FAILED: patch "[PATCH] fhandle: fix UAF due to unlocked ->mnt_ns read in" failed to apply to 6.12-stable tree
Subsystems (3)
[email protected]
maintainerThe patch below does not apply to the 6.12-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y
git checkout FETCH_HEAD
git cherry-pick -x 40ab6644b99685755f740b872c00ef40d9aa870e
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026061543-clavicle-quote-2f44@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^..
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 40ab6644b99685755f740b872c00ef40d9aa870e Mon Sep 17 00:00:00 2001
From: Jann Horn <[email protected]>
Date: Wed, 3 Jun 2026 21:31:57 +0200
Subject: [PATCH] fhandle: fix UAF due to unlocked ->mnt_ns read in
may_decode_fh()
may_decode_fh() accesses mount::mnt_ns without holding any locks; that means the mount can concurrently be unmounted, and the mnt_namespace can concurrently be freed after an RCU grace period.
This race can happens as follows, assuming that the mount point was created by open_tree(..., OPEN_TREE_CLONE):
thread 1 thread 2 RCU
__do_sys_open_by_handle_at
do_handle_open
handle_to_path
may_decode_fh
is_mounted
[mount::mnt_ns access]
[mount::mnt_ns access]
__do_sys_close
fput_close_sync
__fput
dissolve_on_fput
umount_tree
class_namespace_excl_destructor
namespace_unlock
free_mnt_ns
mnt_ns_tree_remove
call_rcu(mnt_ns_release_rcu)
mnt_ns_release_rcu
mnt_ns_release
kfree
[mnt_namespace::user_ns access] **UAF**Fix it by taking rcu_read_lock() around the mount::mnt_ns access, like in __prepend_path().
Additionally, document the semantics of mount::mnt_ns, and use WRITE_ONCE() for writers that can race with lockless readers.
This bug is unreachable unless one of the following is set:
- CONFIG_PREEMPTION
- CONFIG_RCU_STRICT_GRACE_PERIOD
because it requires an RCU grace period to happen during a syscall without an explicit preemption.
This doesn't seem to have interesting security impact; worst-case, it could leak the result of an integer comparison to userspace (from the level check in cap_capable()), cause an endless loop, or crash the kernel by dereferencing an invalid address.
fs/fhandle.c +14 -2
@@ -285,6 +285,19 @@ static int do_handle_to_path(struct file_handle *handle, struct path *path,return 0 ; } +static bool capable_wrt_mount (struct mount *mount) +{ +struct mnt_namespace *mnt_ns; + +/* +* For ->mnt_ns access. +* The following READ_ONCE() is semantically rcu_dereference(). +*/ +guard (rcu)(); + mnt_ns =READ_ONCE (mount->mnt_ns); +return ns_capable (mnt_ns->user_ns,CAP_SYS_ADMIN ); +} +static inline int may_decode_fh (struct handle_to_path_ctx *ctx,unsigned int o_flags) {
@@ -320,8 +333,7 @@ static inline int may_decode_fh(struct handle_to_path_ctx *ctx,if (ns_capable (root->mnt->mnt_sb->s_user_ns,CAP_SYS_ADMIN )) ctx->flags =HANDLE_CHECK_PERMS ;else if (is_mounted (root->mnt) && -ns_capable (real_mount (root->mnt)->mnt_ns->user_ns, -CAP_SYS_ADMIN ) && +capable_wrt_mount (real_mount (root->mnt)) && !has_locked_children (real_mount (root->mnt), root->dentry)) ctx->flags =HANDLE_CHECK_PERMS |HANDLE_CHECK_SUBTREE ;else
fs/mount.h +9 -1
@@ -71,7 +71,15 @@ struct mount {struct hlist_head mnt_slave_list;/* list of slave mounts */ struct hlist_node mnt_slave;/* slave list entry */ struct mount *mnt_master;/* slave is on master->mnt_slave_list */ -struct mnt_namespace *mnt_ns;/* containing namespace */ +/* +* Containing namespace (active or deactivating, non-refcounted). +* Normally protected by namespace_sem. +* Can also be accessed locklessly under RCU. RCU readers can't rely on +* the namespace still being active, but implicitly hold a passive +* reference (because an RCU delay happens between a namespace being +* deactivated and the corresponding passive refcount drop). +*/ +struct mnt_namespace *mnt_ns;struct mountpoint *mnt_mp;/* where is it mounted */ union {struct hlist_node mnt_mp_list;/* list mounts with the same mountpoint */
fs/namespace.c +3 -3
@@ -1079,7 +1079,7 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)bool mnt_first_node = true, mnt_last_node = true;WARN_ON (mnt_ns_attached (mnt)); - mnt->mnt_ns = ns; +WRITE_ONCE (mnt->mnt_ns, ns);while (*link) { parent = *link;if (mnt->mnt_id_unique <node_to_mount (parent)->mnt_id_unique) {
@@ -1434,7 +1434,7 @@ EXPORT_SYMBOL(mntget);void mnt_make_shortterm (struct vfsmount *mnt) {if (mnt) -real_mount (mnt)->mnt_ns =NULL ; +WRITE_ONCE (real_mount (mnt)->mnt_ns,NULL ); }/**
@@ -1806,7 +1806,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) ns->nr_mounts--;__touch_mnt_namespace (ns); } - p->mnt_ns =NULL ; +WRITE_ONCE (p->mnt_ns,NULL );if (how &UMOUNT_SYNC ) p->mnt.mnt_flags |=MNT_SYNC_UMOUNT ;
Sasha Levin
maintainerPATCH 1/1 fhandle: fix UAF due to unlocked ->mnt_ns read in may_decode_fh()
From: Jann Horn <[email protected]>
[ Upstream commit 40ab6644b99685755f740b872c00ef40d9aa870e ]
may_decode_fh() accesses mount::mnt_ns without holding any locks; that means the mount can concurrently be unmounted, and the mnt_namespace can concurrently be freed after an RCU grace period.
