[PATCH v10 0/4] Prepare for upcoming Casefolding/Encryption patches

[PATCH v10 0/4] Prepare for upcoming Casefolding/Encryption patches

[Daniel Rosenberg]

This lays the ground work for enabling casefolding and encryption at the
same time for ext4 and f2fs. A future set of patches will enable that
functionality.

These unify the highly similar dentry_operations that ext4 and f2fs both
use for casefolding. In addition, they improve d_hash by not requiring a
new string allocation, and ensure we don't attempt to casefold the no-key
token of an encrypted filename.

Daniel Rosenberg (4):
  unicode: Add utf8_casefold_hash
  fs: Add standard casefolding support
  f2fs: Use generic casefolding support
  ext4: Use generic casefolding support

 fs/ext4/dir.c           | 64 +--------------------------
 fs/ext4/ext4.h          | 12 ------
 fs/ext4/hash.c          |  2 +-
 fs/ext4/namei.c         | 20 ++++-----
 fs/ext4/super.c         | 12 +++---
 fs/f2fs/dir.c           | 83 ++++-------------------------------
 fs/f2fs/f2fs.h          |  4 --
 fs/f2fs/super.c         | 10 ++---
 fs/f2fs/sysfs.c         | 10 +++--
 fs/libfs.c              | 96 +++++++++++++++++++++++++++++++++++++++++
 fs/unicode/utf8-core.c  | 23 +++++++++-
 include/linux/f2fs_fs.h |  3 --
 include/linux/fs.h      | 16 +++++++
 include/linux/unicode.h |  3 ++
 14 files changed, 174 insertions(+), 184 deletions(-)

-- 
2.27.0.212.ge8ba1cc988-goog

[PATCH v10 1/4] unicode: Add utf8_casefold_hash

[Daniel Rosenberg]

This adds a case insensitive hash function to allow taking the hash
without needing to allocate a casefolded copy of the string.

The existing d_hash implementations for casefolding allocates memory
within rcu-walk, by avoiding it we can be more efficient and avoid
worrying about a failed allocation.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/unicode/utf8-core.c  | 23 ++++++++++++++++++++++-
 include/linux/unicode.h |  3 +++
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index 2a878b739115..dc25823bfed9 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -6,6 +6,7 @@
 #include <linux/parser.h>
 #include <linux/errno.h>
 #include <linux/unicode.h>
+#include <linux/stringhash.h>
 
 #include "utf8n.h"
 
@@ -122,9 +123,29 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 	}
 	return -EINVAL;
 }
-
 EXPORT_SYMBOL(utf8_casefold);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str)
+{
+	const struct utf8data *data = utf8nfdicf(um->version);
+	struct utf8cursor cur;
+	int c;
+	unsigned long hash = init_name_hash(salt);
+
+	if (utf8ncursor(&cur, data, str->name, str->len) < 0)
+		return -EINVAL;
+
+	while ((c = utf8byte(&cur))) {
+		if (c < 0)
+			return -EINVAL;
+		hash = partial_name_hash((unsigned char)c, hash);
+	}
+	str->hash = end_name_hash(hash);
+	return 0;
+}
+EXPORT_SYMBOL(utf8_casefold_hash);
+
 int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 		   unsigned char *dest, size_t dlen)
 {
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 990aa97d8049..74484d44c755 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -27,6 +27,9 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str,
 int utf8_casefold(const struct unicode_map *um, const struct qstr *str,
 		  unsigned char *dest, size_t dlen);
 
+int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
+		       struct qstr *str);
+
 struct unicode_map *utf8_load(const char *version);
 void utf8_unload(struct unicode_map *um);
 
-- 
2.27.0.212.ge8ba1cc988-goog

[PATCH v10 2/4] fs: Add standard casefolding support

[Daniel Rosenberg]

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 ths use of utf8_casefold_hash to
avoid an allocation, and dealing with casefolding and encryption. It
doesn't make sense to casefold the no-key token for the encrypted name,
so we don't casefold in that case.

