Merge tag 'for-5.11/drivers-2020-12-14' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:
 "Nothing major in here:

   - NVMe pull request from Christoph:
        - nvmet passthrough improvements (Chaitanya Kulkarni)
        - fcloop error injection support (James Smart)
        - read-only support for zoned namespaces without Zone Append
          (Javier González)
        - improve some error message (Minwoo Im)
        - reject I/O to offline fabrics namespaces (Victor Gladkov)
        - PCI queue allocation cleanups (Niklas Schnelle)
        - remove an unused allocation in nvmet (Amit Engel)
        - a Kconfig spelling fix (Colin Ian King)
        - nvme_req_qid simplication (Baolin Wang)

   - MD pull request from Song:
        - Fix race condition in md_ioctl() (Dae R. Jeong)
        - Initialize read_slot properly for raid10 (Kevin Vigor)
        - Code cleanup (Pankaj Gupta)
        - md-cluster resync/reshape fix (Zhao Heming)

   - Move null_blk into its own directory (Damien Le Moal)

   - null_blk zone and discard improvements (Damien Le Moal)

   - bcache race fix (Dongsheng Yang)

   - Set of rnbd fixes/improvements (Gioh Kim, Guoqing Jiang, Jack Wang,
     Lutz Pogrell, Md Haris Iqbal)

   - lightnvm NULL pointer deref fix (tangzhenhao)

   - sr in_interrupt() removal (Sebastian Andrzej Siewior)

   - FC endpoint security support for s390/dasd (Jan Höppner, Sebastian
     Ott, Vineeth Vijayan). From the s390 arch guys, arch bits included
     as it made it easier for them to funnel the feature through the
     block driver tree.

   - Follow up fixes (Colin Ian King)"

* tag 'for-5.11/drivers-2020-12-14' of git://git.kernel.dk/linux-block: (64 commits)
  block: drop dead assignments in loop_init()
  sr: Remove in_interrupt() usage in sr_init_command().
  sr: Switch the sector size back to 2048 if sr_read_sector() changed it.
  cdrom: Reset sector_size back it is not 2048.
  drivers/lightnvm: fix a null-ptr-deref bug in pblk-core.c
  null_blk: Move driver into its own directory
  null_blk: Allow controlling max_hw_sectors limit
  null_blk: discard zones on reset
  null_blk: cleanup discard handling
  null_blk: Improve implicit zone close
  null_blk: improve zone locking
  block: Align max_hw_sectors to logical blocksize
  null_blk: Fail zone append to conventional zones
  null_blk: Fix zone size initialization
  bcache: fix race between setting bdev state to none and new write request direct to backing
  block/rnbd: fix a null pointer dereference on dev->blk_symlink_name
  block/rnbd-clt: Dynamically alloc buffer for pathname & blk_symlink_name
  block/rnbd: call kobject_put in the failure path
  Documentation/ABI/rnbd-srv: add document for force_close
  block/rnbd-srv: close a mapped device from server side.
  ...

16 files changed, 418 insertions, 207 deletions

diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ecceaaa1a66f..262326973ee0 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -16,13 +16,7 @@ menuconfig BLK_DEV
 
 if BLK_DEV
 
-config BLK_DEV_NULL_BLK
-	tristate "Null test block driver"
-	select CONFIGFS_FS
-
-config BLK_DEV_NULL_BLK_FAULT_INJECTION
-	bool "Support fault injection for Null test block driver"
-	depends on BLK_DEV_NULL_BLK && FAULT_INJECTION
+source "drivers/block/null_blk/Kconfig"
 
 config BLK_DEV_FD
 	tristate "Normal floppy disk support"
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index e1f63117ee94..a3170859e01d 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -41,12 +41,7 @@ obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
 obj-$(CONFIG_ZRAM) += zram/
 obj-$(CONFIG_BLK_DEV_RNBD)	+= rnbd/
 
-obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
-null_blk-objs	:= null_blk_main.o
-ifeq ($(CONFIG_BLK_DEV_ZONED), y)
-null_blk-$(CONFIG_TRACING) += null_blk_trace.o
-endif
-null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
+obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk/
 
 skd-y		:= skd_main.o
 swim_mod-y	:= swim.o swim_asm.o
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d2ce1ddc192d..e5ff328f0917 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -2304,7 +2304,6 @@ MODULE_ALIAS("devname:loop-control");
 static int __init loop_init(void)
 {
 	int i, nr;
-	unsigned long range;
 	struct loop_device *lo;
 	int err;
 
@@ -2341,13 +2340,10 @@ static int __init loop_init(void)
 	 * /dev/loop-control interface, or be instantiated by accessing
 	 * a 'dead' device node.
 	 */
-	if (max_loop) {
+	if (max_loop)
 		nr = max_loop;
-		range = max_loop << part_shift;
-	} else {
+	else
 		nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT;
-		range = 1UL << MINORBITS;
-	}
 
 	err = misc_register(&loop_misc);
 	if (err < 0)
diff --git a/drivers/block/null_blk/Kconfig b/drivers/block/null_blk/Kconfig
new file mode 100644
index 000000000000..6bf1f8ca20a2
--- /dev/null
+++ b/drivers/block/null_blk/Kconfig
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Null block device driver configuration
+#
+
+config BLK_DEV_NULL_BLK
+	tristate "Null test block driver"
+	select CONFIGFS_FS
+
+config BLK_DEV_NULL_BLK_FAULT_INJECTION
+	bool "Support fault injection for Null test block driver"
+	depends on BLK_DEV_NULL_BLK && FAULT_INJECTION
diff --git a/drivers/block/null_blk/Makefile b/drivers/block/null_blk/Makefile
new file mode 100644
index 000000000000..84c36e512ab8
--- /dev/null
+++ b/drivers/block/null_blk/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# needed for trace events
+ccflags-y			+= -I$(src)
+
+obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
+null_blk-objs			:= main.o
+ifeq ($(CONFIG_BLK_DEV_ZONED), y)
+null_blk-$(CONFIG_TRACING) 	+= trace.o
+endif
+null_blk-$(CONFIG_BLK_DEV_ZONED) += zoned.o
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk/main.c
index 4685ea401d5b..5357c3a4a36f 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk/main.c
@@ -152,6 +152,10 @@ static int g_bs = 512;
 module_param_named(bs, g_bs, int, 0444);
 MODULE_PARM_DESC(bs, "Block size (in bytes)");
 
