Merge tag 'vfs-6.13.tmpfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull tmpfs case folding updates from Christian Brauner:
 "This adds case-insensitive support for tmpfs.

  The work contained in here adds support for case-insensitive file
  names lookups in tmpfs. The main difference from other casefold
  filesystems is that tmpfs has no information on disk, just on RAM, so
  we can't use mkfs to create a case-insensitive tmpfs. For this
  implementation, there's a mount option for casefolding. The rest of
  the patchset follows a similar approach as ext4 and f2fs.

  The use case for this feature is similar to the use case for ext4, to
  better support compatibility layers (like Wine), particularly in
  combination with sandboxing/container tools (like Flatpak).

  Those containerization tools can share a subset of the host filesystem
  with an application. In the container, the root directory and any
  parent directories required for a shared directory are on tmpfs, with
  the shared directories bind-mounted into the container's view of the
  filesystem.

  If the host filesystem is using case-insensitive directories, then the
  application can do lookups inside those directories in a
  case-insensitive way, without this needing to be implemented in
  user-space. However, if the host is only sharing a subset of a
  case-insensitive directory with the application, then the parent
  directories of the mount point will be part of the container's root
  tmpfs. When the application tries to do case-insensitive lookups of
  those parent directories on a case-sensitive tmpfs, the lookup will
  fail"

* tag 'vfs-6.13.tmpfs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  tmpfs: Initialize sysfs during tmpfs init
  tmpfs: Fix type for sysfs' casefold attribute
  libfs: Fix kernel-doc warning in generic_ci_validate_strict_name
  docs: tmpfs: Add casefold options
  tmpfs: Expose filesystem features via sysfs
  tmpfs: Add flag FS_CASEFOLD_FL support for tmpfs dirs
  tmpfs: Add casefold lookup support
  libfs: Export generic_ci_ dentry functions
  unicode: Recreate utf8_parse_version()
  unicode: Export latest available UTF-8 version number
  ext4: Use generic_ci_validate_strict_name helper
  libfs: Create the helper function generic_ci_validate_strict_name()

Author: torvalds

Documentation/filesystems/tmpfs.rst

@@ -241,6 +241,28 @@ So 'mount -t tmpfs -o size=10G,nr_inodes=10k,mode=700 tmpfs /mytmpfs'
 will give you tmpfs instance on /mytmpfs which can allocate 10GB
 RAM/SWAP in 10240 inodes and it is only accessible by root.
 
+tmpfs has the following mounting options for case-insensitive lookup support:
+
+================= ==============================================================
+casefold          Enable casefold support at this mount point using the given
+                  argument as the encoding standard. Currently only UTF-8
+                  encodings are supported. If no argument is used, it will load
+                  the latest UTF-8 encoding available.
+strict_encoding   Enable strict encoding at this mount point (disabled by
+                  default). In this mode, the filesystem refuses to create file
+                  and directory with names containing invalid UTF-8 characters.
+================= ==============================================================
+
+This option doesn't render the entire filesystem case-insensitive. One needs to
+still set the casefold flag per directory, by flipping the +F attribute in an
+empty directory. Nevertheless, new directories will inherit the attribute. The
+mountpoint itself cannot be made case-insensitive.
+
+Example::
+
+    $ mount -t tmpfs -o casefold=utf8-12.1.0,strict_encoding fs_name /mytmpfs
+    $ mount -t tmpfs -o casefold fs_name /mytmpfs
+
 
 :Author:
    Christoph Rohland <[email protected]>, 1.12.01
@@ -250,3 +272,5 @@ RAM/SWAP in 10240 inodes and it is only accessible by root.
    KOSAKI Motohiro, 16 Mar 2010
 :Updated:
    Chris Down, 13 July 2020
+:Updated:
+   André Almeida, 23 Aug 2024

fs/ext4/namei.c

@@ -2395,11 +2395,8 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	if (fscrypt_is_nokey_name(dentry))
 		return -ENOKEY;
 
-#if IS_ENABLED(CONFIG_UNICODE)
-	if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
-	    utf8_validate(sb->s_encoding, &dentry->d_name))
+	if (!generic_ci_validate_strict_name(dir, &dentry->d_name))
 		return -EINVAL;
-#endif
 
 	retval = ext4_fname_setup_filename(dir, &dentry->d_name, 0, &fname);
 	if (retval)

fs/libfs.c

@@ -77,6 +77,10 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned
 		return ERR_PTR(-ENAMETOOLONG);
 	if (!dentry->d_sb->s_d_op)
 		d_set_d_op(dentry, &simple_dentry_operations);
+
+	if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
+		return NULL;
+
 	d_add(dentry, NULL);
 	return NULL;
 }
@@ -1791,8 +1795,8 @@ bool is_empty_dir_inode(struct inode *inode)
  *
  * Return: 0 if names match, 1 if mismatch, or -ERRNO
  */
-static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
-				const char *str, const struct qstr *name)
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			 const char *str, const struct qstr *name)
 {
 	const struct dentry *parent;
 	const struct inode *dir;
@@ -1835,6 +1839,7 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
 
 	return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr);
 }
+EXPORT_SYMBOL(generic_ci_d_compare);
 
