From: hejunhao <hejunhao3@huawei.com>
To: James Clark <james.clark@linaro.org>
Cc: <linuxarm@huawei.com>, <peterz@infradead.org>, <mingo@redhat.com>,
<acme@kernel.org>, <namhyung@kernel.org>, <mark.rutland@arm.com>,
<alexander.shishkin@linux.intel.com>, <jolsa@kernel.org>,
<irogers@google.com>, <linux-perf-users@vger.kernel.org>,
<linux-kernel@vger.kernel.org>, <leo.yan@arm.com>,
<john.g.garry@oracle.com>, <will@kernel.org>,
<mike.leach@linaro.org>, <yangyicong@hisilicon.com>,
<jonathan.cameron@huawei.com>, hejunhao <hejunhao3@huawei.com>
Subject: Re: [PATCH 1/2] perf vendor events arm64: Fill up Desc field for Hisi hip08 hha pmu
Date: Thu, 17 Apr 2025 17:05:27 +0800 [thread overview]
Message-ID: <4c2ddb5f-0d84-7b9e-7b0e-5fa1159b4be0@huawei.com> (raw)
In-Reply-To: <9f562c23-f790-4d82-b51e-79e63d04890a@linaro.org>
On 2025/4/16 21:17, James Clark wrote:
>
>
> On 16/04/2025 3:02 am, Junhao He wrote:
>> In the same PMU, when some JSON events have the "BriefDescription" field
>> populated while others do not, the cmp_sevent() function will split
>> these
>> two types of events into separate groups. As a result, when using perf
>> list to display events, the two types of events cannot be grouped
>> together
>> in the output.
>>
>
> Hi Junhao,
>
> I think just the first patch here [1] might have helped for this
> issue. It would result in them being grouped together, although one
> would still be missing the description so your change is ok either way.
>
> [1]:
> https://lore.kernel.org/lkml/20250304-james-perf-hybrid-list-v1-1-a363ffac283c@linaro.org/
>
Hi James,
Thanks for the comments.
In the cmp_sevent() function [2], the comparison begins with checking
sevent->desc.
Thus, the issue cannot be resolved by the patch [1].
Perhaps the simultaneous occurrence of hisi_sccl1_hha2 and hisi_sccl,hha
is making this
commit hard to understand. This is part of the optimization I'm working
on next, so
please ignore it for now. I will correct the PMU name and Unit in the
next version.
[2]:
https://elixir.bootlin.com/linux/v6.15-rc1/source/tools/perf/util/pmus.c#L435
>> before patch:
>> $ perf list
>> ...
>> uncore hha:
>> hisi_sccl1_hha2/sdir-hit/
>> hisi_sccl1_hha2/sdir-lookup/
>> ...
>> uncore hha:
>> edir-hit
>> [Count of The number of HHA E-Dir hit operations. Unit:
>> hisi_sccl,hha]
>>
>> after patch:
>> $ perf list
>> ...
>> uncore hha:
>> edir-hit
>> [Count of The number of HHA E-Dir hit operations. Unit:
>> hisi_sccl,hha]
>> sdir-hit
>> [Count of The number of HHA S-Dir hit operations. Unit:
>> hisi_sccl,hha]
>> sdir-lookup
>> [Count of the number of HHA S-Dir lookup operations. Unit:
>> hisi_sccl,hha]
>>
>> Signed-off-by: Junhao He <hejunhao3@huawei.com>
>> ---
>> .../arm64/hisilicon/hip08/uncore-hha.json | 32 +++++++++++++++++++
>> 1 file changed, 32 insertions(+)
>>
>> diff --git
>> a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
>> b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
>> index 9a7ec7af2060..5ac8f919b498 100644
>> --- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
>> +++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/uncore-hha.json
>> @@ -30,15 +30,21 @@
>> {
>> "ConfigCode": "0x4",
>> "EventName": "rx_wbi",
>> + "BriefDescription": "Count of the number of WriteBackI
>> operations that HHA has received",
>> + "PublicDescription": "Count of the number of WriteBackI
>> operations that HHA has received",
>
> You only need BriefDescription if both are going to be the same. It
> will be used for both short and long form output.
>
> With that:
>
> Reviewed-by: James Clark <james.clark@linaro.org>
>
Ok, i will drop this PublicDescription.
I will append one new patch to drop other hip08 uncore PMU
PublicDescriptions.
Best regards,
Junhao.
