Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754073AbYK0LgO (ORCPT ); Thu, 27 Nov 2008 06:36:14 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751272AbYK0Lf5 (ORCPT ); Thu, 27 Nov 2008 06:35:57 -0500 Received: from fk-out-0910.google.com ([209.85.128.185]:42217 "EHLO fk-out-0910.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750742AbYK0Lf4 (ORCPT ); Thu, 27 Nov 2008 06:35:56 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=message-id:date:from:reply-to:to:subject:cc:in-reply-to :mime-version:content-type:content-transfer-encoding :content-disposition:references; b=YM7x9HiSkR9cG8SCblp7QR7Ej1v7m1ZS5KFv7WbHS0zpHy/MDauRK1uxeBjmeUpGao g8TLtpt49JlNkTooPTmJLJOUTLfJ8BFEcfCc9i+AaLyb7P/VYlwkFqKeMGAyUt+IF6n4 QFWv0BJvbAgE22SBMX3+ccglzi/Yfp7nKK/Gc= Message-ID: <7c86c4470811270335p2dbd61ebpe2c584e32d8b2292@mail.gmail.com> Date: Thu, 27 Nov 2008 12:35:54 +0100 From: "stephane eranian" Reply-To: eranian@gmail.com To: "Andi Kleen" Subject: Re: [patch 05/24] perfmon: X86 generic code (x86) Cc: "Thomas Gleixner" , linux-kernel@vger.kernel.org, akpm@linux-foundation.org, mingo@elte.hu, x86@kernel.org, sfr@canb.auug.org.au In-Reply-To: <20081127113115.GH6703@one.firstfloor.org> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <492d0be1.09cc660a.0b75.44b7@mx.google.com> <20081126140054.GX6703@one.firstfloor.org> <20081127100602.GF6703@one.firstfloor.org> <7c86c4470811270209q18d4e83aq8901837159838cc4@mail.gmail.com> <20081127113115.GH6703@one.firstfloor.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1552 Lines: 34 On Thu, Nov 27, 2008 at 12:31 PM, Andi Kleen wrote: >> The only reason why I have to deal with NMI is not so much to allow >> for profiling irq-off regions but because I have to share the PMU with >> the NMI watchdog. Otherwise I'd have to fail or disable the NMI watchdog >> on the fly. > > The NMI watchdog is now off by default so failing with it enabled > is fine. Yes, but most likely it is on in distro kernels. > > Longer term having NMI profiling is still a useful feature I think, > but of course it needs to be implemented cleanly. > The difficulty with NMI is locking. Unlike Oprofile, perfmon code needs locking. If you recall our discussion yesterday about passing the file descriptor around or even using it with multiple threads inside the same process. You have to handle the case where the NMI fires while you are holding a perfmon lock. What you have in the patch (and the the fully-featured version) is that we get the NMI and we stop the PMU WITHOUT grabbing any perfmon lock, and the we repost the interrupt with the regular vector. We also make sure we grab the RIP at NMI. That is the one we want to see reported in the sampling buffer. I am still wondering how Oprofile handles the case where multiple processes or threads access the same file descriptor. -- 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/