From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751857AbeCXBBK (ORCPT ); Fri, 23 Mar 2018 21:01:10 -0400 Received: from mail-pl0-f66.google.com ([209.85.160.66]:33076 "EHLO mail-pl0-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751400AbeCXBBJ (ORCPT ); Fri, 23 Mar 2018 21:01:09 -0400 X-Google-Smtp-Source: AG47ELvF+RswVCl5v7JAynO0BukZHkK0NmTv6etByZLQfPAT/OcOoOD322PhLWkfqdQFsA/2uadQVg== Subject: Re: [PATCH v3 2/2] x86, cpuid: allow cpuid_read() to schedule To: "H. Peter Anvin" , Eric Dumazet , x86 Cc: lkml , Thomas Gleixner , Borislav Petkov , Ingo Molnar , Hugh Dickins References: <20180323215818.127774-1-edumazet@google.com> <20180323215818.127774-2-edumazet@google.com> <3622b64c-bae6-00db-6a61-3ccf760144aa@zytor.com> From: Eric Dumazet Message-ID: Date: Fri, 23 Mar 2018 18:01:07 -0700 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.6.0 MIME-Version: 1.0 In-Reply-To: <3622b64c-bae6-00db-6a61-3ccf760144aa@zytor.com> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 03/23/2018 03:17 PM, H. Peter Anvin wrote: > On 03/23/18 14:58, Eric Dumazet wrote: >> I noticed high latencies caused by a daemon periodically reading various >> MSR and cpuid on all cpus. KASAN kernels would see ~10ms latencies >> simply reading one cpuid. Even without KASAN, sending IPI to CPU >> in deep sleep state or blocking hard IRQ in a a long section, >> then waiting for the answer can consume hundreds of usec or more. >> >> Switching to smp_call_function_single_async() and a completion >> allows to reschedule and not burn cpu cycles. > > That being said, the Right Way for a daemon to read multiple MSRs and > CPUIDs on multiple CPUs is to spawn a thread for each CPU and use CPU > affinity to lock them down. No IPI is needed to access MSRs on the > current CPU, and CPUID doesn't even need kernel entry. Indeed, assuming a daemon can have threads running on all cpus :/ Some environments like to partition cpus for different jobs/containers. Yes, we can avoid IPI by carefully re-designing these user programs.