Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755981AbcCNTXk (ORCPT ); Mon, 14 Mar 2016 15:23:40 -0400 Received: from mail-ob0-f176.google.com ([209.85.214.176]:34418 "EHLO mail-ob0-f176.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755764AbcCNTXh (ORCPT ); Mon, 14 Mar 2016 15:23:37 -0400 MIME-Version: 1.0 In-Reply-To: References: <1445996397-32703-1-git-send-email-pbonzini@redhat.com> <1445996397-32703-4-git-send-email-pbonzini@redhat.com> From: Andy Lutomirski Date: Mon, 14 Mar 2016 12:23:17 -0700 Message-ID: Subject: Re: [PATCH 3/3] x86: context_tracking: avoid irq_save/irq_restore on kernel entry and exit To: Paolo Bonzini Cc: "linux-kernel@vger.kernel.org" , kvm list , Andy Lutomirski , Frederic Weisbecker , Rik van Riel , Paul McKenney Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 863 Lines: 19 On Tue, Oct 27, 2015 at 10:22 PM, Andy Lutomirski wrote: > On Tue, Oct 27, 2015 at 6:39 PM, Paolo Bonzini wrote: >> x86 always calls user_enter and user_exit with interrupt disabled. >> Therefore, it is not necessary to check for exceptions, nor to >> save/restore the IRQ state, when context tracking functions are >> called by guest_enter and guest_exit. >> >> Use the previously introduced __context_tracking_entry and >> __context_tracking_exit. > > x86 isn't ready for this yet. We could do a quick-and-dirty fix with > explicit IRQs-on-and-off much protected by the static key, or we could > just wait until I finish the syscall cleanup. I favor the latter, but > you're all welcome to do the former and I'll review it. > Once Linus pulls tip:x86/asm, x86 should be ready for this. Want to try again? --Andy