Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751536AbdF1M0E (ORCPT ); Wed, 28 Jun 2017 08:26:04 -0400 Received: from mail-pg0-f67.google.com ([74.125.83.67]:34127 "EHLO mail-pg0-f67.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751638AbdF1MZZ (ORCPT ); Wed, 28 Jun 2017 08:25:25 -0400 From: Wanpeng Li X-Google-Original-From: Wanpeng Li To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org Cc: Paolo Bonzini , =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= , Wanpeng Li Subject: [PATCH v6 2/4] KVM: async_pf: Add L1 guest async_pf #PF vmexit handler Date: Wed, 28 Jun 2017 05:25:10 -0700 Message-Id: <1498652712-10283-3-git-send-email-wanpeng.li@hotmail.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1498652712-10283-1-git-send-email-wanpeng.li@hotmail.com> References: <1498652712-10283-1-git-send-email-wanpeng.li@hotmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6639 Lines: 202 From: Wanpeng Li This patch adds the L1 guest async page fault #PF vmexit handler, such #PF is converted into vmexit from L2 to L1 on #PF which is then handled by L1 similar to ordinary async page fault. Cc: Paolo Bonzini Cc: Radim Krčmář Signed-off-by: Wanpeng Li --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.c | 33 +++++++++++++++++++++++++++++++++ arch/x86/kvm/mmu.h | 2 ++ arch/x86/kvm/svm.c | 36 +++++------------------------------- arch/x86/kvm/vmx.c | 12 +++++------- 5 files changed, 46 insertions(+), 38 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1f01bfb..e20d8a8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -645,6 +645,7 @@ struct kvm_vcpu_arch { u64 msr_val; u32 id; bool send_user_only; + u32 host_apf_reason; } apf; /* OSVW MSRs (AMD only) */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index cb82259..4a7dc00 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -46,6 +46,7 @@ #include #include #include +#include "trace.h" /* * When setting this variable to true it enables Two-Dimensional-Paging @@ -3736,6 +3737,38 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return false; } +int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, + u64 fault_address) +{ + int r = 1; + + switch (vcpu->arch.apf.host_apf_reason) { + default: + /* TDP won't cause page fault directly */ + WARN_ON_ONCE(tdp_enabled); + trace_kvm_page_fault(fault_address, error_code); + + if (kvm_event_needs_reinjection(vcpu)) + kvm_mmu_unprotect_page_virt(vcpu, fault_address); + r = kvm_mmu_page_fault(vcpu, fault_address, error_code, NULL, 0); + break; + case KVM_PV_REASON_PAGE_NOT_PRESENT: + vcpu->arch.apf.host_apf_reason = 0; + local_irq_disable(); + kvm_async_pf_task_wait(fault_address); + local_irq_enable(); + break; + case KVM_PV_REASON_PAGE_READY: + vcpu->arch.apf.host_apf_reason = 0; + local_irq_disable(); + kvm_async_pf_task_wake(fault_address); + local_irq_enable(); + break; + } + return r; +} +EXPORT_SYMBOL_GPL(kvm_handle_page_fault); + static bool check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) { diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 330bf3a..2ae88f0 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -77,6 +77,8 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty); bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); +int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, + u64 fault_address); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index e1f8e89..8f263bf 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -192,7 +192,6 @@ struct vcpu_svm { unsigned int3_injected; unsigned long int3_rip; - u32 apf_reason; /* cached guest cpuid flags for faster access */ bool nrips_enabled : 1; @@ -2071,34 +2070,9 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) static int pf_interception(struct vcpu_svm *svm) { u64 fault_address = svm->vmcb->control.exit_info_2; - u64 error_code; - int r = 1; + u64 error_code = svm->vmcb->control.exit_info_1; - switch (svm->apf_reason) { - default: - error_code = svm->vmcb->control.exit_info_1; - - trace_kvm_page_fault(fault_address, error_code); - if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu)) - kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); - r = kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code, - svm->vmcb->control.insn_bytes, - svm->vmcb->control.insn_len); - break; - case KVM_PV_REASON_PAGE_NOT_PRESENT: - svm->apf_reason = 0; - local_irq_disable(); - kvm_async_pf_task_wait(fault_address); - local_irq_enable(); - break; - case KVM_PV_REASON_PAGE_READY: - svm->apf_reason = 0; - local_irq_disable(); - kvm_async_pf_task_wake(fault_address); - local_irq_enable(); - break; - } - return r; + return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address); } static int db_interception(struct vcpu_svm *svm) @@ -2551,7 +2525,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) break; case SVM_EXIT_EXCP_BASE + PF_VECTOR: /* When we're shadowing, trap PFs, but not async PF */ - if (!npt_enabled && svm->apf_reason == 0) + if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0) return NESTED_EXIT_HOST; break; default: @@ -2594,7 +2568,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm) vmexit = NESTED_EXIT_DONE; /* async page fault always cause vmexit */ else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && - svm->apf_reason != 0) + svm->vcpu.arch.apf.host_apf_reason != 0) vmexit = NESTED_EXIT_DONE; break; } @@ -4891,7 +4865,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) /* if exit due to PF check for async PF */ if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) - svm->apf_reason = kvm_read_and_reset_pf_reason(); + svm->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); if (npt_enabled) { vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index df825bb..d20f794 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -5648,14 +5648,8 @@ static int handle_exception(struct kvm_vcpu *vcpu) } if (is_page_fault(intr_info)) { - /* EPT won't cause page fault directly */ - BUG_ON(enable_ept); cr2 = vmcs_readl(EXIT_QUALIFICATION); - trace_kvm_page_fault(cr2, error_code); - - if (kvm_event_needs_reinjection(vcpu)) - kvm_mmu_unprotect_page_virt(vcpu, cr2); - return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0); + return kvm_handle_page_fault(vcpu, error_code, cr2); } ex_no = intr_info & INTR_INFO_VECTOR_MASK; @@ -8602,6 +8596,10 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); exit_intr_info = vmx->exit_intr_info; + /* if exit due to PF check for async PF */ + if (is_page_fault(exit_intr_info)) + vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason(); + /* Handle machine checks before interrupts are enabled */ if (is_machine_check(exit_intr_info)) kvm_machine_check(); -- 2.7.4