[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4ce07775-1076-0a2d-55be-bea3c7dc63f9@linux.intel.com>
Date: Tue, 26 Jan 2021 10:44:17 -0500
From: "Liang, Kan" <kan.liang@...ux.intel.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: acme@...nel.org, mingo@...nel.org, linux-kernel@...r.kernel.org,
eranian@...gle.com, namhyung@...nel.org, jolsa@...hat.com,
ak@...ux.intel.com, yao.jin@...ux.intel.com
Subject: Re: [PATCH 03/12] perf/x86/intel: Add perf core PMU support for
Sapphire Rapids
On 1/26/2021 9:44 AM, Peter Zijlstra wrote:
> On Tue, Jan 19, 2021 at 12:38:22PM -0800, kan.liang@...ux.intel.com wrote:
>> @@ -3671,6 +3853,31 @@ static int intel_pmu_hw_config(struct perf_event *event)
>> }
>> }
>>
>> + /*
>> + * To retrieve complete Memory Info of the load latency event, an
>> + * auxiliary event has to be enabled simultaneously. Add a check for
>> + * the load latency event.
>> + *
>> + * In a group, the auxiliary event must be in front of the load latency
>> + * event. The rule is to simplify the implementation of the check.
>> + * That's because perf cannot have a complete group at the moment.
>> + */
>> + if (x86_pmu.flags & PMU_FL_MEM_LOADS_AUX &&
>> + (event->attr.sample_type & PERF_SAMPLE_DATA_SRC) &&
>> + is_mem_loads_event(event)) {
>> + struct perf_event *leader = event->group_leader;
>> + struct perf_event *sibling = NULL;
>> +
>> + if (!is_mem_loads_aux_event(leader)) {
>> + for_each_sibling_event(sibling, leader) {
>> + if (is_mem_loads_aux_event(sibling))
>> + break;
>> + }
>> + if (list_entry_is_head(sibling, &leader->sibling_list, sibling_list))
>> + return -ENODATA;
>> + }
>> + }
>> +
>> if (!(event->attr.config & ARCH_PERFMON_EVENTSEL_ANY))
>> return 0;
>>
>
> I have vague memories of this getting mentioned in a call at some point.
> Pretend I don't know anything and tell me more.
>
Adding the auxiliary event is for the new data source fields, data block
& address block. If perf only samples the load latency event, the value
of the data block & address block fields in a sample is not correct. To
get the correct value, we have to sample both the auxiliary event and
the load latency together on SPR. So I add the check in the kernel. I
also modify the perf mem in the perf tool accordingly.
Thanks,
Kan
Powered by blists - more mailing lists