 /**
  * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems
@@ -1843,7 +1848,7 @@ static int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
  *
  * Return: 0 if hash was successful or unchanged, and -EINVAL on error
  */
-static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 {
 	const struct inode *dir = READ_ONCE(dentry->d_inode);
 	struct super_block *sb = dentry->d_sb;
@@ -1858,6 +1863,7 @@ static int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str)
 		return -EINVAL;
 	return 0;
 }
+EXPORT_SYMBOL(generic_ci_d_hash);
 
 static const struct dentry_operations generic_ci_dentry_ops = {
 	.d_hash = generic_ci_d_hash,

fs/unicode/utf8-core.c

@@ -214,3 +214,29 @@ void utf8_unload(struct unicode_map *um)
 }
 EXPORT_SYMBOL(utf8_unload);
 
+/**
+ * utf8_parse_version - Parse a UTF-8 version number from a string
+ *
+ * @version: input string
+ *
+ * Returns the parsed version on success, negative code on error
+ */
+int utf8_parse_version(char *version)
+{
+	substring_t args[3];
+	unsigned int maj, min, rev;
+	static const struct match_token token[] = {
+		{1, "%d.%d.%d"},
+		{0, NULL}
+	};
+
+	if (match_token(version, token, args) != 1)
+		return -EINVAL;
+
+	if (match_int(&args[0], &maj) || match_int(&args[1], &min) ||
+	    match_int(&args[2], &rev))
+		return -EINVAL;
+
+	return UNICODE_AGE(maj, min, rev);
+}
+EXPORT_SYMBOL(utf8_parse_version);

fs/unicode/utf8-selftest.c

@@ -17,9 +17,6 @@
 static unsigned int failed_tests;
 static unsigned int total_tests;
 
-/* Tests will be based on this version. */
-#define UTF8_LATEST	UNICODE_AGE(12, 1, 0)
-
 #define _test(cond, func, line, fmt, ...) do {				\
 		total_tests++;						\
 		if (!cond) {						\

include/linux/fs.h

@@ -46,6 +46,7 @@
 #include <linux/maple_tree.h>
 #include <linux/rw_hint.h>
 #include <linux/file_ref.h>
+#include <linux/unicode.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -3479,6 +3480,54 @@ extern int generic_ci_match(const struct inode *parent,
 			    const struct qstr *folded_name,
 			    const u8 *de_name, u32 de_name_len);
 
+#if IS_ENABLED(CONFIG_UNICODE)
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			 const char *str, const struct qstr *name);
+
+/**
+ * generic_ci_validate_strict_name - Check if a given name is suitable
+ * for a directory
+ *
+ * This functions checks if the proposed filename is valid for the
+ * parent directory. That means that only valid UTF-8 filenames will be
+ * accepted for casefold directories from filesystems created with the
+ * strict encoding flag.  That also means that any name will be
+ * accepted for directories that doesn't have casefold enabled, or
+ * aren't being strict with the encoding.
+ *
+ * @dir: inode of the directory where the new file will be created
+ * @name: name of the new file
+ *
+ * Return:
+ * * True: if the filename is suitable for this directory. It can be
+ *   true if a given name is not suitable for a strict encoding
+ *   directory, but the directory being used isn't strict
+ * * False if the filename isn't suitable for this directory. This only
+ *   happens when a directory is casefolded and the filesystem is strict
+ *   about its encoding.
+ */
+static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name)
+{
+	if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb))
+		return true;
+
+	/*
+	 * A casefold dir must have a encoding set, unless the filesystem
+	 * is corrupted
+	 */
+	if (WARN_ON_ONCE(!dir->i_sb->s_encoding))
+		return true;
+
+	return !utf8_validate(dir->i_sb->s_encoding, name);
+}
+#else
+static inline bool generic_ci_validate_strict_name(struct inode *dir, struct qstr *name)
+{
+	return true;
+}
+#endif
+
 static inline bool sb_has_encoding(const struct super_block *sb)
 {
 #if IS_ENABLED(CONFIG_UNICODE)

include/linux/shmem_fs.h

@@ -42,10 +42,10 @@ struct shmem_inode_info {
 	struct inode		vfs_inode;
 };
 
-#define SHMEM_FL_USER_VISIBLE		FS_FL_USER_VISIBLE
+#define SHMEM_FL_USER_VISIBLE		(FS_FL_USER_VISIBLE | FS_CASEFOLD_FL)
 #define SHMEM_FL_USER_MODIFIABLE \
-	(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL)
-#define SHMEM_FL_INHERITED		(FS_NODUMP_FL | FS_NOATIME_FL)
+	(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL)
+#define SHMEM_FL_INHERITED		(FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL)
 
 struct shmem_quota_limits {
 	qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */

include/linux/unicode.h

@@ -16,6 +16,8 @@ struct utf8data_table;
 	 ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) |	\
 	 ((unsigned int)(REV)))
 
+#define UTF8_LATEST        UNICODE_AGE(12, 1, 0)
+
 static inline u8 unicode_major(unsigned int age)
 {
 	return (age >> UNICODE_MAJ_SHIFT) & 0xff;
@@ -76,4 +78,6 @@ int utf8_casefold_hash(const struct unicode_map *um, const void *salt,
 struct unicode_map *utf8_load(unsigned int version);
 void utf8_unload(struct unicode_map *um);
 
+int utf8_parse_version(char *version);
+
 #endif /* _LINUX_UNICODE_H */