[PATCH 1/1 v2] userfaultfd: use RCU to free the task struct when fork fails

[Andrea Arcangeli <aarcange@redhat.com>]

The task structure is freed while get_mem_cgroup_from_mm() holds
rcu_read_lock() and dereferences mm->owner.

get_mem_cgroup_from_mm()                failing fork()
----                                    ---
task = mm->owner
                                        mm->owner = NULL;
                                        free(task)
if (task) *task; /* use after free */

The fix consists in freeing the task with RCU also in the fork failure
case, exactly like it always happens for the regular exit(2)
path. That is enough to make the rcu_read_lock hold in
get_mem_cgroup_from_mm() (left side above) effective to avoid a use
after free when dereferencing the task structure.

An alternate possible fix would be to defer the delivery of the
userfaultfd contexts to the monitor until after fork() is guaranteed
to succeed. Such a change would require more changes because it would
create a strict ordering dependency where the uffd methods would need
to be called beyond the last potentially failing branch in order to be
safe. This solution as opposed only adds the dependency to common code
to set mm->owner to NULL and to free the task struct that was pointed
by mm->owner with RCU, if fork ends up failing. The userfaultfd
methods can still be called anywhere during the fork runtime and the
monitor will keep discarding orphaned "mm" coming from failed forks in
userland.

This race condition couldn't trigger if CONFIG_MEMCG was set =n at
build time.

v2: improved commit header and reduced #ifdef material suggested by
Michal Hocko.

Fixes: 893e26e61d04 ("userfaultfd: non-cooperative: Add fork() event")
Cc: stable@kernel.org
Tested-by: zhong jiang <zhongjiang@huawei.com>
Reported-by: syzbot+cbb52e396df3e565ab02@syzkaller.appspotmail.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
---
 kernel/fork.c | 31 +++++++++++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 9dcd18aa210b..2628f3773ca8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -952,6 +952,15 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
+static __always_inline void mm_clear_owner(struct mm_struct *mm,
+					   struct task_struct *p)
+{
+#ifdef CONFIG_MEMCG
+	if (mm->owner == p)
+		WRITE_ONCE(mm->owner, NULL);
+#endif
+}
+
 static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 {
 #ifdef CONFIG_MEMCG
@@ -1331,6 +1340,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
 free_pt:
 	/* don't put binfmt in mmput, we haven't got module yet */
 	mm->binfmt = NULL;
+	mm_init_owner(mm, NULL);
 	mmput(mm);
 
 fail_nomem:
@@ -1662,6 +1672,21 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
+static void __delayed_free_task(struct rcu_head *rhp)
+{
+	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+	free_task(tsk);
+}
+
+static __always_inline void delayed_free_task(struct task_struct *tsk)
+{
+	if (IS_ENABLED(CONFIG_MEMCG))
+		call_rcu(&tsk->rcu, __delayed_free_task);
+	else
+		free_task(tsk);
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -2123,8 +2148,10 @@ static __latent_entropy struct task_struct *copy_process(
 bad_fork_cleanup_namespaces:
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm:
-	if (p->mm)
+	if (p->mm) {
+		mm_clear_owner(p->mm, p);
 		mmput(p->mm);
+	}
 bad_fork_cleanup_signal:
 	if (!(clone_flags & CLONE_THREAD))
 		free_signal_struct(p->signal);
@@ -2155,7 +2182,7 @@ static __latent_entropy struct task_struct *copy_process(
 bad_fork_free:
 	p->state = TASK_DEAD;
 	put_task_stack(p);
-	free_task(p);
+	delayed_free_task(p);
 fork_out:
 	spin_lock_irq(&current->sighand->siglock);
 	hlist_del_init(&delayed.node);