << 1))))
+	if (!nvme_ctrl_sgl_supported(&dev->ctrl))
 		return false;
 	if (!iod->nvmeq->qid)
 		return false;
···
 		dma_pool_free(dev->prp_page_pool, prp_list, dma_addr);
 		dma_addr = next_dma_addr;
 	}
-
 }
 
 static void nvme_free_sgls(struct nvme_dev *dev, struct request *req)
···
 		dma_pool_free(dev->prp_page_pool, sg_list, dma_addr);
 		dma_addr = next_dma_addr;
 	}
-
 }
 
 static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req)
···
 							     &cmnd->rw, &bv);
 
 			if (iod->nvmeq->qid && sgl_threshold &&
-			    dev->ctrl.sgls & ((1 << 0) | (1 << 1)))
+			    nvme_ctrl_sgl_supported(&dev->ctrl))
 				return nvme_setup_sgl_simple(dev, req,
 							     &cmnd->rw, &bv);
 		}
···
 
 static inline void nvme_update_cq_head(struct nvme_queue *nvmeq)
 {
-	u16 tmp = nvmeq->cq_head + 1;
+	u32 tmp = nvmeq->cq_head + 1;
 
 	if (tmp == nvmeq->q_depth) {
 		nvmeq->cq_head = 0;
···
 {
 	struct nvme_dev *dev = to_nvme_dev(ctrl);
 	struct nvme_queue *nvmeq = &dev->queues[0];
-	struct nvme_command c;
+	struct nvme_command c = { };
 
-	memset(&c, 0, sizeof(c));
 	c.common.opcode = nvme_admin_async_event;
 	c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
 	nvme_submit_cmd(nvmeq, &c, true);
···
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
 {
-	struct nvme_command c;
+	struct nvme_command c = { };
 
-	memset(&c, 0, sizeof(c));
 	c.delete_queue.opcode = opcode;
 	c.delete_queue.qid = cpu_to_le16(id);
 
···
 static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
 		struct nvme_queue *nvmeq, s16 vector)
 {
-	struct nvme_command c;
+	struct nvme_command c = { };
 	int flags = NVME_QUEUE_PHYS_CONTIG;
 
 	if (!test_bit(NVMEQ_POLLED, &nvmeq->flags))
···
 	 * Note: we (ab)use the fact that the prp fields survive if no data
 	 * is attached to the request.
 	 */
-	memset(&c, 0, sizeof(c));
 	c.create_cq.opcode = nvme_admin_create_cq;
 	c.create_cq.prp1 = cpu_to_le64(nvmeq->cq_dma_addr);
 	c.create_cq.cqid = cpu_to_le16(qid);
···
 						struct nvme_queue *nvmeq)
 {
 	struct nvme_ctrl *ctrl = &dev->ctrl;
-	struct nvme_command c;
+	struct nvme_command c = { };
 	int flags = NVME_QUEUE_PHYS_CONTIG;
 
 	/*
···
 	 * Note: we (ab)use the fact that the prp fields survive if no data
 	 * is attached to the request.
 	 */
-	memset(&c, 0, sizeof(c));
 	c.create_sq.opcode = nvme_admin_create_sq;
 	c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_dma_addr);
 	c.create_sq.sqid = cpu_to_le16(qid);
···
 	struct nvme_queue *nvmeq = iod->nvmeq;
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *abort_req;
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
 	/* If PCI error recovery process is happening, we cannot reset or
···
 	}
 	iod->aborted = 1;
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.abort.opcode = nvme_admin_abort_cmd;
 	cmd.abort.cid = req->tag;
 	cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
···
 {
 	u32 host_mem_size = dev->host_mem_size >> NVME_CTRL_PAGE_SHIFT;
 	u64 dma_addr = dev->host_mem_descs_dma;
-	struct nvme_command c;
+	struct nvme_command c = { };
 	int ret;
 
-	memset(&c, 0, sizeof(c));
 	c.features.opcode	= nvme_admin_set_features;
 	c.features.fid		= cpu_to_le32(NVME_FEAT_HOST_MEM_BUF);
 	c.features.dword11	= cpu_to_le32(bits);
···
 {
 	struct request_queue *q = nvmeq->dev->ctrl.admin_q;
 	struct request *req;
-	struct nvme_command cmd;
+	struct nvme_command cmd = { };
 
-	memset(&cmd, 0, sizeof(cmd));
 	cmd.delete_queue.opcode = opcode;
 	cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid);
 
···
 	return 0;
 }
 
-#ifdef CONFIG_ACPI
-static bool nvme_acpi_storage_d3(struct pci_dev *dev)
-{
-	struct acpi_device *adev;
-	struct pci_dev *root;
-	acpi_handle handle;
-	acpi_status status;
-	u8 val;
-
-	/*
-	 * Look for _DSD property specifying that the storage device on the port
-	 * must use D3 to support deep platform power savings during
-	 * suspend-to-idle.
-	 */
-	root = pcie_find_root_port(dev);
-	if (!root)
-		return false;
-
-	adev = ACPI_COMPANION(&root->dev);
-	if (!adev)
-		return false;
-
-	/*
-	 * The property is defined in the PXSX device for South complex ports
-	 * and in the PEGP device for North complex ports.
-	 */
-	status = acpi_get_handle(adev->handle, "PXSX", &handle);
-	if (ACPI_FAILURE(status)) {
-		status = acpi_get_handle(adev->handle, "PEGP", &handle);
-		if (ACPI_FAILURE(status))
-			return false;
-	}
-
-	if (acpi_bus_get_device(handle, &adev))
-		return false;
-
-	if (fwnode_property_read_u8(acpi_fwnode_handle(adev), "StorageD3Enable",
-			&val))
-		return false;
-	return val == 1;
-}
-#else
-static inline bool nvme_acpi_storage_d3(struct pci_dev *dev)
-{
-	return false;
-}
-#endif /* CONFIG_ACPI */
-
 static void nvme_async_probe(void *data, async_cookie_t cookie)
 {
 	struct nvme_dev *dev = data;
···
 
 	quirks |= check_vendor_combination_bug(pdev);
 
-	if (!noacpi && nvme_acpi_storage_d3(pdev)) {
+	if (!noacpi && acpi_storage_d3(&pdev->dev)) {
 		/*
 		 * Some systems use a bios work around to ask for D3 on
 		 * platforms that support kernel managed suspend.

drivers/nvme/host/rdma.c

···
 
 static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 {
-	int ret = -EINVAL;
+	int ret;
 	bool changed;
 
 	ret = nvme_rdma_configure_admin_queue(ctrl, new);

drivers/nvme/host/tcp.c

···
 	struct blk_mq_tag_set	admin_tag_set;
 	struct sockaddr_storage addr;
 	struct sockaddr_storage src_addr;
+	struct net_device	*ndev;
 	struct nvme_ctrl	ctrl;
 
 	struct work_struct	err_work;
···
 		}
 	}
 
+	if (nctrl->opts->mask & NVMF_OPT_HOST_IFACE) {
+		char *iface = nctrl->opts->host_iface;
+		sockptr_t optval = KERNEL_SOCKPTR(iface);
+
+		ret = sock_setsockopt(queue->sock, SOL_SOCKET, SO_BINDTODEVICE,
+				      optval, strlen(iface));
+		if (ret) {
+			dev_err(nctrl->device,
+			  "failed to bind to interface %s queue %d err %d\n",
+			  iface, qid, ret);
+			goto err_sock;
+		}
+	}
+
 	queue->hdr_digest = nctrl->opts->hdr_digest;
 	queue->data_digest = nctrl->opts->data_digest;
 	if (queue->hdr_digest || queue->data_digest) {
···
 		return ret;
 
 	if (ctrl->icdoff) {
+		ret = -EOPNOTSUPP;
 		dev_err(ctrl->device, "icdoff is not supported!\n");
 		goto destroy_admin;
 	}
 
