1 files changed, 256 insertions, 202 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index c0f1d6818df7..5064be59dac5 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -15,6 +15,7 @@
 #include "delalloc-space.h"
 #include "discard.h"
 #include "raid56.h"
+#include "zoned.h"
 
 /*
  * Return target flags in extended format or 0 if restripe for this chunk_type
@@ -424,6 +425,23 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
 	return ret;
 }
 
+static bool space_cache_v1_done(struct btrfs_block_group *cache)
+{
+	bool ret;
+
+	spin_lock(&cache->lock);
+	ret = cache->cached != BTRFS_CACHE_FAST;
+	spin_unlock(&cache->lock);
+
+	return ret;
+}
+
+void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache,
+				struct btrfs_caching_control *caching_ctl)
+{
+	wait_event(caching_ctl->wait, space_cache_v1_done(cache));
+}
+
 #ifdef CONFIG_BTRFS_DEBUG
 static void fragment_free_space(struct btrfs_block_group *block_group)
 {
@@ -639,11 +657,36 @@ static noinline void caching_thread(struct btrfs_work *work)
 	mutex_lock(&caching_ctl->mutex);
 	down_read(&fs_info->commit_root_sem);
 
-	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+	if (btrfs_test_opt(fs_info, SPACE_CACHE)) {
+		ret = load_free_space_cache(block_group);
+		if (ret == 1) {
+			ret = 0;
+			goto done;
+		}
+
+		/*
+		 * We failed to load the space cache, set ourselves to
+		 * CACHE_STARTED and carry on.
+		 */
+		spin_lock(&block_group->lock);
+		block_group->cached = BTRFS_CACHE_STARTED;
+		spin_unlock(&block_group->lock);
+		wake_up(&caching_ctl->wait);
+	}
+
+	/*
+	 * If we are in the transaction that populated the free space tree we
+	 * can't actually cache from the free space tree as our commit root and
+	 * real root are the same, so we could change the contents of the blocks
+	 * while caching.  Instead do the slow caching in this case, and after
+	 * the transaction has committed we will be safe.
+	 */
+	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
+	    !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags)))
 		ret = load_free_space_tree(caching_ctl);
 	else
 		ret = load_extent_tree_free(caching_ctl);
-
+done:
 	spin_lock(&block_group->lock);
 	block_group->caching_ctl = NULL;
 	block_group->cached = ret ? BTRFS_CACHE_ERROR : BTRFS_CACHE_FINISHED;
@@ -679,9 +722,13 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 {
 	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
-	struct btrfs_caching_control *caching_ctl;
+	struct btrfs_caching_control *caching_ctl = NULL;
 	int ret = 0;
 
+	/* Allocator for zoned filesystems does not use the cache at all */
+	if (btrfs_is_zoned(fs_info))
+		return 0;
+
 	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
 	if (!caching_ctl)
 		return -ENOMEM;
@@ -691,119 +738,41 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 	init_waitqueue_head(&caching_ctl->wait);
 	caching_ctl->block_group = cache;
 	caching_ctl->progress = cache->start;
-	refcount_set(&caching_ctl->count, 1);
+	refcount_set(&caching_ctl->count, 2);
 	btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
 
 	spin_lock(&cache->lock);
-	/*
-	 * This should be a rare occasion, but this could happen I think in the
-	 * case where one thread starts to load the space cache info, and then
-	 * some other thread starts a transaction commit which tries to do an
-	 * allocation while the other thread is still loading the space cache
-	 * info.  The previous loop should have kept us from choosing this block
-	 * group, but if we've moved to the state where we will wait on caching
-	 * block groups we need to first check if we're doing a fast load here,
-	 * so we can wait for it to finish, otherwise we could end up allocating
-	 * from a block group who's cache gets evicted for one reason or
-	 * another.
-	 */
-	while (cache->cached == BTRFS_CACHE_FAST) {
-		struct btrfs_caching_control *ctl;
-
-		ctl = cache->caching_ctl;
-		refcount_inc(&ctl->count);
-		prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
-		spin_unlock(&cache->lock);
-
-		schedule();
-
-		finish_wait(&ctl->wait, &wait);
-		btrfs_put_caching_control(ctl);
-		spin_lock(&cache->lock);
-	}
-
 	if (cache->cached != BTRFS_CACHE_NO) {
-		spin_unlock(&cache->lock);
 		kfree(caching_ctl);
-		return 0;
+
+		caching_ctl = cache->caching_ctl;
+		if (caching_ctl)
+			refcount_inc(&caching_ctl->count);
+		spin_unlock(&cache->lock);
+		goto out;
 	}
 	WARN_ON(cache->caching_ctl);
 	cache->caching_ctl = caching_ctl;
-	cache->cached = BTRFS_CACHE_FAST;
+	if (btrfs_test_opt(fs_info, SPACE_CACHE))
+		cache->cached = BTRFS_CACHE_FAST;
+	else
+		cache->cached = BTRFS_CACHE_STARTED;
+	cache->has_caching_ctl = 1;
 	spin_unlock(&cache->lock);
 
