linux-kernel - Re: [PATCH V4 07/14] perf/x86/intel: Support hardware TopDown metrics

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: <8d255708-6b8d-c18d-1491-cb19e3c6be4d@linux.intel.com>
Date:   Mon, 30 Sep 2019 12:45:26 -0400
From:   "Liang, Kan" <kan.liang@...ux.intel.com>
To:     Peter Zijlstra <peterz@...radead.org>, ak@...ux.intel.com
Cc:     acme@...nel.org, mingo@...hat.com, linux-kernel@...r.kernel.org,
        tglx@...utronix.de, jolsa@...nel.org, eranian@...gle.com,
        alexander.shishkin@...ux.intel.com
Subject: Re: [PATCH V4 07/14] perf/x86/intel: Support hardware TopDown metrics

On 9/30/2019 12:21 PM, Peter Zijlstra wrote:
>>> {
>>> 	int idx = event->hwc.idx;
>>>
>>> 	if (is_metric_idx(idx))
>>> 		return;
>>>
>>> 	// must be FIXED_SLOTS
>> The FIXED_SLOTS may not be in the group.
> Argh.. can we mandate that it is? that is, if you want a metric thing,
> you have to have a slots counter first?

If we mandate the FIXED_SLOTS in the group, we don't need the 
is_first_topdown_event_in_group() check. We just update everything for 
FIXED_SLOTS event. It will definitely simplify the code.

For perf sub-tool, I can add warning if users missed the SLOTs event or 
just implicitly add the event.

For RDPMC users, it looks like there is no way to warn them.
But they should always apply for both SLOTS and METRICS?

Andi, what do you think? Will it be a problem for RDPMC users?

Thanks,
Kan