From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marcelo Tosatti Subject: Re: cr3 OOS optimisation breaks 32-bit GNU/kFreeBSD guest Date: Tue, 24 Mar 2009 08:49:21 -0300 Message-ID: <20090324114921.GA8043@amt.cnet> References: <20090223003305.GW12976@hall.aurel32.net> <20090320231405.GA26415@amt.cnet> <49C60644.2090904@redhat.com> <20090323172725.GA28775@amt.cnet> <49C8AC35.3030803@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Aurelien Jarno , kvm@vger.kernel.org To: Avi Kivity Return-path: Received: from mx2.redhat.com ([66.187.237.31]:36735 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753270AbZCXLti (ORCPT ); Tue, 24 Mar 2009 07:49:38 -0400 Content-Disposition: inline In-Reply-To: <49C8AC35.3030803@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On Tue, Mar 24, 2009 at 11:47:33AM +0200, Avi Kivity wrote: > Marcelo Tosatti wrote: >>> Maybe it's best to resync when relinking a global page? >>> >> >> How about this. It will shorten the unsync period of global pages, >> unfortunately. >> >> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c >> index 2a36f7f..bccdcc7 100644 >> --- a/arch/x86/kvm/mmu.c >> +++ b/arch/x86/kvm/mmu.c >> @@ -1238,6 +1238,10 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, >> set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests); >> kvm_mmu_mark_parents_unsync(vcpu, sp); >> } >> + if (role.level != PT_PAGE_TABLE_LEVEL && >> + !list_empty(&vcpu->kvm->arch.oos_global_pages)) >> + set_bit(KVM_REQ_MMU_GLOBAL_SYNC, &vcpu->requests); >> + >> pgprintk("%s: found\n", __func__); >> return sp; >> } >> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c >> index 2ea8262..48169d7 100644 >> --- a/arch/x86/kvm/x86.c >> +++ b/arch/x86/kvm/x86.c >> @@ -3109,6 +3109,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) >> kvm_write_guest_time(vcpu); >> if (test_and_clear_bit(KVM_REQ_MMU_SYNC, &vcpu->requests)) >> kvm_mmu_sync_roots(vcpu); >> + if (test_and_clear_bit(KVM_REQ_MMU_GLOBAL_SYNC, &vcpu->requests)) >> + kvm_mmu_sync_global(vcpu); >> if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) >> kvm_x86_ops->tlb_flush(vcpu); >> if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS > > Windows will (I think) write a PDE on every context switch, so this > effectively disables global unsync for that guest. > > What about recursively syncing the newly linked page in FNAME(fetch)()? > If the page isn't global, this becomes a no-op, so no new overhead. The > only question is the expense when linking a populated top-level page, > especially in long mode. Yes, I started doing that but it touches the nice fastpath in fetch(). I'll see if I can come up with something and with numbers. Thanks