1 files changed, 127 insertions, 34 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e52c9088660f..10e20afc3314 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -180,6 +180,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "insn_emulation_fail", VCPU_STAT(insn_emulation_fail) },
 	{ "irq_injections", VCPU_STAT(irq_injections) },
 	{ "nmi_injections", VCPU_STAT(nmi_injections) },
+	{ "req_event", VCPU_STAT(req_event) },
 	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
 	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
 	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
@@ -190,6 +191,8 @@ 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 }
 };
 
@@ -1139,6 +1142,7 @@ struct pvclock_gtod_data {
 
 	u64		boot_ns;
 	u64		nsec_base;
+	u64		wall_time_sec;
 };
 
 static struct pvclock_gtod_data pvclock_gtod_data;
@@ -1162,6 +1166,8 @@ static void update_pvclock_gtod(struct timekeeper *tk)
 	vdata->boot_ns			= boot_ns;
 	vdata->nsec_base		= tk->tkr_mono.xtime_nsec;
 
+	vdata->wall_time_sec            = tk->xtime_sec;
+
 	write_seqcount_end(&vdata->seq);
 }
 #endif
@@ -1623,6 +1629,28 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now)
 	return mode;
 }
 
+static int do_realtime(struct timespec *ts, u64 *cycle_now)
+{
+	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+	unsigned long seq;
+	int mode;
+	u64 ns;
+
+	do {
+		seq = read_seqcount_begin(&gtod->seq);
+		mode = gtod->clock.vclock_mode;
+		ts->tv_sec = gtod->wall_time_sec;
+		ns = gtod->nsec_base;
+		ns += vgettsc(cycle_now);
+		ns >>= gtod->clock.shift;
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
+
+	ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+	ts->tv_nsec = ns;
+
+	return mode;
+}
+
 /* returns true if host is using tsc clocksource */
 static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now)
 {
@@ -1632,6 +1660,17 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now)
 
 	return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC;
 }
+
+/* returns true if host is using tsc clocksource */
+static bool kvm_get_walltime_and_clockread(struct timespec *ts,
+					   u64 *cycle_now)
+{
+	/* checked again under seqlock below */
+	if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+		return false;
+
+	return do_realtime(ts, cycle_now) == VCLOCK_TSC;
+}
 #endif
 
 /*
@@ -3897,7 +3936,7 @@ 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:
@@ -3960,40 +3999,41 @@ 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;
@@ -4029,7 +4069,7 @@ 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)
@@ -4053,7 +4093,7 @@ 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)
@@ -4462,6 +4502,21 @@ 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)
@@ -4488,16 +4543,7 @@ 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,
@@ -4594,6 +4640,22 @@ 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);
 
@@ -5610,6 +5672,9 @@ 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)
@@ -5924,9 +5989,6 @@ static void kvm_set_mmio_spte_mask(void)
 	 /* Mask the reserved physical address bits. */
 	mask = rsvd_bits(maxphyaddr, 51);
 
-	/* Bit 62 is always reserved for 32bit host. */
-	mask |= 0x3ull << 62;
-
 	/* Set the present bit. */
 	mask |= 1ull;
 
@@ -6025,7 +6087,7 @@ 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);
@@ -6087,6 +6149,33 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
+static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
+			        unsigned long clock_type)
+{
+	struct kvm_clock_pairing clock_pairing;
+	struct timespec ts;
+	u64 cycle;
+	int ret;
+
+	if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK)
+		return -KVM_EOPNOTSUPP;
+
+	if (kvm_get_walltime_and_clockread(&ts, &cycle) == false)
+		return -KVM_EOPNOTSUPP;
+
+	clock_pairing.sec = ts.tv_sec;
+	clock_pairing.nsec = ts.tv_nsec;
+	clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle);
+	clock_pairing.flags = 0;
+
+	ret = 0;
+	if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing,
+			    sizeof(struct kvm_clock_pairing)))
+		ret = -KVM_EFAULT;
+
+	return ret;
+}
+
 /*
  * kvm_pv_kick_cpu_op:  Kick a vcpu.
  *
@@ -6151,6 +6240,9 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
 		ret = 0;
 		break;
+	case KVM_HC_CLOCK_PAIRING:
+		ret = kvm_pv_clock_pairing(vcpu, a0, a1);
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
@@ -6733,6 +6825,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
+		++vcpu->stat.req_event;
 		kvm_apic_accept_events(vcpu);
 		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
 			r = 1;