Received-SPF: pass (google.com: domain of linux-kernel+bounces-136968-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Tue, 9 Apr 2024 15:33:36 +0200
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: Frederic Weisbecker <frederic@kernel.org>
Cc: linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Ian Rogers <irogers@google.com>, Ingo Molnar <mingo@redhat.com>,
	Jiri Olsa <jolsa@kernel.org>, Marco Elver <elver@google.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Arnaldo Carvalho de Melo <acme@redhat.com>
Subject: Re: [PATCH v3 3/4] perf: Remove perf_swevent_get_recursion_context()
 from perf_pending_task().
Message-ID: <20240409133336.Y4Io-16-@linutronix.de>
References: <20240322065208.60456-1-bigeasy@linutronix.de>
 <20240322065208.60456-4-bigeasy@linutronix.de>
 <ZhRqSEbyd1rqVwfN@pavilion.home>
 <20240409062501.h4rA_ck4@linutronix.de>
 <ZhUaAjhQXN6ahtpS@localhost.localdomain>
 <20240409105405.TXUU--_W@linutronix.de>
 <ZhUt8XMndGSwNuwx@localhost.localdomain>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
In-Reply-To: <ZhUt8XMndGSwNuwx@localhost.localdomain>

On 2024-04-09 14:00:49 [+0200], Frederic Weisbecker wrote:
> Le Tue, Apr 09, 2024 at 12:54:05PM +0200, Sebastian Andrzej Siewior a =C3=
=A9crit :
> > On 2024-04-09 12:35:46 [+0200], Frederic Weisbecker wrote:
> > > > > > @@ -6800,10 +6792,6 @@ static void perf_pending_task(struct cal=
lback_head *head)
> > > > > >  		local_dec(&event->ctx->nr_pending);
> > > > > >  	}
> > > > > > =20
> > > > > > -	if (rctx >=3D 0)
> > > > > > -		perf_swevent_put_recursion_context(rctx);
> > > > > > -	preempt_enable_notrace();
> > > > >=20
> > > > > Well, if a software event happens during perf_sigtrap(), the task=
 work
> > > > > may be requeued endlessly and the task may get stuck in task_work=
_run()...
> > > >=20
> > > > The last time I checked it had no users in the task context. How wo=
uld
> > > > that happen?
> > >=20
> > > I guess many tracepoint events would do the trick. Such as trace_lock=
_acquire()
> > > for example.
> >=20
> > So the perf_trace_buf_alloc() is invoked from that trace point and
> > avoids the recursion. And any trace event from within perf_sigtrap()
> > would trigger the endless loop?
>=20
> No sure I'm following:
>=20
> 1) event->perf_event_overflow() -> task_work_add()
> //return to userspace
> 2) task_work_run() -> perf_pending_task() -> perf_sigtrap() -> tracepoint=
 event
>    -> perf_event_overflow() -> task_work_add()
> 3) task_work_run() -> perf_pending_task() -> etc...
>
> What am I missing?

Yes, that is what I tried to say. Anyway, I misunderstood the concept
before. That means we need to keep that counter here and a
migrate_disable() is needed to avoid CPU migration which is sad.

> Thanks.

Sebastian