linux-kernel - Re: [PATCH v5 3/5] perf test: Add pmu-event test for "Compat" and new event

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: <2dc21269-2fa0-ea39-454d-5f12a414bc13@linux.alibaba.com>
Date:   Mon, 31 Jul 2023 20:30:43 +0800
From:   Jing Zhang <renyu.zj@...ux.alibaba.com>
To:     John Garry <john.g.garry@...cle.com>,
        Ian Rogers <irogers@...gle.com>
Cc:     Will Deacon <will@...nel.org>, Mark Rutland <mark.rutland@....com>,
        Robin Murphy <robin.murphy@....com>,
        Ilkka Koskinen <ilkka@...amperecomputing.com>,
        Namhyung Kim <namhyung@...nel.org>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
        linux-perf-users@...r.kernel.org, linux-doc@...r.kernel.org,
        Zhuo Song <zhuo.song@...ux.alibaba.com>,
        Shuai Xue <xueshuai@...ux.alibaba.com>
Subject: Re: [PATCH v5 3/5] perf test: Add pmu-event test for "Compat" and new
 event_field.



在 2023/7/28 下午4:30, John Garry 写道:
> On 28/07/2023 07:17, Jing Zhang wrote:
>> Add new event test for uncore system event which is used to verify the
>> functionality of "Compat" matching multiple identifiers and the new event
>> fields "EventIdCode" and "Type".
>>
> 
> Thanks for doing this. It looks ok. I just have a comment, below.
> 

Thanks.

>> Signed-off-by: Jing Zhang <renyu.zj@...ux.alibaba.com>
>> ---
>>   .../pmu-events/arch/test/test_soc/sys/uncore.json  |  8 ++++
>>   tools/perf/tests/pmu-events.c                      | 55 ++++++++++++++++++++++
>>   2 files changed, 63 insertions(+)
>>
>> diff --git a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json
>> index c7e7528..879a0ae 100644
>> --- a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json
>> +++ b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json
>> @@ -12,5 +12,13 @@
>>              "EventName": "sys_ccn_pmu.read_cycles",
>>              "Unit": "sys_ccn_pmu",
>>              "Compat": "0x01"
>> +   },
>> +   {
>> +           "BriefDescription": "Counts total cache misses in first lookup result (high priority).",
>> +           "Type": "0x05",
>> +           "EventIdCode": "0x01",
>> +           "EventName": "sys_cmn_pmu.hnf_cache_miss",
>> +           "Unit": "arm_cmn",
>> +           "Compat": "434*;436*;43c*;43a01"
>>      }
>>   ]
>> diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c
>> index 1dff863b..e227dcd 100644
>> --- a/tools/perf/tests/pmu-events.c
>> +++ b/tools/perf/tests/pmu-events.c
>> @@ -255,9 +255,24 @@ struct perf_pmu_test_pmu {
>>       .matching_pmu = "uncore_sys_ccn_pmu",
>>   };
>>   +static const struct perf_pmu_test_event sys_cmn_pmu_hnf_cache_miss = {
>> +    .event = {
>> +        .name = "sys_cmn_pmu.hnf_cache_miss",
>> +        .event = "type=0x05,eventid=0x01",
>> +        .desc = "Counts total cache misses in first lookup result (high priority). Unit: uncore_arm_cmn ",
>> +        .topic = "uncore",
>> +        .pmu = "uncore_arm_cmn",
>> +        .compat = "434*;436*;43c*;43a01",
>> +    },
>> +    .alias_str = "type=0x5,eventid=0x1",
>> +    .alias_long_desc = "Counts total cache misses in first lookup result (high priority). Unit: uncore_arm_cmn ",
>> +    .matching_pmu = "uncore_arm_cmn_0",
>> +};
>> +
>>   static const struct perf_pmu_test_event *sys_events[] = {
>>       &sys_ddr_pmu_write_cycles,
>>       &sys_ccn_pmu_read_cycles,
>> +    &sys_cmn_pmu_hnf_cache_miss,
>>       NULL
>>   };
>>   @@ -699,6 +714,46 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu)
>>               &sys_ccn_pmu_read_cycles,
>>           },
>>       },
>> +    {
>> +        .pmu = {
>> +            .name = (char *)"uncore_arm_cmn_0",
>> +            .is_uncore = 1,
>> +            .id = (char *)"43401",
>> +        },
>> +        .aliases = {
>> +            &sys_cmn_pmu_hnf_cache_miss,
>> +        },
>> +    },
>> +    {
>> +        .pmu = {
>> +            .name = (char *)"uncore_arm_cmn_0",
>> +            .is_uncore = 1,
>> +            .id = (char *)"43602",
>> +        },
>> +        .aliases = {
>> +            &sys_cmn_pmu_hnf_cache_miss,
>> +        },
>> +    },
>> +    {
>> +        .pmu = {
>> +            .name = (char *)"uncore_arm_cmn_1",
> 
> Shouldn't this match some perf_pmu_test_event entry with same matching_pmu member? But is perf_pmu_test_event.matching_pmu member ever used for any checking???
> 

I need to double check because I was testing against 6.3-rc2.

Thanks,
Jing

> Thanks,
> John
> 
>> +            .is_uncore = 1,
>> +            .id = (char *)"43c03",
>> +        },
>> +        .aliases = {
>> +            &sys_cmn_pmu_hnf_cache_miss,
>> +        },
>> +    },
>> +    {
>> +        .pmu = {
>> +            .name = (char *)"uncore_arm_cmn_1",
>> +            .is_uncore = 1,
>> +            .id = (char *)"43a01",
>> +        },
>> +        .aliases = {
>> +            &sys_cmn_pmu_hnf_cache_miss,
>> +        },
>> +    }
>>   };
>>     /* Test that aliases generated are as expected */