[PATCH V4 00/16] scsi-mq support for ZBC disks

@@ -28,32 +28,8 @@
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
-#include <scsi/scsi_dbg.h>
-#include <scsi/scsi_device.h>
-#include <scsi/scsi_driver.h>
-#include <scsi/scsi_host.h>
-#include <scsi/scsi_eh.h>
 
 #include "sd.h"
-#include "scsi_priv.h"
-
-enum zbc_zone_type {
-	ZBC_ZONE_TYPE_CONV = 0x1,
-	ZBC_ZONE_TYPE_SEQWRITE_REQ,
-	ZBC_ZONE_TYPE_SEQWRITE_PREF,
-	ZBC_ZONE_TYPE_RESERVED,
-};
-
-enum zbc_zone_cond {
-	ZBC_ZONE_COND_NO_WP,
-	ZBC_ZONE_COND_EMPTY,
-	ZBC_ZONE_COND_IMP_OPEN,
-	ZBC_ZONE_COND_EXP_OPEN,
-	ZBC_ZONE_COND_CLOSED,
-	ZBC_ZONE_COND_READONLY = 0xd,
-	ZBC_ZONE_COND_FULL,
-	ZBC_ZONE_COND_OFFLINE,
-};
 
 /**
  * Convert a zone descriptor to a zone struct.

@@ -301,19 +301,42 @@ struct scsi_lun {
 
 /* Reporting options for REPORT ZONES */
 enum zbc_zone_reporting_options {
-	ZBC_ZONE_REPORTING_OPTION_ALL = 0,
-	ZBC_ZONE_REPORTING_OPTION_EMPTY,
-	ZBC_ZONE_REPORTING_OPTION_IMPLICIT_OPEN,
-	ZBC_ZONE_REPORTING_OPTION_EXPLICIT_OPEN,
-	ZBC_ZONE_REPORTING_OPTION_CLOSED,
-	ZBC_ZONE_REPORTING_OPTION_FULL,
-	ZBC_ZONE_REPORTING_OPTION_READONLY,
-	ZBC_ZONE_REPORTING_OPTION_OFFLINE,
-	ZBC_ZONE_REPORTING_OPTION_NEED_RESET_WP = 0x10,
-	ZBC_ZONE_REPORTING_OPTION_NON_SEQWRITE,
-	ZBC_ZONE_REPORTING_OPTION_NON_WP = 0x3f,
+	ZBC_ZONE_REPORTING_OPTION_ALL		= 0x00,
+	ZBC_ZONE_REPORTING_OPTION_EMPTY		= 0x01,
+	ZBC_ZONE_REPORTING_OPTION_IMPLICIT_OPEN	= 0x02,
+	ZBC_ZONE_REPORTING_OPTION_EXPLICIT_OPEN	= 0x03,
+	ZBC_ZONE_REPORTING_OPTION_CLOSED	= 0x04,
+	ZBC_ZONE_REPORTING_OPTION_FULL		= 0x05,
+	ZBC_ZONE_REPORTING_OPTION_READONLY	= 0x06,
+	ZBC_ZONE_REPORTING_OPTION_OFFLINE	= 0x07,
+	/* 0x08 to 0x0f are reserved */
+	ZBC_ZONE_REPORTING_OPTION_NEED_RESET_WP	= 0x10,
+	ZBC_ZONE_REPORTING_OPTION_NON_SEQWRITE	= 0x11,
+	/* 0x12 to 0x3e are reserved */
+	ZBC_ZONE_REPORTING_OPTION_NON_WP	= 0x3f,
 };
 
