From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753207AbeFAS4c (ORCPT ); Fri, 1 Jun 2018 14:56:32 -0400 Received: from shelob.surriel.com ([96.67.55.147]:45048 "EHLO shelob.surriel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751964AbeFAS4b (ORCPT ); Fri, 1 Jun 2018 14:56:31 -0400 Message-ID: <1527879389.7898.84.camel@surriel.com> Subject: Re: 4.13..4.14 scheduling overhead regression (bisected - b956575bed91) From: Rik van Riel To: Peter Zijlstra , Mike Galbraith Cc: LKML , Andy Lutomirski Date: Fri, 01 Jun 2018 14:56:29 -0400 In-Reply-To: <20180601132055.GT12198@hirez.programming.kicks-ass.net> References: <1527857873.4674.11.camel@gmx.de> <20180601132055.GT12198@hirez.programming.kicks-ass.net> Content-Type: multipart/signed; micalg="pgp-sha256"; protocol="application/pgp-signature"; boundary="=-ib3fbF7sKiIwG+QUOToN" X-Mailer: Evolution 3.26.6 (3.26.6-1.fc27) Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --=-ib3fbF7sKiIwG+QUOToN Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Fri, 2018-06-01 at 15:20 +0200, Peter Zijlstra wrote: > On Fri, Jun 01, 2018 at 02:57:53PM +0200, Mike Galbraith wrote: > > b956575bed91ecfb136a8300742ecbbf451471ab is the first bad commit > > commit b956575bed91ecfb136a8300742ecbbf451471ab > > Author: Andy Lutomirski > > Date: Mon Oct 9 09:50:49 2017 -0700 > >=20 > > x86/mm: Flush more aggressively in lazy TLB mode >=20 > Oh boy... Maybe we should start looking at that optimization Andy > mentioned. >=20 > IIRC all page freeing does indeed go through tlb_remove_page(), it > shouldn't be too hard to make that work. Page freeing does. However, page table freeing does not, and might need to be done in a different way. I wonder how expensive/effective it would be to free page tables with RCU, and have the RCU code flush the TLB if it notices the ctx_id is wrong? Also, I need to go find Andy's optimization, and see how it works :) --=20 All Rights Reversed. --=-ib3fbF7sKiIwG+QUOToN Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- iQEzBAABCAAdFiEEKR73pCCtJ5Xj3yADznnekoTE3oMFAlsRlt0ACgkQznnekoTE 3oOcxggAukRp10h7m2BYQNVEleXsqhmQGT+TzLluK21kjfVqUoRfvrEChQP327v6 D2Adxy1siRPPUNI6v3LymUXHhrtgV0Xy3A11oNvMRFNI1R2C9+1u/ULLH3coWvdS 1DSsEQbU08SFAH9cY+dCR+dQkVyN65iZuNCModupSI21cyJgYk5yHtsDzpLgrgKF /OSE92cMS0PQppCarnNIqEhPP9ptFI0tcUDBz4DKF+YNU//yJayEeCDVN1Idn4kM rvTXNqQQ2JjPbsdfWqQWclLHR0q5rAxwV/cQkqY+1pVhc7X16/Yvjo0G9KyoXQmc rZ+iAeMbehSH1SwPbtr998TV8UtOcQ== =vOa3 -----END PGP SIGNATURE----- --=-ib3fbF7sKiIwG+QUOToN--