X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=arch%2Fx86%2Fkvm%2Fsvm.c;h=468ff6e721cedc72c82fecdac39328193a320372;hb=66b7138f913635b40822890ba8913548f8b285b8;hp=3bb6d4b92b34a63cb1fd90c747b797dea7ad1d5e;hpb=9c4e40b9949868928bd7fec67a4b0902d90e57ed;p=safe%2Fjmp%2Flinux-2.6

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 3bb6d4b..468ff6e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -26,6 +26,7 @@
 #include <linux/highmem.h>
 #include <linux/sched.h>
 #include <linux/ftrace_event.h>
+#include <linux/slab.h>
 
 #include <asm/desc.h>
 
@@ -46,17 +47,14 @@ MODULE_LICENSE("GPL");
 #define SVM_FEATURE_NPT  (1 << 0)
 #define SVM_FEATURE_LBRV (1 << 1)
 #define SVM_FEATURE_SVML (1 << 2)
+#define SVM_FEATURE_NRIP (1 << 3)
+#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
 
-#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
-
-/* Turn on to get debugging output*/
-/* #define NESTED_DEBUG */
+#define NESTED_EXIT_HOST	0	/* Exit handled on host level */
+#define NESTED_EXIT_DONE	1	/* Exit caused nested vmexit  */
+#define NESTED_EXIT_CONTINUE	2	/* Further checks needed      */
 
-#ifdef NESTED_DEBUG
-#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args)
-#else
-#define nsvm_printk(fmt, args...) do {} while(0)
-#endif
+#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
 
 static const u32 host_save_user_msrs[] = {
 #ifdef CONFIG_X86_64
@@ -81,6 +79,9 @@ struct nested_state {
 	/* gpa pointers to the real vectors */
 	u64 vmcb_msrpm;
 
+	/* A VMEXIT is required but not yet emulated */
+	bool exit_required;
+
 	/* cache for intercepts of the guest */
 	u16 intercept_cr_read;
 	u16 intercept_cr_write;
@@ -108,6 +109,11 @@ struct vcpu_svm {
 	u32 *msrpm;
 
 	struct nested_state nested;
+
+	bool nmi_singlestep;
+
+	unsigned int3_injected;
+	unsigned long int3_rip;
 };
 
 /* enable NPT for AMD64 and X86 with PAE */
@@ -120,16 +126,15 @@ static int npt = 1;
 
 module_param(npt, int, S_IRUGO);
 
-static int nested = 0;
+static int nested = 1;
 module_param(nested, int, S_IRUGO);
 
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
 
-static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override);
+static int nested_svm_exit_handled(struct vcpu_svm *svm);
+static int nested_svm_intercept(struct vcpu_svm *svm);
 static int nested_svm_vmexit(struct vcpu_svm *svm);
-static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb,
-			     void *arg2, void *opaque);
 static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 				      bool has_error_code, u32 error_code);
 
@@ -232,24 +237,7 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 		efer &= ~EFER_LME;
 
 	to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME;
-	vcpu->arch.shadow_efer = efer;
-}
-
-static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
-				bool has_error_code, u32 error_code)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	/* If we are within a nested VM we'd better #VMEXIT and let the
-	   guest handle the exception */
-	if (nested_svm_check_exception(svm, nr, has_error_code, error_code))
-		return;
-
-	svm->vmcb->control.event_inj = nr
-		| SVM_EVTINJ_VALID
-		| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
-		| SVM_EVTINJ_TYPE_EXEPT;
-	svm->vmcb->control.event_inj_err = error_code;
+	vcpu->arch.efer = efer;
 }
 
 static int is_external_interrupt(u32 info)
@@ -264,7 +252,7 @@ static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 	u32 ret = 0;
 
 	if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
-		ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS;
+		ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
 	return ret & mask;
 }
 
@@ -284,7 +272,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!svm->next_rip) {
-		if (emulate_instruction(vcpu, vcpu->run, 0, 0, EMULTYPE_SKIP) !=
+		if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
 				EMULATE_DONE)
 			printk(KERN_DEBUG "%s: NOP\n", __func__);
 		return;
@@ -297,6 +285,39 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	svm_set_interrupt_shadow(vcpu, 0);
 }
 
+static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
+				bool has_error_code, u32 error_code)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	/* If we are within a nested VM we'd better #VMEXIT and let the
+	   guest handle the exception */
+	if (nested_svm_check_exception(svm, nr, has_error_code, error_code))
+		return;
+
+	if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) {
+		unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
+
+		/*
+		 * For guest debugging where we have to reinject #BP if some
+		 * INT3 is guest-owned:
+		 * Emulate nRIP by moving RIP forward. Will fail if injection
+		 * raises a fault that is not intercepted. Still better than
+		 * failing in all cases.
+		 */
+		skip_emulated_instruction(&svm->vcpu);
+		rip = kvm_rip_read(&svm->vcpu);
+		svm->int3_rip = rip + svm->vmcb->save.cs.base;
+		svm->int3_injected = rip - old_rip;
+	}
+
+	svm->vmcb->control.event_inj = nr
+		| SVM_EVTINJ_VALID
+		| (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
+		| SVM_EVTINJ_TYPE_EXEPT;
+	svm->vmcb->control.event_inj_err = error_code;
+}
+
 static int has_svm(void)
 {
 	const char *msg;
@@ -314,75 +335,79 @@ static void svm_hardware_disable(void *garbage)
 	cpu_svm_disable();
 }
 
-static void svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void *garbage)
 {
 
-	struct svm_cpu_data *svm_data;
+	struct svm_cpu_data *sd;
 	uint64_t efer;
-	struct descriptor_table gdt_descr;
+	struct desc_ptr gdt_descr;
 	struct desc_struct *gdt;
 	int me = raw_smp_processor_id();
 
+	rdmsrl(MSR_EFER, efer);
+	if (efer & EFER_SVME)
+		return -EBUSY;
+
 	if (!has_svm()) {
-		printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me);
-		return;
+		printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n",
+		       me);
+		return -EINVAL;
 	}
-	svm_data = per_cpu(svm_data, me);
+	sd = per_cpu(svm_data, me);
 
-	if (!svm_data) {
-		printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n",
+	if (!sd) {
+		printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n",
 		       me);
-		return;
+		return -EINVAL;
 	}
 
-	svm_data->asid_generation = 1;
-	svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
-	svm_data->next_asid = svm_data->max_asid + 1;
+	sd->asid_generation = 1;
+	sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
+	sd->next_asid = sd->max_asid + 1;
 
 	kvm_get_gdt(&gdt_descr);
-	gdt = (struct desc_struct *)gdt_descr.base;
-	svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
+	gdt = (struct desc_struct *)gdt_descr.address;
+	sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
 
-	rdmsrl(MSR_EFER, efer);
 	wrmsrl(MSR_EFER, efer | EFER_SVME);
 
-	wrmsrl(MSR_VM_HSAVE_PA,
-	       page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
+	wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
+
+	return 0;
 }
 
 static void svm_cpu_uninit(int cpu)
 {
-	struct svm_cpu_data *svm_data
-		= per_cpu(svm_data, raw_smp_processor_id());
+	struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id());
 
-	if (!svm_data)
+	if (!sd)
 		return;
 
 	per_cpu(svm_data, raw_smp_processor_id()) = NULL;
-	__free_page(svm_data->save_area);
-	kfree(svm_data);
+	__free_page(sd->save_area);
+	kfree(sd);
 }
 
 static int svm_cpu_init(int cpu)
 {
-	struct svm_cpu_data *svm_data;
+	struct svm_cpu_data *sd;
 	int r;
 
-	svm_data = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
-	if (!svm_data)
+	sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
+	if (!sd)
 		return -ENOMEM;
-	svm_data->cpu = cpu;
-	svm_data->save_area = alloc_page(GFP_KERNEL);
+	sd->cpu = cpu;
+	sd->save_area = alloc_page(GFP_KERNEL);
 	r = -ENOMEM;
-	if (!svm_data->save_area)
+	if (!sd->save_area)
 		goto err_1;
 
-	per_cpu(svm_data, cpu) = svm_data;
+	per_cpu(svm_data, cpu) = sd;
 
 	return 0;
 
 err_1:
-	kfree(svm_data);
+	kfree(sd);
 	return r;
 