 #define ZBC_REPORT_ZONE_PARTIAL 0x80
 
+/* Zone types of REPORT ZONES zone descriptors */
+enum zbc_zone_type {
+	ZBC_ZONE_TYPE_CONV		= 0x1,
+	ZBC_ZONE_TYPE_SEQWRITE_REQ	= 0x2,
+	ZBC_ZONE_TYPE_SEQWRITE_PREF	= 0x3,
+	/* 0x4 to 0xf are reserved */
+};
+
+/* Zone conditions of REPORT ZONES zone descriptors */
+enum zbc_zone_cond {
+	ZBC_ZONE_COND_NO_WP		= 0x0,
+	ZBC_ZONE_COND_EMPTY		= 0x1,
+	ZBC_ZONE_COND_IMP_OPEN		= 0x2,
+	ZBC_ZONE_COND_EXP_OPEN		= 0x3,
+	ZBC_ZONE_COND_CLOSED		= 0x4,
+	/* 0x5 to 0xc are reserved */
+	ZBC_ZONE_COND_READONLY		= 0xd,
+	ZBC_ZONE_COND_FULL		= 0xe,
+	ZBC_ZONE_COND_OFFLINE		= 0xf,
+};
+
 #endif /* _SCSI_PROTO_H_ */

@@ -1752,7 +1752,10 @@ static void scsi_done(struct scsi_cmnd *cmd)
  *
  * Returns:     Nothing
  *
- * Lock status: IO request lock assumed to be held when called.
+ * Lock status: request queue lock assumed to be held when called.
+ *
+ * Note: See sd_zbc.c sd_zbc_write_lock_zone() for write order
+ * protection for ZBC disks.
  */
 static void scsi_request_fn(struct request_queue *q)
 	__releases(q->queue_lock)

@@ -32,10 +32,14 @@
 #include "sd.h"
 
 /**
- * Convert a zone descriptor to a zone struct.
+ * sd_zbc_parse_report - Convert a zone descriptor to a struct blk_zone,
+ * @sdkp: The disk the report originated from
+ * @buf: Address of the report zone descriptor
+ * @zone: the destination zone structure
+ *
+ * All LBA sized values are converted to 512B sectors unit.
  */
-static void sd_zbc_parse_report(struct scsi_disk *sdkp,
-				u8 *buf,
+static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
 				struct blk_zone *zone)
 {
 	struct scsi_device *sdp = sdkp->device;

@@ -58,7 +62,13 @@ static void sd_zbc_parse_report(struct scsi_disk *sdkp,
 }
 
 /**
- * Issue a REPORT ZONES scsi command.
+ * sd_zbc_report_zones - Issue a REPORT ZONES scsi command.
+ * @sdkp: The target disk
+ * @buf: Buffer to use for the reply
+ * @buflen: the buffer size
+ * @lba: Start LBA of the report
+ *
+ * For internal use during device validation.
  */
 static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 			       unsigned int buflen, sector_t lba)

@@ -99,6 +109,12 @@ static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 	return 0;
 }
 
+/**
+ * sd_zbc_setup_report_cmnd - Prepare a REPORT ZONES scsi command
+ * @cmd: The command to setup
+ *
+ * Call in sd_init_command() for a REQ_OP_ZONE_REPORT request.
+ */
 int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
 {
 	struct request *rq = cmd->request;

@@ -141,6 +157,14 @@ int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
 	return BLKPREP_OK;
 }
 
+/**
+ * sd_zbc_report_zones_complete - Process a REPORT ZONES scsi command reply.
+ * @scmd: The completed report zones command
+ * @good_bytes: reply size in bytes
+ *
+ * Convert all reported zone descriptors to struct blk_zone. The conversion
+ * is done in-place, directly in the request specified sg buffer.
+ */
 static void sd_zbc_report_zones_complete(struct scsi_cmnd *scmd,
 					 unsigned int good_bytes)
 {

@@ -196,17 +220,32 @@ static void sd_zbc_report_zones_complete(struct scsi_cmnd *scmd,
 	local_irq_restore(flags);
 }
 
+/**
+ * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors.
+ * @sdkp: The target disk
+ */
 static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
 {
 	return logical_to_sectors(sdkp->device, sdkp->zone_blocks);
 }
 
+/**
+ * sd_zbc_zone_no - Get the number of the zone conataining a sector.
+ * @sdkp: The target disk
+ * @sector: 512B sector address contained in the zone
+ */
 static inline unsigned int sd_zbc_zone_no(struct scsi_disk *sdkp,
 					  sector_t sector)
 {
 	return sectors_to_logical(sdkp->device, sector) >> sdkp->zone_shift;
 }
 
