Re: [PATCH 3/9] perf/x86/intel: Support overflows on SLOTS

["Liang, Kan" <kan.liang@linux.intel.com>]

On 5/28/2019 8:20 AM, Peter Zijlstra wrote:
> On Tue, May 21, 2019 at 02:40:49PM -0700, kan.liang@linux.intel.com wrote:
>> From: Andi Kleen <ak@linux.intel.com>
>>
>> The internal counters used for the metrics can overflow. If this happens
>> an overflow is triggered on the SLOTS fixed counter. Add special code
>> that resets all the slave metric counters in this case.
> 
> The SDM also talked about a OVF_PERF_METRICS overflow bit. Which seems
> to suggest something else.

Yes, I think we should handle the bit as well and only update metrics event.

It looks like bit 48 is occupied by INTEL_PMC_IDX_FIXED_BTS.
I will also change
INTEL_PMC_IDX_FIXED_BTS to INTEL_PMC_IDX_FIXED + 15.
INTEL_PMC_IDX_FIXED_METRIC_BASE to INTEL_PMC_IDX_FIXED + 16

Thanks,
Kan

> 
>> Signed-off-by: Andi Kleen <ak@linux.intel.com>
>> Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
>> ---
>>   arch/x86/events/intel/core.c | 23 +++++++++++++++++++++++
>>   1 file changed, 23 insertions(+)
>>
>> diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
>> index 75ed91a36413..a66dc761f09d 100644
>> --- a/arch/x86/events/intel/core.c
>> +++ b/arch/x86/events/intel/core.c
>> @@ -2279,12 +2279,35 @@ static void intel_pmu_add_event(struct perf_event *event)
>>   		intel_pmu_lbr_add(event);
>>   }
>>   
>> +/* When SLOTS overflowed update all the active topdown-* events */
>> +static void intel_pmu_update_metrics(struct perf_event *event)
>> +{
>> +	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
>> +	int idx;
>> +	u64 slots_events;
>> +
>> +	slots_events = *(u64 *)cpuc->enabled_events & INTEL_PMC_MSK_ANY_SLOTS;
>> +
>> +	for_each_set_bit(idx, (unsigned long *)&slots_events, 64) {
> 
> 	for (idx = INTEL_PMC_IDX_TD_RETIRING;
> 	     idx <= INTEL_PMC_IDX_TD_BE_BOUND; idx++)
> 
> perhaps?
> 
>> +		struct perf_event *ev = cpuc->events[idx];
>> +
>> +		if (ev == event)
>> +			continue;
>> +		x86_perf_event_update(event);
> 
> 		if (ev != event)
> 			x86_perf_event_update(event)
>> +	}
>> +}
>> +
>>   /*
>>    * Save and restart an expired event. Called by NMI contexts,
>>    * so it has to be careful about preempting normal event ops:
>>    */
>>   int intel_pmu_save_and_restart(struct perf_event *event)
>>   {
>> +	struct hw_perf_event *hwc = &event->hw;
>> +
>> +	if (unlikely(hwc->reg_idx == INTEL_PMC_IDX_FIXED_SLOTS))
>> +		intel_pmu_update_metrics(event);
>> +
>>   	x86_perf_event_update(event);
>>   	/*
>>   	 * For a checkpointed counter always reset back to 0.  This
>> -- 
>> 2.14.5
>>