linux-kernel - Re: [PATCH RESEND] perf/x86/intel: Bit 13 is valid for Icelake MSR_OFFCORE_RSP

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20190725075031.GG31381@hirez.programming.kicks-ass.net>
Date:   Thu, 25 Jul 2019 09:50:31 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     "Liang, Kan" <kan.liang@...ux.intel.com>
Cc:     Yunying Sun <yunying.sun@...el.com>, mingo@...hat.com,
        acme@...nel.org, alexander.shishkin@...ux.intel.com,
        jolsa@...hat.com, namhyung@...nel.org, tglx@...utronix.de,
        bp@...en8.de, hpa@...or.com, ak@...ux.intel.com, x86@...nel.org,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH RESEND] perf/x86/intel: Bit 13 is valid for Icelake
 MSR_OFFCORE_RSP_x register

On Wed, Jul 24, 2019 at 09:11:01AM -0400, Liang, Kan wrote:
> 
> 
> On 7/24/2019 4:29 AM, Yunying Sun wrote:
> >  From Intel SDM, bit 13 of Icelake MSR_OFFCORE_RSP_x register is valid for
> > counting hardware generated prefetches of L3 cache. But current bitmasks
> > in driver takes bit 13 as invalid. Here to fix it.
> > 
> > Before:
> > $ perf stat -e cpu/event=0xb7,umask=0x1,config1=0x1bfff/u sleep 3
> >   Performance counter stats for 'sleep 3':
> >     <not supported>      cpu/event=0xb7,umask=0x1,config1=0x1bfff/u
> > 
> > After:
> > $ perf stat -e cpu/event=0xb7,umask=0x1,config1=0x1bfff/u sleep 3
> >   Performance counter stats for 'sleep 3':
> >               9,293      cpu/event=0xb7,umask=0x1,config1=0x1bfff/u
> > 
> > Signed-off-by: Yunying Sun <yunying.sun@...el.com>
> 
> Thanks Yunying.
> 
> Reviewed-by: Kan Liang <kan.liang@...ux.intel.com>

Thanks!