1 files changed, 289 insertions, 170 deletions

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 41a8cdce5d..3779e76a15 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1282,21 +1282,284 @@ out:
 	return ret;
 }
 
+struct zone_info {
+	u64 physical;
+	u64 capacity;
+	u64 alloc_offset;
+};
+
+static int btrfs_load_zone_info(struct btrfs_fs_info *fs_info, int zone_idx,
+				struct zone_info *info, unsigned long *active,
+				struct map_lookup *map)
+{
+	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
+	struct btrfs_device *device = map->stripes[zone_idx].dev;
+	int dev_replace_is_ongoing = 0;
+	unsigned int nofs_flag;
+	struct blk_zone zone;
+	int ret;
+
+	info->physical = map->stripes[zone_idx].physical;
+
+	if (!device->bdev) {
+		info->alloc_offset = WP_MISSING_DEV;
+		return 0;
+	}
+
+	/* Consider a zone as active if we can allow any number of active zones. */
+	if (!device->zone_info->max_active_zones)
+		__set_bit(zone_idx, active);
+
+	if (!btrfs_dev_is_sequential(device, info->physical)) {
+		info->alloc_offset = WP_CONVENTIONAL;
+		return 0;
+	}
+
+	/* This zone will be used for allocation, so mark this zone non-empty. */
+	btrfs_dev_clear_zone_empty(device, info->physical);
+
+	down_read(&dev_replace->rwsem);
+	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
+	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
+		btrfs_dev_clear_zone_empty(dev_replace->tgtdev, info->physical);
+	up_read(&dev_replace->rwsem);
+
+	/*
+	 * The group is mapped to a sequential zone. Get the zone write pointer
+	 * to determine the allocation offset within the zone.
+	 */
+	WARN_ON(!IS_ALIGNED(info->physical, fs_info->zone_size));
+	nofs_flag = memalloc_nofs_save();
+	ret = btrfs_get_dev_zone(device, info->physical, &zone);
+	memalloc_nofs_restore(nofs_flag);
+	if (ret) {
+		if (ret != -EIO && ret != -EOPNOTSUPP)
+			return ret;
+		info->alloc_offset = WP_MISSING_DEV;
+		return 0;
+	}
+
+	if (zone.type == BLK_ZONE_TYPE_CONVENTIONAL) {
+		btrfs_err_in_rcu(fs_info,
+		"zoned: unexpected conventional zone %llu on device %s (devid %llu)",
+			zone.start << SECTOR_SHIFT, rcu_str_deref(device->name),
+			device->devid);
+		return -EIO;
+	}
+
+	info->capacity = (zone.capacity << SECTOR_SHIFT);
+
+	switch (zone.cond) {
+	case BLK_ZONE_COND_OFFLINE:
+	case BLK_ZONE_COND_READONLY:
+		btrfs_err(fs_info,
+		"zoned: offline/readonly zone %llu on device %s (devid %llu)",
+			  (info->physical >> device->zone_info->zone_size_shift),
+			  rcu_str_deref(device->name), device->devid);
+		info->alloc_offset = WP_MISSING_DEV;
+		break;
+	case BLK_ZONE_COND_EMPTY:
+		info->alloc_offset = 0;
+		break;
+	case BLK_ZONE_COND_FULL:
+		info->alloc_offset = info->capacity;
+		break;
+	default:
+		/* Partially used zone. */
+		info->alloc_offset = ((zone.wp - zone.start) << SECTOR_SHIFT);
+		__set_bit(zone_idx, active);
+		break;
+	}
+
+	return 0;
+}
+
+static int btrfs_load_block_group_single(struct btrfs_block_group *bg,
+					 struct zone_info *info,
+					 unsigned long *active)
+{
+	if (info->alloc_offset == WP_MISSING_DEV) {
+		btrfs_err(bg->fs_info,
+			"zoned: cannot recover write pointer for zone %llu",
+			info->physical);
+		return -EIO;
+	}
+
+	bg->alloc_offset = info->alloc_offset;
+	bg->zone_capacity = info->capacity;
+	if (test_bit(0, active))
+		set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
+	return 0;
+}
+
+static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
+				      struct map_lookup *map,
+				      struct zone_info *zone_info,
+				      unsigned long *active)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+
+	if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) {
+		btrfs_err(fs_info, "zoned: data DUP profile needs raid-stripe-tree");
+		return -EINVAL;
+	}
+
+	if (zone_info[0].alloc_offset == WP_MISSING_DEV) {
+		btrfs_err(bg->fs_info,
+			  "zoned: cannot recover write pointer for zone %llu",
+			  zone_info[0].physical);
+		return -EIO;
+	}
+	if (zone_info[1].alloc_offset == WP_MISSING_DEV) {
+		btrfs_err(bg->fs_info,
+			  "zoned: cannot recover write pointer for zone %llu",
+			  zone_info[1].physical);
+		return -EIO;
+	}
+	if (zone_info[0].alloc_offset != zone_info[1].alloc_offset) {
+		btrfs_err(bg->fs_info,
+			  "zoned: write pointer offset mismatch of zones in DUP profile");