-	if (!(ctrl->sgls & ((1 << 0) | (1 << 1)))) {
+	if (!nvme_ctrl_sgl_supported(ctrl)) {
+		ret = -EOPNOTSUPP;
 		dev_err(ctrl->device, "Mandatory sgls are not supported!\n");
 		goto destroy_admin;
 	}
···
 		}
 	}
 
+	if (opts->mask & NVMF_OPT_HOST_IFACE) {
+		ctrl->ndev = dev_get_by_name(&init_net, opts->host_iface);
+		if (!ctrl->ndev) {
+			pr_err("invalid interface passed: %s\n",
+			       opts->host_iface);
+			ret = -ENODEV;
+			goto out_free_ctrl;
+		}
+	}
+
 	if (!opts->duplicate_connect && nvme_tcp_existing_controller(opts)) {
 		ret = -EALREADY;
 		goto out_free_ctrl;
···
 			  NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO |
 			  NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST |
 			  NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES |
-			  NVMF_OPT_TOS,
+			  NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE,
 	.create_ctrl	= nvme_tcp_create_ctrl,
 };
 

drivers/nvme/host/zns.c

···
 	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)
+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;
 	struct nvme_command c = { };
 	int ret, zone_idx = 0;
 	unsigned int nz, i;
 	size_t buflen;
+
+	if (ns->head->ids.csi != NVME_CSI_ZNS)
+		return -EINVAL;
 
 	report = nvme_zns_alloc_report_buffer(ns, nr_zones, &buflen);
 	if (!report)
···
 		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;
 }
 

drivers/nvme/target/Makefile

···
 nvmet-y		+= core.o configfs.o admin-cmd.o fabrics-cmd.o \
 			discovery.o io-cmd-file.o io-cmd-bdev.o
 nvmet-$(CONFIG_NVME_TARGET_PASSTHRU)	+= passthru.o
+nvmet-$(CONFIG_BLK_DEV_ZONED)		+= zns.o
 nvme-loop-y	+= loop.o
 nvmet-rdma-y	+= rdma.o
 nvmet-fc-y	+= fc.o

drivers/nvme/target/admin-cmd.c

···
 	nvmet_req_complete(req, status);
 }
 
-static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
+static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
 {
-	u16 status = NVME_SC_INTERNAL;
-	struct nvme_effects_log *log;
-
-	log = kzalloc(sizeof(*log), GFP_KERNEL);
-	if (!log)
-		goto out;
-
 	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
 	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
 	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
···
 	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
 	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
 	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);
+}
+
+static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log)
+{
+	log->iocs[nvme_cmd_zone_append]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_zone_mgmt_send]	= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_zone_mgmt_recv]	= cpu_to_le32(1 << 0);
+}
+
+static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
+{
+	struct nvme_effects_log *log;
+	u16 status = NVME_SC_SUCCESS;
+
+	log = kzalloc(sizeof(*log), GFP_KERNEL);
+	if (!log) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	switch (req->cmd->get_log_page.csi) {
+	case NVME_CSI_NVM:
+		nvmet_get_cmd_effects_nvm(log);
+		break;
+	case NVME_CSI_ZNS:
+		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+			status = NVME_SC_INVALID_IO_CMD_SET;
+			goto free;
+		}
+		nvmet_get_cmd_effects_nvm(log);
+		nvmet_get_cmd_effects_zns(log);
+		break;
+	default:
+		status = NVME_SC_INVALID_LOG_PAGE;
+		goto free;
+	}
 
 	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
-
+free:
 	kfree(log);
 out:
 	nvmet_req_complete(req, status);
···
 	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
 }
 
-static u16 nvmet_set_model_number(struct nvmet_subsys *subsys)
-{
-	u16 status = 0;
-
-	mutex_lock(&subsys->lock);
-	if (!subsys->model_number) {
-		subsys->model_number =
-			kstrdup(NVMET_DEFAULT_CTRL_MODEL, GFP_KERNEL);
-		if (!subsys->model_number)
-			status = NVME_SC_INTERNAL;
-	}
-	mutex_unlock(&subsys->lock);
-
-	return status;
-}
-
 static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
···
 	u32 cmd_capsule_size;
 	u16 status = 0;
 
-	/*
-	 * If there is no model number yet, set it now.  It will then remain
-	 * stable for the life time of the subsystem.
-	 */
-	if (!subsys->model_number) {
-		status = nvmet_set_model_number(subsys);
-		if (status)
-			goto out;
+	if (!subsys->subsys_discovered) {
+		mutex_lock(&subsys->lock);
+		subsys->subsys_discovered = true;
+		mutex_unlock(&subsys->lock);
 	}
 
 	id = kzalloc(sizeof(*id), GFP_KERNEL);
···
 	id->vid = 0;
 	id->ssvid = 0;
 
-	memset(id->sn, ' ', sizeof(id->sn));
-	bin2hex(id->sn, &ctrl->subsys->serial,
-		min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
+	memcpy(id->sn, ctrl->subsys->serial, NVMET_SN_MAX_SIZE);
 	memcpy_and_pad(id->mn, sizeof(id->mn), subsys->model_number,
 		       strlen(subsys->model_number), ' ');
 	memcpy_and_pad(id->fr, sizeof(id->fr),
···
 	/* no enforcement soft-limit for maxcmd - pick arbitrary high value */
 	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
 
-	id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
+	id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
 			NVME_CTRL_ONCS_WRITE_ZEROES);
···
 			goto out;
 	}
 
+	status = nvmet_copy_ns_identifier(req, NVME_NIDT_CSI,
+					  NVME_NIDT_CSI_LEN,
+					  &req->ns->csi, &off);
+	if (status)
+		goto out;
+
 	if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off,
 			off) != NVME_IDENTIFY_DATA_SIZE - off)
 		status = NVME_SC_INTERNAL | NVME_SC_DNR;
 
 out:
 	nvmet_req_complete(req, status);
+}
+
+static bool nvmet_handle_identify_desclist(struct nvmet_req *req)
+{
+	switch (req->cmd->identify.csi) {
+	case NVME_CSI_NVM:
+		nvmet_execute_identify_desclist(req);
+		return true;
+	case NVME_CSI_ZNS:
+		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+			nvmet_execute_identify_desclist(req);
+			return true;
+		}
+		return false;
+	default:
+		return false;
+	}
 }
 
 static void nvmet_execute_identify(struct nvmet_req *req)
···
 
 	switch (req->cmd->identify.cns) {
 	case NVME_ID_CNS_NS:
-		return nvmet_execute_identify_ns(req);
+		switch (req->cmd->identify.csi) {
+		case NVME_CSI_NVM:
+			return nvmet_execute_identify_ns(req);
+		default:
+			break;
+		}
+		break;
+	case NVME_ID_CNS_CS_NS:
+		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+			switch (req->cmd->identify.csi) {
+			case NVME_CSI_ZNS:
+				return nvmet_execute_identify_cns_cs_ns(req);
+			default:
+				break;
+			}
+		}
+		break;
 	case NVME_ID_CNS_CTRL:
-		return nvmet_execute_identify_ctrl(req);
+		switch (req->cmd->identify.csi) {
+		case NVME_CSI_NVM:
+			return nvmet_execute_identify_ctrl(req);
+		}
+		break;
+	case NVME_ID_CNS_CS_CTRL:
+		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) {
+			switch (req->cmd->identify.csi) {
+			case NVME_CSI_ZNS:
+				return nvmet_execute_identify_cns_cs_ctrl(req);
+			default:
+				break;
+			}
+		}
+		break;
 	case NVME_ID_CNS_NS_ACTIVE_LIST:
-		return nvmet_execute_identify_nslist(req);
+		switch (req->cmd->identify.csi) {
+		case NVME_CSI_NVM:
+			return nvmet_execute_identify_nslist(req);
+		default:
+			break;
+		}
+		break;
 	case NVME_ID_CNS_NS_DESC_LIST:
-		return nvmet_execute_identify_desclist(req);
+		if (nvmet_handle_identify_desclist(req) == true)
+			return;
+		break;
 	}
 