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         | 96 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/fs.h | 16 ++++++++
 2 files changed, 112 insertions(+)

diff --git a/fs/libfs.c b/fs/libfs.c
index 4d08edf19c78..f7df13806f36 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 +1365,97 @@ 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. It does not make
+ * sense to casefold the no-key token of an encrypted filename.
+ *
+ * Return: if names will need casefolding
+ */
+static bool needs_casefold(const struct inode *dir, const struct dentry *dentry)
+{
+	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding &&
+			!(dentry->d_flags & DCACHE_ENCRYPTED_NAME);
+}
+
+/**
+ * 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, dentry))
+		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, dentry))
+		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 *,
-- 
2.27.0.212.ge8ba1cc988-goog

[PATCH v10 3/4] f2fs: Use generic casefolding support

[Daniel Rosenberg]

This switches f2fs over to the generic support provided in
the previous patch.

Since casefolded dentries behave the same in ext4 and f2fs, we decrease
the maintenance burden by unifying them, and any optimizations will
immediately apply to both.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/f2fs/dir.c           | 83 +++++------------------------------------
 fs/f2fs/f2fs.h          |  4 --
 fs/f2fs/super.c         | 10 ++---
 fs/f2fs/sysfs.c         | 10 +++--
 include/linux/f2fs_fs.h |  3 --
 5 files changed, 20 insertions(+), 90 deletions(-)

diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index d35976785e8c..18bc97b2c72c 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -75,21 +75,22 @@ int f2fs_init_casefolded_name(const struct inode *dir,
 			      struct f2fs_filename *fname)
 {
 #ifdef CONFIG_UNICODE
-	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	struct super_block *sb = dir->i_sb;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 
 	if (IS_CASEFOLDED(dir)) {
 		fname->cf_name.name = f2fs_kmalloc(sbi, F2FS_NAME_LEN,
 						   GFP_NOFS);
 		if (!fname->cf_name.name)
 			return -ENOMEM;
-		fname->cf_name.len = utf8_casefold(sbi->s_encoding,
+		fname->cf_name.len = utf8_casefold(sb->s_encoding,
 						   fname->usr_fname,
 						   fname->cf_name.name,
 						   F2FS_NAME_LEN);
 		if ((int)fname->cf_name.len <= 0) {
 			kfree(fname->cf_name.name);
 			fname->cf_name.name = NULL;
-			if (f2fs_has_strict_mode(sbi))
+			if (sb_has_strict_encoding(sb))
 				return -EINVAL;
 			/* fall back to treating name as opaque byte sequence */
 		}
@@ -215,8 +216,8 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
 static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 			       const u8 *de_name, u32 de_name_len)
 {
-	const struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
-	const struct unicode_map *um = sbi->s_encoding;
+	const struct super_block *sb = dir->i_sb;
+	const struct unicode_map *um = sb->s_encoding;
 	struct qstr entry = QSTR_INIT(de_name, de_name_len);
 	int res;
 
@@ -226,7 +227,7 @@ static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
 		 * In strict mode, ignore invalid names.  In non-strict mode,
 		 * fall back to treating them as opaque byte sequences.
 		 */
-		if (f2fs_has_strict_mode(sbi) || name->len != entry.len)
+		if (sb_has_strict_encoding(sb) || name->len != entry.len)
 			return false;
 		return !memcmp(name->name, entry.name, name->len);
 	}
@@ -1107,75 +1108,9 @@ const struct file_operations f2fs_dir_operations = {
 };
 
