linux-kernel - Re: [PATCH 1/2] perf: ignore LBR and offcore

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] [day] [month] [year] [list]

Message-ID: <878uon8vr7.fsf@tassilo.jf.intel.com>
Date:	Mon, 23 Jun 2014 08:56:44 -0700
From:	Andi Kleen <andi@...stfloor.org>
To:	Peter Zijlstra <peterz@...radead.org>
Cc:	"Liang\, Kan" <kan.liang@...el.com>,
	"linux-kernel\@vger.kernel.org" <linux-kernel@...r.kernel.org>,
	"kvm\@vger.kernel.org" <kvm@...r.kernel.org>,
	"Kleen\, Andi" <andi.kleen@...el.com>
Subject: Re: [PATCH 1/2] perf: ignore LBR and offcore_rsp.

Peter Zijlstra <peterz@...radead.org> writes:

>
> So I really hate this patch, it makes the code hideous. Also, its a
> death by a thousand cuts adding endless branches in this code.

FWIW compared to the cost of a RDMSR (which is a very complex operation
for the CPU) the cost of a predicted branch is nearly in the noise.

>
> Also, the offcore part is retarded, just make sure extra_reg isn't set.
>
> As to the LBR, just make it so that we avoid calling the LBR code to
> begin with; ideally without adding extra code to fast paths.

You mean check once at initialization time.

I'm not sure that would handle all cases unfortunately.

-Andi

-- 
ak@...ux.intel.com -- Speaking for myself only
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/