Merge tag 'for-4.19/block-20180812' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "First pull request for this merge window, there will also be a
  followup request with some stragglers.

  This pull request contains:

   - Fix for a thundering heard issue in the wbt block code (Anchal
     Agarwal)

   - A few NVMe pull requests:
      * Improved tracepoints (Keith)
      * Larger inline data support for RDMA (Steve Wise)
      * RDMA setup/teardown fixes (Sagi)
      * Effects log suppor for NVMe target (Chaitanya Kulkarni)
      * Buffered IO suppor for NVMe target (Chaitanya Kulkarni)
      * TP4004 (ANA) support (Christoph)
      * Various NVMe fixes

   - Block io-latency controller support. Much needed support for
     properly containing block devices. (Josef)

   - Series improving how we handle sense information on the stack
     (Kees)

   - Lightnvm fixes and updates/improvements (Mathias/Javier et al)

   - Zoned device support for null_blk (Matias)

   - AIX partition fixes (Mauricio Faria de Oliveira)

   - DIF checksum code made generic (Max Gurtovoy)

   - Add support for discard in iostats (Michael Callahan / Tejun)

   - Set of updates for BFQ (Paolo)

   - Removal of async write support for bsg (Christoph)

   - Bio page dirtying and clone fixups (Christoph)

   - Set of bcache fix/changes (via Coly)

   - Series improving blk-mq queue setup/teardown speed (Ming)

   - Series improving merging performance on blk-mq (Ming)

   - Lots of other fixes and cleanups from a slew of folks"

* tag 'for-4.19/block-20180812' of git://git.kernel.dk/linux-block: (190 commits)
  blkcg: Make blkg_root_lookup() work for queues in bypass mode
  bcache: fix error setting writeback_rate through sysfs interface
  null_blk: add lock drop/acquire annotation
  Blk-throttle: reduce tail io latency when iops limit is enforced
  block: paride: pd: mark expected switch fall-throughs
  block: Ensure that a request queue is dissociated from the cgroup controller
  block: Introduce blk_exit_queue()
  blkcg: Introduce blkg_root_lookup()
  block: Remove two superfluous #include directives
  blk-mq: count the hctx as active before allocating tag
  block: bvec_nr_vecs() returns value for wrong slab
  bcache: trivial - remove tailing backslash in macro BTREE_FLAG
  bcache: make the pr_err statement used for ENOENT only in sysfs_attatch section
  bcache: set max writeback rate when I/O request is idle
  bcache: add code comments for bset.c
  bcache: fix mistaken comments in request.c
  bcache: fix mistaken code comments in bcache.h
  bcache: add a comment in super.c
  bcache: avoid unncessary cache prefetch bch_btree_node_get()
  bcache: display rate debug parameters to 0 when writeback is not running
  ...

24 files changed, 434 insertions, 188 deletions

diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index f6518067aa7d..f99e5c883368 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -21,6 +21,7 @@
 #define DAC960_DriverDate			"21 Aug 2007"
 
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
@@ -6426,7 +6427,7 @@ static bool DAC960_V2_ExecuteUserCommand(DAC960_Controller_T *Controller,
   return true;
 }
 
-static int dac960_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_proc_show(struct seq_file *m, void *v)
 {
   unsigned char *StatusMessage = "OK\n";
   int ControllerNumber;
@@ -6446,14 +6447,16 @@ static int dac960_proc_show(struct seq_file *m, void *v)
   return 0;
 }
 
-static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_initial_status_proc_show(struct seq_file *m,
+							  void *v)
 {
 	DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
 	seq_printf(m, "%.*s", Controller->InitialStatusLength, Controller->CombinedStatusBuffer);
 	return 0;
 }
 
-static int dac960_current_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_current_status_proc_show(struct seq_file *m,
+							  void *v)
 {
   DAC960_Controller_T *Controller = (DAC960_Controller_T *) m->private;
   unsigned char *StatusMessage =
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ad9b687a236a..d4913516823f 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -74,12 +74,12 @@ config AMIGA_Z2RAM
 
 config CDROM
 	tristate
+	select BLK_SCSI_REQUEST
 
 config GDROM
 	tristate "SEGA Dreamcast GD-ROM drive"
 	depends on SH_DREAMCAST
 	select CDROM
-	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	help
 	  A standard SEGA Dreamcast comes with a modified CD ROM drive called a
 	  "GD-ROM" by SEGA to signify it is capable of reading special disks
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index dc061158b403..8566b188368b 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -36,8 +36,11 @@ obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX)	+= mtip32xx/
 
 obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
-obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
 obj-$(CONFIG_ZRAM) += zram/
 
+obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
+null_blk-objs	:= null_blk_main.o
+null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
+
 skd-y		:= skd_main.o
 swim_mod-y	:= swim.o swim_asm.o
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 096882e54095..136dc507d020 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1137,6 +1137,7 @@ noskb:		if (buf)
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
+		/* fall through */
 	case ATA_CMD_PIO_WRITE:
 	case ATA_CMD_PIO_WRITE_EXT:
 		spin_lock_irq(&d->lock);
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 697f735b07a4..41060e9cedf2 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -284,8 +284,8 @@ freedev(struct aoedev *d)
 	e = t + d->ntargets;
 	for (; t < e && *t; t++)
 		freetgt(d, *t);
-	if (d->bufpool)
-		mempool_destroy(d->bufpool);
+
+	mempool_destroy(d->bufpool);
 	skbpoolfree(d);
 	minor_free(d->sysminor);
 
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bb976598ee43..df8103dd40ac 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -254,20 +254,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	void *mem;
 	int err = 0;
 
-	if (is_write) {
+	if (op_is_write(op)) {
 		err = copy_to_brd_setup(brd, sector, len);
 		if (err)
 			goto out;
 	}
 
 	mem = kmap_atomic(page);
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -296,7 +296,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		int err;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
-					op_is_write(bio_op(bio)), sector);
+				  bio_op(bio), sector);
 		if (err)
 			goto io_error;
 		sector += len >> SECTOR_SHIFT;
@@ -310,15 +310,15 @@ io_error:
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	int err;
 
 	if (PageTransHuge(page))
 		return -ENOTSUPP;
-	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
-	page_endio(page, is_write, err);
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	page_endio(page, op_is_write(op), err);
 	return err;
 }
 
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index bc4ed2ed40a2..e35a234b0a8f 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -55,12 +55,10 @@
 # define __protected_by(x)       __attribute__((require_context(x,1,999,"rdwr")))
 # define __protected_read_by(x)  __attribute__((require_context(x,1,999,"read")))
 # define __protected_write_by(x) __attribute__((require_context(x,1,999,"write")))
-# define __must_hold(x)       __attribute__((context(x,1,1), require_context(x,1,999,"call")))
 #else
 # define __protected_by(x)
 # define __protected_read_by(x)
 # define __protected_write_by(x)
-# define __must_hold(x)
 #endif
 
 /* shared module parameters, defined in drbd_main.c */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a80809bd3057..ef8212a4b73e 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2103,14 +2103,10 @@ static void drbd_destroy_mempools(void)
 	mempool_exit(&drbd_md_io_page_pool);
 	mempool_exit(&drbd_ee_mempool);
 	mempool_exit(&drbd_request_mempool);
-	if (drbd_ee_cache)
-		kmem_cache_destroy(drbd_ee_cache);
-	if (drbd_request_cache)
-		kmem_cache_destroy(drbd_request_cache);
-	if (drbd_bm_ext_cache)
-		kmem_cache_destroy(drbd_bm_ext_cache);
-	if (drbd_al_ext_cache)
-		kmem_cache_destroy(drbd_al_ext_cache);
+	kmem_cache_destroy(drbd_ee_cache);
+	kmem_cache_destroy(drbd_request_cache);
+	kmem_cache_destroy(drbd_bm_ext_cache);
+	kmem_cache_destroy(drbd_al_ext_cache);
 
 	drbd_ee_cache        = NULL;
 	drbd_request_cache   = NULL;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index be9450f5ad1c..75f6b47169e6 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2674,8 +2674,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 	if (c_min_rate == 0)
 		return false;
 
