kvm: svm: Use the hardware provided GPA instead of page walk

[mirror_ubuntu-artful-kernel.git] / arch / x86 / kvm / x86.c

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2f22810a7e0c8e3106c77849a6a3ea78a2b00a0c..edff19d1df97836a112b57fd4ab260ac3a8c53f4 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -190,6 +190,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
        { "mmu_unsync", VM_STAT(mmu_unsync) },
        { "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
        { "largepages", VM_STAT(lpages) },
+       { "max_mmu_page_hash_collisions",
+               VM_STAT(max_mmu_page_hash_collisions) },
        { NULL }
 };
 
@@ -3894,7 +3896,7 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
                        goto split_irqchip_unlock;
                /* Pairs with irqchip_in_kernel. */
                smp_wmb();
-               kvm->arch.irqchip_split = true;
+               kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT;
                kvm->arch.nr_reserved_ioapic_pins = cap->args[0];
                r = 0;
 split_irqchip_unlock:
@@ -3957,40 +3959,41 @@ long kvm_arch_vm_ioctl(struct file *filp,
                r = kvm_vm_ioctl_get_nr_mmu_pages(kvm);
                break;
        case KVM_CREATE_IRQCHIP: {
-               struct kvm_pic *vpic;
-
                mutex_lock(&kvm->lock);
+
                r = -EEXIST;
-               if (kvm->arch.vpic)
+               if (irqchip_in_kernel(kvm))
                        goto create_irqchip_unlock;
+
                r = -EINVAL;
                if (kvm->created_vcpus)
                        goto create_irqchip_unlock;
-               r = -ENOMEM;
-               vpic = kvm_create_pic(kvm);
-               if (vpic) {
-                       r = kvm_ioapic_init(kvm);
-                       if (r) {
-                               mutex_lock(&kvm->slots_lock);
-                               kvm_destroy_pic(vpic);
-                               mutex_unlock(&kvm->slots_lock);
-                               goto create_irqchip_unlock;
-                       }
-               } else
+
+               r = kvm_pic_init(kvm);
+               if (r)
+                       goto create_irqchip_unlock;
+
+               r = kvm_ioapic_init(kvm);
+               if (r) {
+                       mutex_lock(&kvm->slots_lock);
+                       kvm_pic_destroy(kvm);
+                       mutex_unlock(&kvm->slots_lock);
                        goto create_irqchip_unlock;
+               }
+
                r = kvm_setup_default_irq_routing(kvm);
                if (r) {
                        mutex_lock(&kvm->slots_lock);
                        mutex_lock(&kvm->irq_lock);
                        kvm_ioapic_destroy(kvm);
-                       kvm_destroy_pic(vpic);
+                       kvm_pic_destroy(kvm);
                        mutex_unlock(&kvm->irq_lock);
                        mutex_unlock(&kvm->slots_lock);
                        goto create_irqchip_unlock;
                }
-               /* Write kvm->irq_routing before kvm->arch.vpic.  */
+               /* Write kvm->irq_routing before enabling irqchip_in_kernel. */
                smp_wmb();
-               kvm->arch.vpic = vpic;
+               kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL;
        create_irqchip_unlock:
                mutex_unlock(&kvm->lock);
                break;
@@ -4026,7 +4029,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
                }
 
                r = -ENXIO;
-               if (!irqchip_in_kernel(kvm) || irqchip_split(kvm))
+               if (!irqchip_kernel(kvm))
                        goto get_irqchip_out;
                r = kvm_vm_ioctl_get_irqchip(kvm, chip);
                if (r)
@@ -4050,7 +4053,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
                }
 
                r = -ENXIO;
-               if (!irqchip_in_kernel(kvm) || irqchip_split(kvm))
+               if (!irqchip_kernel(kvm))
                        goto set_irqchip_out;
                r = kvm_vm_ioctl_set_irqchip(kvm, chip);
                if (r)
@@ -4459,6 +4462,21 @@ out:
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
 
+static int vcpu_is_mmio_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
+                           gpa_t gpa, bool write)
+{
+       /* For APIC access vmexit */
+       if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
+               return 1;
+
+       if (vcpu_match_mmio_gpa(vcpu, gpa)) {
+               trace_vcpu_match_mmio(gva, gpa, write, true);
+               return 1;
+       }
+
+       return 0;
+}
+
 static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
                                gpa_t *gpa, struct x86_exception *exception,
                                bool write)
@@ -4485,16 +4503,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
        if (*gpa == UNMAPPED_GVA)
                return -1;
 
-       /* For APIC access vmexit */
-       if ((*gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
-               return 1;
-
-       if (vcpu_match_mmio_gpa(vcpu, *gpa)) {
-               trace_vcpu_match_mmio(gva, *gpa, write, true);
-               return 1;
-       }
-
-       return 0;
+       return vcpu_is_mmio_gpa(vcpu, gva, *gpa, write);
 }
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
@@ -4591,6 +4600,22 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
        int handled, ret;
        bool write = ops->write;
        struct kvm_mmio_fragment *frag;
+       struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+
+       /*
+        * If the exit was due to a NPF we may already have a GPA.
+        * If the GPA is present, use it to avoid the GVA to GPA table walk.
+        * Note, this cannot be used on string operations since string
+        * operation using rep will only have the initial GPA from the NPF
+        * occurred.
+        */
+       if (vcpu->arch.gpa_available &&
+           emulator_can_use_gpa(ctxt) &&
+           vcpu_is_mmio_gpa(vcpu, addr, exception->address, write) &&
+           (addr & ~PAGE_MASK) == (exception->address & ~PAGE_MASK)) {
+               gpa = exception->address;
+               goto mmio;
+       }
 
        ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
 
@@ -5607,6 +5632,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
        }
 
 restart:
+       /* Save the faulting GPA (cr2) in the address field */
+       ctxt->exception.address = cr2;
+
        r = x86_emulate_insn(ctxt);
 
        if (r == EMULATION_INTERCEPTED)
@@ -6022,7 +6050,7 @@ int kvm_arch_init(void *opaque)
 
        kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
                        PT_DIRTY_MASK, PT64_NX_MASK, 0,
-                       PT_PRESENT_MASK);
+                       PT_PRESENT_MASK, 0);
        kvm_timer_init();
 
        perf_register_guest_info_callbacks(&kvm_guest_cbs);