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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1270833748-14381-1-git-send-email-dmonakhov@openvz.org>
Date:	Fri,  9 Apr 2010 21:22:28 +0400
From:	Dmitry Monakhov <dmonakhov@...nvz.org>
To:	linux-ext4@...r.kernel.org
Cc:	aneesh.kumar@...ux.vnet.ibm.com, tytso@....edu,
	Dmitry Monakhov <dmonakhov@...nvz.org>
Subject: [PATCH] ext4: Do not zeroout uninitialized extents beyond i_size

Zerrout trick allow us to optimize cases where it is more reasonable
to explicitly zeroout extent and mark it as initialized instead of
splitting to several small ones.
But this optimization is not acceptable is extent is beyond i_size
Because it is not possible to have initialized blocks after i_size.
Fsck treat this as incorrect inode size.

BUG# 15742

Signed-off-by: Dmitry Monakhov <dmonakhov@...nvz.org>
---
 fs/ext4/extents.c |   49 ++++++++++++++++++++++++++++++++++++++-----------
 1 files changed, 38 insertions(+), 11 deletions(-)

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 8bdee27..bdf94f3 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2631,11 +2631,15 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	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 ",
+		inode->i_ino, (unsigned long long)iblock, max_blocks);
 
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
@@ -2644,16 +2648,25 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	ee_len = ext4_ext_get_actual_len(ex);
 	allocated = ee_len - (iblock - ee_block);
 	newblock = iblock - ee_block + ext_pblock(ex);
+	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+		inode->i_sb->s_blocksize_bits;
 	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 <= iblock + max_blocks ||
+		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;
@@ -2684,7 +2697,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	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.
@@ -2760,7 +2773,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		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;
@@ -2784,8 +2797,11 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		 * 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 <= iblock + max_blocks ||
+			ee_block + ee_len <= eof_block;
+
 		depth = newdepth;
 		ext4_ext_drop_refs(path);
 		path = ext4_ext_find_extent(inode, iblock, path);
@@ -2809,7 +2825,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		 * 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;
@@ -2878,7 +2894,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	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;
@@ -2938,14 +2954,16 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 	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,"
 		  "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;
@@ -2953,10 +2971,19 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 	ee_len = ext4_ext_get_actual_len(ex);
 	allocated = ee_len - (iblock - ee_block);
 	newblock = iblock - ee_block + ext_pblock(ex);
+	eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
+		inode->i_sb->s_blocksize_bits;
+
 	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 <= iblock + max_blocks ||
+		ee_block + ee_len <= eof_block;
 
 	/*
  	 * If the uninitialized extent begins at the same logical
@@ -2992,7 +3019,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 		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;
@@ -3063,7 +3090,7 @@ static int ext4_split_unwritten_extents(handle_t *handle,
 	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;
-- 
1.6.6.1

--
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

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