+static int g_max_sectors;
+module_param_named(max_sectors, g_max_sectors, int, 0444);
+MODULE_PARM_DESC(max_sectors, "Maximum size of a command (in 512B sectors)");
+
 static unsigned int nr_devices = 1;
 module_param(nr_devices, uint, 0444);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
@@ -346,6 +350,7 @@ NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues);
 NULLB_DEVICE_ATTR(home_node, uint, NULL);
 NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
 NULLB_DEVICE_ATTR(blocksize, uint, NULL);
+NULLB_DEVICE_ATTR(max_sectors, uint, NULL);
 NULLB_DEVICE_ATTR(irqmode, uint, NULL);
 NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL);
 NULLB_DEVICE_ATTR(index, uint, NULL);
@@ -463,6 +468,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_home_node,
 	&nullb_device_attr_queue_mode,
 	&nullb_device_attr_blocksize,
+	&nullb_device_attr_max_sectors,
 	&nullb_device_attr_irqmode,
 	&nullb_device_attr_hw_queue_depth,
 	&nullb_device_attr_index,
@@ -533,7 +539,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
-			"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv,zone_max_open,zone_max_active\n");
+			"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv,zone_max_open,zone_max_active,blocksize,max_sectors\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -588,6 +594,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->home_node = g_home_node;
 	dev->queue_mode = g_queue_mode;
 	dev->blocksize = g_bs;
+	dev->max_sectors = g_max_sectors;
 	dev->irqmode = g_irqmode;
 	dev->hw_queue_depth = g_hw_queue_depth;
 	dev->blocking = g_blocking;
@@ -1076,13 +1083,16 @@ static void nullb_fill_pattern(struct nullb *nullb, struct page *page,
 	kunmap_atomic(dst);
 }
 
-static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n)
+blk_status_t null_handle_discard(struct nullb_device *dev,
+				 sector_t sector, sector_t nr_sectors)
 {
+	struct nullb *nullb = dev->nullb;
+	size_t n = nr_sectors << SECTOR_SHIFT;
 	size_t temp;
 
 	spin_lock_irq(&nullb->lock);
 	while (n > 0) {
-		temp = min_t(size_t, n, nullb->dev->blocksize);
+		temp = min_t(size_t, n, dev->blocksize);
 		null_free_sector(nullb, sector, false);
 		if (null_cache_active(nullb))
 			null_free_sector(nullb, sector, true);
@@ -1090,6 +1100,8 @@ static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n)
 		n -= temp;
 	}
 	spin_unlock_irq(&nullb->lock);
+
+	return BLK_STS_OK;
 }
 
 static int null_handle_flush(struct nullb *nullb)
@@ -1149,17 +1161,10 @@ static int null_handle_rq(struct nullb_cmd *cmd)
 	struct nullb *nullb = cmd->nq->dev->nullb;
 	int err;
 	unsigned int len;
-	sector_t sector;
+	sector_t sector = blk_rq_pos(rq);
 	struct req_iterator iter;
 	struct bio_vec bvec;
 
-	sector = blk_rq_pos(rq);
-
-	if (req_op(rq) == REQ_OP_DISCARD) {
-		null_handle_discard(nullb, sector, blk_rq_bytes(rq));
-		return 0;
-	}
-
 	spin_lock_irq(&nullb->lock);
 	rq_for_each_segment(bvec, rq, iter) {
 		len = bvec.bv_len;
@@ -1183,18 +1188,10 @@ static int null_handle_bio(struct nullb_cmd *cmd)
 	struct nullb *nullb = cmd->nq->dev->nullb;
 	int err;
 	unsigned int len;
-	sector_t sector;
+	sector_t sector = bio->bi_iter.bi_sector;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 
-	sector = bio->bi_iter.bi_sector;
-
-	if (bio_op(bio) == REQ_OP_DISCARD) {
-		null_handle_discard(nullb, sector,
-			bio_sectors(bio) << SECTOR_SHIFT);
-		return 0;
-	}
-
 	spin_lock_irq(&nullb->lock);
 	bio_for_each_segment(bvec, bio, iter) {
 		len = bvec.bv_len;
@@ -1263,11 +1260,16 @@ static inline blk_status_t null_handle_badblocks(struct nullb_cmd *cmd,
 }
 
 static inline blk_status_t null_handle_memory_backed(struct nullb_cmd *cmd,
-						     enum req_opf op)
+						     enum req_opf op,
+						     sector_t sector,
+						     sector_t nr_sectors)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	int err;
 
+	if (op == REQ_OP_DISCARD)
+		return null_handle_discard(dev, sector, nr_sectors);
+
 	if (dev->queue_mode == NULL_Q_BIO)
 		err = null_handle_bio(cmd);
 	else
@@ -1343,7 +1345,7 @@ blk_status_t null_process_cmd(struct nullb_cmd *cmd,
 	}
 
 	if (dev->memory_backed)
-		return null_handle_memory_backed(cmd, op);
+		return null_handle_memory_backed(cmd, op, sector, nr_sectors);
 
 	return BLK_STS_OK;
 }
@@ -1589,6 +1591,12 @@ static void null_config_discard(struct nullb *nullb)
 	if (nullb->dev->discard == false)
 		return;
 
+	if (!nullb->dev->memory_backed) {
+		nullb->dev->discard = false;
+		pr_info("discard option is ignored without memory backing\n");
+		return;
+	}
+
 	if (nullb->dev->zoned) {
 		nullb->dev->discard = false;
 		pr_info("discard option is ignored in zoned mode\n");
@@ -1866,6 +1874,11 @@ static int null_add_dev(struct nullb_device *dev)
 
 	blk_queue_logical_block_size(nullb->q, dev->blocksize);
 	blk_queue_physical_block_size(nullb->q, dev->blocksize);
+	if (!dev->max_sectors)
+		dev->max_sectors = queue_max_hw_sectors(nullb->q);
+	dev->max_sectors = min_t(unsigned int, dev->max_sectors,
+				 BLK_DEF_MAX_SECTORS);
+	blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
 
 	null_config_discard(nullb);
 
@@ -1909,6 +1922,12 @@ static int __init null_init(void)
 		g_bs = PAGE_SIZE;
 	}
 
+	if (g_max_sectors > BLK_DEF_MAX_SECTORS) {
+		pr_warn("invalid max sectors\n");
+		pr_warn("defaults max sectors to %u\n", BLK_DEF_MAX_SECTORS);
+		g_max_sectors = BLK_DEF_MAX_SECTORS;
+	}
+
 	if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) {
 		pr_err("invalid home_node value\n");
 		g_home_node = NUMA_NO_NODE;
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk/null_blk.h
index c24d9b5ad81a..83504f3cc9d6 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -12,6 +12,8 @@
 #include <linux/configfs.h>
 #include <linux/badblocks.h>
 #include <linux/fault-inject.h>
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
 
 struct nullb_cmd {
 	struct request *rq;
@@ -32,6 +34,26 @@ struct nullb_queue {
 	struct nullb_cmd *cmds;
 };
 
