Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Thu, 6 Oct 2022 18:02:56 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Marco Elver <elver@google.com>
Cc:     Ingo Molnar <mingo@redhat.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Mark Rutland <mark.rutland@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Jiri Olsa <jolsa@kernel.org>,
        Namhyung Kim <namhyung@kernel.org>,
        linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
        kasan-dev@googlegroups.com, Dmitry Vyukov <dvyukov@google.com>
Subject: Re: [PATCH] perf: Fix missing SIGTRAPs
Message-ID: <Yz78MMMJ74tBw0gu@hirez.programming.kicks-ass.net>
References: <20220927121322.1236730-1-elver@google.com>
 <Yz7ZLaT4jW3Y9EYS@hirez.programming.kicks-ass.net>
 <Yz7fWw8duIOezSW1@elver.google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <Yz7fWw8duIOezSW1@elver.google.com>
Precedence: bulk

On Thu, Oct 06, 2022 at 03:59:55PM +0200, Marco Elver wrote:

> That one I could fix up with:
> 
>  | diff --git a/kernel/events/core.c b/kernel/events/core.c
>  | index 9319af6013f1..2f1d51b50be7 100644
>  | --- a/kernel/events/core.c
>  | +++ b/kernel/events/core.c
>  | @@ -6563,6 +6563,7 @@ static void perf_pending_task(struct callback_head *head)
>  |  	 * If we 'fail' here, that's OK, it means recursion is already disabled
>  |  	 * and we won't recurse 'further'.
>  |  	 */
>  | +	preempt_disable_notrace();
>  |  	rctx = perf_swevent_get_recursion_context();
>  |  
>  |  	if (event->pending_work) {
>  | @@ -6573,6 +6574,7 @@ static void perf_pending_task(struct callback_head *head)
>  |  
>  |  	if (rctx >= 0)
>  |  		perf_swevent_put_recursion_context(rctx);
>  | +	preempt_enable_notrace();
>  |  }
>  |  
>  |  #ifdef CONFIG_GUEST_PERF_EVENTS

Right, thanks! It appears I only have lockdep enabled but not the
preempt warning :/

> But following that, I get:
> 

>  | WARNING: CPU: 3 PID: 13018 at kernel/events/core.c:2288 event_sched_out+0x3f2/0x410 kernel/events/core.c:2288

I'm taking this is (my line numbers are slightly different):

	WARN_ON_ONCE(event->pending_work);


> So something isn't quite right yet. Unfortunately I don't have a good
> reproducer. :-/

This can happen if we get two consecutive event_sched_out() and both
instances will have pending_sigtrap set. This can happen when the event
that has sigtrap set also triggers in kernel space.

You then get task_work list corruption and *boom*.

I'm thinking the below might be the simplest solution; we can only send
a single signal after all.


--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2293,9 +2293,10 @@ event_sched_out(struct perf_event *event
 			 */
 			local_dec(&event->ctx->nr_pending);
 		} else {
-			WARN_ON_ONCE(event->pending_work);
-			event->pending_work = 1;
-			task_work_add(current, &event->pending_task, TWA_RESUME);
+			if (!event->pending_work) {
+				event->pending_work = 1;
+				task_work_add(current, &event->pending_task, TWA_RESUME);
+			}
 		}
 	}