linux-kernel - Re: [PATCH v2 0/4] Hybrid event parsing fixes

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]

Message-ID: <07b1f8d9-3839-81cd-0c46-3742f6273901@linux.intel.com>
Date:   Thu, 1 Jun 2023 09:59:20 -0400
From:   "Liang, Kan" <kan.liang@...ux.intel.com>
To:     Ian Rogers <irogers@...gle.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        Jiri Olsa <jolsa@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Adrian Hunter <adrian.hunter@...el.com>,
        Rob Herring <robh@...nel.org>,
        Ravi Bangoria <ravi.bangoria@....com>,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
        Thomas Richter <tmricht@...ux.ibm.com>
Subject: Re: [PATCH v2 0/4] Hybrid event parsing fixes



On 2023-06-01 4:29 a.m., Ian Rogers wrote:
> Correct various issues that have come up in mailing list discussions,
> the most impactful of which is the wildcard opening of events of type
> PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE. But also try to avoid a
> parse-error without a warning, have more fall-back behaviors and be
> liberal with the definition of software events.
> 
> The majority of the change is in correcting the parse-event test to
> match the new hybrid parsing.
> 
> Ian Rogers (4):
>   perf pmu: Correct perf_pmu__auto_merge_stats affecting hybrid
>   perf evsel: Add verbose 3 print of evsel name when opening
>   perf parse-events: Wildcard most "numeric" events
>   perf test: Update parse-events expectations

The patch set fixes the issues I found on a hybrid machine.

Tested-by: Kan Liang <kan.liang@...ux.intel.com>

It's better to fold the examples (especially for the patch 1) in the
description. So we can understand what's it trying to fix and what's the
expected result now.

Thanks,
Kan

> 
>  tools/perf/tests/parse-events.c | 1108 ++++++++++++++++---------------
>  tools/perf/util/evsel.c         |    1 +
>  tools/perf/util/parse-events.c  |  104 ++-
>  tools/perf/util/parse-events.y  |   10 +-
>  tools/perf/util/pmu.c           |   18 +-
>  tools/perf/util/pmu.h           |    5 +
>  tools/perf/util/pmus.c          |    5 +
>  tools/perf/util/pmus.h          |    1 +
>  8 files changed, 698 insertions(+), 554 deletions(-)
>