-	if (btrfs_test_opt(fs_info, SPACE_CACHE)) {
-		mutex_lock(&caching_ctl->mutex);
-		ret = load_free_space_cache(cache);
-
-		spin_lock(&cache->lock);
-		if (ret == 1) {
-			cache->caching_ctl = NULL;
-			cache->cached = BTRFS_CACHE_FINISHED;
-			cache->last_byte_to_unpin = (u64)-1;
-			caching_ctl->progress = (u64)-1;
-		} else {
-			if (load_cache_only) {
-				cache->caching_ctl = NULL;
-				cache->cached = BTRFS_CACHE_NO;
-			} else {
-				cache->cached = BTRFS_CACHE_STARTED;
-				cache->has_caching_ctl = 1;
-			}
-		}
-		spin_unlock(&cache->lock);
-#ifdef CONFIG_BTRFS_DEBUG
-		if (ret == 1 &&
-		    btrfs_should_fragment_free_space(cache)) {
-			u64 bytes_used;
-
-			spin_lock(&cache->space_info->lock);
-			spin_lock(&cache->lock);
-			bytes_used = cache->length - cache->used;
-			cache->space_info->bytes_used += bytes_used >> 1;
-			spin_unlock(&cache->lock);
-			spin_unlock(&cache->space_info->lock);
-			fragment_free_space(cache);
-		}
-#endif
-		mutex_unlock(&caching_ctl->mutex);
-
-		wake_up(&caching_ctl->wait);
-		if (ret == 1) {
-			btrfs_put_caching_control(caching_ctl);
-			btrfs_free_excluded_extents(cache);
-			return 0;
-		}
-	} else {
-		/*
-		 * We're either using the free space tree or no caching at all.
-		 * Set cached to the appropriate value and wakeup any waiters.
-		 */
-		spin_lock(&cache->lock);
-		if (load_cache_only) {
-			cache->caching_ctl = NULL;
-			cache->cached = BTRFS_CACHE_NO;
-		} else {
-			cache->cached = BTRFS_CACHE_STARTED;
-			cache->has_caching_ctl = 1;
-		}
-		spin_unlock(&cache->lock);
-		wake_up(&caching_ctl->wait);
-	}
-
-	if (load_cache_only) {
-		btrfs_put_caching_control(caching_ctl);
-		return 0;
-	}
-
-	down_write(&fs_info->commit_root_sem);
+	spin_lock(&fs_info->block_group_cache_lock);
 	refcount_inc(&caching_ctl->count);
 	list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
-	up_write(&fs_info->commit_root_sem);
+	spin_unlock(&fs_info->block_group_cache_lock);
 
 	btrfs_get_block_group(cache);
 
 	btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);
+out:
+	if (load_cache_only && caching_ctl)
+		btrfs_wait_space_cache_v1_finished(cache, caching_ctl);
+	if (caching_ctl)
+		btrfs_put_caching_control(caching_ctl);
 
 	return ret;
 }
@@ -892,8 +861,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	struct btrfs_block_group *block_group;
 	struct btrfs_free_cluster *cluster;
-	struct btrfs_root *tree_root = fs_info->tree_root;
-	struct btrfs_key key;
 	struct inode *inode;
 	struct kobject *kobj = NULL;
 	int ret;
@@ -934,6 +901,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	btrfs_return_cluster_to_free_space(block_group, cluster);
 	spin_unlock(&cluster->refill_lock);
 
