Merge branch 'for-6.11/block' into for-next

* for-6.11/block:
  dm: Remove unused macro DM_ZONE_INVALID_WP_OFST
  dm: Improve zone resource limits handling
  dm: Call dm_revalidate_zones() after setting the queue limits
  block: Improve checks on zone resource limits

Author: axboe

block/blk-settings.c

@@ -80,6 +80,14 @@ static int blk_validate_zoned_limits(struct queue_limits *lim)
 	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)))
 		return -EINVAL;
 
+	/*
+	 * Given that active zones include open zones, the maximum number of
+	 * open zones cannot be larger than the maximum number of active zones.
+	 */
+	if (lim->max_active_zones &&
+	    lim->max_open_zones > lim->max_active_zones)
+		return -EINVAL;
+
 	if (lim->zone_write_granularity < lim->logical_block_size)
 		lim->zone_write_granularity = lim->logical_block_size;
 

block/blk-zoned.c

@@ -1647,8 +1647,22 @@ static int disk_update_zone_resources(struct gendisk *disk,
 		return -ENODEV;
 	}
 
+	lim = queue_limits_start_update(q);
+
+	/*
+	 * Some devices can advertize zone resource limits that are larger than
+	 * the number of sequential zones of the zoned block device, e.g. a
+	 * small ZNS namespace. For such case, assume that the zoned device has
+	 * no zone resource limits.
+	 */
+	nr_seq_zones = disk->nr_zones - nr_conv_zones;
+	if (lim.max_open_zones >= nr_seq_zones)
+		lim.max_open_zones = 0;
+	if (lim.max_active_zones >= nr_seq_zones)
+		lim.max_active_zones = 0;
+
 	if (!disk->zone_wplugs_pool)
-		return 0;
+		goto commit;
 
 	/*
 	 * If the device has no limit on the maximum number of open and active
@@ -1657,9 +1671,6 @@ static int disk_update_zone_resources(struct gendisk *disk,
 	 * dynamic zone write plug allocation when simultaneously writing to
 	 * more zones than the size of the mempool.
 	 */
-	lim = queue_limits_start_update(q);
-
-	nr_seq_zones = disk->nr_zones - nr_conv_zones;
 	pool_size = max(lim.max_open_zones, lim.max_active_zones);
 	if (!pool_size)
 		pool_size = min(BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE, nr_seq_zones);
@@ -1673,6 +1684,7 @@ static int disk_update_zone_resources(struct gendisk *disk,
 			lim.max_open_zones = 0;
 	}
 
+commit:
 	return queue_limits_commit_update(q, &lim);
 }
 

drivers/md/dm-table.c

@@ -1921,10 +1921,7 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	    dm_table_any_dev_attr(t, device_is_not_random, NULL))
 		blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
 
-	/*
-	 * For a zoned target, setup the zones related queue attributes
-	 * and resources necessary for zone append emulation if necessary.
-	 */
+	/* For a zoned table, setup the zone related queue attributes. */
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
 		r = dm_set_zones_restrictions(t, q, limits);
 		if (r)
@@ -1935,6 +1932,16 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	if (r)
 		return r;
 
+	/*
+	 * Now that the limits are set, check the zones mapped by the table
+	 * and setup the resources for zone append emulation if necessary.
+	 */
+	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
+		r = dm_revalidate_zones(t, q);
+		if (r)
+			return r;
+	}
+
 	dm_update_crypto_profile(q, t);
 
 	/*

drivers/md/dm-zone.c

@@ -13,8 +13,6 @@
 
 #define DM_MSG_PREFIX "zone"
 
-#define DM_ZONE_INVALID_WP_OFST		UINT_MAX
-
 /*
  * For internal zone reports bypassing the top BIO submission path.
  */
@@ -145,35 +143,28 @@ bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 	}
 }
 
