linux-kernel - Re: [PATCH] perf stat: Fix display of grouped aliased events.

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:   Fri, 4 Feb 2022 17:48:20 -0800
From:   Andi Kleen <ak@...ux.intel.com>
To:     Ian Rogers <irogers@...gle.com>, vineet.singh@...el.com,
        perry.taylor@...el.com, caleb.biggers@...el.com,
        asaf.yaffe@...el.com, kshipra.bopardikar@...el.com,
        Kan Liang <kan.liang@...ux.intel.com>,
        Zhengjun Xing <zhengjun.xing@...ux.intel.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@...hat.com>,
        Namhyung Kim <namhyung@...nel.org>,
        Maxime Coquelin <mcoquelin.stm32@...il.com>,
        Alexandre Torgue <alexandre.torgue@...s.st.com>,
        James Clark <james.clark@....com>,
        John Garry <john.garry@...wei.com>,
        linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org
Cc:     Stephane Eranian <eranian@...gle.com>
Subject: Re: [PATCH] perf stat: Fix display of grouped aliased events.


On 2/4/2022 5:09 PM, Ian Rogers wrote:
> An event may have a number of uncore aliases that when added to
> the evlist are consecutive. If there are multiple uncore events
> in a group then parse_events__set_leader_for_uncore_aliase will
> reorder the evlist so that events on the same PMU are
> adjacent. collect_all_aliases assumes that aliases are in blocks
> so that only the first counter is printed and all others are
> marked merged. The reordering for groups breaks the assumption
> and so all counts are printed. This change removes the assumption
> from collect_all_aliases that the events are in blocks and
> instead processes the entire evlist.

Looks good to me.

Reviewed-by: Andi Kleen <ak@...ux.intel.com>


-Andi