linux-kernel - Re: [PATCH] perf pmu: Fix event list for uncore PMUs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 21 Dec 2021 08:58:31 +0100
From:   Jiri Olsa <jolsa@...hat.com>
To:     John Garry <john.garry@...wei.com>
Cc:     peterz@...radead.org, mingo@...hat.com, acme@...nel.org,
        mark.rutland@....com, alexander.shishkin@...ux.intel.com,
        namhyung@...nel.org, irogers@...gle.com, kan.liang@...ux.intel.com,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH] perf pmu: Fix event list for uncore PMUs

On Thu, Dec 16, 2021 at 11:53:37PM +0800, John Garry wrote:
> Commit 0e0ae8742207 ("perf list: Display hybrid PMU events with cpu type")
> changed the list for uncore PMUs, such that duplicate aliases are now
> listed per PMU (which they should not be), like:
> 
> ./perf list
> ...
> unc_cbo_cache_lookup.any_es
> [Unit: uncore_cbox L3 Lookup any request that access cache and found
> line in E or S-state]
> unc_cbo_cache_lookup.any_es
> [Unit: uncore_cbox L3 Lookup any request that access cache and found
> line in E or S-state]
> unc_cbo_cache_lookup.any_i
> [Unit: uncore_cbox L3 Lookup any request that access cache and found
> line in I-state]
> unc_cbo_cache_lookup.any_i
> [Unit: uncore_cbox L3 Lookup any request that access cache and found
> line in I-state]
> ...
> 
> Notice how the events are listed twice.
> 
> The named commit changed how we remove duplicate events, in that events
> for different PMUs are not treated as duplicates. I suppose this is to
> handle how "Each hybrid pmu event has been assigned with a pmu name".
> 
> Fix uncore PMU alias list by also checking if events with PMU name are not
> cpu PMUs.
> 
> Fixes: 0e0ae8742207 ("perf list: Display hybrid PMU events with cpu type")
> Signed-off-by: John Garry <john.garry@...wei.com>
> ---
> It would be helpful if someone with some of these hybrid CPU systems could
> test this change, thanks!
> 
> diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
> index 6ae58406f4fc..392f6a36418b 100644
> --- a/tools/perf/util/pmu.c
> +++ b/tools/perf/util/pmu.c
> @@ -1659,6 +1659,24 @@ bool is_pmu_core(const char *name)
>  	return !strcmp(name, "cpu") || is_arm_pmu_core(name);
>  }
>  
> +static bool pmu_alias_is_duplicate(struct sevent *alias_a,
> +				   struct sevent *alias_b)
> +{
> +	/* Different names -> never duplicates */
> +	if (strcmp(alias_a->name, alias_b->name))
> +		return false;
> +	if (!alias_a->pmu)
> +		return true;
> +	if (!alias_b->pmu)
> +		return true;

nit could be:

	if (!alias_a->pmu || !alias_b->pmu)
		return true;

would be great to have more comments explaining the check

thanks,
jirka

> +	if (!strcmp(alias_a->pmu, alias_b->pmu))
> +		return true;
> +	/* uncore PMUs */
> +	if (!alias_a->is_cpu && !alias_b->is_cpu)
> +		return true;
> +	return false;
> +}
> +
>  void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
>  			bool long_desc, bool details_flag, bool deprecated,
>  			const char *pmu_name)
> @@ -1744,12 +1762,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
>  	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
>  	for (j = 0; j < len; j++) {
>  		/* Skip duplicates */
> -		if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name)) {
> -			if (!aliases[j].pmu || !aliases[j - 1].pmu ||
> -			    !strcmp(aliases[j].pmu, aliases[j - 1].pmu)) {
> -				continue;
> -			}
> -		}
> +		if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1]))
> +			continue;
>  
>  		if (name_only) {
>  			printf("%s ", aliases[j].name);
> -- 
> 2.26.2
>