+struct nullb_zone {
+	/*
+	 * Zone lock to prevent concurrent modification of a zone write
+	 * pointer position and condition: with memory backing, a write
+	 * command execution may sleep on memory allocation. For this case,
+	 * use mutex as the zone lock. Otherwise, use the spinlock for
+	 * locking the zone.
+	 */
+	union {
+		spinlock_t spinlock;
+		struct mutex mutex;
+	};
+	enum blk_zone_type type;
+	enum blk_zone_cond cond;
+	sector_t start;
+	sector_t wp;
+	unsigned int len;
+	unsigned int capacity;
+};
+
 struct nullb_device {
 	struct nullb *nullb;
 	struct config_item item;
@@ -45,10 +67,11 @@ struct nullb_device {
 	unsigned int nr_zones_imp_open;
 	unsigned int nr_zones_exp_open;
 	unsigned int nr_zones_closed;
-	struct blk_zone *zones;
+	unsigned int imp_close_zone_no;
+	struct nullb_zone *zones;
 	sector_t zone_size_sects;
-	spinlock_t zone_lock;
-	unsigned long *zone_locks;
+	bool need_zone_res_mgmt;
+	spinlock_t zone_res_lock;
 
 	unsigned long size; /* device size in MB */
 	unsigned long completion_nsec; /* time in ns to complete a request */
@@ -62,6 +85,7 @@ struct nullb_device {
 	unsigned int home_node; /* home node for the device */
 	unsigned int queue_mode; /* block interface */
 	unsigned int blocksize; /* block size */
+	unsigned int max_sectors; /* Max sectors per command */
 	unsigned int irqmode; /* IRQ completion handler */
 	unsigned int hw_queue_depth; /* queue depth */
 	unsigned int index; /* index of the disk, only valid with a disk */
@@ -93,6 +117,8 @@ struct nullb {
 	char disk_name[DISK_NAME_LEN];
 };
 
+blk_status_t null_handle_discard(struct nullb_device *dev, sector_t sector,
+				 sector_t nr_sectors);
 blk_status_t null_process_cmd(struct nullb_cmd *cmd,
 			      enum req_opf op, sector_t sector,
 			      unsigned int nr_sectors);
diff --git a/drivers/block/null_blk_trace.c b/drivers/block/null_blk/trace.c
index f246e7bff698..3711cba16071 100644
--- a/drivers/block/null_blk_trace.c
+++ b/drivers/block/null_blk/trace.c
@@ -4,7 +4,7 @@
  *
  * Copyright (C) 2020 Western Digital Corporation or its affiliates.
  */
-#include "null_blk_trace.h"
+#include "trace.h"
 
 /*
  * Helper to use for all null_blk traces to extract disk name.
diff --git a/drivers/block/null_blk_trace.h b/drivers/block/null_blk/trace.h
index 4f83032eb544..ce3b430e88c5 100644
--- a/drivers/block/null_blk_trace.h
+++ b/drivers/block/null_blk/trace.h
@@ -73,7 +73,7 @@ TRACE_EVENT(nullb_report_zones,
 #undef TRACE_INCLUDE_PATH
 #define TRACE_INCLUDE_PATH .
 #undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_FILE null_blk_trace
+#define TRACE_INCLUDE_FILE trace
 
 /* This part must be outside protection */
 #include <trace/define_trace.h>
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk/zoned.c
index beb34b4f76b0..148b871f263b 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -4,19 +4,58 @@
 #include "null_blk.h"
 
 #define CREATE_TRACE_POINTS
-#include "null_blk_trace.h"
+#include "trace.h"
 
-/* zone_size in MBs to sectors. */
-#define ZONE_SIZE_SHIFT		11
+#define MB_TO_SECTS(mb) (((sector_t)mb * SZ_1M) >> SECTOR_SHIFT)
 
 static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
 {
 	return sect >> ilog2(dev->zone_size_sects);
 }
 
+static inline void null_lock_zone_res(struct nullb_device *dev)
+{
+	if (dev->need_zone_res_mgmt)
+		spin_lock_irq(&dev->zone_res_lock);
+}
+
+static inline void null_unlock_zone_res(struct nullb_device *dev)
+{
+	if (dev->need_zone_res_mgmt)
+		spin_unlock_irq(&dev->zone_res_lock);
+}
+
+static inline void null_init_zone_lock(struct nullb_device *dev,
+				       struct nullb_zone *zone)
+{
+	if (!dev->memory_backed)
+		spin_lock_init(&zone->spinlock);
+	else
+		mutex_init(&zone->mutex);
+}
+
+static inline void null_lock_zone(struct nullb_device *dev,
+				  struct nullb_zone *zone)
+{
+	if (!dev->memory_backed)
+		spin_lock_irq(&zone->spinlock);
+	else
+		mutex_lock(&zone->mutex);
+}
+
+static inline void null_unlock_zone(struct nullb_device *dev,
+				    struct nullb_zone *zone)
+{
+	if (!dev->memory_backed)
+		spin_unlock_irq(&zone->spinlock);
+	else
+		mutex_unlock(&zone->mutex);
+}
+
 int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 {
-	sector_t dev_size = (sector_t)dev->size * 1024 * 1024;
+	sector_t dev_capacity_sects, zone_capacity_sects;
+	struct nullb_zone *zone;
 	sector_t sector = 0;
 	unsigned int i;
 
@@ -38,29 +77,19 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 		return -EINVAL;
 	}
 
-	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
-	dev->nr_zones = dev_size >>
-				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
-	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct blk_zone),
-			GFP_KERNEL | __GFP_ZERO);
+	zone_capacity_sects = MB_TO_SECTS(dev->zone_capacity);
+	dev_capacity_sects = MB_TO_SECTS(dev->size);
+	dev->zone_size_sects = MB_TO_SECTS(dev->zone_size);
+	dev->nr_zones = dev_capacity_sects >> ilog2(dev->zone_size_sects);
+	if (dev_capacity_sects & (dev->zone_size_sects - 1))
+		dev->nr_zones++;
+
+	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct nullb_zone),
+				    GFP_KERNEL | __GFP_ZERO);
 	if (!dev->zones)
 		return -ENOMEM;
 
