From patchwork Mon Oct 4 15:56:31 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Gleb Natapov X-Patchwork-Id: 228721 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter1.kernel.org (8.14.4/8.14.3) with ESMTP id o94HOq1l004239 for ; Mon, 4 Oct 2010 17:25:23 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756578Ab0JDP5l (ORCPT ); Mon, 4 Oct 2010 11:57:41 -0400 Received: from mx1.redhat.com ([209.132.183.28]:18084 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756378Ab0JDP5H (ORCPT ); Mon, 4 Oct 2010 11:57:07 -0400 Received: from int-mx01.intmail.prod.int.phx2.redhat.com (int-mx01.intmail.prod.int.phx2.redhat.com [10.5.11.11]) by mx1.redhat.com (8.13.8/8.13.8) with ESMTP id o94FubZ0019977 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Mon, 4 Oct 2010 11:56:37 -0400 Received: from dhcp-1-237.tlv.redhat.com (dhcp-1-237.tlv.redhat.com [10.35.1.237]) by int-mx01.intmail.prod.int.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id o94FuafD028045; Mon, 4 Oct 2010 11:56:36 -0400 Received: by dhcp-1-237.tlv.redhat.com (Postfix, from userid 13519) id 7FFC118D478; Mon, 4 Oct 2010 17:56:34 +0200 (IST) From: Gleb Natapov To: kvm@vger.kernel.org Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, avi@redhat.com, mingo@elte.hu, a.p.zijlstra@chello.nl, tglx@linutronix.de, hpa@zytor.com, riel@redhat.com, cl@linux-foundation.org, mtosatti@redhat.com Subject: [PATCH v6 09/12] Inject asynchronous page fault into a PV guest if page is swapped out. Date: Mon, 4 Oct 2010 17:56:31 +0200 Message-Id: <1286207794-16120-10-git-send-email-gleb@redhat.com> In-Reply-To: <1286207794-16120-1-git-send-email-gleb@redhat.com> References: <1286207794-16120-1-git-send-email-gleb@redhat.com> X-Scanned-By: MIMEDefang 2.67 on 10.5.11.11 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter1.kernel.org [140.211.167.41]); Mon, 04 Oct 2010 17:25:24 +0000 (UTC) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index de31551..2f6fc87 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -419,6 +419,7 @@ struct kvm_vcpu_arch { gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)]; struct gfn_to_hva_cache data; u64 msr_val; + u32 id; } apf; }; @@ -594,6 +595,7 @@ struct kvm_x86_ops { }; struct kvm_arch_async_pf { + u32 token; gfn_t gfn; }; @@ -842,6 +844,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); +bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu); extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d85fda8..de53cab 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2580,6 +2580,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) { struct kvm_arch_async_pf arch; + arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; arch.gfn = gfn; return kvm_setup_async_pf(vcpu, gva, gfn, &arch); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3e123ab..0e69d37 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6225,25 +6225,58 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) } } +static int apf_put_user(struct kvm_vcpu *vcpu, u32 val) +{ + + return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val, + sizeof(val)); +} + void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { - vcpu->arch.mp_state = KVM_MP_STATE_HALTED; - - if (work == kvm_double_apf) + if (work == kvm_double_apf) { trace_kvm_async_pf_doublefault(kvm_rip_read(vcpu)); - else { - trace_kvm_async_pf_not_present(work->gva); - + vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + } else { + trace_kvm_async_pf_not_present(work->arch.token, work->gva); kvm_add_async_pf_gfn(vcpu, work->arch.gfn); + + if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) || + kvm_x86_ops->get_cpl(vcpu) == 0) + vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) { + vcpu->arch.fault.error_code = 0; + vcpu->arch.fault.address = work->arch.token; + kvm_inject_page_fault(vcpu); + } } } void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) { - trace_kvm_async_pf_ready(work->gva); - kvm_del_async_pf_gfn(vcpu, work->arch.gfn); + trace_kvm_async_pf_ready(work->arch.token, work->gva); + if (is_error_page(work->page)) + work->arch.token = ~0; /* broadcast wakeup */ + else + kvm_del_async_pf_gfn(vcpu, work->arch.gfn); + + if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) && + !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) { + vcpu->arch.fault.error_code = 0; + vcpu->arch.fault.address = work->arch.token; + kvm_inject_page_fault(vcpu); + } +} + +bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) + return true; + else + return !kvm_event_needs_reinjection(vcpu) && + kvm_x86_ops->interrupt_allowed(vcpu); } EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index bcc69b2..dd44aa3 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -204,34 +204,39 @@ TRACE_EVENT( TRACE_EVENT( kvm_async_pf_not_present, - TP_PROTO(u64 gva), - TP_ARGS(gva), + TP_PROTO(u64 token, u64 gva), + TP_ARGS(token, gva), TP_STRUCT__entry( + __field(__u64, token) __field(__u64, gva) ), TP_fast_assign( + __entry->token = token; __entry->gva = gva; ), - TP_printk("gva %#llx not present", __entry->gva) + TP_printk("token %#llx gva %#llx not present", __entry->token, + __entry->gva) ); TRACE_EVENT( kvm_async_pf_ready, - TP_PROTO(u64 gva), - TP_ARGS(gva), + TP_PROTO(u64 token, u64 gva), + TP_ARGS(token, gva), TP_STRUCT__entry( + __field(__u64, token) __field(__u64, gva) ), TP_fast_assign( + __entry->token = token; __entry->gva = gva; ), - TP_printk("gva %#llx ready", __entry->gva) + TP_printk("token %#llx gva %#llx ready", __entry->token, __entry->gva) ); TRACE_EVENT( diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 44f4005..d1cd495 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -138,7 +138,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) } } - if (list_empty_careful(&vcpu->async_pf.done)) + if (list_empty_careful(&vcpu->async_pf.done) || + !kvm_arch_can_inject_async_page_present(vcpu)) return; spin_lock(&vcpu->async_pf.lock);