Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757272Ab2J1Xa4 (ORCPT ); Sun, 28 Oct 2012 19:30:56 -0400 Received: from shadbolt.e.decadent.org.uk ([88.96.1.126]:42224 "EHLO shadbolt.e.decadent.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757037Ab2J1X2b (ORCPT ); Sun, 28 Oct 2012 19:28:31 -0400 Message-Id: <20121028231547.747971375@decadent.org.uk> User-Agent: quilt/0.60-1 Date: Sun, 28 Oct 2012 23:16:11 +0000 From: Ben Hutchings To: linux-kernel@vger.kernel.org, stable@vger.kernel.org Cc: akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk, Dmitry Monakhov , "Theodore Tso" Subject: [ 035/105] ext4: race-condition protection for ext4_convert_unwritten_extents_endio In-Reply-To: <20121028231536.970033833@decadent.org.uk> X-SA-Exim-Connect-IP: 2001:470:1f08:1539:21c:bfff:fe03:f805 X-SA-Exim-Mail-From: ben@decadent.org.uk X-SA-Exim-Scanned: No (on shadbolt.decadent.org.uk); SAEximRunCond expanded to false Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5742 Lines: 159 3.2-stable review patch. If anyone has any objections, please let me know. ------------------ From: Dmitry Monakhov commit dee1f973ca341c266229faa5a1a5bb268bed3531 upstream. We assumed that at the time we call ext4_convert_unwritten_extents_endio() extent in question is fully inside [map.m_lblk, map->m_len] because it was already split during submission. But this may not be true due to a race between writeback vs fallocate. If extent in question is larger than requested we will split it again. Special precautions should being done if zeroout required because [map.m_lblk, map->m_len] already contains valid data. Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" [bwh: Backported to 3.2: adjust context] Signed-off-by: Ben Hutchings --- fs/ext4/extents.c | 57 ++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 46 insertions(+), 11 deletions(-) --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2715,6 +2715,9 @@ static int ext4_ext_zeroout(struct inode #define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */ #define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */ +#define EXT4_EXT_DATA_VALID1 0x8 /* first half contains valid data */ +#define EXT4_EXT_DATA_VALID2 0x10 /* second half contains valid data */ + /* * ext4_split_extent_at() splits an extent at given block. * @@ -2750,6 +2753,9 @@ static int ext4_split_extent_at(handle_t unsigned int ee_len, depth; int err = 0; + BUG_ON((split_flag & (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)) == + (EXT4_EXT_DATA_VALID1 | EXT4_EXT_DATA_VALID2)); + ext_debug("ext4_split_extents_at: inode %lu, logical" "block %llu\n", inode->i_ino, (unsigned long long)split); @@ -2808,7 +2814,14 @@ static int ext4_split_extent_at(handle_t err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) { - err = ext4_ext_zeroout(inode, &orig_ex); + if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) { + if (split_flag & EXT4_EXT_DATA_VALID1) + err = ext4_ext_zeroout(inode, ex2); + else + err = ext4_ext_zeroout(inode, ex); + } else + err = ext4_ext_zeroout(inode, &orig_ex); + if (err) goto fix_extent_len; /* update the extent length and mark as initialized */ @@ -2861,12 +2874,13 @@ static int ext4_split_extent(handle_t *h uninitialized = ext4_ext_is_uninitialized(ex); if (map->m_lblk + map->m_len < ee_block + ee_len) { - split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ? - EXT4_EXT_MAY_ZEROOUT : 0; + split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT; flags1 = flags | EXT4_GET_BLOCKS_PRE_IO; if (uninitialized) split_flag1 |= EXT4_EXT_MARK_UNINIT1 | EXT4_EXT_MARK_UNINIT2; + if (split_flag & EXT4_EXT_DATA_VALID2) + split_flag1 |= EXT4_EXT_DATA_VALID1; err = ext4_split_extent_at(handle, inode, path, map->m_lblk + map->m_len, split_flag1, flags1); if (err) @@ -2879,8 +2893,8 @@ static int ext4_split_extent(handle_t *h return PTR_ERR(path); if (map->m_lblk >= ee_block) { - split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT ? - EXT4_EXT_MAY_ZEROOUT : 0; + split_flag1 = split_flag & (EXT4_EXT_MAY_ZEROOUT | + EXT4_EXT_DATA_VALID2); if (uninitialized) split_flag1 |= EXT4_EXT_MARK_UNINIT1; if (split_flag & EXT4_EXT_MARK_UNINIT2) @@ -3158,26 +3172,47 @@ static int ext4_split_unwritten_extents( split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; split_flag |= EXT4_EXT_MARK_UNINIT2; - + if (flags & EXT4_GET_BLOCKS_CONVERT) + split_flag |= EXT4_EXT_DATA_VALID2; flags |= EXT4_GET_BLOCKS_PRE_IO; return ext4_split_extent(handle, inode, path, map, split_flag, flags); } static int ext4_convert_unwritten_extents_endio(handle_t *handle, - struct inode *inode, - struct ext4_ext_path *path) + struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path) { struct ext4_extent *ex; + ext4_lblk_t ee_block; + unsigned int ee_len; int depth; int err = 0; depth = ext_depth(inode); ex = path[depth].p_ext; + ee_block = le32_to_cpu(ex->ee_block); + ee_len = ext4_ext_get_actual_len(ex); ext_debug("ext4_convert_unwritten_extents_endio: inode %lu, logical" "block %llu, max_blocks %u\n", inode->i_ino, - (unsigned long long)le32_to_cpu(ex->ee_block), - ext4_ext_get_actual_len(ex)); + (unsigned long long)ee_block, ee_len); + + /* If extent is larger than requested then split is required */ + if (ee_block != map->m_lblk || ee_len > map->m_len) { + err = ext4_split_unwritten_extents(handle, inode, map, path, + EXT4_GET_BLOCKS_CONVERT); + if (err < 0) + goto out; + ext4_ext_drop_refs(path); + path = ext4_ext_find_extent(inode, map->m_lblk, path); + if (IS_ERR(path)) { + err = PTR_ERR(path); + goto out; + } + depth = ext_depth(inode); + ex = path[depth].p_ext; + } err = ext4_ext_get_access(handle, inode, path + depth); if (err) @@ -3479,7 +3514,7 @@ ext4_ext_handle_uninitialized_extents(ha } /* IO end_io complete, convert the filled extent to written */ if ((flags & EXT4_GET_BLOCKS_CONVERT)) { - ret = ext4_convert_unwritten_extents_endio(handle, inode, + ret = ext4_convert_unwritten_extents_endio(handle, inode, map, path); if (ret >= 0) { ext4_update_inode_fsync_trans(handle, inode, 1); -- 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/