From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx3-rdu2.redhat.com ([66.187.233.73] helo=mx1.redhat.com) by Galois.linutronix.de with esmtps (TLS1.2:DHE_RSA_AES_256_CBC_SHA256:256) (Exim 4.80) (envelope-from ) id 1fRLXv-0000TH-OC for speck@linutronix.de; Fri, 08 Jun 2018 19:51:32 +0200 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.rdu2.redhat.com [10.11.54.6]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 7DEBBBB42D for ; Fri, 8 Jun 2018 17:51:25 +0000 (UTC) Received: from treble (ovpn-120-53.rdu2.redhat.com [10.10.120.53]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 5044B20287C1 for ; Fri, 8 Jun 2018 17:51:25 +0000 (UTC) Date: Fri, 8 Jun 2018 12:51:23 -0500 From: Josh Poimboeuf Subject: [MODERATED] Re: [patch V2 00/12] cpu/hotplug: SMT control Message-ID: <20180608175123.lgjdogcsy5jhil3w@treble> References: <20180606192714.754943543@linutronix.de> MIME-Version: 1.0 In-Reply-To: <20180606192714.754943543@linutronix.de> Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit To: speck@linutronix.de List-ID: On Wed, Jun 06, 2018 at 09:27:14PM +0200, speck for Thomas Gleixner wrote: > The following series is a reworked version of the initial proof of concept > patch. The main changes are: > > - The primary sibling evaluation has been changed to use APIC ID, so the > hacky stuff is gone. > > - The control has now 3 states: on, off, forceoff > > forceoff is a irreversible operation and if given on the command line > via 'nosmt=force' it makes the processor/APIC enumeration code discard > the non primary siblings. That affects also the number of possible CPUs > and is more or less equivalent to disabling SMT in the BIOS. > > If 'forceoff' is written to the sysfs file, then the non primamry > siblings are offlined as with 'off', but the operation cannot be > undone. That has obviously no effect on num_possible_cpus as that has > been evaluated in the early boot process. > > - Command line and sysfs interface are documented > > Survived testing on various Intel and AMD machines and in VMs of different > flavours and topology configurations. > > Applies on top of Linus tree. If smt is disabled, should it be reported in the 'l1tf' vulnerabilities file? -- Josh