-	/*
-	 * With memory backing, the zone_lock spinlock needs to be temporarily
-	 * released to avoid scheduling in atomic context. To guarantee zone
-	 * information protection, use a bitmap to lock zones with
-	 * wait_on_bit_lock_io(). Sleeping on the lock is OK as memory backing
-	 * implies that the queue is marked with BLK_MQ_F_BLOCKING.
-	 */
-	spin_lock_init(&dev->zone_lock);
-	if (dev->memory_backed) {
-		dev->zone_locks = bitmap_zalloc(dev->nr_zones, GFP_KERNEL);
-		if (!dev->zone_locks) {
-			kvfree(dev->zones);
-			return -ENOMEM;
-		}
-	}
+	spin_lock_init(&dev->zone_res_lock);
 
 	if (dev->zone_nr_conv >= dev->nr_zones) {
 		dev->zone_nr_conv = dev->nr_zones - 1;
@@ -83,10 +112,13 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 		dev->zone_max_open = 0;
 		pr_info("zone_max_open limit disabled, limit >= zone count\n");
 	}
+	dev->need_zone_res_mgmt = dev->zone_max_active || dev->zone_max_open;
+	dev->imp_close_zone_no = dev->zone_nr_conv;
 
 	for (i = 0; i <  dev->zone_nr_conv; i++) {
-		struct blk_zone *zone = &dev->zones[i];
+		zone = &dev->zones[i];
 
+		null_init_zone_lock(dev, zone);
 		zone->start = sector;
 		zone->len = dev->zone_size_sects;
 		zone->capacity = zone->len;
@@ -98,11 +130,16 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 	}
 
 	for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
-		struct blk_zone *zone = &dev->zones[i];
+		zone = &dev->zones[i];
 
+		null_init_zone_lock(dev, zone);
 		zone->start = zone->wp = sector;
-		zone->len = dev->zone_size_sects;
-		zone->capacity = dev->zone_capacity << ZONE_SIZE_SHIFT;
+		if (zone->start + dev->zone_size_sects > dev_capacity_sects)
+			zone->len = dev_capacity_sects - zone->start;
+		else
+			zone->len = dev->zone_size_sects;
+		zone->capacity =
+			min_t(sector_t, zone->len, zone_capacity_sects);
 		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
 		zone->cond = BLK_ZONE_COND_EMPTY;
 
@@ -140,32 +177,17 @@ int null_register_zoned_dev(struct nullb *nullb)
 
 void null_free_zoned_dev(struct nullb_device *dev)
 {
-	bitmap_free(dev->zone_locks);
 	kvfree(dev->zones);
 }
 
-static inline void null_lock_zone(struct nullb_device *dev, unsigned int zno)
-{
-	if (dev->memory_backed)
-		wait_on_bit_lock_io(dev->zone_locks, zno, TASK_UNINTERRUPTIBLE);
-	spin_lock_irq(&dev->zone_lock);
-}
-
-static inline void null_unlock_zone(struct nullb_device *dev, unsigned int zno)
-{
-	spin_unlock_irq(&dev->zone_lock);
-
-	if (dev->memory_backed)
-		clear_and_wake_up_bit(zno, dev->zone_locks);
-}
-
 int null_report_zones(struct gendisk *disk, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct nullb *nullb = disk->private_data;
 	struct nullb_device *dev = nullb->dev;
-	unsigned int first_zone, i, zno;
-	struct blk_zone zone;
+	unsigned int first_zone, i;
+	struct nullb_zone *zone;
+	struct blk_zone blkz;
 	int error;
 
 	first_zone = null_zone_no(dev, sector);
@@ -175,19 +197,25 @@ int null_report_zones(struct gendisk *disk, sector_t sector,
 	nr_zones = min(nr_zones, dev->nr_zones - first_zone);
 	trace_nullb_report_zones(nullb, nr_zones);
 
-	zno = first_zone;
-	for (i = 0; i < nr_zones; i++, zno++) {
+	memset(&blkz, 0, sizeof(struct blk_zone));
+	zone = &dev->zones[first_zone];
+	for (i = 0; i < nr_zones; i++, zone++) {
 		/*
 		 * Stacked DM target drivers will remap the zone information by
 		 * modifying the zone information passed to the report callback.
 		 * So use a local copy to avoid corruption of the device zone
 		 * array.
 		 */
-		null_lock_zone(dev, zno);
-		memcpy(&zone, &dev->zones[zno], sizeof(struct blk_zone));
-		null_unlock_zone(dev, zno);
-
-		error = cb(&zone, i, data);
+		null_lock_zone(dev, zone);
+		blkz.start = zone->start;
+		blkz.len = zone->len;
+		blkz.wp = zone->wp;
+		blkz.type = zone->type;
+		blkz.cond = zone->cond;
+		blkz.capacity = zone->capacity;
+		null_unlock_zone(dev, zone);
+
+		error = cb(&blkz, i, data);
 		if (error)
 			return error;
 	}
@@ -203,7 +231,7 @@ size_t null_zone_valid_read_len(struct nullb *nullb,
 				sector_t sector, unsigned int len)
 {
 	struct nullb_device *dev = nullb->dev;
-	struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
+	struct nullb_zone *zone = &dev->zones[null_zone_no(dev, sector)];
 	unsigned int nr_sectors = len >> SECTOR_SHIFT;
 
 	/* Read must be below the write pointer position */
@@ -217,11 +245,9 @@ size_t null_zone_valid_read_len(struct nullb *nullb,
 	return (zone->wp - sector) << SECTOR_SHIFT;
 }
 
-static blk_status_t null_close_zone(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t __null_close_zone(struct nullb_device *dev,
+				      struct nullb_zone *zone)
 {
-	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
-		return BLK_STS_IOERR;
-
 	switch (zone->cond) {
 	case BLK_ZONE_COND_CLOSED:
 		/* close operation on closed is not an error */
@@ -248,13 +274,24 @@ static blk_status_t null_close_zone(struct nullb_device *dev, struct blk_zone *z
 	return BLK_STS_OK;
 }
 
-static void null_close_first_imp_zone(struct nullb_device *dev)
+static void null_close_imp_open_zone(struct nullb_device *dev)
 {
-	unsigned int i;
+	struct nullb_zone *zone;
+	unsigned int zno, i;
+
+	zno = dev->imp_close_zone_no;
+	if (zno >= dev->nr_zones)
+		zno = dev->zone_nr_conv;
 
 	for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
-		if (dev->zones[i].cond == BLK_ZONE_COND_IMP_OPEN) {
-			null_close_zone(dev, &dev->zones[i]);
+		zone = &dev->zones[zno];
+		zno++;
+		if (zno >= dev->nr_zones)
+			zno = dev->zone_nr_conv;
+
+		if (zone->cond == BLK_ZONE_COND_IMP_OPEN) {
+			__null_close_zone(dev, zone);
+			dev->imp_close_zone_no = zno;
 			return;
 		}
 	}
@@ -282,7 +319,7 @@ static blk_status_t null_check_open(struct nullb_device *dev)
 
 	if (dev->nr_zones_imp_open) {
 		if (null_check_active(dev) == BLK_STS_OK) {
-			null_close_first_imp_zone(dev);
+			null_close_imp_open_zone(dev);
 			return BLK_STS_OK;
 		}
 	}
@@ -303,7 +340,8 @@ static blk_status_t null_check_open(struct nullb_device *dev)
  * it is not certain that closing an implicit open zone will allow a new zone
  * to be opened, since we might already be at the active limit capacity.
  */
-static blk_status_t null_check_zone_resources(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_check_zone_resources(struct nullb_device *dev,
+					      struct nullb_zone *zone)
 {
 	blk_status_t ret;
 
