From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from az33egw02.freescale.net (az33egw02.freescale.net [192.88.158.103]) by ozlabs.org (Postfix) with ESMTP id A652C67A6E for ; Wed, 6 Apr 2005 02:21:50 +1000 (EST) Received: from az33smr01.freescale.net (az33smr01.freescale.net [10.64.34.199]) by az33egw02.freescale.net (8.12.11/az33egw02) with ESMTP id j35GO1Ux010332 for ; Tue, 5 Apr 2005 09:24:01 -0700 (MST) Received: from [10.82.244.138] ([10.82.244.138]) by az33smr01.freescale.net (8.13.1/8.13.0) with ESMTP id j35GNuZ6006823 for ; Tue, 5 Apr 2005 11:23:56 -0500 (CDT) Mime-Version: 1.0 (Apple Message framework v619.2) Message-Id: <17e04050dd77805d8dd464fd6a1af284@freescale.com> Content-Type: text/plain; charset=US-ASCII; format=flowed To: Linux/PPC Development From: Andy Fleming Date: Tue, 5 Apr 2005 11:21:52 -0500 Subject: Perfmon feature List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , I'm adding oprofile support for 7450 (and derivative) processors, and I'm considering adding a couple PPC_FEATURE bits (one for classic, and one for fsl-book-e perfmon). Reasons: 1) The need to distinguish between Freescale Book-E processors with performance monitor support, Classic PPC processors with perfmon support, and processors without perfmon support. (ie - 7450 parts will have support, but 7410 parts will not for now). 2) Applications could determine if these features were present, and decide between using mfspr and mfpmr instructions to read the counters from user-space. Thoughts, objections? Andy Fleming Open Source Team Freescale Semiconductor, Inc