-	pr_debug("unhandled identify cns %d on qid %d\n",
-	       req->cmd->identify.cns, req->sq->qid);
-	req->error_loc = offsetof(struct nvme_identify, cns);
-	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+	nvmet_req_cns_error_complete(req);
 }
 
 /*

drivers/nvme/target/configfs.c

···
 			NVME_MINOR(subsys->ver));
 }
 
-static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
-					       const char *page, size_t count)
+static ssize_t
+nvmet_subsys_attr_version_store_locked(struct nvmet_subsys *subsys,
+		const char *page, size_t count)
 {
-	struct nvmet_subsys *subsys = to_subsys(item);
 	int major, minor, tertiary = 0;
 	int ret;
+
+	if (subsys->subsys_discovered) {
+		if (NVME_TERTIARY(subsys->ver))
+			pr_err("Can't set version number. %llu.%llu.%llu is already assigned\n",
+			       NVME_MAJOR(subsys->ver),
+			       NVME_MINOR(subsys->ver),
+			       NVME_TERTIARY(subsys->ver));
+		else
+			pr_err("Can't set version number. %llu.%llu is already assigned\n",
+			       NVME_MAJOR(subsys->ver),
+			       NVME_MINOR(subsys->ver));
+		return -EINVAL;
+	}
 
 	/* passthru subsystems use the underlying controller's version */
 	if (nvmet_passthru_ctrl(subsys))
···
 	if (ret != 2 && ret != 3)
 		return -EINVAL;
 
-	down_write(&nvmet_config_sem);
 	subsys->ver = NVME_VS(major, minor, tertiary);
-	up_write(&nvmet_config_sem);
 
 	return count;
 }
+
+static ssize_t nvmet_subsys_attr_version_store(struct config_item *item,
+					       const char *page, size_t count)
+{
+	struct nvmet_subsys *subsys = to_subsys(item);
+	ssize_t ret;
+
+	down_write(&nvmet_config_sem);
+	mutex_lock(&subsys->lock);
+	ret = nvmet_subsys_attr_version_store_locked(subsys, page, count);
+	mutex_unlock(&subsys->lock);
+	up_write(&nvmet_config_sem);
+
+	return ret;
+}
 CONFIGFS_ATTR(nvmet_subsys_, attr_version);
+
+/* See Section 1.5 of NVMe 1.4 */
+static bool nvmet_is_ascii(const char c)
+{
+	return c >= 0x20 && c <= 0x7e;
+}
 
 static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item,
 					     char *page)
 {
 	struct nvmet_subsys *subsys = to_subsys(item);
 
-	return snprintf(page, PAGE_SIZE, "%llx\n", subsys->serial);
+	return snprintf(page, PAGE_SIZE, "%s\n", subsys->serial);
+}
+
+static ssize_t
+nvmet_subsys_attr_serial_store_locked(struct nvmet_subsys *subsys,
+		const char *page, size_t count)
+{
+	int pos, len = strcspn(page, "\n");
+
+	if (subsys->subsys_discovered) {
+		pr_err("Can't set serial number. %s is already assigned\n",
+		       subsys->serial);
+		return -EINVAL;
+	}
+
+	if (!len || len > NVMET_SN_MAX_SIZE) {
+		pr_err("Serial Number can not be empty or exceed %d Bytes\n",
+		       NVMET_SN_MAX_SIZE);
+		return -EINVAL;
+	}
+
+	for (pos = 0; pos < len; pos++) {
+		if (!nvmet_is_ascii(page[pos])) {
+			pr_err("Serial Number must contain only ASCII strings\n");
+			return -EINVAL;
+		}
+	}
+
+	memcpy_and_pad(subsys->serial, NVMET_SN_MAX_SIZE, page, len, ' ');
+
+	return count;
 }
 
 static ssize_t nvmet_subsys_attr_serial_store(struct config_item *item,
 					      const char *page, size_t count)
 {
-	u64 serial;
-
-	if (sscanf(page, "%llx\n", &serial) != 1)
-		return -EINVAL;
+	struct nvmet_subsys *subsys = to_subsys(item);
+	ssize_t ret;
 
 	down_write(&nvmet_config_sem);
-	to_subsys(item)->serial = serial;
+	mutex_lock(&subsys->lock);
+	ret = nvmet_subsys_attr_serial_store_locked(subsys, page, count);
+	mutex_unlock(&subsys->lock);
 	up_write(&nvmet_config_sem);
 
-	return count;
+	return ret;
 }
 CONFIGFS_ATTR(nvmet_subsys_, attr_serial);
 
···
 					    char *page)
 {
 	struct nvmet_subsys *subsys = to_subsys(item);
-	int ret;
 
-	mutex_lock(&subsys->lock);
-	ret = snprintf(page, PAGE_SIZE, "%s\n", subsys->model_number ?
-			subsys->model_number : NVMET_DEFAULT_CTRL_MODEL);
-	mutex_unlock(&subsys->lock);
-
-	return ret;
-}
-
-/* See Section 1.5 of NVMe 1.4 */
-static bool nvmet_is_ascii(const char c)
-{
-	return c >= 0x20 && c <= 0x7e;
+	return snprintf(page, PAGE_SIZE, "%s\n", subsys->model_number);
 }
 
 static ssize_t nvmet_subsys_attr_model_store_locked(struct nvmet_subsys *subsys,
···
 {
 	int pos = 0, len;
 
-	if (subsys->model_number) {
+	if (subsys->subsys_discovered) {
 		pr_err("Can't set model number. %s is already assigned\n",
 		       subsys->model_number);
 		return -EINVAL;

drivers/nvme/target/core.c

···
 #include "nvmet.h"
 
 struct workqueue_struct *buffered_io_wq;
+struct workqueue_struct *zbd_wq;
 static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
 static DEFINE_IDA(cntlid_ida);
 