@@ -327,34 +365,23 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	unsigned int zno = null_zone_no(dev, sector);
-	struct blk_zone *zone = &dev->zones[zno];
+	struct nullb_zone *zone = &dev->zones[zno];
 	blk_status_t ret;
 
 	trace_nullb_zone_op(cmd, zno, zone->cond);
 
-	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) {
+		if (append)
+			return BLK_STS_IOERR;
 		return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
+	}
 
-	null_lock_zone(dev, zno);
+	null_lock_zone(dev, zone);
 
-	switch (zone->cond) {
-	case BLK_ZONE_COND_FULL:
+	if (zone->cond == BLK_ZONE_COND_FULL) {
 		/* Cannot write to a full zone */
 		ret = BLK_STS_IOERR;
 		goto unlock;
-	case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_CLOSED:
-		ret = null_check_zone_resources(dev, zone);
-		if (ret != BLK_STS_OK)
-			goto unlock;
-		break;
-	case BLK_ZONE_COND_IMP_OPEN:
-	case BLK_ZONE_COND_EXP_OPEN:
-		break;
-	default:
-		/* Invalid zone condition */
-		ret = BLK_STS_IOERR;
-		goto unlock;
 	}
 
 	/*
@@ -379,60 +406,69 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 		goto unlock;
 	}
 
-	if (zone->cond == BLK_ZONE_COND_CLOSED) {
-		dev->nr_zones_closed--;
-		dev->nr_zones_imp_open++;
-	} else if (zone->cond == BLK_ZONE_COND_EMPTY) {
-		dev->nr_zones_imp_open++;
+	if (zone->cond == BLK_ZONE_COND_CLOSED ||
+	    zone->cond == BLK_ZONE_COND_EMPTY) {
+		null_lock_zone_res(dev);
+
+		ret = null_check_zone_resources(dev, zone);
+		if (ret != BLK_STS_OK) {
+			null_unlock_zone_res(dev);
+			goto unlock;
+		}
+		if (zone->cond == BLK_ZONE_COND_CLOSED) {
+			dev->nr_zones_closed--;
+			dev->nr_zones_imp_open++;
+		} else if (zone->cond == BLK_ZONE_COND_EMPTY) {
+			dev->nr_zones_imp_open++;
+		}
+
+		if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
+			zone->cond = BLK_ZONE_COND_IMP_OPEN;
+
+		null_unlock_zone_res(dev);
 	}
-	if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
-		zone->cond = BLK_ZONE_COND_IMP_OPEN;
 
-	/*
-	 * Memory backing allocation may sleep: release the zone_lock spinlock
-	 * to avoid scheduling in atomic context. Zone operation atomicity is
-	 * still guaranteed through the zone_locks bitmap.
-	 */
-	if (dev->memory_backed)
-		spin_unlock_irq(&dev->zone_lock);
 	ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
-	if (dev->memory_backed)
-		spin_lock_irq(&dev->zone_lock);
-
 	if (ret != BLK_STS_OK)
 		goto unlock;
 
 	zone->wp += nr_sectors;
 	if (zone->wp == zone->start + zone->capacity) {
+		null_lock_zone_res(dev);
 		if (zone->cond == BLK_ZONE_COND_EXP_OPEN)
 			dev->nr_zones_exp_open--;
 		else if (zone->cond == BLK_ZONE_COND_IMP_OPEN)
 			dev->nr_zones_imp_open--;
 		zone->cond = BLK_ZONE_COND_FULL;
+		null_unlock_zone_res(dev);
 	}
+
 	ret = BLK_STS_OK;
 
 unlock:
-	null_unlock_zone(dev, zno);
+	null_unlock_zone(dev, zone);
 
 	return ret;
 }
 
-static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_open_zone(struct nullb_device *dev,
+				   struct nullb_zone *zone)
 {
-	blk_status_t ret;
+	blk_status_t ret = BLK_STS_OK;
 
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
+	null_lock_zone_res(dev);
+
 	switch (zone->cond) {
 	case BLK_ZONE_COND_EXP_OPEN:
 		/* open operation on exp open is not an error */
-		return BLK_STS_OK;
+		goto unlock;
 	case BLK_ZONE_COND_EMPTY:
 		ret = null_check_zone_resources(dev, zone);
 		if (ret != BLK_STS_OK)
-			return ret;
+			goto unlock;
 		break;
 	case BLK_ZONE_COND_IMP_OPEN:
 		dev->nr_zones_imp_open--;
@@ -440,35 +476,57 @@ static blk_status_t null_open_zone(struct nullb_device *dev, struct blk_zone *zo
 	case BLK_ZONE_COND_CLOSED:
 		ret = null_check_zone_resources(dev, zone);
 		if (ret != BLK_STS_OK)
-			return ret;
+			goto unlock;
 		dev->nr_zones_closed--;
 		break;
 	case BLK_ZONE_COND_FULL:
 	default:
-		return BLK_STS_IOERR;
+		ret = BLK_STS_IOERR;
+		goto unlock;
 	}
 
 	zone->cond = BLK_ZONE_COND_EXP_OPEN;
 	dev->nr_zones_exp_open++;
 
-	return BLK_STS_OK;
+unlock:
+	null_unlock_zone_res(dev);
+
+	return ret;
 }
 
-static blk_status_t null_finish_zone(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_close_zone(struct nullb_device *dev,
+				    struct nullb_zone *zone)
 {
 	blk_status_t ret;
 
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
+	null_lock_zone_res(dev);
+	ret = __null_close_zone(dev, zone);
+	null_unlock_zone_res(dev);
+
+	return ret;
+}
+
+static blk_status_t null_finish_zone(struct nullb_device *dev,
+				     struct nullb_zone *zone)
+{
+	blk_status_t ret = BLK_STS_OK;
+
+	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+		return BLK_STS_IOERR;
+
+	null_lock_zone_res(dev);
+
 	switch (zone->cond) {
 	case BLK_ZONE_COND_FULL:
 		/* finish operation on full is not an error */
-		return BLK_STS_OK;
+		goto unlock;
 	case BLK_ZONE_COND_EMPTY:
 		ret = null_check_zone_resources(dev, zone);
 		if (ret != BLK_STS_OK)
-			return ret;
+			goto unlock;
 		break;
 	case BLK_ZONE_COND_IMP_OPEN:
 		dev->nr_zones_imp_open--;
@@ -479,27 +537,35 @@ static blk_status_t null_finish_zone(struct nullb_device *dev, struct blk_zone *
 	case BLK_ZONE_COND_CLOSED:
 		ret = null_check_zone_resources(dev, zone);
 		if (ret != BLK_STS_OK)
-			return ret;
+			goto unlock;
 		dev->nr_zones_closed--;
 		break;
 	default:
-		return BLK_STS_IOERR;
+		ret = BLK_STS_IOERR;
+		goto unlock;
 	}
 
 	zone->cond = BLK_ZONE_COND_FULL;
 	zone->wp = zone->start + zone->len;
 
