ext4: Support case-insensitive file name lookups

This patch implements the actual support for case-insensitive file name
lookups in ext4, based on the feature bit and the encoding stored in the
superblock.

A filesystem that has the casefold feature set is able to configure
directories with the +F (EXT4_CASEFOLD_FL) attribute, enabling lookups
to succeed in that directory in a case-insensitive fashion, i.e: match
a directory entry even if the name used by userspace is not a byte per
byte match with the disk name, but is an equivalent case-insensitive
version of the Unicode string. This operation is called a
case-insensitive file name lookup.

The feature is configured as an inode attribute applied to directories
and inherited by its children. This attribute can only be enabled on
empty directories for filesystems that support the encoding feature,
thus preventing collision of file names that only differ by case.

* dcache handling:

For a +F directory, Ext4 only stores the first equivalent name dentry
used in the dcache. This is done to prevent unintentional duplication of
dentries in the dcache, while also allowing the VFS code to quickly find
the right entry in the cache despite which equivalent string was used in
a previous lookup, without having to resort to ->lookup().

d_hash() of casefolded directories is implemented as the hash of the
casefolded string, such that we always have a well-known bucket for all
the equivalencies of the same string. d_compare() uses the
utf8_strncasecmp() infrastructure, which handles the comparison of
equivalent, same case, names as well.

For now, negative lookups are not inserted in the dcache, since they
would need to be invalidated anyway, because we can't trust missing file
dentries. This is bad for performance but requires some leveraging of
the vfs layer to fix. We can live without that for now, and so does
everyone else.

* on-disk data:

Despite using a specific version of the name as the internal
representation within the dcache, the name stored and fetched from the
disk is a byte-per-byte match with what the user requested, making this
implementation 'name-preserving'. i.e. no actual information is lost
when writing to storage.

DX is supported by modifying the hashes used in +F directories to make
them case/encoding-aware. The new disk hashes are calculated as the
hash of the full casefolded string, instead of the string directly.
This allows us to efficiently search for file names in the htree without
requiring the user to provide an exact name.

* Dealing with invalid sequences:

By default, when a invalid UTF-8 sequence is identified, ext4 will treat
it as an opaque byte sequence, ignoring the encoding and reverting to
the old behavior for that unique file. This means that case-insensitive
file name lookup will not work only for that file. An optional bit can
be set in the superblock telling the filesystem code and userspace tools
to enforce the encoding. When that optional bit is set, any attempt to
create a file name using an invalid UTF-8 sequence will fail and return
an error to userspace.

* Normalization algorithm:

The UTF-8 algorithms used to compare strings in ext4 is implemented
lives in fs/unicode, and is based on a previous version developed by
SGI. It implements the Canonical decomposition (NFD) algorithm
described by the Unicode specification 12.1, or higher, combined with
the elimination of ignorable code points (NFDi) and full
case-folding (CF) as documented in fs/unicode/utf8_norm.c.

NFD seems to be the best normalization method for EXT4 because:

- It has a lower cost than NFC/NFKC (which requires
decomposing to NFD as an intermediary step)
- It doesn't eliminate important semantic meaning like
compatibility decompositions.

Although:

- This implementation is not completely linguistic accurate, because
different languages have conflicting rules, which would require the
specialization of the filesystem to a given locale, which brings all
sorts of problems for removable media and for users who use more than
one language.

Signed-off-by: Gabriel Krisman Bertazi <[e-mail]>
Signed-off-by: Theodore Ts'o <[e-mail]>

fs/ext4/dir.c

···
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
 #include <linux/iversion.h>
+#include <linux/unicode.h>
 #include "ext4.h"
 #include "xattr.h"
 
···
 	.open		= ext4_dir_open,
 	.release	= ext4_release_dir,
 };
+
+#ifdef CONFIG_UNICODE
+static int ext4_d_compare(const struct dentry *dentry, unsigned int len,
+			  const char *str, const struct qstr *name)
+{
+	struct qstr qstr = {.name = str, .len = len };
+
+	if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) {
+		if (len != name->len)
+			return -1;
+		return !memcmp(str, name, len);
+	}
+
+	return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr);
+}
+
+static int ext4_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	const struct ext4_sb_info *sbi = EXT4_SB(dentry->d_sb);
+	const struct unicode_map *um = sbi->s_encoding;
+	unsigned char *norm;
+	int len, ret = 0;
+
+	if (!IS_CASEFOLDED(dentry->d_inode))
+		return 0;
+
+	norm = kmalloc(PATH_MAX, GFP_ATOMIC);
+	if (!norm)
+		return -ENOMEM;
+
+	len = utf8_casefold(um, str, norm, PATH_MAX);
+	if (len < 0) {
+		if (ext4_has_strict_mode(sbi))
+			ret = -EINVAL;
+		goto out;
+	}
+	str->hash = full_name_hash(dentry, norm, len);
+out:
+	kfree(norm);
+	return ret;
+}
+
+const struct dentry_operations ext4_dentry_ops = {
+	.d_hash = ext4_d_hash,
+	.d_compare = ext4_d_compare,
+};
+#endif

