X-Git-Url: http://pileus.org/git/?a=blobdiff_plain;f=fs%2Fext4%2Fnamei.c;h=94ee6f315dc17580c6de82f65d3f58735a29b870;hb=6d435365dd49ac5f7fe6f0e757e942875b1d1550;hp=2811e5720ad019d18e9976ac8afc21e3c885768b;hpb=cab8e5c4444cb7d9b8035de5d81fbfd5284a02fa;p=~andy%2Flinux diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 2811e5720ad..94ee6f315dc 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -140,10 +140,10 @@ struct dx_frame struct dx_map_entry { u32 hash; - u32 offs; + u16 offs; + u16 size; }; -#ifdef CONFIG_EXT4_INDEX static inline unsigned dx_get_block (struct dx_entry *entry); static void dx_set_block (struct dx_entry *entry, unsigned value); static inline unsigned dx_get_hash (struct dx_entry *entry); @@ -379,13 +379,28 @@ dx_probe(struct dentry *dentry, struct inode *dir, entries = (struct dx_entry *) (((char *)&root->info) + root->info.info_length); - assert(dx_get_limit(entries) == dx_root_limit(dir, - root->info.info_length)); + + if (dx_get_limit(entries) != dx_root_limit(dir, + root->info.info_length)) { + ext4_warning(dir->i_sb, __FUNCTION__, + "dx entry: limit != root limit"); + brelse(bh); + *err = ERR_BAD_DX_DIR; + goto fail; + } + dxtrace (printk("Look up %x", hash)); while (1) { count = dx_get_count(entries); - assert (count && count <= dx_get_limit(entries)); + if (!count || count > dx_get_limit(entries)) { + ext4_warning(dir->i_sb, __FUNCTION__, + "dx entry: no count or count > limit"); + brelse(bh); + *err = ERR_BAD_DX_DIR; + goto fail2; + } + p = entries + 1; q = entries + count - 1; while (p <= q) @@ -423,8 +438,15 @@ dx_probe(struct dentry *dentry, struct inode *dir, if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err))) goto fail2; at = entries = ((struct dx_node *) bh->b_data)->entries; - assert (dx_get_limit(entries) == dx_node_limit (dir)); + if (dx_get_limit(entries) != dx_node_limit (dir)) { + ext4_warning(dir->i_sb, __FUNCTION__, + "dx entry: limit != node limit"); + brelse(bh); + *err = ERR_BAD_DX_DIR; + goto fail2; + } frame++; + frame->bh = NULL; } fail2: while (frame >= frame_in) { @@ -432,6 +454,10 @@ fail2: frame--; } fail: + if (*err == ERR_BAD_DX_DIR) + ext4_warning(dir->i_sb, __FUNCTION__, + "Corrupt dir inode %ld, running e2fsck is " + "recommended.", dir->i_ino); return NULL; } @@ -671,6 +697,10 @@ errout: * Directory block splitting, compacting */ +/* + * Create map of hash values, offsets, and sizes, stored at end of block. + * Returns number of entries mapped. + */ static int dx_make_map (struct ext4_dir_entry_2 *de, int size, struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) { @@ -684,7 +714,8 @@ static int dx_make_map (struct ext4_dir_entry_2 *de, int size, ext4fs_dirhash(de->name, de->name_len, &h); map_tail--; map_tail->hash = h.hash; - map_tail->offs = (u32) ((char *) de - base); + map_tail->offs = (u16) ((char *) de - base); + map_tail->size = le16_to_cpu(de->rec_len); count++; cond_resched(); } @@ -694,6 +725,7 @@ static int dx_make_map (struct ext4_dir_entry_2 *de, int size, return count; } +/* Sort map by hash value */ static void dx_sort_map (struct dx_map_entry *map, unsigned count) { struct dx_map_entry *p, *q, *top = map + count - 1; @@ -733,8 +765,6 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, u32 block) dx_set_block(new, block); dx_set_count(entries, count + 1); } -#endif - static void ext4_update_dx_flag(struct inode *inode) { @@ -836,7 +866,6 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry, name = dentry->d_name.name; if (namelen > EXT4_NAME_LEN) return NULL; -#ifdef CONFIG_EXT4_INDEX if (is_dx(dir)) { bh = ext4_dx_find_entry(dentry, res_dir, &err); /* @@ -848,7 +877,6 @@ static struct buffer_head * ext4_find_entry (struct dentry *dentry, return bh; dxtrace(printk("ext4_find_entry: dx failed, falling back\n")); } -#endif nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb); start = EXT4_I(dir)->i_dir_start_lookup; if (start >= nblocks) @@ -924,7 +952,6 @@ cleanup_and_exit: return ret; } -#ifdef CONFIG_EXT4_INDEX static struct buffer_head * ext4_dx_find_entry(struct dentry *dentry, struct ext4_dir_entry_2 **res_dir, int *err) { @@ -992,7 +1019,6 @@ errout: dx_release (frames); return NULL; } -#endif static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd) { @@ -1017,6 +1043,11 @@ static struct dentry *ext4_lookup(struct inode * dir, struct dentry *dentry, str if (!inode) return ERR_PTR(-EACCES); + + if (is_bad_inode(inode)) { + iput(inode); + return ERR_PTR(-ENOENT); + } } return d_splice_alias(inode, dentry); } @@ -1052,6 +1083,11 @@ struct dentry *ext4_get_parent(struct dentry *child) if (!inode) return ERR_PTR(-EACCES); + if (is_bad_inode(inode)) { + iput(inode); + return ERR_PTR(-ENOENT); + } + parent = d_alloc_anon(inode); if (!parent) { iput(inode); @@ -1078,7 +1114,10 @@ static inline void ext4_set_de_type(struct super_block *sb, de->file_type = ext4_type_by_mode[(mode & S_IFMT)>>S_SHIFT]; } -#ifdef CONFIG_EXT4_INDEX +/* + * Move count entries from end of map between two memory locations. + * Returns pointer to last entry moved. + */ static struct ext4_dir_entry_2 * dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count) { @@ -1097,6 +1136,10 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count) return (struct ext4_dir_entry_2 *) (to - rec_len); } +/* + * Compact each dir entry in the range to the minimal rec_len. + * Returns pointer to last entry in range. + */ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size) { struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base; @@ -1119,6 +1162,11 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, int size) return prev; } +/* + * Split a full leaf block to make room for a new dir entry. + * Allocate a new block, and move entries so that they are approx. equally full. + * Returns pointer to de in block into which the new entry will be inserted. + */ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, struct buffer_head **bh,struct dx_frame *frame, struct dx_hash_info *hinfo, int *error) @@ -1130,7 +1178,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, u32 hash2; struct dx_map_entry *map; char *data1 = (*bh)->b_data, *data2; - unsigned split; + unsigned split, move, size, i; struct ext4_dir_entry_2 *de = NULL, *de2; int err = 0; @@ -1158,8 +1206,19 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, count = dx_make_map ((struct ext4_dir_entry_2 *) data1, blocksize, hinfo, map); map -= count; - split = count/2; // need to adjust to actual middle dx_sort_map (map, count); + /* Split the existing block in the middle, size-wise */ + size = 0; + move = 0; + for (i = count-1; i >= 0; i--) { + /* is more than half of this entry in 2nd half of the block? */ + if (size + map[i].size/2 > blocksize/2) + break; + size += map[i].size; + move++; + } + /* map index at which we will split */ + split = count - move; hash2 = map[split].hash; continued = hash2 == map[split - 1].hash; dxtrace(printk("Split block %i at %x, %i/%i\n", @@ -1199,8 +1258,6 @@ errout: *error = err; return NULL; } -#endif - /* * Add a new entry into a directory (leaf) block. If de is non-NULL, @@ -1285,7 +1342,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, * happen is that the times are slightly out of date * and/or different from the directory change time. */ - dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC; + dir->i_mtime = dir->i_ctime = ext4_current_time(dir); ext4_update_dx_flag(dir); dir->i_version++; ext4_mark_inode_dirty(handle, dir); @@ -1297,7 +1354,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, return 0; } -#ifdef CONFIG_EXT4_INDEX /* * This converts a one block unindexed directory to a 3 block indexed * directory, and adds the dentry to the indexed directory. @@ -1376,7 +1432,6 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, return add_dirent_to_buf(handle, dentry, inode, de, bh); } -#endif /* * ext4_add_entry() @@ -1397,9 +1452,7 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, struct ext4_dir_entry_2 *de; struct super_block * sb; int retval; -#ifdef CONFIG_EXT4_INDEX int dx_fallback=0; -#endif unsigned blocksize; u32 block, blocks; @@ -1407,7 +1460,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, blocksize = sb->s_blocksize; if (!dentry->d_name.len) return -EINVAL; -#ifdef CONFIG_EXT4_INDEX if (is_dx(dir)) { retval = ext4_dx_add_entry(handle, dentry, inode); if (!retval || (retval != ERR_BAD_DX_DIR)) @@ -1416,7 +1468,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, dx_fallback++; ext4_mark_inode_dirty(handle, dir); } -#endif blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0, offset = 0; block < blocks; block++) { bh = ext4_bread(handle, dir, block, 0, &retval); @@ -1426,11 +1477,9 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, if (retval != -ENOSPC) return retval; -#ifdef CONFIG_EXT4_INDEX if (blocks == 1 && !dx_fallback && EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) return make_indexed_dir(handle, dentry, inode, bh); -#endif brelse(bh); } bh = ext4_append(handle, dir, &block, &retval); @@ -1442,7 +1491,6 @@ static int ext4_add_entry (handle_t *handle, struct dentry *dentry, return add_dirent_to_buf(handle, dentry, inode, de, bh); } -#ifdef CONFIG_EXT4_INDEX /* * Returns 0 for success, or a negative error value */ @@ -1577,7 +1625,6 @@ cleanup: dx_release(frames); return err; } -#endif /* * ext4_delete_entry deletes a directory entry by merging it with the @@ -1619,6 +1666,35 @@ static int ext4_delete_entry (handle_t *handle, return -ENOENT; } +/* + * DIR_NLINK feature is set if 1) nlinks > EXT4_LINK_MAX or 2) nlinks == 2, + * since this indicates that nlinks count was previously 1. + */ +static void ext4_inc_count(handle_t *handle, struct inode *inode) +{ + inc_nlink(inode); + if (is_dx(inode) && inode->i_nlink > 1) { + /* limit is 16-bit i_links_count */ + if (inode->i_nlink >= EXT4_LINK_MAX || inode->i_nlink == 2) { + inode->i_nlink = 1; + EXT4_SET_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_DIR_NLINK); + } + } +} + +/* + * If a directory had nlink == 1, then we should let it be 1. This indicates + * directory has >EXT4_LINK_MAX subdirs. + */ +static void ext4_dec_count(handle_t *handle, struct inode *inode) +{ + drop_nlink(inode); + if (S_ISDIR(inode->i_mode) && inode->i_nlink == 0) + inc_nlink(inode); +} + + static int ext4_add_nondir(handle_t *handle, struct dentry *dentry, struct inode *inode) { @@ -1715,7 +1791,7 @@ static int ext4_mkdir(struct inode * dir, struct dentry * dentry, int mode) struct ext4_dir_entry_2 * de; int err, retries = 0; - if (dir->i_nlink >= EXT4_LINK_MAX) + if (EXT4_DIR_LINK_MAX(dir)) return -EMLINK; retry: @@ -1738,7 +1814,7 @@ retry: inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize; dir_block = ext4_bread (handle, inode, 0, 1, &err); if (!dir_block) { - drop_nlink(inode); /* is this nlink == 0? */ + ext4_dec_count(handle, inode); /* is this nlink == 0? */ ext4_mark_inode_dirty(handle, inode); iput (inode); goto out_stop; @@ -1770,7 +1846,7 @@ retry: iput (inode); goto out_stop; } - inc_nlink(dir); + ext4_inc_count(handle, dir); ext4_update_dx_flag(dir); ext4_mark_inode_dirty(handle, dir); d_instantiate(dentry, inode); @@ -2035,9 +2111,9 @@ static int ext4_rmdir (struct inode * dir, struct dentry *dentry) retval = ext4_delete_entry(handle, dir, de, bh); if (retval) goto end_rmdir; - if (inode->i_nlink != 2) + if (!EXT4_DIR_LINK_EMPTY(inode)) ext4_warning (inode->i_sb, "ext4_rmdir", - "empty directory has nlink!