-	return BLK_STS_OK;
+unlock:
+	null_unlock_zone_res(dev);
+
+	return ret;
 }
 
-static blk_status_t null_reset_zone(struct nullb_device *dev, struct blk_zone *zone)
+static blk_status_t null_reset_zone(struct nullb_device *dev,
+				    struct nullb_zone *zone)
 {
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
 		return BLK_STS_IOERR;
 
+	null_lock_zone_res(dev);
+
 	switch (zone->cond) {
 	case BLK_ZONE_COND_EMPTY:
 		/* reset operation on empty is not an error */
+		null_unlock_zone_res(dev);
 		return BLK_STS_OK;
 	case BLK_ZONE_COND_IMP_OPEN:
 		dev->nr_zones_imp_open--;
@@ -513,12 +579,18 @@ static blk_status_t null_reset_zone(struct nullb_device *dev, struct blk_zone *z
 	case BLK_ZONE_COND_FULL:
 		break;
 	default:
+		null_unlock_zone_res(dev);
 		return BLK_STS_IOERR;
 	}
 
 	zone->cond = BLK_ZONE_COND_EMPTY;
 	zone->wp = zone->start;
 
+	null_unlock_zone_res(dev);
+
+	if (dev->memory_backed)
+		return null_handle_discard(dev, zone->start, zone->len);
+
 	return BLK_STS_OK;
 }
 
@@ -527,19 +599,19 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	unsigned int zone_no;
-	struct blk_zone *zone;
+	struct nullb_zone *zone;
 	blk_status_t ret;
 	size_t i;
 
 	if (op == REQ_OP_ZONE_RESET_ALL) {
 		for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
-			null_lock_zone(dev, i);
 			zone = &dev->zones[i];
+			null_lock_zone(dev, zone);
 			if (zone->cond != BLK_ZONE_COND_EMPTY) {
 				null_reset_zone(dev, zone);
 				trace_nullb_zone_op(cmd, i, zone->cond);
 			}
-			null_unlock_zone(dev, i);
+			null_unlock_zone(dev, zone);
 		}
 		return BLK_STS_OK;
 	}
@@ -547,7 +619,7 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 	zone_no = null_zone_no(dev, sector);
 	zone = &dev->zones[zone_no];
 
-	null_lock_zone(dev, zone_no);
+	null_lock_zone(dev, zone);
 
 	switch (op) {
 	case REQ_OP_ZONE_RESET:
@@ -570,7 +642,7 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 	if (ret == BLK_STS_OK)
 		trace_nullb_zone_op(cmd, zone_no, zone->cond);
 
-	null_unlock_zone(dev, zone_no);
+	null_unlock_zone(dev, zone);
 
 	return ret;
 }
@@ -578,29 +650,28 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
 blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
 				    sector_t sector, sector_t nr_sectors)
 {
-	struct nullb_device *dev = cmd->nq->dev;
-	unsigned int zno = null_zone_no(dev, sector);
+	struct nullb_device *dev;
+	struct nullb_zone *zone;
 	blk_status_t sts;
 
 	switch (op) {
 	case REQ_OP_WRITE:
-		sts = null_zone_write(cmd, sector, nr_sectors, false);
-		break;
+		return null_zone_write(cmd, sector, nr_sectors, false);
 	case REQ_OP_ZONE_APPEND:
-		sts = null_zone_write(cmd, sector, nr_sectors, true);
-		break;
+		return null_zone_write(cmd, sector, nr_sectors, true);
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_RESET_ALL:
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
 	case REQ_OP_ZONE_FINISH:
-		sts = null_zone_mgmt(cmd, op, sector);
-		break;
+		return null_zone_mgmt(cmd, op, sector);
 	default:
-		null_lock_zone(dev, zno);
+		dev = cmd->nq->dev;
+		zone = &dev->zones[null_zone_no(dev, sector)];
+
+		null_lock_zone(dev, zone);
 		sts = null_process_cmd(cmd, op, sector, nr_sectors);
-		null_unlock_zone(dev, zno);
+		null_unlock_zone(dev, zone);
+		return sts;
 	}
-
-	return sts;
 }
diff --git a/drivers/block/rnbd/rnbd-clt-sysfs.c b/drivers/block/rnbd/rnbd-clt-sysfs.c
index 4f4474eecadb..a7caeedeb198 100644
--- a/drivers/block/rnbd/rnbd-clt-sysfs.c
+++ b/drivers/block/rnbd/rnbd-clt-sysfs.c
@@ -37,7 +37,6 @@ enum {
 };
 
 static const unsigned int rnbd_opt_mandatory[] = {
-	RNBD_OPT_PATH,
 	RNBD_OPT_DEV_PATH,
 	RNBD_OPT_SESSNAME,
 };
@@ -435,6 +434,7 @@ void rnbd_clt_remove_dev_symlink(struct rnbd_clt_dev *dev)
 	 */
 	if (strlen(dev->blk_symlink_name) && try_module_get(THIS_MODULE)) {
 		sysfs_remove_link(rnbd_devs_kobj, dev->blk_symlink_name);
+		kfree(dev->blk_symlink_name);
 		module_put(THIS_MODULE);
 	}
 }
@@ -451,9 +451,11 @@ static int rnbd_clt_add_dev_kobj(struct rnbd_clt_dev *dev)
 
 	ret = kobject_init_and_add(&dev->kobj, &rnbd_dev_ktype, gd_kobj, "%s",
 				   "rnbd");
-	if (ret)
+	if (ret) {
 		rnbd_clt_err(dev, "Failed to create device sysfs dir, err: %d\n",
 			      ret);
+		kobject_put(&dev->kobj);
+	}
 
 	return ret;
 }
@@ -481,16 +483,27 @@ static int rnbd_clt_get_path_name(struct rnbd_clt_dev *dev, char *buf,
 	if (ret >= len)
 		return -ENAMETOOLONG;
 