-	curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-		      (int)part_stat_read(&disk->part0, sectors[1]) -
+	curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
@@ -2790,6 +2789,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 		   then we would do something smarter here than reading
 		   the block... */
 		peer_req->flags |= EE_RS_THIN_REQ;
+		/* fall through */
 	case P_RS_DATA_REQUEST:
 		peer_req->w.cb = w_e_end_rsdata_req;
 		fault_type = DRBD_FAULT_RS_RD;
@@ -2968,6 +2968,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		/* Else fall through to one of the other strategies... */
 		drbd_warn(device, "Discard younger/older primary did not find a decision\n"
 		     "Using discard-least-changes instead\n");
+		/* fall through */
 	case ASB_DISCARD_ZERO_CHG:
 		if (ch_peer == 0 && ch_self == 0) {
 			rv = test_bit(RESOLVE_CONFLICTS, &peer_device->connection->flags)
@@ -2979,6 +2980,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		}
 		if (after_sb_0p == ASB_DISCARD_ZERO_CHG)
 			break;
+		/* else: fall through */
 	case ASB_DISCARD_LEAST_CHG:
 		if	(ch_self < ch_peer)
 			rv = -1;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index d146fedc38bb..19cac36e9737 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -38,7 +38,7 @@ static void _drbd_start_io_acct(struct drbd_device *device, struct drbd_request
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_start_io_acct(q, bio_data_dir(req->master_bio),
+	generic_start_io_acct(q, bio_op(req->master_bio),
 				req->i.size >> 9, &device->vdisk->part0);
 }
 
@@ -47,7 +47,7 @@ static void _drbd_end_io_acct(struct drbd_device *device, struct drbd_request *r
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_end_io_acct(q, bio_data_dir(req->master_bio),
+	generic_end_io_acct(q, bio_op(req->master_bio),
 			    &device->vdisk->part0, req->start_jif);
 }
 
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 5e793dd7adfb..b8f77e83d456 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1690,9 +1690,7 @@ void drbd_rs_controller_reset(struct drbd_device *device)
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
-	device->rs_last_events =
-		(int)part_stat_read(&disk->part0, sectors[0]) +
-		(int)part_stat_read(&disk->part0, sectors[1]);
+	device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 8871b5044d9e..48f622728ce6 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -1461,7 +1461,6 @@ static void setup_rw_floppy(void)
 	int i;
 	int r;
 	int flags;
-	int dflags;
 	unsigned long ready_date;
 	void (*function)(void);
 
@@ -1485,8 +1484,6 @@ static void setup_rw_floppy(void)
 		if (fd_wait_for_completion(ready_date, function))
 			return;
 	}
-	dflags = DRS->flags;
-
 	if ((flags & FD_RAW_READ) || (flags & FD_RAW_WRITE))
 		setup_DMA();
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 4cb1d1be3cfb..ea9debf59b22 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -690,7 +690,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			  unsigned int arg)
 {
 	struct file	*file, *old_file;
-	struct inode	*inode;
 	int		error;
 
 	error = -ENXIO;
@@ -711,7 +710,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (error)
 		goto out_putf;
 
-	inode = file->f_mapping->host;
 	old_file = lo->lo_backing_file;
 
 	error = -EINVAL;
@@ -1611,6 +1609,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_GET_STATUS64:
 	case LOOP_SET_STATUS64:
 		arg = (unsigned long) compat_ptr(arg);
+		/* fall through */
 	case LOOP_SET_FD:
 	case LOOP_CHANGE_FD:
 	case LOOP_SET_BLOCK_SIZE:
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index c73626decb46..db253cd5b32a 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2575,8 +2575,7 @@ static int mtip_hw_debugfs_init(struct driver_data *dd)
 
 static void mtip_hw_debugfs_exit(struct driver_data *dd)
 {
-	if (dd->dfs_node)
-		debugfs_remove_recursive(dd->dfs_node);
+	debugfs_remove_recursive(dd->dfs_node);
 }
 