+/**
+ * sd_zbc_setup_reset_cmnd - Prepare a RESET WRITE POINTER scsi command.
+ * @cmd: the command to setup
+ *
+ * Called from sd_init_command() for a REQ_OP_ZONE_RESET request.
+ */
 int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
 {
 	struct request *rq = cmd->request;

@@ -239,6 +278,23 @@ int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
 	return BLKPREP_OK;
 }
 
+/**
+ * sd_zbc_write_lock_zone - Write lock a sequential zone.
+ * @cmd: write command
+ *
+ * Called from sd_init_cmd() for write requests (standard write, write same or
+ * write zeroes operations). If the request target zone is not already locked,
+ * the zone is locked and BLKPREP_OK returned, allowing the request to proceed
+ * through dispatch in scsi_request_fn(). Otherwise, BLKPREP_DEFER is returned,
+ * forcing the request to wait for the zone to be unlocked, that is, for the
+ * previously issued write request targeting the same zone to complete.
+ *
+ * This is called from blk_peek_request() context with the queue lock held and
+ * before the request is removed from the scheduler. As a result, multiple
+ * contexts executing concurrently scsi_request_fn() cannot result in write
+ * sequence reordering as only a single write request per zone is allowed to
+ * proceed.
+ */
 int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd)
 {
 	struct request *rq = cmd->request;

@@ -261,10 +317,7 @@ int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd)
 	 * Do not issue more than one write at a time per
 	 * zone. This solves write ordering problems due to
 	 * the unlocking of the request queue in the dispatch
-	 * path in the non scsi-mq case. For scsi-mq, this
-	 * also avoids potential write reordering when multiple
-	 * threads running on different CPUs write to the same
-	 * zone (with a synchronized sequential pattern).
+	 * path in the non scsi-mq case.
 	 */
 	if (sdkp->zones_wlock &&
 	    test_and_set_bit(zno, sdkp->zones_wlock))

@@ -276,6 +329,13 @@ int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd)
 	return BLKPREP_OK;
 }
 
+/**
+ * sd_zbc_write_unlock_zone - Write unlock a sequential zone.
+ * @cmd: write command
+ *
+ * Called from sd_uninit_cmd(). Unlocking the request target zone will allow
+ * dispatching the next write request for the zone.
+ */
 void sd_zbc_write_unlock_zone(struct scsi_cmnd *cmd)
 {
 	struct request *rq = cmd->request;

@@ -290,8 +350,16 @@ void sd_zbc_write_unlock_zone(struct scsi_cmnd *cmd)
 	}
 }
 
-void sd_zbc_complete(struct scsi_cmnd *cmd,
-		     unsigned int good_bytes,
+/**
+ * sd_zbc_complete - ZBC command post processing.
+ * @cmd: Completed command
+ * @good_bytes: Command reply bytes
+ * @sshdr: command sense header
+ *
+ * Called from sd_done(). Process report zones reply and handle reset zone
+ * and write commands errors.
+ */
+void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 		     struct scsi_sense_hdr *sshdr)
 {
 	int result = cmd->result;

@@ -336,7 +404,11 @@ void sd_zbc_complete(struct scsi_cmnd *cmd,
 }
 
 /**
- * Read zoned block device characteristics (VPD page B6).
+ * sd_zbc_read_zoned_characteristics - Read zoned block device characteristics
+ * @sdkp: Target disk
+ * @buf: Buffer where to store the VPD page data
+ *
+ * Read VPD page B6.
  */
 static int sd_zbc_read_zoned_characteristics(struct scsi_disk *sdkp,
 					     unsigned char *buf)

@@ -366,10 +438,16 @@ static int sd_zbc_read_zoned_characteristics(struct scsi_disk *sdkp,
 }
 
 /**
- * Check reported capacity.
+ * sd_zbc_check_capacity - Check reported capacity.
+ * @sdkp: Target disk
+ * @buf: Buffer to use for commands
+ *
+ * ZBC drive may report only the capacity of the first conventional zones at
+ * LBA 0. This is indicated by the RC_BASIS field of the read capacity reply.
+ * Check this here. If the disk reported only its conventional zones capacity,
+ * get the total capacity by doing a report zones.
  */
-static int sd_zbc_check_capacity(struct scsi_disk *sdkp,
-				 unsigned char *buf)
+static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
 {
 	sector_t lba;
 	int ret;