 }
@@ -474,7 +499,7 @@ static __init int svm_hardware_setup(void)
 		kvm_enable_efer_bits(EFER_SVME);
 	}
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		r = svm_cpu_init(cpu);
 		if (r)
 			goto err;
@@ -508,7 +533,7 @@ static __exit void svm_hardware_unsetup(void)
 {
 	int cpu;
 
-	for_each_online_cpu(cpu)
+	for_each_possible_cpu(cpu)
 		svm_cpu_uninit(cpu);
 
 	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
@@ -537,6 +562,8 @@ static void init_vmcb(struct vcpu_svm *svm)
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct vmcb_save_area *save = &svm->vmcb->save;
 
+	svm->vcpu.fpu_active = 1;
+
 	control->intercept_cr_read = 	INTERCEPT_CR0_MASK |
 					INTERCEPT_CR3_MASK |
 					INTERCEPT_CR4_MASK;
@@ -549,13 +576,19 @@ static void init_vmcb(struct vcpu_svm *svm)
 	control->intercept_dr_read = 	INTERCEPT_DR0_MASK |
 					INTERCEPT_DR1_MASK |
 					INTERCEPT_DR2_MASK |
-					INTERCEPT_DR3_MASK;
+					INTERCEPT_DR3_MASK |
+					INTERCEPT_DR4_MASK |
+					INTERCEPT_DR5_MASK |
+					INTERCEPT_DR6_MASK |
+					INTERCEPT_DR7_MASK;
 
 	control->intercept_dr_write = 	INTERCEPT_DR0_MASK |
 					INTERCEPT_DR1_MASK |
 					INTERCEPT_DR2_MASK |
 					INTERCEPT_DR3_MASK |
+					INTERCEPT_DR4_MASK |
 					INTERCEPT_DR5_MASK |
+					INTERCEPT_DR6_MASK |
 					INTERCEPT_DR7_MASK;
 
 	control->intercept_exceptions = (1 << PF_VECTOR) |
@@ -566,6 +599,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 	control->intercept = 	(1ULL << INTERCEPT_INTR) |
 				(1ULL << INTERCEPT_NMI) |
 				(1ULL << INTERCEPT_SMI) |
+				(1ULL << INTERCEPT_SELECTIVE_CR0) |
 				(1ULL << INTERCEPT_CPUID) |
 				(1ULL << INTERCEPT_INVD) |
 				(1ULL << INTERCEPT_HLT) |
@@ -623,11 +657,12 @@ static void init_vmcb(struct vcpu_svm *svm)
 	save->rip = 0x0000fff0;
 	svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
 
-	/*
-	 * cr0 val on cpu init should be 0x60000010, we enable cpu
-	 * cache by default. the orderly way is to enable cache in bios.
+	/* This is the guest-visible cr0 value.
+	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
 	 */
-	save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP;
+	svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+	kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0);
+
 	save->cr4 = X86_CR4_PAE;
 	/* rdx = ?? */
 
@@ -637,13 +672,9 @@ static void init_vmcb(struct vcpu_svm *svm)
 		control->intercept &= ~((1ULL << INTERCEPT_TASK_SWITCH) |
 					(1ULL << INTERCEPT_INVLPG));
 		control->intercept_exceptions &= ~(1 << PF_VECTOR);
-		control->intercept_cr_read &= ~(INTERCEPT_CR0_MASK|
-						INTERCEPT_CR3_MASK);
-		control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK|
-						 INTERCEPT_CR3_MASK);
+		control->intercept_cr_read &= ~INTERCEPT_CR3_MASK;
+		control->intercept_cr_write &= ~INTERCEPT_CR3_MASK;
 		save->g_pat = 0x0007040600070406ULL;
-		/* enable caching because the QEMU Bios doesn't enable it */
-		save->cr0 = X86_CR0_ET;
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -652,6 +683,11 @@ static void init_vmcb(struct vcpu_svm *svm)
 	svm->nested.vmcb = 0;
 	svm->vcpu.arch.hflags = 0;
 
+	if (svm_has(SVM_FEATURE_PAUSE_FILTER)) {
+		control->pause_filter_count = 3000;
+		control->intercept |= (1ULL << INTERCEPT_PAUSE);
+	}
+
 	enable_gif(svm);
 }
 
@@ -691,29 +727,28 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_svm;
 
+	err = -ENOMEM;
 	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		err = -ENOMEM;
+	if (!page)
 		goto uninit;
-	}
 
-	err = -ENOMEM;
 	msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
 	if (!msrpm_pages)
-		goto uninit;
+		goto free_page1;
 
 	nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
 	if (!nested_msrpm_pages)
-		goto uninit;
-
-	svm->msrpm = page_address(msrpm_pages);
-	svm_vcpu_init_msrpm(svm->msrpm);
+		goto free_page2;
 
 	hsave_page = alloc_page(GFP_KERNEL);
 	if (!hsave_page)
-		goto uninit;
+		goto free_page3;
+
 	svm->nested.hsave = page_address(hsave_page);
 
+	svm->msrpm = page_address(msrpm_pages);
+	svm_vcpu_init_msrpm(svm->msrpm);
+
 	svm->nested.msrpm = page_address(nested_msrpm_pages);
 
 	svm->vmcb = page_address(page);
@@ -723,13 +758,18 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	init_vmcb(svm);
 
 	fx_init(&svm->vcpu);
-	svm->vcpu.fpu_active = 1;
 	svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
 	if (kvm_vcpu_is_bsp(&svm->vcpu))
 		svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
 
 	return &svm->vcpu;
 
+free_page3:
+	__free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page2:
+	__free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page1:
+	__free_page(page);
 uninit:
 	kvm_vcpu_uninit(&svm->vcpu);
 free_svm:
@@ -756,15 +796,18 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	int i;
 
 	if (unlikely(cpu != vcpu->cpu)) {
-		u64 tsc_this, delta;
-
-		/*
-		 * Make sure that the guest sees a monotonically
-		 * increasing TSC.
-		 */
-		rdtscll(tsc_this);
-		delta = vcpu->arch.host_tsc - tsc_this;
-		svm->vmcb->control.tsc_offset += delta;
+		u64 delta;
+
+		if (check_tsc_unstable()) {
+			/*
+			 * Make sure that the guest sees a monotonically
+			 * increasing TSC.
+			 */
+			delta = vcpu->arch.host_tsc - native_read_tsc();
+			svm->vmcb->control.tsc_offset += delta;
+			if (is_nested(svm))
+				svm->nested.hsave->control.tsc_offset += delta;
+		}
 		vcpu->cpu = cpu;
 		kvm_migrate_timers(vcpu);
 		svm->asid_generation = 0;
@@ -783,7 +826,7 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
 		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 
-	rdtscll(vcpu->arch.host_tsc);
+	vcpu->arch.host_tsc = native_read_tsc();
 }
 
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
@@ -914,74 +957,106 @@ static int svm_get_cpl(struct kvm_vcpu *vcpu)
 	return save->cpl;
 }
 
-static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	dt->limit = svm->vmcb->save.idtr.limit;
-	dt->base = svm->vmcb->save.idtr.base;
+	dt->size = svm->vmcb->save.idtr.limit;
+	dt->address = svm->vmcb->save.idtr.base;
 }
 
-static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm->vmcb->save.idtr.limit = dt->limit;
-	svm->vmcb->save.idtr.base = dt->base ;
+	svm->vmcb->save.idtr.limit = dt->size;
+	svm->vmcb->save.idtr.base = dt->address ;
 }
 
-static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	dt->limit = svm->vmcb->save.gdtr.limit;
-	dt->base = svm->vmcb->save.gdtr.base;
+	dt->size = svm->vmcb->save.gdtr.limit;
+	dt->address = svm->vmcb->save.gdtr.base;
 }
 
