X-Git-Url: https://git.karo-electronics.de/?a=blobdiff_plain;f=arch%2Fx86%2Fkvm%2Fx86.c;h=a28379507d30a44ddf0d8171b8cdab0c77ac4ea8;hb=a0044755679f3e761b8b95995e5f2db2b7efd0f6;hp=28127c936c3b3e889670310d1ce6c075ae6467b6;hpb=a983fb238728e1123177e8058d4f644b949a7d05;p=karo-tx-linux.git

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 28127c936c3b..a28379507d30 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -428,12 +428,18 @@ out:
 
 void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
-	if (cr0 & CR0_RESERVED_BITS) {
+	cr0 |= X86_CR0_ET;
+
+#ifdef CONFIG_X86_64
+	if (cr0 & 0xffffffff00000000UL) {
 		printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
-		       cr0, vcpu->arch.cr0);
+		       cr0, kvm_read_cr0(vcpu));
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
+#endif
+
+	cr0 &= ~CR0_RESERVED_BITS;
 
 	if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
 		printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
@@ -450,7 +456,7 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
 #ifdef CONFIG_X86_64
-		if ((vcpu->arch.shadow_efer & EFER_LME)) {
+		if ((vcpu->arch.efer & EFER_LME)) {
 			int cs_db, cs_l;
 
 			if (!is_pae(vcpu)) {
@@ -488,7 +494,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr0);
 
 void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 {
-	kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+	kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f));
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
@@ -620,9 +626,11 @@ static inline u32 bit(int bitno)
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	2
+#define KVM_SAVE_MSRS_BEGIN	5
 static u32 msrs_to_save[] = {
 	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
+	HV_X64_MSR_APIC_ASSIST_PAGE,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_K6_STAR,
 #ifdef CONFIG_X86_64
@@ -647,7 +655,7 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	}
 
 	if (is_paging(vcpu)
-	    && (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) {
+	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) {
 		printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
@@ -678,9 +686,9 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	kvm_x86_ops->set_efer(vcpu, efer);
 
 	efer &= ~EFER_LMA;
-	efer |= vcpu->arch.shadow_efer & EFER_LMA;
+	efer |= vcpu->arch.efer & EFER_LMA;
 
-	vcpu->arch.shadow_efer = efer;
+	vcpu->arch.efer = efer;
 
 	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
 	kvm_mmu_reset_context(vcpu);
@@ -1002,6 +1010,100 @@ out:
 	return r;
 }
 
+static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
+{
+	return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
+}
+
+static bool kvm_hv_msr_partition_wide(u32 msr)
+{
+	bool r = false;
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+	case HV_X64_MSR_HYPERCALL:
+		r = true;
+		break;
+	}
+
+	return r;
+}
+
+static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		kvm->arch.hv_guest_os_id = data;
+		/* setting guest os id to zero disables hypercall page */
+		if (!kvm->arch.hv_guest_os_id)
+			kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
+		break;
+	case HV_X64_MSR_HYPERCALL: {
+		u64 gfn;
+		unsigned long addr;
+		u8 instructions[4];
+
+		/* if guest os id is not set hypercall should remain disabled */
+		if (!kvm->arch.hv_guest_os_id)
+			break;
+		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
+			kvm->arch.hv_hypercall = data;
+			break;
+		}
+		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
+		addr = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		kvm_x86_ops->patch_hypercall(vcpu, instructions);
+		((unsigned char *)instructions)[3] = 0xc3; /* ret */
+		if (copy_to_user((void __user *)addr, instructions, 4))
+			return 1;
+		kvm->arch.hv_hypercall = data;
+		break;
+	}
+	default:
+		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
+			  "data 0x%llx\n", msr, data);
+		return 1;
+	}
+	return 0;
+}
+
+static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	switch (msr) {
+	case HV_X64_MSR_APIC_ASSIST_PAGE: {
+		unsigned long addr;
+
+		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
+			vcpu->arch.hv_vapic = data;
+			break;
+		}
+		addr = gfn_to_hva(vcpu->kvm, data >>
+				  HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT);
+		if (kvm_is_error_hva(addr))
+			return 1;
+		if (clear_user((void __user *)addr, PAGE_SIZE))
+			return 1;
+		vcpu->arch.hv_vapic = data;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
+	default:
+		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
+			  "data 0x%llx\n", msr, data);
+		return 1;
+	}
+
+	return 0;
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
@@ -1116,6 +1218,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
 			"0x%x data 0x%llx\n", msr, data);
 		break;
+	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+		if (kvm_hv_msr_partition_wide(msr)) {
+			int r;
+			mutex_lock(&vcpu->kvm->lock);
+			r = set_msr_hyperv_pw(vcpu, msr, data);
+			mutex_unlock(&vcpu->kvm->lock);
+			return r;
+		} else
+			return set_msr_hyperv(vcpu, msr, data);
+		break;
 	default:
 		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
 			return xen_hvm_config(vcpu, data);
@@ -1215,6 +1327,54 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	return 0;
 }
 
