[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <db2de7d0-d60d-33f8-3587-c776a3eb8fce@huawei.com>
Date: Fri, 25 Aug 2023 13:41:06 +0800
From: Yang Jihong <yangjihong1@...wei.com>
To: Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>
CC: <peterz@...radead.org>, <mingo@...hat.com>, <acme@...nel.org>,
<mark.rutland@....com>, <alexander.shishkin@...ux.intel.com>,
<jolsa@...nel.org>, <namhyung@...nel.org>,
<kan.liang@...ux.intel.com>, <james.clark@....com>,
<tmricht@...ux.ibm.com>, <ak@...ux.intel.com>,
<anshuman.khandual@....com>, <linux-kernel@...r.kernel.org>,
<linux-perf-users@...r.kernel.org>
Subject: Re: [PATCH v6 1/7] perf evlist: Add perf_evlist__go_system_wide()
helper
Hello,
On 2023/8/25 12:51, Ian Rogers wrote:
> On Sun, Aug 20, 2023 at 6:30 PM Yang Jihong <yangjihong1@...wei.com> wrote:
>>
>> For dummy events that keep tracking, we may need to modify its cpu_maps.
>> For example, change the cpu_maps to record sideband events for all CPUS.
>> Add perf_evlist__go_system_wide() helper to support this scenario.
>>
>> Signed-off-by: Yang Jihong <yangjihong1@...wei.com>
>> Acked-by: Adrian Hunter <adrian.hunter@...el.com>
>> ---
>> tools/lib/perf/evlist.c | 9 +++++++++
>> tools/lib/perf/include/internal/evlist.h | 2 ++
>> 2 files changed, 11 insertions(+)
>>
>> diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
>> index b8b066d0dc5e..3acbbccc1901 100644
>> --- a/tools/lib/perf/evlist.c
>> +++ b/tools/lib/perf/evlist.c
>> @@ -738,3 +738,12 @@ int perf_evlist__nr_groups(struct perf_evlist *evlist)
>> }
>> return nr_groups;
>> }
>> +
>> +void perf_evlist__go_system_wide(struct perf_evlist *evlist, struct perf_evsel *evsel)
>> +{
>> + if (!evsel->system_wide) {
>> + evsel->system_wide = true;
>> + if (evlist->needs_map_propagation)
>> + __perf_evlist__propagate_maps(evlist, evsel);
>> + }
>> +}
>
> I think this should be:
>
> void evsel__set_system_wide(struct evsel *evsel)
> {
> if (evsel->system_wide)
> return;
> evsel->system_wide = true;
> if (evsel->evlist->core.needs_map_propagation)
> ...
>
> The API being on evlist makes it look like all evsels are affected.
>
This part of the code is implemented according to Adrian's suggestion.
Refer to:
https://lore.kernel.org/linux-perf-users/206972a3-d44d-1c75-3fbc-426427614543@intel.com/
The logic of both is the same, and either is OK for me.
If really want to change it, please let me know.
Thanks,
Yang
Powered by blists - more mailing lists