@@ -399,6 +477,13 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp,
 
 #define SD_ZBC_BUF_SIZE 131072
 
+/**
+ * sd_zbc_check_zone_size - Check the device zone sizes
+ * @sdkp: Target disk
+ *
+ * Check that all zones of the device are equal. The last zone can however
+ * be smaller. The zone size must also be a power of two number of LBAs.
+ */
 static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 {
 	u64 zone_blocks;

@@ -525,8 +610,7 @@ static int sd_zbc_setup(struct scsi_disk *sdkp)
 	return 0;
 }
 
-int sd_zbc_read_zones(struct scsi_disk *sdkp,
-		      unsigned char *buf)
+int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 {
 	int ret;
 

@@ -537,7 +621,6 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp,
 		 */
 		return 0;
 
-
 	/* Get zoned block device characteristics */
 	ret = sd_zbc_read_zoned_characteristics(sdkp, buf);
 	if (ret)

@@ -584,6 +584,7 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 	}
 
 	sdkp->zone_blocks = zone_blocks;
+	sdkp->zone_shift = ilog2(zone_blocks);
 
 	return 0;
 }

@@ -591,10 +592,13 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 static int sd_zbc_setup(struct scsi_disk *sdkp)
 {
 
+	/* READ16/WRITE16 is mandatory for ZBC disks */
+	sdkp->device->use_16_for_rw = 1;
+	sdkp->device->use_10_for_rw = 0;
+
 	/* chunk_sectors indicates the zone size */
 	blk_queue_chunk_sectors(sdkp->disk->queue,
 			logical_to_sectors(sdkp->device, sdkp->zone_blocks));
-	sdkp->zone_shift = ilog2(sdkp->zone_blocks);
 	sdkp->nr_zones = sdkp->capacity >> sdkp->zone_shift;
 	if (sdkp->capacity & (sdkp->zone_blocks - 1))
 		sdkp->nr_zones++;

@@ -657,10 +661,6 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	if (ret)
 		goto err;
 
-	/* READ16/WRITE16 is mandatory for ZBC disks */
-	sdkp->device->use_16_for_rw = 1;
-	sdkp->device->use_10_for_rw = 0;
-
 	return 0;
 
 err:

@@ -475,7 +475,7 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
 	return 0;
 }
 
-#define SD_ZBC_BUF_SIZE 131072
+#define SD_ZBC_BUF_SIZE 131072U
 
 /**
  * sd_zbc_check_zone_size - Check the device zone sizes

@@ -526,10 +526,7 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 		/* Parse REPORT ZONES header */
 		list_length = get_unaligned_be32(&buf[0]) + 64;
 		rec = buf + 64;
-		if (list_length < SD_ZBC_BUF_SIZE)
-			buf_len = list_length;
-		else
-			buf_len = SD_ZBC_BUF_SIZE;
+		buf_len = min(list_length, SD_ZBC_BUF_SIZE);
 
 		/* Parse zone descriptors */
 		while (rec < buf + buf_len) {

@@ -599,9 +596,8 @@ static int sd_zbc_setup(struct scsi_disk *sdkp)
 	/* chunk_sectors indicates the zone size */
 	blk_queue_chunk_sectors(sdkp->disk->queue,
 			logical_to_sectors(sdkp->device, sdkp->zone_blocks));
-	sdkp->nr_zones = sdkp->capacity >> sdkp->zone_shift;
-	if (sdkp->capacity & (sdkp->zone_blocks - 1))
-		sdkp->nr_zones++;
+	sdkp->nr_zones =
+		round_up(sdkp->capacity, sdkp->zone_blocks) >> sdkp->zone_shift;
 
 	if (!sdkp->zones_wlock) {
 		sdkp->zones_wlock = kcalloc(BITS_TO_LONGS(sdkp->nr_zones),

