From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935237AbaFTR2c (ORCPT ); Fri, 20 Jun 2014 13:28:32 -0400 Received: from mx1.redhat.com ([209.132.183.28]:28976 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756777AbaFTR23 (ORCPT ); Fri, 20 Jun 2014 13:28:29 -0400 From: Prarit Bhargava To: linux-kernel@vger.kernel.org Cc: Prarit Bhargava , Oren Twaig , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , x86@kernel.org, Borislav Petkov , Paul Gortmaker , Andrew Morton , Andi Kleen , Dave Jones , Torsten Kaiser , Jan Beulich , Jan Kiszka , Toshi Kani , Andrew Jones Subject: [PATCH 0/2] Fixes for smp_num_siblings calculation Date: Fri, 20 Jun 2014 13:27:31 -0400 Message-Id: <1403285253-25547-1-git-send-email-prarit@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org I have a system on which I have disabled threading in the BIOS, and I am booting the kernel with the option "idle=poll". The kernel displays process: WARNING: polling idle and HT enabled, performance may degrade which is incorrect -- I've already disabled HT. This warning is issued here: void select_idle_routine(const struct cpuinfo_x86 *c) { if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1) pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); >>From my understanding of the other areas of kernel that use smp_num_siblings, the value is supposed to be the actual number of threads per core, and this value of smp_num_siblings is incorrect. In theory, it should be 1 but it is reported as 2. When I looked into how smp_num_siblings is calculated I found the following call sequence in the kernel: start_kernel -> check_bugs -> identify_boot_cpu -> identify_cpu -> c_init = init_intel init_intel -> detect_extended_topology (sets value) OR c_init = init_amd init_amd -> amd_detect_cmp -> amd_get_topology (sets value) -> detect_ht() ... (sets value) detect_ht() (also sets value) ie) it is confusing to figure out where smp_num_siblings is set, and AFAICT, it is set to the "factory reported" value. This patchset sets smp_num_siblings to the expected value of the actual number of siblings each core has. The 2/2 patchset, disables the "ht" flag if each core has only one sibling. Cc: Oren Twaig Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: x86@kernel.org Cc: Borislav Petkov Cc: Paul Gortmaker Cc: Andrew Morton Cc: Andi Kleen Cc: Dave Jones Cc: Torsten Kaiser Cc: Jan Beulich Cc: Jan Kiszka Cc: Toshi Kani Cc: Andrew Jones Signed-off-by: Prarit Bhargava Prarit Bhargava (2): x86, Clean up smp_num_siblings calculation x86, disable ht flag when hyperthreading is disabled arch/x86/kernel/cpu/amd.c | 1 - arch/x86/kernel/cpu/common.c | 23 +++++++++++------------ arch/x86/kernel/cpu/topology.c | 2 +- arch/x86/kernel/smpboot.c | 14 +++++++++++--- 4 files changed, 23 insertions(+), 17 deletions(-) -- 1.7.9.3