Files
erofs-linux/include/linux/unicode.h
T
Christian Brauner a96c5299bd unicode: free the map after a grace period
generic_ci_d_hash() and generic_ci_d_compare() read sb->s_encoding and
dereference the unicode map while a pathwalk in rcu mode holds nothing
but rcu_read_lock(). The filesystems that use them, ext4, f2fs and
tmpfs, drop the map with utf8_unload() from ->put_super(), which runs
when the last reference to the mount goes away. A lookup that is still
inside such a filesystem at that point reads a freed map.

With a pathwalk held up in utf8_casefold_hash() while the last reference
to a casefolded tmpfs goes away:

  BUG: KASAN: slab-use-after-free in utf8nlookup+0x74c/0x950
  Read of size 8 at addr ff110001030fe658 by task walker/98
  Call Trace:
   <TASK>
   utf8nlookup+0x74c/0x950
   utf8byte+0x160/0x1560
   utf8_casefold_hash+0x167/0x230
   generic_ci_d_hash+0xdd/0x1c0
   link_path_walk+0x11ad/0x1d30
   path_lookupat+0x63/0xb00
   filename_lookup+0x1f1/0x5b0
   vfs_statx+0xd7/0x3b0
  [...]
  Allocated by task 94:
   __kmalloc_cache_noprof+0x249/0x560
   utf8_load+0x4e/0x570
   shmem_parse_opt_casefold.isra.0+0x92/0x270
  [...]
  Freed by task 97:
   kfree+0x1db/0x5b0
   shmem_put_super+0x72/0x170
   generic_shutdown_super+0x14c/0x530
   kill_anon_super+0x3a/0x60
   deactivate_locked_super+0x9c/0xf0
   cleanup_mnt+0x9f/0x130

So far that has been hard to hit. umount(2) waits for a grace period
in namespace_unlock() before it drops the mount, so only a mount whose
last reference goes away elsewhere, like the close of a file or a chdir
out of a lazily unmounted directory, can race a walker. So it is
reachable.

Delay the free until a grace period has passed. The map and the data
table it holds a reference to then outlive any pathwalk that found the
superblock before the mount went away. The reference on the data table
module is dropped from the rcu callback as well. utf8-core is built in
whenever CONFIG_UNICODE is set, so there is no module exit that would
have to wait for the callbacks.

Overlayfs points the s_encoding of an overlay at the map of its first
layer without taking a reference of its own. That stays correct. The
layer is held by the overlay, so its map is dropped only after the
overlay is gone.

Fixes: b886ee3e77 ("ext4: Support case-insensitive file name lookups")
Cc: [email protected]
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Christian Brauner (Amutable) <[email protected]>
2026-10-14 22:08:03 +02:00

82 lines
2.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_UNICODE_H
#define _LINUX_UNICODE_H
#include <linux/init.h>
#include <linux/dcache.h>
struct utf8data;
struct utf8data_table;
#define UNICODE_MAJ_SHIFT 16
#define UNICODE_MIN_SHIFT 8
#define UNICODE_AGE(MAJ, MIN, REV) \
(((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \
((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;
}
static inline u8 unicode_minor(unsigned int age)
{
return (age >> UNICODE_MIN_SHIFT) & 0xff;
}
static inline u8 unicode_rev(unsigned int age)
{
return age & 0xff;
}
/*
* Two normalization forms are supported:
* 1) NFDI
* - Apply unicode normalization form NFD.
* - Remove any Default_Ignorable_Code_Point.
* 2) NFDICF
* - Apply unicode normalization form NFD.
* - Remove any Default_Ignorable_Code_Point.
* - Apply a full casefold (C + F).
*/
enum utf8_normalization {
UTF8_NFDI = 0,
UTF8_NFDICF,
UTF8_NMAX,
};
struct unicode_map {
unsigned int version;
const struct utf8data *ntab[UTF8_NMAX];
const struct utf8data_table *tables;
struct rcu_head rcu;
};
int utf8_validate(const struct unicode_map *um, const struct qstr *str);
int utf8_strncmp(const struct unicode_map *um,
const struct qstr *s1, const struct qstr *s2);
int utf8_strncasecmp(const struct unicode_map *um,
const struct qstr *s1, const struct qstr *s2);
int utf8_strncasecmp_folded(const struct unicode_map *um,
const struct qstr *cf,
const struct qstr *s1);
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(unsigned int version);
void utf8_unload(struct unicode_map *um);
int utf8_parse_version(char *version);
#endif /* _LINUX_UNICODE_H */