+	ret = snprintf(buf, len, "%s@%s", buf, dev->sess->sessname);
+	if (ret >= len)
+		return -ENAMETOOLONG;
+
 	return 0;
 }
 
 static int rnbd_clt_add_dev_symlink(struct rnbd_clt_dev *dev)
 {
 	struct kobject *gd_kobj = &disk_to_dev(dev->gd)->kobj;
-	int ret;
+	int ret, len;
+
+	len = strlen(dev->pathname) + strlen(dev->sess->sessname) + 2;
+	dev->blk_symlink_name = kzalloc(len, GFP_KERNEL);
+	if (!dev->blk_symlink_name) {
+		rnbd_clt_err(dev, "Failed to allocate memory for blk_symlink_name\n");
+		return -ENOMEM;
+	}
 
 	ret = rnbd_clt_get_path_name(dev, dev->blk_symlink_name,
-				      sizeof(dev->blk_symlink_name));
+				      len);
 	if (ret) {
 		rnbd_clt_err(dev, "Failed to get /sys/block symlink path, err: %d\n",
 			      ret);
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index bb13d7dd195a..a199b190c73d 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -59,6 +59,7 @@ static void rnbd_clt_put_dev(struct rnbd_clt_dev *dev)
 	ida_simple_remove(&index_ida, dev->clt_device_id);
 	mutex_unlock(&ida_lock);
 	kfree(dev->hw_queues);
+	kfree(dev->pathname);
 	rnbd_clt_put_sess(dev->sess);
 	mutex_destroy(&dev->lock);
 	kfree(dev);
@@ -1192,6 +1193,12 @@ find_and_get_or_create_sess(const char *sessname,
 	else if (!first)
 		return sess;
 
+	if (!path_cnt) {
+		pr_err("Session %s not found, and path parameter not given", sessname);
+		err = -ENXIO;
+		goto put_sess;
+	}
+
 	rtrs_ops = (struct rtrs_clt_ops) {
 		.priv = sess,
 		.link_ev = rnbd_clt_link_ev,
@@ -1380,10 +1387,17 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess,
 		       pathname, sess->sessname, ret);
 		goto out_queues;
 	}
+
+	dev->pathname = kzalloc(strlen(pathname) + 1, GFP_KERNEL);
+	if (!dev->pathname) {
+		ret = -ENOMEM;
+		goto out_queues;
+	}
+	strlcpy(dev->pathname, pathname, strlen(pathname) + 1);
+
 	dev->clt_device_id	= ret;
 	dev->sess		= sess;
 	dev->access_mode	= access_mode;
-	strlcpy(dev->pathname, pathname, sizeof(dev->pathname));
 	mutex_init(&dev->lock);
 	refcount_set(&dev->refcount, 1);
 	dev->dev_state = DEV_STATE_INIT;
@@ -1403,17 +1417,20 @@ out_alloc:
 	return ERR_PTR(ret);
 }
 
-static bool __exists_dev(const char *pathname)
+static bool __exists_dev(const char *pathname, const char *sessname)
 {
 	struct rnbd_clt_session *sess;
 	struct rnbd_clt_dev *dev;
 	bool found = false;
 
 	list_for_each_entry(sess, &sess_list, list) {
+		if (sessname && strncmp(sess->sessname, sessname,
+					sizeof(sess->sessname)))
+			continue;
 		mutex_lock(&sess->lock);
 		list_for_each_entry(dev, &sess->devs_list, list) {
-			if (!strncmp(dev->pathname, pathname,
-				     sizeof(dev->pathname))) {
+			if (strlen(dev->pathname) == strlen(pathname) &&
+			    !strcmp(dev->pathname, pathname)) {
 				found = true;
 				break;
 			}
@@ -1426,12 +1443,12 @@ static bool __exists_dev(const char *pathname)
 	return found;
 }
 
-static bool exists_devpath(const char *pathname)
+static bool exists_devpath(const char *pathname, const char *sessname)
 {
 	bool found;
 
 	mutex_lock(&sess_lock);
-	found = __exists_dev(pathname);
+	found = __exists_dev(pathname, sessname);
 	mutex_unlock(&sess_lock);
 
 	return found;
@@ -1444,7 +1461,7 @@ static bool insert_dev_if_not_exists_devpath(const char *pathname,
 	bool found;
 
 	mutex_lock(&sess_lock);
-	found = __exists_dev(pathname);
+	found = __exists_dev(pathname, sess->sessname);
 	if (!found) {
 		mutex_lock(&sess->lock);
 		list_add_tail(&dev->list, &sess->devs_list);
@@ -1474,7 +1491,7 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname,
 	struct rnbd_clt_dev *dev;
 	int ret;
 
-	if (exists_devpath(pathname))
+	if (unlikely(exists_devpath(pathname, sessname)))
 		return ERR_PTR(-EEXIST);
 
 	sess = find_and_get_or_create_sess(sessname, paths, path_cnt, port_nr);
diff --git a/drivers/block/rnbd/rnbd-clt.h b/drivers/block/rnbd/rnbd-clt.h
index ed33654aa486..b193d5904050 100644
--- a/drivers/block/rnbd/rnbd-clt.h
+++ b/drivers/block/rnbd/rnbd-clt.h
@@ -108,7 +108,7 @@ struct rnbd_clt_dev {
 	u32			clt_device_id;
 	struct mutex		lock;
 	enum rnbd_clt_dev_state	dev_state;
-	char			pathname[NAME_MAX];
+	char			*pathname;
 	enum rnbd_access_mode	access_mode;
 	bool			read_only;
 	bool			rotational;
@@ -126,7 +126,7 @@ struct rnbd_clt_dev {
 	struct list_head        list;
 	struct gendisk		*gd;
 	struct kobject		kobj;
-	char			blk_symlink_name[NAME_MAX];
+	char			*blk_symlink_name;
 	refcount_t		refcount;
 	struct work_struct	unmap_on_rmmod_work;
 };
diff --git a/drivers/block/rnbd/rnbd-srv-sysfs.c b/drivers/block/rnbd/rnbd-srv-sysfs.c
index 106775c074d1..05ffe488ddc6 100644
--- a/drivers/block/rnbd/rnbd-srv-sysfs.c
+++ b/drivers/block/rnbd/rnbd-srv-sysfs.c
@@ -47,13 +47,17 @@ int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev,
 
 	ret = kobject_init_and_add(&dev->dev_kobj, &dev_ktype,
 				   rnbd_devs_kobj, dev_name);
-	if (ret)
+	if (ret) {
+		kobject_put(&dev->dev_kobj);
 		return ret;
+	}
 
 	dev->dev_sessions_kobj = kobject_create_and_add("sessions",
 							&dev->dev_kobj);
-	if (!dev->dev_sessions_kobj)
-		goto put_dev_kobj;
+	if (!dev->dev_sessions_kobj) {
+		ret = -ENOMEM;
+		goto free_dev_kobj;
+	}
 
 	bdev_kobj = &disk_to_dev(bdev->bd_disk)->kobj;
 	ret = sysfs_create_link(&dev->dev_kobj, bdev_kobj, "block_dev");
@@ -64,7 +68,8 @@ int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev,
 
 put_sess_kobj:
 	kobject_put(dev->dev_sessions_kobj);
-put_dev_kobj:
+free_dev_kobj:
+	kobject_del(&dev->dev_kobj);
 	kobject_put(&dev->dev_kobj);
 	return ret;
 }
@@ -120,10 +125,46 @@ static ssize_t mapping_path_show(struct kobject *kobj,
 static struct kobj_attribute rnbd_srv_dev_session_mapping_path_attr =
 	__ATTR_RO(mapping_path);
 