-static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm->vmcb->save.gdtr.limit = dt->limit;
-	svm->vmcb->save.gdtr.base = dt->base ;
+	svm->vmcb->save.gdtr.limit = dt->size;
+	svm->vmcb->save.gdtr.base = dt->address ;
+}
+
+static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
+{
 }
 
 static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 {
 }
 
+static void update_cr0_intercept(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = svm->vmcb;
+	ulong gcr0 = svm->vcpu.arch.cr0;
+	u64 *hcr0 = &svm->vmcb->save.cr0;
+
+	if (!svm->vcpu.fpu_active)
+		*hcr0 |= SVM_CR0_SELECTIVE_MASK;
+	else
+		*hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK)
+			| (gcr0 & SVM_CR0_SELECTIVE_MASK);
+
+
+	if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
+		vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+		vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+		if (is_nested(svm)) {
+			struct vmcb *hsave = svm->nested.hsave;
+
+			hsave->control.intercept_cr_read  &= ~INTERCEPT_CR0_MASK;
+			hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+			vmcb->control.intercept_cr_read  |= svm->nested.intercept_cr_read;
+			vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write;
+		}
+	} else {
+		svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
+		svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+		if (is_nested(svm)) {
+			struct vmcb *hsave = svm->nested.hsave;
+
+			hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
+			hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+		}
+	}
+}
+
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 #ifdef CONFIG_X86_64
-	if (vcpu->arch.shadow_efer & EFER_LME) {
+	if (vcpu->arch.efer & EFER_LME) {
 		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
-			vcpu->arch.shadow_efer |= EFER_LMA;
+			vcpu->arch.efer |= EFER_LMA;
 			svm->vmcb->save.efer |= EFER_LMA | EFER_LME;
 		}
 
 		if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) {
-			vcpu->arch.shadow_efer &= ~EFER_LMA;
+			vcpu->arch.efer &= ~EFER_LMA;
 			svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME);
 		}
 	}
 #endif
-	if (npt_enabled)
-		goto set;
+	vcpu->arch.cr0 = cr0;
 
-	if ((vcpu->arch.cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) {
-		svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
-		vcpu->fpu_active = 1;
-	}
+	if (!npt_enabled)
+		cr0 |= X86_CR0_PG | X86_CR0_WP;
 
-	vcpu->arch.cr0 = cr0;
-	cr0 |= X86_CR0_PG | X86_CR0_WP;
-	if (!vcpu->fpu_active) {
-		svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
+	if (!vcpu->fpu_active)
 		cr0 |= X86_CR0_TS;
-	}
-set:
 	/*
 	 * re-enable caching here because the QEMU bios
 	 * does not do it - this results in some delay at
@@ -989,6 +1064,7 @@ set:
 	 */
 	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	svm->vmcb->save.cr0 = cr0;
+	update_cr0_intercept(svm);
 }
 
 static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -1041,7 +1117,7 @@ static void update_db_intercept(struct kvm_vcpu *vcpu)
 	svm->vmcb->control.intercept_exceptions &=
 		~((1 << DB_VECTOR) | (1 << BP_VECTOR));
 
-	if (vcpu->arch.singlestep)
+	if (svm->nmi_singlestep)
 		svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR);
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
@@ -1056,26 +1132,16 @@ static void update_db_intercept(struct kvm_vcpu *vcpu)
 		vcpu->guest_debug = 0;
 }
 
-static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
+static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 {
-	int old_debug = vcpu->guest_debug;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	vcpu->guest_debug = dbg->control;
-
-	update_db_intercept(vcpu);
-
 	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
 		svm->vmcb->save.dr7 = dbg->arch.debugreg[7];
 	else
 		svm->vmcb->save.dr7 = vcpu->arch.dr7;
 
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
-	else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
-		svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
-
-	return 0;
+	update_db_intercept(vcpu);
 }
 
 static void load_host_msrs(struct kvm_vcpu *vcpu)
@@ -1092,91 +1158,85 @@ static void save_host_msrs(struct kvm_vcpu *vcpu)
 #endif
 }
 
-static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
+static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 {
-	if (svm_data->next_asid > svm_data->max_asid) {
-		++svm_data->asid_generation;
-		svm_data->next_asid = 1;
+	if (sd->next_asid > sd->max_asid) {
+		++sd->asid_generation;
+		sd->next_asid = 1;
 		svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
 	}
 
-	svm->asid_generation = svm_data->asid_generation;
-	svm->vmcb->control.asid = svm_data->next_asid++;
+	svm->asid_generation = sd->asid_generation;
+	svm->vmcb->control.asid = sd->next_asid++;
 }
 
-static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
+static int svm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *dest)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	unsigned long val;
 
 	switch (dr) {
 	case 0 ... 3:
-		val = vcpu->arch.db[dr];
+		*dest = vcpu->arch.db[dr];
 		break;
+	case 4:
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
+			return EMULATE_FAIL; /* will re-inject UD */
+		/* fall through */
 	case 6:
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
-			val = vcpu->arch.dr6;
+			*dest = vcpu->arch.dr6;
 		else
-			val = svm->vmcb->save.dr6;
+			*dest = svm->vmcb->save.dr6;
 		break;
+	case 5:
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
+			return EMULATE_FAIL; /* will re-inject UD */
+		/* fall through */
 	case 7:
 		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
-			val = vcpu->arch.dr7;
+			*dest = vcpu->arch.dr7;
 		else
-			val = svm->vmcb->save.dr7;
+			*dest = svm->vmcb->save.dr7;
 		break;
-	default:
-		val = 0;
 	}
 
-	return val;
+	return EMULATE_DONE;
 }
 
-static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
-		       int *exception)
+static int svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	*exception = 0;
-
 	switch (dr) {
 	case 0 ... 3:
 		vcpu->arch.db[dr] = value;
 		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
 			vcpu->arch.eff_db[dr] = value;
-		return;
-	case 4 ... 5:
-		if (vcpu->arch.cr4 & X86_CR4_DE)
-			*exception = UD_VECTOR;
-		return;
+		break;
+	case 4:
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
+			return EMULATE_FAIL; /* will re-inject UD */
+		/* fall through */
 	case 6:
-		if (value & 0xffffffff00000000ULL) {
-			*exception = GP_VECTOR;
-			return;
-		}
 		vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1;
-		return;
+		break;
+	case 5:
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
+			return EMULATE_FAIL; /* will re-inject UD */
+		/* fall through */
 	case 7:
-		if (value & 0xffffffff00000000ULL) {
-			*exception = GP_VECTOR;
-			return;
-		}
 		vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1;
 		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
 			svm->vmcb->save.dr7 = vcpu->arch.dr7;
 			vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK);
 		}
-		return;
-	default:
-		/* FIXME: Possible case? */
-		printk(KERN_DEBUG "%s: unexpected dr %u\n",
-		       __func__, dr);
-		*exception = UD_VECTOR;
-		return;
+		break;
 	}
+
+	return EMULATE_DONE;
 }
 
-static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int pf_interception(struct vcpu_svm *svm)
 {
 	u64 fault_address;
 	u32 error_code;
@@ -1185,31 +1245,24 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	error_code = svm->vmcb->control.exit_info_1;
 
 	trace_kvm_page_fault(fault_address, error_code);
-	/*
-	 * FIXME: Tis shouldn't be necessary here, but there is a flush
-	 * missing in the MMU code. Until we find this bug, flush the
-	 * complete TLB here on an NPF
-	 */
-	if (npt_enabled)
-		svm_flush_tlb(&svm->vcpu);
-	else {
-		if (kvm_event_needs_reinjection(&svm->vcpu))
-			kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
-	}
+	if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu))
+		kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
 }
 
-static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int db_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	if (!(svm->vcpu.guest_debug &
 	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
-		!svm->vcpu.arch.singlestep) {
+		!svm->nmi_singlestep) {
 		kvm_queue_exception(&svm->vcpu, DB_VECTOR);
 		return 1;
 	}
 
-	if (svm->vcpu.arch.singlestep) {
-		svm->vcpu.arch.singlestep = false;
+	if (svm->nmi_singlestep) {
+		svm->nmi_singlestep = false;
 		if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
 			svm->vmcb->save.rflags &=
 				~(X86_EFLAGS_TF | X86_EFLAGS_RF);
@@ -1228,35 +1281,56 @@ static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int bp_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	kvm_run->exit_reason = KVM_EXIT_DEBUG;
 	kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
 	kvm_run->debug.arch.exception = BP_VECTOR;
 	return 0;
 }
 
-static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int ud_interception(struct vcpu_svm *svm)
 {
 	int er;
 