···
 
 inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
 {
-	u16 status;
-
 	switch (errno) {
 	case 0:
-		status = NVME_SC_SUCCESS;
-		break;
+		return NVME_SC_SUCCESS;
 	case -ENOSPC:
 		req->error_loc = offsetof(struct nvme_rw_command, length);
-		status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
-		break;
+		return NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
 	case -EREMOTEIO:
 		req->error_loc = offsetof(struct nvme_rw_command, slba);
-		status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
-		break;
+		return  NVME_SC_LBA_RANGE | NVME_SC_DNR;
 	case -EOPNOTSUPP:
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
 		switch (req->cmd->common.opcode) {
 		case nvme_cmd_dsm:
 		case nvme_cmd_write_zeroes:
-			status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
-			break;
+			return NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
 		default:
-			status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
+			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		}
 		break;
 	case -ENODATA:
 		req->error_loc = offsetof(struct nvme_rw_command, nsid);
-		status = NVME_SC_ACCESS_DENIED;
-		break;
+		return NVME_SC_ACCESS_DENIED;
 	case -EIO:
 		fallthrough;
 	default:
 		req->error_loc = offsetof(struct nvme_common_command, opcode);
-		status = NVME_SC_INTERNAL | NVME_SC_DNR;
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
 	}
-
-	return status;
 }
 
 u16 nvmet_report_invalid_opcode(struct nvmet_req *req)
···
 	return 0;
 }
 
-static unsigned int nvmet_max_nsid(struct nvmet_subsys *subsys)
+static u32 nvmet_max_nsid(struct nvmet_subsys *subsys)
 {
-	unsigned long nsid = 0;
 	struct nvmet_ns *cur;
 	unsigned long idx;
+	u32 nsid = 0;
 
 	xa_for_each(&subsys->namespaces, idx, cur)
 		nsid = cur->nsid;
···
 
 static void nvmet_async_events_failall(struct nvmet_ctrl *ctrl)
 {
-	u16 status = NVME_SC_INTERNAL | NVME_SC_DNR;
 	struct nvmet_req *req;
 
 	mutex_lock(&ctrl->lock);
 	while (ctrl->nr_async_event_cmds) {
 		req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
 		mutex_unlock(&ctrl->lock);
-		nvmet_req_complete(req, status);
+		nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR);
 		mutex_lock(&ctrl->lock);
 	}
 	mutex_unlock(&ctrl->lock);
···
 	pr_debug("ctrl %d start keep-alive timer for %d secs\n",
 		ctrl->cntlid, ctrl->kato);
 
-	INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer);
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 
···
 
 	uuid_gen(&ns->uuid);
 	ns->buffered_io = false;
+	ns->csi = NVME_CSI_NVM;
 
 	return ns;
 }
···
 		return ret;
 	}
 
-	if (req->ns->file)
-		return nvmet_file_parse_io_cmd(req);
-
-	return nvmet_bdev_parse_io_cmd(req);
+	switch (req->ns->csi) {
+	case NVME_CSI_NVM:
+		if (req->ns->file)
+			return nvmet_file_parse_io_cmd(req);
+		return nvmet_bdev_parse_io_cmd(req);
+	case NVME_CSI_ZNS:
+		if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+			return nvmet_bdev_zns_parse_io_cmd(req);
+		return NVME_SC_INVALID_IO_CMD_SET;
+	default:
+		return NVME_SC_INVALID_IO_CMD_SET;
+	}
 }
 
 bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
···
 	return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf;
 }
 
+static inline bool nvmet_css_supported(u8 cc_css)
+{
+	switch (cc_css <<= NVME_CC_CSS_SHIFT) {
+	case NVME_CC_CSS_NVM:
+	case NVME_CC_CSS_CSI:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
 {
 	lockdep_assert_held(&ctrl->lock);
···
 
 	if (nvmet_cc_mps(ctrl->cc) != 0 ||
 	    nvmet_cc_ams(ctrl->cc) != 0 ||
-	    nvmet_cc_css(ctrl->cc) != 0) {
+	    !nvmet_css_supported(nvmet_cc_css(ctrl->cc))) {
 		ctrl->csts = NVME_CSTS_CFS;
 		return;
 	}
···
 {
 	/* command sets supported: NVMe command set: */
 	ctrl->cap = (1ULL << 37);
+	/* Controller supports one or more I/O Command Sets */
+	ctrl->cap |= (1ULL << 43);
 	/* CC.EN timeout in 500msec units: */
 	ctrl->cap |= (15ULL << 24);
 	/* maximum queue entries supported: */
···
 	INIT_LIST_HEAD(&ctrl->async_events);
 	INIT_RADIX_TREE(&ctrl->p2p_ns_map, GFP_KERNEL);
 	INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler);
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer);
 
 	memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
 	memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);
···
 		enum nvme_subsys_type type)
 {
 	struct nvmet_subsys *subsys;
+	char serial[NVMET_SN_MAX_SIZE / 2];
+	int ret;
 
 	subsys = kzalloc(sizeof(*subsys), GFP_KERNEL);
 	if (!subsys)
···
 
 	subsys->ver = NVMET_DEFAULT_VS;
 	/* generate a random serial number as our controllers are ephemeral: */
-	get_random_bytes(&subsys->serial, sizeof(subsys->serial));
+	get_random_bytes(&serial, sizeof(serial));
+	bin2hex(subsys->serial, &serial, sizeof(serial));
+
+	subsys->model_number = kstrdup(NVMET_DEFAULT_CTRL_MODEL, GFP_KERNEL);
+	if (!subsys->model_number) {
+		ret = -ENOMEM;
+		goto free_subsys;
+	}
 
 	switch (type) {
 	case NVME_NQN_NVME:
···
 		break;
 	default:
 		pr_err("%s: Unknown Subsystem type - %d\n", __func__, type);
-		kfree(subsys);
-		return ERR_PTR(-EINVAL);
+		ret = -EINVAL;
+		goto free_mn;
 	}
 	subsys->type = type;
 	subsys->subsysnqn = kstrndup(subsysnqn, NVMF_NQN_SIZE,
 			GFP_KERNEL);
 	if (!subsys->subsysnqn) {
-		kfree(subsys);
-		return ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
+		goto free_mn;
 	}
 	subsys->cntlid_min = NVME_CNTLID_MIN;
 	subsys->cntlid_max = NVME_CNTLID_MAX;
···
 	INIT_LIST_HEAD(&subsys->hosts);
 
 	return subsys;
+
+free_mn:
+	kfree(subsys->model_number);
+free_subsys:
+	kfree(subsys);
+	return ERR_PTR(ret);
 }
 
 static void nvmet_subsys_free(struct kref *ref)
···
 
 	nvmet_ana_group_enabled[NVMET_DEFAULT_ANA_GRPID] = 1;
 
+	zbd_wq = alloc_workqueue("nvmet-zbd-wq", WQ_MEM_RECLAIM, 0);
+	if (!zbd_wq)
+		return -ENOMEM;
+
 	buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq",
 			WQ_MEM_RECLAIM, 0);
 	if (!buffered_io_wq) {
 		error = -ENOMEM;
-		goto out;
+		goto out_free_zbd_work_queue;
 	}
 
 	error = nvmet_init_discovery();
···
 	nvmet_exit_discovery();
 out_free_work_queue:
 	destroy_workqueue(buffered_io_wq);
-out:
+out_free_zbd_work_queue:
+	destroy_workqueue(zbd_wq);
 	return error;
 }
 
···
 	nvmet_exit_discovery();
 	ida_destroy(&cntlid_ida);
 	destroy_workqueue(buffered_io_wq);
+	destroy_workqueue(zbd_wq);
 
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);

drivers/nvme/target/discovery.c

···
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 	struct nvme_id_ctrl *id;
-	const char model[] = "Linux";
 	u16 status = 0;
 
 	if (!nvmet_check_transfer_len(req, NVME_IDENTIFY_DATA_SIZE))
···
 		goto out;
 	}
 
-	memset(id->sn, ' ', sizeof(id->sn));
-	bin2hex(id->sn, &ctrl->subsys->serial,
-		min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2));
+	memcpy(id->sn, ctrl->subsys->serial, NVMET_SN_MAX_SIZE);
 	memset(id->fr, ' ', sizeof(id->fr));
-	memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' ');
+	memcpy_and_pad(id->mn, sizeof(id->mn), ctrl->subsys->model_number,
+		       strlen(ctrl->subsys->model_number), ' ');
 	memcpy_and_pad(id->fr, sizeof(id->fr),
 		       UTS_RELEASE, strlen(UTS_RELEASE), ' ');
 

drivers/nvme/target/fc.c

···
 	int ret;
 