@@ -423,15 +423,15 @@ static int sd_zbc_read_zoned_characteristics(struct scsi_disk *sdkp,
 	if (sdkp->device->type != TYPE_ZBC) {
 		/* Host-aware */
 		sdkp->urswrz = 1;
-		sdkp->zones_optimal_open = get_unaligned_be64(&buf[8]);
-		sdkp->zones_optimal_nonseq = get_unaligned_be64(&buf[12]);
+		sdkp->zones_optimal_open = get_unaligned_be32(&buf[8]);
+		sdkp->zones_optimal_nonseq = get_unaligned_be32(&buf[12]);
 		sdkp->zones_max_open = 0;
 	} else {
 		/* Host-managed */
 		sdkp->urswrz = buf[4] & 1;
 		sdkp->zones_optimal_open = 0;
 		sdkp->zones_optimal_nonseq = 0;
-		sdkp->zones_max_open = get_unaligned_be64(&buf[16]);
+		sdkp->zones_max_open = get_unaligned_be32(&buf[16]);
 	}
 
 	return 0;

@@ -544,6 +544,13 @@ struct request_queue {
 	struct queue_limits	limits;
 
 	/*
+	 * Zoned block device information for mq I/O schedulers.
+	 * Set by low level device driver (stacking driver may not set this).
+	 */
+	unsigned int	nr_zones;
+	unsigned long	*seq_zones;
+
+	/*
 	 * sg stuff
 	 */
 	unsigned int		sg_timeout;

@@ -785,6 +792,27 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
+static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+{
+	return q->nr_zones;
+}
+
+static inline unsigned int blk_queue_zone_no(struct request_queue *q,
+					     sector_t sector)
+{
+	if (!blk_queue_is_zoned(q))
+		return 0;
+	return sector >> ilog2(q->limits.chunk_sectors);
+}
+
+static inline bool blk_queue_zone_is_seq(struct request_queue *q,
+					 sector_t sector)
+{
+	if (!blk_queue_is_zoned(q) || !q->seq_zones)
+		return false;
+	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones);
+}
+
 static inline bool rq_is_sync(struct request *rq)
 {
 	return op_is_sync(rq->cmd_flags);

@@ -1031,6 +1059,16 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> 9;
 }
 
+static inline unsigned int blk_rq_zone_no(struct request *rq)
+{
+	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
+}
+
+static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
+{
+	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
+}
+
 /*
  * Some commands like WRITE SAME have a payload or data transfer size which
  * is different from the size of the request.  Any driver that supports such

@@ -1582,6 +1620,16 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return blk_queue_nr_zones(q);
+
+	return 0;
+}
+
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;

@@ -586,8 +586,110 @@ static int sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 	return 0;
 }
 
