On Aug 3, 2023, at 12:09 AM, zhangshida <[email protected]> wrote:
>
> From: Shida Zhang <[email protected]>
>
> With the configuration PAGE_SIZE 64k and filesystem blocksize 64k,
> a problem occurred when more than 13 million files were directly created
> under a directory:
>
> EXT4-fs error (device xx): ext4_dx_csum_set:492: inode #xxxx: comm xxxxx: dir seems corrupt? Run e2fsck -D.
> EXT4-fs error (device xx): ext4_dx_csum_verify:463: inode #xxxx: comm xxxxx: dir seems corrupt? Run e2fsck -D.
> EXT4-fs error (device xx): dx_probe:856: inode #xxxx: block 8188: comm xxxxx: Directory index failed checksum
>
> When enough files are created, the fake_dirent->reclen will be 0xffff.
> it doesn't equal to the blocksize 65536, i.e. 0x10000.
>
> But it is not the same condition when blocksize equals to 4k.
> when enough files are created, the fake_dirent->reclen will be 0x1000.
> it equals to the blocksize 4k, i.e. 0x1000.
>
> The problem seems to be related to the limitation of the 16-bit field
> when the blocksize is set to 64k.
> To address this, helpers like ext4_rec_len_{from,to}_disk has already
> been introduced to complete the conversion between the encoded and the
> plain form of rec_len.
>
> So fix this one by using the helper, and all the other in this file too.
>
> Cc: [email protected]
> Fixes: dbe89444042a ("ext4: Calculate and verify checksums for htree nodes")
> Suggested-by: Andreas Dilger <[email protected]>
> Suggested-by: Darrick J. Wong <[email protected]>
> Signed-off-by: Shida Zhang <[email protected]>
Thanks for the updated patch. You can add:
Reviewed-by: Andreas Dilger <[email protected]>
> ---
> v3->v4:
> 1,Convert all the other rec_len, litrerally.
> 2,Lift a helper output to a local variable.
> --Suggested by Darrick.
> v2->v3:
> 1,Convert all the other rec_len if necessary, as suggested by Darrick.
> 2,Rephrase the commit message.
> v1->v2:
> Use the existing helper to covert the rec_len, as suggested by Andreas.
>
> fs/ext4/namei.c | 26 +++++++++++++++-----------
> 1 file changed, 15 insertions(+), 11 deletions(-)
>
> diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
> index 0caf6c730ce3..34fb2d1e66aa 100644
> --- a/fs/ext4/namei.c
> +++ b/fs/ext4/namei.c
> @@ -343,17 +343,17 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
> struct buffer_head *bh)
> {
> struct ext4_dir_entry_tail *t;
> + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);
>
> #ifdef PARANOID
> struct ext4_dir_entry *d, *top;
>
> d = (struct ext4_dir_entry *)bh->b_data;
> top = (struct ext4_dir_entry *)(bh->b_data +
> - (EXT4_BLOCK_SIZE(inode->i_sb) -
> - sizeof(struct ext4_dir_entry_tail)));
> - while (d < top && d->rec_len)
> + (blocksize - sizeof(struct ext4_dir_entry_tail)));
> + while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize))
> d = (struct ext4_dir_entry *)(((void *)d) +
> - le16_to_cpu(d->rec_len));
> + ext4_rec_len_from_disk(d->rec_len, blocksize));
>
> if (d != top)
> return NULL;
> @@ -364,7 +364,8 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
> #endif
>
> if (t->det_reserved_zero1 ||
> - le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) ||
> + (ext4_rec_len_from_disk(t->det_rec_len, blocksize) !=
> + sizeof(struct ext4_dir_entry_tail)) ||
> t->det_reserved_zero2 ||
> t->det_reserved_ft != EXT4_FT_DIR_CSUM)
> return NULL;
> @@ -445,13 +446,14 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode,
> struct ext4_dir_entry *dp;
> struct dx_root_info *root;
> int count_offset;
> + int blocksize = EXT4_BLOCK_SIZE(inode->i_sb);
> + unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize);
>
> - if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb))
> + if (rlen == blocksize)
> count_offset = 8;
> - else if (le16_to_cpu(dirent->rec_len) == 12) {
> + else if (rlen == 12) {
> dp = (struct ext4_dir_entry *)(((void *)dirent) + 12);
> - if (le16_to_cpu(dp->rec_len) !=
> - EXT4_BLOCK_SIZE(inode->i_sb) - 12)
> + if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12)
> return NULL;
> root = (struct dx_root_info *)(((void *)dp + 12));
> if (root->reserved_zero ||
> @@ -1315,6 +1317,7 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh,
> unsigned int buflen = bh->b_size;
> char *base = bh->b_data;
> struct dx_hash_info h = *hinfo;
> + int blocksize = EXT4_BLOCK_SIZE(dir->i_sb);
>
> if (ext4_has_metadata_csum(dir->i_sb))
> buflen -= sizeof(struct ext4_dir_entry_tail);
> @@ -1335,11 +1338,12 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh,
> map_tail--;
> map_tail->hash = h.hash;
> map_tail->offs = ((char *) de - base)>>2;
> - map_tail->size = le16_to_cpu(de->rec_len);
> + map_tail->size = ext4_rec_len_from_disk(de->rec_len,
> + blocksize);
> count++;
> cond_resched();
> }
> - de = ext4_next_entry(de, dir->i_sb->s_blocksize);
> + de = ext4_next_entry(de, blocksize);
> }
> return count;
> }
> --
> 2.27.0
>
Cheers, Andreas