 	/*
-	 * if there is no nvmet mapping to the targetport there
-	 * shouldn't be requests. just terminate them.
-	 */
-	if (!tgtport->pe)
-		goto transport_error;
-
-	/*
 	 * Fused commands are currently not supported in the linux
 	 * implementation.
 	 *
···
 
 	fod->req.cmd = &fod->cmdiubuf.sqe;
 	fod->req.cqe = &fod->rspiubuf.cqe;
-	fod->req.port = tgtport->pe->port;
+	if (tgtport->pe)
+		fod->req.port = tgtport->pe->port;
 
 	/* clear any response payload */
 	memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf));

drivers/nvme/target/io-cmd-bdev.c

···
 	id->nows = to0based(ql->io_opt / ql->logical_block_size);
 }
 
+void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
+{
+	if (ns->bdev) {
+		blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ);
+		ns->bdev = NULL;
+	}
+}
+
 static void nvmet_bdev_ns_enable_integrity(struct nvmet_ns *ns)
 {
 	struct blk_integrity *bi = bdev_get_integrity(ns->bdev);
···
 	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY_T10))
 		nvmet_bdev_ns_enable_integrity(ns);
 
-	return 0;
-}
-
-void nvmet_bdev_ns_disable(struct nvmet_ns *ns)
-{
-	if (ns->bdev) {
-		blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ);
-		ns->bdev = NULL;
+	if (bdev_is_zoned(ns->bdev)) {
+		if (!nvmet_bdev_zns_enable(ns)) {
+			nvmet_bdev_ns_disable(ns);
+			return -EINVAL;
+		}
+		ns->csi = NVME_CSI_ZNS;
 	}
+
+	return 0;
 }
 
 void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns)
···
 	ns->size = i_size_read(ns->bdev->bd_inode);
 }
 
-static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
+u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
 {
 	u16 status = NVME_SC_SUCCESS;
 
···
 	struct nvmet_req *req = bio->bi_private;
 
 	nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status));
-	if (bio != &req->b.inline_bio)
-		bio_put(bio);
+	nvmet_req_bio_put(req, bio);
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
···
 {
 	struct blk_integrity *bi;
 	struct bio_integrity_payload *bip;
-	struct block_device *bdev = req->ns->bdev;
 	int rc;
 	size_t resid, len;
 
-	bi = bdev_get_integrity(bdev);
+	bi = bdev_get_integrity(req->ns->bdev);
 	if (unlikely(!bi)) {
 		pr_err("Unable to locate bio_integrity\n");
 		return -ENODEV;
···
 
 u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req)
 {
-	struct nvme_command *cmd = req->cmd;
-
-	switch (cmd->common.opcode) {
+	switch (req->cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
 		req->execute = nvmet_bdev_execute_rw;

drivers/nvme/target/io-cmd-file.c

···
 
 u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 {
-	struct nvme_command *cmd = req->cmd;
-
-	switch (cmd->common.opcode) {
+	switch (req->cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
 		req->execute = nvmet_file_execute_rw;

drivers/nvme/target/nvmet.h

···
 #define NVMET_NO_ERROR_LOC		((u16)-1)
 #define NVMET_DEFAULT_CTRL_MODEL	"Linux"
 #define NVMET_MN_MAX_SIZE		40
+#define NVMET_SN_MAX_SIZE		20
 
 /*
  * Supported optional AENs:
···
 	struct pci_dev		*p2p_dev;
 	int			pi_type;
 	int			metadata_size;
+	u8			csi;
 };
 
 static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item)
···
 
 	struct xarray		namespaces;
 	unsigned int		nr_namespaces;
-	unsigned int		max_nsid;
+	u32			max_nsid;
 	u16			cntlid_min;
 	u16			cntlid_max;
 
···
 	u16			max_qid;
 
 	u64			ver;
-	u64			serial;
+	char			serial[NVMET_SN_MAX_SIZE];
+	bool			subsys_discovered;
 	char			*subsysnqn;
 	bool			pi_support;
 
···
 	unsigned int		admin_timeout;
 	unsigned int		io_timeout;
 #endif /* CONFIG_NVME_TARGET_PASSTHRU */
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	u8			zasl;
+#endif /* CONFIG_BLK_DEV_ZONED */
 };
 
 static inline struct nvmet_subsys *to_subsys(struct config_item *item)
···
 			struct work_struct      work;
 			bool			use_workqueue;
 		} p;
+#ifdef CONFIG_BLK_DEV_ZONED
+		struct {
+			struct bio		inline_bio;
+			struct work_struct	zmgmt_work;
+		} z;
+#endif /* CONFIG_BLK_DEV_ZONED */
 	};
 	int			sg_cnt;
 	int			metadata_sg_cnt;
···
 };
 
 extern struct workqueue_struct *buffered_io_wq;
+extern struct workqueue_struct *zbd_wq;
 
 static inline void nvmet_set_result(struct nvmet_req *req, u32 result)
 {
···
 void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id);
 u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req);
 u16 nvmet_file_parse_io_cmd(struct nvmet_req *req);
+u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req);
 u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
 u16 nvmet_parse_discovery_cmd(struct nvmet_req *req);
 u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
···
 void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns);
 int nvmet_file_ns_revalidate(struct nvmet_ns *ns);
 void nvmet_ns_revalidate(struct nvmet_ns *ns);
+u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts);
+
+bool nvmet_bdev_zns_enable(struct nvmet_ns *ns);
+void nvmet_execute_identify_cns_cs_ctrl(struct nvmet_req *req);
+void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req);
+void nvmet_bdev_execute_zone_mgmt_recv(struct nvmet_req *req);
+void nvmet_bdev_execute_zone_mgmt_send(struct nvmet_req *req);
+void nvmet_bdev_execute_zone_append(struct nvmet_req *req);
 
 static inline u32 nvmet_rw_data_len(struct nvmet_req *req)
 {
···
 {
 	return req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN &&
 	       req->sg_cnt <= NVMET_MAX_INLINE_BIOVEC;
+}
+
+static inline void nvmet_req_cns_error_complete(struct nvmet_req *req)
+{
+	pr_debug("unhandled identify cns %d on qid %d\n",
+	       req->cmd->identify.cns, req->sq->qid);
+	req->error_loc = offsetof(struct nvme_identify, cns);
+	nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
+}
+
+static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio)
+{
+	if (bio != &req->b.inline_bio)
+		bio_put(bio);
 }
 
 #endif /* _NVMET_H */

drivers/nvme/target/passthru.c

···
 	for_each_sg(req->sg, sg, req->sg_cnt, i) {
 		if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length,
 				    sg->offset) < sg->length) {
-			if (bio != &req->p.inline_bio)
-				bio_put(bio);
+			nvmet_req_bio_put(req, bio);
 			return -EINVAL;
 		}
 	}

drivers/nvme/target/rdma.c

···
 
 static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 {
-	struct ib_qp_init_attr qp_attr;
+	struct ib_qp_init_attr qp_attr = { };
 	struct nvmet_rdma_device *ndev = queue->dev;
 	int nr_cqe, ret, i, factor;
 
