The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to stable@vger.kernel.org.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x 2331fd4a49864e1571b4f50aa3aa1536ed6220d0 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to 'stable@vger.kernel.org' --in-reply-to '2024021911-vibes-blitz-7944@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
2331fd4a4986 ("ext4: avoid bb_free and bb_fragments inconsistency in mb_free_blocks()") c9b528c35795 ("ext4: regenerate buddy after block freeing failed if under fc replay") 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning") 4b68f6df1059 ("ext4: add MB_NUM_ORDERS macro") a6c75eaf1103 ("ext4: add mballoc stats proc file") b237e3044450 ("ext4: add ability to return parsed options from parse_options") 67d251860461 ("ext4: drop s_mb_bal_lock and convert protected fields to atomic") 6bd97bf273bd ("ext4: remove redundant mb_regenerate_buddy()") a72b38eebea4 ("ext4: handle dax mount option collision") 99c880decf27 ("ext4: cleanup fast commit mount options") 0f0672ffb61a ("ext4: add a mount opt to forcefully turn fast commits on") 8016e29f4362 ("ext4: fast commit recovery path") 5b849b5f96b4 ("jbd2: fast commit recovery path") aa75f4d3daae ("ext4: main fast-commit commit path") ff780b91efe9 ("jbd2: add fast commit machinery") 6866d7b3f2bb ("ext4 / jbd2: add fast commit initialization") 995a3ed67fc8 ("ext4: add fast_commit feature and handling for extended mount options") 2d069c0889ef ("ext4: use common helpers in all places reading metadata buffers") d9befedaafcf ("ext4: clear buffer verified flag if read meta block from disk") 15ed2851b0f4 ("ext4: remove unused argument from ext4_(inc|dec)_count")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 2331fd4a49864e1571b4f50aa3aa1536ed6220d0 Mon Sep 17 00:00:00 2001 From: Baokun Li libaokun1@huawei.com Date: Thu, 4 Jan 2024 22:20:36 +0800 Subject: [PATCH] ext4: avoid bb_free and bb_fragments inconsistency in mb_free_blocks()
After updating bb_free in mb_free_blocks, it is possible to return without updating bb_fragments because the block being freed is found to have already been freed, which leads to inconsistency between bb_free and bb_fragments.
Since the group may be unlocked in ext4_grp_locked_error(), this can lead to problems such as dividing by zero when calculating the average fragment length. Hence move the update of bb_free to after the block double-free check guarantees that the corresponding statistics are updated only after the core block bitmap is modified.
Fixes: eabe0444df90 ("ext4: speed-up releasing blocks on commit") CC: stable@vger.kernel.org # 3.10 Suggested-by: Jan Kara jack@suse.cz Signed-off-by: Baokun Li libaokun1@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20240104142040.2835097-5-libaokun1@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c97ad0e77831..fa351aa323dc 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1909,11 +1909,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count);
- this_cpu_inc(discard_pa_seq); - e4b->bd_info->bb_free += count; - if (first < e4b->bd_info->bb_first_free) - e4b->bd_info->bb_first_free = first; - /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ @@ -1927,23 +1922,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr;
+ /* + * Fastcommit replay can free already freed blocks which + * corrupts allocation info. Regenerate it. + */ + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + mb_regenerate_buddy(e4b); + goto check; + } + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); - if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block (bit %u); block bitmap corrupt.", - block); - ext4_mark_group_bitmap_corrupted( - sb, e4b->bd_group, + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, blocknr, + "freeing already freed block (bit %u); block bitmap corrupt.", + block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); - } else { - mb_regenerate_buddy(e4b); - } - goto done; + return; }
+ this_cpu_inc(discard_pa_seq); + e4b->bd_info->bb_free += count; + if (first < e4b->bd_info->bb_first_free) + e4b->bd_info->bb_first_free = first; + /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; @@ -1968,9 +1971,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1);
-done: mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); +check: mb_check_buddy(e4b); }