[PATCH 5.10 212/523] hfsplus: fix slab-out-of-bounds read in hfsplus_uni2asc()

[PATCH 5.10 212/523] hfsplus: fix slab-out-of-bounds read in hfsplus_uni2asc()

[Greg Kroah-Hartman]

5.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Viacheslav Dubeyko <slava@dubeyko.com>

[ Upstream commit 94458781aee6045bd3d0ad4b80b02886b9e2219b ]

The hfsplus_readdir() method is capable to crash by calling
hfsplus_uni2asc():

[  667.121659][ T9805] ==================================================================
[  667.122651][ T9805] BUG: KASAN: slab-out-of-bounds in hfsplus_uni2asc+0x902/0xa10
[  667.123627][ T9805] Read of size 2 at addr ffff88802592f40c by task repro/9805
[  667.124578][ T9805]
[  667.124876][ T9805] CPU: 3 UID: 0 PID: 9805 Comm: repro Not tainted 6.16.0-rc3 #1 PREEMPT(full)
[  667.124886][ T9805] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[  667.124890][ T9805] Call Trace:
[  667.124893][ T9805]  <TASK>
[  667.124896][ T9805]  dump_stack_lvl+0x10e/0x1f0
[  667.124911][ T9805]  print_report+0xd0/0x660
[  667.124920][ T9805]  ? __virt_addr_valid+0x81/0x610
[  667.124928][ T9805]  ? __phys_addr+0xe8/0x180
[  667.124934][ T9805]  ? hfsplus_uni2asc+0x902/0xa10
[  667.124942][ T9805]  kasan_report+0xc6/0x100
[  667.124950][ T9805]  ? hfsplus_uni2asc+0x902/0xa10
[  667.124959][ T9805]  hfsplus_uni2asc+0x902/0xa10
[  667.124966][ T9805]  ? hfsplus_bnode_read+0x14b/0x360
[  667.124974][ T9805]  hfsplus_readdir+0x845/0xfc0
[  667.124984][ T9805]  ? __pfx_hfsplus_readdir+0x10/0x10
[  667.124994][ T9805]  ? stack_trace_save+0x8e/0xc0
[  667.125008][ T9805]  ? iterate_dir+0x18b/0xb20
[  667.125015][ T9805]  ? trace_lock_acquire+0x85/0xd0
[  667.125022][ T9805]  ? lock_acquire+0x30/0x80
[  667.125029][ T9805]  ? iterate_dir+0x18b/0xb20
[  667.125037][ T9805]  ? down_read_killable+0x1ed/0x4c0
[  667.125044][ T9805]  ? putname+0x154/0x1a0
[  667.125051][ T9805]  ? __pfx_down_read_killable+0x10/0x10
[  667.125058][ T9805]  ? apparmor_file_permission+0x239/0x3e0
[  667.125069][ T9805]  iterate_dir+0x296/0xb20
[  667.125076][ T9805]  __x64_sys_getdents64+0x13c/0x2c0
[  667.125084][ T9805]  ? __pfx___x64_sys_getdents64+0x10/0x10
[  667.125091][ T9805]  ? __x64_sys_openat+0x141/0x200
[  667.125126][ T9805]  ? __pfx_filldir64+0x10/0x10
[  667.125134][ T9805]  ? do_user_addr_fault+0x7fe/0x12f0
[  667.125143][ T9805]  do_syscall_64+0xc9/0x480
[  667.125151][ T9805]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  667.125158][ T9805] RIP: 0033:0x7fa8753b2fc9
[  667.125164][ T9805] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 48
[  667.125172][ T9805] RSP: 002b:00007ffe96f8e0f8 EFLAGS: 00000217 ORIG_RAX: 00000000000000d9
[  667.125181][ T9805] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fa8753b2fc9
[  667.125185][ T9805] RDX: 0000000000000400 RSI: 00002000000063c0 RDI: 0000000000000004
[  667.125190][ T9805] RBP: 00007ffe96f8e110 R08: 00007ffe96f8e110 R09: 00007ffe96f8e110
[  667.125195][ T9805] R10: 0000000000000000 R11: 0000000000000217 R12: 0000556b1e3b4260
[  667.125199][ T9805] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[  667.125207][ T9805]  </TASK>
[  667.125210][ T9805]
[  667.145632][ T9805] Allocated by task 9805:
[  667.145991][ T9805]  kasan_save_stack+0x20/0x40
[  667.146352][ T9805]  kasan_save_track+0x14/0x30
[  667.146717][ T9805]  __kasan_kmalloc+0xaa/0xb0
[  667.147065][ T9805]  __kmalloc_noprof+0x205/0x550
[  667.147448][ T9805]  hfsplus_find_init+0x95/0x1f0
[  667.147813][ T9805]  hfsplus_readdir+0x220/0xfc0
[  667.148174][ T9805]  iterate_dir+0x296/0xb20
[  667.148549][ T9805]  __x64_sys_getdents64+0x13c/0x2c0