fs/ext4/ext4.h

···
 #define EXT4_EOFBLOCKS_FL		0x00400000 /* Blocks allocated beyond EOF */
 #define EXT4_INLINE_DATA_FL		0x10000000 /* Inode has inline data. */
 #define EXT4_PROJINHERIT_FL		0x20000000 /* Create with parents projid */
+#define EXT4_CASEFOLD_FL		0x40000000 /* Casefolded file */
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
-#define EXT4_FL_USER_VISIBLE		0x304BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x204BC0FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE		0x704BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE		0x604BC0FF /* User modifiable flags */
 
 /* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
 #define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
···
 			   EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
 			   EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
 			   EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
-			   EXT4_PROJINHERIT_FL)
+			   EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL)
 
 /* Flags that are appropriate for regular files (all but dir-specific ones). */
-#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL))
+#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL))
 
 /* Flags that are appropriate for non-directories/regular files. */
 #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)
···
 extern int ext4_sync_file(struct file *, loff_t, loff_t, int);
 
 /* hash.c */
-extern int ext4fs_dirhash(const char *name, int len, struct
-			  dx_hash_info *hinfo);
+extern int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
+			  struct dx_hash_info *hinfo);
 
 /* ialloc.c */
 extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
···
 /* dir.c */
 extern const struct file_operations ext4_dir_operations;
 
+#ifdef CONFIG_UNICODE
+extern const struct dentry_operations ext4_dentry_ops;
+#endif
+
 /* file.c */
 extern const struct inode_operations ext4_file_inode_operations;
 extern const struct file_operations ext4_file_operations;
···
 extern int ext4_handle_dirty_dirent_node(handle_t *handle,
 					 struct inode *inode,
 					 struct buffer_head *bh);
+extern int ext4_ci_compare(const struct inode *parent,
+			   const struct qstr *name,
+			   const struct qstr *entry);
+
 #define S_SHIFT 12
 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
 	[S_IFREG >> S_SHIFT]	= EXT4_FT_REG_FILE,

fs/ext4/hash.c

···
  */
 
 #include <linux/fs.h>
+#include <linux/unicode.h>
 #include <linux/compiler.h>
 #include <linux/bitops.h>
 #include "ext4.h"
···
  * represented, and whether or not the returned hash is 32 bits or 64
  * bits.  32 bit hashes will return 0 for the minor hash.
  */
-int ext4fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo)
+static int __ext4fs_dirhash(const char *name, int len,
+			    struct dx_hash_info *hinfo)
 {
 	__u32	hash;
 	__u32	minor_hash = 0;
···
 	hinfo->hash = hash;
 	hinfo->minor_hash = minor_hash;
 	return 0;
+}
+
+int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
+		   struct dx_hash_info *hinfo)
+{
+#ifdef CONFIG_UNICODE
+	const struct unicode_map *um = EXT4_SB(dir->i_sb)->s_encoding;
+	int r, dlen;
+	unsigned char *buff;
+	struct qstr qstr = {.name = name, .len = len };
+
+	if (len && IS_CASEFOLDED(dir)) {
+		buff = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
+		if (!buff)
+			return -ENOMEM;
+
+		dlen = utf8_casefold(um, &qstr, buff, PATH_MAX);
+		if (dlen < 0) {
+			kfree(buff);
+			goto opaque_seq;
+		}
+
+		r = __ext4fs_dirhash(buff, dlen, hinfo);
+
+		kfree(buff);
+		return r;
+	}
+opaque_seq:
+#endif
+	return __ext4fs_dirhash(name, len, hinfo);
 }

fs/ext4/ialloc.c

···
 		if (qstr) {
 			hinfo.hash_version = DX_HASH_HALF_MD4;
 			hinfo.seed = sbi->s_hash_seed;
-			ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
+			ext4fs_dirhash(parent, qstr->name, qstr->len, &hinfo);
 			grp = hinfo.hash;
 		} else
 			grp = prandom_u32();

fs/ext4/inline.c

···
 			}
 		}
 
-		ext4fs_dirhash(de->name, de->name_len, hinfo);
+		ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
 		if ((hinfo->hash < start_hash) ||
 		    ((hinfo->hash == start_hash) &&
 		     (hinfo->minor_hash < start_minor_hash)))

fs/ext4/inode.c

···
 		new_fl |= S_DAX;
 	if (flags & EXT4_ENCRYPT_FL)
 		new_fl |= S_ENCRYPTED;
+	if (flags & EXT4_CASEFOLD_FL)
+		new_fl |= S_CASEFOLD;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX|
-			S_ENCRYPTED);
+			S_ENCRYPTED|S_CASEFOLD);
 }
 
 static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,

fs/ext4/ioctl.c

···
 	struct ext4_iloc iloc;
 	unsigned int oldflags, mask, i;
 	unsigned int jflag;
+	struct super_block *sb = inode->i_sb;
 