+static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+	struct kvm *kvm = vcpu->kvm;
+
+	switch (msr) {
+	case HV_X64_MSR_GUEST_OS_ID:
+		data = kvm->arch.hv_guest_os_id;
+		break;
+	case HV_X64_MSR_HYPERCALL:
+		data = kvm->arch.hv_hypercall;
+		break;
+	default:
+		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+
+	*pdata = data;
+	return 0;
+}
+
+static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+{
+	u64 data = 0;
+
+	switch (msr) {
+	case HV_X64_MSR_VP_INDEX: {
+		int r;
+		struct kvm_vcpu *v;
+		kvm_for_each_vcpu(r, v, vcpu->kvm)
+			if (v == vcpu)
+				data = r;
+		break;
+	}
+	case HV_X64_MSR_EOI:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
+	case HV_X64_MSR_ICR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
+	case HV_X64_MSR_TPR:
+		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+	default:
+		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
+		return 1;
+	}
+	*pdata = data;
+	return 0;
+}
+
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 {
 	u64 data;
@@ -1266,7 +1426,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		data |= (((uint64_t)4ULL) << 40);
 		break;
 	case MSR_EFER:
-		data = vcpu->arch.shadow_efer;
+		data = vcpu->arch.efer;
 		break;
 	case MSR_KVM_WALL_CLOCK:
 		data = vcpu->kvm->arch.wall_clock;
@@ -1281,6 +1441,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
 		return get_msr_mce(vcpu, msr, pdata);
+	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+		if (kvm_hv_msr_partition_wide(msr)) {
+			int r;
+			mutex_lock(&vcpu->kvm->lock);
+			r = get_msr_hyperv_pw(vcpu, msr, pdata);
+			mutex_unlock(&vcpu->kvm->lock);
+			return r;
+		} else
+			return get_msr_hyperv(vcpu, msr, pdata);
+		break;
 	default:
 		if (!ignore_msrs) {
 			pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
@@ -1306,15 +1476,15 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
 		    int (*do_msr)(struct kvm_vcpu *vcpu,
 				  unsigned index, u64 *data))
 {
-	int i;
+	int i, idx;
 
 	vcpu_load(vcpu);
 
-	down_read(&vcpu->kvm->slots_lock);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	for (i = 0; i < msrs->nmsrs; ++i)
 		if (do_msr(vcpu, entries[i].index, &entries[i].data))
 			break;
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 	vcpu_put(vcpu);
 
@@ -1396,6 +1566,10 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_XEN_HVM:
 	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
+	case KVM_CAP_HYPERV:
+	case KVM_CAP_HYPERV_VAPIC:
+	case KVM_CAP_HYPERV_SPIN:
+	case KVM_CAP_PCI_SEGMENT:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -1509,8 +1683,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
+	kvm_x86_ops->vcpu_put(vcpu);
 }
 
 static int is_efer_nx(void)
@@ -1641,10 +1815,12 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			 u32 index, int *nent, int maxnent)
 {
 	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
-	unsigned f_gbpages = kvm_x86_ops->gb_page_enable() ? F(GBPAGES) : 0;
 #ifdef CONFIG_X86_64
+	unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
+				? F(GBPAGES) : 0;
 	unsigned f_lm = F(LM);
 #else
+	unsigned f_gbpages = 0;
 	unsigned f_lm = 0;
 #endif
 	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
@@ -2208,14 +2384,14 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
 		return -EINVAL;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	spin_lock(&kvm->mmu_lock);
 
 	kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
 	kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;
 
 	spin_unlock(&kvm->mmu_lock);
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return 0;
 }
 