 /*
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
new file mode 100644
index 000000000000..d81781f22dba
--- /dev/null
+++ b/drivers/block/null_blk.h
@@ -0,0 +1,108 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BLK_NULL_BLK_H
+#define __BLK_NULL_BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/blk-mq.h>
+#include <linux/hrtimer.h>
+#include <linux/configfs.h>
+#include <linux/badblocks.h>
+#include <linux/fault-inject.h>
+
+struct nullb_cmd {
+	struct list_head list;
+	struct llist_node ll_list;
+	struct __call_single_data csd;
+	struct request *rq;
+	struct bio *bio;
+	unsigned int tag;
+	blk_status_t error;
+	struct nullb_queue *nq;
+	struct hrtimer timer;
+};
+
+struct nullb_queue {
+	unsigned long *tag_map;
+	wait_queue_head_t wait;
+	unsigned int queue_depth;
+	struct nullb_device *dev;
+	unsigned int requeue_selection;
+
+	struct nullb_cmd *cmds;
+};
+
+struct nullb_device {
+	struct nullb *nullb;
+	struct config_item item;
+	struct radix_tree_root data; /* data stored in the disk */
+	struct radix_tree_root cache; /* disk cache data */
+	unsigned long flags; /* device flags */
+	unsigned int curr_cache;
+	struct badblocks badblocks;
+
+	unsigned int nr_zones;
+	struct blk_zone *zones;
+	sector_t zone_size_sects;
+
+	unsigned long size; /* device size in MB */
+	unsigned long completion_nsec; /* time in ns to complete a request */
+	unsigned long cache_size; /* disk cache size in MB */
+	unsigned long zone_size; /* zone size in MB if device is zoned */
+	unsigned int submit_queues; /* number of submission queues */
+	unsigned int home_node; /* home node for the device */
+	unsigned int queue_mode; /* block interface */
+	unsigned int blocksize; /* block size */
+	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 */
+	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
+	bool blocking; /* blocking blk-mq device */
+	bool use_per_node_hctx; /* use per-node allocation for hardware context */
+	bool power; /* power on/off the device */
+	bool memory_backed; /* if data is stored in memory */
+	bool discard; /* if support discard */
+	bool zoned; /* if device is zoned */
+};
+
+struct nullb {
+	struct nullb_device *dev;
+	struct list_head list;
+	unsigned int index;
+	struct request_queue *q;
+	struct gendisk *disk;
+	struct blk_mq_tag_set *tag_set;
+	struct blk_mq_tag_set __tag_set;
+	unsigned int queue_depth;
+	atomic_long_t cur_bytes;
+	struct hrtimer bw_timer;
+	unsigned long cache_flush_pos;
+	spinlock_t lock;
+
+	struct nullb_queue *queues;
+	unsigned int nr_queues;
+	char disk_name[DISK_NAME_LEN];
+};
+
+#ifdef CONFIG_BLK_DEV_ZONED
+int null_zone_init(struct nullb_device *dev);
+void null_zone_exit(struct nullb_device *dev);
+blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd);
+void null_zone_write(struct nullb_cmd *cmd);
+void null_zone_reset(struct nullb_cmd *cmd);
+#else
+static inline int null_zone_init(struct nullb_device *dev)
+{
+	return -EINVAL;
+}
+static inline void null_zone_exit(struct nullb_device *dev) {}
+static inline blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd)
+{
+	return BLK_STS_NOTSUPP;
+}
+static inline void null_zone_write(struct nullb_cmd *cmd) {}
+static inline void null_zone_reset(struct nullb_cmd *cmd) {}
+#endif /* CONFIG_BLK_DEV_ZONED */
+#endif /* __NULL_BLK_H */
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk_main.c
index 042c778e5a4e..6127e3ff7b4b 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk_main.c
@@ -7,14 +7,8 @@
 #include <linux/moduleparam.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
-#include <linux/blkdev.h>
 #include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/blk-mq.h>
-#include <linux/hrtimer.h>
-#include <linux/configfs.h>
-#include <linux/badblocks.h>
-#include <linux/fault-inject.h>
+#include "null_blk.h"
 
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
@@ -35,28 +29,6 @@ static inline u64 mb_per_tick(int mbps)
 	return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
 }
 
-struct nullb_cmd {
-	struct list_head list;
-	struct llist_node ll_list;
-	struct __call_single_data csd;
-	struct request *rq;
-	struct bio *bio;
-	unsigned int tag;
-	blk_status_t error;
-	struct nullb_queue *nq;
-	struct hrtimer timer;
-};
-
-struct nullb_queue {
-	unsigned long *tag_map;
-	wait_queue_head_t wait;
-	unsigned int queue_depth;
-	struct nullb_device *dev;
-	unsigned int requeue_selection;
-
-	struct nullb_cmd *cmds;
-};
-
 /*
  * Status flags for nullb_device.
  *
@@ -92,52 +64,6 @@ struct nullb_page {
 #define NULLB_PAGE_LOCK (MAP_SZ - 1)
 #define NULLB_PAGE_FREE (MAP_SZ - 2)
 