···
 		goto out;
 	}
 
-	memset(&qp_attr, 0, sizeof(qp_attr));
 	qp_attr.qp_context = queue;
 	qp_attr.event_handler = nvmet_rdma_qp_event;
 	qp_attr.send_cq = queue->cq;

drivers/nvme/target/zns.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVMe ZNS-ZBD command implementation.
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/nvme.h>
+#include <linux/blkdev.h>
+#include "nvmet.h"
+
+/*
+ * We set the Memory Page Size Minimum (MPSMIN) for target controller to 0
+ * which gets added by 12 in the nvme_enable_ctrl() which results in 2^12 = 4k
+ * as page_shift value. When calculating the ZASL use shift by 12.
+ */
+#define NVMET_MPSMIN_SHIFT	12
+
+static inline u8 nvmet_zasl(unsigned int zone_append_sects)
+{
+	/*
+	 * Zone Append Size Limit (zasl) is expressed as a power of 2 value
+	 * with the minimum memory page size (i.e. 12) as unit.
+	 */
+	return ilog2(zone_append_sects >> (NVMET_MPSMIN_SHIFT - 9));
+}
+
+static int validate_conv_zones_cb(struct blk_zone *z,
+				  unsigned int i, void *data)
+{
+	if (z->type == BLK_ZONE_TYPE_CONVENTIONAL)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
+{
+	struct request_queue *q = ns->bdev->bd_disk->queue;
+	u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q));
+	struct gendisk *bd_disk = ns->bdev->bd_disk;
+	int ret;
+
+	if (ns->subsys->zasl) {
+		if (ns->subsys->zasl > zasl)
+			return false;
+	}
+	ns->subsys->zasl = zasl;
+
+	/*
+	 * Generic zoned block devices may have a smaller last zone which is
+	 * not supported by ZNS. Exclude zoned drives that have such smaller
+	 * last zone.
+	 */
+	if (get_capacity(bd_disk) & (bdev_zone_sectors(ns->bdev) - 1))
+		return false;
+	/*
+	 * ZNS does not define a conventional zone type. If the underlying
+	 * device has a bitmap set indicating the existence of conventional
+	 * zones, reject the device. Otherwise, use report zones to detect if
+	 * the device has conventional zones.
+	 */
+	if (ns->bdev->bd_disk->queue->conv_zones_bitmap)
+		return false;
+
+	ret = blkdev_report_zones(ns->bdev, 0, blkdev_nr_zones(bd_disk),
+				  validate_conv_zones_cb, NULL);
+	if (ret < 0)
+		return false;
+
+	ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev));
+
+	return true;
+}
+
+void nvmet_execute_identify_cns_cs_ctrl(struct nvmet_req *req)
+{
+	u8 zasl = req->sq->ctrl->subsys->zasl;
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvme_id_ctrl_zns *id;
+	u16 status;
+
+	id = kzalloc(sizeof(*id), GFP_KERNEL);
+	if (!id) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	if (ctrl->ops->get_mdts)
+		id->zasl = min_t(u8, ctrl->ops->get_mdts(ctrl), zasl);
+	else
+		id->zasl = zasl;
+
+	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
+
+	kfree(id);
+out:
+	nvmet_req_complete(req, status);
+}
+
+void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req)
+{
+	struct nvme_id_ns_zns *id_zns;
+	u64 zsze;
+	u16 status;
+
+	if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
+		req->error_loc = offsetof(struct nvme_identify, nsid);
+		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
+		goto out;
+	}
+
+	id_zns = kzalloc(sizeof(*id_zns), GFP_KERNEL);
+	if (!id_zns) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	status = nvmet_req_find_ns(req);
+	if (status) {
+		status = NVME_SC_INTERNAL;
+		goto done;
+	}
+
+	if (!bdev_is_zoned(req->ns->bdev)) {
+		req->error_loc = offsetof(struct nvme_identify, nsid);
+		status = NVME_SC_INVALID_NS | NVME_SC_DNR;
+		goto done;
+	}
+
+	nvmet_ns_revalidate(req->ns);
+	zsze = (bdev_zone_sectors(req->ns->bdev) << 9) >>
+					req->ns->blksize_shift;
+	id_zns->lbafe[0].zsze = cpu_to_le64(zsze);
+	id_zns->mor = cpu_to_le32(bdev_max_open_zones(req->ns->bdev));
+	id_zns->mar = cpu_to_le32(bdev_max_active_zones(req->ns->bdev));
+
+done:
+	status = nvmet_copy_to_sgl(req, 0, id_zns, sizeof(*id_zns));
+	kfree(id_zns);
+out:
+	nvmet_req_complete(req, status);
+}
+
+static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req)
+{
+	sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba);
+	u32 out_bufsize = (le32_to_cpu(req->cmd->zmr.numd) + 1) << 2;
+
+	if (sect >= get_capacity(req->ns->bdev->bd_disk)) {
+		req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, slba);
+		return NVME_SC_LBA_RANGE | NVME_SC_DNR;
+	}
+
+	if (out_bufsize < sizeof(struct nvme_zone_report)) {
+		req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, numd);
+		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+
+	if (req->cmd->zmr.zra != NVME_ZRA_ZONE_REPORT) {
+		req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, zra);
+		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+
+	switch (req->cmd->zmr.pr) {
+	case 0:
+	case 1:
+		break;
+	default:
+		req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, pr);
+		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+
+	switch (req->cmd->zmr.zrasf) {
+	case NVME_ZRASF_ZONE_REPORT_ALL:
+	case NVME_ZRASF_ZONE_STATE_EMPTY:
+	case NVME_ZRASF_ZONE_STATE_IMP_OPEN:
+	case NVME_ZRASF_ZONE_STATE_EXP_OPEN:
+	case NVME_ZRASF_ZONE_STATE_CLOSED:
+	case NVME_ZRASF_ZONE_STATE_FULL:
+	case NVME_ZRASF_ZONE_STATE_READONLY:
+	case NVME_ZRASF_ZONE_STATE_OFFLINE:
+		break;
+	default:
+		req->error_loc =
+			offsetof(struct nvme_zone_mgmt_recv_cmd, zrasf);
+		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+
+	return NVME_SC_SUCCESS;
+}
+
+struct nvmet_report_zone_data {
+	struct nvmet_req *req;
+	u64 out_buf_offset;
+	u64 out_nr_zones;
+	u64 nr_zones;
+	u8 zrasf;
+};
+
+static int nvmet_bdev_report_zone_cb(struct blk_zone *z, unsigned i, void *d)
+{
+	static const unsigned int nvme_zrasf_to_blk_zcond[] = {
+		[NVME_ZRASF_ZONE_STATE_EMPTY]	 = BLK_ZONE_COND_EMPTY,
+		[NVME_ZRASF_ZONE_STATE_IMP_OPEN] = BLK_ZONE_COND_IMP_OPEN,
+		[NVME_ZRASF_ZONE_STATE_EXP_OPEN] = BLK_ZONE_COND_EXP_OPEN,
+		[NVME_ZRASF_ZONE_STATE_CLOSED]	 = BLK_ZONE_COND_CLOSED,
+		[NVME_ZRASF_ZONE_STATE_READONLY] = BLK_ZONE_COND_READONLY,
+		[NVME_ZRASF_ZONE_STATE_FULL]	 = BLK_ZONE_COND_FULL,
+		[NVME_ZRASF_ZONE_STATE_OFFLINE]	 = BLK_ZONE_COND_OFFLINE,
+	};
+	struct nvmet_report_zone_data *rz = d;
+
+	if (rz->zrasf != NVME_ZRASF_ZONE_REPORT_ALL &&
+	    z->cond != nvme_zrasf_to_blk_zcond[rz->zrasf])
+		return 0;
+
+	if (rz->nr_zones < rz->out_nr_zones) {
+		struct nvme_zone_descriptor zdesc = { };
+		u16 status;
+
+		zdesc.zcap = nvmet_sect_to_lba(rz->req->ns, z->capacity);
+		zdesc.zslba = nvmet_sect_to_lba(rz->req->ns, z->start);
+		zdesc.wp = nvmet_sect_to_lba(rz->req->ns, z->wp);
+		zdesc.za = z->reset ? 1 << 2 : 0;
+		zdesc.zs = z->cond << 4;
+		zdesc.zt = z->type;
+
+		status = nvmet_copy_to_sgl(rz->req, rz->out_buf_offset, &zdesc,
+					   sizeof(zdesc));
+		if (status)
+			return -EINVAL;
+
+		rz->out_buf_offset += sizeof(zdesc);
+	}
+
+	rz->nr_zones++;
+
+	return 0;
+}
+
+static unsigned long nvmet_req_nr_zones_from_slba(struct nvmet_req *req)
+{
+	unsigned int sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba);
+
+	return blkdev_nr_zones(req->ns->bdev->bd_disk) -
+		(sect >> ilog2(bdev_zone_sectors(req->ns->bdev)));
+}
+
+static unsigned long get_nr_zones_from_buf(struct nvmet_req *req, u32 bufsize)
+{
+	if (bufsize <= sizeof(struct nvme_zone_report))
+		return 0;
+
+	return (bufsize - sizeof(struct nvme_zone_report)) /
+		sizeof(struct nvme_zone_descriptor);
+}
+
+static void nvmet_bdev_zone_zmgmt_recv_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, z.zmgmt_work);
+	sector_t start_sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba);
+	unsigned long req_slba_nr_zones = nvmet_req_nr_zones_from_slba(req);
+	u32 out_bufsize = (le32_to_cpu(req->cmd->zmr.numd) + 1) << 2;
+	__le64 nr_zones;
+	u16 status;
+	int ret;
+	struct nvmet_report_zone_data rz_data = {
+		.out_nr_zones = get_nr_zones_from_buf(req, out_bufsize),
+		/* leave the place for report zone header */
+		.out_buf_offset = sizeof(struct nvme_zone_report),
+		.zrasf = req->cmd->zmr.zrasf,
+		.nr_zones = 0,
+		.req = req,
+	};
+
+	status = nvmet_bdev_validate_zone_mgmt_recv(req);
+	if (status)
+		goto out;
+
+	if (!req_slba_nr_zones) {
+		status = NVME_SC_SUCCESS;
+		goto out;
+	}
+
+	ret = blkdev_report_zones(req->ns->bdev, start_sect, req_slba_nr_zones,
+				 nvmet_bdev_report_zone_cb, &rz_data);
+	if (ret < 0) {
