block: add zone open, close and finish operations

Zoned block devices (ZBC and ZAC devices) allow an explicit control
over the condition (state) of zones. The operations allowed are:
* Open a zone: Transition to open condition to indicate that a zone will
  actively be written
* Close a zone: Transition to closed condition to release the drive
  resources used for writing to a zone
* Finish a zone: Transition an open or closed zone to the full
  condition to prevent write operations

To enable this control for in-kernel zoned block device users, define
the new request operations REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE
and REQ_OP_ZONE_FINISH as well as the generic function
blkdev_zone_mgmt() for submitting these operations on a range of zones.
This results in blkdev_reset_zones() removal and replacement with this
new zone magement function. Users of blkdev_reset_zones() (f2fs and
dm-zoned) are updated accordingly.

Contains contributions from Matias Bjorling, Hans Holmberg,
Dmitry Fomichev, Keith Busch, Damien Le Moal and Christoph Hellwig.

Reviewed-by: Javier González <[email protected]>
Reviewed-by: Christoph Hellwig <[email protected]>
Signed-off-by: Ajay Joshi <[email protected]>
Signed-off-by: Matias Bjorling <[email protected]>
Signed-off-by: Hans Holmberg <[email protected]>
Signed-off-by: Dmitry Fomichev <[email protected]>
Signed-off-by: Keith Busch <[email protected]>
Signed-off-by: Damien Le Moal <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>

block/blk-core.c

@@ -132,6 +132,9 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(SECURE_ERASE),
 	REQ_OP_NAME(ZONE_RESET),
 	REQ_OP_NAME(ZONE_RESET_ALL),
+	REQ_OP_NAME(ZONE_OPEN),
+	REQ_OP_NAME(ZONE_CLOSE),
+	REQ_OP_NAME(ZONE_FINISH),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(SCSI_IN),
@@ -849,10 +852,10 @@ static inline int blk_partition_remap(struct bio *bio)
 		goto out;
 
 	/*
-	 * Zone reset does not include bi_size so bio_sectors() is always 0.
-	 * Include a test for the reset op code and perform the remap if needed.
+	 * Zone management bios do not have a sector count but they do have
+	 * a start sector filled out and need to be remapped.
 	 */
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) {
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) {
 		if (bio_check_eod(bio, part_nr_sects_read(p)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
@@ -936,6 +939,9 @@ generic_make_request_checks(struct bio *bio)
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
 		if (!blk_queue_is_zoned(q))
 			goto not_supported;
 		break;

block/blk-zoned.c

@@ -221,23 +221,27 @@ static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
 }
 
 /**
- * blkdev_reset_zones - Reset zones write pointer
+ * blkdev_zone_mgmt - Execute a zone management operation on a range of zones
  * @bdev:	Target block device
- * @sector:	Start sector of the first zone to reset
- * @nr_sectors:	Number of sectors, at least the length of one zone
+ * @op:		Operation to be performed on the zones
+ * @sector:	Start sector of the first zone to operate on
+ * @nr_sectors:	Number of sectors, should be at least the length of one zone and
+ *		must be zone size aligned.
  * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
- *    Reset the write pointer of the zones contained in the range
+ *    Perform the specified operation on the range of zones specified by
  *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
  *    is valid, but the specified range should not contain conventional zones.
+ *    The operation to execute on each zone can be a zone reset, open, close
+ *    or finish request.
  */
-int blkdev_reset_zones(struct block_device *bdev,
-		       sector_t sector, sector_t nr_sectors,
-		       gfp_t gfp_mask)
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+		     sector_t sector, sector_t nr_sectors,
+		     gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t zone_sectors;
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
 	int ret;
@@ -248,12 +252,14 @@ int blkdev_reset_zones(struct block_device *bdev,
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
+	if (!op_is_zone_mgmt(op))
+		return -EOPNOTSUPP;
+
 	if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
 		/* Out of range */
 		return -EINVAL;
 
 	/* Check alignment (handle eventual smaller last zone) */
-	zone_sectors = blk_queue_zone_sectors(q);
 	if (sector & (zone_sectors - 1))
 		return -EINVAL;
 
@@ -269,12 +275,13 @@ int blkdev_reset_zones(struct block_device *bdev,
 		 * Special case for the zone reset operation that reset all
 		 * zones, this is useful for applications like mkfs.
 		 */
-		if (blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
+		if (op == REQ_OP_ZONE_RESET &&
+		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
 			bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
 			break;
 		}
 
-		bio->bi_opf = REQ_OP_ZONE_RESET;
+		bio->bi_opf = op;
 		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
@@ -287,7 +294,7 @@ int blkdev_reset_zones(struct block_device *bdev,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
 
 /*
  * BLKREPORTZONE ioctl processing.
@@ -379,8 +386,8 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
 		return -EFAULT;
 
-	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
-				  GFP_KERNEL);
+	return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+				zrange.sector, zrange.nr_sectors, GFP_KERNEL);
 }
 
 static inline unsigned long *blk_alloc_zone_bitmap(int node,

drivers/md/dm-zoned-metadata.c

@@ -1312,9 +1312,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zmd->dev;
 
-		ret = blkdev_reset_zones(dev->bdev,
-					 dmz_start_sect(zmd, zone),
-					 dev->zone_nr_sectors, GFP_NOIO);
+		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
+				       dmz_start_sect(zmd, zone),
+				       dev->zone_nr_sectors, GFP_NOIO);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    dmz_id(zmd, zone), ret);

fs/f2fs/segment.c

@@ -1771,7 +1771,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 			return -EIO;
 		}
 		trace_f2fs_issue_reset_zone(bdev, blkstart);
-		return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS);
+		return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+					sector, nr_sects, GFP_NOFS);
 	}
 
 	/* For conventional zones, use regular discard if supported */

include/linux/blk_types.h

@@ -290,6 +290,12 @@ enum req_opf {
 	REQ_OP_ZONE_RESET_ALL	= 8,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= 9,
+	/* Open a zone */
+	REQ_OP_ZONE_OPEN	= 10,
+	/* Close a zone */
+	REQ_OP_ZONE_CLOSE	= 11,
+	/* Transition a zone to full */
+	REQ_OP_ZONE_FINISH	= 12,
 
 	/* SCSI passthrough using struct scsi_request */
 	REQ_OP_SCSI_IN		= 32,
@@ -417,6 +423,25 @@ static inline bool op_is_discard(unsigned int op)
 	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
 }
 
+/*
+ * Check if a bio or request operation is a zone management operation, with
+ * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case
+ * due to its different handling in the block layer and device response in
+ * case of command failure.
+ */
+static inline bool op_is_zone_mgmt(enum req_opf op)
+{
+	switch (op & REQ_OP_MASK) {
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline int op_stat_group(unsigned int op)
 {
 	if (op_is_discard(op))

include/linux/blkdev.h

@@ -360,8 +360,9 @@ extern unsigned int blkdev_nr_zones(struct block_device *bdev);
 extern int blkdev_report_zones(struct block_device *bdev,
 			       sector_t sector, struct blk_zone *zones,
 			       unsigned int *nr_zones);
-extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
-			      sector_t nr_sectors, gfp_t gfp_mask);
+extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+			    sector_t sectors, sector_t nr_sectors,
+			    gfp_t gfp_mask);
 extern int blk_revalidate_disk_zones(struct gendisk *disk);
 
 extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,