=2 (%d)", + "empty directory has too many links (%d)", inode->i_nlink); inode->i_version++; clear_nlink(inode); @@ -2046,9 +2122,9 @@ static int ext4_rmdir (struct inode * dir, struct dentry *dentry) * recovery. */ inode->i_size = 0; ext4_orphan_add(handle, inode); - inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; + inode->i_ctime = dir->i_ctime = dir->i_mtime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); - drop_nlink(dir); + ext4_dec_count(handle, dir); ext4_update_dx_flag(dir); ext4_mark_inode_dirty(handle, dir); @@ -2096,13 +2172,13 @@ static int ext4_unlink(struct inode * dir, struct dentry *dentry) retval = ext4_delete_entry(handle, dir, de, bh); if (retval) goto end_unlink; - dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC; + dir->i_ctime = dir->i_mtime = ext4_current_time(dir); ext4_update_dx_flag(dir); ext4_mark_inode_dirty(handle, dir); - drop_nlink(inode); + ext4_dec_count(handle, inode); if (!inode->i_nlink) ext4_orphan_add(handle, inode); - inode->i_ctime = dir->i_ctime; + inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); retval = 0; @@ -2149,7 +2225,7 @@ retry: err = __page_symlink(inode, symname, l, mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); if (err) { - drop_nlink(inode); + ext4_dec_count(handle, inode); ext4_mark_inode_dirty(handle, inode); iput (inode); goto out_stop; @@ -2175,8 +2251,9 @@ static int ext4_link (struct dentry * old_dentry, struct inode *inode = old_dentry->d_inode; int err, retries = 0; - if (inode->i_nlink >= EXT4_LINK_MAX) + if (EXT4_DIR_LINK_MAX(inode)) return -EMLINK; + /* * Return -ENOENT if we've raced with unlink and i_nlink is 0. Doing * otherwise has the potential to corrupt the orphan inode list. @@ -2193,8 +2270,8 @@ retry: if (IS_DIRSYNC(dir)) handle->h_sync = 1; - inode->i_ctime = CURRENT_TIME_SEC; - inc_nlink(inode); + inode->i_ctime = ext4_current_time(inode); + ext4_inc_count(handle, inode); atomic_inc(&inode->i_count); err = ext4_add_nondir(handle, dentry, inode); @@ -2295,7 +2372,7 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry, * Like most other Unix systems, set the ctime for inodes on a * rename. */ - old_inode->i_ctime = CURRENT_TIME_SEC; + old_inode->i_ctime = ext4_current_time(old_inode); ext4_mark_inode_dirty(handle, old_inode); /* @@ -2327,10 +2404,10 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry, } if (new_inode) { - drop_nlink(new_inode); - new_inode->i_ctime = CURRENT_TIME_SEC; + ext4_dec_count(handle, new_inode); + new_inode->i_ctime = ext4_current_time(new_inode); } - old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; + old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir); ext4_update_dx_flag(old_dir); if (dir_bh) { BUFFER_TRACE(dir_bh, "get_write_access"); @@ -2338,11 +2415,13 @@ static int ext4_rename (struct inode * old_dir, struct dentry *old_dentry, PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino); BUFFER_TRACE(dir_bh, "call ext4_journal_dirty_metadata"); ext4_journal_dirty_metadata(handle, dir_bh); - drop_nlink(old_dir); + ext4_dec_count(handle, old_dir); if (new_inode) { - drop_nlink(new_inode); + /* checked empty_dir above, can't have another parent, + * ext3_dec_count() won't work for many-linked dirs */ + new_inode->i_nlink = 0; } else { - inc_nlink(new_dir); + ext4_inc_count(handle, new_dir); ext4_update_dx_flag(new_dir); ext4_mark_inode_dirty(handle, new_dir); }