Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754660AbZKCUPF (ORCPT ); Tue, 3 Nov 2009 15:15:05 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753896AbZKCUPE (ORCPT ); Tue, 3 Nov 2009 15:15:04 -0500 Received: from mail-bw0-f227.google.com ([209.85.218.227]:55599 "EHLO mail-bw0-f227.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752586AbZKCUPC (ORCPT ); Tue, 3 Nov 2009 15:15:02 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=date:from:to:cc:subject:message-id:references:mime-version :content-type:content-disposition:in-reply-to:user-agent; b=Fzlh6lKa7ARCamdgWNK/k2U1h5L5aEvh+Z8oWVJ0GpVfAMl3yH9EwbRvYQb6CIOeqV AWDTTwBO7of6f+HNiJRHzz0xoMpudYuCP+MaA7NqGxX4GnD+PKy9Efa1E2yViH1zrTST 8Tf6VTIaZKpS14Ik4IuKeSQGCxT9AAcksHwgM= Date: Tue, 3 Nov 2009 21:15:06 +0100 From: Frederic Weisbecker To: Jan Kiszka Cc: Ingo Molnar , LKML , Prasad , Alan Stern , Peter Zijlstra , Arnaldo Carvalho de Melo , Steven Rostedt , Jiri Slaby , Li Zefan , Avi Kivity , Paul Mackerras , Mike Galbraith , Masami Hiramatsu , Paul Mundt Subject: Re: [PATCH 4/6] hw-breakpoints: Rewrite the hw-breakpoints layer on top of perf events Message-ID: <20091103201503.GA4962@nowhere> References: <1257275474-5285-1-git-send-email-fweisbec@gmail.com> <1257275474-5285-5-git-send-email-fweisbec@gmail.com> <4AF08B7C.8040903@web.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4AF08B7C.8040903@web.de> 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 Content-Length: 2308 Lines: 63 On Tue, Nov 03, 2009 at 08:58:52PM +0100, Jan Kiszka wrote: > Frederic Weisbecker wrote: > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > > index fc2974a..6560129 100644 > > --- a/arch/x86/kvm/x86.c > > +++ b/arch/x86/kvm/x86.c > > @@ -42,6 +42,7 @@ > > #define CREATE_TRACE_POINTS > > #include "trace.h" > > > > +#include > > #include > > #include > > #include > > @@ -3643,14 +3644,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) > > trace_kvm_entry(vcpu->vcpu_id); > > kvm_x86_ops->run(vcpu, kvm_run); > > > > - if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) { > > - set_debugreg(current->thread.debugreg[0], 0); > > - set_debugreg(current->thread.debugreg[1], 1); > > - set_debugreg(current->thread.debugreg[2], 2); > > - set_debugreg(current->thread.debugreg[3], 3); > > - set_debugreg(current->thread.debugreg6, 6); > > - set_debugreg(current->thread.debugreg7, 7); > > - } > > + /* > > + * CHECKME: is vcpu->arch.switch_db_regs sufficient to check > > + * if the guest is using breakpoints? If so we may want to do > > + * this check before. > > + */ > > + hw_breakpoint_restore(); > > Obviously, this variant will make KVM users very unhappy. But trying to > reduce this performance regression via vcpu->arch.switch_db_regs will > make hw-breakpoint users unhappy: KVM leaves at least dr7 clobbered > behind, even if the guest does not use breakpoints. Yeah, that's why I've made unconditionally. At least it works in every cases, but this is temporary. > We really need a replacement for TIF_DEBUG (but we only need this [1]). > > Jan > > [1]http://thread.gmane.org/gmane.comp.emulators.kvm.devel/39784/focus=39827 > Thinking about it, this check should cover every cases: if (vcpu->arch.switch_db_regs || __get_cpu_var(dr7) & DR_GLOBAL_ENABLE_MASK) If we have __get_cpu_var(dr7) & DR_GLOBAL_ENABLE_MASK, it means there is an active breakpoint and then we should restore the current state. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/