null_blk: support read-only and offline zone conditions

In zoned mode, zones with write pointers can have conditions "read-only"
or "offline". In read-only condition, zones can not be written. In
offline condition, the zones can be neither written nor read. These
conditions are intended for zones with media failures, then it is
difficult to set those conditions to zones on real devices.

To test handling of zones in the conditions, add a feature to null_blk
to set up zones in read-only or offline condition. Add new configuration
attributes "zone_readonly" and "zone_offline". Write a sector to the
attribute files to specify the target zone to set the zone conditions.
For example, following command lines do it:

   echo 0 > nullb1/zone_readonly
   echo 524288 > nullb1/zone_offline

When the specified zones are already in read-only or offline condition,
normal empty condition is restored to the zones. These condition changes
can be done only after the null_blk device get powered, since status
area of each zone is not yet allocated before power-on.

Also improve zone condition checks to inhibit all commands for zones in
offline conditions. In same manner, inhibit write and zone management
commands for zones in read-only condition.

Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
Link: https://lore.kernel.org/r/20221201061036.2342206-1-shinichiro.kawasaki@wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: kawasaki

drivers/block/null_blk/main.c

@@ -523,6 +523,24 @@ static ssize_t nullb_device_badblocks_store(struct config_item *item,
 }
 CONFIGFS_ATTR(nullb_device_, badblocks);
 
+static ssize_t nullb_device_zone_readonly_store(struct config_item *item,
+						const char *page, size_t count)
+{
+	struct nullb_device *dev = to_nullb_device(item);
+
+	return zone_cond_store(dev, page, count, BLK_ZONE_COND_READONLY);
+}
+CONFIGFS_ATTR_WO(nullb_device_, zone_readonly);
+
+static ssize_t nullb_device_zone_offline_store(struct config_item *item,
+					       const char *page, size_t count)
+{
+	struct nullb_device *dev = to_nullb_device(item);
+
+	return zone_cond_store(dev, page, count, BLK_ZONE_COND_OFFLINE);
+}
+CONFIGFS_ATTR_WO(nullb_device_, zone_offline);
+
 static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_size,
 	&nullb_device_attr_completion_nsec,
@@ -549,6 +567,8 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_nr_conv,
 	&nullb_device_attr_zone_max_open,
 	&nullb_device_attr_zone_max_active,
+	&nullb_device_attr_zone_readonly,
+	&nullb_device_attr_zone_offline,
 	&nullb_device_attr_virt_boundary,
 	&nullb_device_attr_no_sched,
 	&nullb_device_attr_shared_tag_bitmap,
@@ -614,7 +634,7 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
 			"poll_queues,power,queue_mode,shared_tag_bitmap,size,"
 			"submit_queues,use_per_node_hctx,virt_boundary,zoned,"
 			"zone_capacity,zone_max_active,zone_max_open,"
-			"zone_nr_conv,zone_size\n");
+			"zone_nr_conv,zone_offline,zone_readonly,zone_size\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);

drivers/block/null_blk/null_blk.h

@@ -151,6 +151,8 @@ blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_op op,
 				    sector_t sector, sector_t nr_sectors);
 size_t null_zone_valid_read_len(struct nullb *nullb,
 				sector_t sector, unsigned int len);
+ssize_t zone_cond_store(struct nullb_device *dev, const char *page,
+			size_t count, enum blk_zone_cond cond);
 #else
 static inline int null_init_zoned_dev(struct nullb_device *dev,
 				      struct request_queue *q)
@@ -174,6 +176,12 @@ static inline size_t null_zone_valid_read_len(struct nullb *nullb,
 {
 	return len;
 }
+static inline ssize_t zone_cond_store(struct nullb_device *dev,
+				      const char *page, size_t count,
+				      enum blk_zone_cond cond)
+{
+	return -EOPNOTSUPP;
+}
 #define null_report_zones	NULL
 #endif /* CONFIG_BLK_DEV_ZONED */
 #endif /* __NULL_BLK_H */

drivers/block/null_blk/zoned.c

@@ -384,8 +384,10 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 
 	null_lock_zone(dev, zone);
 
