linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Robert Richter <robert.richter@amd.com>
Cc: Ingo Molnar <mingo@elte.hu>,
	Stephane Eranian <eranian@google.com>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 3/7] perf, x86: Implement IBS event configuration
Date: Wed, 14 Sep 2011 17:35:32 +0200	[thread overview]
Message-ID: <1316014532.5040.26.camel@twins> (raw)
In-Reply-To: <1315413376-769-4-git-send-email-robert.richter@amd.com>

On Wed, 2011-09-07 at 18:36 +0200, Robert Richter wrote:
> +static struct perf_ibs perf_ibs_fetch = {
> +       .pmu = {
> +               .event_init     = perf_ibs_init,
> +               .add            = perf_ibs_add,
> +               .del            = perf_ibs_del,
> +       },
> +       .msr                    = MSR_AMD64_IBSFETCHCTL,
> +       .config_mask            = IBS_FETCH_CONFIG_MASK,
> +       .cnt_mask               = IBS_FETCH_MAX_CNT,
> +       .enable_mask            = IBS_FETCH_ENABLE,
> +};
> +
> +static struct perf_ibs perf_ibs_op = {
> +       .pmu = {
> +               .event_init     = perf_ibs_init,
> +               .add            = perf_ibs_add,
> +               .del            = perf_ibs_del,
> +       },
> +       .msr                    = MSR_AMD64_IBSOPCTL,
> +       .config_mask            = IBS_OP_CONFIG_MASK,
> +       .cnt_mask               = IBS_OP_MAX_CNT,
> +       .enable_mask            = IBS_OP_ENABLE,
>  }; 

Both those .pmu things want:

  .task_ctx_nr = perf_invalid_context,

disabling per-task events, or you need to create a new context and
somehow fix per-task scheduling for these two things.

Adding two task contexts (one for each type) really isn't nice.

  reply	other threads:[~2011-09-14 15:35 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-09-07 16:36 [PATCH 0/7 -v2] perf, x86: Implement AMD IBS Robert Richter
2011-09-07 16:36 ` [PATCH 1/7] perf, x86: share IBS macros between perf and oprofile Robert Richter
2011-09-07 16:36 ` [PATCH 2/7] perf, x86: Implement IBS initialization Robert Richter
2011-09-07 16:36 ` [PATCH 3/7] perf, x86: Implement IBS event configuration Robert Richter
2011-09-14 15:35   ` Peter Zijlstra [this message]
2011-09-07 16:36 ` [PATCH 4/7] perf, x86: Implement IBS interrupt handler Robert Richter
2011-09-14 16:13   ` Peter Zijlstra
2011-09-21  8:39     ` Robert Richter
2011-09-07 16:36 ` [PATCH 5/7] perf, x86: Implement IBS pmu control ops Robert Richter
2011-09-07 16:36 ` [PATCH 6/7] perf, x86: Implement 64 bit counter support for IBS Robert Richter
2011-09-07 16:36 ` [PATCH 7/7] perf, x86: Example code for AMD IBS Robert Richter
  -- strict thread matches above, loose matches on Subject: below --
2011-07-28 13:46 [PATCH 0/7] perf, x86: Implement " Robert Richter
2011-07-28 13:46 ` [PATCH 3/7] perf, x86: Implement IBS event configuration Robert Richter
2011-08-02 11:35   ` Peter Zijlstra
2011-08-12 19:51     ` Robert Richter

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=1316014532.5040.26.camel@twins \
    --to=peterz@infradead.org \
    --cc=eranian@google.com \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).