+	btrfs_clear_treelog_bg(block_group);
+
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
@@ -971,42 +940,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	spin_unlock(&trans->transaction->dirty_bgs_lock);
 	mutex_unlock(&trans->transaction->cache_write_mutex);
 
-	if (!IS_ERR(inode)) {
-		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
-		if (ret) {
-			btrfs_add_delayed_iput(inode);
-			goto out;
-		}
-		clear_nlink(inode);
-		/* One for the block groups ref */
-		spin_lock(&block_group->lock);
-		if (block_group->iref) {
-			block_group->iref = 0;
-			block_group->inode = NULL;
-			spin_unlock(&block_group->lock);
-			iput(inode);
-		} else {
-			spin_unlock(&block_group->lock);
-		}
-		/* One for our lookup ref */
-		btrfs_add_delayed_iput(inode);
-	}
-
-	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.type = 0;
-	key.offset = block_group->start;
-
-	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	if (ret < 0)
+	ret = btrfs_remove_free_space_inode(trans, inode, block_group);
+	if (ret)
 		goto out;
-	if (ret > 0)
-		btrfs_release_path(path);
-	if (ret == 0) {
-		ret = btrfs_del_item(trans, tree_root, path);
-		if (ret)
-			goto out;
-		btrfs_release_path(path);
-	}
 
 	spin_lock(&fs_info->block_group_cache_lock);
 	rb_erase(&block_group->cache_node,
@@ -1043,7 +979,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	if (block_group->cached == BTRFS_CACHE_STARTED)
 		btrfs_wait_block_group_cache_done(block_group);
 	if (block_group->has_caching_ctl) {
-		down_write(&fs_info->commit_root_sem);
+		spin_lock(&fs_info->block_group_cache_lock);
 		if (!caching_ctl) {
 			struct btrfs_caching_control *ctl;
 
@@ -1057,7 +993,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		}
 		if (caching_ctl)
 			list_del_init(&caching_ctl->list);
-		up_write(&fs_info->commit_root_sem);
+		spin_unlock(&fs_info->block_group_cache_lock);
 		if (caching_ctl) {
 			/* Once for the caching bgs list and once for us. */
 			btrfs_put_caching_control(caching_ctl);
@@ -1079,12 +1015,17 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		WARN_ON(block_group->space_info->total_bytes
 			< block_group->length);
 		WARN_ON(block_group->space_info->bytes_readonly
-			< block_group->length);
+			< block_group->length - block_group->zone_unusable);
+		WARN_ON(block_group->space_info->bytes_zone_unusable
+			< block_group->zone_unusable);
 		WARN_ON(block_group->space_info->disk_total
 			< block_group->length * factor);
 	}
 	block_group->space_info->total_bytes -= block_group->length;
-	block_group->space_info->bytes_readonly -= block_group->length;
+	block_group->space_info->bytes_readonly -=
+		(block_group->length - block_group->zone_unusable);
+	block_group->space_info->bytes_zone_unusable -=
+		block_group->zone_unusable;
 	block_group->space_info->disk_total -= block_group->length * factor;
 
 	spin_unlock(&block_group->space_info->lock);
@@ -1228,7 +1169,7 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 	}
 
 	num_bytes = cache->length - cache->reserved - cache->pinned -
-		    cache->bytes_super - cache->used;
+		    cache->bytes_super - cache->zone_unusable - cache->used;
 
 	/*
 	 * Data never overcommits, even in mixed mode, so do just the straight
@@ -1259,6 +1200,12 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 
 	if (!ret) {
 		sinfo->bytes_readonly += num_bytes;
+		if (btrfs_is_zoned(cache->fs_info)) {
+			/* Migrate zone_unusable bytes to readonly */
+			sinfo->bytes_readonly += cache->zone_unusable;
+			sinfo->bytes_zone_unusable -= cache->zone_unusable;
+			cache->zone_unusable = 0;
+		}
 		cache->ro++;
 		list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
 	}
@@ -1333,6 +1280,13 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 	if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
 		return;
 