 	/* Is it quota file? Do not allow user to mess with it */
 	if (ext4_is_quota_file(inode))
···
 		err = ext4_truncate(inode);
 		if (err)
 			goto flags_out;
+	}
+
+	if ((flags ^ oldflags) & EXT4_CASEFOLD_FL) {
+		if (!ext4_has_feature_casefold(sb)) {
+			err = -EOPNOTSUPP;
+			goto flags_out;
+		}
+
+		if (!S_ISDIR(inode->i_mode)) {
+			err = -ENOTDIR;
+			goto flags_out;
+		}
+
+		if (!ext4_empty_dir(inode)) {
+			err = -ENOTEMPTY;
+			goto flags_out;
+		}
 	}
 
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);

fs/ext4/namei.c

···
 #include <linux/buffer_head.h>
 #include <linux/bio.h>
 #include <linux/iversion.h>
+#include <linux/unicode.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 
···
 				}
 				if (!fscrypt_has_encryption_key(dir)) {
 					/* Directory is not encrypted */
-					ext4fs_dirhash(de->name,
+					ext4fs_dirhash(dir, de->name,
 						de->name_len, &h);
 					printk("%*.s:(U)%x.%u ", len,
 					       name, h.hash,
···
 						name = fname_crypto_str.name;
 						len = fname_crypto_str.len;
 					}
-					ext4fs_dirhash(de->name, de->name_len,
-						       &h);
+					ext4fs_dirhash(dir, de->name,
+						       de->name_len, &h);
 					printk("%*.s:(E)%x.%u ", len, name,
 					       h.hash, (unsigned) ((char *) de
 								   - base));
···
 #else
 				int len = de->name_len;
 				char *name = de->name;
-				ext4fs_dirhash(de->name, de->name_len, &h);
+				ext4fs_dirhash(dir, de->name, de->name_len, &h);
 				printk("%*.s:%x.%u ", len, name, h.hash,
 				       (unsigned) ((char *) de - base));
 #endif
···
 		hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	if (fname && fname_name(fname))
-		ext4fs_dirhash(fname_name(fname), fname_len(fname), hinfo);
+		ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo);
 	hash = hinfo->hash;
 
 	if (root->info.unused_flags & 1) {
···
 			/* silently ignore the rest of the block */
 			break;
 		}
-		ext4fs_dirhash(de->name, de->name_len, hinfo);
+		ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
 		if ((hinfo->hash < start_hash) ||
 		    ((hinfo->hash == start_hash) &&
 		     (hinfo->minor_hash < start_minor_hash)))
···
 
 	while ((char *) de < base + blocksize) {
 		if (de->name_len && de->inode) {
-			ext4fs_dirhash(de->name, de->name_len, &h);
+			ext4fs_dirhash(dir, de->name, de->name_len, &h);
 			map_tail--;
 			map_tail->hash = h.hash;
 			map_tail->offs = ((char *) de - base)>>2;
···
 	dx_set_count(entries, count + 1);
 }
 
+#ifdef CONFIG_UNICODE
+/*
+ * Test whether a case-insensitive directory entry matches the filename
+ * being searched for.
+ *
+ * Returns: 0 if the directory entry matches, more than 0 if it
+ * doesn't match or less than zero on error.
+ */
+int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
+		    const struct qstr *entry)
+{
+	const struct ext4_sb_info *sbi = EXT4_SB(parent->i_sb);
+	const struct unicode_map *um = sbi->s_encoding;
+	int ret;
+
+	ret = utf8_strncasecmp(um, name, entry);
+	if (ret < 0) {
+		/* Handle invalid character sequence as either an error
+		 * or as an opaque byte sequence.
+		 */
+		if (ext4_has_strict_mode(sbi))
+			return -EINVAL;
+
+		if (name->len != entry->len)
+			return 1;
+
+		return !!memcmp(name->name, entry->name, name->len);
+	}
+
+	return ret;
+}
+#endif
+
 /*
  * Test whether a directory entry matches the filename being searched for.
  *
  * Return: %true if the directory entry matches, otherwise %false.
  */
-static inline bool ext4_match(const struct ext4_filename *fname,
+static inline bool ext4_match(const struct inode *parent,
+			      const struct ext4_filename *fname,
 			      const struct ext4_dir_entry_2 *de)
 {
 	struct fscrypt_name f;
+#ifdef CONFIG_UNICODE
+	const struct qstr entry = {.name = de->name, .len = de->name_len};
+#endif
 
 	if (!de->inode)
 		return false;
···
 #ifdef CONFIG_FS_ENCRYPTION
 	f.crypto_buf = fname->crypto_buf;
 #endif
+
+#ifdef CONFIG_UNICODE
+	if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent))
+		return (ext4_ci_compare(parent, fname->usr_fname, &entry) == 0);
+#endif
+
 	return fscrypt_match_name(&f, de->name, de->name_len);
 }
 
