Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933551AbcJZR6E (ORCPT ); Wed, 26 Oct 2016 13:58:04 -0400 Received: from mail-oi0-f67.google.com ([209.85.218.67]:32836 "EHLO mail-oi0-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932334AbcJZR6D (ORCPT ); Wed, 26 Oct 2016 13:58:03 -0400 MIME-Version: 1.0 In-Reply-To: References: From: Linus Torvalds Date: Wed, 26 Oct 2016 10:58:01 -0700 X-Google-Sender-Auth: uHJTTKkWT58IFIAo3ZazHRcZbDU Message-ID: Subject: Re: CONFIG_VMAP_STACK, on-stack struct, and wake_up_bit To: Andy Lutomirski Cc: Andreas Gruenbacher , Peter Zijlstra , Andy Lutomirski , LKML , Bob Peterson , Steven Whitehouse , Mel Gorman , linux-mm Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 978 Lines: 22 On Wed, Oct 26, 2016 at 10:15 AM, Linus Torvalds wrote: > > Oh, and the patch is obviously entirely untested. I wouldn't want to > ruin my reputation by *testing* the patches I send out. What would be > the fun in that? So I tested it. It compiles, and it actually also solves the performance problem I was complaining about a couple of weeks ago with "unlock_page()" having an insane 3% CPU overhead when doing lots of small script ("make -j16 test" in the git tree for those that weren't involved in the original thread three weeks ago). So quite frankly, I'll just commit it. It should fix the new problem with gfs2 and CONFIG_VMAP_STACK, and I see no excuse for the crazy zone stuff considering how harmful it is to everybody else. I expect that when the NUMA people complain about page locking (if they ever even notice), PeterZ will stand up like the hero he is, and say "look here, I can solve this for you". Linus