From: "Liang, Kan" <kan.liang@linux.intel.com>
To: peterz@infradead.org
Cc: acme@redhat.com, mingo@kernel.org, linux-kernel@vger.kernel.org,
jolsa@kernel.org, eranian@google.com,
alexander.shishkin@linux.intel.com, ak@linux.intel.com,
like.xu@linux.intel.com
Subject: Re: [PATCH V7 08/14] perf/x86/intel: Generic support for hardware TopDown metrics
Date: Tue, 28 Jul 2020 10:01:25 -0400 [thread overview]
Message-ID: <4313ed1f-03b2-48e7-36fe-6a112fa6c70f@linux.intel.com> (raw)
In-Reply-To: <20200728134412.GX119549@hirez.programming.kicks-ass.net>
On 7/28/2020 9:44 AM, peterz@infradead.org wrote:
> On Tue, Jul 28, 2020 at 09:28:39AM -0400, Liang, Kan wrote:
>>
>>
>> On 7/28/2020 9:09 AM, Peter Zijlstra wrote:
>>> On Fri, Jul 24, 2020 at 03:10:52PM -0400, Liang, Kan wrote:
>>>
>>>> diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
>>>> index 6cb079e0c9d9..010ac74afc09 100644
>>>> --- a/arch/x86/events/intel/core.c
>>>> +++ b/arch/x86/events/intel/core.c
>>>> @@ -2405,27 +2405,18 @@ static u64 icl_update_topdown_event(struct
>>>> perf_event *event)
>>>> return slots;
>>>> }
>>>>
>>>> -static void intel_pmu_read_topdown_event(struct perf_event *event)
>>>> +static void intel_pmu_read_event(struct perf_event *event)
>>>> {
>>>> - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
>>>> -
>>>> - /* Only need to call update_topdown_event() once for group read. */
>>>> - if ((cpuc->txn_flags & PERF_PMU_TXN_READ) &&
>>>> - !is_slots_event(event))
>>>> return;
>>>>
>>>> - perf_pmu_disable(event->pmu);
>>>> - x86_pmu.update_topdown_event(event);
>>>> - perf_pmu_enable(event->pmu);
>>>> -}
>>>> -
>>>> -static void intel_pmu_read_event(struct perf_event *event)
>>>> -{
>>>> if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
>>>> intel_pmu_auto_reload_read(event);
>>>> - else if (is_topdown_count(event) && x86_pmu.update_topdown_event)
>>>> - intel_pmu_read_topdown_event(event);
>>>> - else
>>>> + else if (is_slots_count(event) && x86_pmu.update_topdown_event) {
>>>> + perf_pmu_disable(event->pmu);
>>>> + x86_pmu.update_topdown_event(event);
>>>> + perf_pmu_enable(event->pmu);
>>>> + } else
>>>> x86_perf_event_update(event);
>>>> }
>>>
>>> I'm a little puzzled by this; what happens if you:
>>>
>>> fd = sys_perf_event_open(&attr_slots);
>>> fd1 = sys_perf_event_open(&attr_metric, .group_fd=fd);
>>>
>>> read(fd1);
>>>
>>> ?
>>>
>>
>> I did a quick test. It depends on the .read_format of attr_metric.
>> If PERF_FORMAT_GROUP is applied for attr_metric, perf_read_group() will be
>> invoked. The value of fd1 is updated correctly.
>> If the flag is not applied, 0 will be returned.
>
> Exactly :-), was that intentional?
Kind of, because a metric event must be in a group with the leader slots
event. If a user reads (treats) the metric event as a singleton event,
an invalid value should be expected.
> Because prior to this change that
> would've worked just fine.
>
> Now, I agree it's a daft thing, because that value is pretty useless
> without also having the slots value, but I feel we should be explicit in
> our choices here.
>
> If for example, we would've had hardware provide us the raw metric
> counters, instead of us having to reconstruct them, this would've been a
> semi useful thing.
>
> So I'm tempted to leave things as it, and keep this 'working'.
I will update the perf tool document to force the PERF_FORMAT_GROUP flag
for each metric events.
Thanks,
Kan
next prev parent reply other threads:[~2020-07-28 14:01 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-23 17:11 [PATCH V7 00/14] TopDown metrics support for Icelake kan.liang
2020-07-23 17:11 ` [PATCH V7 01/14] perf/x86: Use event_base_rdpmc for the RDPMC userspace support kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 02/14] perf/x86/intel: Name the global status bit in NMI handler kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 03/14] perf/x86/intel: Introduce the fourth fixed counter kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 04/14] perf/x86/intel: Move BTS index to 47 kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 05/14] perf/x86/intel: Fix the name of perf METRICS kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 06/14] perf/x86/intel: Use switch in intel_pmu_disable/enable_event kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 07/14] perf/core: Add a new PERF_EV_CAP_COEXIST event capability kan.liang
2020-07-24 10:55 ` peterz
2020-07-24 11:46 ` peterz
2020-07-24 13:43 ` Liang, Kan
2020-07-24 13:54 ` Peter Zijlstra
2020-07-24 14:19 ` Liang, Kan
2020-07-24 14:32 ` Peter Zijlstra
2020-07-24 14:46 ` Andi Kleen
2020-07-24 14:59 ` Peter Zijlstra
2020-07-24 16:43 ` peterz
2020-07-24 17:00 ` Liang, Kan
2020-07-24 14:39 ` Andi Kleen
2020-07-24 14:51 ` Peter Zijlstra
2020-08-19 8:52 ` [tip: perf/core] perf/core: Add a new PERF_EV_CAP_SIBLING " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 08/14] perf/x86/intel: Generic support for hardware TopDown metrics kan.liang
2020-07-24 13:19 ` peterz
2020-07-24 15:27 ` peterz
2020-07-24 16:07 ` Liang, Kan
2020-07-24 19:10 ` Liang, Kan
2020-07-28 12:32 ` Peter Zijlstra
2020-07-28 13:09 ` Peter Zijlstra
2020-07-28 13:28 ` Liang, Kan
2020-07-28 13:44 ` peterz
2020-07-28 14:01 ` Liang, Kan [this message]
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 09/14] perf/x86: Add a macro for RDPMC offset of fixed counters kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 10/14] perf/x86/intel: Support TopDown metrics on Ice Lake kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 11/14] perf/x86/intel: Support per-thread RDPMC TopDown metrics kan.liang
2020-08-19 8:52 ` [tip: perf/core] " tip-bot2 for Kan Liang
2020-07-23 17:11 ` [PATCH V7 12/14] perf, tools, stat: Support new per thread " kan.liang
2020-07-24 3:29 ` Andi Kleen
2020-07-23 17:11 ` [PATCH V7 13/14] perf, tools, stat: Check Topdown Metric group kan.liang
2020-07-23 17:11 ` [PATCH V7 14/14] perf, tools: Add documentation for topdown metrics 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=4313ed1f-03b2-48e7-36fe-6a112fa6c70f@linux.intel.com \
--to=kan.liang@linux.intel.com \
--cc=acme@redhat.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=eranian@google.com \
--cc=jolsa@kernel.org \
--cc=like.xu@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.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;
as well as URLs for NNTP newsgroup(s).