+static ssize_t rnbd_srv_dev_session_force_close_show(struct kobject *kobj,
+					struct kobj_attribute *attr, char *page)
+{
+	return scnprintf(page, PAGE_SIZE, "Usage: echo 1 > %s\n",
+			 attr->attr.name);
+}
+
+static ssize_t rnbd_srv_dev_session_force_close_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct rnbd_srv_sess_dev *sess_dev;
+
+	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
+
+	if (!sysfs_streq(buf, "1")) {
+		rnbd_srv_err(sess_dev, "%s: invalid value: '%s'\n",
+			      attr->attr.name, buf);
+		return -EINVAL;
+	}
+
+	rnbd_srv_info(sess_dev, "force close requested\n");
+
+	/* first remove sysfs itself to avoid deadlock */
+	sysfs_remove_file_self(&sess_dev->kobj, &attr->attr);
+	rnbd_srv_sess_dev_force_close(sess_dev);
+
+	return count;
+}
+
+static struct kobj_attribute rnbd_srv_dev_session_force_close_attr =
+	__ATTR(force_close, 0644,
+	       rnbd_srv_dev_session_force_close_show,
+	       rnbd_srv_dev_session_force_close_store);
+
 static struct attribute *rnbd_srv_default_dev_sessions_attrs[] = {
 	&rnbd_srv_dev_session_access_mode_attr.attr,
 	&rnbd_srv_dev_session_ro_attr.attr,
 	&rnbd_srv_dev_session_mapping_path_attr.attr,
+	&rnbd_srv_dev_session_force_close_attr.attr,
 	NULL,
 };
 
@@ -145,7 +186,7 @@ static void rnbd_srv_sess_dev_release(struct kobject *kobj)
 	struct rnbd_srv_sess_dev *sess_dev;
 
 	sess_dev = container_of(kobj, struct rnbd_srv_sess_dev, kobj);
-	rnbd_destroy_sess_dev(sess_dev);
+	rnbd_destroy_sess_dev(sess_dev, sess_dev->keep_id);
 }
 
 static struct kobj_type rnbd_srv_sess_dev_ktype = {
@@ -160,18 +201,17 @@ int rnbd_srv_create_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev)
 	ret = kobject_init_and_add(&sess_dev->kobj, &rnbd_srv_sess_dev_ktype,
 				   sess_dev->dev->dev_sessions_kobj, "%s",
 				   sess_dev->sess->sessname);
-	if (ret)
+	if (ret) {
+		kobject_put(&sess_dev->kobj);
 		return ret;
+	}
 
 	ret = sysfs_create_group(&sess_dev->kobj,
 				 &rnbd_srv_default_dev_session_attr_group);
-	if (ret)
-		goto err;
-
-	return 0;
-
-err:
-	kobject_put(&sess_dev->kobj);
+	if (ret) {
+		kobject_del(&sess_dev->kobj);
+		kobject_put(&sess_dev->kobj);
+	}
 
 	return ret;
 }
diff --git a/drivers/block/rnbd/rnbd-srv.c b/drivers/block/rnbd/rnbd-srv.c
index e1bc8b4cd592..d1ee72ed8384 100644
--- a/drivers/block/rnbd/rnbd-srv.c
+++ b/drivers/block/rnbd/rnbd-srv.c
@@ -212,12 +212,20 @@ static void rnbd_put_srv_dev(struct rnbd_srv_dev *dev)
 	kref_put(&dev->kref, destroy_device_cb);
 }
 
-void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev)
+void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id)
 {
 	DECLARE_COMPLETION_ONSTACK(dc);
 
-	xa_erase(&sess_dev->sess->index_idr, sess_dev->device_id);
+	if (keep_id)
+		/* free the resources for the id but don't  */
+		/* allow to re-use the id itself because it */
+		/* is still used by the client              */
+		xa_cmpxchg(&sess_dev->sess->index_idr, sess_dev->device_id,
+			   sess_dev, NULL, 0);
+	else
+		xa_erase(&sess_dev->sess->index_idr, sess_dev->device_id);
 	synchronize_rcu();
+
 	sess_dev->destroy_comp = &dc;
 	rnbd_put_sess_dev(sess_dev);
 	wait_for_completion(&dc); /* wait for inflights to drop to zero */
@@ -328,6 +336,13 @@ static int rnbd_srv_link_ev(struct rtrs_srv *rtrs,
 	}
 }
 
+void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev)
+{
+	rnbd_srv_destroy_dev_session_sysfs(sess_dev);
+	sess_dev->keep_id = true;
+
+}
+
 static int process_msg_close(struct rtrs_srv *rtrs,
 			     struct rnbd_srv_session *srv_sess,
 			     void *data, size_t datalen, const void *usr,
diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h
index 5a8544b5e74f..b157371c25ed 100644
--- a/drivers/block/rnbd/rnbd-srv.h
+++ b/drivers/block/rnbd/rnbd-srv.h
@@ -56,6 +56,7 @@ struct rnbd_srv_sess_dev {
 	struct rnbd_srv_dev		*dev;
 	struct kobject                  kobj;
 	u32                             device_id;
+	bool				keep_id;
 	fmode_t                         open_flags;
 	struct kref			kref;
 	struct completion               *destroy_comp;
@@ -63,6 +64,7 @@ struct rnbd_srv_sess_dev {
 	enum rnbd_access_mode		access_mode;
 };
 
+void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev);
 /* rnbd-srv-sysfs.c */
 
 int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev,
@@ -73,6 +75,6 @@ int rnbd_srv_create_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev);
 void rnbd_srv_destroy_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev);
 int rnbd_srv_create_sysfs_files(void);
 void rnbd_srv_destroy_sysfs_files(void);
-void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev);
+void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id);
 
 #endif /* RNBD_SRV_H */