[v11,2/4] fs: Add standard casefolding support
diff mbox series

Message ID 20200708030552.3829094-3-drosen@google.com
State Superseded
Headers show
Series
  • Prepare for upcoming Casefolding/Encryption patches
Related show

Commit Message

Daniel Rosenberg July 8, 2020, 3:05 a.m. UTC
This adds general supporting functions for filesystems that use
utf8 casefolding. It provides standard dentry_operations and adds the
necessary structures in struct super_block to allow this standardization.

The new dentry operations are functionally equivalent to the existing
operations in ext4 and f2fs, apart from the use of utf8_casefold_hash to
avoid an allocation.

By providing a common implementation, all users can benefit from any
optimizations without needing to port over improvements.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/libfs.c         | 94 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h | 16 ++++++++
 2 files changed, 110 insertions(+)

Comments

Eric Biggers July 8, 2020, 4:12 a.m. UTC | #1
On Tue, Jul 07, 2020 at 08:05:50PM -0700, Daniel Rosenberg wrote:
> +/**
> + * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems
> + * @dentry:	dentry whose name we are checking against
> + * @len:	len of name of dentry
> + * @str:	str pointer to name of dentry
> + * @name:	Name to compare against
> + *
> + * Return: 0 if names match, 1 if mismatch, or -ERRNO
> + */
> +int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
> +			  const char *str, const struct qstr *name)
> +{
> +	const struct dentry *parent = READ_ONCE(dentry->d_parent);
> +	const struct inode *inode = READ_ONCE(parent->d_inode);

How about calling the 'inode' variable 'dir' instead?

That would help avoid confusion about what is the directory and what is a file
in the directory.

Likewise in generic_ci_d_hash().

> +/**
> + * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
> + * @dentry:	dentry whose name we are hashing

This comment for @dentry needs to be updated.

It's the parent dentry, not the dentry whose name we are hashing.

> + * @str:	qstr of name whose hash we should fill in
> + *
> + * Return: 0 if hash was successful, or -ERRNO

As I mentioned on v9, this can also return 0 if the hashing was not done because
it wants to fallback to the standard hashing.  Can you please fix the comment?

> +int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
> +{
> +	const struct inode *inode = READ_ONCE(dentry->d_inode);
> +	struct super_block *sb = dentry->d_sb;
> +	const struct unicode_map *um = sb->s_encoding;
> +	int ret = 0;
> +
> +	if (!inode || !needs_casefold(inode))
> +		return 0;
> +
> +	ret = utf8_casefold_hash(um, dentry, str);
> +	if (ret < 0)
> +		goto err;
> +
> +	return 0;
> +err:
> +	if (sb_has_strict_encoding(sb))
> +		ret = -EINVAL;
> +	else
> +		ret = 0;
> +	return ret;
> +}

On v9, Gabriel suggested simplifying this to:

	ret = utf8_casefold_hash(um, dentry, str);
	if (ret < 0 && sb_has_enc_strict_mode(sb))
		return -EINVAL;
	return 0;

Any reason not to do that?

- Eric
Daniel Rosenberg July 8, 2020, 8:36 a.m. UTC | #2
On Tue, Jul 7, 2020 at 9:12 PM Eric Biggers <ebiggers@kernel.org> wrote:
>
> On Tue, Jul 07, 2020 at 08:05:50PM -0700, Daniel Rosenberg wrote:
> > +/**
> > + * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems
> > + * @dentry:  dentry whose name we are checking against
> > + * @len:     len of name of dentry
> > + * @str:     str pointer to name of dentry
> > + * @name:    Name to compare against
> > + *
> > + * Return: 0 if names match, 1 if mismatch, or -ERRNO
> > + */
> > +int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
> > +                       const char *str, const struct qstr *name)
> > +{
> > +     const struct dentry *parent = READ_ONCE(dentry->d_parent);
> > +     const struct inode *inode = READ_ONCE(parent->d_inode);
>
> How about calling the 'inode' variable 'dir' instead?
>
> That would help avoid confusion about what is the directory and what is a file
> in the directory.
>
> Likewise in generic_ci_d_hash().
>
> > +/**
> > + * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
> > + * @dentry:  dentry whose name we are hashing
>
> This comment for @dentry needs to be updated.
>
> It's the parent dentry, not the dentry whose name we are hashing.
>
> > + * @str:     qstr of name whose hash we should fill in
> > + *
> > + * Return: 0 if hash was successful, or -ERRNO
>
> As I mentioned on v9, this can also return 0 if the hashing was not done because
> it wants to fallback to the standard hashing.  Can you please fix the comment?
>
> > +int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
> > +{
> > +     const struct inode *inode = READ_ONCE(dentry->d_inode);
> > +     struct super_block *sb = dentry->d_sb;
> > +     const struct unicode_map *um = sb->s_encoding;
> > +     int ret = 0;
> > +
> > +     if (!inode || !needs_casefold(inode))
> > +             return 0;
> > +
> > +     ret = utf8_casefold_hash(um, dentry, str);
> > +     if (ret < 0)
> > +             goto err;
> > +
> > +     return 0;
> > +err:
> > +     if (sb_has_strict_encoding(sb))
> > +             ret = -EINVAL;
> > +     else
> > +             ret = 0;
> > +     return ret;
> > +}
>
> On v9, Gabriel suggested simplifying this to:
>
>         ret = utf8_casefold_hash(um, dentry, str);
>         if (ret < 0 && sb_has_enc_strict_mode(sb))
>                 return -EINVAL;
>         return 0;
>
> Any reason not to do that?
>
> - Eric