 #ifdef CONFIG_UNICODE
-static int f2fs_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 *dir = READ_ONCE(parent->d_inode);
-	const struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
-	struct qstr entry = QSTR_INIT(str, len);
-	char strbuf[DNAME_INLINE_LEN];
-	int res;
-
-	if (!dir || !IS_CASEFOLDED(dir))
-		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;
-		entry.name = strbuf;
-		/* prevent compiler from optimizing out the temporary buffer */
-		barrier();
-	}
-
-	res = utf8_strncasecmp(sbi->s_encoding, name, &entry);
-	if (res >= 0)
-		return res;
-
-	if (f2fs_has_strict_mode(sbi))
-		return -EINVAL;
-fallback:
-	if (len != name->len)
-		return 1;
-	return !!memcmp(str, name->name, len);
-}
-
-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;
-	const struct inode *inode = READ_ONCE(dentry->d_inode);
-	unsigned char *norm;
-	int len, ret = 0;
-
-	if (!inode || !IS_CASEFOLDED(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,
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
 };
 #endif
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index b35a50f4953c..d11ffe26bfde 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1402,10 +1402,6 @@ struct f2fs_sb_info {
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
 	struct mutex writepages;		/* mutex for writepages() */
-#ifdef CONFIG_UNICODE
-	struct unicode_map *s_encoding;
-	__u16 s_encoding_flags;
-#endif
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 20e56b0fa46a..cca7a83ffa08 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1257,7 +1257,7 @@ static void f2fs_put_super(struct super_block *sb)
 	for (i = 0; i < NR_PAGE_TYPE; i++)
 		kvfree(sbi->write_io[i]);
 #ifdef CONFIG_UNICODE
-	utf8_unload(sbi->s_encoding);
+	utf8_unload(sb->s_encoding);
 #endif
 	kvfree(sbi);
 }
@@ -3278,7 +3278,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 {
 #ifdef CONFIG_UNICODE
-	if (f2fs_sb_has_casefold(sbi) && !sbi->s_encoding) {
+	if (f2fs_sb_has_casefold(sbi) && !sbi->sb->s_encoding) {
 		const struct f2fs_sb_encodings *encoding_info;
 		struct unicode_map *encoding;
 		__u16 encoding_flags;
@@ -3309,8 +3309,8 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
 			 "%s-%s with flags 0x%hx", encoding_info->name,
 			 encoding_info->version?:"\b", encoding_flags);
 
-		sbi->s_encoding = encoding;
-		sbi->s_encoding_flags = encoding_flags;
+		sbi->sb->s_encoding = encoding;
+		sbi->sb->s_encoding_flags = encoding_flags;
 		sbi->sb->s_d_op = &f2fs_dentry_ops;
 	}
 #else
@@ -3806,7 +3806,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 		kvfree(sbi->write_io[i]);
 
 #ifdef CONFIG_UNICODE
-	utf8_unload(sbi->s_encoding);
+	utf8_unload(sb->s_encoding);
 #endif
 free_options:
 #ifdef CONFIG_QUOTA
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index e877c59b9fdb..8bee99ab3978 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -176,12 +176,14 @@ static ssize_t encoding_show(struct f2fs_attr *a,
 		struct f2fs_sb_info *sbi, char *buf)
 {
 #ifdef CONFIG_UNICODE
+	struct super_block *sb = sbi->sb;
+
 	if (f2fs_sb_has_casefold(sbi))
 		return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
-			sbi->s_encoding->charset,
-			(sbi->s_encoding->version >> 16) & 0xff,
-			(sbi->s_encoding->version >> 8) & 0xff,
-			sbi->s_encoding->version & 0xff);
+			sb->s_encoding->charset,
+			(sb->s_encoding->version >> 16) & 0xff,
+			(sb->s_encoding->version >> 8) & 0xff,
+			sb->s_encoding->version & 0xff);
 #endif
 	return sprintf(buf, "(none)");
 }
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 3c383ddd92dd..a5dbb57a687f 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -38,9 +38,6 @@
 #define F2FS_MAX_QUOTAS		3
 
 #define F2FS_ENC_UTF8_12_1	1
-#define F2FS_ENC_STRICT_MODE_FL	(1 << 0)
-#define f2fs_has_strict_mode(sbi) \
-	(sbi->s_encoding_flags & F2FS_ENC_STRICT_MODE_FL)
 
 #define F2FS_IO_SIZE(sbi)	(1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
 #define F2FS_IO_SIZE_KB(sbi)	(1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */
-- 
2.27.0.212.ge8ba1cc988-goog

[PATCH v10 4/4] ext4: Use generic casefolding support

[Daniel Rosenberg]

This switches ext4 over to the generic support provided in
the previous patch.

Since casefolded dentries behave the same in ext4 and f2fs, we decrease
the maintenance burden by unifying them, and any optimizations will
immediately apply to both.