+		status = NVME_SC_INTERNAL;
+		goto out;
+	}
+
+	/*
+	 * When partial bit is set nr_zones must indicate the number of zone
+	 * descriptors actually transferred.
+	 */
+	if (req->cmd->zmr.pr)
+		rz_data.nr_zones = min(rz_data.nr_zones, rz_data.out_nr_zones);
+
+	nr_zones = cpu_to_le64(rz_data.nr_zones);
+	status = nvmet_copy_to_sgl(req, 0, &nr_zones, sizeof(nr_zones));
+
+out:
+	nvmet_req_complete(req, status);
+}
+
+void nvmet_bdev_execute_zone_mgmt_recv(struct nvmet_req *req)
+{
+	INIT_WORK(&req->z.zmgmt_work, nvmet_bdev_zone_zmgmt_recv_work);
+	queue_work(zbd_wq, &req->z.zmgmt_work);
+}
+
+static inline enum req_opf zsa_req_op(u8 zsa)
+{
+	switch (zsa) {
+	case NVME_ZONE_OPEN:
+		return REQ_OP_ZONE_OPEN;
+	case NVME_ZONE_CLOSE:
+		return REQ_OP_ZONE_CLOSE;
+	case NVME_ZONE_FINISH:
+		return REQ_OP_ZONE_FINISH;
+	case NVME_ZONE_RESET:
+		return REQ_OP_ZONE_RESET;
+	default:
+		return REQ_OP_LAST;
+	}
+}
+
+static u16 blkdev_zone_mgmt_errno_to_nvme_status(int ret)
+{
+	switch (ret) {
+	case 0:
+		return NVME_SC_SUCCESS;
+	case -EINVAL:
+	case -EIO:
+		return NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR;
+	default:
+		return NVME_SC_INTERNAL;
+	}
+}
+
+struct nvmet_zone_mgmt_send_all_data {
+	unsigned long *zbitmap;
+	struct nvmet_req *req;
+};
+
+static int zmgmt_send_scan_cb(struct blk_zone *z, unsigned i, void *d)
+{
+	struct nvmet_zone_mgmt_send_all_data *data = d;
+
+	switch (zsa_req_op(data->req->cmd->zms.zsa)) {
+	case REQ_OP_ZONE_OPEN:
+		switch (z->cond) {
+		case BLK_ZONE_COND_CLOSED:
+			break;
+		default:
+			return 0;
+		}
+		break;
+	case REQ_OP_ZONE_CLOSE:
+		switch (z->cond) {
+		case BLK_ZONE_COND_IMP_OPEN:
+		case BLK_ZONE_COND_EXP_OPEN:
+			break;
+		default:
+			return 0;
+		}
+		break;
+	case REQ_OP_ZONE_FINISH:
+		switch (z->cond) {
+		case BLK_ZONE_COND_IMP_OPEN:
+		case BLK_ZONE_COND_EXP_OPEN:
+		case BLK_ZONE_COND_CLOSED:
+			break;
+		default:
+			return 0;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	set_bit(i, data->zbitmap);
+
+	return 0;
+}
+
+static u16 nvmet_bdev_zone_mgmt_emulate_all(struct nvmet_req *req)
+{
+	struct block_device *bdev = req->ns->bdev;
+	unsigned int nr_zones = blkdev_nr_zones(bdev->bd_disk);
+	struct request_queue *q = bdev_get_queue(bdev);
+	struct bio *bio = NULL;
+	sector_t sector = 0;
+	int ret;
+	struct nvmet_zone_mgmt_send_all_data d = {
+		.req = req,
+	};
+
+	d.zbitmap = kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(*(d.zbitmap)),
+				 GFP_NOIO, q->node);
+	if (!d.zbitmap) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* Scan and build bitmap of the eligible zones */
+	ret = blkdev_report_zones(bdev, 0, nr_zones, zmgmt_send_scan_cb, &d);
+	if (ret != nr_zones) {
+		if (ret > 0)
+			ret = -EIO;
+		goto out;
+	} else {
+		/* We scanned all the zones */
+		ret = 0;
+	}
+
+	while (sector < get_capacity(bdev->bd_disk)) {
+		if (test_bit(blk_queue_zone_no(q, sector), d.zbitmap)) {
+			bio = blk_next_bio(bio, 0, GFP_KERNEL);
+			bio->bi_opf = zsa_req_op(req->cmd->zms.zsa) | REQ_SYNC;
+			bio->bi_iter.bi_sector = sector;
+			bio_set_dev(bio, bdev);
+			/* This may take a while, so be nice to others */
+			cond_resched();
+		}
+		sector += blk_queue_zone_sectors(q);
+	}
+
+	if (bio) {
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+
+out:
+	kfree(d.zbitmap);
+
+	return blkdev_zone_mgmt_errno_to_nvme_status(ret);
+}
+
+static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req)
+{
+	int ret;
+
+	switch (zsa_req_op(req->cmd->zms.zsa)) {
+	case REQ_OP_ZONE_RESET:
+		ret = blkdev_zone_mgmt(req->ns->bdev, REQ_OP_ZONE_RESET, 0,
+				       get_capacity(req->ns->bdev->bd_disk),
+				       GFP_KERNEL);
+		if (ret < 0)
+			return blkdev_zone_mgmt_errno_to_nvme_status(ret);
+		break;
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
+		return nvmet_bdev_zone_mgmt_emulate_all(req);
+	default:
+		/* this is needed to quiet compiler warning */
+		req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa);
+		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+	}
+
+	return NVME_SC_SUCCESS;
+}
+
+static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, z.zmgmt_work);
+	sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->zms.slba);
+	enum req_opf op = zsa_req_op(req->cmd->zms.zsa);
+	struct block_device *bdev = req->ns->bdev;
+	sector_t zone_sectors = bdev_zone_sectors(bdev);
+	u16 status = NVME_SC_SUCCESS;
+	int ret;
+
+	if (op == REQ_OP_LAST) {
+		req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa);
+		status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR;
+		goto out;
+	}
+
+	/* when select all bit is set slba field is ignored */
+	if (req->cmd->zms.select_all) {
+		status = nvmet_bdev_execute_zmgmt_send_all(req);
+		goto out;
+	}
+
+	if (sect >= get_capacity(bdev->bd_disk)) {
+		req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba);
+		status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+		goto out;
+	}
+
+	if (sect & (zone_sectors - 1)) {
+		req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba);
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		goto out;
+	}
+
+	ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors, GFP_KERNEL);
+	if (ret < 0)
+		status = blkdev_zone_mgmt_errno_to_nvme_status(ret);
+
+out:
+	nvmet_req_complete(req, status);
+}
+
+void nvmet_bdev_execute_zone_mgmt_send(struct nvmet_req *req)
+{
+	INIT_WORK(&req->z.zmgmt_work, nvmet_bdev_zmgmt_send_work);
+	queue_work(zbd_wq, &req->z.zmgmt_work);
+}
+
+static void nvmet_bdev_zone_append_bio_done(struct bio *bio)
+{
+	struct nvmet_req *req = bio->bi_private;
+
+	if (bio->bi_status == BLK_STS_OK) {
+		req->cqe->result.u64 =
+			nvmet_sect_to_lba(req->ns, bio->bi_iter.bi_sector);
+	}
+
+	nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status));
+	nvmet_req_bio_put(req, bio);
+}
+
+void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
+{
+	sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->rw.slba);
+	u16 status = NVME_SC_SUCCESS;
+	unsigned int total_len = 0;
+	struct scatterlist *sg;
+	struct bio *bio;
+	int sg_cnt;
+
+	/* Request is completed on len mismatch in nvmet_check_transter_len() */
+	if (!nvmet_check_transfer_len(req, nvmet_rw_data_len(req)))
+		return;
+
+	if (!req->sg_cnt) {
+		nvmet_req_complete(req, 0);
+		return;
+	}
+
+	if (sect >= get_capacity(req->ns->bdev->bd_disk)) {
+		req->error_loc = offsetof(struct nvme_rw_command, slba);
+		status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+		goto out;
+	}
+
+	if (sect & (bdev_zone_sectors(req->ns->bdev) - 1)) {
+		req->error_loc = offsetof(struct nvme_rw_command, slba);
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		goto out;
+	}
+
+	if (nvmet_use_inline_bvec(req)) {
+		bio = &req->z.inline_bio;
+		bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec));
+	} else {
+		bio = bio_alloc(GFP_KERNEL, req->sg_cnt);
+	}
+
+	bio->bi_opf = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE;
+	bio->bi_end_io = nvmet_bdev_zone_append_bio_done;
+	bio_set_dev(bio, req->ns->bdev);
+	bio->bi_iter.bi_sector = sect;
+	bio->bi_private = req;
+	if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA))
+		bio->bi_opf |= REQ_FUA;
+
+	for_each_sg(req->sg, sg, req->sg_cnt, sg_cnt) {
+		struct page *p = sg_page(sg);
+		unsigned int l = sg->length;
+		unsigned int o = sg->offset;
+		unsigned int ret;
+
+		ret = bio_add_zone_append_page(bio, p, l, o);
+		if (ret != sg->length) {
+			status = NVME_SC_INTERNAL;
+			goto out_put_bio;
+		}
+		total_len += sg->length;
+	}
+
+	if (total_len != nvmet_rw_data_len(req)) {
+		status = NVME_SC_INTERNAL | NVME_SC_DNR;
+		goto out_put_bio;
+	}
+
+	submit_bio(bio);
+	return;
+
+out_put_bio:
+	nvmet_req_bio_put(req, bio);
+out:
+	nvmet_req_complete(req, status);
+}
+
+u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req)
+{
+	struct nvme_command *cmd = req->cmd;
+
+	switch (cmd->common.opcode) {
+	case nvme_cmd_zone_append:
+		req->execute = nvmet_bdev_execute_zone_append;
+		return 0;
+	case nvme_cmd_zone_mgmt_recv:
+		req->execute = nvmet_bdev_execute_zone_mgmt_recv;
+		return 0;
+	case nvme_cmd_zone_mgmt_send:
+		req->execute = nvmet_bdev_execute_zone_mgmt_send;
+		return 0;
+	default:
+		return nvmet_bdev_parse_io_cmd(req);
+	}
+}

