Received-SPF: pass (google.com: domain of linux-ext4+bounces-2771-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: Gabriel Krisman Bertazi <krisman@suse.de>
To: Eugen Hristev <eugen.hristev@collabora.com>
Cc: linux-ext4@vger.kernel.org,  linux-kernel@vger.kernel.org,
  linux-f2fs-devel@lists.sourceforge.net,  linux-fsdevel@vger.kernel.org,
  jaegeuk@kernel.org,  adilger.kernel@dilger.ca,  tytso@mit.edu,
  chao@kernel.org,  viro@zeniv.linux.org.uk,  brauner@kernel.org,
  jack@suse.cz,  ebiggers@google.com,  kernel@collabora.com,  Gabriel
 Krisman Bertazi <krisman@collabora.com>
Subject: Re: [PATCH v17 4/7] ext4: Reuse generic_ci_match for ci comparisons
In-Reply-To: <20240529082634.141286-5-eugen.hristev@collabora.com> (Eugen
	Hristev's message of "Wed, 29 May 2024 11:26:31 +0300")
Organization: SUSE
References: <20240529082634.141286-1-eugen.hristev@collabora.com>
	<20240529082634.141286-5-eugen.hristev@collabora.com>
Date: Tue, 04 Jun 2024 15:17:41 -0400
Message-ID: <87cyowldpm.fsf@mailhost.krisman.be>
User-Agent: Gnus/5.13 (Gnus v5.13)
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain

Eugen Hristev <eugen.hristev@collabora.com> writes:

> From: Gabriel Krisman Bertazi <krisman@collabora.com>
>
> Instead of reimplementing ext4_match_ci, use the new libfs helper.
>
> It also adds a comment explaining why fname->cf_name.name must be
> checked prior to the encryption hash optimization, because that tripped
> me before.
>
> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
> Signed-off-by: Eugen Hristev <eugen.hristev@collabora.com>
> Reviewed-by: Eric Biggers <ebiggers@google.com>
> ---
>  fs/ext4/namei.c | 91 +++++++++++++++----------------------------------
>  1 file changed, 27 insertions(+), 64 deletions(-)
>
> diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
> index ec4c9bfc1057..20668741a23c 100644
> --- a/fs/ext4/namei.c
> +++ b/fs/ext4/namei.c
> @@ -1390,58 +1390,6 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
>  }
>  
>  #if IS_ENABLED(CONFIG_UNICODE)
> -/*
> - * Test whether a case-insensitive directory entry matches the filename
> - * being searched for.  If quick is set, assume the name being looked up
> - * is already in the casefolded form.
> - *
> - * Returns: 0 if the directory entry matches, more than 0 if it
> - * doesn't match or less than zero on error.
> - */
> -static int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
> -			   u8 *de_name, size_t de_name_len, bool quick)
> -{
> -	const struct super_block *sb = parent->i_sb;
> -	const struct unicode_map *um = sb->s_encoding;
> -	struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
> -	struct qstr entry = QSTR_INIT(de_name, de_name_len);
> -	int ret;
> -
> -	if (IS_ENCRYPTED(parent)) {
> -		const struct fscrypt_str encrypted_name =
> -				FSTR_INIT(de_name, de_name_len);
> -
> -		decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
> -		if (!decrypted_name.name)
> -			return -ENOMEM;
> -		ret = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name,
> -						&decrypted_name);
> -		if (ret < 0)
> -			goto out;
> -		entry.name = decrypted_name.name;
> -		entry.len = decrypted_name.len;
> -	}
> -
> -	if (quick)
> -		ret = utf8_strncasecmp_folded(um, name, &entry);
> -	else
> -		ret = utf8_strncasecmp(um, name, &entry);
> -	if (ret < 0) {
> -		/* Handle invalid character sequence as either an error
> -		 * or as an opaque byte sequence.
> -		 */
> -		if (sb_has_strict_encoding(sb))
> -			ret = -EINVAL;
> -		else if (name->len != entry.len)
> -			ret = 1;
> -		else
> -			ret = !!memcmp(name->name, entry.name, entry.len);
> -	}
> -out:
> -	kfree(decrypted_name.name);
> -	return ret;
> -}
> -
>  int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
>  				  struct ext4_filename *name)
>  {
> @@ -1503,20 +1451,35 @@ static bool ext4_match(struct inode *parent,
>  #if IS_ENABLED(CONFIG_UNICODE)
>  	if (IS_CASEFOLDED(parent) &&
>  	    (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) {
> -		if (fname->cf_name.name) {
> -			if (IS_ENCRYPTED(parent)) {
> -				if (fname->hinfo.hash != EXT4_DIRENT_HASH(de) ||
> -					fname->hinfo.minor_hash !=
> -						EXT4_DIRENT_MINOR_HASH(de)) {
> +		int ret;
>  
> -					return false;
> -				}
> -			}
> -			return !ext4_ci_compare(parent, &fname->cf_name,
> -						de->name, de->name_len, true);
> +		/*
> +		 * Just checking IS_ENCRYPTED(parent) below is not
> +		 * sufficient to decide whether one can use the hash for
> +		 * skipping the string comparison, because the key might
> +		 * have been added right after
> +		 * ext4_fname_setup_ci_filename().  In this case, a hash
> +		 * mismatch will be a false negative.  Therefore, make
> +		 * sure cf_name was properly initialized before
> +		 * considering the calculated hash.
> +		 */
> +		if (IS_ENCRYPTED(parent) && fname->cf_name.name &&
> +		    (fname->hinfo.hash != EXT4_DIRENT_HASH(de) ||
> +		     fname->hinfo.minor_hash != EXT4_DIRENT_MINOR_HASH(de)))
> +			return false;
> +
> +		ret = generic_ci_match(parent, fname->usr_fname,
> +				       &fname->cf_name, de->name,
> +				       de->name_len);
> +		if (ret < 0) {
> +			/*
> +			 * Treat comparison errors as not a match.  The
> +			 * only case where it happens is on a disk
> +			 * corruption or ENOMEM.
> +			 */
> +			return false;
>  		}
> -		return !ext4_ci_compare(parent, fname->usr_fname, de->name,
> -						de->name_len, false);

With the changes to patch 3 in this iteration, This could become:

/*
 * Treat comparison errors as not a match.  The
 * only case where it happens is disk corruption
 * or ENOMEM.
 */
return ext4_ci_compare(parent, fname->usr_fname, de->name,
		       de->name_len, false) > 0;

-- 
Gabriel Krisman Bertazi