[  667.148937][ T9805]  do_syscall_64+0xc9/0x480
[  667.149291][ T9805]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  667.149809][ T9805]
[  667.150030][ T9805] The buggy address belongs to the object at ffff88802592f000
[  667.150030][ T9805]  which belongs to the cache kmalloc-2k of size 2048
[  667.151282][ T9805] The buggy address is located 0 bytes to the right of
[  667.151282][ T9805]  allocated 1036-byte region [ffff88802592f000, ffff88802592f40c)
[  667.152580][ T9805]
[  667.152798][ T9805] The buggy address belongs to the physical page:
[  667.153373][ T9805] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x25928
[  667.154157][ T9805] head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[  667.154916][ T9805] anon flags: 0xfff00000000040(head|node=0|zone=1|lastcpupid=0x7ff)
[  667.155631][ T9805] page_type: f5(slab)
[  667.155997][ T9805] raw: 00fff00000000040 ffff88801b442f00 0000000000000000 dead000000000001
[  667.156770][ T9805] raw: 0000000000000000 0000000080080008 00000000f5000000 0000000000000000
[  667.157536][ T9805] head: 00fff00000000040 ffff88801b442f00 0000000000000000 dead000000000001
[  667.158317][ T9805] head: 0000000000000000 0000000080080008 00000000f5000000 0000000000000000
[  667.159088][ T9805] head: 00fff00000000003 ffffea0000964a01 00000000ffffffff 00000000ffffffff
[  667.159865][ T9805] head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000008
[  667.160643][ T9805] page dumped because: kasan: bad access detected
[  667.161216][ T9805] page_owner tracks the page as allocated
[  667.161732][ T9805] page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN9
[  667.163566][ T9805]  post_alloc_hook+0x1c0/0x230
[  667.164003][ T9805]  get_page_from_freelist+0xdeb/0x3b30
[  667.164503][ T9805]  __alloc_frozen_pages_noprof+0x25c/0x2460
[  667.165040][ T9805]  alloc_pages_mpol+0x1fb/0x550
[  667.165489][ T9805]  new_slab+0x23b/0x340
[  667.165872][ T9805]  ___slab_alloc+0xd81/0x1960
[  667.166313][ T9805]  __slab_alloc.isra.0+0x56/0xb0
[  667.166767][ T9805]  __kmalloc_cache_noprof+0x255/0x3e0
[  667.167255][ T9805]  psi_cgroup_alloc+0x52/0x2d0
[  667.167693][ T9805]  cgroup_mkdir+0x694/0x1210
[  667.168118][ T9805]  kernfs_iop_mkdir+0x111/0x190
[  667.168568][ T9805]  vfs_mkdir+0x59b/0x8d0
[  667.168956][ T9805]  do_mkdirat+0x2ed/0x3d0
[  667.169353][ T9805]  __x64_sys_mkdir+0xef/0x140
[  667.169784][ T9805]  do_syscall_64+0xc9/0x480
[  667.170195][ T9805]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  667.170730][ T9805] page last free pid 1257 tgid 1257 stack trace:
[  667.171304][ T9805]  __free_frozen_pages+0x80c/0x1250
[  667.171770][ T9805]  vfree.part.0+0x12b/0xab0
[  667.172182][ T9805]  delayed_vfree_work+0x93/0xd0
[  667.172612][ T9805]  process_one_work+0x9b5/0x1b80
[  667.173067][ T9805]  worker_thread+0x630/0xe60
[  667.173486][ T9805]  kthread+0x3a8/0x770
[  667.173857][ T9805]  ret_from_fork+0x517/0x6e0
[  667.174278][ T9805]  ret_from_fork_asm+0x1a/0x30
[  667.174703][ T9805]
[  667.174917][ T9805] Memory state around the buggy address:
[  667.175411][ T9805]  ffff88802592f300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  667.176114][ T9805]  ffff88802592f380: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  667.176830][ T9805] >ffff88802592f400: 00 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  667.177547][ T9805]                       ^
[  667.177933][ T9805]  ffff88802592f480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  667.178640][ T9805]  ffff88802592f500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  667.179350][ T9805] ==================================================================

