diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c index bd18987326a3f4572309ad2f02d4c823c368e198..93470b728dd0b8a7af71c299e08d489d24841380 100644 --- a/fs/xfs/xfs_bmap_btree.c +++ b/fs/xfs/xfs_bmap_btree.c @@ -2027,6 +2027,24 @@ xfs_bmbt_increment( /* * Insert the current record at the point referenced by cur. + * + * A multi-level split of the tree on insert will invalidate the original + * cursor. It appears, however, that some callers assume that the cursor is + * always valid. Hence if we do a multi-level split we need to revalidate the + * cursor. + * + * When a split occurs, we will see a new cursor returned. Use that as a + * trigger to determine if we need to revalidate the original cursor. If we get + * a split, then use the original irec to lookup up the path of the record we + * just inserted. + * + * Note that the fact that the btree root is in the inode means that we can + * have the level of the tree change without a "split" occurring at the root + * level. What happens is that the root is migrated to an allocated block and + * the inode root is pointed to it. This means a single split can change the + * level of the tree (level 2 -> level 3) and invalidate the old cursor. Hence + * the level change should be accounted as a split so as to correctly trigger a + * revalidation of the old cursor. */ int /* error */ xfs_bmbt_insert( @@ -2039,11 +2057,14 @@ xfs_bmbt_insert( xfs_fsblock_t nbno; xfs_btree_cur_t *ncur; xfs_bmbt_rec_t nrec; + xfs_bmbt_irec_t oirec; /* original irec */ xfs_btree_cur_t *pcur; + int splits = 0; XFS_BMBT_TRACE_CURSOR(cur, ENTRY); level = 0; nbno = NULLFSBLOCK; + oirec = cur->bc_rec.b; xfs_bmbt_disk_set_all(&nrec, &cur->bc_rec.b); ncur = NULL; pcur = cur; @@ -2052,11 +2073,13 @@ xfs_bmbt_insert( &i))) { if (pcur != cur) xfs_btree_del_cursor(pcur, XFS_BTREE_ERROR); - XFS_BMBT_TRACE_CURSOR(cur, ERROR); - return error; + goto error0; } XFS_WANT_CORRUPTED_GOTO(i == 1, error0); if (pcur != cur && (ncur || nbno == NULLFSBLOCK)) { + /* allocating a new root is effectively a split */ + if (cur->bc_nlevels != pcur->bc_nlevels) + splits++; cur->bc_nlevels = pcur->bc_nlevels; cur->bc_private.b.allocated += pcur->bc_private.b.allocated; @@ -2070,10 +2093,21 @@ xfs_bmbt_insert( xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR); } if (ncur) { + splits++; pcur = ncur; ncur = NULL; } } while (nbno != NULLFSBLOCK); + + if (splits > 1) { + /* revalidate the old cursor as we had a multi-level split */ + error = xfs_bmbt_lookup_eq(cur, oirec.br_startoff, + oirec.br_startblock, oirec.br_blockcount, &i); + if (error) + goto error0; + ASSERT(i == 1); + } + XFS_BMBT_TRACE_CURSOR(cur, EXIT); *stat = i; return 0;