Subject: Re: [PATCH 2/4] nmi_backtrace: generate one-line reports for idle
 cpus
To: Daniel Thompson <daniel.thompson@linaro.org>
References: <1456782024-7122-1-git-send-email-cmetcalf@ezchip.com>
 <1456782024-7122-3-git-send-email-cmetcalf@ezchip.com>
 <56D5A5E6.9050206@linaro.org> <56D5BCE6.3010300@mellanox.com>
 <56DD3B3D.1010404@linaro.org>
CC: Russell King <linux@arm.linux.org.uk>,
        Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
        Andrew Morton <akpm@osdl.org>, <linux-kernel@vger.kernel.org>,
        Aaron Tomlin <atomlin@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        "Rafael J. Wysocki" <rjw@rjwysocki.net>,
        Daniel Lezcano <daniel.lezcano@linaro.org>
From: Chris Metcalf <cmetcalf@mellanox.com>
Message-ID: <56DDB4BC.3040301@mellanox.com>
Date: Mon, 7 Mar 2016 12:05:00 -0500
User-Agent: Mozilla/5.0 (X11; Linux i686 on x86_64; rv:38.0) Gecko/20100101
 Thunderbird/38.6.0
MIME-Version: 1.0
In-Reply-To: <56DD3B3D.1010404@linaro.org>
Content-Type: text/plain; charset="windows-1252"; format=flowed
Content-Transfer-Encoding: 7bit
SpamDiagnosticOutput: 1:23
SpamDiagnosticMetadata: NSPM
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 07 Mar 2016 17:05:13.9147 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-Transport-CrossTenantHeadersStamped: AM4PR05MB1682
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
Content-Length: 722
Lines: 21

On 03/07/2016 03:26 AM, Daniel Thompson wrote:
>> Chris Metcalf wrote:
>> +static DEFINE_PER_CPU(bool, cpu_idling);
>> +
>> +/* Was the cpu was in the low-level idle code when interrupted? */
>> +bool in_cpu_idle(void)
>> +{
>> +    return this_cpu_read(cpu_idling);
>
> I think we continue to need the code to identify a core that is 
> running an interrupt handler. Interrupts are not masked at the point 
> we set cpu_idling to false meaning we can easily be preempted before 
> we clear the flag.

Yes, good catch.  However, mooted by PeterZ wanting to keep any extra 
state-switching code out of the idle path.  See my reply to him for more 
on that.

-- 
Chris Metcalf, Mellanox Technologies
http://www.mellanox.com