[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Tue, 3 Mar 2020 20:02:58 +0530
From: Ravi Bangoria <ravi.bangoria@...ux.ibm.com>
To: Mark Rutland <mark.rutland@....com>
Cc: linuxppc-dev@...ts.ozlabs.org, linux-kernel@...r.kernel.org,
eranian@...gle.com, peterz@...radead.org, mpe@...erman.id.au,
paulus@...ba.org, mingo@...hat.com, acme@...nel.org,
alexander.shishkin@...ux.intel.com, jolsa@...hat.com,
namhyung@...nel.org, adrian.hunter@...el.com, ak@...ux.intel.com,
kan.liang@...ux.intel.com, alexey.budankov@...ux.intel.com,
yao.jin@...ux.intel.com, robert.richter@....com,
kim.phillips@....com, maddy@...ux.ibm.com,
Madhavan Srinivasan <maddy@...ux.vnet.ibm.com>,
Ravi Bangoria <ravi.bangoria@...ux.ibm.com>
Subject: Re: [RFC 02/11] perf/core: Data structure to present hazard data
On 3/2/20 8:18 PM, Mark Rutland wrote:
>> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
>> index 377d794d3105..ff252618ca93 100644
>> --- a/include/uapi/linux/perf_event.h
>> +++ b/include/uapi/linux/perf_event.h
>> @@ -142,8 +142,9 @@ enum perf_event_sample_format {
>> PERF_SAMPLE_REGS_INTR = 1U << 18,
>> PERF_SAMPLE_PHYS_ADDR = 1U << 19,
>> PERF_SAMPLE_AUX = 1U << 20,
>> + PERF_SAMPLE_PIPELINE_HAZ = 1U << 21,
>
> Can we please have perf_event_open() reject this sample flag for PMUs
> without the new callback (introduced in the next patch)?
>
> That way it'll be possible to detect whether the PMU exposes this.
Sure. Will change it.
Ravi
Powered by blists - more mailing lists