From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754905Ab1BWBIw (ORCPT ); Tue, 22 Feb 2011 20:08:52 -0500 Received: from mga02.intel.com ([134.134.136.20]:43864 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751697Ab1BWBIv (ORCPT ); Tue, 22 Feb 2011 20:08:51 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.62,209,1297065600"; d="scan'208";a="605526528" Subject: Re: [PATCH 1/6] perf-events: Add support for supplementary event registers v5 From: Lin Ming To: Peter Zijlstra Cc: Ingo Molnar , Stephane Eranian , Andi Kleen , linux-kernel , Frederic Weisbecker In-Reply-To: <1298388053.2217.204.camel@twins> References: <1298221019.2318.62.camel@localhost> <1298388053.2217.204.camel@twins> Content-Type: text/plain; charset="UTF-8" Date: Wed, 23 Feb 2011 09:09:08 +0800 Message-ID: <1298423348.2835.3.camel@minggr.sh.intel.com> Mime-Version: 1.0 X-Mailer: Evolution 2.30.2 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2011-02-22 at 23:20 +0800, Peter Zijlstra wrote: > On Mon, 2011-02-21 at 00:56 +0800, Lin Ming wrote: > > @@ -225,7 +225,10 @@ struct perf_event_attr { > > }; > > > > __u32 bp_type; > > - __u64 bp_addr; > > + union { > > + __u64 bp_addr; > > + __u64 event_extra; /* Extra for some events */ > > + }; > > __u64 bp_len; > > }; > > I did s/event_extra/config1/g and: > > Index: linux-2.6/include/linux/perf_event.h > =================================================================== > --- linux-2.6.orig/include/linux/perf_event.h > +++ linux-2.6/include/linux/perf_event.h > @@ -227,9 +230,12 @@ struct perf_event_attr { > __u32 bp_type; > union { > __u64 bp_addr; > - __u64 config1; /* Extra for some events */ > + __u64 config1; /* extension of config0 */ > + }; > + union { > + __u64 bp_len; > + __u64 config2; /* extension of config1 */ > }; > - __u64 bp_len; > }; > > /* > > Giving us basically 192 bits of config{,1,2} space and the possibility > of eventually deprecating the bp_ stuff. OK, Do you mean it's possible to encode bp_type/bp_addr/bp_len into config1/config2?