Re: [PATCH 2/5] perf,tools: check and re-organize evsel cpu maps

[Arnaldo Carvalho de Melo]

Em Tue, Mar 03, 2015 at 03:54:43AM -0500, kan.liang@xxxxxxxxx escreveu:
> From: Kan Liang <kan.liang@xxxxxxxxx>
> 
> With the patch 1/5, it's possible to group read events from different
> pmus. "-C" can be used to set cpu list. The cpu list may be incompatible
> with pmu's cpumask.
> This patch checks the event's cpu maps, and discard the incompatible cpu
> maps.
> event's cpu maps is saved in evsel->cpus during option parse. Then the
> evlist's cpu maps is created in perf_evlist__create_maps. So the cpu
> maps can be check and re-organized in perf_evlist__create_maps.
> Only cpu_list need to check the cpu maps.

Humm, I had something done in this area...

Stephane complained about the confusion about which cpumap to use with
pmus, so I wrote a patch and sent an RFC, which I think I got no
comments, lemme dig it...

- Arnaldo
 
> Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
> ---
>  tools/perf/builtin-top.c |  6 ++--
>  tools/perf/util/evlist.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 75 insertions(+), 3 deletions(-)
> 
> diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
> index 5fb8723..f40d1d6 100644
> --- a/tools/perf/builtin-top.c
> +++ b/tools/perf/builtin-top.c
> @@ -1218,9 +1218,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
>  	if (target__none(target))
>  		target->system_wide = true;
>  
> -	if (perf_evlist__create_maps(top.evlist, target) < 0)
> -		usage_with_options(top_usage, options);
> -
>  	if (!top.evlist->nr_entries &&
>  	    perf_evlist__add_default(top.evlist) < 0) {
>  		ui__error("Not enough memory for event selector list\n");
> @@ -1229,6 +1226,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
>  
>  	symbol_conf.nr_events = top.evlist->nr_entries;
>  
> +	if (perf_evlist__create_maps(top.evlist, target) < 0)
> +		usage_with_options(top_usage, options);
> +
>  	if (top.delay_secs < 1)
>  		top.delay_secs = 1;
>  
> diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
> index 8d0b623..3c6115c 100644
> --- a/tools/perf/util/evlist.c
> +++ b/tools/perf/util/evlist.c
> @@ -1026,6 +1026,74 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
>  	return perf_evlist__mmap_per_cpu(evlist, &mp);
>  }
>  
> +static int cmp_ids(const void *a, const void *b)
> +{
> +	return *(int *)a - *(int *)b;
> +}
> +
> +/*
> + * Check evsel cpu map according to pmu cpumask and input
> + * Only available cpu can be stored in evsel->cpus->map.
> + */
> +static int perf_evlist__check_evsel_cpus(struct perf_evlist *evlist)
> +{
> +	const struct cpu_map *cpus = evlist->cpus;
> +	const int ncpus = cpu_map__nr(evlist->cpus);
> +	struct perf_evsel *evsel;
> +	int i, j, cpu_nr, tmp;
> +
> +	/* ensure we process id in increasing order */
> +	qsort(evlist->cpus->map, evlist->cpus->nr, sizeof(int), cmp_ids);
> +
> +	evlist__for_each(evlist, evsel) {
> +		if (!evsel->cpus)
> +			continue;
> +
> +		cpu_nr = 0;
> +		j = 0;
> +		for (i = 0; i < cpu_map__nr(evsel->cpus);)  {
> +
> +			if (j >= ncpus) {
> +				evsel->cpus->map[i++] = -1;
> +				continue;
> +			}
> +			for (; j < ncpus; j++) {
> +				if (cpus->map[j] < evsel->cpus->map[i])
> +					continue;
> +				if (cpus->map[j] == evsel->cpus->map[i]) {
> +					cpu_nr++;
> +					j++;
> +					i++;
> +				} else
> +					evsel->cpus->map[i++] = -1;
> +				break;
> +			}
> +		}
> +
> +		if (cpu_nr == cpu_map__nr(evsel->cpus))
> +			continue;
> +		if (cpu_nr == 0) {
> +			perror("failed to create CPUs map, please check cpumask");
> +			return -1;
> +		}
> +
> +		tmp = 0;
> +		for (i = 0; i < cpu_nr; i++) {
> +			if (evsel->cpus->map[i] == -1) {
> +				while (evsel->cpus->map[tmp] == -1) {
> +					tmp++;
> +					BUG_ON(tmp >= cpu_map__nr(evsel->cpus));
> +				}
> +				evsel->cpus->map[i] = evsel->cpus->map[tmp];
> +				evsel->cpus->map[tmp] = -1;
> +			}
> +			tmp++;
> +		}
> +		evsel->cpus->nr = cpu_nr;
> +	}
> +	return 0;
> +}
> +
>  int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
>  {
>  	evlist->threads = thread_map__new_str(target->pid, target->tid,
> @@ -1042,6 +1110,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
>  	if (evlist->cpus == NULL)
>  		goto out_delete_threads;
>  
> +	if (target->cpu_list &&
> +	   (perf_evlist__check_evsel_cpus(evlist) < 0))
> +		goto out_delete_threads;
> +
>  	return 0;
>  
>  out_delete_threads:
> -- 
> 1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/