+	/*
+	 * Long running balances can keep us blocked here for eternity, so
+	 * simply skip deletion if we're unable to get the mutex.
+	 */
+	if (!mutex_trylock(&fs_info->delete_unused_bgs_mutex))
+		return;
+
 	spin_lock(&fs_info->unused_bgs_lock);
 	while (!list_empty(&fs_info->unused_bgs)) {
 		int trimming;
@@ -1352,8 +1306,6 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 
 		btrfs_discard_cancel_work(&fs_info->discard_ctl, block_group);
 
-		mutex_lock(&fs_info->delete_unused_bgs_mutex);
-
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 
@@ -1442,9 +1394,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		btrfs_space_info_update_bytes_pinned(fs_info, space_info,
 						     -block_group->pinned);
 		space_info->bytes_readonly += block_group->pinned;
-		percpu_counter_add_batch(&space_info->total_bytes_pinned,
-				   -block_group->pinned,
-				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
+		__btrfs_mod_total_bytes_pinned(space_info, -block_group->pinned);
 		block_group->pinned = 0;
 
 		spin_unlock(&block_group->lock);
@@ -1460,8 +1410,12 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		if (!async_trim_enabled && btrfs_test_opt(fs_info, DISCARD_ASYNC))
 			goto flip_async;
 
-		/* DISCARD can flip during remount */
-		trimming = btrfs_test_opt(fs_info, DISCARD_SYNC);
+		/*
+		 * DISCARD can flip during remount. On zoned filesystems, we
+		 * need to reset sequential-required zones.
+		 */
+		trimming = btrfs_test_opt(fs_info, DISCARD_SYNC) ||
+				btrfs_is_zoned(fs_info);
 
 		/* Implicit trim during transaction commit. */
 		if (trimming)
@@ -1499,11 +1453,11 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 end_trans:
 		btrfs_end_transaction(trans);
 next:
-		mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 		btrfs_put_block_group(block_group);
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
 	spin_unlock(&fs_info->unused_bgs_lock);
+	mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 	return;
 
 flip_async:
@@ -1632,8 +1586,11 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 }
 
 /**
- * btrfs_rmap_block - Map a physical disk address to a list of logical addresses
+ * Map a physical disk address to a list of logical addresses
+ *
+ * @fs_info:       the filesystem
  * @chunk_start:   logical address of block group
+ * @bdev:	   physical device to resolve, can be NULL to indicate any device
  * @physical:	   physical address to map to logical addresses
  * @logical:	   return array of logical addresses which map to @physical
  * @naddrs:	   length of @logical
@@ -1643,9 +1600,9 @@ static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
  * Used primarily to exclude those portions of a block group that contain super
  * block copies.
  */
-EXPORT_FOR_TESTS
 int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
-		     u64 physical, u64 **logical, int *naddrs, int *stripe_len)
+		     struct block_device *bdev, u64 physical, u64 **logical,
+		     int *naddrs, int *stripe_len)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
@@ -1663,6 +1620,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 	map = em->map_lookup;
 	data_stripe_length = em->orig_block_len;
 	io_stripe_size = map->stripe_len;
+	chunk_start = em->start;
 
 	/* For RAID5/6 adjust to a full IO stripe length */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
@@ -1677,14 +1635,18 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 	for (i = 0; i < map->num_stripes; i++) {
 		bool already_inserted = false;
 		u64 stripe_nr;
+		u64 offset;
 		int j;
 
 		if (!in_range(physical, map->stripes[i].physical,
 			      data_stripe_length))
 			continue;
 
+		if (bdev && map->stripes[i].dev->bdev != bdev)
+			continue;
+
 		stripe_nr = physical - map->stripes[i].physical;
-		stripe_nr = div64_u64(stripe_nr, map->stripe_len);
+		stripe_nr = div64_u64_rem(stripe_nr, map->stripe_len, &offset);
 
 		if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
 			stripe_nr = stripe_nr * map->num_stripes + i;
@@ -1698,7 +1660,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 		 * instead of map->stripe_len
 		 */
 
-		bytenr = chunk_start + stripe_nr * io_stripe_size;
+		bytenr = chunk_start + stripe_nr * io_stripe_size + offset;
 