Signed-off-by: Daniel Rosenberg <drosen@google.com>
---
 fs/ext4/dir.c   | 64 ++-----------------------------------------------
 fs/ext4/ext4.h  | 12 ----------
 fs/ext4/hash.c  |  2 +-
 fs/ext4/namei.c | 20 +++++++---------
 fs/ext4/super.c | 12 +++++-----
 5 files changed, 17 insertions(+), 93 deletions(-)

diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 1d82336b1cd4..b437120f0b3f 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -669,68 +669,8 @@ const struct file_operations ext4_dir_operations = {
 };
 
 #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 };
-	const struct dentry *parent = READ_ONCE(dentry->d_parent);
-	const struct inode *inode = READ_ONCE(parent->d_inode);
-	char strbuf[DNAME_INLINE_LEN];
-
-	if (!inode || !IS_CASEFOLDED(inode) ||
-	    !EXT4_SB(inode->i_sb)->s_encoding) {
-		if (len != name->len)
-			return -1;
-		return memcmp(str, name->name, len);
-	}
-
-	/*
-	 * 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();
-	}
-
-	return ext4_ci_compare(inode, name, &qstr, false);
-}
-
-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;
-	const struct inode *inode = READ_ONCE(dentry->d_inode);
-	unsigned char *norm;
-	int len, ret = 0;
-
-	if (!inode || !IS_CASEFOLDED(inode) || !um)
-		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,
+	.d_hash = generic_ci_d_hash,
+	.d_compare = generic_ci_d_compare,
 };
 #endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 42f5060f3cdf..5cd8be24a4fd 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1393,14 +1393,6 @@ struct ext4_super_block {
 
 #define EXT4_ENC_UTF8_12_1	1
 
-/*
- * Flags for ext4_sb_info.s_encoding_flags.
- */
-#define EXT4_ENC_STRICT_MODE_FL	(1 << 0)
-
-#define ext4_has_strict_mode(sbi) \
-	(sbi->s_encoding_flags & EXT4_ENC_STRICT_MODE_FL)
-
 /*
  * fourth extended-fs super-block data in memory
  */
@@ -1450,10 +1442,6 @@ struct ext4_sb_info {
 	struct kobject s_kobj;
 	struct completion s_kobj_unregister;
 	struct super_block *s_sb;
-#ifdef CONFIG_UNICODE
-	struct unicode_map *s_encoding;
-	__u16 s_encoding_flags;
-#endif
 
 	/* Journaling */
 	struct journal_s *s_journal;
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index 3e133793a5a3..143b0073b3f4 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -275,7 +275,7 @@ 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;
+	const struct unicode_map *um = dir->i_sb->s_encoding;
 	int r, dlen;
 	unsigned char *buff;
 	struct qstr qstr = {.name = name, .len = len };
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 56738b538ddf..6ffd53e6455e 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1286,8 +1286,8 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
 int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
 		    const struct qstr *entry, bool quick)
 {
-	const struct ext4_sb_info *sbi = EXT4_SB(parent->i_sb);
-	const struct unicode_map *um = sbi->s_encoding;
+	const struct super_block *sb = parent->i_sb;
+	const struct unicode_map *um = sb->s_encoding;
 	int ret;
 
 	if (quick)
@@ -1299,7 +1299,7 @@ int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
 		/* Handle invalid character sequence as either an error
 		 * or as an opaque byte sequence.
 		 */
-		if (ext4_has_strict_mode(sbi))
+		if (sb_has_strict_encoding(sb))
 			return -EINVAL;
 
 		if (name->len != entry->len)
@@ -1316,7 +1316,7 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
 {
 	int len;
 
-	if (!IS_CASEFOLDED(dir) || !EXT4_SB(dir->i_sb)->s_encoding) {
+	if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding) {
 		cf_name->name = NULL;
 		return;
 	}
@@ -1325,7 +1325,7 @@ void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
 	if (!cf_name->name)
 		return;
 
-	len = utf8_casefold(EXT4_SB(dir->i_sb)->s_encoding,
+	len = utf8_casefold(dir->i_sb->s_encoding,
 			    iname, cf_name->name,
 			    EXT4_NAME_LEN);
 	if (len <= 0) {
@@ -1362,7 +1362,7 @@ static inline bool ext4_match(const struct inode *parent,
 #endif
 
 #ifdef CONFIG_UNICODE
-	if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent)) {
+	if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent)) {
 		if (fname->cf_name.name) {
 			struct qstr cf = {.name = fname->cf_name.name,
 					  .len = fname->cf_name.len};
@@ -2171,9 +2171,6 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	struct buffer_head *bh = NULL;
 	struct ext4_dir_entry_2 *de;
 	struct super_block *sb;
-#ifdef CONFIG_UNICODE
-	struct ext4_sb_info *sbi;
-#endif
 	struct ext4_filename fname;
 	int	retval;
 	int	dx_fallback=0;
@@ -2190,9 +2187,8 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 		return -EINVAL;
 
