f2fs: Support case-insensitive file name lookups

Modeled after commit b886ee3e778e ("ext4: Support case-insensitive file
name lookups")

"""
This patch implements the actual support for case-insensitive file name
lookups in f2fs, 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 (F2FS_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, F2Fs 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 f2fs is implemented
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 F2FS 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: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 115 insertions, 10 deletions

diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 85a1528f319f..dac07d17cdbd 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -8,6 +8,7 @@
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/sched/signal.h>
+#include <linux/unicode.h>
 #include "f2fs.h"
 #include "node.h"
 #include "acl.h"
@@ -81,7 +82,8 @@ static unsigned long dir_block_index(unsigned int level,
 	return bidx;
 }
 
-static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
+static struct f2fs_dir_entry *find_in_block(struct inode *dir,
+				struct page *dentry_page,
 				struct fscrypt_name *fname,
 				f2fs_hash_t namehash,
 				int *max_slots,
@@ -93,7 +95,7 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 
 	dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page);
 
-	make_dentry_ptr_block(NULL, &d, dentry_blk);
+	make_dentry_ptr_block(dir, &d, dentry_blk);
 	de = f2fs_find_target_dentry(fname, namehash, max_slots, &d);
 	if (de)
 		*res_page = dentry_page;
@@ -101,6 +103,39 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 	return de;
 }
 
+#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 f2fs_ci_compare(const struct inode *parent, const struct qstr *name,
+		    const struct qstr *entry)
+{
+	const struct f2fs_sb_info *sbi = F2FS_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 (f2fs_has_strict_mode(sbi))
+			return -EINVAL;
+
+		if (name->len != entry->len)
+			return 1;
+
+		return !!memcmp(name->name, entry->name, name->len);
+	}
+
+	return ret;
+}
+#endif
+
 struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
 			f2fs_hash_t namehash, int *max_slots,
 			struct f2fs_dentry_ptr *d)
@@ -108,6 +143,9 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
 	struct f2fs_dir_entry *de;
 	unsigned long bit_pos = 0;
 	int max_len = 0;
+#ifdef CONFIG_UNICODE
+	struct qstr entry;
+#endif
 
 	if (max_slots)
 		*max_slots = 0;
@@ -119,16 +157,28 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
 		}
 
 		de = &d->dentry[bit_pos];
+#ifdef CONFIG_UNICODE
+		entry.name = d->filename[bit_pos];
+		entry.len = de->name_len;
+#endif
 
 		if (unlikely(!de->name_len)) {
 			bit_pos++;
 			continue;
 		}
+		if (de->hash_code == namehash) {
+#ifdef CONFIG_UNICODE
+			if (F2FS_SB(d->inode->i_sb)->s_encoding &&
+					IS_CASEFOLDED(d->inode) &&
+					!f2fs_ci_compare(d->inode,
+						fname->usr_fname, &entry))
+				goto found;
 
-		if (de->hash_code == namehash &&
-		    fscrypt_match_name(fname, d->filename[bit_pos],
-				       le16_to_cpu(de->name_len)))
-			goto found;
+#endif
+			if (fscrypt_match_name(fname, d->filename[bit_pos],
+						le16_to_cpu(de->name_len)))
+				goto found;
+		}
 
 		if (max_slots && max_len > *max_slots)
 			*max_slots = max_len;
@@ -157,7 +207,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 	struct f2fs_dir_entry *de = NULL;
 	bool room = false;
 	int max_slots;
-	f2fs_hash_t namehash = f2fs_dentry_hash(&name, fname);
+	f2fs_hash_t namehash = f2fs_dentry_hash(dir, &name, fname);
 
 	nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
 	nblock = bucket_blocks(level);
@@ -179,8 +229,8 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 			}
 		}
 
-		de = find_in_block(dentry_page, fname, namehash, &max_slots,
-								res_page);
+		de = find_in_block(dir, dentry_page, fname, namehash,
+							&max_slots, res_page);
 		if (de)
 			break;
 
@@ -250,6 +300,14 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 	struct fscrypt_name fname;
 	int err;
 
+#ifdef CONFIG_UNICODE
+	if (f2fs_has_strict_mode(F2FS_I_SB(dir)) && IS_CASEFOLDED(dir) &&
+			utf8_validate(F2FS_I_SB(dir)->s_encoding, child)) {
+		*res_page = ERR_PTR(-EINVAL);
+		return NULL;
+	}
+#endif
+
 	err = fscrypt_setup_filename(dir, child, 1, &fname);
 	if (err) {
 		if (err == -ENOENT)
@@ -504,7 +562,7 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
 
 	level = 0;
 	slots = GET_DENTRY_SLOTS(new_name->len);
-	dentry_hash = f2fs_dentry_hash(new_name, NULL);
+	dentry_hash = f2fs_dentry_hash(dir, new_name, NULL);
 
 	current_depth = F2FS_I(dir)->i_current_depth;
 	if (F2FS_I(dir)->chash == dentry_hash) {
@@ -943,3 +1001,50 @@ const struct file_operations f2fs_dir_operations = {
 	.compat_ioctl   = f2fs_compat_ioctl,
 #endif
 };
+
+#ifdef CONFIG_UNICODE
+static int f2fs_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 f2fs_ci_compare(dentry->d_parent->d_inode, name, &qstr);
+}
+
+static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str)
+{
+	struct f2fs_sb_info *sbi = F2FS_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 = f2fs_kmalloc(sbi, PATH_MAX, GFP_ATOMIC);
+	if (!norm)
+		return -ENOMEM;
+
+	len = utf8_casefold(um, str, norm, PATH_MAX);
+	if (len < 0) {
+		if (f2fs_has_strict_mode(sbi))
+			ret = -EINVAL;
+		goto out;
+	}
+	str->hash = full_name_hash(dentry, norm, len);
+out:
+	kvfree(norm);
+	return ret;
+}
+
+const struct dentry_operations f2fs_dentry_ops = {
+	.d_hash = f2fs_d_hash,
+	.d_compare = f2fs_d_compare,
+};
+#endif