 		/* Ensure we don't add duplicate addresses */
 		for (j = 0; j < nr; j++) {
@@ -1723,6 +1685,7 @@ out:
 static int exclude_super_stripes(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
+	const bool zoned = btrfs_is_zoned(fs_info);
 	u64 bytenr;
 	u64 *logical;
 	int stripe_len;
@@ -1739,11 +1702,19 @@ static int exclude_super_stripes(struct btrfs_block_group *cache)
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
 		bytenr = btrfs_sb_offset(i);
-		ret = btrfs_rmap_block(fs_info, cache->start,
+		ret = btrfs_rmap_block(fs_info, cache->start, NULL,
 				       bytenr, &logical, &nr, &stripe_len);
 		if (ret)
 			return ret;
 
+		/* Shouldn't have super stripes in sequential zones */
+		if (zoned && nr) {
+			btrfs_err(fs_info,
+			"zoned: block group %llu must not contain super block",
+				  cache->start);
+			return -EUCLEAN;
+		}
+
 		while (nr--) {
 			u64 len = min_t(u64, stripe_len,
 				cache->start + cache->length - logical[nr]);
@@ -1805,7 +1776,7 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
 	INIT_LIST_HEAD(&cache->discard_list);
 	INIT_LIST_HEAD(&cache->dirty_list);
 	INIT_LIST_HEAD(&cache->io_list);
-	btrfs_init_free_space_ctl(cache);
+	btrfs_init_free_space_ctl(cache, cache->free_space_ctl);
 	atomic_set(&cache->frozen, 0);
 	mutex_init(&cache->free_space_lock);
 	btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root);
@@ -1867,24 +1838,8 @@ static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
 	return ret;
 }
 
-static void read_block_group_item(struct btrfs_block_group *cache,
-				 struct btrfs_path *path,
-				 const struct btrfs_key *key)
-{
-	struct extent_buffer *leaf = path->nodes[0];
-	struct btrfs_block_group_item bgi;
-	int slot = path->slots[0];
-
-	cache->length = key->offset;
-
-	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
-			   sizeof(bgi));
-	cache->used = btrfs_stack_block_group_used(&bgi);
-	cache->flags = btrfs_stack_block_group_flags(&bgi);
-}
-
 static int read_one_block_group(struct btrfs_fs_info *info,
-				struct btrfs_path *path,
+				struct btrfs_block_group_item *bgi,
 				const struct btrfs_key *key,
 				int need_clear)
 {
@@ -1899,7 +1854,9 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 	if (!cache)
 		return -ENOMEM;
 
-	read_block_group_item(cache, path, key);
+	cache->length = key->offset;
+	cache->used = btrfs_stack_block_group_used(bgi);
+	cache->flags = btrfs_stack_block_group_flags(bgi);
 
 	set_free_space_tree_thresholds(cache);
 
@@ -1926,6 +1883,13 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 			goto error;
 	}
 
+	ret = btrfs_load_block_group_zone_info(cache, false);
+	if (ret) {
+		btrfs_err(info, "zoned: failed to load zone info of bg %llu",
+			  cache->start);
+		goto error;
+	}
+
 	/*
 	 * We need to exclude the super stripes now so that the space info has
 	 * super bytes accounted for, otherwise we'll think we have more space
@@ -1939,12 +1903,20 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 	}
 
 	/*
-	 * Check for two cases, either we are full, and therefore don't need
-	 * to bother with the caching work since we won't find any space, or we
-	 * are empty, and we can just add all the space in and be done with it.
-	 * This saves us _a_lot_ of time, particularly in the full case.
+	 * For zoned filesystem, space after the allocation offset is the only
+	 * free space for a block group. So, we don't need any caching work.
+	 * btrfs_calc_zone_unusable() will set the amount of free space and
+	 * zone_unusable space.
+	 *
+	 * For regular filesystem, check for two cases, either we are full, and
+	 * therefore don't need to bother with the caching work since we won't
+	 * find any space, or we are empty, and we can just add all the space
+	 * in and be done with it.  This saves us _a_lot_ of time, particularly
+	 * in the full case.
 	 */
-	if (cache->length == cache->used) {
+	if (btrfs_is_zoned(info)) {
+		btrfs_calc_zone_unusable(cache);
+	} else if (cache->length == cache->used) {
 		cache->last_byte_to_unpin = (u64)-1;
 		cache->cached = BTRFS_CACHE_FINISHED;
 		btrfs_free_excluded_extents(cache);
@@ -1963,7 +1935,8 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 	}
 	trace_btrfs_add_block_group(info, cache, 0);
 	btrfs_update_space_info(info, cache->flags, cache->length,
-				cache->used, cache->bytes_super, &space_info);
+				cache->used, cache->bytes_super,
+				cache->zone_unusable, &space_info);
 
 	cache->space_info = space_info;
 