-struct nullb_device {
-	struct nullb *nullb;
-	struct config_item item;
-	struct radix_tree_root data; /* data stored in the disk */
-	struct radix_tree_root cache; /* disk cache data */
-	unsigned long flags; /* device flags */
-	unsigned int curr_cache;
-	struct badblocks badblocks;
-
-	unsigned long size; /* device size in MB */
-	unsigned long completion_nsec; /* time in ns to complete a request */
-	unsigned long cache_size; /* disk cache size in MB */
-	unsigned int submit_queues; /* number of submission queues */
-	unsigned int home_node; /* home node for the device */
-	unsigned int queue_mode; /* block interface */
-	unsigned int blocksize; /* block size */
-	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 */
-	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
-	bool blocking; /* blocking blk-mq device */
-	bool use_per_node_hctx; /* use per-node allocation for hardware context */
-	bool power; /* power on/off the device */
-	bool memory_backed; /* if data is stored in memory */
-	bool discard; /* if support discard */
-};
-
-struct nullb {
-	struct nullb_device *dev;
-	struct list_head list;
-	unsigned int index;
-	struct request_queue *q;
-	struct gendisk *disk;
-	struct blk_mq_tag_set *tag_set;
-	struct blk_mq_tag_set __tag_set;
-	unsigned int queue_depth;
-	atomic_long_t cur_bytes;
-	struct hrtimer bw_timer;
-	unsigned long cache_flush_pos;
-	spinlock_t lock;
-
-	struct nullb_queue *queues;
-	unsigned int nr_queues;
-	char disk_name[DISK_NAME_LEN];
-};
-
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
@@ -254,6 +180,14 @@ static bool g_use_per_node_hctx;
 module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
 MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
 
+static bool g_zoned;
+module_param_named(zoned, g_zoned, bool, S_IRUGO);
+MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false");
+
+static unsigned long g_zone_size = 256;
+module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
+MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -357,6 +291,8 @@ NULLB_DEVICE_ATTR(memory_backed, bool);
 NULLB_DEVICE_ATTR(discard, bool);
 NULLB_DEVICE_ATTR(mbps, uint);
 NULLB_DEVICE_ATTR(cache_size, ulong);
+NULLB_DEVICE_ATTR(zoned, bool);
+NULLB_DEVICE_ATTR(zone_size, ulong);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -390,6 +326,7 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 		null_del_dev(dev->nullb);
 		mutex_unlock(&lock);
 		clear_bit(NULLB_DEV_FL_UP, &dev->flags);
+		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 	}
 
 	return count;
@@ -468,6 +405,8 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_mbps,
 	&nullb_device_attr_cache_size,
 	&nullb_device_attr_badblocks,
+	&nullb_device_attr_zoned,
+	&nullb_device_attr_zone_size,
 	NULL,
 };
 
@@ -520,7 +459,7 @@ 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\n");
+	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -579,6 +518,8 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->hw_queue_depth = g_hw_queue_depth;
 	dev->blocking = g_blocking;
 	dev->use_per_node_hctx = g_use_per_node_hctx;
+	dev->zoned = g_zoned;
+	dev->zone_size = g_zone_size;
 	return dev;
 }
 
@@ -587,6 +528,7 @@ static void null_free_dev(struct nullb_device *dev)
 	if (!dev)
 		return;
 
+	null_zone_exit(dev);
 	badblocks_exit(&dev->badblocks);
 	kfree(dev);
 }
@@ -862,7 +804,9 @@ static struct nullb_page *null_lookup_page(struct nullb *nullb,
 }
 
 static struct nullb_page *null_insert_page(struct nullb *nullb,
-	sector_t sector, bool ignore_cache)
+					   sector_t sector, bool ignore_cache)
+	__releases(&nullb->lock)
+	__acquires(&nullb->lock)
 {
 	u64 idx;
 	struct nullb_page *t_page;
@@ -1219,6 +1163,11 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 	struct nullb *nullb = dev->nullb;
 	int err = 0;
 
+	if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) {
+		cmd->error = null_zone_report(nullb, cmd);
+		goto out;
+	}
+
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
 		struct request *rq = cmd->rq;
 
