1 files changed, 80 insertions, 64 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 57908ee964a2..692d0d71e8c5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -629,7 +629,21 @@ cont:
 				btrfs_free_reserved_data_space_noquota(inode,
 							       start,
 							       end - start + 1);
-			goto free_pages_out;
+
+			/*
+			 * Ensure we only free the compressed pages if we have
+			 * them allocated, as we can still reach here with
+			 * inode_need_compress() == false.
+			 */
+			if (pages) {
+				for (i = 0; i < nr_pages; i++) {
+					WARN_ON(pages[i]->mapping);
+					put_page(pages[i]);
+				}
+				kfree(pages);
+			}
+
+			return;
 		}
 	}
 
@@ -708,13 +722,6 @@ cleanup_and_bail_uncompressed:
 	*num_added += 1;
 
 	return;
-
-free_pages_out:
-	for (i = 0; i < nr_pages; i++) {
-		WARN_ON(pages[i]->mapping);
-		put_page(pages[i]);
-	}
-	kfree(pages);
 }
 
 static void free_async_extent_pages(struct async_extent *async_extent)
@@ -1328,7 +1335,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	u64 disk_num_bytes;
 	u64 ram_bytes;
 	int extent_type;
-	int ret, err;
+	int ret;
 	int type;
 	int nocow;
 	int check_prev = 1;
@@ -1453,11 +1460,8 @@ next_slot:
 			 * if there are pending snapshots for this root,
 			 * we fall into common COW way.
 			 */
-			if (!nolock) {
-				err = btrfs_start_write_no_snapshotting(root);
-				if (!err)
-					goto out_check;
-			}
+			if (!nolock && atomic_read(&root->snapshot_force_cow))
+				goto out_check;
 			/*
 			 * force cow if csum exists in the range.
 			 * this ensure that csum for a given extent are
@@ -1466,9 +1470,6 @@ next_slot:
 			ret = csum_exist_in_range(fs_info, disk_bytenr,
 						  num_bytes);
 			if (ret) {
-				if (!nolock)
-					btrfs_end_write_no_snapshotting(root);
-
 				/*
 				 * ret could be -EIO if the above fails to read
 				 * metadata.
@@ -1481,11 +1482,8 @@ next_slot:
 				WARN_ON_ONCE(nolock);
 				goto out_check;
 			}
-			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) {
-				if (!nolock)
-					btrfs_end_write_no_snapshotting(root);
+			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr))
 				goto out_check;
-			}
 			nocow = 1;
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = found_key.offset +
@@ -1498,8 +1496,6 @@ next_slot:
 out_check:
 		if (extent_end <= start) {
 			path->slots[0]++;
-			if (!nolock && nocow)
-				btrfs_end_write_no_snapshotting(root);
 			if (nocow)
 				btrfs_dec_nocow_writers(fs_info, disk_bytenr);
 			goto next_slot;
@@ -1521,8 +1517,6 @@ out_check:
 					     end, page_started, nr_written, 1,
 					     NULL);
 			if (ret) {
-				if (!nolock && nocow)
-					btrfs_end_write_no_snapshotting(root);
 				if (nocow)
 					btrfs_dec_nocow_writers(fs_info,
 								disk_bytenr);
@@ -1542,8 +1536,6 @@ out_check:
 					  ram_bytes, BTRFS_COMPRESS_NONE,
 					  BTRFS_ORDERED_PREALLOC);
 			if (IS_ERR(em)) {
-				if (!nolock && nocow)
-					btrfs_end_write_no_snapshotting(root);
 				if (nocow)
 					btrfs_dec_nocow_writers(fs_info,
 								disk_bytenr);
@@ -1582,8 +1574,6 @@ out_check:
 					     EXTENT_CLEAR_DATA_RESV,
 					     PAGE_UNLOCK | PAGE_SET_PRIVATE2);
 
-		if (!nolock && nocow)
-			btrfs_end_write_no_snapshotting(root);
 		cur_offset = extent_end;
 
 		/*
@@ -5594,11 +5584,14 @@ no_delete:
 }
 
 /*
- * this returns the key found in the dir entry in the location pointer.
- * If no dir entries were found, location->objectid is 0.
+ * Return the key found in the dir entry in the location pointer, fill @type
+ * with BTRFS_FT_*, and return 0.
+ *
+ * If no dir entries were found, returns -ENOENT.
+ * If found a corrupted location in dir entry, returns -EUCLEAN.
  */
 static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
-			       struct btrfs_key *location)
+			       struct btrfs_key *location, u8 *type)
 {
 	const char *name = dentry->d_name.name;
 	int namelen = dentry->d_name.len;
@@ -5613,27 +5606,29 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
 
 	di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)),
 			name, namelen, 0);
-	if (IS_ERR(di))
+	if (!di) {
+		ret = -ENOENT;
+		goto out;
+	}
+	if (IS_ERR(di)) {
 		ret = PTR_ERR(di);
-
-	if (IS_ERR_OR_NULL(di))
-		goto out_err;
+		goto out;
+	}
 
 	btrfs_dir_item_key_to_cpu(path->nodes[0], di, location);
 	if (location->type != BTRFS_INODE_ITEM_KEY &&
 	    location->type != BTRFS_ROOT_ITEM_KEY) {
+		ret = -EUCLEAN;
 		btrfs_warn(root->fs_info,
 "%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))",
 			   __func__, name, btrfs_ino(BTRFS_I(dir)),
 			   location->objectid, location->type, location->offset);
-		goto out_err;
 	}
+	if (!ret)
+		*type = btrfs_dir_type(path->nodes[0], di);
 out:
 	btrfs_free_path(path);
 	return ret;
-out_err:
-	location->objectid = 0;
-	goto out;
 }
 