The hfsplus_uni2asc() method operates by struct hfsplus_unistr:

struct hfsplus_unistr {
	__be16 length;
	hfsplus_unichr unicode[HFSPLUS_MAX_STRLEN];
} __packed;

where HFSPLUS_MAX_STRLEN is 255 bytes. The issue happens if length
of the structure instance has value bigger than 255 (for example,
65283). In such case, pointer on unicode buffer is going beyond of
the allocated memory.

The patch fixes the issue by checking the length value of
hfsplus_unistr instance and using 255 value in the case if length
value is bigger than HFSPLUS_MAX_STRLEN. Potential reason of such
situation could be a corruption of Catalog File b-tree's node.

Reported-by: Wenzhi Wang <wenzhi.wang@uwaterloo.ca>
Signed-off-by: Liu Shixin <liushixin2@huawei.com>
Signed-off-by: Viacheslav Dubeyko <slava@dubeyko.com>
cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
cc: Yangtao Li <frank.li@vivo.com>
cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Yangtao Li <frank.li@vivo.com>
Link: https://lore.kernel.org/r/20250710230830.110500-1-slava@dubeyko.com
Signed-off-by: Viacheslav Dubeyko <slava@dubeyko.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/hfsplus/unicode.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
index 73342c925a4b..36b6cf2a3abb 100644
--- a/fs/hfsplus/unicode.c
+++ b/fs/hfsplus/unicode.c
@@ -132,7 +132,14 @@ int hfsplus_uni2asc(struct super_block *sb,
 
 	op = astr;
 	ip = ustr->unicode;
+
 	ustrlen = be16_to_cpu(ustr->length);
+	if (ustrlen > HFSPLUS_MAX_STRLEN) {
+		ustrlen = HFSPLUS_MAX_STRLEN;
+		pr_err("invalid length %u has been corrected to %d\n",
+			be16_to_cpu(ustr->length), ustrlen);
+	}
+
 	len = *len_p;
 	ce1 = NULL;
 	compose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
-- 
2.39.5

[PATCH 5.10 402/523] move_mount: allow to add a mount into an existing group

[Greg Kroah-Hartman]

5.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>

[ Upstream commit 9ffb14ef61bab83fa818736bf3e7e6b6e182e8e2 ]

Previously a sharing group (shared and master ids pair) can be only
inherited when mount is created via bindmount. This patch adds an
ability to add an existing private mount into an existing sharing group.

With this functionality one can first create the desired mount tree from
only private mounts (without the need to care about undesired mount
propagation or mount creation order implied by sharing group
dependencies), and next then setup any desired mount sharing between
those mounts in tree as needed.

This allows CRIU to restore any set of mount namespaces, mount trees and
sharing group trees for a container.

We have many issues with restoring mounts in CRIU related to sharing
groups and propagation:
- reverse sharing groups vs mount tree order requires complex mounts
  reordering which mostly implies also using some temporary mounts
(please see https://lkml.org/lkml/2021/3/23/569 for more info)

- mount() syscall creates tons of mounts due to propagation
- mount re-parenting due to propagation
- "Mount Trap" due to propagation
- "Non Uniform" propagation, meaning that with different tricks with
  mount order and temporary children-"lock" mounts one can create mount
  trees which can't be restored without those tricks
(see https://www.linuxplumbersconf.org/event/7/contributions/640/)

With this new functionality we can resolve all the problems with
propagation at once.

Link: https://lore.kernel.org/r/20210715100714.120228-1-ptikhomirov@virtuozzo.com
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Mattias Nissler <mnissler@chromium.org>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-api@vger.kernel.org
Cc: lkml <linux-kernel@vger.kernel.org>
Co-developed-by: Andrei Vagin <avagin@gmail.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Stable-dep-of: cffd0441872e ("use uniform permission checks for all mount propagation changes")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/namespace.c             | 77 +++++++++++++++++++++++++++++++++++++-
 include/uapi/linux/mount.h |  3 +-
 2 files changed, 78 insertions(+), 2 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index ee6d139f7529..7f7ccc9e53b8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2692,6 +2692,78 @@ static bool check_for_nsfs_mounts(struct mount *subtree)
 	return ret;
 }
 
+static int do_set_group(struct path *from_path, struct path *to_path)
+{
+	struct mount *from, *to;
+	int err;
+
+	from = real_mount(from_path->mnt);
+	to = real_mount(to_path->mnt);
+
+	namespace_lock();
+
+	err = -EINVAL;
+	/* To and From must be mounted */
+	if (!is_mounted(&from->mnt))
+		goto out;
+	if (!is_mounted(&to->mnt))
+		goto out;
+
+	err = -EPERM;
+	/* We should be allowed to modify mount namespaces of both mounts */
+	if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		goto out;
+	if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		goto out;
+
+	err = -EINVAL;
+	/* To and From paths should be mount roots */
+	if (from_path->dentry != from_path->mnt->mnt_root)
+		goto out;
+	if (to_path->dentry != to_path->mnt->mnt_root)
+		goto out;
+
+	/* Setting sharing groups is only allowed across same superblock */
+	if (from->mnt.mnt_sb != to->mnt.mnt_sb)
+		goto out;
+
+	/* From mount root should be wider than To mount root */
+	if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root))
+		goto out;
+
+	/* From mount should not have locked children in place of To's root */
+	if (has_locked_children(from, to->mnt.mnt_root))
+		goto out;
+
+	/* Setting sharing groups is only allowed on private mounts */
+	if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to))
+		goto out;
+
+	/* From should not be private */
+	if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from))
+		goto out;
+
+	if (IS_MNT_SLAVE(from)) {
+		struct mount *m = from->mnt_master;
+
+		list_add(&to->mnt_slave, &m->mnt_slave_list);
+		to->mnt_master = m;
+	}
+
+	if (IS_MNT_SHARED(from)) {
+		to->mnt_group_id = from->mnt_group_id;
+		list_add(&to->mnt_share, &from->mnt_share);
+		lock_mount_hash();
+		set_mnt_shared(to);
+		unlock_mount_hash();
+	}
+
+	err = 0;
+out:
+	namespace_unlock();
+	return err;
+}
+
 static int do_move_mount(struct path *old_path, struct path *new_path)
 {
 	struct mnt_namespace *ns;
@@ -3667,7 +3739,10 @@ SYSCALL_DEFINE5(move_mount,
 	if (ret < 0)
 		goto out_to;
 
-	ret = do_move_mount(&from_path, &to_path);
+	if (flags & MOVE_MOUNT_SET_GROUP)
+		ret = do_set_group(&from_path, &to_path);
+	else
+		ret = do_move_mount(&from_path, &to_path);
 
 out_to:
 	path_put(&to_path);
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index dd8306ea336c..fc6a2e63130b 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -71,7 +71,8 @@
 #define MOVE_MOUNT_T_SYMLINKS		0x00000010 /* Follow symlinks on to path */
 #define MOVE_MOUNT_T_AUTOMOUNTS		0x00000020 /* Follow automounts on to path */
 #define MOVE_MOUNT_T_EMPTY_PATH		0x00000040 /* Empty to path permitted */
-#define MOVE_MOUNT__MASK		0x00000077
+#define MOVE_MOUNT_SET_GROUP		0x00000100 /* Set sharing group instead */
+#define MOVE_MOUNT__MASK		0x00000177
 
 /*
  * fsopen() flags.
-- 
2.50.1