@@ -2292,7 +2468,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
 	if (!aliases)
 		goto out;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	/* invalidate any gfn reference in case of deletion/shrinking */
 	memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases));
@@ -2328,7 +2504,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
 	r = 0;
 
 out_unlock:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 out:
 	return r;
 }
@@ -2462,7 +2638,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	unsigned long is_dirty = 0;
 	unsigned long *dirty_bitmap = NULL;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
 	if (log->slot >= KVM_MEMORY_SLOTS)
@@ -2512,7 +2688,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 out_free:
 	vfree(dirty_bitmap);
 out:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 
@@ -2595,6 +2771,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (vpic) {
 			r = kvm_ioapic_init(kvm);
 			if (r) {
+				kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
+							  &vpic->dev);
 				kfree(vpic);
 				goto create_irqchip_unlock;
 			}
@@ -2606,10 +2784,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
 			mutex_lock(&kvm->irq_lock);
-			kfree(kvm->arch.vpic);
-			kfree(kvm->arch.vioapic);
-			kvm->arch.vpic = NULL;
-			kvm->arch.vioapic = NULL;
+			kvm_ioapic_destroy(kvm);
+			kvm_destroy_pic(kvm);
 			mutex_unlock(&kvm->irq_lock);
 		}
 	create_irqchip_unlock:
@@ -2625,7 +2801,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 				   sizeof(struct kvm_pit_config)))
 			goto out;
 	create_pit:
-		down_write(&kvm->slots_lock);
+		mutex_lock(&kvm->slots_lock);
 		r = -EEXIST;
 		if (kvm->arch.vpit)
 			goto create_pit_unlock;
@@ -2634,7 +2810,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (kvm->arch.vpit)
 			r = 0;
 	create_pit_unlock:
-		up_write(&kvm->slots_lock);
+		mutex_unlock(&kvm->slots_lock);
 		break;
 	case KVM_IRQ_LINE_STATUS:
 	case KVM_IRQ_LINE: {
@@ -2851,7 +3027,7 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
 	    !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v))
 		return 0;
 
-	return kvm_io_bus_write(&vcpu->kvm->mmio_bus, addr, len, v);
+	return kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
 }
 
 static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
@@ -2860,7 +3036,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
 	    !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, len, v))
 		return 0;
 
-	return kvm_io_bus_read(&vcpu->kvm->mmio_bus, addr, len, v);
+	return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
 }
 
 static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
@@ -3093,35 +3269,21 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
 
 int emulate_clts(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS);
+	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
+	kvm_x86_ops->fpu_activate(vcpu);
 	return X86EMUL_CONTINUE;
 }
 
 int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
 {
-	struct kvm_vcpu *vcpu = ctxt->vcpu;
-
-	switch (dr) {
-	case 0 ... 3:
-		*dest = kvm_x86_ops->get_dr(vcpu, dr);
-		return X86EMUL_CONTINUE;
-	default:
-		pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr);
-		return X86EMUL_UNHANDLEABLE;
-	}
+	return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest);
 }
 
 int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
 {
 	unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
-	int exception;
 
-	kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception);
-	if (exception) {
-		/* FIXME: better handling */
-		return X86EMUL_UNHANDLEABLE;
-	}
-	return X86EMUL_CONTINUE;
+	return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask);
 }
 
 void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
@@ -3186,8 +3348,9 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		vcpu->arch.emulate_ctxt.vcpu = vcpu;
 		vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu);
 		vcpu->arch.emulate_ctxt.mode =
+			(!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
 			(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
-			? X86EMUL_MODE_REAL : cs_l
+			? X86EMUL_MODE_VM86 : cs_l
 			? X86EMUL_MODE_PROT64 :	cs_db
 			? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
 
@@ -3345,11 +3508,12 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 	int r;
 
 	if (vcpu->arch.pio.in)
-		r = kvm_io_bus_read(&vcpu->kvm->pio_bus, vcpu->arch.pio.port,
+		r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
 				    vcpu->arch.pio.size, pd);
 	else
-		r = kvm_io_bus_write(&vcpu->kvm->pio_bus, vcpu->arch.pio.port,
-				     vcpu->arch.pio.size, pd);
+		r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
+				     vcpu->arch.pio.port, vcpu->arch.pio.size,
+				     pd);
 	return r;
 }
 
