Btrfs: Fix race in btrfs_mark_extent_written

Fix bug reported by Johannes Hirte. The reason of that bug
is btrfs_del_items is called after btrfs_duplicate_item and
btrfs_del_items triggers tree balance. The fix is check that
case and call btrfs_search_slot when needed.

Signed-off-by: Yan Zheng <zheng.yan@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 3bfe9f03990bc434b6c0b3552e73421aaabf6bf8..ae96fdae1f7de9e4c2f91035f6d26497a1393d7f 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -506,7 +506,8 @@ next_slot:
 }
 
 static int extent_mergeable(struct extent_buffer *leaf, int slot,
-                           u64 objectid, u64 bytenr, u64 *start, u64 *end)
+                           u64 objectid, u64 bytenr, u64 orig_offset,
+                           u64 *start, u64 *end)
 {
        struct btrfs_file_extent_item *fi;
        struct btrfs_key key;
@@ -522,6 +523,7 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
        fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
        if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG ||
            btrfs_file_extent_disk_bytenr(leaf, fi) != bytenr ||
+           btrfs_file_extent_offset(leaf, fi) != key.offset - orig_offset ||
            btrfs_file_extent_compression(leaf, fi) ||
            btrfs_file_extent_encryption(leaf, fi) ||
            btrfs_file_extent_other_encoding(leaf, fi))
@@ -561,6 +563,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
        u64 split;
        int del_nr = 0;
        int del_slot = 0;
+       int recow;
        int ret;
 
        btrfs_drop_extent_cache(inode, start, end - 1, 0);
@@ -568,6 +571,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
        path = btrfs_alloc_path();
        BUG_ON(!path);
 again:
+       recow = 0;
        split = start;
        key.objectid = inode->i_ino;
        key.type = BTRFS_EXTENT_DATA_KEY;
@@ -591,12 +595,60 @@ again:
        bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
        num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
        orig_offset = key.offset - btrfs_file_extent_offset(leaf, fi);
+       memcpy(&new_key, &key, sizeof(new_key));
+
+       if (start == key.offset && end < extent_end) {
+               other_start = 0;
+               other_end = start;
+               if (extent_mergeable(leaf, path->slots[0] - 1,
+                                    inode->i_ino, bytenr, orig_offset,
+                                    &other_start, &other_end)) {
+                       new_key.offset = end;
+                       btrfs_set_item_key_safe(trans, root, path, &new_key);
+                       fi = btrfs_item_ptr(leaf, path->slots[0],
+                                           struct btrfs_file_extent_item);
+                       btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                       extent_end - end);
+                       btrfs_set_file_extent_offset(leaf, fi,
+                                                    end - orig_offset);
+                       fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
+                                           struct btrfs_file_extent_item);
+                       btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                       end - other_start);
+                       btrfs_mark_buffer_dirty(leaf);
+                       goto out;
+               }
+       }
+
+       if (start > key.offset && end == extent_end) {
+               other_start = end;
+               other_end = 0;
+               if (extent_mergeable(leaf, path->slots[0] + 1,
+                                    inode->i_ino, bytenr, orig_offset,
+                                    &other_start, &other_end)) {
+                       fi = btrfs_item_ptr(leaf, path->slots[0],
+                                           struct btrfs_file_extent_item);
+                       btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                       start - key.offset);
+                       path->slots[0]++;
+                       new_key.offset = start;
+                       btrfs_set_item_key_safe(trans, root, path, &new_key);
+
+                       fi = btrfs_item_ptr(leaf, path->slots[0],
+                                           struct btrfs_file_extent_item);
+                       btrfs_set_file_extent_num_bytes(leaf, fi,
+                                                       other_end - start);
+                       btrfs_set_file_extent_offset(leaf, fi,
+                                                    start - orig_offset);
+                       btrfs_mark_buffer_dirty(leaf);
+                       goto out;
+               }
+       }
 
        while (start > key.offset || end < extent_end) {
                if (key.offset == start)
                        split = end;
 
-               memcpy(&new_key, &key, sizeof(new_key));
                new_key.offset = split;
                ret = btrfs_duplicate_item(trans, root, path, &new_key);
                if (ret == -EAGAIN) {
@@ -631,15 +683,18 @@ again:
                        path->slots[0]--;
                        extent_end = end;
                }
+               recow = 1;
        }
 
-       fi = btrfs_item_ptr(leaf, path->slots[0],
-                           struct btrfs_file_extent_item);
-
        other_start = end;
        other_end = 0;
-       if (extent_mergeable(leaf, path->slots[0] + 1, inode->i_ino,
-                            bytenr, &other_start, &other_end)) {
+       if (extent_mergeable(leaf, path->slots[0] + 1,
+                            inode->i_ino, bytenr, orig_offset,
+                            &other_start, &other_end)) {
+               if (recow) {
+                       btrfs_release_path(root, path);
+                       goto again;
+               }
                extent_end = other_end;
                del_slot = path->slots[0] + 1;
                del_nr++;
@@ -650,8 +705,13 @@ again:
        }
        other_start = 0;
        other_end = start;
-       if (extent_mergeable(leaf, path->slots[0] - 1, inode->i_ino,
-                            bytenr, &other_start, &other_end)) {
+       if (extent_mergeable(leaf, path->slots[0] - 1,
+                            inode->i_ino, bytenr, orig_offset,
+                            &other_start, &other_end)) {
+               if (recow) {
+                       btrfs_release_path(root, path);
+                       goto again;
+               }
                key.offset = other_start;
                del_slot = path->slots[0];
                del_nr++;
@@ -660,22 +720,22 @@ again:
                                        inode->i_ino, orig_offset);
                BUG_ON(ret);
        }
+       fi = btrfs_item_ptr(leaf, path->slots[0],
+                          struct btrfs_file_extent_item);
        if (del_nr == 0) {
                btrfs_set_file_extent_type(leaf, fi,
                                           BTRFS_FILE_EXTENT_REG);
                btrfs_mark_buffer_dirty(leaf);
-               goto out;
-       }
-
-       fi = btrfs_item_ptr(leaf, del_slot - 1,
-                           struct btrfs_file_extent_item);
-       btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG);
-       btrfs_set_file_extent_num_bytes(leaf, fi,
-                                       extent_end - key.offset);
-       btrfs_mark_buffer_dirty(leaf);
+       } else {
+               btrfs_set_file_extent_type(leaf, fi,
+                                          BTRFS_FILE_EXTENT_REG);
+               btrfs_set_file_extent_num_bytes(leaf, fi,
+                                               extent_end - key.offset);
+               btrfs_mark_buffer_dirty(leaf);
 
-       ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
-       BUG_ON(ret);
+               ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
+               BUG_ON(ret);
+       }
 out:
        btrfs_free_path(path);
        return 0;