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x5",
>> "EventName": "rx_wbip",
>> + "BriefDescription": "Count of the number of WriteBackIPtl
>> operations that HHA has received",
>> + "PublicDescription": "Count of the number of WriteBackIPtl
>> operations that HHA has received",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x11",
>> + "BriefDescription": "Count of the number of WriteThruIStash
>> operations that HHA has received",
>> + "PublicDescription": "Count of the number of WriteThruIStash
>> operations that HHA has received",
>> "EventName": "rx_wtistash",
>> "Unit": "hisi_sccl,hha"
>> },
>> @@ -87,66 +93,92 @@
>> {
>> "ConfigCode": "0x23",
>> "EventName": "bi_num",
>> + "BriefDescription": "Count of the number of HHA BackInvalid
>> operations",
>> + "PublicDescription": "Count of the number of HHA BackInvalid
>> operations",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x32",
>> "EventName": "mediated_num",
>> + "BriefDescription": "Count of the number of Mediated
>> operations that the HHA has forwarded",
>> + "PublicDescription": "Count of the number of Mediated
>> operations that the HHA has forwarded",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x33",
>> "EventName": "tx_snp_num",
>> + "BriefDescription": "Count of the number of Snoop operations
>> that the HHA has sent",
>> + "PublicDescription": "Count of the number of Snoop
>> operations that the HHA has sent",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x34",
>> "EventName": "tx_snp_outer",
>> + "BriefDescription": "Count of the number of Snoop operations
>> that the HHA has sent to another socket",
>> + "PublicDescription": "Count of the number of Snoop
>> operations that the HHA has sent to another socket",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x35",
>> "EventName": "tx_snp_ccix",
>> + "BriefDescription": "Count of the number of Snoop operations
>> that the HHA has sent to CCIX",
>> + "PublicDescription": "Count of the number of Snoop
>> operations that the HHA has sent to CCIX",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x38",
>> "EventName": "rx_snprspdata",
>> + "BriefDescription": "Count of the number of SnprspData flit
>> operations that HHA has received",
>> + "PublicDescription": "Count of the number of SnprspData flit
>> operations that HHA has received",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x3c",
>> "EventName": "rx_snprsp_outer",
>> + "BriefDescription": "Count of the number of SnprspData
>> operations that HHA has received from another socket",
>> + "PublicDescription": "Count of the number of SnprspData
>> operations that HHA has received from another socket",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x40",
>> "EventName": "sdir-lookup",
>> + "BriefDescription": "Count of the number of HHA S-Dir lookup
>> operations",
>> + "PublicDescription": "Count of the number of HHA S-Dir
>> lookup operations",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x41",
>> "EventName": "edir-lookup",
>> + "BriefDescription": "Count of the number of HHA E-Dir lookup
>> operations",
>> + "PublicDescription": "Count of the number of HHA E-Dir
>> lookup operations",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x42",
>> "EventName": "sdir-hit",
>> + "BriefDescription": "Count of the number of HHA S-Dir hit
>> operations",
>> + "PublicDescription": "Count of the number of HHA S-Dir hit
>> operations",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x43",
>> "EventName": "edir-hit",
>> + "BriefDescription": "Count of the number of HHA E-Dir hit
>> operations",
>> + "PublicDescription": "Count of the number of HHA E-Dir hit
>> operations",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x4c",
>> "EventName": "sdir-home-migrate",
>> + "BriefDescription": "Count of the number of HHA S-Dir read
>> home migrate operations",
>> + "PublicDescription": "Count of the number of HHA S-Dir read
>> home migrate operations",
>> "Unit": "hisi_sccl,hha"
>> },
>> {
>> "ConfigCode": "0x4d",
>> "EventName": "edir-home-migrate",
>> + "BriefDescription": "Count of the number of HHA E-Dir read
>> home migrate operations",
>> + "PublicDescription": "Count of the number of HHA E-Dir read
>> home migrate operations",
>> "Unit": "hisi_sccl,hha"
>> }
>> ]
>
> .
>
next prev parent reply other threads:[~2025-04-17 9:05 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-16 2:02 [PATCH 0/2] perf vendor events arm64: Add some missing content for Hisi hip08 json Junhao He
2025-04-16 2:02 ` [PATCH 1/2] perf vendor events arm64: Fill up Desc field for Hisi hip08 hha pmu Junhao He
2025-04-16 13:17 ` James Clark
2025-04-17 9:05 ` hejunhao [this message]
2025-04-16 2:02 ` [PATCH 2/2] MAINTAINERS: Add hisilicon pmu json events under its entry Junhao He
2025-04-16 13:18 ` James Clark
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4c2ddb5f-0d84-7b9e-7b0e-5fa1159b4be0@huawei.com \
--to=hejunhao3@huawei.com \
--cc=acme@kernel.org \
--cc=alexander.shishkin@linux.intel.com \
--cc=irogers@google.com \
--cc=james.clark@linaro.org \
--cc=john.g.garry@oracle.com \
--cc=jolsa@kernel.org \
--cc=jonathan.cameron@huawei.com \
--cc=leo.yan@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=linuxarm@huawei.com \
--cc=mark.rutland@arm.com \
--cc=mike.leach@linaro.org \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=will@kernel.org \
--cc=yangyicong@hisilicon.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®