From mboxrd@z Thu Jan  1 00:00:00 1970
From: Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
Subject: Re: [PATCH 1/2] perf: Add sampling of the raw monotonic clock
Date: Mon, 29 Sep 2014 17:28:32 +0200
Message-ID: <20140929152832.GL4140@worktop.programming.kicks-ass.net>
References: <1411050873-9310-1-git-send-email-pawel.moll@arm.com>
 <1411050873-9310-2-git-send-email-pawel.moll@arm.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Return-path: <linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Content-Disposition: inline
In-Reply-To: <1411050873-9310-2-git-send-email-pawel.moll-5wv7dgnIgG8@public.gmane.org>
Sender: linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
To: Pawel Moll <pawel.moll-5wv7dgnIgG8@public.gmane.org>
Cc: Richard Cochran <richardcochran-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>, Steven Rostedt <rostedt-nx8X9YLhiw1AfugRpC6u6w@public.gmane.org>, Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, Paul Mackerras <paulus-eUNUBHrolfbYtjvyW6yDsg@public.gmane.org>, Arnaldo Carvalho de Melo <acme-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>, John Stultz <john.stultz-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>
List-Id: linux-api@vger.kernel.org

On Thu, Sep 18, 2014 at 03:34:32PM +0100, Pawel Moll wrote:
> @@ -4456,6 +4459,13 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
>  		data->cpu_entry.cpu	 = raw_smp_processor_id();
>  		data->cpu_entry.reserved = 0;
>  	}
> +
> +	if (sample_type & PERF_SAMPLE_CLOCK_RAW_MONOTONIC) {
> +		struct timespec now;
> +
> +		getrawmonotonic(&now);
> +		data->clock_raw_monotonic = timespec_to_ns(&now);
> +	}
>  }
>  

This cannot work, getrawmonotonic() isn't NMI-safe and there's
nothing stopping this being used from NMI context.

Also getrawmonotonic() + timespec_to_ns() will make tglx sad, he's just
done a tree-wide eradication of silly conversions and now you're adding
a ns -> timespec -> ns dance right back.

I _think_ you want ktime_get_mono_fast_ns(), but this does bring us
right back to the question/discussion on which timebase you'd want to
sync again. MONO does make sense for most cases, but I think we've had
fairly sane stories for people wanting to sync against other clocks.

A well..