+/**
+ * sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone).
+ * @sdkp: The disk of the bitmap
+ */
+static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
+{
+	struct request_queue *q = sdkp->disk->queue;
+
+	return kzalloc_node(BITS_TO_LONGS(sdkp->nr_zones)
+			    * sizeof(unsigned long),
+			    GFP_KERNEL, q->node);
+}
+
+/**
+ * sd_zbc_setup_seq_zones - Initialize the disk request queue zone type bitmap.
+ * @sdkp: The disk of the bitmap
+ *
+ * Allocate a zone bitmap and initialize it by identifying sequential zones.
+ */
+static int sd_zbc_setup_seq_zones(struct scsi_disk *sdkp)
+{
+	struct request_queue *q = sdkp->disk->queue;
+	unsigned long *seq_zones;
+	sector_t block = 0;
+	unsigned char *buf;
+	unsigned char *rec;
+	unsigned int buf_len;
+	unsigned int list_length;
+	unsigned int n = 0;
+	u8 type, cond;
+	int ret = -ENOMEM;
+
+	kfree(q->seq_zones);
+	q->seq_zones = NULL;
+
+	seq_zones = sd_zbc_alloc_zone_bitmap(sdkp);
+	if (!seq_zones)
+		return -ENOMEM;
+
+	buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	while (block < sdkp->capacity) {
+
+		ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, block);
+		if (ret)
+			goto out;
+
+		/*
+		 * Parse reported zone descriptors to find sequiential zones.
+		 * Since read-only and offline zones cannot be written, do not
+		 * mark them as sequential in the bitmap.
+		 */
+		list_length = get_unaligned_be32(&buf[0]) + 64;
+		rec = buf + 64;
+		buf_len = min(list_length, SD_ZBC_BUF_SIZE);
+		while (rec < buf + buf_len) {
+			type = rec[0] & 0x0f;
+			cond = (rec[1] >> 4) & 0xf;
+			if (type != ZBC_ZONE_TYPE_CONV &&
+			    cond != ZBC_ZONE_COND_READONLY &&
+			    cond != ZBC_ZONE_COND_OFFLINE)
+				set_bit(n, seq_zones);
+			block = get_unaligned_be64(&rec[8]) +
+				get_unaligned_be64(&rec[16]);
+			rec += 64;
+			n++;
+		}
+
+	}
+
+	if (n != sdkp->nr_zones) {
+		/* Something was wrong */
+		ret = -EIO;
+	}
+
+out:
+	kfree(buf);
+	if (ret) {
+		kfree(seq_zones);
+		return ret;
+	}
+
+	q->seq_zones = seq_zones;
+
+	return 0;
+}
+
+static void sd_zbc_cleanup(struct scsi_disk *sdkp)
+{
+	struct request_queue *q = sdkp->disk->queue;
+
+	kfree(q->seq_zones);
+	q->seq_zones = NULL;
+
+	kfree(sdkp->zones_wlock);
+	sdkp->zones_wlock = NULL;
+}
+
 static int sd_zbc_setup(struct scsi_disk *sdkp)
 {
+	struct request_queue *q = sdkp->disk->queue;
+	int ret;
 
 	/* READ16/WRITE16 is mandatory for ZBC disks */
 	sdkp->device->use_16_for_rw = 1;

@@ -599,14 +701,30 @@ static int sd_zbc_setup(struct scsi_disk *sdkp)
 	sdkp->nr_zones =
 		round_up(sdkp->capacity, sdkp->zone_blocks) >> sdkp->zone_shift;
 
-	if (!sdkp->zones_wlock) {
-		sdkp->zones_wlock = kcalloc(BITS_TO_LONGS(sdkp->nr_zones),
-					    sizeof(unsigned long),
-					    GFP_KERNEL);
+	/*
+	 * Wait for the disk capacity to stabilize before
+	 * initializing zone related information.
+	 */
+	if (sdkp->first_scan)
+		return 0;
+
+	if (!sdkp->zones_wlock || q->nr_zones != sdkp->nr_zones) {
+		kfree(sdkp->zones_wlock);
+		sdkp->zones_wlock = sd_zbc_alloc_zone_bitmap(sdkp);
 		if (!sdkp->zones_wlock)
 			return -ENOMEM;
 	}
 
+	if (!q->seq_zones || q->nr_zones != sdkp->nr_zones) {
+		ret = sd_zbc_setup_seq_zones(sdkp);
+		if (ret) {
+			sd_zbc_cleanup(sdkp);
+			return ret;
+		}
+	}
+
+	q->nr_zones = sdkp->nr_zones;
+
 	return 0;
 }
 

@@ -661,14 +779,14 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 
 err:
 	sdkp->capacity = 0;
+	sd_zbc_cleanup(sdkp);
 
 	return ret;
 }
 
 void sd_zbc_remove(struct scsi_disk *sdkp)
 {
-	kfree(sdkp->zones_wlock);
-	sdkp->zones_wlock = NULL;
+	sd_zbc_cleanup(sdkp);
 }
 
 void sd_zbc_print_zones(struct scsi_disk *sdkp)

@@ -298,10 +298,11 @@ int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
 int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd)
 {
 	struct request *rq = cmd->request;
+	struct request_queue *q = rq->q;
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	sector_t sector = blk_rq_pos(rq);
 	sector_t zone_sectors = sd_zbc_zone_sectors(sdkp);
-	unsigned int zno = sd_zbc_zone_no(sdkp, sector);
+	unsigned int zno;
 
