diff mbox series

[f2fs-dev,v17,3/7] libfs: Introduce case-insensitive string comparison helper

Message ID 20240529082634.141286-4-eugen.hristev@collabora.com (mailing list archive)
State Superseded
Headers show
Series Case insensitive cleanup for ext4/f2fs | expand

Commit Message

Eugen Hristev May 29, 2024, 8:26 a.m. UTC
From: Gabriel Krisman Bertazi <krisman@collabora.com>

generic_ci_match can be used by case-insensitive filesystems to compare
strings under lookup with dirents in a case-insensitive way.  This
function is currently reimplemented by each filesystem supporting
casefolding, so this reduces code duplication in filesystem-specific
code.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
[eugen.hristev@collabora.com: rework to first test the exact match, cleanup
and add error message]
Signed-off-by: Eugen Hristev <eugen.hristev@collabora.com>
---
 fs/libfs.c         | 74 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h |  4 +++
 2 files changed, 78 insertions(+)

Comments

Eric Biggers May 31, 2024, 4:48 a.m. UTC | #1
On Wed, May 29, 2024 at 11:26:30AM +0300, Eugen Hristev via Linux-f2fs-devel wrote:
> +	/*
> +	 * Attempt a case-sensitive match first. It is cheaper and
> +	 * should cover most lookups, including all the sane
> +	 * applications that expect a case-sensitive filesystem.
> +	 */
> +
> +	if (dirent.len == (folded_name->name ? folded_name->len : name->len) &&
> +	    !memcmp(name->name, dirent.name, dirent.len))
> +		goto out;

Shouldn't it be just 'name->len' instead of
'(folded_name->name ? folded_name->len : name->len)'?

- Eric
Eugen Hristev May 31, 2024, 10:12 a.m. UTC | #2
On 5/31/24 07:48, Eric Biggers wrote:
> On Wed, May 29, 2024 at 11:26:30AM +0300, Eugen Hristev via Linux-f2fs-devel wrote:
>> +	/*
>> +	 * Attempt a case-sensitive match first. It is cheaper and
>> +	 * should cover most lookups, including all the sane
>> +	 * applications that expect a case-sensitive filesystem.
>> +	 */
>> +
>> +	if (dirent.len == (folded_name->name ? folded_name->len : name->len) &&
>> +	    !memcmp(name->name, dirent.name, dirent.len))
>> +		goto out;
> 
> Shouldn't it be just 'name->len' instead of
> '(folded_name->name ? folded_name->len : name->len)'?

Okay, I will change it. I am also waiting for other reviews to prepare the next
version.

Thanks for looking at this.

Eugen
> 
> - Eric
> _______________________________________________
> Kernel mailing list -- kernel@mailman.collabora.com
> To unsubscribe send an email to kernel-leave@mailman.collabora.com
> This list is managed by https://mailman.collabora.com
Gabriel Krisman Bertazi June 4, 2024, 7:18 p.m. UTC | #3
Eugen Hristev <eugen.hristev@collabora.com> writes:

> From: Gabriel Krisman Bertazi <krisman@collabora.com>
>
> generic_ci_match can be used by case-insensitive filesystems to compare
> strings under lookup with dirents in a case-insensitive way.  This
> function is currently reimplemented by each filesystem supporting
> casefolding, so this reduces code duplication in filesystem-specific
> code.
>
> Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
> [eugen.hristev@collabora.com: rework to first test the exact match, cleanup
> and add error message]
> Signed-off-by: Eugen Hristev <eugen.hristev@collabora.com>

Other than the origin of the length in memcmp mentioned by Eric, this patch
looks good to me now.

Thanks again for picking up this work!

