From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754237Ab1LUWdW (ORCPT ); Wed, 21 Dec 2011 17:33:22 -0500 Received: from merlin.infradead.org ([205.233.59.134]:51641 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751071Ab1LUWdT convert rfc822-to-8bit (ORCPT ); Wed, 21 Dec 2011 17:33:19 -0500 Message-ID: <1324506779.17070.23.camel@twins> Subject: Re: [RFC][PATCH 0/6] perf: x86 RDPMC and RDTSC support From: Peter Zijlstra To: Vince Weaver Cc: Vince Weaver , mingo@elte.hu, William Cohen , Stephane Eranian , Arun Sharma , linux-kernel@vger.kernel.org Date: Wed, 21 Dec 2011 23:32:59 +0100 In-Reply-To: References: <20111121145114.049265181@chello.nl> <1324472337.10752.11.camel@twins> <1324503667.17070.7.camel@twins> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8BIT X-Mailer: Evolution 3.2.1- Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 2011-12-21 at 17:19 -0500, Vince Weaver wrote: > > Speaking of bit 48, does your implementation do anything useful about > the 32/40/48 bit limitation that some processors have with rdpmc? > Or is the answer that if you might get overflow, then you have to use slow > syscall-based read? Yeah, we program an overflow interrupt around there (47 bits iirc) and consume the total into the u64 count value and update the mmap control page's offset.