@@ -1283,6 +1232,13 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 		}
 	}
 	cmd->error = errno_to_blk_status(err);
+
+	if (!cmd->error && dev->zoned) {
+		if (req_op(cmd->rq) == REQ_OP_WRITE)
+			null_zone_write(cmd);
+		else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET)
+			null_zone_reset(cmd);
+	}
 out:
 	/* Complete IO by inline, softirq or timer */
 	switch (dev->irqmode) {
@@ -1810,6 +1766,15 @@ static int null_add_dev(struct nullb_device *dev)
 		blk_queue_flush_queueable(nullb->q, true);
 	}
 
+	if (dev->zoned) {
+		rv = null_zone_init(dev);
+		if (rv)
+			goto out_cleanup_blk_queue;
+
+		blk_queue_chunk_sectors(nullb->q, dev->zone_size_sects);
+		nullb->q->limits.zoned = BLK_ZONED_HM;
+	}
+
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
@@ -1828,13 +1793,16 @@ static int null_add_dev(struct nullb_device *dev)
 
 	rv = null_gendisk_register(nullb);
 	if (rv)
-		goto out_cleanup_blk_queue;
+		goto out_cleanup_zone;
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
 	mutex_unlock(&lock);
 
 	return 0;
+out_cleanup_zone:
+	if (dev->zoned)
+		null_zone_exit(dev);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -1861,6 +1829,11 @@ static int __init null_init(void)
 		g_bs = PAGE_SIZE;
 	}
 
+	if (!is_power_of_2(g_zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
 	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.\n",
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
new file mode 100644
index 000000000000..a979ca00d7be
--- /dev/null
+++ b/drivers/block/null_blk_zoned.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/vmalloc.h>
+#include "null_blk.h"
+
+/* zone_size in MBs to sectors. */
+#define ZONE_SIZE_SHIFT		11
+
+static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
+{
+	return sect >> ilog2(dev->zone_size_sects);
+}
+
+int null_zone_init(struct nullb_device *dev)
+{
+	sector_t dev_size = (sector_t)dev->size * 1024 * 1024;
+	sector_t sector = 0;
+	unsigned int i;
+
+	if (!is_power_of_2(dev->zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		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);
+	if (!dev->zones)
+		return -ENOMEM;
+
+	for (i = 0; i < dev->nr_zones; i++) {
+		struct blk_zone *zone = &dev->zones[i];
+
+		zone->start = zone->wp = sector;
+		zone->len = dev->zone_size_sects;
+		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
+		zone->cond = BLK_ZONE_COND_EMPTY;
+
+		sector += dev->zone_size_sects;
+	}
+
+	return 0;
+}
+
+void null_zone_exit(struct nullb_device *dev)
+{
+	kvfree(dev->zones);
+}
+
+static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq,
+			      unsigned int zno, unsigned int nr_zones)
+{
+	struct blk_zone_report_hdr *hdr = NULL;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	void *addr;
+	unsigned int zones_to_cpy;
+
+	bio_for_each_segment(bvec, rq->bio, iter) {
+		addr = kmap_atomic(bvec.bv_page);
+
+		zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone);
+
+		if (!hdr) {
+			hdr = (struct blk_zone_report_hdr *)addr;
+			hdr->nr_zones = nr_zones;
+			zones_to_cpy--;
+			addr += sizeof(struct blk_zone_report_hdr);
+		}
+
+		zones_to_cpy = min_t(unsigned int, zones_to_cpy, nr_zones);
+
+		memcpy(addr, &dev->zones[zno],
+				zones_to_cpy * sizeof(struct blk_zone));
+
+		kunmap_atomic(addr);
+
+		nr_zones -= zones_to_cpy;
+		zno += zones_to_cpy;
+
+		if (!nr_zones)
+			break;
+	}
+}
+
+blk_status_t null_zone_report(struct nullb *nullb,
+				     struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = nullb->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	unsigned int nr_zones = dev->nr_zones - zno;
+	unsigned int max_zones = (blk_rq_bytes(rq) /
+					sizeof(struct blk_zone)) - 1;
+
+	nr_zones = min_t(unsigned int, nr_zones, max_zones);
+
+	null_zone_fill_rq(nullb->dev, rq, zno, nr_zones);
+
+	return BLK_STS_OK;
+}
+
+void null_zone_write(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct r