Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754869AbaGHNA6 (ORCPT ); Tue, 8 Jul 2014 09:00:58 -0400 Received: from cn.fujitsu.com ([59.151.112.132]:29969 "EHLO heian.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP id S1754254AbaGHNAv (ORCPT ); Tue, 8 Jul 2014 09:00:51 -0400 X-IronPort-AV: E=Sophos;i="5.00,856,1396972800"; d="scan'208";a="32994968" From: Tang Chen To: , , CC: , , , , , Subject: [PATCH v2 5/5] kvm, mem-hotplug: Do not pin apic access page in memory. Date: Tue, 8 Jul 2014 21:01:32 +0800 Message-ID: <1404824492-30095-6-git-send-email-tangchen@cn.fujitsu.com> X-Mailer: git-send-email 1.7.11.7 In-Reply-To: <1404824492-30095-1-git-send-email-tangchen@cn.fujitsu.com> References: <1404824492-30095-1-git-send-email-tangchen@cn.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.167.226.99] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org apic access page is pinned in memory. As a result, it cannot be migrated/hot-removed. Actually, it is not necessary to be pinned. The hpa of apic access page is stored in VMCS APIC_ACCESS_ADDR pointer. When the page is migrated, kvm_mmu_notifier_invalidate_page() will invalidate the corresponding ept entry. This patch introduces a new vcpu request named KVM_REQ_APIC_PAGE_RELOAD, and makes this request to all the vcpus at this time, and force all the vcpus exit guest, and re-enter guest till they updates the VMCS APIC_ACCESS_ADDR pointer to the new apic access page address, and updates kvm->arch.apic_access_page to the new page. Signed-off-by: Tang Chen --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.c | 11 +++++++++++ arch/x86/kvm/svm.c | 6 ++++++ arch/x86/kvm/vmx.c | 8 +++++++- arch/x86/kvm/x86.c | 14 ++++++++++++++ include/linux/kvm_host.h | 2 ++ virt/kvm/kvm_main.c | 12 ++++++++++++ 7 files changed, 53 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 62f973e..9ce6bfd 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -737,6 +737,7 @@ struct kvm_x86_ops { void (*hwapic_isr_update)(struct kvm *kvm, int isr); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); + void (*set_apic_access_page_addr)(struct kvm *kvm, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9314678..551693d 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3427,6 +3427,17 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); + /* + * apic access page could be migrated. When the guest tries to access + * the apic access page, ept violation will occur, and we can use GUP + * to find the new page. + * + * GUP will wait till the migrate entry be replaced with the new page. + */ + if (gpa == APIC_DEFAULT_PHYS_BASE) + vcpu->kvm->arch.apic_access_page = gfn_to_page_no_pin(vcpu->kvm, + APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + return r; out_unlock: diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 576b525..dc76f29 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3612,6 +3612,11 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) return; } +static void svm_set_apic_access_page_addr(struct kvm *kvm, hpa_t hpa) +{ + return; +} + static int svm_vm_has_apicv(struct kvm *kvm) { return 0; @@ -4365,6 +4370,7 @@ static struct kvm_x86_ops svm_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, + .set_apic_access_page_addr = svm_set_apic_access_page_addr, .vm_has_apicv = svm_vm_has_apicv, .load_eoi_exitmap = svm_load_eoi_exitmap, .hwapic_isr_update = svm_hwapic_isr_update, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5532ac8..f7c6313 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3992,7 +3992,7 @@ static int alloc_apic_access_page(struct kvm *kvm) if (r) goto out; - page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + page = gfn_to_page_no_pin(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); if (is_error_page(page)) { r = -EFAULT; goto out; @@ -7073,6 +7073,11 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) vmx_set_msr_bitmap(vcpu); } +static void vmx_set_apic_access_page_addr(struct kvm *kvm, hpa_t hpa) +{ + vmcs_write64(APIC_ACCESS_ADDR, hpa); +} + static void vmx_hwapic_isr_update(struct kvm *kvm, int isr) { u16 status; @@ -8842,6 +8847,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, + .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .vm_has_apicv = vmx_vm_has_apicv, .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ffbe557..7080eda 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5929,6 +5929,18 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) kvm_apic_update_tmr(vcpu, tmr); } +static void vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) +{ + /* + * When the page is being migrated, GUP will wait till the migrate + * entry is replaced with the new pte entry pointing to the new page. + */ + struct page *page = gfn_to_page_no_pin(vcpu->kvm, + APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + kvm_x86_ops->set_apic_access_page_addr(vcpu->kvm, + page_to_phys(page)); +} + /* * Returns 1 to let __vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -5989,6 +6001,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_deliver_pmi(vcpu); if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) vcpu_scan_ioapic(vcpu); + if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) + vcpu_reload_apic_access_page(vcpu); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7c58d9d..f49be86 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -136,6 +136,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_GLOBAL_CLOCK_UPDATE 22 #define KVM_REQ_ENABLE_IBS 23 #define KVM_REQ_DISABLE_IBS 24 +#define KVM_REQ_APIC_PAGE_RELOAD 25 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -596,6 +597,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); void kvm_make_mclock_inprogress_request(struct kvm *kvm); void kvm_make_scan_ioapic_request(struct kvm *kvm); +void kvm_reload_apic_access_page(struct kvm *kvm); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6091849..965b702 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -210,6 +210,11 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm) make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } +void kvm_reload_apic_access_page(struct kvm *kvm) +{ + make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); +} + int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { struct page *page; @@ -294,6 +299,13 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, if (need_tlb_flush) kvm_flush_remote_tlbs(kvm); + /* + * The physical address of apic access page is stroed in VMCS. + * So need to update it when it becomes invalid. + */ + if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT)) + kvm_reload_apic_access_page(kvm); + spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); } -- 1.8.3.1 -- 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/