> ---
>  fs/libfs.c         | 74 ++++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/fs.h |  4 +++
>  2 files changed, 78 insertions(+)
>
> diff --git a/fs/libfs.c b/fs/libfs.c
> index b635ee5adbcc..6a6cfa2d7d93 100644
> --- a/fs/libfs.c
> +++ b/fs/libfs.c
> @@ -1854,6 +1854,80 @@ static const struct dentry_operations generic_ci_dentry_ops = {
>  	.d_revalidate = fscrypt_d_revalidate,
>  #endif
>  };
> +
> +/**
> + * generic_ci_match() - Match a name (case-insensitively) with a dirent.
> + * This is a filesystem helper for comparison with directory entries.
> + * generic_ci_d_compare should be used in VFS' ->d_compare instead.
> + *
> + * @parent: Inode of the parent of the dirent under comparison
> + * @name: name under lookup.
> + * @folded_name: Optional pre-folded name under lookup
> + * @de_name: Dirent name.
> + * @de_name_len: dirent name length.
> + *
> + * Test whether a case-insensitive directory entry matches the filename
> + * being searched.  If @folded_name is provided, it is used instead of
> + * recalculating the casefold of @name.
> + *
> + * Return: > 0 if the directory entry matches, 0 if it doesn't match, or
> + * < 0 on error.
> + */
> +int generic_ci_match(const struct inode *parent,
> +		     const struct qstr *name,
> +		     const struct qstr *folded_name,
> +		     const u8 *de_name, u32 de_name_len)
> +{
> +	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 dirent = QSTR_INIT(de_name, de_name_len);
> +	int res = 0;
> +
> +	if (IS_ENCRYPTED(parent)) {
> +		const struct fscrypt_str encrypted_name =
> +			FSTR_INIT((u8 *) de_name, de_name_len);
> +
> +		if (WARN_ON_ONCE(!fscrypt_has_encryption_key(parent)))
> +			return -EINVAL;
> +
> +		decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
> +		if (!decrypted_name.name)
> +			return -ENOMEM;
> +		res = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name,
> +						&decrypted_name);
> +		if (res < 0) {
> +			kfree(decrypted_name.name);
> +			return res;
> +		}
> +		dirent.name = decrypted_name.name;
> +		dirent.len = decrypted_name.len;
> +	}
> +
> +	/*
> +	 * Attempt a case-sensitive match first. It is cheaper and
> +	 * should cover most lookups, including all the sane
> +	 * applications that expect a case-sensitive filesystem.
> +	 */
> +
> +	if (dirent.len == (folded_name->name ? folded_name->len : name->len) &&
> +	    !memcmp(name->name, dirent.name, dirent.len))
> +		goto out;
> +
> +	if (folded_name->name)
> +		res = utf8_strncasecmp_folded(um, folded_name, &dirent);
> +	else
> +		res = utf8_strncasecmp(um, name, &dirent);
> +
> +out:
> +	kfree(decrypted_name.name);
> +	if (res < 0 && sb_has_strict_encoding(sb)) {
> +		pr_err_ratelimited("Directory contains filename that is invalid UTF-8");
> +		return 0;
> +	}
> +	return !res;
> +}
> +EXPORT_SYMBOL(generic_ci_match);
>  #endif
>  
>  #ifdef CONFIG_FS_ENCRYPTION
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 639885621608..f8ca264a0edc 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -3367,6 +3367,10 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
>  extern int generic_check_addressable(unsigned, u64);
>  
>  extern void generic_set_sb_d_ops(struct super_block *sb);
> +extern int generic_ci_match(const struct inode *parent,
> +			    const struct qstr *name,
> +			    const struct qstr *folded_name,
> +			    const u8 *de_name, u32 de_name_len);
>  
>  static inline bool sb_has_encoding(const struct super_block *sb)
>  {
diff mbox series

Patch

diff --git a/fs/libfs.c b/fs/libfs.c
index b635ee5adbcc..6a6cfa2d7d93 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1854,6 +1854,80 @@  static const struct dentry_operations generic_ci_dentry_ops = {
 	.d_revalidate = fscrypt_d_revalidate,
 #endif
 };
+
+/**
+ * generic_ci_match() - Match a name (case-insensitively) with a dirent.
+ * This is a filesystem helper for comparison with directory entries.
+ * generic_ci_d_compare should be used in VFS' ->d_compare instead.
+ *
+ * @parent: Inode of the parent of the dirent under comparison
+ * @name: name under lookup.
+ * @folded_name: Optional pre-folded name under lookup
+ * @de_name: Dirent name.
+ * @de_name_len: dirent name length.
+ *
+ * Test whether a case-insensitive directory entry matches the filename
+ * being searched.  If @folded_name is provided, it is used instead of
+ * recalculating the casefold of @name.
+ *
+ * Return: > 0 if the directory entry matches, 0 if it doesn't match, or
+ * < 0 on error.
+ */
+int generic_ci_match(const struct inode *parent,
+		     const struct qstr *name,
+		     const struct qstr *folded_name,
+		     const u8 *de_name, u32 de_name_len)
+{
+	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 dirent = QSTR_INIT(de_name, de_name_len);
+	int res = 0;
+
+	if (IS_ENCRYPTED(parent)) {
+		const struct fscrypt_str encrypted_name =
+			FSTR_INIT((u8 *) de_name, de_name_len);
+
+		if (WARN_ON_ONCE(!fscrypt_has_encryption_key(parent)))
+			return -EINVAL;
+
+		decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
+		if (!decrypted_name.name)
+			return -ENOMEM;
+		res = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name,
+						&decrypted_name);
+		if (res < 0) {
+			kfree(decrypted_name.name);
+			return res;
+		}
+		dirent.name = decrypted_name.name;
+		dirent.len = decrypted_name.len;
+	}
+
+	/*
+	 * Attempt a case-sensitive match first. It is cheaper and
+	 * should cover most lookups, including all the sane
+	 * applications that expect a case-sensitive filesystem.
+	 */
+
+	if (dirent.len == (folded_name->name ? folded_name->len : name->len) &&
+	    !memcmp(name->name, dirent.name, dirent.len))
+		goto out;
+
+	if (folded_name->name)
+		res = utf8_strncasecmp_folded(um, folded_name, &dirent);
+	else
+		res = utf8_strncasecmp(um, name, &dirent);
+
+out:
+	kfree(decrypted_name.name);
+	if (res < 0 && sb_has_strict_encoding(sb)) {
+		pr_err_ratelimited("Directory contains filename that is invalid UTF-8");
+		return 0;
+	}
+	return !res;
+}
+EXPORT_SYMBOL(generic_ci_match);
 #endif
 
 #ifdef CONFIG_FS_ENCRYPTION
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 639885621608..f8ca264a0edc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3367,6 +3367,10 @@  extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 extern int generic_check_addressable(unsigned, u64);
 
 extern void generic_set_sb_d_ops(struct super_block *sb);
+extern int generic_ci_match(const struct inode *parent,
+			    const struct qstr *name,
+			    const struct qstr *folded_name,
+			    const u8 *de_name, u32 de_name_len);
 
 static inline bool sb_has_encoding(const struct super_block *sb)
 {