Guh, I remember making those changes, must've lost them in a rebase :(
I'll resend shortly.
-Daniel

Patch
diff mbox series

diff --git a/fs/libfs.c b/fs/libfs.c
index 4d08edf19c78..fe22e2be6f7a 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -20,6 +20,8 @@ 
 #include <linux/fs_context.h>
 #include <linux/pseudo_fs.h>
 #include <linux/fsnotify.h>
+#include <linux/unicode.h>
+#include <linux/fscrypt.h>
 
 #include <linux/uaccess.h>
 
@@ -1363,3 +1365,95 @@  bool is_empty_dir_inode(struct inode *inode)
 	return (inode->i_fop == &empty_dir_operations) &&
 		(inode->i_op == &empty_dir_inode_operations);
 }
+
+#ifdef CONFIG_UNICODE
+/*
+ * Determine if the name of a dentry should be casefolded.
+ *
+ * Return: if names will need casefolding
+ */
+static bool needs_casefold(const struct inode *dir)
+{
+	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding;
+}
+
+/**
+ * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems
+ * @dentry:	dentry whose name we are checking against
+ * @len:	len of name of dentry
+ * @str:	str pointer to name of dentry
+ * @name:	Name to compare against
+ *
+ * Return: 0 if names match, 1 if mismatch, or -ERRNO
+ */
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			  const char *str, const struct qstr *name)
+{
+	const struct dentry *parent = READ_ONCE(dentry->d_parent);
+	const struct inode *inode = READ_ONCE(parent->d_inode);
+	const struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	struct qstr qstr = QSTR_INIT(str, len);
+	char strbuf[DNAME_INLINE_LEN];
+	int ret;
+
+	if (!inode || !needs_casefold(inode))
+		goto fallback;
+	/*
+	 * If the dentry name is stored in-line, then it may be concurrently
+	 * modified by a rename.  If this happens, the VFS will eventually retry
+	 * the lookup, so it doesn't matter what ->d_compare() returns.
+	 * However, it's unsafe to call utf8_strncasecmp() with an unstable
+	 * string.  Therefore, we have to copy the name into a temporary buffer.
+	 */
+	if (len <= DNAME_INLINE_LEN - 1) {
+		memcpy(strbuf, str, len);
+		strbuf[len] = 0;
+		qstr.name = strbuf;
+		/* prevent compiler from optimizing out the temporary buffer */
+		barrier();
+	}
+	ret = utf8_strncasecmp(um, name, &qstr);
+	if (ret >= 0)
+		return ret;
+
+	if (sb_has_strict_encoding(sb))
+		return -EINVAL;
+fallback:
+	if (len != name->len)
+		return 1;
+	return !!memcmp(str, name->name, len);
+}
+EXPORT_SYMBOL(generic_ci_d_compare);
+
+/**
+ * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
+ * @dentry:	dentry whose name we are hashing
+ * @str:	qstr of name whose hash we should fill in
+ *
+ * Return: 0 if hash was successful, or -ERRNO
+ */
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	const struct inode *inode = READ_ONCE(dentry->d_inode);
+	struct super_block *sb = dentry->d_sb;
+	const struct unicode_map *um = sb->s_encoding;
+	int ret = 0;
+
+	if (!inode || !needs_casefold(inode))
+		return 0;
+
+	ret = utf8_casefold_hash(um, dentry, str);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+err:
+	if (sb_has_strict_encoding(sb))
+		ret = -EINVAL;
+	else
+		ret = 0;
+	return ret;
+}
+EXPORT_SYMBOL(generic_ci_d_hash);
+#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3f881a892ea7..af8f2ecec8ff 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1392,6 +1392,12 @@  extern int send_sigurg(struct fown_struct *fown);
 #define SB_ACTIVE	(1<<30)
 #define SB_NOUSER	(1<<31)
 
+/* These flags relate to encoding and casefolding */
+#define SB_ENC_STRICT_MODE_FL	(1 << 0)
+
+#define sb_has_strict_encoding(sb) \
+	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
+
 /*
  *	Umount options
  */
@@ -1461,6 +1467,10 @@  struct super_block {
 #endif
 #ifdef CONFIG_FS_VERITY
 	const struct fsverity_operations *s_vop;
+#endif
+#ifdef CONFIG_UNICODE
+	struct unicode_map *s_encoding;
+	__u16 s_encoding_flags;
 #endif
 	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
@@ -3385,6 +3395,12 @@  extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);
 
+#ifdef CONFIG_UNICODE
+extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
+extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+				const char *str, const struct qstr *name);
+#endif
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
 				struct page *, struct page *,