Re: [PATCH v4 26/48] perf evsel: Derive CPUs and threads in alloc_counts

From: Jiri Olsa <jolsa@redhat.com>
To: Ian Rogers <irogers@google.com>
Cc: Andi Kleen <ak@linux.intel.com>,
	Namhyung Kim <namhyung@kernel.org>,
	John Garry <john.garry@huawei.com>,
	Kajol Jain <kjain@linux.ibm.com>,
	"Paul A . Clarke" <pc@us.ibm.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Riccardo Mancini <rickyman7@gmail.com>,
	Kan Liang <kan.liang@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
	Vineet Singh <vineet.singh@intel.com>,
	James Clark <james.clark@arm.com>,
	Mathieu Poirier <mathieu.poirier@linaro.org>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Mike Leach <mike.leach@linaro.org>, Leo Yan <leo.yan@linaro.org>,
	coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org,
	zhengjun.xing@intel.com, eranian@google.com
Subject: Re: [PATCH v4 26/48] perf evsel: Derive CPUs and threads in alloc_counts
Date: Sun, 9 Jan 2022 19:30:45 +0100	[thread overview]
Message-ID: <Ydsp1d58t/gp/GHd@krava> (raw)
In-Reply-To: <20220105061351.120843-27-irogers@google.com>

On Tue, Jan 04, 2022 at 10:13:29PM -0800, Ian Rogers wrote:

SNIP

> diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
> index 7ff36bf6d644..3e275e9c60d1 100644
> --- a/tools/perf/util/counts.h
> +++ b/tools/perf/util/counts.h
> @@ -40,7 +40,7 @@ void perf_counts__delete(struct perf_counts *counts);
>  void perf_counts__reset(struct perf_counts *counts);
>  
>  void evsel__reset_counts(struct evsel *evsel);
> -int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads);
> +int evsel__alloc_counts(struct evsel *evsel);
>  void evsel__free_counts(struct evsel *evsel);
>  
>  #endif /* __PERF_COUNTS_H */
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 656c30b988ce..6c9af21776e6 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1578,7 +1578,7 @@ int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale)
>  	if (FD(evsel, cpu, thread) < 0)
>  		return -EINVAL;
>  
> -	if (evsel->counts == NULL && evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
> +	if (evsel->counts == NULL && evsel__alloc_counts(evsel) < 0)

ugh, nice.. good that it's used only from test code ;-)

btw I noticed evsel__read_on_cpu_scaled is not used at all

jirka

>  		return -ENOMEM;
>  
>  	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
> diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
> index c69b221f5e3e..995cb5003133 100644
> --- a/tools/perf/util/stat.c
> +++ b/tools/perf/util/stat.c
> @@ -152,11 +152,13 @@ static void evsel__free_stat_priv(struct evsel *evsel)
>  	zfree(&evsel->stats);
>  }
>  
> -static int evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads)
> +static int evsel__alloc_prev_raw_counts(struct evsel *evsel)
>  {
> +	int cpu_map_nr = evsel__nr_cpus(evsel);
> +	int nthreads = perf_thread_map__nr(evsel->core.threads);
>  	struct perf_counts *counts;
>  
> -	counts = perf_counts__new(ncpus, nthreads);
> +	counts = perf_counts__new(cpu_map_nr, nthreads);
>  	if (counts)
>  		evsel->prev_raw_counts = counts;
>  
> @@ -177,12 +179,9 @@ static void evsel__reset_prev_raw_counts(struct evsel *evsel)
>  
>  static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
>  {
> -	int ncpus = evsel__nr_cpus(evsel);
> -	int nthreads = perf_thread_map__nr(evsel->core.threads);
> -
>  	if (evsel__alloc_stat_priv(evsel) < 0 ||
> -	    evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
> -	    (alloc_raw && evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
> +	    evsel__alloc_counts(evsel) < 0 ||
> +	    (alloc_raw && evsel__alloc_prev_raw_counts(evsel) < 0))
>  		return -ENOMEM;
>  
>  	return 0;
> -- 
> 2.34.1.448.ga2b2bfdf31-goog
> 