Btrfs: avoid visiting all extent items when cloning a range

When cloning a range of a file, we were visiting all the extent items in
the btree that belong to our source inode. We don't need to visit those
extent items that don't overlap the range we are cloning, as doing so only
makes us waste time and do unnecessary btree navigations (btrfs_next_leaf)
for inodes that have a large number of file extent items in the btree.

Signed-off-by: Filipe David Borba Manana <[email protected]>
Signed-off-by: Chris Mason <[email protected]>

Author: fdmanana

fs/btrfs/ioctl.c

@@ -3020,7 +3020,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	/* clone data */
 	key.objectid = btrfs_ino(src);
 	key.type = BTRFS_EXTENT_DATA_KEY;
-	key.offset = 0;
+	key.offset = off;
 
 	while (1) {
 		/*
@@ -3032,6 +3032,17 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 				0, 0);
 		if (ret < 0)
 			goto out;
+		/*
+		 * First search, if no extent item that starts at offset off was
+		 * found but the previous item is an extent item, it's possible
+		 * it might overlap our target range, therefore process it.
+		 */
+		if (key.offset == off && ret > 0 && path->slots[0] > 0) {
+			btrfs_item_key_to_cpu(path->nodes[0], &key,
+					      path->slots[0] - 1);
+			if (key.type == BTRFS_EXTENT_DATA_KEY)
+				path->slots[0]--;
+		}
 
 		nritems = btrfs_header_nritems(path->nodes[0]);
 process_slot:
@@ -3081,10 +3092,16 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 								    extent);
 			}
 
-			if (key.offset + datal <= off ||
-			    key.offset >= off + len - 1) {
+			/*
+			 * The first search might have left us at an extent
+			 * item that ends before our target range's start, can
+			 * happen if we have holes and NO_HOLES feature enabled.
+			 */
+			if (key.offset + datal <= off) {
 				path->slots[0]++;
 				goto process_slot;
+			} else if (key.offset >= off + len) {
+				break;
 			}
 
 			size = btrfs_item_size_nr(leaf, slot);
@@ -3291,14 +3308,15 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 				goto out;
 			}
 			ret = btrfs_end_transaction(trans, root);
+			if (new_key.offset + datal >= destoff + len)
+				break;
 		}
 		btrfs_release_path(path);
 		key.offset++;
 	}
 	ret = 0;
 
 out:
-	btrfs_release_path(path);
 	btrfs_free_path(path);
 	vfree(buf);
 	return ret;