Re: [PATCH v14 02/12] ext4: use the e2fsck limit for htree index nodes

[sashiko-bot@kernel.org]

> From: Artem Blagodarenko <artem.blagodarenko@gmail.com>
> 
> Since commit 471fbbea7ff7 ("ext4: handle casefolding with encryption"),
> dx_node_limit() passes the directory to ext4_dir_rec_len(), which for a
> casefolded+encrypted directory reserves 8 bytes for a hash in the fake
> dirent at the start of an index node.  That dirent never holds a name or
> a hash, and e2fsck computes the limit without it.  e2fsck also only
> treats a block as an index node when its limit has that value.
> 
> As a result, on a casefolded+encrypted directory deep enough to have
> index nodes, e2fsck reports the index nodes the kernel wrote as corrupt
> leaf blocks ("directory corrupted"), and the kernel refuses the index
> nodes that e2fsck -D wrote ("dx entry: limit 510 != node limit 509",
> 4k blocks with metadata_csum).
> 
> Compute the limit without the hash, as e2fsck does, and keep accepting
> the old value so that directories written by older kernels can still be
> read.  Older kernels already reject index nodes written by e2fsck -D;
> they will reject those written by this kernel in the same way.
> 
> Fixes: 471fbbea7ff7 ("ext4: handle casefolding with encryption")
> Signed-off-by: Artem Blagodarenko <artem.blagodarenko@gmail.com>

Sashiko has reviewed this patch and found no issues.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20261103134921.610047-1-ablagodarenko@thelustrecollective.com?part=2