@@ -3360,7 +3524,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu)
 	int i, r = 0;
 
 	for (i = 0; i < io->cur_count; i++) {
-		if (kvm_io_bus_write(&vcpu->kvm->pio_bus,
+		if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
 				     io->port, io->size, pd)) {
 			r = -EOPNOTSUPP;
 			break;
@@ -3388,8 +3552,10 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port)
 	trace_kvm_pio(vcpu->run->io.direction == KVM_EXIT_IO_OUT, port,
 		      size, 1);
 
-	val = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	memcpy(vcpu->arch.pio_data, &val, 4);
+	if (!vcpu->arch.pio.in) {
+		val = kvm_register_read(vcpu, VCPU_REGS_RAX);
+		memcpy(vcpu->arch.pio_data, &val, 4);
+	}
 
 	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
 		complete_pio(vcpu);
@@ -3613,11 +3779,76 @@ static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
 		return a0 | ((gpa_t)a1 << 32);
 }
 
+int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
+{
+	u64 param, ingpa, outgpa, ret;
+	uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0;
+	bool fast, longmode;
+	int cs_db, cs_l;
+
+	/*
+	 * hypercall generates UD from non zero cpl and real mode
+	 * per HYPER-V spec
+	 */
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 0;
+	}
+
+	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+	longmode = is_long_mode(vcpu) && cs_l == 1;
+
+	if (!longmode) {
+		param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff);
+		ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff);
+		outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) |
+			(kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff);
+	}
+#ifdef CONFIG_X86_64
+	else {
+		param = kvm_register_read(vcpu, VCPU_REGS_RCX);
+		ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX);
+		outgpa = kvm_register_read(vcpu, VCPU_REGS_R8);
+	}
+#endif
+
+	code = param & 0xffff;
+	fast = (param >> 16) & 0x1;
+	rep_cnt = (param >> 32) & 0xfff;
+	rep_idx = (param >> 48) & 0xfff;
+
+	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
+
+	switch (code) {
+	case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT:
+		kvm_vcpu_on_spin(vcpu);
+		break;
+	default:
+		res = HV_STATUS_INVALID_HYPERCALL_CODE;
+		break;
+	}
+
+	ret = res | (((u64)rep_done & 0xfff) << 32);
+	if (longmode) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret);
+	} else {
+		kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32);
+		kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff);
+	}
+
+	return 1;
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
 	int r = 1;
 
+	if (kvm_hv_hypercall_enabled(vcpu->kvm))
+		return kvm_hv_hypercall(vcpu);
+
 	nr = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	a0 = kvm_register_read(vcpu, VCPU_REGS_RBX);
 	a1 = kvm_register_read(vcpu, VCPU_REGS_RCX);
@@ -3660,10 +3891,8 @@ EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
 int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
 {
 	char instruction[3];
-	int ret = 0;
 	unsigned long rip = kvm_rip_read(vcpu);
 
-
 	/*
 	 * Blow out the MMU to ensure that no other VCPU has an active mapping
 	 * to ensure that the updated hypercall appears atomically across all
@@ -3672,11 +3901,8 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
 	kvm_mmu_zap_all(vcpu->kvm);
 
 	kvm_x86_ops->patch_hypercall(vcpu, instruction);
-	if (emulator_write_emulated(rip, instruction, 3, vcpu)
-	    != X86EMUL_CONTINUE)
-		ret = -EFAULT;
 
-	return ret;
+	return emulator_write_emulated(rip, instruction, 3, vcpu);
 }
 
 static u64 mk_cr_64(u64 curr_cr, u32 new_val)
@@ -3711,7 +3937,7 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
 
 	switch (cr) {
 	case 0:
-		value = vcpu->arch.cr0;
+		value = kvm_read_cr0(vcpu);
 		break;
 	case 2:
 		value = vcpu->arch.cr2;
@@ -3738,7 +3964,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
 {
 	switch (cr) {
 	case 0:
-		kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
+		kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
 		*rflags = kvm_get_rflags(vcpu);
 		break;
 	case 2:
@@ -3899,14 +4125,15 @@ static void vapic_enter(struct kvm_vcpu *vcpu)
 static void vapic_exit(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
+	int idx;
 
 	if (!apic || !apic->vapic_addr)
 		return;
 
