All of lore.kernel.org
 help / color / mirror / Atom feed
From: Joerg Roedel <joerg.roedel@amd.com>
To: Avi Kivity <avi@redhat.com>
Cc: <linux-kernel@vger.kernel.org>, <kvm@vger.kernel.org>,
	<joro@8bytes.org>, Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Ingo Molnar <mingo@elte.hu>,
	Stephane Eranian <eranian@google.com>,
	David Ahern <dsahern@gmail.com>, Gleb Natapov <gleb@redhat.com>,
	Robert Richter <robert.richter@amd.com>
Subject: Re: [PATCH v2] perf/x86: Fix HO/GO counting with SVM disabled
Date: Wed, 29 Feb 2012 18:05:36 +0100	[thread overview]
Message-ID: <20120229170536.GE10684@amd.com> (raw)
In-Reply-To: <4F4E5999.6080600@redhat.com>

On Wed, Feb 29, 2012 at 07:00:09PM +0200, Avi Kivity wrote:
> On 02/29/2012 03:57 PM, Joerg Roedel wrote:
> > It turned out that a performance counter on AMD does not
> > count at all when the GO or HO bit is set in the control
> > register and SVM is disabled in EFER.
> >
> > This patch works around this issue by masking out the HO bit
> > in the performance counter control register when SVM is not
> > enabled.
> >
> > The GO bit is not touched because it is only set when the
> > user wants to count in guest-mode only. So when SVM is
> > disabled the counter should not run at all and the
> > not-counting is the intended behaviour.
> >
> > diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
> > index 0397b23..67250a5 100644
> > --- a/arch/x86/kernel/cpu/perf_event_amd.c
> > +++ b/arch/x86/kernel/cpu/perf_event_amd.c
> > @@ -1,4 +1,5 @@
> >  #include <linux/perf_event.h>
> > +#include <linux/export.h>
> >  #include <linux/types.h>
> >  #include <linux/init.h>
> >  #include <linux/slab.h>
> > @@ -357,7 +358,9 @@ static void amd_pmu_cpu_starting(int cpu)
> >  	struct amd_nb *nb;
> >  	int i, nb_id;
> >  
> > -	if (boot_cpu_data.x86_max_cores < 2)
> > +	cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
> > +
> > +	if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15)
> >  		return;
> 
> Why this (boot_cpu_data.x86 == 0x15) change?

This is because this function did not run on Fam15h before but now it
has to so that cpuc->perf_ctr_virt_mask is initialized. The other stuff
done in this function is setup for northbridge counter. These are not
yet implemented for Fam15h CPUs so this setup must not run on those
CPUs. Therefore the check was added.
Once northbridge counters are implemented for Fam15h this check can go
away again.


	Joerg


-- 
AMD Operating System Research Center

Advanced Micro Devices GmbH Einsteinring 24 85609 Dornach
General Managers: Alberto Bozzo
Registration: Dornach, Landkr. Muenchen; Registerger. Muenchen, HRB Nr. 43632

  parent reply	other threads:[~2012-02-29 17:05 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-02-27 17:33 [PATCH] perf tools: fix guest mode monitoring on AMD Stephane Eranian
2012-02-27 17:39 ` Gleb Natapov
2012-02-27 17:47 ` David Ahern
2012-02-27 17:52   ` Stephane Eranian
2012-02-27 18:00     ` David Ahern
2012-02-27 18:23     ` Joerg Roedel
2012-02-28 15:55       ` [PATCH] perf/x86: Fix HO/GO counting with SVM disabled Joerg Roedel
2012-02-28 17:24         ` Avi Kivity
2012-02-28 17:36           ` David Ahern
2012-02-28 17:38             ` Avi Kivity
2012-02-29 13:24               ` Joerg Roedel
2012-02-29 13:57         ` [PATCH v2] " Joerg Roedel
2012-02-29 17:00           ` Avi Kivity
2012-02-29 17:03             ` Gleb Natapov
2012-02-29 17:05             ` Joerg Roedel [this message]
2012-02-29 17:08               ` Avi Kivity
2012-02-29 17:24               ` Peter Zijlstra
2012-02-29 17:44           ` Peter Zijlstra
2012-03-02 14:54           ` [tip:perf/urgent] perf/x86/kvm: Fix Host-Only/ Guest-Only " tip-bot for Joerg Roedel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20120229170536.GE10684@amd.com \
    --to=joerg.roedel@amd.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=avi@redhat.com \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=gleb@redhat.com \
    --cc=joro@8bytes.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=robert.richter@amd.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.