 	/*
 	 * Note: Checks of the alignment of the write command on

@@ -309,18 +310,21 @@ int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd)
 	 */
 
 	/* Do not allow zone boundaries crossing on host-managed drives */
-	if (blk_queue_zoned_model(sdkp->disk->queue) == BLK_ZONED_HM &&
+	if (blk_queue_zoned_model(q) == BLK_ZONED_HM &&
 	    (sector & (zone_sectors - 1)) + blk_rq_sectors(rq) > zone_sectors)
 		return BLKPREP_KILL;
 
 	/*
-	 * Do not issue more than one write at a time per
-	 * zone. This solves write ordering problems due to
-	 * the unlocking of the request queue in the dispatch
-	 * path in the non scsi-mq case.
+	 * There is no write constraints on conventional zones. So any write
+	 * command can be sent. But do not issue more than one write command
+	 * at a time per sequential zone. This avoids write ordering problems
+	 * due to the unlocking of the request queue in the dispatch path of
+	 * legacy scsi path, as well as at the HBA level (e.g. AHCI).
 	 */
-	if (sdkp->zones_wlock &&
-	    test_and_set_bit(zno, sdkp->zones_wlock))
+	zno = sd_zbc_zone_no(sdkp, sector);
+	if (q->seq_zones && test_bit(zno, q->seq_zones))
+		return BLKPREP_OK;
+	if (sdkp->zones_wlock && test_and_set_bit(zno, sdkp->zones_wlock))
 		return BLKPREP_DEFER;
 
 	WARN_ON_ONCE(cmd->flags & SCMD_ZONE_WRITE_LOCK);

@@ -341,8 +345,9 @@ void sd_zbc_write_unlock_zone(struct scsi_cmnd *cmd)
 	struct request *rq = cmd->request;
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 
-	if (sdkp->zones_wlock && cmd->flags & SCMD_ZONE_WRITE_LOCK) {
+	if (cmd->flags & SCMD_ZONE_WRITE_LOCK) {
 		unsigned int zno = sd_zbc_zone_no(sdkp, blk_rq_pos(rq));
+
 		WARN_ON_ONCE(!test_bit(zno, sdkp->zones_wlock));
 		cmd->flags &= ~SCMD_ZONE_WRITE_LOCK;
 		clear_bit_unlock(zno, sdkp->zones_wlock);

@@ -314,6 +314,10 @@ int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd)
 	    (sector & (zone_sectors - 1)) + blk_rq_sectors(rq) > zone_sectors)
 		return BLKPREP_KILL;
 
+	/* No write locking with scsi-mq */
+	if (q->mq_ops)
+		return BLKPREP_OK;
+
 	/*
 	 * There is no write constraints on conventional zones. So any write
 	 * command can be sent. But do not issue more than one write command

@@ -713,7 +717,8 @@ static int sd_zbc_setup(struct scsi_disk *sdkp)
 	if (sdkp->first_scan)
 		return 0;
 
-	if (!sdkp->zones_wlock || q->nr_zones != sdkp->nr_zones) {
+	if (!q->mq_ops &&
+	    (!sdkp->zones_wlock || q->nr_zones != sdkp->nr_zones)) {
 		kfree(sdkp->zones_wlock);
 		sdkp->zones_wlock = sd_zbc_alloc_zone_bitmap(sdkp);
 		if (!sdkp->zones_wlock)

@@ -60,6 +60,10 @@ struct deadline_data {
 
 	spinlock_t lock;
 	struct list_head dispatch;
+
+	struct request_queue *q;
+	spinlock_t zone_lock;
+	unsigned long *zones_wlock;
 };
 
 static inline struct rb_root *

@@ -300,6 +304,24 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	return rq;
 }
 
+static int deadline_enable_zones_wlock(struct deadline_data *dd,
+				       gfp_t gfp_mask)
+{
+	dd->zones_wlock = kzalloc_node(BITS_TO_LONGS(blk_queue_nr_zones(dd->q))
+				       * sizeof(unsigned long),
+				       gfp_mask, dd->q->node);
+	if (!dd->zones_wlock)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void deadline_disable_zones_wlock(struct deadline_data *dd)
+{
+	kfree(dd->zones_wlock);
+	dd->zones_wlock = NULL;
+}
+
 static void dd_exit_queue(struct elevator_queue *e)
 {
 	struct deadline_data *dd = e->elevator_data;

