Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon, 10 Feb 2020 21:32:23 -0500
User-Agent: K-9 Mail for Android
In-Reply-To: <20200210212222.59a8c519@rorschach.local.home>
References: <20200210170643.3544795d@gandalf.local.home> <576504045.617212.1581381032132.JavaMail.zimbra@efficios.com> <20200210212222.59a8c519@rorschach.local.home>
MIME-Version: 1.0
Content-Type: text/plain;
 charset=utf-8
Content-Transfer-Encoding: quoted-printable
Subject: Re: [PATCH] tracing/perf: Move rcu_irq_enter/exit_irqson() to perf trace point hook
To:     Steven Rostedt <rostedt@goodmis.org>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC:     linux-kernel <linux-kernel@vger.kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@kernel.org>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        "Gustavo A. R. Silva" <gustavo@embeddedor.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        paulmck <paulmck@kernel.org>,
        Josh Triplett <josh@joshtriplett.org>,
        Lai Jiangshan <jiangshanlai@gmail.com>
From:   joel@joelfernandes.org
Message-ID: <522406EB-8788-47F1-B616-0A6338A03304@joelfernandes.org>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


On February 10, 2020 9:22:22 PM EST, Steven Rostedt <rostedt@goodmis=2Eorg=
> wrote:
>
>> Which brings a question about handling of NMIs: in the proposed
>patch, if
>> a NMI nests over rcuidle context, AFAIU it will be in a state
>> !rcu_is_watching() && in_nmi(), which is handled by this patch with a
>simple
>> "return", meaning important NMIs doing hardware event sampling can be
>> completely lost=2E
>>=20
>> Considering that we cannot use rcu_irq_enter/exit_irqson() from NMI
>context,
>> is it at all valid to use rcu_read_lock/unlock() as perf does from
>NMI handlers,
>> considering that those can be nested on top of rcuidle context ?
>>=20
>
>Note, in the __DO_TRACE macro, we've had this for a long time:
>
>		/* srcu can't be used from NMI */			\
>		WARN_ON_ONCE(rcuidle && in_nmi());			\
>
>With nothing triggering=2E

I did not understand Mathieu's question, afaik perf event sampling code in=
 NMI handler does not invoke trace_=2E=2E=2E_rcuidle functions anywhere=2E =
That afair is independently dealt within perf and does not involve tracepoi=
nt code=2E And if NMI has interrupted any code currently running in __DO_TR=
ACE, that's ok because NMI is higher priority and will run to completion be=
fore resuming the interrupted code=2E Did I miss something? I am not surpri=
sed the warning doesn't ever trigger=2E

Thanks,
Joel=2E


>
>-- Steve

--=20
Sent from my Android device with K-9 Mail=2E Please excuse my brevity=2E