Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758035Ab1DMPzb (ORCPT ); Wed, 13 Apr 2011 11:55:31 -0400 Received: from kroah.org ([198.145.64.141]:54311 "EHLO coco.kroah.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757920Ab1DMPzZ (ORCPT ); Wed, 13 Apr 2011 11:55:25 -0400 X-Mailbox-Line: From gregkh@clark.kroah.org Wed Apr 13 08:51:45 2011 Message-Id: <20110413155145.738074242@clark.kroah.org> User-Agent: quilt/0.48-16.4 Date: Wed, 13 Apr 2011 08:50:50 -0700 From: Greg KH To: linux-kernel@vger.kernel.org, stable@kernel.org Cc: stable-review@kernel.org, torvalds@linux-foundation.org, akpm@linux-foundation.org, alan@lxorguk.ukuu.org.uk, Suresh Siddha , Eric Anholt , "H. Peter Anvin" Subject: [26/74] x86, mtrr, pat: Fix one cpu getting out of sync during resume In-Reply-To: <20110413155406.GA22568@kroah.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3689 Lines: 95 2.6.32-longterm review patch. If anyone has any objections, please let us know. ------------------ From: Suresh Siddha commit 84ac7cdbdd0f04df6b96153f7a79127fd6e45467 upstream. On laptops with core i5/i7, there were reports that after resume graphics workloads were performing poorly on a specific AP, while the other cpu's were ok. This was observed on a 32bit kernel specifically. Debug showed that the PAT init was not happening on that AP during resume and hence it contributing to the poor workload performance on that cpu. On this system, resume flow looked like this: 1. BP starts the resume sequence and we reinit BP's MTRR's/PAT early on using mtrr_bp_restore() 2. Resume sequence brings all AP's online 3. Resume sequence now kicks off the MTRR reinit on all the AP's. 4. For some reason, between point 2 and 3, we moved from BP to one of the AP's. My guess is that printk() during resume sequence is contributing to this. We don't see similar behavior with the 64bit kernel but there is no guarantee that at this point the remaining resume sequence (after AP's bringup) has to happen on BP. 5. set_mtrr() was assuming that we are still on BP and skipped the MTRR/PAT init on that cpu (because of 1 above) 6. But we were on an AP and this led to not reprogramming PAT on this cpu leading to bad performance. Fix this by doing unconditional mtrr_if->set_all() in set_mtrr() during MTRR/PAT init. This might be unnecessary if we are still running on BP. But it is of no harm and will guarantee that after resume, all the cpu's will be in sync with respect to the MTRR/PAT registers. Signed-off-by: Suresh Siddha LKML-Reference: <1301438292-28370-1-git-send-email-eric@anholt.net> Signed-off-by: Eric Anholt Tested-by: Keith Packard Signed-off-by: H. Peter Anvin Signed-off-by: Greg Kroah-Hartman --- arch/x86/kernel/cpu/mtrr/main.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -262,14 +262,24 @@ set_mtrr(unsigned int reg, unsigned long /* * HACK! - * We use this same function to initialize the mtrrs on boot. - * The state of the boot cpu's mtrrs has been saved, and we want - * to replicate across all the APs. - * If we're doing that @reg is set to something special... + * + * We use this same function to initialize the mtrrs during boot, + * resume, runtime cpu online and on an explicit request to set a + * specific MTRR. + * + * During boot or suspend, the state of the boot cpu's mtrrs has been + * saved, and we want to replicate that across all the cpus that come + * online (either at the end of boot or resume or during a runtime cpu + * online). If we're doing that, @reg is set to something special and on + * this cpu we still do mtrr_if->set_all(). During boot/resume, this + * is unnecessary if at this point we are still on the cpu that started + * the boot/resume sequence. But there is no guarantee that we are still + * on the same cpu. So we do mtrr_if->set_all() on this cpu aswell to be + * sure that we are in sync with everyone else. */ if (reg != ~0U) mtrr_if->set(reg, base, size, type); - else if (!mtrr_aps_delayed_init) + else mtrr_if->set_all(); /* Wait for the others */ -- 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/