From: Mingming Cao Subject: [PATCH 2/2] ext3: Avoid rec_len overflow with 64KB block size Date: Mon, 01 Oct 2007 17:36:20 -0700 Message-ID: <1191285380.11737.60.camel@localhost.localdomain> References: <20070828190551.415127746@sgi.com> <20070828190735.292638294@sgi.com> <1188432669.3799.35.camel@localhost.localdomain> <1188434857.3799.76.camel@localhost.localdomain> Reply-To: cmm@us.ibm.com Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: sho@tnes.nec.co.jp, Jan Kara , clameter@sgi.com, akmp@osdl.org To: ext4 development , linux-kernel@vger.kernel.org Return-path: Received: from e3.ny.us.ibm.com ([32.97.182.143]:59289 "EHLO e3.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751941AbXJBAxp (ORCPT ); Mon, 1 Oct 2007 20:53:45 -0400 In-Reply-To: <1188434857.3799.76.camel@localhost.localdomain> Sender: linux-ext4-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org ext3: Avoid rec_len overflow with 64KB block size From: Jan Kara With 64KB blocksize, a directory entry can have size 64KB which does not fit into 16 bits we have for entry lenght. So we store 0xffff instead and convert value when read from / written to disk. The patch also converts some places to use ext3_next_entry() when we are changing them anyway. Signed-off-by: Jan Kara Signed-off-by: Mingming Cao --- fs/ext3/dir.c | 10 +++-- fs/ext3/namei.c | 90 ++++++++++++++++++++++------------------------- include/linux/ext3_fs.h | 20 ++++++++++ 3 files changed, 68 insertions(+), 52 deletions(-) diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index c00723a..3c4c43a 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -69,7 +69,7 @@ int ext3_check_dir_entry (const char * function, struct inode * dir, unsigned long offset) { const char * error_msg = NULL; - const int rlen = le16_to_cpu(de->rec_len); + const int rlen = ext3_rec_len_from_disk(de->rec_len); if (rlen < EXT3_DIR_REC_LEN(1)) error_msg = "rec_len is smaller than minimal"; @@ -177,10 +177,10 @@ revalidate: * least that it is non-zero. A * failure will be detected in the * dirent test below. */ - if (le16_to_cpu(de->rec_len) < + if (ext3_rec_len_from_disk(de->rec_len) < EXT3_DIR_REC_LEN(1)) break; - i += le16_to_cpu(de->rec_len); + i += ext3_rec_len_from_disk(de->rec_len); } offset = i; filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1)) @@ -201,7 +201,7 @@ revalidate: ret = stored; goto out; } - offset += le16_to_cpu(de->rec_len); + offset += ext3_rec_len_from_disk(de->rec_len); if (le32_to_cpu(de->inode)) { /* We might block in the next section * if the data destination is @@ -223,7 +223,7 @@ revalidate: goto revalidate; stored ++; } - filp->f_pos += le16_to_cpu(de->rec_len); + filp->f_pos += ext3_rec_len_from_disk(de->rec_len); } offset = 0; brelse (bh); diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index c1fa190..2c38eb6 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -144,6 +144,15 @@ struct dx_map_entry u16 size; }; +/* + * p is at least 6 bytes before the end of page + */ +static inline struct ext3_dir_entry_2 *ext3_next_entry(struct ext3_dir_entry_2 *p) +{ + return (struct ext3_dir_entry_2 *)((char*)p + + ext3_rec_len_from_disk(p->rec_len)); +} + #ifdef CONFIG_EXT3_INDEX static inline unsigned dx_get_block (struct dx_entry *entry); static void dx_set_block (struct dx_entry *entry, unsigned value); @@ -281,7 +290,7 @@ static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext3_dir_ent space += EXT3_DIR_REC_LEN(de->name_len); names++; } - de = (struct ext3_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len)); + de = ext3_next_entry(de); } printk("(%i)\n", names); return (struct stats) { names, space, 1 }; @@ -548,14 +557,6 @@ static int ext3_htree_next_block(struct inode *dir, __u32 hash, /* - * p is at least 6 bytes before the end of page - */ -static inline struct ext3_dir_entry_2 *ext3_next_entry(struct ext3_dir_entry_2 *p) -{ - return (struct ext3_dir_entry_2 *)((char*)p + le16_to_cpu(p->rec_len)); -} - -/* * This function fills a red-black tree with information from a * directory block. It returns the number directory entries loaded * into the tree. If there is an error it is returned in err. @@ -721,7 +722,7 @@ static int dx_make_map (struct ext3_dir_entry_2 *de, int size, cond_resched(); } /* XXX: do we need to check rec_len == 0 case? -Chris */ - de = (struct ext3_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len)); + de = ext3_next_entry(de); } return count; } @@ -825,7 +826,7 @@ static inline int search_dirblock(struct buffer_head * bh, return 1; } /* prevent looping on a bad block */ - de_len = le16_to_cpu(de->rec_len); + de_len = ext3_rec_len_from_disk(de->rec_len); if (de_len <= 0) return -1; offset += de_len; @@ -1138,7 +1139,7 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count) rec_len = EXT3_DIR_REC_LEN(de->name_len); memcpy (to, de, rec_len); ((struct ext3_dir_entry_2 *) to)->rec_len = - cpu_to_le16(rec_len); + ext3_rec_len_to_disk(rec_len); de->inode = 0; map++; to += rec_len; @@ -1157,13 +1158,12 @@ static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size) prev = to = de; while ((char*)de < base + size) { - next = (struct ext3_dir_entry_2 *) ((char *) de + - le16_to_cpu(de->rec_len)); + next = ext3_next_entry(de); if (de->inode && de->name_len) { rec_len = EXT3_DIR_REC_LEN(de->name_len); if (de > to) memmove(to, de, rec_len); - to->rec_len = cpu_to_le16(rec_len); + to->rec_len = ext3_rec_len_to_disk(rec_len); prev = to; to = (struct ext3_dir_entry_2 *) (((char *) to) + rec_len); } @@ -1237,8 +1237,8 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, /* Fancy dance to stay within two buffers */ de2 = dx_move_dirents(data1, data2, map + split, count - split); de = dx_pack_dirents(data1,blocksize); - de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de); - de2->rec_len = cpu_to_le16(data2 + blocksize - (char *) de2); + de->rec_len = ext3_rec_len_to_disk(data1 + blocksize - (char *) de); + de2->rec_len = ext3_rec_len_to_disk(data2 + blocksize - (char *) de2); dxtrace(dx_show_leaf (hinfo, (struct ext3_dir_entry_2 *) data1, blocksize, 1)); dxtrace(dx_show_leaf (hinfo, (struct ext3_dir_entry_2 *) data2, blocksize, 1)); @@ -1309,7 +1309,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, return -EEXIST; } nlen = EXT3_DIR_REC_LEN(de->name_len); - rlen = le16_to_cpu(de->rec_len); + rlen = ext3_rec_len_from_disk(de->rec_len); if ((de->inode? rlen - nlen: rlen) >= reclen) break; de = (struct ext3_dir_entry_2 *)((char *)de + rlen); @@ -1328,11 +1328,11 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, /* By now the buffer is marked for journaling */ nlen = EXT3_DIR_REC_LEN(de->name_len); - rlen = le16_to_cpu(de->rec_len); + rlen = ext3_rec_len_from_disk(de->rec_len); if (de->inode) { struct ext3_dir_entry_2 *de1 = (struct ext3_dir_entry_2 *)((char *)de + nlen); - de1->rec_len = cpu_to_le16(rlen - nlen); - de->rec_len = cpu_to_le16(nlen); + de1->rec_len = ext3_rec_len_to_disk(rlen - nlen); + de->rec_len = ext3_rec_len_to_disk(nlen); de = de1; } de->file_type = EXT3_FT_UNKNOWN; @@ -1410,17 +1410,18 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, /* The 0th block becomes the root, move the dirents out */ fde = &root->dotdot; - de = (struct ext3_dir_entry_2 *)((char *)fde + le16_to_cpu(fde->rec_len)); + de = (struct ext3_dir_entry_2 *)((char *)fde + + ext3_rec_len_from_disk(fde->rec_len)); len = ((char *) root) + blocksize - (char *) de; memcpy (data1, de, len); de = (struct ext3_dir_entry_2 *) data1; top = data1 + len; - while ((char *)(de2=(void*)de+le16_to_cpu(de->rec_len)) < top) + while ((char *)(de2 = ext3_next_entry(de)) < top) de = de2; - de->rec_len = cpu_to_le16(data1 + blocksize - (char *) de); + de->rec_len = ext3_rec_len_to_disk(data1 + blocksize - (char *) de); /* Initialize the root; the dot dirents already exist */ de = (struct ext3_dir_entry_2 *) (&root->dotdot); - de->rec_len = cpu_to_le16(blocksize - EXT3_DIR_REC_LEN(2)); + de->rec_len = ext3_rec_len_to_disk(blocksize - EXT3_DIR_REC_LEN(2)); memset (&root->info, 0, sizeof(root->info)); root->info.info_length = sizeof(root->info); root->info.