-	er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD);
+	er = emulate_instruction(&svm->vcpu, 0, 0, EMULTYPE_TRAP_UD);
 	if (er != EMULATE_DONE)
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
 }
 
-static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static void svm_fpu_activate(struct kvm_vcpu *vcpu)
 {
-	svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
-	if (!(svm->vcpu.arch.cr0 & X86_CR0_TS))
-		svm->vmcb->save.cr0 &= ~X86_CR0_TS;
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u32 excp;
+
+	if (is_nested(svm)) {
+		u32 h_excp, n_excp;
+
+		h_excp  = svm->nested.hsave->control.intercept_exceptions;
+		n_excp  = svm->nested.intercept_exceptions;
+		h_excp &= ~(1 << NM_VECTOR);
+		excp    = h_excp | n_excp;
+	} else {
+		excp  = svm->vmcb->control.intercept_exceptions;
+	        excp &= ~(1 << NM_VECTOR);
+	}
+
+	svm->vmcb->control.intercept_exceptions = excp;
+
 	svm->vcpu.fpu_active = 1;
+	update_cr0_intercept(svm);
+}
 
+static int nm_interception(struct vcpu_svm *svm)
+{
+	svm_fpu_activate(&svm->vcpu);
 	return 1;
 }
 
-static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int mc_interception(struct vcpu_svm *svm)
 {
 	/*
 	 * On an #MC intercept the MCE handler is not called automatically in
@@ -1269,8 +1343,10 @@ static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int shutdown_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	/*
 	 * VMCB is undefined after a SHUTDOWN intercept
 	 * so reinitialize it.
@@ -1282,7 +1358,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 0;
 }
 
-static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int io_interception(struct vcpu_svm *svm)
 {
 	u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
 	int size, in, string;
@@ -1296,7 +1372,7 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 
 	if (string) {
 		if (emulate_instruction(&svm->vcpu,
-					kvm_run, 0, 0, 0) == EMULATE_DO_MMIO)
+					0, 0, 0) == EMULATE_DO_MMIO)
 			return 0;
 		return 1;
 	}
@@ -1306,33 +1382,33 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
 
 	skip_emulated_instruction(&svm->vcpu);
-	return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
+	return kvm_emulate_pio(&svm->vcpu, in, size, port);
 }
 
-static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nmi_interception(struct vcpu_svm *svm)
 {
 	return 1;
 }
 
-static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int intr_interception(struct vcpu_svm *svm)
 {
 	++svm->vcpu.stat.irq_exits;
 	return 1;
 }
 
-static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nop_on_interception(struct vcpu_svm *svm)
 {
 	return 1;
 }
 
-static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int halt_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 1;
 	skip_emulated_instruction(&svm->vcpu);
 	return kvm_emulate_halt(&svm->vcpu);
 }
 
-static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmmcall_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	skip_emulated_instruction(&svm->vcpu);
@@ -1342,7 +1418,7 @@ static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 
 static int nested_svm_check_permissions(struct vcpu_svm *svm)
 {
-	if (!(svm->vcpu.arch.shadow_efer & EFER_SVME)
+	if (!(svm->vcpu.arch.efer & EFER_SVME)
 	    || !is_paging(&svm->vcpu)) {
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 		return 1;
@@ -1359,112 +1435,89 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm)
 static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 				      bool has_error_code, u32 error_code)
 {
-	if (is_nested(svm)) {
-		svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
-		svm->vmcb->control.exit_code_hi = 0;
-		svm->vmcb->control.exit_info_1 = error_code;
-		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
-		if (nested_svm_exit_handled(svm, false)) {
-			nsvm_printk("VMexit -> EXCP 0x%x\n", nr);
-			return 1;
-		}
-	}
-
-	return 0;
-}
-
-static inline int nested_svm_intr(struct vcpu_svm *svm)
-{
-	if (is_nested(svm)) {
-		if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
-			return 0;
+	int vmexit;
 
-		if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
-			return 0;
+	if (!is_nested(svm))
+		return 0;
 
-		svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+	svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
+	svm->vmcb->control.exit_code_hi = 0;
+	svm->vmcb->control.exit_info_1 = error_code;
+	svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
 
-		if (nested_svm_exit_handled(svm, false)) {
-			nsvm_printk("VMexit -> INTR\n");
-			return 1;
-		}
-	}
+	vmexit = nested_svm_intercept(svm);
+	if (vmexit == NESTED_EXIT_DONE)
+		svm->nested.exit_required = true;
 
-	return 0;
+	return vmexit;
 }
 
-static struct page *nested_svm_get_page(struct vcpu_svm *svm, u64 gpa)
+/* This function returns true if it is save to enable the irq window */
+static inline bool nested_svm_intr(struct vcpu_svm *svm)
 {
-	struct page *page;
+	if (!is_nested(svm))
+		return true;
 
-	down_read(&current->mm->mmap_sem);
-	page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
-	up_read(&current->mm->mmap_sem);
+	if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
+		return true;
 
-	if (is_error_page(page)) {
-		printk(KERN_INFO "%s: could not find page at 0x%llx\n",
-		       __func__, gpa);
-		kvm_release_page_clean(page);
-		kvm_inject_gp(&svm->vcpu, 0);
-		return NULL;
+	if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
+		return false;
+
+	svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+
+	if (svm->nested.intercept & 1ULL) {
+		/*
+		 * The #vmexit can't be emulated here directly because this
+		 * code path runs with irqs and preemtion disabled. A
+		 * #vmexit emulation might sleep. Only signal request for
+		 * the #vmexit here.
+		 */
+		svm->nested.exit_required = true;
+		trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
+		return false;
 	}
-	return page;
+
+	return true;
 }
 
-static int nested_svm_do(struct vcpu_svm *svm,
-			 u64 arg1_gpa, u64 arg2_gpa, void *opaque,
-			 int (*handler)(struct vcpu_svm *svm,
-					void *arg1,
-					void *arg2,
-					void *opaque))
+static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
 {
-	struct page *arg1_page;
-	struct page *arg2_page = NULL;
-	void *arg1;
-	void *arg2 = NULL;
-	int retval;
+	struct page *page;
 
-	arg1_page = nested_svm_get_page(svm, arg1_gpa);
-	if(arg1_page == NULL)
-		return 1;
+	might_sleep();
 
-	if (arg2_gpa) {
-		arg2_page = nested_svm_get_page(svm, arg2_gpa);
-		if(arg2_page == NULL) {
-			kvm_release_page_clean(arg1_page);
-			return 1;
-		}
-	}
+	page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
+	if (is_error_page(page))
+		goto error;
 
-	arg1 = kmap_atomic(arg1_page, KM_USER0);
-	if (arg2_gpa)
-		arg2 = kmap_atomic(arg2_page, KM_USER1);
+	*_page = page;
 
-	retval = handler(svm, arg1, arg2, opaque);
+	return kmap(page);
 
-	kunmap_atomic(arg1, KM_USER0);
-	if (arg2_gpa)
-		kunmap_atomic(arg2, KM_USER1);
+error:
+	kvm_release_page_clean(page);
+	kvm_inject_gp(&svm->vcpu, 0);
 
-	kvm_release_page_dirty(arg1_page);
-	if (arg2_gpa)
-		kvm_release_page_dirty(arg2_page);
+	return NULL;
+}
 
-	return retval;
+static void nested_svm_unmap(struct page *page)
+{
+	kunmap(page);
+	kvm_release_page_dirty(page);
 }
 
-static int nested_svm_exit_handled_msr(struct vcpu_svm *svm,
-				       void *arg1, void *arg2,
-				       void *opaque)
+static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 {
-	struct vmcb *nested_vmcb = (struct vmcb *)arg1;
-	u8 *msrpm = (u8 *)arg2;
-	u32 t0, t1;
-	u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
 	u32 param = svm->vmcb->control.exit_info_1 & 1;
+	u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+	bool ret = false;
+	u32 t0, t1;
+	u8 val;
 
-	if (!(nested_vmcb->control.intercept & (1ULL << INTERCEPT_MSR_PROT)))
-		return 0;
+	if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+		return false;
 
 	switch (msr) {
 	case 0 ... 0x1fff:
@@ -1482,88 +1535,105 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm,
 		t0 %= 8;
 		break;
 	default:
-		return 1;
-		break;
+		ret = true;
+		goto out;
 	}
-	if (msrpm[t1] & ((1 << param) << t0))
-		return 1;
 
-	return 0;
+	if (!kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + t1, &val, 1))
+		ret = val & ((1 << param) << t0);
+
+out:
+	return ret;
 }
 
-static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override)
+static int nested_svm_exit_special(struct vcpu_svm *svm)
 {
 	u32 exit_code = svm->vmcb->control.exit_code;
-	bool vmexit = false;
 
-	if (kvm_override) {
-		switch (exit_code) {
-		case SVM_EXIT_INTR:
-		case SVM_EXIT_NMI:
-			return 0;
+	switch (exit_code) {
+	case SVM_EXIT_INTR:
+	case SVM_EXIT_NMI:
+		return NESTED_EXIT_HOST;
 		/* For now we are always handling NPFs when using them */
-		case SVM_EXIT_NPF:
-			if (npt_enabled)
-				return 0;
-			break;
-		/* When we're shadowing, trap PFs */
-		case SVM_EXIT_EXCP_BASE + PF_VECTOR:
-			if (!npt_enabled)
-				return 0;
-			break;
-		default:
-			break;
-		}
+	case SVM_EXIT_NPF:
+		if (npt_enabled)
+			return NESTED_EXIT_HOST;
+		break;
+	/* When we're shadowing, trap PFs */
+	case SVM_EXIT_EXCP_BASE + PF_VECTOR:
+		if (!npt_enabled)
+			return NESTED_EXIT_HOST;
+		break;
+	case SVM_EXIT_EXCP_BASE + NM_VECTOR:
+		nm_interception(svm);
+		break;
+	default:
+		break;
 	}
 
+	return NESTED_EXIT_CONTINUE;
+}
+
+/*
+ * If this function returns true, this #vmexit was already handled
+ */
+static int nested_svm_intercept(struct vcpu_svm *svm)
+{
+	u32 exit_code = svm->vmcb->control.exit_code;
+	int vmexit = NESTED_EXIT_HOST;
+
 	switch (exit_code) {
 	case SVM_EXIT_MSR:
-		if (nested_svm_do(svm, svm->nested.vmcb, svm->nested.vmcb_msrpm,
-				  NULL, nested_svm_exit_handled_msr))
-			vmexit = true;
+		vmexit = nested_svm_exit_handled_msr(svm);
 		break;
 	case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: {
 		u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0);
 		if (svm->nested.intercept_cr_read & cr_bits)
-			vmexit = true;
+			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_WRITE_CR0 ... SVM_EXIT_WRITE_CR8: {
 		u32 cr_bits = 1 << (exit_code - SVM_EXIT_WRITE_CR0);
 		if (svm->nested.intercept_cr_write & cr_bits)
-			vmexit = true;
+			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_READ_DR0 ... SVM_EXIT_READ_DR7: {
 		u32 dr_bits = 1 << (exit_code - SVM_EXIT_READ_DR0);
 		if (svm->nested.intercept_dr_read & dr_bits)
-			vmexit = true;
+			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_WRITE_DR0 ... SVM_EXIT_WRITE_DR7: {
 		u32 dr_bits = 1 << (exit_code - SVM_EXIT_WRITE_DR0);
 		if (svm->nested.intercept_dr_write & dr_bits)
-			vmexit = true;
+			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
 		u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
 		if (svm->nested.intercept_exceptions & excp_bits)
-			vmexit = true;
+			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	default: {
 		u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
-		nsvm_printk("exit code: 0x%x\n", exit_code);
 		if (svm->nested.intercept & exit_bits)
-			vmexit = true;
+			vmexit = NESTED_EXIT_DONE;
 	}
 	}
 
-	if (vmexit) {
-		nsvm_printk("#VMEXIT reason=%04x\n", exit_code);
+	return vmexit;
+}
+
+static int nested_svm_exit_handled(struct vcpu_svm *svm)
+{
+	int vmexit;
+
+	vmexit = nested_svm_intercept(svm);
+
+	if (vmexit == NESTED_EXIT_DONE)
 		nested_svm_vmexit(svm);
-	}
 
 	return vmexit;
 }
@@ -1600,12 +1670,25 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr
 	dst->lbr_ctl              = from->lbr_ctl;
 }
 
-static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
-				  void *arg2, void *opaque)
+static int nested_svm_vmexit(struct vcpu_svm *svm)
 {
-	struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
+	struct page *page;
+
+	trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
+				       vmcb->control.exit_info_1,
+				       vmcb->control.exit_info_2,
+				       vmcb->control.exit_int_info,
+				       vmcb->control.exit_int_info_err);
+
+	nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page);
+	if (!nested_vmcb)
+		return 1;
+
+	/* Exit nested SVM mode */
+	svm->nested.vmcb = 0;
 
 	/* Give the current vmcb to the guest */
 	disable_gif(svm);
@@ -1616,9 +1699,13 @@ static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
 	nested_vmcb->save.ds     = vmcb->save.ds;
 	nested_vmcb->save.gdtr   = vmcb->save.gdtr;
 	nested_vmcb->save.idtr   = vmcb->save.idtr;
+	nested_vmcb->save.cr0    = kvm_read_cr0(&svm->vcpu);
 	if (npt_enabled)
 		nested_vmcb->save.cr3    = vmcb->save.cr3;
+	else
+		nested_vmcb->save.cr3    = svm->vcpu.arch.cr3;
 	nested_vmcb->save.cr2    = vmcb->save.cr2;
+	nested_vmcb->save.cr4    = svm->vcpu.arch.cr4;
 	nested_vmcb->save.rflags = vmcb->save.rflags;
 	nested_vmcb->save.rip    = vmcb->save.rip;
 	nested_vmcb->save.rsp    = vmcb->save.rsp;
@@ -1636,6 +1723,22 @@ static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
 	nested_vmcb->control.exit_info_2       = vmcb->control.exit_info_2;
 	nested_vmcb->control.exit_int_info     = vmcb->control.exit_int_info;
 	nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err;
+
+	/*
+	 * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have
+	 * to make sure that we do not lose injected events. So check event_inj
+	 * here and copy it to exit_int_info if it is valid.
+	 * Exit_int_info and event_inj can't be both valid because the case
+	 * below only happens on a VMRUN instruction intercept which has
+	 * no valid exit_int_info set.
+	 */
+	if (vmcb->control.event_inj & SVM_EVTINJ_VALID) {
+		struct vmcb_control_area *nc = &nested_vmcb->control;
+
+		nc->exit_int_info     = vmcb->control.event_inj;
+		nc->exit_int_info_err = vmcb->control.event_inj_err;
+	}
+
 	nested_vmcb->control.tlb_ctl           = 0;
 	nested_vmcb->control.event_inj         = 0;
 	nested_vmcb->control.event_inj_err     = 0;
@@ -1647,10 +1750,6 @@ static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
 	/* Restore the original control entries */
 	copy_vmcb_control_area(vmcb, hsave);
 
-	/* Kill any pending exceptions */
-	if (svm->vcpu.arch.exception.pending == true)
-		nsvm_printk("WARNING: Pending Exception\n");
-
 	kvm_clear_exception_queue(&svm->vcpu);
 	kvm_clear_interrupt_queue(&svm->vcpu);
 
@@ -1678,18 +1777,7 @@ static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
 	svm->vmcb->save.cpl = 0;
 	svm->vmcb->control.exit_int_info = 0;
 
-	/* Exit nested SVM mode */
-	svm->nested.vmcb = 0;
-
-	return 0;
-}
-
-static int nested_svm_vmexit(struct vcpu_svm *svm)
-{
-	nsvm_printk("VMexit\n");
-	if (nested_svm_do(svm, svm->nested.vmcb, 0,
-			  NULL, nested_svm_vmexit_real))
-		return 1;
+	nested_svm_unmap(page);
 
 	kvm_mmu_reset_context(&svm->vcpu);
 	kvm_mmu_load(&svm->vcpu);
@@ -1697,27 +1785,45 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	return 0;
 }
 
