| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20130104072533.GD31130@gmail.com>
Date: Fri, 4 Jan 2013 15:25:33 +0800
From: Zheng Liu <gnehzuil.liu@...il.com>
To: Jan Kara <jack@...e.cz>
Cc: Ted Tso <tytso@....edu>, linux-ext4@...r.kernel.org
Subject: Re: [PATCH 4/5] ext4: Disable merging of uninitialized extents
On Wed, Jan 02, 2013 at 06:45:43PM +0100, Jan Kara wrote:
> Merging of uninitialized extents creates all sorts of interesting race
> possibilities when writeback / DIO races with fallocate. Thus
> ext4_convert_unwritten_extents_endio() has to deal with a case where
> extent to be converted needs to be split out first. That isn't nice
> for two reasons:
>
> 1) It may need allocation of extent tree block so ENOSPC is possible.
> 2) It complicates end_io handling code
>
> So we disable merging of uninitialized extents which allows us to simplify
> the code. Extents will get merged after they are converted to initialized
> ones.
>
> Signed-off-by: Jan Kara <jack@...e.cz>
Reviewed-by: Zheng Liu <wenqing.lz@...bao.com>
Regards,
- Zheng
> ---
> fs/ext4/extents.c | 61 +++++++++++++++-------------------------------------
> 1 files changed, 18 insertions(+), 43 deletions(-)
>
> diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
> index 26af228..f1ce33a 100644
> --- a/fs/ext4/extents.c
> +++ b/fs/ext4/extents.c
> @@ -54,9 +54,6 @@
> #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 */
> -
> static __le32 ext4_extent_block_csum(struct inode *inode,
> struct ext4_extent_header *eh)
> {
> @@ -1579,20 +1576,17 @@ int
> ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
> struct ext4_extent *ex2)
> {
> - unsigned short ext1_ee_len, ext2_ee_len, max_len;
> + unsigned ext1_ee_len, ext2_ee_len;
>
> /*
> - * Make sure that either both extents are uninitialized, or
> - * both are _not_.
> + * Make sure that both extents are initialized. We don't merge
> + * uninitialized extents so that we can be sure that end_io code has
> + * the extent that was written properly split out and conversion to
> + * initialized is trivial.
> */
> - if (ext4_ext_is_uninitialized(ex1) ^ ext4_ext_is_uninitialized(ex2))
> + if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
> return 0;
>
> - if (ext4_ext_is_uninitialized(ex1))
> - max_len = EXT_UNINIT_MAX_LEN;
> - else
> - max_len = EXT_INIT_MAX_LEN;
> -
> ext1_ee_len = ext4_ext_get_actual_len(ex1);
> ext2_ee_len = ext4_ext_get_actual_len(ex2);
>
> @@ -1605,7 +1599,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
> * as an RO_COMPAT feature, refuse to merge to extents if
> * this can result in the top bit of ee_len being set.
> */
> - if (ext1_ee_len + ext2_ee_len > max_len)
> + if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
> return 0;
> #ifdef AGGRESSIVE_TEST
> if (ext1_ee_len >= 4)
> @@ -2959,9 +2953,6 @@ static int ext4_split_extent_at(handle_t *handle,
> 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);
>
> @@ -3020,14 +3011,7 @@ static int ext4_split_extent_at(handle_t *handle,
>
> err = ext4_ext_insert_extent(handle, inode, path, &newex, flags);
> if (err == -ENOSPC && (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
> - 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);
> -
> + err = ext4_ext_zeroout(inode, &orig_ex);
> if (err)
> goto fix_extent_len;
> /* update the extent length and mark as initialized */
> @@ -3085,8 +3069,6 @@ static int ext4_split_extent(handle_t *handle,
> 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)
> @@ -3099,8 +3081,7 @@ static int ext4_split_extent(handle_t *handle,
> return PTR_ERR(path);
>
> if (map->m_lblk >= ee_block) {
> - split_flag1 = split_flag & (EXT4_EXT_MAY_ZEROOUT |
> - EXT4_EXT_DATA_VALID2);
> + split_flag1 = split_flag & EXT4_EXT_MAY_ZEROOUT;
> if (uninitialized)
> split_flag1 |= EXT4_EXT_MARK_UNINIT1;
> if (split_flag & EXT4_EXT_MARK_UNINIT2)
> @@ -3379,8 +3360,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
>
> 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);
> }
> @@ -3405,20 +3385,15 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
> "block %llu, max_blocks %u\n", inode->i_ino,
> (unsigned long long)ee_block, ee_len);
>
> - /* If extent is larger than requested then split is required */
> + /* Extent is larger than requested? */
> 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;
> + EXT4_ERROR_INODE(inode, "Written extent modified before IO"
> + " finished: extent logical block %llu, len %u; IO"
> + " logical block %llu, len %u\n",
> + (unsigned long long)ee_block, ee_len,
> + (unsigned long long)map->m_lblk, map->m_len);
> + err = -EIO;
> + goto out;
> }
>
> err = ext4_ext_get_access(handle, inode, path + depth);
> --
> 1.7.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists