ext4: mark block group as corrupt on block bitmap error
When we notice a block-bitmap corruption (because of device failure or
something else), we should mark this group as corrupt and prevent
further block allocations/deallocations from it. Currently, we end up
generating one error message for every block in the bitmap. This
potentially could make the system unstable as noticed in some
bugs. With this patch, the error will be printed only the first time
and mark the entire block group as corrupted. This prevents future
access allocations/deallocations from it.
Also tested by corrupting the block
bitmap and forcefully introducing the mb_free_blocks error:
(1) create a largefile (2Gb)
$ dd if=/dev/zero of=largefile oflag=direct bs=10485760 count=200
(2) umount filesystem. use dumpe2fs to see which block-bitmaps
are in use by largefile and note their block numbers
(3) use dd to zero-out the used block bitmaps
$ dd if=/dev/zero of=/dev/hdc4 bs=4096 seek=14 count=8 oflag=direct
(4) mount the FS and delete the largefile.
(5) recreate the largefile. verify that the new largefile does not
get any blocks from the groups marked as bad.
Without the patch, we will see mb_free_blocks error for each bit in
each zero'ed out bitmap at (4). With the patch, we only see the error
once per blockgroup:
[ 309.706803] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 15: 32768 clusters in bitmap, 0 in gd. blk grp corrupted.
[ 309.720824] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 14: 32768 clusters in bitmap, 0 in gd. blk grp corrupted.
[ 309.732858] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure
[ 309.748321] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 13: 32768 clusters in bitmap, 0 in gd. blk grp corrupted.
[ 309.760331] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure
[ 309.769695] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 12: 32768 clusters in bitmap, 0 in gd. blk grp corrupted.
[ 309.781721] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure
[ 309.798166] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 11: 32768 clusters in bitmap, 0 in gd. blk grp corrupted.
[ 309.810184] EXT4-fs error (device sdb4) in ext4_free_blocks:4802: IO failure
[ 309.819532] EXT4-fs error (device sdb4): ext4_mb_generate_buddy:735: group 10: 32768 clusters in bitmap, 0 in gd. blk grp corrupted.
Google-Bug-Id: 7258357
[darrick.wong@oracle.com]
Further modifications (by Darrick) to make more obvious that this corruption
bit applies to blocks only. Set the corruption flag if the block group bitmap
verification fails.
Original-author: Aditya Kali <adityakali@google.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index a40b1f9..d9b66c4 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -356,6 +356,7 @@
struct buffer_head *bh)
{
ext4_fsblk_t blk;
+ struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
if (buffer_verified(bh))
return;
@@ -366,12 +367,14 @@
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
block_group, blk);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
return;
}
if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
desc, bh))) {
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
return;
}
set_buffer_verified(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2e58182..02b764b 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2480,9 +2480,12 @@
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
+#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp) \
+ (test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_WAS_TRIMMED(grp) \
(test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index aa7d058..a41e3ba 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -751,13 +751,15 @@
if (free != grp->bb_free) {
ext4_grp_locked_error(sb, group, 0, 0,
- "%u clusters in bitmap, %u in gd",
+ "%u clusters in bitmap, %u in gd; "
+ "block bitmap corrupt.",
free, grp->bb_free);
/*
- * If we intent to continue, we consider group descritor
+ * If we intend to continue, we consider group descriptor
* corrupt and update bb_free using bitmap value
*/
grp->bb_free = free;
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
}
mb_set_largest_free_order(sb, grp);
@@ -1398,6 +1400,10 @@
BUG_ON(last >= (sb->s_blocksize << 3));
assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
+ /* Don't bother if the block group is corrupt. */
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+ return;
+
mb_check_buddy(e4b);
mb_free_blocks_double(inode, e4b, first, count);
@@ -1423,7 +1429,11 @@
inode ? inode->i_ino : 0,
blocknr,
"freeing already freed block "
- "(bit %u)", block);
+ "(bit %u); block bitmap corrupt.",
+ block);
+ /* Mark the block group as corrupt. */
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+ &e4b->bd_info->bb_state);
mb_regenerate_buddy(e4b);
goto done;
}
@@ -1790,6 +1800,11 @@
if (err)
return err;
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
+ ext4_mb_unload_buddy(e4b);
+ return 0;
+ }
+
ext4_lock_group(ac->ac_sb, group);
max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
ac->ac_g_ex.fe_len, &ex);
@@ -1987,6 +2002,9 @@
if (cr <= 2 && free < ac->ac_g_ex.fe_len)
return 0;
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
+ return 0;
+
/* We only do this if the grp has never been initialized */
if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
int ret = ext4_mb_init_group(ac->ac_sb, group);
@@ -4674,6 +4692,10 @@
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(
+ ext4_get_group_info(sb, block_group))))
+ return;
+
/*
* Check to see if we are freeing blocks across a group
* boundary.