Re: [PATCH V3 0/5] bugs fix for large PEBS mmap read and rdpmc read

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

On 1/30/2018 8:39 AM, Jiri Olsa wrote:
> On Tue, Jan 30, 2018 at 01:16:39AM -0800, Stephane Eranian wrote:
>> Hi,
>>
>> On Mon, Jan 29, 2018 at 8:29 AM, <kan.liang@linux.intel.com> wrote:
>>>
>>> From: Kan Liang <kan.liang@linux.intel.com>
>>>
>>> ------
>>>
>>> Changes since V2:
>>>   - Refined the changelog
>>>   - Introduced specific read function for large PEBS.
>>>     The previous generic PEBS read function is confusing.
>>>     Disabled PMU in pmu::read() path for large PEBS.
>>>     Handled the corner case when reload_times == 0.
>>>   - Modified the parameter of intel_pmu_save_and_restart_reload()
>>>     Discarded local64_cmpxchg
>>>   - Added fixes tag
>>>   - Added WARN to handle reload_times == 0 || reload_val == 0
>>>
>>> Changes since V1:
>>>   - Check PERF_X86_EVENT_AUTO_RELOAD before call
>>>     intel_pmu_save_and_restore()
>>
>> It is not yet clear to me why PERF_SAMPLE_PERIOD is not allowed
>> with large PEBS. Large PEBS requires fixed period. So the kernel could
>> make up the period from the event and store it in the sampling buffer.
>>
>> I tried using large PEBS recently, and despite trying different option
>> combination of perf record, I was not able to get it to work.
>>
>> $ perf record  -c 1  -e cpu/event=0xd1,umask=0x10,period=19936/pp
>> --no-timestamp --no-period -a -C 0
>>
>> But I was able to make this work with a much older kernel.
>>
>> Another annoyance I ran into is with perf record requiring -c period
>> in order not to set
>> PERF_SAMPLE_PERIOD in the event.
>>
>> If I do:
>> perf record  -c 1  -e cpu/event=0xd1,umask=0x10,period=19936/pp
>> --no-timestamp --no-period -a -C 0
>>
>> I get
>>
>> perf_event_attr:
>>    type                             4
>>    size                             112
>>    config                           0x10d1
>>    { sample_period, sample_freq }   199936
>>    sample_type                      IP|TID|CPU
>>
>> But if I do:
>> perf record  -e cpu/event=0xd1,umask=0x10,period=19936/pp
>> --no-timestamp --no-period -a -C 0
>>
>> I get
>>
>> perf_event_attr:
>>    type                             4
>>    size                             112
>>    config                           0x10d1
>>    { sample_period, sample_freq }   199936
>>    sample_type                      IP|TID|CPU|PERIOD
>>
>> Perf should check if all events have a period=, then it should not
>> pass PERF_SAMPLE_PERIOD, even
>> more so when only one event is defined.
>>
>> Also it does not seem to honor --no-period.
> 
> yep, there's a bug in period=x term handling
> we did not re/set the sample_type based on that
> 
> attached patch fixes that for me, also takes into account
> the --no/-period options
> 
> jirka
> 
> 
> ---
> diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
> index f251e824edac..907267206973 100644
> --- a/tools/perf/builtin-record.c
> +++ b/tools/perf/builtin-record.c
> @@ -1566,7 +1566,8 @@ static struct option __record_options[] = {
>   	OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
>   			&record.opts.sample_time_set,
>   			"Record the sample timestamps"),
> -	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
> +	OPT_BOOLEAN_SET('P', "period", &record.opts.period, &record.opts.period_set,
> +			"Record the sample period"),
>   	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
>   		    "don't sample"),
>   	OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
> diff --git a/tools/perf/perf.h b/tools/perf/perf.h
> index 2357f4ccc9c7..cfe46236a5e5 100644
> --- a/tools/perf/perf.h
> +++ b/tools/perf/perf.h
> @@ -50,6 +50,7 @@ struct record_opts {
>   	bool	     sample_time_set;
>   	bool	     sample_cpu;
>   	bool	     period;
> +	bool	     period_set;
>   	bool	     running_time;
>   	bool	     full_auxtrace;
>   	bool	     auxtrace_snapshot_mode;
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 66fa45198a11..ff359c9ece2e 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -745,12 +745,14 @@ static void apply_config_terms(struct perf_evsel *evsel,
>   			if (!(term->weak && opts->user_interval != ULLONG_MAX)) {
>   				attr->sample_period = term->val.period;
>   				attr->freq = 0;
> +				perf_evsel__reset_sample_bit(evsel, PERIOD);
>   			}
>   			break;
>   		case PERF_EVSEL__CONFIG_TERM_FREQ:
>   			if (!(term->weak && opts->user_freq != UINT_MAX)) {
>   				attr->sample_freq = term->val.freq;
>   				attr->freq = 1;
> +				perf_evsel__set_sample_bit(evsel, PERIOD);
>   			}

If we do so, some events could be in fixed mode without PERIOD set. 
Other events could be in freq mode with PERIOD set.
That could be a problem for large PEBS. The PEBS buffer is shared among 
events. It doesn't support freq mode yet.

Thanks,
Kan

>   			break;
>   		case PERF_EVSEL__CONFIG_TERM_TIME:
> @@ -969,9 +971,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
>   	if (target__has_cpu(&opts->target) || opts->sample_cpu)
>   		perf_evsel__set_sample_bit(evsel, CPU);
>   
> -	if (opts->period)
> -		perf_evsel__set_sample_bit(evsel, PERIOD);
> -
>   	/*
>   	 * When the user explicitly disabled time don't force it here.
>   	 */
> @@ -1073,6 +1072,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
>   	apply_config_terms(evsel, opts, track);
>   
>   	evsel->ignore_missing_thread = opts->ignore_missing_thread;
> +
> +	/* The --period option takes the precedence. */
> +	if (opts->period_set) {
> +		if (opts->period)
> +			perf_evsel__set_sample_bit(evsel, PERIOD);
> +		else
> +			perf_evsel__reset_sample_bit(evsel, PERIOD);
> +	}
>   }
>   
>   static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
>