+		return -EIO;
+	}
+
+	if (test_bit(0, active) != test_bit(1, active)) {
+		if (!btrfs_zone_activate(bg))
+			return -EIO;
+	} else if (test_bit(0, active)) {
+		set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
+	}
+
+	bg->alloc_offset = zone_info[0].alloc_offset;
+	bg->zone_capacity = min(zone_info[0].capacity, zone_info[1].capacity);
+	return 0;
+}
+
+static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
+					struct map_lookup *map,
+					struct zone_info *zone_info,
+					unsigned long *active)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+	int i;
+
+	if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) {
+		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
+			  btrfs_bg_type_to_raid_name(map->type));
+		return -EINVAL;
+	}
+
+	for (i = 0; i < map->num_stripes; i++) {
+		if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
+		    zone_info[i].alloc_offset == WP_CONVENTIONAL)
+			continue;
+
+		if ((zone_info[0].alloc_offset != zone_info[i].alloc_offset) &&
+		    !btrfs_test_opt(fs_info, DEGRADED)) {
+			btrfs_err(fs_info,
+			"zoned: write pointer offset mismatch of zones in %s profile",
+				  btrfs_bg_type_to_raid_name(map->type));
+			return -EIO;
+		}
+		if (test_bit(0, active) != test_bit(i, active)) {
+			if (!btrfs_test_opt(fs_info, DEGRADED) &&
+			    !btrfs_zone_activate(bg)) {
+				return -EIO;
+			}
+		} else {
+			if (test_bit(0, active))
+				set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
+		}
+		/* In case a device is missing we have a cap of 0, so don't use it. */
+		bg->zone_capacity = min_not_zero(zone_info[0].capacity,
+						 zone_info[1].capacity);
+	}
+
+	if (zone_info[0].alloc_offset != WP_MISSING_DEV)
+		bg->alloc_offset = zone_info[0].alloc_offset;
+	else
+		bg->alloc_offset = zone_info[i - 1].alloc_offset;
+
+	return 0;
+}
+
+static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
+					struct map_lookup *map,
+					struct zone_info *zone_info,
+					unsigned long *active)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+
+	if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) {
+		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
+			  btrfs_bg_type_to_raid_name(map->type));
+		return -EINVAL;
+	}
+
+	for (int i = 0; i < map->num_stripes; i++) {
+		if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
+		    zone_info[i].alloc_offset == WP_CONVENTIONAL)
+			continue;
+
+		if (test_bit(0, active) != test_bit(i, active)) {
+			if (!btrfs_zone_activate(bg))
+				return -EIO;
+		} else {
+			if (test_bit(0, active))
+				set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
+		}
+		bg->zone_capacity += zone_info[i].capacity;
+		bg->alloc_offset += zone_info[i].alloc_offset;
+	}
+
+	return 0;
+}
+
+static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
+					 struct map_lookup *map,
+					 struct zone_info *zone_info,
+					 unsigned long *active)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+
+	if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) {
+		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
+			  btrfs_bg_type_to_raid_name(map->type));
+		return -EINVAL;
+	}
+
+	for (int i = 0; i < map->num_stripes; i++) {
+		if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
+		    zone_info[i].alloc_offset == WP_CONVENTIONAL)
+			continue;
+
+		if (test_bit(0, active) != test_bit(i, active)) {
+			if (!btrfs_zone_activate(bg))
+				return -EIO;
+		} else {
+			if (test_bit(0, active))
+				set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
+		}
+
+		if ((i % map->sub_stripes) == 0) {
+			bg->zone_capacity += zone_info[i].capacity;
+			bg->alloc_offset += zone_info[i].alloc_offset;
+		}
+	}
+
+	return 0;
+}
+
 int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
 	struct extent_map *em;
 	struct map_lookup *map;
-	struct btrfs_device *device;
 	u64 logical = cache->start;
 	u64 length = cache->length;
+	struct zone_info *zone_info = NULL;
 	int ret;
 	int i;
-	unsigned int nofs_flag;
-	u64 *alloc_offsets = NULL;
-	u64 *caps = NULL;
-	u64 *physical = NULL;
 	unsigned long *active = NULL;
 	u64 last_alloc = 0;
 	u32 num_sequential = 0, num_conventional = 0;
@@ -1328,20 +1591,8 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		goto out;
 	}
 
