linux-kernel - Re: [PATCH V2 4/4] perf parse-events: Move slots event for the hybrid platform too

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:   Mon, 16 May 2022 19:54:00 -0700
From:   Ian Rogers <irogers@...gle.com>
To:     kan.liang@...ux.intel.com
Cc:     acme@...nel.org, mingo@...hat.com, jolsa@...nel.org,
        namhyung@...nel.org, linux-kernel@...r.kernel.org,
        linux-perf-users@...r.kernel.org, peterz@...radead.org,
        zhengjun.xing@...ux.intel.com, adrian.hunter@...el.com,
        ak@...ux.intel.com, eranian@...gle.com
Subject: Re: [PATCH V2 4/4] perf parse-events: Move slots event for the hybrid
 platform too

On Mon, May 16, 2022 at 8:25 AM <kan.liang@...ux.intel.com> wrote:
>
> From: Kan Liang <kan.liang@...ux.intel.com>
>
> The commit 94dbfd6781a0 ("perf parse-events: Architecture specific
> leader override") introduced a feature to reorder the slots event to
> fulfill the restriction of the perf metrics topdown group. But the
> feature doesn't work on the hybrid machine.
>
> $perf stat -e "{cpu_core/instructions/,cpu_core/slots/,cpu_core/topdown-retiring/}" -a sleep 1
>
>  Performance counter stats for 'system wide':
>
>      <not counted>      cpu_core/instructions/
>      <not counted>      cpu_core/slots/
>    <not supported>      cpu_core/topdown-retiring/
>
>        1.002871801 seconds time elapsed
>
> A hybrid platform has a different PMU name for the core PMUs, while
> current perf hard code the PMU name "cpu".
>
> Introduce a new function to check whether the system supports the perf
> metrics feature. The result is cached for the future usage.
>
> For X86, the core PMU name always has "cpu" prefix.
>
> With the patch,
>
> $perf stat -e "{cpu_core/instructions/,cpu_core/slots/,cpu_core/topdown-retiring/}" -a sleep 1
>
>  Performance counter stats for 'system wide':
>
>         76,337,010      cpu_core/slots/
>         10,416,809      cpu_core/instructions/
>         11,692,372      cpu_core/topdown-retiring/
>
>        1.002805453 seconds time elapsed
>
> Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>

Reviewed-by: Ian Rogers <irogers@...gle.com>

Thanks!
Ian

> ---
>  tools/perf/arch/x86/util/evlist.c  |  5 +++--
>  tools/perf/arch/x86/util/topdown.c | 24 ++++++++++++++++++++++++
>  tools/perf/arch/x86/util/topdown.h |  7 +++++++
>  3 files changed, 34 insertions(+), 2 deletions(-)
>  create mode 100644 tools/perf/arch/x86/util/topdown.h
>
> diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
> index 75564a7df15b..68f681ad54c1 100644
> --- a/tools/perf/arch/x86/util/evlist.c
> +++ b/tools/perf/arch/x86/util/evlist.c
> @@ -3,6 +3,7 @@
>  #include "util/pmu.h"
>  #include "util/evlist.h"
>  #include "util/parse-events.h"
> +#include "topdown.h"
>
>  #define TOPDOWN_L1_EVENTS      "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}"
>  #define TOPDOWN_L2_EVENTS      "{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}"
> @@ -25,12 +26,12 @@ struct evsel *arch_evlist__leader(struct list_head *list)
>
>         first = list_first_entry(list, struct evsel, core.node);
>
> -       if (!pmu_have_event("cpu", "slots"))
> +       if (!topdown_sys_has_perf_metrics())
>                 return first;
>
>         /* If there is a slots event and a topdown event then the slots event comes first. */
>         __evlist__for_each_entry(list, evsel) {
> -               if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") && evsel->name) {
> +               if (evsel->pmu_name && !strncmp(evsel->pmu_name, "cpu", 3) && evsel->name) {
>                         if (strcasestr(evsel->name, "slots")) {
>                                 slots = evsel;
>                                 if (slots == first)
> diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
> index 2f3d96aa92a5..5e86859279e3 100644
> --- a/tools/perf/arch/x86/util/topdown.c
> +++ b/tools/perf/arch/x86/util/topdown.c
> @@ -3,6 +3,30 @@
>  #include "api/fs/fs.h"
>  #include "util/pmu.h"
>  #include "util/topdown.h"
> +#include "topdown.h"
> +
> +bool topdown_sys_has_perf_metrics(void)
> +{
> +       static bool has_perf_metrics;
> +       static bool cached;
> +       struct perf_pmu *pmu;
> +
> +       if (cached)
> +               return has_perf_metrics;
> +
> +       /*
> +        * The perf metrics feature is a core PMU feature.
> +        * The PERF_TYPE_RAW type is the type of a core PMU.
> +        * The slots event is only available when the core PMU
> +        * supports the perf metrics feature.
> +        */
> +       pmu = perf_pmu__find_by_type(PERF_TYPE_RAW);
> +       if (pmu && pmu_have_event(pmu->name, "slots"))
> +               has_perf_metrics = true;
> +
> +       cached = true;
> +       return has_perf_metrics;
> +}
>
>  /*
>   * Check whether we can use a group for top down.
> diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h
> new file mode 100644
> index 000000000000..46bf9273e572
> --- /dev/null
> +++ b/tools/perf/arch/x86/util/topdown.h
> @@ -0,0 +1,7 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef _TOPDOWN_H
> +#define _TOPDOWN_H 1
> +
> +bool topdown_sys_has_perf_metrics(void);
> +
> +#endif
> --
> 2.35.1
>