 #ifdef CONFIG_UNICODE
-	sbi = EXT4_SB(sb);
-	if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) &&
-	    sbi->s_encoding && utf8_validate(sbi->s_encoding, &dentry->d_name))
+	if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
+	    sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name))
 		return -EINVAL;
 #endif
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 330957ed1f05..d097771a374f 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1102,7 +1102,7 @@ static void ext4_put_super(struct super_block *sb)
 	fs_put_dax(sbi->s_daxdev);
 	fscrypt_free_dummy_context(&sbi->s_dummy_enc_ctx);
 #ifdef CONFIG_UNICODE
-	utf8_unload(sbi->s_encoding);
+	utf8_unload(sb->s_encoding);
 #endif
 	kfree(sbi);
 }
@@ -4035,7 +4035,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 
 #ifdef CONFIG_UNICODE
-	if (ext4_has_feature_casefold(sb) && !sbi->s_encoding) {
+	if (ext4_has_feature_casefold(sb) && !sb->s_encoding) {
 		const struct ext4_sb_encodings *encoding_info;
 		struct unicode_map *encoding;
 		__u16 encoding_flags;
@@ -4066,8 +4066,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			 "%s-%s with flags 0x%hx", encoding_info->name,
 			 encoding_info->version?:"\b", encoding_flags);
 
-		sbi->s_encoding = encoding;
-		sbi->s_encoding_flags = encoding_flags;
+		sb->s_encoding = encoding;
+		sb->s_encoding_flags = encoding_flags;
 	}
 #endif
 
@@ -4678,7 +4678,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 #ifdef CONFIG_UNICODE
-	if (sbi->s_encoding)
+	if (sb->s_encoding)
 		sb->s_d_op = &ext4_dentry_ops;
 #endif
 
@@ -4873,7 +4873,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		crypto_free_shash(sbi->s_chksum_driver);
 
 #ifdef CONFIG_UNICODE
-	utf8_unload(sbi->s_encoding);
+	utf8_unload(sb->s_encoding);
 #endif
 
 #ifdef CONFIG_QUOTA
-- 
2.27.0.212.ge8ba1cc988-goog

Re: [PATCH v10 1/4] unicode: Add utf8_casefold_hash

[Gabriel Krisman Bertazi]

Daniel Rosenberg <drosen@google.com> writes:

> This adds a case insensitive hash function to allow taking the hash
> without needing to allocate a casefolded copy of the string.
>
> The existing d_hash implementations for casefolding allocates memory
> within rcu-walk, by avoiding it we can be more efficient and avoid
> worrying about a failed allocation.
>
> Signed-off-by: Daniel Rosenberg <drosen@google.com>

Reviewed-by: Gabriel Krisman Bertazi <krisman@collabora.com>

-- 
Gabriel Krisman Bertazi

Re: [PATCH v10 2/4] fs: Add standard casefolding support

[Eric Biggers]

On Tue, Jul 07, 2020 at 04:31:21AM -0700, Daniel Rosenberg wrote:
> +/*
> + * Determine if the name of a dentry should be casefolded. It does not make
> + * sense to casefold the no-key token of an encrypted filename.
> + *
> + * Return: if names will need casefolding
> + */
> +static bool needs_casefold(const struct inode *dir, const struct dentry *dentry)
> +{
> +	return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding &&
> +			!(dentry->d_flags & DCACHE_ENCRYPTED_NAME);
> +}
> +
[...]
> +/**
> + * 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, dentry))
> +		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);

I thought this was discussed before, but the 'dentry' passed to ->d_hash() is
the parent dentry, not the one being hashed.

Therefore checking DCACHE_ENCRYPTED_NAME on 'dentry' is wrong here.  Instead we
need to use !fscrypt_has_encryption_key() here.  (IOW, while checking
DCACHE_ENCRYPTED_NAME is better *when possible*, it's not possible here.)

Note that the whole point of ->d_hash() is to hash the filename so that the VFS
can find the dentry.  If the VFS already had the dentry, there would be no need
for ->d_hash().

Also, did you consider my suggestion to not handle encrypt+casefold in this
patch?  I'd like to get this series in as a refactoring for 5.9.  The encryption
handling (which is new) might better belong in a later patch series.