@@ -1985,6 +1958,51 @@ error:
 	return ret;
 }
 
+static int fill_dummy_bgs(struct btrfs_fs_info *fs_info)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
+	struct btrfs_space_info *space_info;
+	struct rb_node *node;
+	int ret = 0;
+
+	for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) {
+		struct extent_map *em;
+		struct map_lookup *map;
+		struct btrfs_block_group *bg;
+
+		em = rb_entry(node, struct extent_map, rb_node);
+		map = em->map_lookup;
+		bg = btrfs_create_block_group_cache(fs_info, em->start);
+		if (!bg) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		/* Fill dummy cache as FULL */
+		bg->length = em->len;
+		bg->flags = map->type;
+		bg->last_byte_to_unpin = (u64)-1;
+		bg->cached = BTRFS_CACHE_FINISHED;
+		bg->used = em->len;
+		bg->flags = map->type;
+		ret = btrfs_add_block_group_cache(fs_info, bg);
+		if (ret) {
+			btrfs_remove_free_space_cache(bg);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		btrfs_update_space_info(fs_info, bg->flags, em->len, em->len,
+					0, 0, &space_info);
+		bg->space_info = space_info;
+		link_block_group(bg);
+
+		set_avail_alloc_bits(fs_info, bg->flags);
+	}
+	if (!ret)
+		btrfs_init_global_block_rsv(fs_info);
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;
@@ -1995,6 +2013,9 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 	int need_clear = 0;
 	u64 cache_gen;
 
+	if (!info->extent_root)
+		return fill_dummy_bgs(info);
+
 	key.objectid = 0;
 	key.offset = 0;
 	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
@@ -2010,20 +2031,31 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		need_clear = 1;
 
 	while (1) {
+		struct btrfs_block_group_item bgi;
+		struct extent_buffer *leaf;
+		int slot;
+
 		ret = find_first_block_group(info, path, &key);
 		if (ret > 0)
 			break;
 		if (ret != 0)
 			goto error;
 
-		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-		ret = read_one_block_group(info, path, &key, need_clear);
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+
+		read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+				   sizeof(bgi));
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		btrfs_release_path(path);
+		ret = read_one_block_group(info, &bgi, &key, need_clear);
 		if (ret < 0)
 			goto error;
 		key.objectid += key.offset;
 		key.offset = 0;
-		btrfs_release_path(path);
 	}
+	btrfs_release_path(path);
 
 	list_for_each_entry(space_info, &info->space_info, list) {
 		int i;
@@ -2151,7 +2183,15 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 	cache->flags = type;
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
-	cache->needs_free_space = 1;
+	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+		cache->needs_free_space = 1;
+
+	ret = btrfs_load_block_group_zone_info(cache, true);
+	if (ret) {
+		btrfs_put_block_group(cache);
+		return ret;
+	}
+
 	ret = exclude_super_stripes(cache);
 	if (ret) {
 		/* We may have excluded something, so call this just in case */
@@ -2193,7 +2233,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 	 */
 	trace_btrfs_add_block_group(fs_info, cache, 1);
 	btrfs_update_space_info(fs_info, cache->flags, size, bytes_used,
-				cache->bytes_super, &cache->space_info);
+				cache->bytes_super, 0, &cache->space_info);
 	btrfs_update_global_block_rsv(fs_info);
 
 	link_block_group(cache);
@@ -2301,8 +2341,15 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
 	spin_lock(&cache->lock);
 	if (!--cache->ro) {
 		num_bytes = cache->length - cache->reserved -
-			    cache->pinned - cache->bytes_super - cache->used;
+			    cache->pinned - cache->bytes_super -
+			    cache->zone_unusable - cache->used;
 		sinfo->bytes_readonly -= num_bytes;
+		if (btrfs_is_zoned(cache->fs_info)) {
+			/* Migrate zone_unusable bytes back */
+			cache->zone_unusable = cache->alloc_offset - cache->used;
+			sinfo->bytes_zone_unusable += cache->zone_unusable;
+			sinfo->bytes_readonly -= cache->zone_unusable;
+		}
 		list_del_init(&cache->ro_list);
 	}
 	spin_unlock(&cache->lock);
@@ -2360,6 +2407,9 @@ static int cache_save_setup(struct btrfs_block_group *block_group,
 	int retries = 0;
 	int ret = 0;
 
