Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Thomas Gleixner <tglx@linutronix.de>
To:     peterz@infradead.org, Joel Fernandes <joel@joelfernandes.org>
Cc:     linux-kernel@vger.kernel.org, mingo@kernel.org, will@kernel.org,
        npiggin@gmail.com, elver@google.com, jgross@suse.com,
        paulmck@kernel.org, rostedt@goodmis.org, rjw@rjwysocki.net,
        svens@linux.ibm.com
Subject: Re: [PATCH v2 03/11] sched,idle,rcu: Push rcu_idle deeper into the idle path
In-Reply-To: <20200827074748.GY2674@hirez.programming.kicks-ass.net>
References: <20200821084738.508092956@infradead.org> <20200821085348.310943801@infradead.org> <20200827011826.GA1942571@google.com> <20200827012419.GB1942571@google.com> <20200827074748.GY2674@hirez.programming.kicks-ass.net>
Date:   Thu, 27 Aug 2020 09:53:20 +0200
Message-ID: <875z94le33.fsf@nanos.tec.linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, Aug 27 2020 at 09:47, peterz wrote:
> On Wed, Aug 26, 2020 at 09:24:19PM -0400, Joel Fernandes wrote:
>> On Wed, Aug 26, 2020 at 09:18:26PM -0400, Joel Fernandes wrote:
>> > On Fri, Aug 21, 2020 at 10:47:41AM +0200, Peter Zijlstra wrote:
>> > > Lots of things take locks, due to a wee bug, rcu_lockdep didn't notice
>> > > that the locking tracepoints were using RCU.
>> > > 
>> > > Push rcu_idle_{enter,exit}() as deep as possible into the idle paths,
>> > > this also resolves a lot of _rcuidle()/RCU_NONIDLE() usage.
>> > > 
>> > > Specifically, sched_clock_idle_wakeup_event() will use ktime which
>> > > will use seqlocks which will tickle lockdep, and
>> > > stop_critical_timings() uses lock.
>> > 
>> > I was wondering if those tracepoints should just use _rcuidle variant of the
>> > trace call. But that's a terrible idea considering that would add unwanted
>> > overhead I think.
>> > 
>> > Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
>> 
>> BTW, if tracepoint is converted to use RCU-trace flavor, then these kinds of
>> issues go away, no? That RCU flavor is always watching.
>
> All trace_*_rcuidle() and RCU_NONIDLE() usage is a bug IMO.

It's the same problem as low level entry/exit. And that stuff is a hack
which papers over the problem instead of fixing it from ground up. But
we are talking about tracing, right?

Thanks,

        tglx