1 files changed, 169 insertions, 31 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 260f94b019c9..df2bb4b61a00 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2342,7 +2342,13 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		ins.type = BTRFS_EXTENT_ITEM_KEY;
 	}
 
-	BUG_ON(node->ref_mod != 1);
+	if (node->ref_mod != 1) {
+		btrfs_err(root->fs_info,
+	"btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
+			  node->bytenr, node->ref_mod, node->action, ref_root,
+			  parent);
+		return -EIO;
+	}
 	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
 		BUG_ON(!extent_op || !extent_op->update_flags);
 		ret = alloc_reserved_tree_block(trans, root,
@@ -4128,7 +4134,7 @@ commit_trans:
 				      data_sinfo->flags, bytes, 1);
 	spin_unlock(&data_sinfo->lock);
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -4392,6 +4398,7 @@ again:
 	if (wait_for_alloc) {
 		mutex_unlock(&fs_info->chunk_mutex);
 		wait_for_alloc = 0;
+		cond_resched();
 		goto again;
 	}
 
@@ -7834,6 +7841,20 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	buf = btrfs_find_create_tree_block(root, bytenr);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Extra safety check in case the extent tree is corrupted and extent
+	 * allocator chooses to use a tree block which is already used and
+	 * locked.
+	 */
+	if (buf->lock_owner == current->pid) {
+		btrfs_err_rl(root->fs_info,
+"tree block %llu owner %llu already locked by pid=%d, extent tree corruption detected",
+			buf->start, btrfs_header_owner(buf), current->pid);
+		free_extent_buffer(buf);
+		return ERR_PTR(-EUCLEAN);
+	}
+
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
@@ -8703,15 +8724,14 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 	if (eb == root->node) {
 		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
 			parent = eb->start;
-		else
-			BUG_ON(root->root_key.objectid !=
-			       btrfs_header_owner(eb));
+		else if (root->root_key.objectid != btrfs_header_owner(eb))
+			goto owner_mismatch;
 	} else {
 		if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
 			parent = path->nodes[level + 1]->start;
-		else
-			BUG_ON(root->root_key.objectid !=
-			       btrfs_header_owner(path->nodes[level + 1]));
+		else if (root->root_key.objectid !=
+			 btrfs_header_owner(path->nodes[level + 1]))
+			goto owner_mismatch;
 	}
 
 	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
@@ -8719,6 +8739,11 @@ out:
 	wc->refs[level] = 0;
 	wc->flags[level] = 0;
 	return 0;
+
+owner_mismatch:
+	btrfs_err_rl(root->fs_info, "unexpected tree owner, have %llu expect %llu",
+		     btrfs_header_owner(eb), root->root_key.objectid);
+	return -EUCLEAN;
 }
 
 static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
@@ -8772,6 +8797,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
 			ret = walk_up_proc(trans, root, path, wc);
 			if (ret > 0)
 				return 0;
+			if (ret < 0)
+				return ret;
 
 			if (path->locks[level]) {
 				btrfs_tree_unlock_rw(path->nodes[level],
@@ -9460,6 +9487,8 @@ static int find_first_block_group(struct btrfs_root *root,
 	int ret = 0;
 	struct btrfs_key found_key;
 	struct extent_buffer *leaf;
+	struct btrfs_block_group_item bg;
+	u64 flags;
 	int slot;
 
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
@@ -9481,7 +9510,47 @@ static int find_first_block_group(struct btrfs_root *root,
 
 		if (found_key.objectid >= key->objectid &&
 		    found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
-			ret = 0;
+			struct extent_map_tree *em_tree;
+			struct extent_map *em;
+
+			em_tree = &root->fs_info->mapping_tree.map_tree;
+			read_lock(&em_tree->lock);
+			em = lookup_extent_mapping(em_tree, found_key.objectid,
+						   found_key.offset);
+			read_unlock(&em_tree->lock);
+			if (!em) {
+				btrfs_err(root->fs_info,
+			"logical %llu len %llu found bg but no related chunk",
+					  found_key.objectid, found_key.offset);
+				ret = -ENOENT;
+			} else if (em->start != found_key.objectid ||
+				   em->len != found_key.offset) {
+				btrfs_err(root->fs_info,
+		"block group %llu len %llu mismatch with chunk %llu len %llu",
+					  found_key.objectid, found_key.offset,
+					  em->start, em->len);
+				ret = -EUCLEAN;
+			} else {
+				read_extent_buffer(leaf, &bg,
+					btrfs_item_ptr_offset(leaf, slot),
+					sizeof(bg));
+				flags = btrfs_block_group_flags(&bg) &
+					BTRFS_BLOCK_GROUP_TYPE_MASK;
+
+				if (flags != (em->map_lookup->type &
+					      BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+					btrfs_err(root->fs_info,
+"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
+						found_key.objectid,
+						found_key.offset, flags,
+						(BTRFS_BLOCK_GROUP_TYPE_MASK &
+						 em->map_lookup->type));
+					ret = -EUCLEAN;
+				} else {
+					ret = 0;
+				}
+			}
+			free_extent_map(em);
 			goto out;
 		}
 		path->slots[0]++;
@@ -9500,6 +9569,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 
 		block_group = btrfs_lookup_first_block_group(info, last);
 		while (block_group) {
+			wait_block_group_cache_done(block_group);
 			spin_lock(&block_group->lock);
 			if (block_group->iref)
 				break;
@@ -9695,6 +9765,62 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
 	return cache;
 }
 
