From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752103AbbAMQvo (ORCPT ); Tue, 13 Jan 2015 11:51:44 -0500 Received: from mx1.redhat.com ([209.132.183.28]:50887 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750976AbbAMQvn (ORCPT ); Tue, 13 Jan 2015 11:51:43 -0500 Date: Tue, 13 Jan 2015 17:50:43 +0100 From: Oleg Nesterov To: Rik van Riel Cc: linux-kernel@vger.kernel.org, mingo@redhat.com, hpa@zytor.com, matt.fleming@intel.com, bp@suse.de, pbonzini@redhat.com, tglx@linutronix.de, luto@amacapital.net Subject: Re: [RFC PATCH 05/11] x86,fpu: ensure FPU state is reloaded from memory if task is traced Message-ID: <20150113165043.GA26931@redhat.com> References: <1421012793-30106-1-git-send-email-riel@redhat.com> <1421012793-30106-6-git-send-email-riel@redhat.com> <20150113161938.GA24447@redhat.com> <54B548EA.7020005@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <54B548EA.7020005@redhat.com> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 01/13, Rik van Riel wrote: > > >> @@ -412,8 +412,14 @@ static inline void switch_fpu_prepare(struct > >> task_struct *old, struct task_struc bool preload = > >> tsk_used_math(new) && (use_eager_fpu() || new->thread.fpu_counter > >> > 5); if (__thread_has_fpu(old)) { - if (!__save_init_fpu(old)) > >> + /* + * Make sure the FPU state is restored from memory next > >> time, + * if the task has an FPU exception pending, or the > >> task's in + * memory FPU state could be changed by a debugger. > >> + */ + if (!__save_init_fpu(old) || > >> task_is_stopped_or_traced(old)) cpu = ~0; > > > > Well, if debugger wants to change FPU state, it should call > > init_fpu() which resets .last_cpu ? > > Does the ptrace (and utrace, and ... ) code actually do that? Yes, see xfpregs_get/set. So I think this change is not needed (but I didn't look at the next patches). Oleg.