-/*
- * Count conventional zones of a mapped zoned device. If the device
- * only has conventional zones, do not expose it as zoned.
- */
-static int dm_check_zoned_cb(struct blk_zone *zone, unsigned int idx,
-			     void *data)
-{
-	unsigned int *nr_conv_zones = data;
-
-	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
-		(*nr_conv_zones)++;
-
-	return 0;
-}
-
 /*
  * Revalidate the zones of a mapped device to initialize resource necessary
  * for zone append emulation. Note that we cannot simply use the block layer
  * blk_revalidate_disk_zones() function here as the mapped device is suspended
  * (this is called from __bind() context).
  */
-static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t)
+int dm_revalidate_zones(struct dm_table *t, struct request_queue *q)
 {
+	struct mapped_device *md = t->md;
 	struct gendisk *disk = md->disk;
 	int ret;
 
+	if (!get_capacity(disk))
+		return 0;
+
 	/* Revalidate only if something changed. */
-	if (!disk->nr_zones || disk->nr_zones != md->nr_zones)
+	if (!disk->nr_zones || disk->nr_zones != md->nr_zones) {
+		DMINFO("%s using %s zone append",
+		       disk->disk_name,
+		       queue_emulates_zone_append(q) ? "emulated" : "native");
 		md->nr_zones = 0;
+	}
 
 	if (md->nr_zones)
 		return 0;
@@ -220,13 +211,127 @@ static bool dm_table_supports_zone_append(struct dm_table *t)
 	return true;
 }
 
+struct dm_device_zone_count {
+	sector_t start;
+	sector_t len;
+	unsigned int total_nr_seq_zones;
+	unsigned int target_nr_seq_zones;
+};
+
+/*
+ * Count the total number of and the number of mapped sequential zones of a
+ * target zoned device.
+ */
+static int dm_device_count_zones_cb(struct blk_zone *zone,
+				    unsigned int idx, void *data)
+{
+	struct dm_device_zone_count *zc = data;
+
+	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
+		zc->total_nr_seq_zones++;
+		if (zone->start >= zc->start &&
+		    zone->start < zc->start + zc->len)
+			zc->target_nr_seq_zones++;
+	}
+
+	return 0;
+}
+
+static int dm_device_count_zones(struct dm_dev *dev,
+				 struct dm_device_zone_count *zc)
+{
+	int ret;
+
+	ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES,
+				  dm_device_count_zones_cb, zc);
+	if (ret < 0)
+		return ret;
+	if (!ret)
+		return -EIO;
+	return 0;
+}
+
+struct dm_zone_resource_limits {
+	unsigned int mapped_nr_seq_zones;
+	struct queue_limits *lim;
+	bool reliable_limits;
+};
+
+static int device_get_zone_resource_limits(struct dm_target *ti,
+					   struct dm_dev *dev, sector_t start,
+					   sector_t len, void *data)
+{
+	struct dm_zone_resource_limits *zlim = data;
+	struct gendisk *disk = dev->bdev->bd_disk;
+	unsigned int max_open_zones, max_active_zones;
+	int ret;
+	struct dm_device_zone_count zc = {
+		.start = start,
+		.len = len,
+	};
+
+	/*
+	 * If the target is not the whole device, the device zone resources may
+	 * be shared between different targets. Check this by counting the
+	 * number of mapped sequential zones: if this number is smaller than the
+	 * total number of sequential zones of the target device, then resource
+	 * sharing may happen and the zone limits will not be reliable.
+	 */
+	ret = dm_device_count_zones(dev, &zc);
+	if (ret) {
+		DMERR("Count %s zones failed %d", disk->disk_name, ret);
+		return ret;
+	}
+
+	/*
+	 * If the target does not map any sequential zones, then we do not need
+	 * any zone resource limits.
+	 */
+	if (!zc.target_nr_seq_zones)
+		return 0;
+
+	/*
+	 * If the target does not map all sequential zones, the limits
+	 * will not be reliable.
+	 */
+	if (zc.target_nr_seq_zones < zc.total_nr_seq_zones)
+		zlim->reliable_limits = false;
+
+	/*
+	 * If the target maps less sequential zones than the limit values, then
+	 * we do not have limits for this target.
+	 */
+	max_active_zones = disk->queue->limits.max_active_zones;
+	if (max_active_zones >= zc.target_nr_seq_zones)
+		max_active_zones = 0;
+	zlim->lim->max_active_zones =
+		min_not_zero(max_active_zones, zlim->lim->max_active_zones);
+
+	max_open_zones = disk->queue->limits.max_open_zones;
+	if (max_open_zones >= zc.target_nr_seq_zones)
+		max_open_zones = 0;
+	zlim->lim->max_open_zones =
+		min_not_zero(max_open_zones, zlim->lim->max_open_zones);
+
+	/*
+	 * Also count the total number of sequential zones for the mapped
+	 * device so that when we are done inspecting all its targets, we are
+	 * able to check if the mapped device actually has any sequential zones.
+	 */
+	zlim->mapped_nr_seq_zones += zc.target_nr_seq_zones;
+
+	return 0;
+}
+
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 		struct queue_limits *lim)
 {
 	struct mapped_device *md = t->md;
 	struct gendisk *disk = md->disk;
-	unsigned int nr_conv_zones = 0;
-	int ret;
+	struct dm_zone_resource_limits zlim = {
+		.reliable_limits = true,
+		.lim = lim,
+	};
 
