1 files changed, 203 insertions, 43 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 47cdc6f3390b..978bbfed5a2c 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,
@@ -2520,11 +2526,11 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		if (ref && ref->seq &&
 		    btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
 			spin_unlock(&locked_ref->lock);
-			btrfs_delayed_ref_unlock(locked_ref);
 			spin_lock(&delayed_refs->lock);
 			locked_ref->processing = 0;
 			delayed_refs->num_heads_ready++;
 			spin_unlock(&delayed_refs->lock);
+			btrfs_delayed_ref_unlock(locked_ref);
 			locked_ref = NULL;
 			cond_resched();
 			count++;
@@ -2570,7 +2576,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 					 */
 					if (must_insert_reserved)
 						locked_ref->must_insert_reserved = 1;
+					spin_lock(&delayed_refs->lock);
 					locked_ref->processing = 0;
+					delayed_refs->num_heads_ready++;
+					spin_unlock(&delayed_refs->lock);
 					btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
 					btrfs_delayed_ref_unlock(locked_ref);
 					return ret;
@@ -3358,13 +3367,6 @@ again:
 		goto again;
 	}
 
-	/* We've already setup this transaction, go ahead and exit */
-	if (block_group->cache_generation == trans->transid &&
-	    i_size_read(inode)) {
-		dcs = BTRFS_DC_SETUP;
-		goto out_put;
-	}
-
 	/*
 	 * We want to set the generation to 0, that way if anything goes wrong
 	 * from here on out we know not to trust this cache when we load up next
@@ -3388,6 +3390,13 @@ again:
 	}
 	WARN_ON(ret);
 
+	/* We've already setup this transaction, go ahead and exit */
+	if (block_group->cache_generation == trans->transid &&
+	    i_size_read(inode)) {
+		dcs = BTRFS_DC_SETUP;
+		goto out_put;
+	}
+
 	if (i_size_read(inode) > 0) {
 		ret = btrfs_check_trunc_cache_free_space(root,
 					&root->fs_info->global_block_rsv);
@@ -3851,6 +3860,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 				    info->space_info_kobj, "%s",
 				    alloc_name(found->flags));
 	if (ret) {
+		percpu_counter_destroy(&found->total_bytes_pinned);
 		kfree(found);
 		return ret;
 	}
@@ -4124,7 +4134,7 @@ commit_trans:
 				      data_sinfo->flags, bytes, 1);
 	spin_unlock(&data_sinfo->lock);
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -4388,6 +4398,7 @@ again:
 	if (wait_for_alloc) {
 		mutex_unlock(&fs_info->chunk_mutex);
 		wait_for_alloc = 0;
+		cond_resched();
 		goto again;
 	}
 
@@ -7830,6 +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);
@@ -8486,14 +8511,13 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	ret = btrfs_lookup_extent_info(trans, root, bytenr, level - 1, 1,
 				       &wc->refs[level - 1],
 				       &wc->flags[level - 1]);
-	if (ret < 0) {
-		btrfs_tree_unlock(next);
-		return ret;
-	}
+	if (ret < 0)
+		goto out_unlock;
 
 	if (unlikely(wc->refs[level - 1] == 0)) {
 		btrfs_err(root->fs_info, "Missing references.");
-		BUG();
+		ret = -EIO;
+		goto out_unlock;
 	}
 	*lookup_info = 0;
 
@@ -8545,7 +8569,12 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	}
 
 	level--;
-	BUG_ON(level != btrfs_header_level(next));
+	ASSERT(level == btrfs_header_level(next));
+	if (level != btrfs_header_level(next)) {
+		btrfs_err(root->fs_info, "mismatched level");
+		ret = -EIO;
+		goto out_unlock;
+	}
 	path->nodes[level] = next;
 	path->slots[level] = 0;
 	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
@@ -8560,8 +8589,15 @@ skip:
 		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
 			parent = path->nodes[level]->start;
 		} else {
-			BUG_ON(root->root_key.objectid !=
+			ASSERT(root->root_key.objectid ==
 			       btrfs_header_owner(path->nodes[level]));
+			if (root->root_key.objectid !=
+			    btrfs_header_owner(path->nodes[level])) {
+				btrfs_err(root->fs_info,
+						"mismatched block owner");
+				ret = -EIO;
+				goto out_unlock;
+			}
 			parent = 0;
 		}
 
@@ -8578,12 +8614,18 @@ skip:
 		}
 		ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent,
 				root->root_key.objectid, level - 1, 0);
-		BUG_ON(ret); /* -ENOMEM */
+		if (ret)
+			goto out_unlock;
 	}
+
+	*lookup_info = 1;
+	ret = 1;
+
+out_unlock:
 	btrfs_tree_unlock(next);
 	free_extent_buffer(next);
-	*lookup_info = 1;
-	return 1;
+
+	return ret;
 }
 
 /*
@@ -8682,15 +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);
@@ -8698,6 +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,
@@ -8751,6 +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],
@@ -9439,6 +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);
@@ -9460,7 +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]++;
@@ -9479,6 +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;
@@ -9674,6 +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;
@@ -9686,6 +9833,11 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 	struct extent_buffer *leaf;
 	int need_clear = 0;
 	u64 cache_gen;
+	u64 feature;
+	int mixed;
+
+	feature = btrfs_super_incompat_flags(info->super_copy);
+	mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS);
 
 	root = info->extent_root;
 	key.objectid = 0;
@@ -9739,6 +9891,15 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 				   btrfs_item_ptr_offset(leaf, path->slots[0]),
 				   sizeof(cache->item));
 		cache->flags = btrfs_block_group_flags(&cache->item);
+		if (!mixed &&
+		    ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
+		    (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
+			btrfs_err(info,
+"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
+				  cache->key.objectid);
+			ret = -EINVAL;
+			goto error;
+		}
 
 		key.objectid = found_key.objectid + found_key.offset;
 		btrfs_release_path(path);
@@ -9846,7 +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;
@@ -9855,7 +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;
@@ -9863,7 +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;
 
@@ -10328,7 +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);
 
@@ -10374,7 +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)) {
@@ -10573,6 +10737,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 
 	*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;
@@ -10644,17 +10812,9 @@ 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);
@@ -10695,8 +10855,8 @@ 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) {
+	devices = &root->fs_info->fs_devices->devices;
+	list_for_each_entry(device, devices, dev_list) {
 		ret = btrfs_trim_free_extents(device, range->minlen,
 					      &group_trimmed);
 		if (ret)