-	alloc_offsets = kcalloc(map->num_stripes, sizeof(*alloc_offsets), GFP_NOFS);
-	if (!alloc_offsets) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	caps = kcalloc(map->num_stripes, sizeof(*caps), GFP_NOFS);
-	if (!caps) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	physical = kcalloc(map->num_stripes, sizeof(*physical), GFP_NOFS);
-	if (!physical) {
+	zone_info = kcalloc(map->num_stripes, sizeof(*zone_info), GFP_NOFS);
+	if (!zone_info) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -1353,98 +1604,14 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 
 	for (i = 0; i < map->num_stripes; i++) {
-		bool is_sequential;
-		struct blk_zone zone;
-		struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
-		int dev_replace_is_ongoing = 0;
-
-		device = map->stripes[i].dev;
-		physical[i] = map->stripes[i].physical;
-
-		if (device->bdev == NULL) {
-			alloc_offsets[i] = WP_MISSING_DEV;
-			continue;
-		}
-
-		is_sequential = btrfs_dev_is_sequential(device, physical[i]);
-		if (is_sequential)
-			num_sequential++;
-		else
-			num_conventional++;
-
-		/*
-		 * Consider a zone as active if we can allow any number of
-		 * active zones.
-		 */
-		if (!device->zone_info->max_active_zones)
-			__set_bit(i, active);
-
-		if (!is_sequential) {
-			alloc_offsets[i] = WP_CONVENTIONAL;
-			continue;
-		}
-
-		/*
-		 * This zone will be used for allocation, so mark this zone
-		 * non-empty.
-		 */
-		btrfs_dev_clear_zone_empty(device, physical[i]);
-
-		down_read(&dev_replace->rwsem);
-		dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
-		if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
-			btrfs_dev_clear_zone_empty(dev_replace->tgtdev, physical[i]);
-		up_read(&dev_replace->rwsem);
-
-		/*
-		 * The group is mapped to a sequential zone. Get the zone write
-		 * pointer to determine the allocation offset within the zone.
-		 */
-		WARN_ON(!IS_ALIGNED(physical[i], fs_info->zone_size));
-		nofs_flag = memalloc_nofs_save();
-		ret = btrfs_get_dev_zone(device, physical[i], &zone);
-		memalloc_nofs_restore(nofs_flag);
-		if (ret == -EIO || ret == -EOPNOTSUPP) {
-			ret = 0;
-			alloc_offsets[i] = WP_MISSING_DEV;
-			continue;
-		} else if (ret) {
-			goto out;
-		}
-
-		if (zone.type == BLK_ZONE_TYPE_CONVENTIONAL) {
-			btrfs_err_in_rcu(fs_info,
-	"zoned: unexpected conventional zone %llu on device %s (devid %llu)",
-				zone.start << SECTOR_SHIFT,
-				rcu_str_deref(device->name), device->devid);
-			ret = -EIO;
+		ret = btrfs_load_zone_info(fs_info, i, &zone_info[i], active, map);
+		if (ret)
 			goto out;
-		}
 
-		caps[i] = (zone.capacity << SECTOR_SHIFT);
-
-		switch (zone.cond) {
-		case BLK_ZONE_COND_OFFLINE:
-		case BLK_ZONE_COND_READONLY:
-			btrfs_err(fs_info,
-		"zoned: offline/readonly zone %llu on device %s (devid %llu)",
-				  physical[i] >> device->zone_info->zone_size_shift,
-				  rcu_str_deref(device->name), device->devid);
-			alloc_offsets[i] = WP_MISSING_DEV;
-			break;
-		case BLK_ZONE_COND_EMPTY:
-			alloc_offsets[i] = 0;
-			break;
-		case BLK_ZONE_COND_FULL:
-			alloc_offsets[i] = caps[i];
-			break;
-		default:
-			/* Partially used zone */
-			alloc_offsets[i] =
-					((zone.wp - zone.start) << SECTOR_SHIFT);
-			__set_bit(i, active);
-			break;
-		}
+		if (zone_info[i].alloc_offset == WP_CONVENTIONAL)
+			num_conventional++;
+		else
+			num_sequential++;
 	}
 
