linux-kernel - RE: [PATCH V2 25/37] perf script: Add synthesized Intel PT power and ptwrite events

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: <363DA0ED52042842948283D2FC38E4649BEC7BB1@IRSMSX106.ger.corp.intel.com>
Date:   Fri, 30 Jun 2017 19:37:58 +0000
From:   "Hunter, Adrian" <adrian.hunter@...el.com>
To:     Arnaldo Carvalho de Melo <acme@...nel.org>
CC:     Andi Kleen <ak@...ux.intel.com>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: RE: [PATCH V2 25/37] perf script: Add synthesized Intel PT power
 and ptwrite events

-----Original Message-----
From: Arnaldo Carvalho de Melo [mailto:acme@...nel.org] 
Sent: Friday, June 30, 2017 5:54 PM
To: Hunter, Adrian <adrian.hunter@...el.com>
Cc: Andi Kleen <ak@...ux.intel.com>; linux-kernel@...r.kernel.org
Subject: Re: [PATCH V2 25/37] perf script: Add synthesized Intel PT power and ptwrite events

> Em Fri, Jun 30, 2017 at 11:51:22AM +0300, Adrian Hunter escreveu:
> > On 06/30/2017 05:08 AM, Arnaldo Carvalho de Melo wrote:
> > > Em Thu, Jun 29, 2017 at 05:13:54PM -0300, Arnaldo Carvalho de Melo escreveu:
> > > Ok, passes all tests (gcc, clang where available) on:
>
> > >   41 ubuntu:16.10: Ok
> > >   42 ubuntu:17.04: Ok
>
> > > Can you provide new versions for the relevant patches?
 
> > I have sent new versions of the 2 patches affected.

> Thanks, a grafted those in my branch, will perform the usual build tests, then try it on a kaby lake machine.

> Have you thought about further "perf test" test cases to make sure this code stays working with all this infrastructure and details?

> Things like running synthetic workloads and getting a short sequence known to have these new packet types, checking if the hardware performing the tests is capable of generating such traces, etc?

The power events might not occur.  Ptwrite and cbr might be possible.  Perhaps simpler to just synthesize and then parse the events back to check them.