-static int nested_svm_vmrun_msrpm(struct vcpu_svm *svm, void *arg1,
-				  void *arg2, void *opaque)
+static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 {
+	u32 *nested_msrpm;
+	struct page *page;
 	int i;
-	u32 *nested_msrpm = (u32*)arg1;
+
+	nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, &page);
+	if (!nested_msrpm)
+		return false;
+
 	for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++)
 		svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
+
 	svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
 
-	return 0;
+	nested_svm_unmap(page);
+
+	return true;
 }
 
-static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1,
-			    void *arg2, void *opaque)
+static bool nested_svm_vmrun(struct vcpu_svm *svm)
 {
-	struct vmcb *nested_vmcb = (struct vmcb *)arg1;
+	struct vmcb *nested_vmcb;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
+	struct page *page;
+	u64 vmcb_gpa;
 
-	/* nested_vmcb is our indicator if nested SVM is activated */
-	svm->nested.vmcb = svm->vmcb->save.rax;
+	vmcb_gpa = svm->vmcb->save.rax;
+
+	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
+	if (!nested_vmcb)
+		return false;
+
+	trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
+			       nested_vmcb->save.rip,
+			       nested_vmcb->control.int_ctl,
+			       nested_vmcb->control.event_inj,
+			       nested_vmcb->control.nested_ctl);
 
 	/* Clear internal status */
 	kvm_clear_exception_queue(&svm->vcpu);
@@ -1731,8 +1837,8 @@ static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1,
 	hsave->save.ds     = vmcb->save.ds;
 	hsave->save.gdtr   = vmcb->save.gdtr;
 	hsave->save.idtr   = vmcb->save.idtr;
-	hsave->save.efer   = svm->vcpu.arch.shadow_efer;
-	hsave->save.cr0    = svm->vcpu.arch.cr0;
+	hsave->save.efer   = svm->vcpu.arch.efer;
+	hsave->save.cr0    = kvm_read_cr0(&svm->vcpu);
 	hsave->save.cr4    = svm->vcpu.arch.cr4;
 	hsave->save.rflags = vmcb->save.rflags;
 	hsave->save.rip    = svm->next_rip;
@@ -1780,21 +1886,6 @@ static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1,
 	svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
 	svm->vmcb->save.cpl = nested_vmcb->save.cpl;
 
-	/* We don't want a nested guest to be more powerful than the guest,
-	   so all intercepts are ORed */
-	svm->vmcb->control.intercept_cr_read |=
-		nested_vmcb->control.intercept_cr_read;
-	svm->vmcb->control.intercept_cr_write |=
-		nested_vmcb->control.intercept_cr_write;
-	svm->vmcb->control.intercept_dr_read |=
-		nested_vmcb->control.intercept_dr_read;
-	svm->vmcb->control.intercept_dr_write |=
-		nested_vmcb->control.intercept_dr_write;
-	svm->vmcb->control.intercept_exceptions |=
-		nested_vmcb->control.intercept_exceptions;
-
-	svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
-
 	svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
 
 	/* cache intercepts */
@@ -1806,37 +1897,51 @@ static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1,
 	svm->nested.intercept            = nested_vmcb->control.intercept;
 
 	force_new_asid(&svm->vcpu);
-	svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info;
-	svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err;
 	svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
-	if (nested_vmcb->control.int_ctl & V_IRQ_MASK) {
-		nsvm_printk("nSVM Injecting Interrupt: 0x%x\n",
-				nested_vmcb->control.int_ctl);
-	}
 	if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
 		svm->vcpu.arch.hflags |= HF_VINTR_MASK;
 	else
 		svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
 
-	nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n",
-			nested_vmcb->control.exit_int_info,
-			nested_vmcb->control.int_state);
+	if (svm->vcpu.arch.hflags & HF_VINTR_MASK) {
+		/* We only want the cr8 intercept bits of the guest */
+		svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK;
+		svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
+	}
 
+	/* We don't want a nested guest to be more powerful than the guest,
+	   so all intercepts are ORed */
+	svm->vmcb->control.intercept_cr_read |=
+		nested_vmcb->control.intercept_cr_read;
+	svm->vmcb->control.intercept_cr_write |=
+		nested_vmcb->control.intercept_cr_write;
+	svm->vmcb->control.intercept_dr_read |=
+		nested_vmcb->control.intercept_dr_read;
+	svm->vmcb->control.intercept_dr_write |=
+		nested_vmcb->control.intercept_dr_write;
+	svm->vmcb->control.intercept_exceptions |=
+		nested_vmcb->control.intercept_exceptions;
+
+	svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
+
+	svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl;
 	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
 	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
 	svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
-	if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID)
-		nsvm_printk("Injecting Event: 0x%x\n",
-				nested_vmcb->control.event_inj);
 	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
 	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
 
+	nested_svm_unmap(page);
+
+	/* nested_vmcb is our indicator if nested SVM is activated */
+	svm->nested.vmcb = vmcb_gpa;
+
 	enable_gif(svm);
 
-	return 0;
+	return true;
 }
 
-static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
 {
 	to_vmcb->save.fs = from_vmcb->save.fs;
 	to_vmcb->save.gs = from_vmcb->save.gs;
@@ -1850,69 +1955,79 @@ static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
 	to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs;
 	to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp;
 	to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
-
-	return 1;
-}
-
-static int nested_svm_vmload(struct vcpu_svm *svm, void *nested_vmcb,
-			     void *arg2, void *opaque)
-{
-	return nested_svm_vmloadsave((struct vmcb *)nested_vmcb, svm->vmcb);
 }
 
-static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb,
-			     void *arg2, void *opaque)
+static int vmload_interception(struct vcpu_svm *svm)
 {
-	return nested_svm_vmloadsave(svm->vmcb, (struct vmcb *)nested_vmcb);
-}
+	struct vmcb *nested_vmcb;
+	struct page *page;
 
-static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
-{
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	skip_emulated_instruction(&svm->vcpu);
 
-	nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmload);
+	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
+	if (!nested_vmcb)
+		return 1;
+
+	nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
+	nested_svm_unmap(page);
 
 	return 1;
 }
 
-static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmsave_interception(struct vcpu_svm *svm)
 {
+	struct vmcb *nested_vmcb;
+	struct page *page;
+
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	skip_emulated_instruction(&svm->vcpu);
 
-	nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmsave);
+	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
+	if (!nested_vmcb)
+		return 1;
+
+	nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
+	nested_svm_unmap(page);
 
 	return 1;
 }
 
-static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmrun_interception(struct vcpu_svm *svm)
 {
-	nsvm_printk("VMrun\n");
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	skip_emulated_instruction(&svm->vcpu);
 
-	if (nested_svm_do(svm, svm->vmcb->save.rax, 0,
-			  NULL, nested_svm_vmrun))
+	if (!nested_svm_vmrun(svm))
 		return 1;
 
-	if (nested_svm_do(svm, svm->nested.vmcb_msrpm, 0,
-		      NULL, nested_svm_vmrun_msrpm))
-		return 1;
+	if (!nested_svm_vmrun_msrpm(svm))
+		goto failed;
+
+	return 1;
+
+failed:
+
+	svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
+	svm->vmcb->control.exit_code_hi = 0;
+	svm->vmcb->control.exit_info_1  = 0;
+	svm->vmcb->control.exit_info_2  = 0;
+
+	nested_svm_vmexit(svm);
 
 	return 1;
 }
 
-static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int stgi_interception(struct vcpu_svm *svm)
 {
 	if (nested_svm_check_permissions(svm))
 		return 1;
@@ -1925,7 +2040,7 @@ static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int clgi_interception(struct vcpu_svm *svm)
 {
 	if (nested_svm_check_permissions(svm))
 		return 1;
@@ -1942,10 +2057,12 @@ static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int invlpga_interception(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	nsvm_printk("INVLPGA\n");
+
+	trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX],
+			  vcpu->arch.regs[VCPU_REGS_RAX]);
 
 	/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
 	kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]);
@@ -1955,15 +2072,21 @@ static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int invalid_op_interception(struct vcpu_svm *svm,
-				   struct kvm_run *kvm_run)
+static int skinit_interception(struct vcpu_svm *svm)
+{
+	trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]);
+
+	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
+	return 1;
+}
+
+static int invalid_op_interception(struct vcpu_svm *svm)
 {
 	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
 }
 
