Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759112Ab0G3Rav (ORCPT ); Fri, 30 Jul 2010 13:30:51 -0400 Received: from kroah.org ([198.145.64.141]:52021 "EHLO coco.kroah.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758802Ab0G3RTo (ORCPT ); Fri, 30 Jul 2010 13:19:44 -0400 X-Mailbox-Line: From gregkh@clark.site Fri Jul 30 10:15:10 2010 Message-Id: <20100730171510.387195355@clark.site> User-Agent: quilt/0.48-11.2 Date: Fri, 30 Jul 2010 10:15:47 -0700 From: Greg KH To: linux-kernel@vger.kernel.org, stable@kernel.org Cc: stable-review@kernel.org, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk, Dmitry Monakhov , "Theodore Tso" Subject: [119/165] ext4: Do not zero out uninitialized extents beyond i_size In-Reply-To: <20100730171550.GA1299@kroah.com Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7346 Lines: 205 2.6.32-stable review patch. If anyone has any objections, please let us know. ------------------ commit 21ca087a3891efab4d45488db8febee474d26c68 upstream (as of v2.6.34-git13) The extents code will sometimes zero out blocks and mark them as initialized instead of splitting an extent into several smaller ones. This optimization however, causes problems if the extent is beyond i_size because fsck will complain if there are uninitialized blocks after i_size as this can not be distinguished from an inode that has an incorrect i_size field. https://bugzilla.kernel.org/show_bug.cgi?id=15742 Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" Signed-off-by: Greg Kroah-Hartman --- fs/ext4/extents.c | 67 +++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 51 insertions(+), 16 deletions(-) --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2533,11 +2533,21 @@ static int ext4_ext_convert_to_initializ struct ext4_extent *ex2 = NULL; struct ext4_extent *ex3 = NULL; struct ext4_extent_header *eh; - ext4_lblk_t ee_block; + ext4_lblk_t ee_block, eof_block; unsigned int allocated, ee_len, depth; ext4_fsblk_t newblock; int err = 0; int ret = 0; + int may_zeroout; + + ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical" + "block %llu, max_blocks %u\n", inode->i_ino, + (unsigned long long)iblock, max_blocks); + + eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> + inode->i_sb->s_blocksize_bits; + if (eof_block < iblock + max_blocks) + eof_block = iblock + max_blocks; depth = ext_depth(inode); eh = path[depth].p_hdr; @@ -2546,16 +2556,23 @@ static int ext4_ext_convert_to_initializ ee_len = ext4_ext_get_actual_len(ex); allocated = ee_len - (iblock - ee_block); newblock = iblock - ee_block + ext_pblock(ex); + ex2 = ex; orig_ex.ee_block = ex->ee_block; orig_ex.ee_len = cpu_to_le16(ee_len); ext4_ext_store_pblock(&orig_ex, ext_pblock(ex)); + /* + * It is safe to convert extent to initialized via explicit + * zeroout only if extent is fully insde i_size or new_size. + */ + may_zeroout = ee_block + ee_len <= eof_block; + err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */ - if (ee_len <= 2*EXT4_EXT_ZERO_LEN) { + if (ee_len <= 2*EXT4_EXT_ZERO_LEN && may_zeroout) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) goto fix_extent_len; @@ -2586,7 +2603,7 @@ static int ext4_ext_convert_to_initializ if (allocated > max_blocks) { unsigned int newdepth; /* If extent has less than EXT4_EXT_ZERO_LEN zerout directly */ - if (allocated <= EXT4_EXT_ZERO_LEN) { + if (allocated <= EXT4_EXT_ZERO_LEN && may_zeroout) { /* * iblock == ee_block is handled by the zerouout * at the beginning. @@ -2662,7 +2679,7 @@ static int ext4_ext_convert_to_initializ ex3->ee_len = cpu_to_le16(allocated - max_blocks); ext4_ext_mark_uninitialized(ex3); err = ext4_ext_insert_extent(handle, inode, path, ex3, 0); - if (err == -ENOSPC) { + if (err == -ENOSPC && may_zeroout) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) goto fix_extent_len; @@ -2686,8 +2703,10 @@ static int ext4_ext_convert_to_initializ * update the extent length after successful insert of the * split extent */ - orig_ex.ee_len = cpu_to_le16(ee_len - - ext4_ext_get_actual_len(ex3)); + ee_len -= ext4_ext_get_actual_len(ex3); + orig_ex.ee_len = cpu_to_le16(ee_len); + may_zeroout = ee_block + ee_len <= eof_block; + depth = newdepth; ext4_ext_drop_refs(path); path = ext4_ext_find_extent(inode, iblock, path); @@ -2711,7 +2730,7 @@ static int ext4_ext_convert_to_initializ * otherwise give the extent a chance to merge to left */ if (le16_to_cpu(orig_ex.ee_len) <= EXT4_EXT_ZERO_LEN && - iblock != ee_block) { + iblock != ee_block && may_zeroout) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) goto fix_extent_len; @@ -2780,7 +2799,7 @@ static int ext4_ext_convert_to_initializ goto out; insert: err = ext4_ext_insert_extent(handle, inode, path, &newex, 0); - if (err == -ENOSPC) { + if (err == -ENOSPC && may_zeroout) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) goto fix_extent_len; @@ -2840,14 +2859,21 @@ static int ext4_split_unwritten_extents( struct ext4_extent *ex2 = NULL; struct ext4_extent *ex3 = NULL; struct ext4_extent_header *eh; - ext4_lblk_t ee_block; + ext4_lblk_t ee_block, eof_block; unsigned int allocated, ee_len, depth; ext4_fsblk_t newblock; int err = 0; + int may_zeroout; + + ext_debug("ext4_split_unwritten_extents: inode %lu, logical" + "block %llu, max_blocks %u\n", inode->i_ino, + (unsigned long long)iblock, max_blocks); + + eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> + inode->i_sb->s_blocksize_bits; + if (eof_block < iblock + max_blocks) + eof_block = iblock + max_blocks; - ext_debug("ext4_split_unwritten_extents: inode %lu," - "iblock %llu, max_blocks %u\n", inode->i_ino, - (unsigned long long)iblock, max_blocks); depth = ext_depth(inode); eh = path[depth].p_hdr; ex = path[depth].p_ext; @@ -2855,12 +2881,19 @@ static int ext4_split_unwritten_extents( ee_len = ext4_ext_get_actual_len(ex); allocated = ee_len - (iblock - ee_block); newblock = iblock - ee_block + ext_pblock(ex); + ex2 = ex; orig_ex.ee_block = ex->ee_block; orig_ex.ee_len = cpu_to_le16(ee_len); ext4_ext_store_pblock(&orig_ex, ext_pblock(ex)); /* + * It is safe to convert extent to initialized via explicit + * zeroout only if extent is fully insde i_size or new_size. + */ + may_zeroout = ee_block + ee_len <= eof_block; + + /* * If the uninitialized extent begins at the same logical * block where the write begins, and the write completely * covers the extent, then we don't need to split it. @@ -2894,7 +2927,7 @@ static int ext4_split_unwritten_extents( ex3->ee_len = cpu_to_le16(allocated - max_blocks); ext4_ext_mark_uninitialized(ex3); err = ext4_ext_insert_extent(handle, inode, path, ex3, flags); - if (err == -ENOSPC) { + if (err == -ENOSPC && may_zeroout) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) goto fix_extent_len; @@ -2918,8 +2951,10 @@ static int ext4_split_unwritten_extents( * update the extent length after successful insert of the * split extent */ - orig_ex.ee_len = cpu_to_le16(ee_len - - ext4_ext_get_actual_len(ex3)); + ee_len -= ext4_ext_get_actual_len(ex3); + orig_ex.ee_len = cpu_to_le16(ee_len); + may_zeroout = ee_block + ee_len <= eof_block; + depth = newdepth; ext4_ext_drop_refs(path); path = ext4_ext_find_extent(inode, iblock, path); @@ -2965,7 +3000,7 @@ static int ext4_split_unwritten_extents( goto out; insert: err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); - if (err == -ENOSPC) { + if (err == -ENOSPC && may_zeroout) { err = ext4_ext_zeroout(inode, &orig_ex); if (err) goto fix_extent_len; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/