+
+/*
+ * Iterate all chunks and verify that each of them has the corresponding block
+ * group
+ */
+static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+	struct extent_map *em;
+	struct btrfs_block_group_cache *bg;
+	u64 start = 0;
+	int ret = 0;
+
+	while (1) {
+		read_lock(&map_tree->map_tree.lock);
+		/*
+		 * lookup_extent_mapping will return the first extent map
+		 * intersecting the range, so setting @len to 1 is enough to
+		 * get the first chunk.
+		 */
+		em = lookup_extent_mapping(&map_tree->map_tree, start, 1);
+		read_unlock(&map_tree->map_tree.lock);
+		if (!em)
+			break;
+
+		bg = btrfs_lookup_block_group(fs_info, em->start);
+		if (!bg) {
+			btrfs_err(fs_info,
+	"chunk start=%llu len=%llu doesn't have corresponding block group",
+				     em->start, em->len);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			break;
+		}
+		if (bg->key.objectid != em->start ||
+		    bg->key.offset != em->len ||
+		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
+		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+			btrfs_err(fs_info,
+"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
+				em->start, em->len,
+				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
+				bg->key.objectid, bg->key.offset,
+				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		start = em->start + em->len;
+		free_extent_map(em);
+		btrfs_put_block_group(bg);
+	}
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_root *root)
 {
 	struct btrfs_path *path;
@@ -9881,7 +10007,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 	}
 
 	init_global_block_rsv(info);
-	ret = 0;
+	ret = check_chunk_block_group_mappings(info);
 error:
 	btrfs_free_path(path);
 	return ret;
@@ -9890,7 +10016,7 @@ error:
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 				       struct btrfs_root *root)
 {
-	struct btrfs_block_group_cache *block_group, *tmp;
+	struct btrfs_block_group_cache *block_group;
 	struct btrfs_root *extent_root = root->fs_info->extent_root;
 	struct btrfs_block_group_item item;
 	struct btrfs_key key;
@@ -9898,7 +10024,10 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 	bool can_flush_pending_bgs = trans->can_flush_pending_bgs;
 
 	trans->can_flush_pending_bgs = false;
-	list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
+	while (!list_empty(&trans->new_bgs)) {
+		block_group = list_first_entry(&trans->new_bgs,
+					       struct btrfs_block_group_cache,
+					       bg_list);
 		if (ret)
 			goto next;
 
@@ -10363,7 +10492,7 @@ btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
 	 * more device items and remove one chunk item), but this is done at
 	 * btrfs_remove_chunk() through a call to check_system_chunk().
 	 */
-	map = (struct map_lookup *)em->bdev;
+	map = em->map_lookup;
 	num_items = 3 + map->num_stripes;
 	free_extent_map(em);
 
@@ -10409,7 +10538,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
-		if (block_group->reserved ||
+		if (block_group->reserved || block_group->pinned ||
 		    btrfs_block_group_used(&block_group->item) ||
 		    block_group->ro ||
 		    list_is_singular(&block_group->list)) {
@@ -10601,13 +10730,17 @@ int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
  * transaction.
  */
 static int btrfs_trim_free_extents(struct btrfs_device *device,
-				   u64 minlen, u64 *trimmed)
+				   struct fstrim_range *range, u64 *trimmed)
 {
-	u64 start = 0, len = 0;
+	u64 start = range->start, len = 0;
 	int ret;
 
 	*trimmed = 0;
 
+	/* Discard not supported = nothing to do. */
+	if (!blk_queue_discard(bdev_get_queue(device->bdev)))
+		return 0;
+
 	/* Not writeable = nothing to do. */
 	if (!device->writeable)
 		return 0;
@@ -10635,8 +10768,8 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 			atomic_inc(&trans->use_count);
 		spin_unlock(&fs_info->trans_lock);
 
-		ret = find_free_dev_extent_start(trans, device, minlen, start,
-						 &start, &len);
+		ret = find_free_dev_extent_start(trans, device, range->minlen,
+						 start, &start, &len);
 		if (trans)
 			btrfs_put_transaction(trans);
 
@@ -10648,6 +10781,16 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 			break;
 		}
 
+		/* If we are out of the passed range break */
+		if (start > range->start + range->len - 1) {
+			mutex_unlock(&fs_info->chunk_mutex);
+			ret = 0;
+			break;
+		}
+
+		start = max(range->start, start);
+		len = min(range->len, len);
+
 		ret = btrfs_issue_discard(device->bdev, start, len, &bytes);
 		up_read(&fs_info->commit_root_sem);
 		mutex_unlock(&fs_info->chunk_mutex);
@@ -10658,6 +10801,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 		start += len;
 		*trimmed += bytes;
 
+		/* We've trimmed enough */
+		if (*trimmed >= range->len)
+			break;
+
 		if (fatal_signal_pending(current)) {
 			ret = -ERESTARTSYS;
 			break;
@@ -10679,17 +10826,9 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
 	u64 start;
 	u64 end;
 	u64 trimmed = 0;
-	u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
 	int ret = 0;
 
-	/*
-	 * try to trim all FS space, our block group may start from non-zero.
-	 */
-	if (range->len == total_bytes)
-		cache = btrfs_lookup_first_block_group(fs_info, range->start);
-	else
-		cache = btrfs_lookup_block_group(fs_info, range->start);
-
+	cache = btrfs_lookup_first_block_group(fs_info, range->start);
 	while (cache) {
 		if (cache->key.objectid >= (range->start + range->len)) {
 			btrfs_put_block_group(cache);
@@ -10730,10 +10869,9 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
 	}
 
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
-	devices = &root->fs_info->fs_devices->alloc_list;
-	list_for_each_entry(device, devices, dev_alloc_list) {
-		ret = btrfs_trim_free_extents(device, range->minlen,
-					      &group_trimmed);
+	devices = &root->fs_info->fs_devices->devices;
+	list_for_each_entry(device, devices, dev_list) {
+		ret = btrfs_trim_free_extents(device, range, &group_trimmed);
 		if (ret)
 			break;