From: peterz@infradead.org
To: kan.liang@linux.intel.com
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: Fri, 24 Jul 2020 17:27:55 +0200 [thread overview]
Message-ID: <20200724152755.GK43129@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20200724131906.GW119549@hirez.programming.kicks-ass.net>
On Fri, Jul 24, 2020 at 03:19:06PM +0200, peterz@infradead.org wrote:
> On Thu, Jul 23, 2020 at 10:11:11AM -0700, kan.liang@linux.intel.com wrote:
> > @@ -3375,6 +3428,72 @@ static int intel_pmu_hw_config(struct perf_event *event)
> > if (event->attr.type != PERF_TYPE_RAW)
> > return 0;
> >
> > + /*
> > + * Config Topdown slots and metric events
> > + *
> > + * The slots event on Fixed Counter 3 can support sampling,
> > + * which will be handled normally in x86_perf_event_update().
> > + *
> > + * The metric events don't support sampling.
> > + *
> > + * For counting, topdown slots and metric events will be
> > + * handled specially for event update.
> > + * A flag PERF_X86_EVENT_TOPDOWN is applied for the case.
> > + */
> > + if (x86_pmu.intel_cap.perf_metrics && is_topdown_event(event)) {
> > + if (is_metric_event(event)) {
> > + struct perf_event *leader = event->group_leader;
> > + struct perf_event *sibling;
> > +
> > + /* The metric events don't support sampling. */
> > + if (is_sampling_event(event))
> > + return -EINVAL;
> > +
> > + /* The metric events cannot be a group leader. */
> > + if (leader == event)
> > + return -EINVAL;
> > +
> > + /*
> > + * The slots event cannot be the leader of a topdown
> > + * sample-read group, e.g., {slots, topdown-retiring}:S
> > + */
> > + if (is_slots_event(leader) && is_sampling_event(leader))
> > + return -EINVAL;
>
> This has nothing to do with sample-read; SLOTS cannot be sampling when
> coupled with the METRIC stuff because hardware is daft.
>
> And you can have SAMPLE_READ on non-leader events just fine.
>
> > +
> > + /*
> > + * The slots event must be before the metric events,
> > + * because we only update the values of a topdown
> > + * group once with the slots event.
> > + */
> > + if (!is_slots_event(leader)) {
> > + for_each_sibling_event(sibling, leader) {
> > + if (is_slots_event(sibling))
> > + break;
> > + if (is_metric_event(sibling))
> > + return -EINVAL;
> > + }
> > + }
>
> Per the SIBLING patch this then wants to be:
>
> if (!is_slots_event(leader))
> return -EINVAL;
>
> event->event_caps |= PERF_EV_CAP_SIBLING.
> /*
> * Only once we have a METRICs sibling to we
> * need TopDown magic.
> */
> leader->hw.flags |= PERF_X86_EVENT_TOPDOWN;
> > + }
> > +
> > + if (!is_sampling_event(event)) {
> > + if (event->attr.config1 != 0)
> > + return -EINVAL;
>
> How does this depend on sampling?
>
> > + /*
> > + * The TopDown metrics events and slots event don't
> > + * support any filters.
> > + */
> > + if (event->attr.config & X86_ALL_EVENT_FLAGS)
> > + return -EINVAL;
>
> That seems independent of sampling too. Even a sampling SLOTS shouldn't
> be having any of those afaict.
>
> > +
> > + event->hw.flags |= PERF_X86_EVENT_TOPDOWN;
>
> This is confusing too, a !sampling SLOTS event without METRIC siblings
> shouldn't have this set, right? So arguably, this should be like above.
>
> > +
> > + event->event_caps |= PERF_EV_CAP_COEXIST;
> > +
> > + if (is_metric_event(event))
> > + event->hw.flags &= ~PERF_X86_EVENT_RDPMC_ALLOWED;
>
> This too seems like something that should be in the is_metric_event()
> branch above.
>
> > + }
> > + }
> > +
> > if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY))
> > return 0;
> >
FWIW, I pushed out a branch with all these changes in:
git://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git perf/metric
Just to get it some build love, if you want it differently, I'm happy to
throw it all out again.
next prev parent reply other threads:[~2020-07-24 15:28 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 [this message]
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
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=20200724152755.GK43129@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=acme@redhat.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=eranian@google.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=like.xu@linux.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;
as well as URLs for NNTP newsgroup(s).