From: Peter Zijlstra <peterz@infradead.org>
To: Kan Liang <kan.liang@intel.com>
Cc: linux-kernel@vger.kernel.org, mingo@kernel.org,
acme@infradead.org, eranian@google.com, andi@firstfloor.org
Subject: Re: [PATCH V5 1/6] perf, x86: use the PEBS auto reload mechanism when possible
Date: Mon, 30 Mar 2015 14:06:07 +0200 [thread overview]
Message-ID: <20150330120607.GU23123@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <1424701556-28270-2-git-send-email-kan.liang@intel.com>
On Mon, Feb 23, 2015 at 09:25:51AM -0500, Kan Liang wrote:
> +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> @@ -673,6 +673,8 @@ void intel_pmu_pebs_enable(struct perf_event *event)
> struct hw_perf_event *hwc = &event->hw;
>
> hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
> + if (!event->attr.freq)
> + hwc->flags |= PERF_X86_EVENT_AUTO_RELOAD;
>
> cpuc->pebs_enabled |= 1ULL << hwc->idx;
Why not in x86_pmu_event_init()? This is not something that will change,
ever, right?
> @@ -680,6 +682,12 @@ void intel_pmu_pebs_enable(struct perf_event *event)
> cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
> else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
> cpuc->pebs_enabled |= 1ULL << 63;
> +
> + /* Use auto-reload if possible to save a MSR write in the PMI */
> + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
> + ds->pebs_event_reset[hwc->idx] =
> + (u64)-hwc->sample_period & x86_pmu.cntval_mask;
> + }
> }
>
> void intel_pmu_pebs_disable(struct perf_event *event)
> @@ -698,6 +706,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
> wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
>
> hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
> + hwc->flags &= ~PERF_X86_EVENT_AUTO_RELOAD;
Equally, we should not ever have to clear this. You cannot change
attributes after the event is created, if that flag ever gets set, it
stays valid.
next prev parent reply other threads:[~2015-03-30 12:06 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-02-23 14:25 [PATCH V5 0/6] large PEBS interrupt threshold Kan Liang
2015-02-23 14:25 ` [PATCH V5 1/6] perf, x86: use the PEBS auto reload mechanism when possible Kan Liang
2015-03-30 12:06 ` Peter Zijlstra [this message]
2015-03-30 14:02 ` Peter Zijlstra
2015-02-23 14:25 ` [PATCH V5 2/6] perf, x86: introduce setup_pebs_sample_data() Kan Liang
2015-02-23 14:25 ` [PATCH V5 3/6] perf, x86: large PEBS interrupt threshold Kan Liang
2015-03-02 17:08 ` Stephane Eranian
2015-03-02 17:59 ` Andi Kleen
2015-03-02 18:07 ` Stephane Eranian
2015-03-30 13:54 ` Peter Zijlstra
2015-02-23 14:25 ` [PATCH V5 4/6] perf, x86: handle multiple records in PEBS buffer Kan Liang
2015-03-30 13:45 ` Peter Zijlstra
2015-03-30 17:19 ` Liang, Kan
2015-03-30 17:25 ` Andi Kleen
2015-03-30 17:43 ` Liang, Kan
2015-03-30 17:45 ` Andi Kleen
2015-03-30 20:07 ` Peter Zijlstra
2015-03-30 20:11 ` Andi Kleen
2015-03-30 21:24 ` Peter Zijlstra
2015-03-30 21:53 ` Andi Kleen
2015-02-23 14:25 ` [PATCH V5 5/6] perf, x86: drain PEBS buffer during context switch Kan Liang
2015-03-30 13:50 ` Peter Zijlstra
2015-02-23 14:25 ` [PATCH V5 6/6] perf, x86: enlarge PEBS buffer Kan Liang
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=20150330120607.GU23123@twins.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=acme@infradead.org \
--cc=andi@firstfloor.org \
--cc=eranian@google.com \
--cc=kan.liang@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
/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