linux-kernel - Re: [PATCH] perf vendor events riscv: add StarFive Dubhe-80 JSON file

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 for Android: free password hash cracker in your pocket

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

Message-ID: <CAP-5=fW6Qeu8Q_mQ7zUBsHn+BiMmDJvjn0nT1YAZaLH6EaBjnA@mail.gmail.com>
Date:   Thu, 2 Nov 2023 11:24:24 -0700
From:   Ian Rogers <irogers@...gle.com>
To:     Ji Sheng Teoh <jisheng.teoh@...rfivetech.com>
Cc:     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>,
        Paul Walmsley <paul.walmsley@...ive.com>,
        Palmer Dabbelt <palmer@...belt.com>,
        Albert Ou <aou@...s.berkeley.edu>,
        Ley Foon Tan <leyfoon.tan@...rfivetech.com>,
        linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
        Beeman Strong <beeman@...osinc.com>,
        linux-riscv@...ts.infradead.org, n.shubin@...ro.com,
        kconsul@...tanamicro.com
Subject: Re: [PATCH] perf vendor events riscv: add StarFive Dubhe-80 JSON file

On Wed, Nov 1, 2023 at 6:55 PM Ji Sheng Teoh
<jisheng.teoh@...rfivetech.com> wrote:
>
> StarFive's Dubhe-80 supports raw event id 0x00 - 0x22.
> The raw events are enabled through PMU node of DT binding.
>
> Example of PMU DT node:
> pmu {
>         compatible = "riscv,pmu";
>         riscv,raw-event-to-mhpmcounters =
>                 /* Event ID 1-31 */
>                 <0x00 0x00 0xFFFFFFFF 0xFFFFFFE0 0x00007FF8>,
>                 /* Event ID 32-33 */
>                 <0x00 0x20 0xFFFFFFFF 0xFFFFFFFE 0x00007FF8>,
>                 /* Event ID 34 */
>                 <0x00 0x22 0xFFFFFFFF 0xFFFFFF22 0x00007FF8>;
> };
>
> Example of Perf stat output:
> [root@...r]# perf stat -a \
>         -e access_mmu_stlb \
>         -e miss_mmu_stlb \
>         -e access_mmu_pte_c \
>         -e rob_flush \
>         -e btb_prediction_miss \
>         -e itlb_miss \
>         -e sync_del_fetch_g \
>         -e icache_miss \
>         -e bpu_br_retire \
>         -e bpu_br_miss \
>         -e ret_ins_retire \
>         -e ret_ins_miss \
>         -- openssl speed rsa2048
>
> Doing 2048 bits private rsa's for 10s: 39 2048 bits private RSA's in
> 10.14s
> Doing 2048 bits public rsa's for 10s: 1563 2048 bits public RSA's in
> 10.00s
> version: 3.0.11
> built on: Tue Sep 19 13:02:31 2023 UTC
> options: bn(64,64)
> CPUINFO: N/A
>                   sign    verify    sign/s verify/s
> rsa 2048 bits 0.260000s 0.006398s      3.8    156.3
>
>  Performance counter stats for 'system wide':
>
>            1338350      access_mmu_stlb
>            1154025      miss_mmu_stlb
>            1162691      access_mmu_pte_c
>              34067      rob_flush
>           11212384      btb_prediction_miss
>            1256242      itlb_miss
>          652523491      sync_del_fetch_g
>             384465      icache_miss
>           64635789      bpu_br_retire
>             323440      bpu_br_miss
>            8785143      ret_ins_retire
>              31236      ret_ins_miss
>
>       20.760822480 seconds time elapsed
>
> Signed-off-by: Ji Sheng Teoh <jisheng.teoh@...rfivetech.com>

Thanks Ji Sheng,

in adding these events for this new architecture is there a reason not
to add the architecture standard events in
tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json ?
https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git/tree/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json?h=perf-tools-next

Perhaps it is worth commenting in the commit message whether or not
these events are supported.

Thanks,
Ian