- Eric

Re: [PATCH v10 1/4] unicode: Add utf8_casefold_hash

[Eric Biggers]

On Tue, Jul 07, 2020 at 04:31:20AM -0700, Daniel Rosenberg wrote:
> This adds a case insensitive hash function to allow taking the hash
> without needing to allocate a casefolded copy of the string.
> 
> The existing d_hash implementations for casefolding allocates memory
> within rcu-walk, by avoiding it we can be more efficient and avoid
> worrying about a failed allocation.
> 
> Signed-off-by: Daniel Rosenberg <drosen@google.com>

You can add:

	Reviewed-by: Eric Biggers <ebiggers@google.com>

If you have a chance please fix the grammar in the commit message though:

"The existing d_hash implementations for casefolding allocate memory
within rcu-walk.  By avoiding this we can be more efficient and avoid
worrying about a failed allocation."

- Eric

Re: [PATCH v10 3/4] f2fs: Use generic casefolding support

[Eric Biggers]

On Tue, Jul 07, 2020 at 04:31:22AM -0700, Daniel Rosenberg wrote:
> This switches f2fs over to the generic support provided in
> the previous patch.
> 
> Since casefolded dentries behave the same in ext4 and f2fs, we decrease
> the maintenance burden by unifying them, and any optimizations will
> immediately apply to both.
> 
> Signed-off-by: Daniel Rosenberg <drosen@google.com>
> ---
>  fs/f2fs/dir.c           | 83 +++++------------------------------------
>  fs/f2fs/f2fs.h          |  4 --
>  fs/f2fs/super.c         | 10 ++---
>  fs/f2fs/sysfs.c         | 10 +++--
>  include/linux/f2fs_fs.h |  3 --
>  5 files changed, 20 insertions(+), 90 deletions(-)

Looks good, you can add:

    Reviewed-by: Eric Biggers <ebiggers@google.com>

One nit below:

>  #ifdef CONFIG_UNICODE
> -static int f2fs_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 *dir = READ_ONCE(parent->d_inode);
> -	const struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
> -	struct qstr entry = QSTR_INIT(str, len);
> -	char strbuf[DNAME_INLINE_LEN];
> -	int res;
> -
> -	if (!dir || !IS_CASEFOLDED(dir))
> -		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;
> -		entry.name = strbuf;
> -		/* prevent compiler from optimizing out the temporary buffer */
> -		barrier();
> -	}
> -
> -	res = utf8_strncasecmp(sbi->s_encoding, name, &entry);
> -	if (res >= 0)
> -		return res;
> -
> -	if (f2fs_has_strict_mode(sbi))
> -		return -EINVAL;
> -fallback:
> -	if (len != name->len)
> -		return 1;
> -	return !!memcmp(str, name->name, len);
> -}
> -
> -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;
> -	const struct inode *inode = READ_ONCE(dentry->d_inode);
> -	unsigned char *norm;
> -	int len, ret = 0;
> -
> -	if (!inode || !IS_CASEFOLDED(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,
> +	.d_hash = generic_ci_d_hash,
> +	.d_compare = generic_ci_d_compare,
>  };
>  #endif

This leaves an extra blank line just above f2fs_dentry_ops.

- Eric

Re: [PATCH v10 4/4] ext4: Use generic casefolding support

[Eric Biggers]

On Tue, Jul 07, 2020 at 04:31:23AM -0700, Daniel Rosenberg wrote:
> This switches ext4 over to the generic support provided in
> the previous patch.
> 
> Since casefolded dentries behave the same in ext4 and f2fs, we decrease
> the maintenance burden by unifying them, and any optimizations will
> immediately apply to both.
> 
> Signed-off-by: Daniel Rosenberg <drosen@google.com>
> ---
>  fs/ext4/dir.c   | 64 ++-----------------------------------------------
>  fs/ext4/ext4.h  | 12 ----------
>  fs/ext4/hash.c  |  2 +-
>  fs/ext4/namei.c | 20 +++++++---------
>  fs/ext4/super.c | 12 +++++-----
>  5 files changed, 17 insertions(+), 93 deletions(-)
> 

Looks good, you can add:

    Reviewed-by: Eric Biggers <ebiggers@google.com>

- Eric