-	down_read(&vcpu->kvm->slots_lock);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	kvm_release_page_dirty(apic->vapic_page);
 	mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -4002,12 +4229,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
+		if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) {
+			vcpu->fpu_active = 0;
+			kvm_x86_ops->fpu_deactivate(vcpu);
+		}
 	}
 
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
-	kvm_load_guest_fpu(vcpu);
+	if (vcpu->fpu_active)
+		kvm_load_guest_fpu(vcpu);
 
 	local_irq_disable();
 
@@ -4035,7 +4267,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		kvm_lapic_sync_to_vapic(vcpu);
 	}
 
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 
 	kvm_guest_enter();
 
@@ -4077,7 +4309,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	preempt_enable();
 
-	down_read(&vcpu->kvm->slots_lock);
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	/*
 	 * Profile KVM exit RIPs:
@@ -4099,6 +4331,7 @@ out:
 static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int r;
+	struct kvm *kvm = vcpu->kvm;
 
 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
 		pr_debug("vcpu %d received sipi with vector # %x\n",
@@ -4110,7 +4343,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 	}
 
-	down_read(&vcpu->kvm->slots_lock);
+	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 	vapic_enter(vcpu);
 
 	r = 1;
@@ -4118,9 +4351,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
 			r = vcpu_enter_guest(vcpu);
 		else {
-			up_read(&vcpu->kvm->slots_lock);
+			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 			kvm_vcpu_block(vcpu);
-			down_read(&vcpu->kvm->slots_lock);
+			vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 			if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
 			{
 				switch(vcpu->arch.mp_state) {
@@ -4155,13 +4388,13 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 			++vcpu->stat.signal_exits;
 		}
 		if (need_resched()) {
-			up_read(&vcpu->kvm->slots_lock);
+			srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 			kvm_resched(vcpu);
-			down_read(&vcpu->kvm->slots_lock);
+			vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
 		}
 	}
 
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 	post_kvm_run_save(vcpu);
 
 	vapic_exit(vcpu);
@@ -4200,10 +4433,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->mmio_read_completed = 1;
 		vcpu->mmio_needed = 0;
 
-		down_read(&vcpu->kvm->slots_lock);
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0,
 					EMULTYPE_NO_DECODE);
-		up_read(&vcpu->kvm->slots_lock);
+		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 		if (r == EMULATE_DO_MMIO) {
 			/*
 			 * Read-modify-write.  Back to userspace.
@@ -4330,12 +4563,12 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	sregs->gdt.limit = dt.limit;
 	sregs->gdt.base = dt.base;
 
-	sregs->cr0 = vcpu->arch.cr0;
+	sregs->cr0 = kvm_read_cr0(vcpu);
 	sregs->cr2 = vcpu->arch.cr2;
 	sregs->cr3 = vcpu->arch.cr3;
 	sregs->cr4 = kvm_read_cr4(vcpu);
 	sregs->cr8 = kvm_get_cr8(vcpu);
-	sregs->efer = vcpu->arch.shadow_efer;
+	sregs->efer = vcpu->arch.efer;
 	sregs->apic_base = kvm_get_apic_base(vcpu);
 
 	memset(sregs->interrupt_bitmap, 0, sizeof sregs->interrupt_bitmap);
@@ -4428,7 +4661,7 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 
 	if (dtable.limit < index * 8 + 7) {
 		kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
-		return 1;
+		return X86EMUL_PROPAGATE_FAULT;
 	}
 	return kvm_read_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu);
 }
@@ -4463,18 +4696,6 @@ static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
 	return kvm_seg.selector;
 }
 