···
 		/* this code is executed quadratically often */
 		/* do minimal checking `by hand' */
 		if ((char *) de + de->name_len <= dlimit &&
-		    ext4_match(fname, de)) {
+		    ext4_match(dir, fname, de)) {
 			/* found a match - just to be sure, do
 			 * a full check */
 			if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data,
···
 			return ERR_PTR(-EPERM);
 		}
 	}
+
+#ifdef CONFIG_UNICODE
+	if (!inode && IS_CASEFOLDED(dir)) {
+		/* Eventually we want to call d_add_ci(dentry, NULL)
+		 * for negative dentries in the encoding case as
+		 * well.  For now, prevent the negative dentry
+		 * from being cached.
+		 */
+		return NULL;
+	}
+#endif
 	return d_splice_alias(inode, dentry);
 }
 
···
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
 					 buf, buf_size, offset))
 			return -EFSCORRUPTED;
-		if (ext4_match(fname, de))
+		if (ext4_match(dir, fname, de))
 			return -EEXIST;
 		nlen = EXT4_DIR_REC_LEN(de->name_len);
 		rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
···
 	if (fname->hinfo.hash_version <= DX_HASH_TEA)
 		fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
-	ext4fs_dirhash(fname_name(fname), fname_len(fname), &fname->hinfo);
+	ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), &fname->hinfo);
 
 	memset(frames, 0, sizeof(frames));
 	frame = frames;
···
 	struct ext4_dir_entry_2 *de;
 	struct ext4_dir_entry_tail *t;
 	struct super_block *sb;
+	struct ext4_sb_info *sbi;
 	struct ext4_filename fname;
 	int	retval;
 	int	dx_fallback=0;
···
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	sb = dir->i_sb;
+	sbi = EXT4_SB(sb);
 	blocksize = sb->s_blocksize;
 	if (!dentry->d_name.len)
 		return -EINVAL;
+
+#ifdef CONFIG_UNICODE
+	if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) &&
+	    utf8_validate(sbi->s_encoding, &dentry->d_name))
+		return -EINVAL;
+#endif
 
 	retval = ext4_fname_setup_filename(dir, &dentry->d_name, 0, &fname);
 	if (retval)
···
 	ext4_update_dx_flag(dir);
 	ext4_mark_inode_dirty(handle, dir);
 
+#ifdef CONFIG_UNICODE
+	/* VFS negative dentries are incompatible with Encoding and
+	 * Case-insensitiveness. Eventually we'll want avoid
+	 * invalidating the dentries here, alongside with returning the
+	 * negative dentries at ext4_lookup(), when it is better
+	 * supported by the VFS for the CI case.
+	 */
+	if (IS_CASEFOLDED(dir))
+		d_invalidate(dentry);
+#endif
+
 end_rmdir:
 	brelse(bh);
 	if (handle)
···
 		ext4_orphan_add(handle, inode);
 	inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+
+#ifdef CONFIG_UNICODE
+	/* VFS negative dentries are incompatible with Encoding and
+	 * Case-insensitiveness. Eventually we'll want avoid
+	 * invalidating the dentries here, alongside with returning the
+	 * negative dentries at ext4_lookup(), when it is  better
+	 * supported by the VFS for the CI case.
+	 */
+	if (IS_CASEFOLDED(dir))
+		d_invalidate(dentry);
+#endif
 
 end_unlink:
 	brelse(bh);

fs/ext4/super.c

···
 		iput(root);
 		goto failed_mount4;
 	}
+
+#ifdef CONFIG_UNICODE
+	if (sbi->s_encoding)
+		sb->s_d_op = &ext4_dentry_ops;
+#endif
+
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		ext4_msg(sb, KERN_ERR, "get root dentry failed");

include/linux/fs.h

···
 #define S_DAX		0	/* Make all the DAX code disappear */
 #endif
 #define S_ENCRYPTED	16384	/* Encrypted file (using fs/crypto/) */
+#define S_CASEFOLD	32768	/* Casefolded file */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
···
 #define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
 #define IS_DAX(inode)		((inode)->i_flags & S_DAX)
 #define IS_ENCRYPTED(inode)	((inode)->i_flags & S_ENCRYPTED)
+#define IS_CASEFOLDED(inode)	((inode)->i_flags & S_CASEFOLD)
 
 #define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
 				 (inode)->i_rdev == WHITEOUT_DEV)