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version; @@ -1507,7 +1508,7 @@ static int ext3_add_entry (handle_t *handle, struct dentry *dentry, return retval; de = (struct ext3_dir_entry_2 *) bh->b_data; de->inode = 0; - de->rec_len = cpu_to_le16(blocksize); + de->rec_len = ext3_rec_len_to_disk(blocksize); return add_dirent_to_buf(handle, dentry, inode, de, bh); } @@ -1571,7 +1572,7 @@ static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry, goto cleanup; node2 = (struct dx_node *)(bh2->b_data); entries2 = node2->entries; - node2->fake.rec_len = cpu_to_le16(sb->s_blocksize); + node2->fake.rec_len = ext3_rec_len_to_disk(sb->s_blocksize); node2->fake.inode = 0; BUFFER_TRACE(frame->bh, "get_write_access"); err = ext3_journal_get_write_access(handle, frame->bh); @@ -1670,9 +1671,9 @@ static int ext3_delete_entry (handle_t *handle, BUFFER_TRACE(bh, "get_write_access"); ext3_journal_get_write_access(handle, bh); if (pde) - pde->rec_len = - cpu_to_le16(le16_to_cpu(pde->rec_len) + - le16_to_cpu(de->rec_len)); + pde->rec_len = ext3_rec_len_to_disk( + ext3_rec_len_from_disk(pde->rec_len) + + ext3_rec_len_from_disk(de->rec_len)); else de->inode = 0; dir->i_version++; @@ -1680,10 +1681,9 @@ static int ext3_delete_entry (handle_t *handle, ext3_journal_dirty_metadata(handle, bh); return 0; } - i += le16_to_cpu(de->rec_len); + i += ext3_rec_len_from_disk(de->rec_len); pde = de; - de = (struct ext3_dir_entry_2 *) - ((char *) de + le16_to_cpu(de->rec_len)); + de = ext3_next_entry(de); } return -ENOENT; } @@ -1817,13 +1817,12 @@ retry: de = (struct ext3_dir_entry_2 *) dir_block->b_data; de->inode = cpu_to_le32(inode->i_ino); de->name_len = 1; - de->rec_len = cpu_to_le16(EXT3_DIR_REC_LEN(de->name_len)); + de->rec_len = ext3_rec_len_to_disk(EXT3_DIR_REC_LEN(de->name_len)); strcpy (de->name, "."); ext3_set_de_type(dir->i_sb, de, S_IFDIR); - de = (struct ext3_dir_entry_2 *) - ((char *) de + le16_to_cpu(de->rec_len)); + de = ext3_next_entry(de); de->inode = cpu_to_le32(dir->i_ino); - de->rec_len = cpu_to_le16(inode->i_sb->s_blocksize-EXT3_DIR_REC_LEN(1)); + de->rec_len = ext3_rec_len_to_disk(inode->i_sb->s_blocksize-EXT3_DIR_REC_LEN(1)); de->name_len = 2; strcpy (de->name, ".."); ext3_set_de_type(dir->i_sb, de, S_IFDIR); @@ -1875,8 +1874,7 @@ static int empty_dir (struct inode * inode) return 1; } de = (struct ext3_dir_entry_2 *) bh->b_data; - de1 = (struct ext3_dir_entry_2 *) - ((char *) de + le16_to_cpu(de->rec_len)); + de1 = ext3_next_entry(de); if (le32_to_cpu(de->inode) != inode->i_ino || !le32_to_cpu(de1->inode) || strcmp (".", de->name) || @@ -1887,9 +1885,9 @@ static int empty_dir (struct inode * inode) brelse (bh); return 1; } - offset = le16_to_cpu(de->rec_len) + le16_to_cpu(de1->rec_len); - de = (struct ext3_dir_entry_2 *) - ((char *) de1 + le16_to_cpu(de1->rec_len)); + offset = ext3_rec_len_from_disk(de->rec_len) + + ext3_rec_len_from_disk(de1->rec_len); + de = ext3_next_entry(de1); while (offset < inode->i_size ) { if (!bh || (void *) de >= (void *) (bh->b_data+sb->s_blocksize)) { @@ -1918,9 +1916,8 @@ static int empty_dir (struct inode * inode) brelse (bh); return 0; } - offset += le16_to_cpu(de->rec_len); - de = (struct ext3_dir_entry_2 *) - ((char *) de + le16_to_cpu(de->rec_len)); + offset += ext3_rec_len_from_disk(de->rec_len); + de = ext3_next_entry(de); } brelse (bh); return 1; @@ -2274,8 +2271,7 @@ retry: } #define PARENT_INO(buffer) \ - ((struct ext3_dir_entry_2 *) ((char *) buffer + \ - le16_to_cpu(((struct ext3_dir_entry_2 *) buffer)->rec_len)))->inode + (ext3_next_entry((struct ext3_dir_entry_2 *)(buffer))->inode) /* * Anybody can rename anything with this: the permission checks are left to the diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 7aa5556..d9e378d 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -660,6 +660,26 @@ struct ext3_dir_entry_2 { #define EXT3_DIR_ROUND (EXT3_DIR_PAD - 1) #define EXT3_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT3_DIR_ROUND) & \ ~EXT3_DIR_ROUND) +#define EXT3_MAX_REC_LEN ((1<<16)-1) + +static inline unsigned ext3_rec_len_from_disk(__le16 dlen) +{ + unsigned len = le16_to_cpu(dlen); + + if (len == EXT3_MAX_REC_LEN) + return 1 << 16; + return len; +} + +static inline __le16 ext3_rec_len_to_disk(unsigned len) +{ + if (len == (1 << 16)) + return cpu_to_le16(EXT3_MAX_REC_LEN); + else if (len > (1 << 16)) + BUG(); + return cpu_to_le16(len); +} + /* * Hash Tree Directory indexing * (c) Daniel Phillips, 2001