From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1753128AbbBJRQO (ORCPT <rfc822;w@1wt.eu>);
	Tue, 10 Feb 2015 12:16:14 -0500
Received: from casper.infradead.org ([85.118.1.10]:60741 "EHLO
	casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1752036AbbBJRQN (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Tue, 10 Feb 2015 12:16:13 -0500
Date: Tue, 10 Feb 2015 18:16:06 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Andi Kleen <ak@linux.intel.com>
Cc: Andi Kleen <andi@firstfloor.org>, linux-kernel@vger.kernel.org,
        kan.liang@intel.com
Subject: Re: [PATCH 1/3] perf, x86: Add new cache events table for Haswell
Message-ID: <20150210171606.GB21418@twins.programming.kicks-ass.net>
References: <1423509466-24430-1-git-send-email-andi@firstfloor.org>
 <20150210103455.GX21418@twins.programming.kicks-ass.net>
 <20150210171135.GL680@tassilo.jf.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20150210171135.GL680@tassilo.jf.intel.com>
User-Agent: Mutt/1.5.21 (2012-12-30)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, Feb 10, 2015 at 09:11:35AM -0800, Andi Kleen wrote:

> > Now the other tables create little helpers like:
> > 
> > #define HSW_DMND_READ	(HSW_DMND_DATA_RD)
> > #define HSW_DMND_WRITE	(HSW_DMND_RFO)
> > 
> > #define HSW_L3_ACCESS	(HSW_ANY_RESPONSE)
> > #define HSW_L3_MISS	(HSW_L3_MISS)
> > 
> > And compose the tables values using those:
> > 
> > 	HSW_DMND_READ|HSW_L3_ACCESS
> > 
> > Please do so here too.
> 
> I'm trying to stay with the official documented bit names. No such bit names exist.
> If we make up our own names nobody else can read it anymore.

Well, its a simple matter of looking up the bit definitions; we define
those helpers in terms of the official names after all.

By having the 4 helpers {r,w}x{access,miss} you avoid some repetition
and decrease the room for mistakes.

> > Now; when comparing these value to the SNB for example I note that you
> > include ANY_SNOOP and SUPPLIER_NONE in L3_ACCESS, SNB and other do not,
> > please explain.
> 
> You're supposed to set a snoop and supplier qualifier.
> AFAIK SNB should set them too. It may work without them due to some
> quirk.

OK, then we should fix the others. Thanks.