scsi: sd_zbc: emulate ZONE_APPEND commands

Emulate ZONE_APPEND for SCSI disks using a regular WRITE(16) command
with a start LBA set to the target zone write pointer position.

In order to always know the write pointer position of a sequential write
zone, the write pointer of all zones is tracked using an array of 32bits
zone write pointer offset attached to the scsi disk structure. Each
entry of the array indicate a zone write pointer position relative to
the zone start sector. The write pointer offsets are maintained in sync
with the device as follows:
1) the write pointer offset of a zone is reset to 0 when a
   REQ_OP_ZONE_RESET command completes.
2) the write pointer offset of a zone is set to the zone size when a
   REQ_OP_ZONE_FINISH command completes.
3) the write pointer offset of a zone is incremented by the number of
   512B sectors written when a write, write same or a zone append
   command completes.
4) the write pointer offset of all zones is reset to 0 when a
   REQ_OP_ZONE_RESET_ALL command completes.

Since the block layer does not write lock zones for zone append
commands, to ensure a sequential ordering of the regular write commands
used for the emulation, the target zone of a zone append command is
locked when the function sd_zbc_prepare_zone_append() is called from
sd_setup_read_write_cmnd(). If the zone write lock cannot be obtained
(e.g. a zone append is in-flight or a regular write has already locked
the zone), the zone append command dispatching is delayed by returning
BLK_STS_ZONE_RESOURCE.

To avoid the need for write locking all zones for REQ_OP_ZONE_RESET_ALL
requests, use a spinlock to protect accesses and modifications of the
zone write pointer offsets. This spinlock is initialized from sd_probe()
using the new function sd_zbc_init().
Co-developed-by: Damien Le Moal <Damien.LeMoal@wdc.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/scsi/sd.c

@@ -1206,6 +1206,12 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 		}
 	}
 
+	if (req_op(rq) == REQ_OP_ZONE_APPEND) {
+		ret = sd_zbc_prepare_zone_append(cmd, &lba, nr_blocks);
+		if (ret)
+			return ret;
+	}
+
 	fua = rq->cmd_flags & REQ_FUA ? 0x8 : 0;
 	dix = scsi_prot_sg_count(cmd);
 	dif = scsi_host_dif_capable(cmd->device->host, sdkp->protection_type);
@@ -1287,6 +1293,7 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
 		return sd_setup_flush_cmnd(cmd);
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
+	case REQ_OP_ZONE_APPEND:
 		return sd_setup_read_write_cmnd(cmd);
 	case REQ_OP_ZONE_RESET:
 		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER,
@@ -2055,7 +2062,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 
  out:
 	if (sd_is_zoned(sdkp))
-		sd_zbc_complete(SCpnt, good_bytes, &sshdr);
+		good_bytes = sd_zbc_complete(SCpnt, good_bytes, &sshdr);
 
 	SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt,
 					   "sd_done: completed %d of %d bytes\n",
@@ -3372,6 +3379,10 @@ static int sd_probe(struct device *dev)
 	sdkp->first_scan = 1;
 	sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS;
 
+	error = sd_zbc_init_disk(sdkp);
+	if (error)
+		goto out_free_index;
+
 	sd_revalidate_disk(gd);
 
 	gd->flags = GENHD_FL_EXT_DEVT;
@@ -3409,6 +3420,7 @@ static int sd_probe(struct device *dev)
  out_put:
 	put_disk(gd);
  out_free:
+	sd_zbc_release_disk(sdkp);
 	kfree(sdkp);
  out:
 	scsi_autopm_put_device(sdp);
@@ -3485,6 +3497,8 @@ static void scsi_disk_release(struct device *dev)
 	put_disk(disk);
 	put_device(&sdkp->device->sdev_gendev);
 
+	sd_zbc_release_disk(sdkp);
+
 	kfree(sdkp);
 }
 

drivers/scsi/sd.h

@@ -79,6 +79,12 @@ struct scsi_disk {
 	u32		zones_optimal_open;
 	u32		zones_optimal_nonseq;
 	u32		zones_max_open;
+	u32		*zones_wp_offset;
+	spinlock_t	zones_wp_offset_lock;
+	u32		*rev_wp_offset;
+	struct mutex	rev_mutex;
+	struct work_struct zone_wp_offset_work;
+	char		*zone_wp_update_buf;
 #endif
 	atomic_t	openers;
 	sector_t	capacity;	/* size in logical blocks */
@@ -207,17 +213,35 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
+int sd_zbc_init_disk(struct scsi_disk *sdkp);
+void sd_zbc_release_disk(struct scsi_disk *sdkp);
 extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
 extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
 blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
 					 unsigned char op, bool all);
-extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
+unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 			     struct scsi_sense_hdr *sshdr);
 int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
 
+blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
+				        unsigned int nr_blocks);
+
 #else /* CONFIG_BLK_DEV_ZONED */
 
+static inline int sd_zbc_init(void)
+{
+	return 0;
+}
+
+static inline int sd_zbc_init_disk(struct scsi_disk *sdkp)
+{
+	return 0;
+}
+
+static inline void sd_zbc_exit(void) {}
+static inline void sd_zbc_release_disk(struct scsi_disk *sdkp) {}
+
 static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
 				    unsigned char *buf)
 {
@@ -233,9 +257,18 @@ static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
 	return BLK_STS_TARGET;
 }
 
-static inline void sd_zbc_complete(struct scsi_cmnd *cmd,
-				   unsigned int good_bytes,
-				   struct scsi_sense_hdr *sshdr) {}
+static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd,
+			unsigned int good_bytes, struct scsi_sense_hdr *sshdr)
+{
+	return 0;
+}
+
+static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd,
+						      sector_t *lba,
+						      unsigned int nr_blocks)
+{
+	return BLK_STS_TARGET;
+}
 
 #define sd_zbc_report_zones NULL