 /*
@@ -5917,6 +5912,11 @@ static struct inode *new_simple_dir(struct super_block *s,
 	return inode;
 }
 
+static inline u8 btrfs_inode_type(struct inode *inode)
+{
+	return btrfs_type_by_mode[(inode->i_mode & S_IFMT) >> S_SHIFT];
+}
+
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
@@ -5924,21 +5924,31 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_root *sub_root = root;
 	struct btrfs_key location;
+	u8 di_type = 0;
 	int index;
 	int ret = 0;
 
 	if (dentry->d_name.len > BTRFS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	ret = btrfs_inode_by_name(dir, dentry, &location);
+	ret = btrfs_inode_by_name(dir, dentry, &location, &di_type);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
-	if (location.objectid == 0)
-		return ERR_PTR(-ENOENT);
-
 	if (location.type == BTRFS_INODE_ITEM_KEY) {
 		inode = btrfs_iget(dir->i_sb, &location, root, NULL);
+		if (IS_ERR(inode))
+			return inode;
+
+		/* Do extra check against inode mode with di_type */
+		if (btrfs_inode_type(inode) != di_type) {
+			btrfs_crit(fs_info,
+"inode mode mismatch with dir: inode mode=0%o btrfs type=%u dir type=%u",
+				  inode->i_mode, btrfs_inode_type(inode),
+				  di_type);
+			iput(inode);
+			return ERR_PTR(-EUCLEAN);
+		}
 		return inode;
 	}
 
@@ -6556,11 +6566,6 @@ fail:
 	return ERR_PTR(ret);
 }
 
-static inline u8 btrfs_inode_type(struct inode *inode)
-{
-	return btrfs_type_by_mode[(inode->i_mode & S_IFMT) >> S_SHIFT];
-}
-
 /*
  * utility function to add 'inode' into 'parent_inode' with
  * a give name and a given sequence number.
@@ -7172,6 +7177,14 @@ again:
 	extent_start = found_key.offset;
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+		/* Only regular file could have regular/prealloc extent */
+		if (!S_ISREG(inode->vfs_inode.i_mode)) {
+			err = -EUCLEAN;
+			btrfs_crit(fs_info,
+		"regular/prealloc extent found for non-regular inode %llu",
+				   btrfs_ino(inode));
+			goto out;
+		}
 		extent_end = extent_start +
 		       btrfs_file_extent_num_bytes(leaf, item);
 
@@ -9197,20 +9210,17 @@ again:
 	/*
 	 * Qgroup reserved space handler
 	 * Page here will be either
-	 * 1) Already written to disk
-	 *    In this case, its reserved space is released from data rsv map
-	 *    and will be freed by delayed_ref handler finally.
-	 *    So even we call qgroup_free_data(), it won't decrease reserved
-	 *    space.
-	 * 2) Not written to disk
-	 *    This means the reserved space should be freed here. However,
-	 *    if a truncate invalidates the page (by clearing PageDirty)
-	 *    and the page is accounted for while allocating extent
-	 *    in btrfs_check_data_free_space() we let delayed_ref to
-	 *    free the entire extent.
+	 * 1) Already written to disk or ordered extent already submitted
+	 *    Then its QGROUP_RESERVED bit in io_tree is already cleaned.
+	 *    Qgroup will be handled by its qgroup_record then.
+	 *    btrfs_qgroup_free_data() call will do nothing here.
+	 *
+	 * 2) Not written to disk yet
+	 *    Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED
+	 *    bit of its io_tree, and free the qgroup reserved data space.
+	 *    Since the IO will never happen for this page.
 	 */
-	if (PageDirty(page))
-		btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
@@ -9823,8 +9833,14 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	bool root_log_pinned = false;
 	bool dest_log_pinned = false;
 
-	/* we only allow rename subvolume link between subvolumes */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
+	/*
+	 * For non-subvolumes allow exchange only within one subvolume, in the
+	 * same inode namespace. Two subvolumes (represented as directory) can
+	 * be exchanged as they're a logical link and have a fixed inode number.
+	 */
+	if (root != dest &&
+	    (old_ino != BTRFS_FIRST_FREE_OBJECTID ||
+	     new_ino != BTRFS_FIRST_FREE_OBJECTID))
 		return -EXDEV;
 
 	/* close the race window with snapshot create/destroy ioctl */