-static int task_switch_interception(struct vcpu_svm *svm,
-				    struct kvm_run *kvm_run)
+static int task_switch_interception(struct vcpu_svm *svm)
 {
 	u16 tss_selector;
 	int reason;
@@ -2013,14 +2136,14 @@ static int task_switch_interception(struct vcpu_svm *svm,
 	return kvm_task_switch(&svm->vcpu, tss_selector, reason);
 }
 
-static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int cpuid_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
 	kvm_emulate_cpuid(&svm->vcpu);
 	return 1;
 }
 
-static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int iret_interception(struct vcpu_svm *svm)
 {
 	++svm->vcpu.stat.nmi_window_exits;
 	svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
@@ -2028,26 +2151,27 @@ static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int invlpg_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int invlpg_interception(struct vcpu_svm *svm)
 {
-	if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0) != EMULATE_DONE)
+	if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
 		pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
 	return 1;
 }
 
-static int emulate_on_interception(struct vcpu_svm *svm,
-				   struct kvm_run *kvm_run)
+static int emulate_on_interception(struct vcpu_svm *svm)
 {
-	if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE)
+	if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
 		pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
 	return 1;
 }
 
-static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int cr8_write_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
 	/* instruction emulation calls kvm_set_cr8() */
-	emulate_instruction(&svm->vcpu, NULL, 0, 0, 0);
+	emulate_instruction(&svm->vcpu, 0, 0, 0);
 	if (irqchip_in_kernel(svm->vcpu.kvm)) {
 		svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
 		return 1;
@@ -2064,10 +2188,14 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 
 	switch (ecx) {
 	case MSR_IA32_TSC: {
-		u64 tsc;
+		u64 tsc_offset;
+
+		if (is_nested(svm))
+			tsc_offset = svm->nested.hsave->control.tsc_offset;
+		else
+			tsc_offset = svm->vmcb->control.tsc_offset;
 
-		rdtscll(tsc);
-		*data = svm->vmcb->control.tsc_offset + tsc;
+		*data = tsc_offset + native_read_tsc();
 		break;
 	}
 	case MSR_K6_STAR:
@@ -2129,14 +2257,15 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 	return 0;
 }
 
-static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int rdmsr_interception(struct vcpu_svm *svm)
 {
 	u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
 	u64 data;
 
-	if (svm_get_msr(&svm->vcpu, ecx, &data))
+	if (svm_get_msr(&svm->vcpu, ecx, &data)) {
+		trace_kvm_msr_read_ex(ecx);
 		kvm_inject_gp(&svm->vcpu, 0);
-	else {
+	} else {
 		trace_kvm_msr_read(ecx, data);
 
 		svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff;
@@ -2153,10 +2282,17 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 
 	switch (ecx) {
 	case MSR_IA32_TSC: {
-		u64 tsc;
+		u64 tsc_offset = data - native_read_tsc();
+		u64 g_tsc_offset = 0;
+
+		if (is_nested(svm)) {
+			g_tsc_offset = svm->vmcb->control.tsc_offset -
+				       svm->nested.hsave->control.tsc_offset;
+			svm->nested.hsave->control.tsc_offset = tsc_offset;
+		}
+
+		svm->vmcb->control.tsc_offset = tsc_offset + g_tsc_offset;
 
-		rdtscll(tsc);
-		svm->vmcb->control.tsc_offset = data - tsc;
 		break;
 	}
 	case MSR_K6_STAR:
@@ -2215,33 +2351,36 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 	return 0;
 }
 
-static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int wrmsr_interception(struct vcpu_svm *svm)
 {
 	u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
 	u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u)
 		| ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32);
 
-	trace_kvm_msr_write(ecx, data);
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-	if (svm_set_msr(&svm->vcpu, ecx, data))
+	if (svm_set_msr(&svm->vcpu, ecx, data)) {
+		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(&svm->vcpu, 0);
-	else
+	} else {
+		trace_kvm_msr_write(ecx, data);
 		skip_emulated_instruction(&svm->vcpu);
+	}
 	return 1;
 }
 
-static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int msr_interception(struct vcpu_svm *svm)
 {
 	if (svm->vmcb->control.exit_info_1)
-		return wrmsr_interception(svm, kvm_run);
+		return wrmsr_interception(svm);
 	else
-		return rdmsr_interception(svm, kvm_run);
+		return rdmsr_interception(svm);
 }
 
-static int interrupt_window_interception(struct vcpu_svm *svm,
-				   struct kvm_run *kvm_run)
+static int interrupt_window_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	svm_clear_vintr(svm);
 	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 	/*
@@ -2259,13 +2398,18 @@ static int interrupt_window_interception(struct vcpu_svm *svm,
 	return 1;
 }
 
-static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
-				      struct kvm_run *kvm_run) = {
+static int pause_interception(struct vcpu_svm *svm)
+{
+	kvm_vcpu_on_spin(&(svm->vcpu));
+	return 1;
+}
+
+static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR0]           		= emulate_on_interception,
 	[SVM_EXIT_READ_CR3]           		= emulate_on_interception,
 	[SVM_EXIT_READ_CR4]           		= emulate_on_interception,
 	[SVM_EXIT_READ_CR8]           		= emulate_on_interception,
-	/* for now: */
+	[SVM_EXIT_CR0_SEL_WRITE]		= emulate_on_interception,
 	[SVM_EXIT_WRITE_CR0]          		= emulate_on_interception,
 	[SVM_EXIT_WRITE_CR3]          		= emulate_on_interception,
 	[SVM_EXIT_WRITE_CR4]          		= emulate_on_interception,
@@ -2274,11 +2418,17 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_READ_DR1]			= emulate_on_interception,
 	[SVM_EXIT_READ_DR2]			= emulate_on_interception,
 	[SVM_EXIT_READ_DR3]			= emulate_on_interception,
+	[SVM_EXIT_READ_DR4]			= emulate_on_interception,
+	[SVM_EXIT_READ_DR5]			= emulate_on_interception,
+	[SVM_EXIT_READ_DR6]			= emulate_on_interception,
+	[SVM_EXIT_READ_DR7]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR0]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR1]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR2]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR3]			= emulate_on_interception,
+	[SVM_EXIT_WRITE_DR4]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR5]			= emulate_on_interception,
+	[SVM_EXIT_WRITE_DR6]			= emulate_on_interception,
 	[SVM_EXIT_WRITE_DR7]			= emulate_on_interception,
 	[SVM_EXIT_EXCP_BASE + DB_VECTOR]	= db_interception,
 	[SVM_EXIT_EXCP_BASE + BP_VECTOR]	= bp_interception,
@@ -2295,6 +2445,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_CPUID]			= cpuid_interception,
 	[SVM_EXIT_IRET]                         = iret_interception,
 	[SVM_EXIT_INVD]                         = emulate_on_interception,
+	[SVM_EXIT_PAUSE]			= pause_interception,
 	[SVM_EXIT_HLT]				= halt_interception,
 	[SVM_EXIT_INVLPG]			= invlpg_interception,
 	[SVM_EXIT_INVLPGA]			= invlpga_interception,
@@ -2308,44 +2459,52 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_VMSAVE]			= vmsave_interception,
 	[SVM_EXIT_STGI]				= stgi_interception,
 	[SVM_EXIT_CLGI]				= clgi_interception,
-	[SVM_EXIT_SKINIT]			= invalid_op_interception,
+	[SVM_EXIT_SKINIT]			= skinit_interception,
 	[SVM_EXIT_WBINVD]                       = emulate_on_interception,
 	[SVM_EXIT_MONITOR]			= invalid_op_interception,
 	[SVM_EXIT_MWAIT]			= invalid_op_interception,
 	[SVM_EXIT_NPF]				= pf_interception,
 };
 
-static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+static int handle_exit(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_run *kvm_run = vcpu->run;
 	u32 exit_code = svm->vmcb->control.exit_code;
 
 	trace_kvm_exit(exit_code, svm->vmcb->save.rip);
 