-	if (zone->cond == BLK_ZONE_COND_FULL) {
-		/* Cannot write to a full zone */
+	if (zone->cond == BLK_ZONE_COND_FULL ||
+	    zone->cond == BLK_ZONE_COND_READONLY ||
+	    zone->cond == BLK_ZONE_COND_OFFLINE) {
+		/* Cannot write to the zone */
 		ret = BLK_STS_IOERR;
 		goto unlock;
 	}
@@ -613,7 +615,9 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_op op,
 		for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
 			zone = &dev->zones[i];
 			null_lock_zone(dev, zone);
-			if (zone->cond != BLK_ZONE_COND_EMPTY) {
+			if (zone->cond != BLK_ZONE_COND_EMPTY &&
+			    zone->cond != BLK_ZONE_COND_READONLY &&
+			    zone->cond != BLK_ZONE_COND_OFFLINE) {
 				null_reset_zone(dev, zone);
 				trace_nullb_zone_op(cmd, i, zone->cond);
 			}
@@ -627,6 +631,12 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_op op,
 
 	null_lock_zone(dev, zone);
 
+	if (zone->cond == BLK_ZONE_COND_READONLY ||
+	    zone->cond == BLK_ZONE_COND_OFFLINE) {
+		ret = BLK_STS_IOERR;
+		goto unlock;
+	}
+
 	switch (op) {
 	case REQ_OP_ZONE_RESET:
 		ret = null_reset_zone(dev, zone);
@@ -648,6 +658,7 @@ static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_op op,
 	if (ret == BLK_STS_OK)
 		trace_nullb_zone_op(cmd, zone_no, zone->cond);
 
+unlock:
 	null_unlock_zone(dev, zone);
 
 	return ret;
@@ -674,10 +685,88 @@ blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_op op,
 	default:
 		dev = cmd->nq->dev;
 		zone = &dev->zones[null_zone_no(dev, sector)];
+		if (zone->cond == BLK_ZONE_COND_OFFLINE)
+			return BLK_STS_IOERR;
 
 		null_lock_zone(dev, zone);
 		sts = null_process_cmd(cmd, op, sector, nr_sectors);
 		null_unlock_zone(dev, zone);
 		return sts;
 	}
 }
+
+/*
+ * Set a zone in the read-only or offline condition.
+ */
+static void null_set_zone_cond(struct nullb_device *dev,
+			       struct nullb_zone *zone, enum blk_zone_cond cond)
+{
+	if (WARN_ON_ONCE(cond != BLK_ZONE_COND_READONLY &&
+			 cond != BLK_ZONE_COND_OFFLINE))
+		return;
+
+	null_lock_zone(dev, zone);
+
+	/*
+	 * If the read-only condition is requested again to zones already in
+	 * read-only condition, restore back normal empty condition. Do the same
+	 * if the offline condition is requested for offline zones. Otherwise,
+	 * set the specified zone condition to the zones. Finish the zones
+	 * beforehand to free up zone resources.
+	 */
+	if (zone->cond == cond) {
+		zone->cond = BLK_ZONE_COND_EMPTY;
+		zone->wp = zone->start;
+		if (dev->memory_backed)
+			null_handle_discard(dev, zone->start, zone->len);
+	} else {
+		if (zone->cond != BLK_ZONE_COND_READONLY &&
+		    zone->cond != BLK_ZONE_COND_OFFLINE)
+			null_finish_zone(dev, zone);
+		zone->cond = cond;
+		zone->wp = (sector_t)-1;
+	}
+
+	null_unlock_zone(dev, zone);
+}
+
+/*
+ * Identify a zone from the sector written to configfs file. Then set zone
+ * condition to the zone.
+ */
+ssize_t zone_cond_store(struct nullb_device *dev, const char *page,
+			size_t count, enum blk_zone_cond cond)
+{
+	unsigned long long sector;
+	unsigned int zone_no;
+	int ret;
+
+	if (!dev->zoned) {
+		pr_err("null_blk device is not zoned\n");
+		return -EINVAL;
+	}
+
+	if (!dev->zones) {
+		pr_err("null_blk device is not yet powered\n");
+		return -EINVAL;
+	}
+
+	ret = kstrtoull(page, 0, &sector);
+	if (ret < 0)
+		return ret;
+
+	zone_no = null_zone_no(dev, sector);
+	if (zone_no >= dev->nr_zones) {
+		pr_err("Sector out of range\n");
+		return -EINVAL;
+	}
+
+	if (dev->zones[zone_no].type == BLK_ZONE_TYPE_CONVENTIONAL) {
+		pr_err("Can not change condition of conventional zones\n");
+		return -EINVAL;
+	}
+
+	null_set_zone_cond(dev, &dev->zones[zone_no], cond);
+
+	return count;
+}