 	if (num_sequential > 0)
@@ -1468,63 +1635,24 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 
 	switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
 	case 0: /* single */
-		if (alloc_offsets[0] == WP_MISSING_DEV) {
-			btrfs_err(fs_info,
-			"zoned: cannot recover write pointer for zone %llu",
-				physical[0]);
-			ret = -EIO;
-			goto out;
-		}
-		cache->alloc_offset = alloc_offsets[0];
-		cache->zone_capacity = caps[0];
-		if (test_bit(0, active))
-			set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &cache->runtime_flags);
+		ret = btrfs_load_block_group_single(cache, &zone_info[0], active);
 		break;
 	case BTRFS_BLOCK_GROUP_DUP:
-		if (map->type & BTRFS_BLOCK_GROUP_DATA) {
-			btrfs_err(fs_info, "zoned: profile DUP not yet supported on data bg");
-			ret = -EINVAL;
-			goto out;
-		}
-		if (alloc_offsets[0] == WP_MISSING_DEV) {
-			btrfs_err(fs_info,
-			"zoned: cannot recover write pointer for zone %llu",
-				physical[0]);
-			ret = -EIO;
-			goto out;
-		}
-		if (alloc_offsets[1] == WP_MISSING_DEV) {
-			btrfs_err(fs_info,
-			"zoned: cannot recover write pointer for zone %llu",
-				physical[1]);
-			ret = -EIO;
-			goto out;
-		}
-		if (alloc_offsets[0] != alloc_offsets[1]) {
-			btrfs_err(fs_info,
-			"zoned: write pointer offset mismatch of zones in DUP profile");
-			ret = -EIO;
-			goto out;
-		}
-		if (test_bit(0, active) != test_bit(1, active)) {
-			if (!btrfs_zone_activate(cache)) {
-				ret = -EIO;
-				goto out;
-			}
-		} else {
-			if (test_bit(0, active))
-				set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE,
-					&cache->runtime_flags);
-		}
-		cache->alloc_offset = alloc_offsets[0];
-		cache->zone_capacity = min(caps[0], caps[1]);
+		ret = btrfs_load_block_group_dup(cache, map, zone_info, active);
 		break;
 	case BTRFS_BLOCK_GROUP_RAID1:
+	case BTRFS_BLOCK_GROUP_RAID1C3:
+	case BTRFS_BLOCK_GROUP_RAID1C4:
+		ret = btrfs_load_block_group_raid1(cache, map, zone_info, active);
+		break;
 	case BTRFS_BLOCK_GROUP_RAID0:
+		ret = btrfs_load_block_group_raid0(cache, map, zone_info, active);
+		break;
 	case BTRFS_BLOCK_GROUP_RAID10:
+		ret = btrfs_load_block_group_raid10(cache, map, zone_info, active);
+		break;
 	case BTRFS_BLOCK_GROUP_RAID5:
 	case BTRFS_BLOCK_GROUP_RAID6:
-		/* non-single profiles are not supported yet */
 	default:
 		btrfs_err(fs_info, "zoned: profile %s not yet supported",
 			  btrfs_bg_type_to_raid_name(map->type));
@@ -1533,13 +1661,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 
 out:
-	if (cache->alloc_offset > fs_info->zone_size) {
-		btrfs_err(fs_info,
-			"zoned: invalid write pointer %llu in block group %llu",
-			cache->alloc_offset, cache->start);
-		ret = -EIO;
-	}
-
 	if (cache->alloc_offset > cache->zone_capacity) {
 		btrfs_err(fs_info,
 "zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu",
@@ -1570,9 +1691,7 @@ out:
 		cache->physical_map = NULL;
 	}
 	bitmap_free(active);
-	kfree(physical);
-	kfree(caps);
-	kfree(alloc_offsets);
+	kfree(zone_info);
 	free_extent_map(em);
 
 	return ret;
@@ -1609,7 +1728,7 @@ void btrfs_redirty_list_add(struct btrfs_transaction *trans,
 	set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
 	set_extent_buffer_dirty(eb);
 	set_extent_bit(&trans->dirty_pages, eb->start, eb->start + eb->len - 1,
-			EXTENT_DIRTY | EXTENT_NOWAIT, NULL);
+			EXTENT_DIRTY, NULL);
 }
 
 bool btrfs_use_zone_append(struct btrfs_bio *bbio)
@@ -1887,7 +2006,7 @@ static int read_zone_info(struct btrfs_fs_info *fs_info, u64 logical,
 	int i, ret;
 
 	ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
-			      &mapped_length, &bioc, NULL, NULL, 1);
+			      &mapped_length, &bioc, NULL, NULL);
 	if (ret || !bioc || mapped_length < PAGE_SIZE) {
 		ret = -EIO;
 		goto out_put_bioc;