+	if (!btrfs_test_opt(fs_info, SPACE_CACHE))
+		return 0;
+
 	/*
 	 * If this block group is smaller than 100 megs don't bother caching the
 	 * block group.
@@ -2400,7 +2450,7 @@ again:
 	 * time.
 	 */
 	BTRFS_I(inode)->generation = 0;
-	ret = btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 	if (ret) {
 		/*
 		 * So theoretically we could recover from this, simply set the
@@ -2573,8 +2623,10 @@ again:
 
 	if (!path) {
 		path = btrfs_alloc_path();
-		if (!path)
-			return -ENOMEM;
+		if (!path) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
 	/*
@@ -2668,16 +2720,14 @@ again:
 			btrfs_put_block_group(cache);
 		if (drop_reserve)
 			btrfs_delayed_refs_rsv_release(fs_info, 1);
-
-		if (ret)
-			break;
-
 		/*
 		 * Avoid blocking other tasks for too long. It might even save
 		 * us from writing caches for block groups that are going to be
 		 * removed.
 		 */
 		mutex_unlock(&trans->transaction->cache_write_mutex);
+		if (ret)
+			goto out;
 		mutex_lock(&trans->transaction->cache_write_mutex);
 	}
 	mutex_unlock(&trans->transaction->cache_write_mutex);
@@ -2686,7 +2736,8 @@ again:
 	 * Go through delayed refs for all the stuff we've just kicked off
 	 * and then loop back (just once)
 	 */
-	ret = btrfs_run_delayed_refs(trans, 0);
+	if (!ret)
+		ret = btrfs_run_delayed_refs(trans, 0);
 	if (!ret && loops == 0) {
 		loops++;
 		spin_lock(&cur_trans->dirty_bgs_lock);
@@ -2700,7 +2751,12 @@ again:
 			goto again;
 		}
 		spin_unlock(&cur_trans->dirty_bgs_lock);
-	} else if (ret < 0) {
+	}
+out:
+	if (ret < 0) {
+		spin_lock(&cur_trans->dirty_bgs_lock);
+		list_splice_init(&dirty, &cur_trans->dirty_bgs);
+		spin_unlock(&cur_trans->dirty_bgs_lock);
 		btrfs_cleanup_dirty_bgs(cur_trans, fs_info);
 	}
 
@@ -2904,10 +2960,8 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 			spin_unlock(&cache->lock);
 			spin_unlock(&cache->space_info->lock);
 
-			percpu_counter_add_batch(
-					&cache->space_info->total_bytes_pinned,
-					num_bytes,
-					BTRFS_TOTAL_BYTES_PINNED_BATCH);
+			__btrfs_mod_total_bytes_pinned(cache->space_info,
+						       num_bytes);
 			set_extent_dirty(&trans->transaction->pinned_extents,
 					 bytenr, bytenr + num_bytes - 1,
 					 GFP_NOFS | __GFP_NOFAIL);
@@ -3306,14 +3360,14 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	struct btrfs_caching_control *caching_ctl;
 	struct rb_node *n;
 
-	down_write(&info->commit_root_sem);
+	spin_lock(&info->block_group_cache_lock);
 	while (!list_empty(&info->caching_block_groups)) {
 		caching_ctl = list_entry(info->caching_block_groups.next,
 					 struct btrfs_caching_control, list);
 		list_del(&caching_ctl->list);
 		btrfs_put_caching_control(caching_ctl);
 	}
-	up_write(&info->commit_root_sem);
+	spin_unlock(&info->block_group_cache_lock);
 
 	spin_lock(&info->unused_bgs_lock);
 	while (!list_empty(&info->unused_bgs)) {