This race can happens as follows, assuming that the mount point was created by open_tree(..., OPEN_TREE_CLONE):
thread 1 thread 2 RCU
__do_sys_open_by_handle_at
do_handle_open
handle_to_path
may_decode_fh
is_mounted
[mount::mnt_ns access]
[mount::mnt_ns access]
__do_sys_close
fput_close_sync
__fput
dissolve_on_fput
umount_tree
class_namespace_excl_destructor
namespace_unlock
free_mnt_ns
mnt_ns_tree_remove
call_rcu(mnt_ns_release_rcu)
mnt_ns_release_rcu
mnt_ns_release
kfree
[mnt_namespace::user_ns access] **UAF**Fix it by taking rcu_read_lock() around the mount::mnt_ns access, like in __prepend_path().
Additionally, document the semantics of mount::mnt_ns, and use WRITE_ONCE() for writers that can race with lockless readers.
This bug is unreachable unless one of the following is set:
- CONFIG_PREEMPTION
- CONFIG_RCU_STRICT_GRACE_PERIOD
because it requires an RCU grace period to happen during a syscall without an explicit preemption.
This doesn't seem to have interesting security impact; worst-case, it could leak the result of an integer comparison to userspace (from the level check in cap_capable()), cause an endless loop, or crash the kernel by dereferencing an invalid address.
--- fs/fhandle.c | 16 ++++++++++++++-- fs/mount.h | 10 +++++++++- fs/namespace.c | 6 +++--- 3 files changed, 26 insertions(+), 6 deletions(-)
fs/fhandle.c +14 -2
@@ -242,6 +242,19 @@ static int do_handle_to_path(struct file_handle *handle, struct path *path,return 0 ; } +static bool capable_wrt_mount (struct mount *mount) +{ +struct mnt_namespace *mnt_ns; + +/* +* For ->mnt_ns access. +* The following READ_ONCE() is semantically rcu_dereference(). +*/ +guard (rcu)(); + mnt_ns =READ_ONCE (mount->mnt_ns); +return ns_capable (mnt_ns->user_ns,CAP_SYS_ADMIN ); +} +/* * Allow relaxed permissions of file handles if the caller has the * ability to mount the filesystem or create a bind-mount of the
@@ -273,8 +286,7 @@ static inline bool may_decode_fh(struct handle_to_path_ctx *ctx,if (ns_capable (root->mnt->mnt_sb->s_user_ns,CAP_SYS_ADMIN )) ctx->flags =HANDLE_CHECK_PERMS ;else if (is_mounted (root->mnt) && -ns_capable (real_mount (root->mnt)->mnt_ns->user_ns, -CAP_SYS_ADMIN ) && +capable_wrt_mount (real_mount (root->mnt)) && !has_locked_children (real_mount (root->mnt), root->dentry)) ctx->flags =HANDLE_CHECK_PERMS |HANDLE_CHECK_SUBTREE ;else
fs/mount.h +9 -1
@@ -58,7 +58,15 @@ struct mount {struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave;/* slave list entry */ struct mount *mnt_master;/* slave is on master->mnt_slave_list */ -struct mnt_namespace *mnt_ns;/* containing namespace */ +/* +* Containing namespace (active or deactivating, non-refcounted). +* Normally protected by namespace_sem. +* Can also be accessed locklessly under RCU. RCU readers can't rely on +* the namespace still being active, but implicitly hold a passive +* reference (because an RCU delay happens between a namespace being +* deactivated and the corresponding passive refcount drop). +*/ +struct mnt_namespace *mnt_ns;struct mountpoint *mnt_mp;/* where is it mounted */ union {struct hlist_node mnt_mp_list;/* list mounts with the same mountpoint */
fs/namespace.c +3 -3
@@ -1132,7 +1132,7 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)struct rb_node *parent =NULL ;WARN_ON (mnt_ns_attached (mnt)); - mnt->mnt_ns = ns; +WRITE_ONCE (mnt->mnt_ns, ns);while (*link) { parent = *link;if (mnt->mnt_id_unique <node_to_mount (parent)->mnt_id_unique)
@@ -1493,7 +1493,7 @@ EXPORT_SYMBOL(mntget);void mnt_make_shortterm (struct vfsmount *mnt) {if (mnt) -real_mount (mnt)->mnt_ns =NULL ; +WRITE_ONCE (real_mount (mnt)->mnt_ns,NULL ); }/**
@@ -1805,7 +1805,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) ns->nr_mounts--;__touch_mnt_namespace (ns); } - p->mnt_ns =NULL ; +WRITE_ONCE (p->mnt_ns,NULL );if (how &UMOUNT_SYNC ) p->mnt.mnt_flags |=MNT_SYNC_UMOUNT ;
Signature · 1 line
2.53.0