@@ -307,16 +329,40 @@ static void dd_exit_queue(struct elevator_queue *e)
 	BUG_ON(!list_empty(&dd->fifo_list[READ]));
 	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));
 
+	deadline_disable_zones_wlock(dd);
 	kfree(dd);
 }
 
 /*
+ * initialize zoned block device related elevator private data.
+ */
+static int deadline_zoned_init_queue(struct request_queue *q,
+				     struct deadline_data *dd)
+{
+	if (!blk_queue_is_zoned(q) ||
+	    !blk_queue_nr_zones(q)) {
+		/*
+		 * Regular drive, or non-conforming zoned block device.
+		 * Do not use zone write locking.
+		 */
+		return 0;
+	}
+
+	/*
+	 * Enable zone write locking by default for any zoned
+	 * block device model.
+	 */
+	return deadline_enable_zones_wlock(dd, GFP_KERNEL);
+}
+
+/*
  * initialize elevator private data (deadline_data).
  */
 static int dd_init_queue(struct request_queue *q, struct elevator_type *e)
 {
 	struct deadline_data *dd;
 	struct elevator_queue *eq;
+	int ret;
 
 	eq = elevator_alloc(q, e);
 	if (!eq)

@@ -341,6 +387,15 @@ static int dd_init_queue(struct request_queue *q, struct elevator_type *e)
 	spin_lock_init(&dd->lock);
 	INIT_LIST_HEAD(&dd->dispatch);
 
+	dd->q = q;
+	spin_lock_init(&dd->zone_lock);
+	ret = deadline_zoned_init_queue(q, dd);
+	if (ret) {
+		kfree(dd);
+		kobject_put(&eq->kobj);
+		return ret;
+	}
+
 	q->elevator = eq;
 	return 0;
 }

@@ -339,8 +339,7 @@ static void dd_exit_queue(struct elevator_queue *e)
 static int deadline_zoned_init_queue(struct request_queue *q,
 				     struct deadline_data *dd)
 {
-	if (!blk_queue_is_zoned(q) ||
-	    !blk_queue_nr_zones(q)) {
+	if (!blk_queue_is_zoned(q) || !blk_queue_nr_zones(q)) {
 		/*
 		 * Regular drive, or non-conforming zoned block device.
 		 * Do not use zone write locking.

@@ -559,6 +558,45 @@ STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
 STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
 #undef STORE_FUNCTION
 
+static ssize_t deadline_zones_wlock_show(struct elevator_queue *e, char *page)
+{
+	struct deadline_data *dd = e->elevator_data;
+
+	return deadline_var_show(dd->zones_wlock ? 1 : 0, page);
+}
+
+static ssize_t deadline_zones_wlock_store(struct elevator_queue *e,
+					  const char *page, size_t count)
+{
+	struct deadline_data *dd = e->elevator_data;
+	int ret, enable_zones_wlock;
+
+	deadline_var_store(&enable_zones_wlock, page);
+	if (enable_zones_wlock != 0 && enable_zones_wlock != 1)
+		return -EINVAL;
+
+	if ((enable_zones_wlock && dd->zones_wlock) ||
+	    (!enable_zones_wlock && !dd->zones_wlock))
+		return count;
+
+	/* Changes are allowed only for host-aware disks */
+	if (blk_queue_zoned_model(dd->q) != BLK_ZONED_HA)
+		return -EPERM;
+
+	blk_mq_freeze_queue(dd->q);
+
+	if (enable_zones_wlock) {
+		ret = deadline_enable_zones_wlock(dd, GFP_NOIO);
+	} else {
+		deadline_disable_zones_wlock(dd);
+		ret = 0;
+	}
+
+	blk_mq_unfreeze_queue(dd->q);
+
+	return ret ? ret : count;
+}
+
 #define DD_ATTR(name) \
 	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
 				      deadline_##name##_store)