Re: [PATCH] signal: Prevent exec() race

["Eric W. Biederman" <ebiederm@xmission.com>]

Thomas Gleixner <tglx@kernel.org> writes:

> On Mon, Aug 31 2026 at 10:26, Eric W. Biederman wrote:
>>
>> This changes partially fixes another bug.  Recursive
>> UCOUNT_RLIMIT_SIGPENDING should be decremented when the process exits
>> and not when the process is reaped.
>>
>> Others have noticed possible races flushing the siqueue not
>> holding siglock.
>
> Yes. I doesn't work.
>
>> If I read the history correctly in flush_sigqueue with irqs
>> disabled can trigger the NMI lock-up detector.  So flush_sigqueue
>> was moved outside of siglock_irq.
>>
>> Apparently it took KASAN to make kmem_cache_free slow enough
>> to trigger the lock-up detector.
>>
>> The fix to avoid the lock-up detector was not comprehensive and
>> flush_sigqueue is still called in many places with irqs disabled.
>> So if necessary the code can probably just take siglock.
>
> Right, invoke flush_sigqueue() right after setting PF_EXITING.
>
> But we can be smarter than that. See below.
>
>> We can also avoid problems by updating the loops that go:
>> for_each_thread(p, q)
>> 	flush_sigqueue_mask(p, &flush, &t->pending)
>>
>> To include
>> 	if (t->flags & PF_EXITING)
>>         	continue;
>>
>> Or perhaps better tweak flush_sigqueue_mask to take t (and not p) and
>> perform the test of PF_EXITING there.  The only current uses I see of
>> the passed in task is to get a reference to signal_struct.
>
> Correct. Though that check would have to be limited to flushing
> tsk::pending not signal::shared_pending.

Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>

I was just about to suggest removing the entire list under the lock,
and then cleaning up the list entries outside of the lock, then I saw
this email :)

I am not wild about the name sigqueue_splice_pending (what is being
spliced together).

Perhaps call it sigqueue_dequeue_pending?  I think that conveys what
is happening a little better.

Eric



>
> Thanks,
>
>         tglx
> ---
> --- a/kernel/signal.c
> +++ b/kernel/signal.c
> @@ -457,30 +457,44 @@ static void __sigqueue_free(struct sigqu
>  	kmem_cache_free(sigqueue_cachep, q);
>  }
>  
> -void flush_sigqueue(struct sigpending *queue)
> +static void flush_sigqueue_list(struct list_head *head)
>  {
> -	struct sigqueue *q;
> +	struct sigqueue *q, *tmp;
>  
> -	sigemptyset(&queue->signal);
> -	while (!list_empty(&queue->list)) {
> -		q = list_entry(queue->list.next, struct sigqueue , list);
> +	list_for_each_entry_safe(q, tmp, head, list) {
>  		list_del_init(&q->list);
>  		__sigqueue_free(q);
>  	}
>  }
>  
> +void flush_sigqueue(struct sigpending *queue)
> +{
> +	sigemptyset(&queue->signal);
> +	flush_sigqueue_list(&queue->list);
> +}
> +
> +static void sigqueue_splice_pending(struct sigpending *queue, struct list_head *head)
> +{
> +	sigemptyset(&queue->signal);
> +	list_splice_init(&queue->list, head);
> +}
> +
>  /*
>   * Flush all pending signals for this kthread.
>   */
>  void flush_signals(struct task_struct *t)
>  {
> -	unsigned long flags;
> +	LIST_HEAD(pending);
> +	LIST_HEAD(shared);
>  
> -	spin_lock_irqsave(&t->sighand->siglock, flags);
> -	clear_tsk_thread_flag(t, TIF_SIGPENDING);
> -	flush_sigqueue(&t->pending);
> -	flush_sigqueue(&t->signal->shared_pending);
> -	spin_unlock_irqrestore(&t->sighand->siglock, flags);
> +	scoped_guard(spinlock_irqsave, &t->sighand->siglock) {
> +		clear_tsk_thread_flag(t, TIF_SIGPENDING);
> +		sigqueue_splice_pending(&t->pending, &pending);
> +		sigqueue_splice_pending(&t->signal->shared_pending, &shared);
> +	}
> +
> +	flush_sigqueue_list(&pending);
> +	flush_sigqueue_list(&shared);
>  }
>  EXPORT_SYMBOL(flush_signals);
>  
> @@ -3125,18 +3139,9 @@ static void retarget_shared_pending(stru
>  	}
>  }
>  
> -/*
> - * tsk::flags has PF_EXITING set which prevents signals to be queued on
> - * tsk::pending. Nothing else can touch tsk::pending anymore so it can be
> - * flushed lockless.
> - */
> -static inline void flush_pending_unlocked(struct task_struct *tsk)
> -{
> -	flush_sigqueue(&tsk->pending);
> -}
> -
>  void exit_signals(struct task_struct *tsk)
>  {
> +	LIST_HEAD(sigq_list);
>  	int group_stop = 0;
>  	sigset_t unblocked;
>  
> @@ -3147,10 +3152,12 @@ void exit_signals(struct task_struct *ts
>  	cgroup_threadgroup_change_begin(tsk);
>  
>  	if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) {
> -		scoped_guard(spinlock_irq, &tsk->sighand->siglock)
> +		scoped_guard(spinlock_irq, &tsk->sighand->siglock) {
>  			tsk->flags |= PF_EXITING;
> +			sigqueue_splice_pending(&tsk->pending, &sigq_list);
> +		}
>  		cgroup_threadgroup_change_end(tsk);
> -		flush_pending_unlocked(tsk);
> +		flush_sigqueue_list(&sigq_list);
>  		return;
>  	}
>  
> @@ -3160,6 +3167,7 @@ void exit_signals(struct task_struct *ts
>  	 * see wants_signal(), do_signal_stop().
>  	 */
>  	tsk->flags |= PF_EXITING;
> +	sigqueue_splice_pending(&tsk->pending, &sigq_list);
>  
>  	cgroup_threadgroup_change_end(tsk);
>  
> @@ -3176,7 +3184,7 @@ void exit_signals(struct task_struct *ts
>  out:
>  	spin_unlock_irq(&tsk->sighand->siglock);
>  
> -	flush_pending_unlocked(tsk);
> +	flush_sigqueue_list(&sigq_list);
>  
>  	/*
>  	 * If group stop has completed, deliver the notification.  This