Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751876AbbBURaM (ORCPT ); Sat, 21 Feb 2015 12:30:12 -0500 Received: from mail.skyhub.de ([78.46.96.112]:53708 "EHLO mail.skyhub.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751662AbbBURaK (ORCPT ); Sat, 21 Feb 2015 12:30:10 -0500 Date: Sat, 21 Feb 2015 18:29:14 +0100 From: Borislav Petkov To: Ingo Molnar Cc: Andy Lutomirski , Oleg Nesterov , Rik van Riel , x86@kernel.org, linux-kernel@vger.kernel.org, Linus Torvalds Subject: Re: [RFC PATCH] x86, fpu: Use eagerfpu by default on all CPUs Message-ID: <20150221172914.GB32073@pd.tnic> References: <20150221093150.GA27841@gmail.com> <20150221163840.GA32073@pd.tnic> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: <20150221163840.GA32073@pd.tnic> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1349 Lines: 37 On Sat, Feb 21, 2015 at 05:38:40PM +0100, Borislav Petkov wrote: > My assumption is that libc uses SSE for memcpy and thus the FPU will > be used. (I'll trace FPU-specific PMCs later to confirm). Ok, so I slapped a trace_printk() at the beginning of fpu_save_init() and did a kernel build once with default 3.19 and once with Andy's patch. So we end up with this count: default: 712000 eager: 780000 This would explain the very small difference in the performance counters data from the previous email. Provided I've not made a mistake, this leads me to think that this simple workload and pretty much everything else uses the FPU through glibc which does the SSE memcpy and so on. Which basically kills the whole idea behind lazy FPU as practically you don't really encounter workloads nowadays which don't use the FPU thanks to glibc and the lazy strategy doesn't really bring anything. Which would then mean, we don't really need the lazy handling as userspace is making it eager, so to speak, for us. Thoughts? -- Regards/Gruss, Boris. ECO tip #101: Trim your mails when you reply. -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/