-static int load_segment_descriptor_to_kvm_desct(struct kvm_vcpu *vcpu,
-						u16 selector,
-						struct kvm_segment *kvm_seg)
-{
-	struct desc_struct seg_desc;
-
-	if (load_guest_segment_descriptor(vcpu, selector, &seg_desc))
-		return 1;
-	seg_desct_to_kvm_desct(&seg_desc, selector, kvm_seg);
-	return 0;
-}
-
 static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg)
 {
 	struct kvm_segment segvar = {
@@ -4515,11 +4736,14 @@ int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 				int type_bits, int seg)
 {
 	struct kvm_segment kvm_seg;
+	struct desc_struct seg_desc;
 
-	if (is_vm86_segment(vcpu, seg) || !(vcpu->arch.cr0 & X86_CR0_PE))
+	if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu))
 		return kvm_load_realmode_segment(vcpu, selector, seg);
-	if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg))
+
+	if (load_guest_segment_descriptor(vcpu, selector, &seg_desc))
 		return 1;
+	seg_desct_to_kvm_desct(&seg_desc, selector, &kvm_seg);
 
 	kvm_check_segment_descriptor(vcpu, seg, selector);
 	kvm_seg.type |= type_bits;
@@ -4530,6 +4754,11 @@ int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 			kvm_seg.unusable = 1;
 
 	kvm_set_segment(vcpu, &kvm_seg, seg);
+	if (selector && !kvm_seg.unusable && kvm_seg.s) {
+		/* mark segment as accessed */
+		seg_desc.type |= 1;
+		save_guest_segment_descriptor(vcpu, selector, &seg_desc);
+	}
 	return 0;
 }
 
@@ -4794,7 +5023,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 					      &nseg_desc);
 	}
 
-	kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | X86_CR0_TS);
+	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS);
 	seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
 	tr_seg.type = 11;
 	kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
@@ -4825,11 +5054,11 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	kvm_set_cr8(vcpu, sregs->cr8);
 
-	mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer;
+	mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
 	kvm_x86_ops->set_efer(vcpu, sregs->efer);
 	kvm_set_apic_base(vcpu, sregs->apic_base);
 
-	mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0;
+	mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
 	kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
 	vcpu->arch.cr0 = sregs->cr0;
 
@@ -4868,7 +5097,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	/* Older userspace won't unhalt the vcpu on reset. */
 	if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 &&
 	    sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 &&
-	    !(vcpu->arch.cr0 & X86_CR0_PE))
+	    !is_protmode(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	vcpu_put(vcpu);
@@ -4966,11 +5195,12 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 {
 	unsigned long vaddr = tr->linear_address;
 	gpa_t gpa;
+	int idx;
 
 	vcpu_load(vcpu);
-	down_read(&vcpu->kvm->slots_lock);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr);
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	tr->physical_address = gpa;
 	tr->valid = gpa != UNMAPPED_GVA;
 	tr->writeable = 1;
@@ -5051,14 +5281,14 @@ EXPORT_SYMBOL_GPL(fx_init);
 
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->fpu_active || vcpu->guest_fpu_loaded)
+	if (vcpu->guest_fpu_loaded)
 		return;
 
 	vcpu->guest_fpu_loaded = 1;
 	kvm_fx_save(&vcpu->arch.host_fx_image);
 	kvm_fx_restore(&vcpu->arch.guest_fx_image);
+	trace_kvm_fpu(1);
 }
-EXPORT_SYMBOL_GPL(kvm_load_guest_fpu);
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
@@ -5069,8 +5299,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 	kvm_fx_save(&vcpu->arch.guest_fx_image);
 	kvm_fx_restore(&vcpu->arch.host_fx_image);
 	++vcpu->stat.fpu_reload;
+	set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests);
+	trace_kvm_fpu(0);
 }
-EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
@@ -5222,11 +5453,13 @@ fail:
 
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
+	int idx;
+
 	kfree(vcpu->arch.mce_banks);
 	kvm_free_lapic(vcpu);
-	down_read(&vcpu->kvm->slots_lock);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
 	kvm_mmu_destroy(vcpu);
-	up_read(&vcpu->kvm->slots_lock);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	free_page((unsigned long)vcpu->arch.pio_data);
 }
 
@@ -5299,6 +5532,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		put_page(kvm->arch.apic_access_page);
 	if (kvm->arch.ept_identity_pagetable)
 		put_page(kvm->arch.ept_identity_pagetable);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm->arch.aliases);
 	kfree(kvm);
 }