fs/pstore/Kconfig

···
 	tristate "Log panic/oops to a block device"
 	depends on PSTORE
 	depends on BLOCK
+	depends on BROKEN
 	select PSTORE_ZONE
 	default n
 	help

include/linux/acpi.h

···
 int acpi_subsys_runtime_suspend(struct device *dev);
 int acpi_subsys_runtime_resume(struct device *dev);
 int acpi_dev_pm_attach(struct device *dev, bool power_on);
+bool acpi_storage_d3(struct device *dev);
 #else
 static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; }
 static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; }
 static inline int acpi_dev_pm_attach(struct device *dev, bool power_on)
 {
 	return 0;
+}
+static inline bool acpi_storage_d3(struct device *dev)
+{
+	return false;
 }
 #endif
 

include/linux/bio.h

···
 		bio->bi_opf |= REQ_NOWAIT;
 }
 
+struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
+
 #endif /* __LINUX_BIO_H */

include/linux/nvme.h

···
 	__u8			type;
 	__u8			attributes;
 	__u8			rsvd2[14];
-	__u64			slba;
-	__u64			nlb;
+	__le64			slba;
+	__le64			nlb;
 	__u8			guid[16];
 	__u8			rsvd48[16];
 };
···
 enum {
 	NVME_ZRA_ZONE_REPORT		= 0,
 	NVME_ZRASF_ZONE_REPORT_ALL	= 0,
+	NVME_ZRASF_ZONE_STATE_EMPTY	= 0x01,
+	NVME_ZRASF_ZONE_STATE_IMP_OPEN	= 0x02,
+	NVME_ZRASF_ZONE_STATE_EXP_OPEN	= 0x03,
+	NVME_ZRASF_ZONE_STATE_CLOSED	= 0x04,
+	NVME_ZRASF_ZONE_STATE_READONLY	= 0x05,
+	NVME_ZRASF_ZONE_STATE_FULL	= 0x06,
+	NVME_ZRASF_ZONE_STATE_OFFLINE	= 0x07,
 	NVME_REPORT_ZONE_PARTIAL	= 1,
 };
 
···
 	NVME_SC_NS_WRITE_PROTECTED	= 0x20,
 	NVME_SC_CMD_INTERRUPTED		= 0x21,
 	NVME_SC_TRANSIENT_TR_ERR	= 0x22,
+	NVME_SC_INVALID_IO_CMD_SET	= 0x2C,
 
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,