 	/*
 	 * Check if zone append is natively supported, and if not, set the
@@ -240,46 +345,54 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 		lim->max_zone_append_sectors = 0;
 	}
 
-	if (!get_capacity(md->disk))
-		return 0;
-
 	/*
-	 * Count conventional zones to check that the mapped device will indeed 
-	 * have sequential write required zones.
+	 * Determine the max open and max active zone limits for the mapped
+	 * device by inspecting the zone resource limits and the zones mapped
+	 * by each target.
 	 */
-	md->zone_revalidate_map = t;
-	ret = dm_blk_report_zones(disk, 0, UINT_MAX,
-				  dm_check_zoned_cb, &nr_conv_zones);
-	md->zone_revalidate_map = NULL;
-	if (ret < 0) {
-		DMERR("Check zoned failed %d", ret);
-		return ret;
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (!ti->type->iterate_devices ||
+		    ti->type->iterate_devices(ti,
+				device_get_zone_resource_limits, &zlim)) {
+			DMERR("Could not determine %s zone resource limits",
+			      disk->disk_name);
+			return -ENODEV;
+		}
 	}
 
 	/*
-	 * If we only have conventional zones, expose the mapped device as
-	 * a regular device.
+	 * If we only have conventional zones mapped, expose the mapped device
+	 + as a regular device.
 	 */
-	if (nr_conv_zones >= ret) {
+	if (!zlim.mapped_nr_seq_zones) {
 		lim->max_open_zones = 0;
 		lim->max_active_zones = 0;
+		lim->max_zone_append_sectors = 0;
+		lim->zone_write_granularity = 0;
+		lim->chunk_sectors = 0;
 		lim->zoned = false;
 		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
+		md->nr_zones = 0;
 		disk->nr_zones = 0;
 		return 0;
 	}
 
-	if (!md->disk->nr_zones) {
-		DMINFO("%s using %s zone append",
-		       md->disk->disk_name,
-		       queue_emulates_zone_append(q) ? "emulated" : "native");
-	}
-
-	ret = dm_revalidate_zones(md, t);
-	if (ret < 0)
-		return ret;
+	/*
+	 * Warn once (when the capacity is not yet set) if the mapped device is
+	 * partially using zone resources of the target devices as that leads to
+	 * unreliable limits, i.e. if another mapped device uses the same
+	 * underlying devices, we cannot enforce zone limits to guarantee that
+	 * writing will not lead to errors. Note that we really should return
+	 * an error for such case but there is no easy way to find out if
+	 * another mapped device uses the same underlying zoned devices.
+	 */
+	if (!get_capacity(disk) && !zlim.reliable_limits)
+		DMWARN("%s zone resource limits may be unreliable",
+		       disk->disk_name);
 
-	if (!static_key_enabled(&zoned_enabled.key))
+	if (lim->zoned && !static_key_enabled(&zoned_enabled.key))
 		static_branch_enable(&zoned_enabled);
 	return 0;
 }

drivers/md/dm.h

@@ -103,6 +103,7 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
  */
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
 		struct queue_limits *lim);
+int dm_revalidate_zones(struct dm_table *t, struct request_queue *q);
 void dm_zone_endio(struct dm_io *io, struct bio *clone);
 #ifdef CONFIG_BLK_DEV_ZONED
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,