+	if (unlikely(svm->nested.exit_required)) {
+		nested_svm_vmexit(svm);
+		svm->nested.exit_required = false;
+
+		return 1;
+	}
+
 	if (is_nested(svm)) {
-		nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n",
-			    exit_code, svm->vmcb->control.exit_info_1,
-			    svm->vmcb->control.exit_info_2, svm->vmcb->save.rip);
-		if (nested_svm_exit_handled(svm, true))
+		int vmexit;
+
+		trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code,
+					svm->vmcb->control.exit_info_1,
+					svm->vmcb->control.exit_info_2,
+					svm->vmcb->control.exit_int_info,
+					svm->vmcb->control.exit_int_info_err);
+
+		vmexit = nested_svm_exit_special(svm);
+
+		if (vmexit == NESTED_EXIT_CONTINUE)
+			vmexit = nested_svm_exit_handled(svm);
+
+		if (vmexit == NESTED_EXIT_DONE)
 			return 1;
 	}
 
 	svm_complete_interrupts(svm);
 
-	if (npt_enabled) {
-		int mmu_reload = 0;
-		if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) {
-			svm_set_cr0(vcpu, svm->vmcb->save.cr0);
-			mmu_reload = 1;
-		}
+	if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
 		vcpu->arch.cr0 = svm->vmcb->save.cr0;
+	if (npt_enabled)
 		vcpu->arch.cr3 = svm->vmcb->save.cr3;
-		if (mmu_reload) {
-			kvm_mmu_reset_context(vcpu);
-			kvm_mmu_load(vcpu);
-		}
-	}
-
 
 	if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
@@ -2369,15 +2528,15 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	return svm_exit_handlers[exit_code](svm, kvm_run);
+	return svm_exit_handlers[exit_code](svm);
 }
 
 static void reload_tss(struct kvm_vcpu *vcpu)
 {
 	int cpu = raw_smp_processor_id();
 
-	struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
-	svm_data->tss_desc->type = 9; /* available 32/64-bit TSS */
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+	sd->tss_desc->type = 9; /* available 32/64-bit TSS */
 	load_TR_desc();
 }
 
@@ -2385,12 +2544,12 @@ static void pre_svm_run(struct vcpu_svm *svm)
 {
 	int cpu = raw_smp_processor_id();
 
-	struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
 	/* FIXME: handle wraparound of asid_generation */
-	if (svm->asid_generation != svm_data->asid_generation)
-		new_asid(svm, svm_data);
+	if (svm->asid_generation != sd->asid_generation)
+		new_asid(svm, sd);
 }
 
 static void svm_inject_nmi(struct kvm_vcpu *vcpu)
@@ -2431,6 +2590,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+		return;
+
 	if (irr == -1)
 		return;
 
@@ -2446,28 +2608,53 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 		!(svm->vcpu.arch.hflags & HF_NMI_MASK);
 }
 
+static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	return !!(svm->vcpu.arch.hflags & HF_NMI_MASK);
+}
+
+static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (masked) {
+		svm->vcpu.arch.hflags |= HF_NMI_MASK;
+		svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+	} else {
+		svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
+		svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+	}
+}
+
 static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb;
-	return (vmcb->save.rflags & X86_EFLAGS_IF) &&
-		!(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
-		gif_set(svm) &&
-		!is_nested(svm);
+	int ret;
+
+	if (!gif_set(svm) ||
+	     (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK))
+		return 0;
+
+	ret = !!(vmcb->save.rflags & X86_EFLAGS_IF);
+
+	if (is_nested(svm))
+		return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK);
+
+	return ret;
 }
 
 static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	nsvm_printk("Trying to open IRQ window\n");
-
-	nested_svm_intr(svm);
 
 	/* In case GIF=0 we can't rely on the CPU to tell us when
 	 * GIF becomes 1, because that's a separate STGI/VMRUN intercept.
 	 * The next time we get that intercept, this function will be
 	 * called again though and we'll get the vintr intercept. */
-	if (gif_set(svm)) {
+	if (gif_set(svm) && nested_svm_intr(svm)) {
 		svm_set_vintr(svm);
 		svm_inject_irq(svm, 0x0);
 	}
@@ -2484,7 +2671,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 	/* Something prevents NMI from been injected. Single step over
 	   possible problem (IRET or exception injection or interrupt
 	   shadow) */
-	vcpu->arch.singlestep = true;
+	svm->nmi_singlestep = true;
 	svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
 	update_db_intercept(vcpu);
 }
@@ -2507,6 +2694,9 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+		return;
+
 	if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) {
 		int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
 		kvm_set_cr8(vcpu, cr8);
@@ -2518,6 +2708,9 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 cr8;
 
+	if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+		return;
+
 	cr8 = kvm_get_cr8(vcpu);
 	svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
 	svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
@@ -2528,6 +2721,9 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 	u8 vector;
 	int type;
 	u32 exitintinfo = svm->vmcb->control.exit_int_info;
+	unsigned int3_injected = svm->int3_injected;
+
+	svm->int3_injected = 0;
 
 	if (svm->vcpu.arch.hflags & HF_IRET_MASK)
 		svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
@@ -2547,12 +2743,21 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 		svm->vcpu.arch.nmi_injected = true;
 		break;
 	case SVM_EXITINTINFO_TYPE_EXEPT:
-		/* In case of software exception do not reinject an exception
-		   vector, but re-execute and instruction instead */
 		if (is_nested(svm))
 			break;
-		if (kvm_exception_is_soft(vector))
+		/*
+		 * In case of software exceptions, do not reinject the vector,
+		 * but re-execute the instruction instead. Rewind RIP first
+		 * if we emulated INT3 before.
+		 */
+		if (kvm_exception_is_soft(vector)) {
+			if (vector == BP_VECTOR && int3_injected &&
+			    kvm_is_linear_rip(&svm->vcpu, svm->int3_rip))
+				kvm_rip_write(&svm->vcpu,
+					      kvm_rip_read(&svm->vcpu) -
+					      int3_injected);
 			break;
+		}
 		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
 			u32 err = svm->vmcb->control.exit_int_info_err;
 			kvm_queue_exception_e(&svm->vcpu, vector, err);
@@ -2574,13 +2779,20 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 #define R "e"
 #endif
 
-static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u16 fs_selector;
 	u16 gs_selector;
 	u16 ldt_selector;
 
+	/*
+	 * A vmexit emulation is required before the vcpu can be executed
+	 * again.
+	 */
+	if (unlikely(svm->nested.exit_required))
+		return;
+
 	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
 	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
 	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
@@ -2593,8 +2805,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	fs_selector = kvm_read_fs();
 	gs_selector = kvm_read_gs();
 	ldt_selector = kvm_read_ldt();
-	if (!is_nested(svm))
-		svm->vmcb->save.cr2 = vcpu->arch.cr2;
+	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 	/* required for live migration with NPT */
 	if (npt_enabled)
 		svm->vmcb->save.cr3 = vcpu->arch.cr3;
@@ -2714,12 +2925,6 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
 
 	svm->vmcb->save.cr3 = root;
 	force_new_asid(vcpu);
-
-	if (vcpu->fpu_active) {
-		svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR);
-		svm->vmcb->save.cr0 |= X86_CR0_TS;
-		vcpu->fpu_active = 0;
-	}
 }
 
 static int is_disabled(void)
@@ -2768,6 +2973,10 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	return 0;
 }
 
+static void svm_cpuid_update(struct kvm_vcpu *vcpu)
+{
+}
+
 static const struct trace_print_flags svm_exit_reasons_str[] = {
 	{ SVM_EXIT_READ_CR0,           		"read_cr0" },
 	{ SVM_EXIT_READ_CR3,	      		"read_cr3" },
@@ -2821,9 +3030,24 @@ static const struct trace_print_flags svm_exit_reasons_str[] = {
 	{ -1, NULL }
 };
 
-static bool svm_gb_page_enable(void)
+static int svm_get_lpage_level(void)
 {
-	return true;
+	return PT_PDPE_LEVEL;
+}
+
+static bool svm_rdtscp_supported(void)
+{
+	return false;
+}
+
+static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR;
+	if (is_nested(svm))
+		svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR;
+	update_cr0_intercept(svm);
 }
 
 static struct kvm_x86_ops svm_x86_ops = {
@@ -2852,6 +3076,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.set_segment = svm_set_segment,
 	.get_cpl = svm_get_cpl,
 	.get_cs_db_l_bits = kvm_get_cs_db_l_bits,
+	.decache_cr0_guest_bits = svm_decache_cr0_guest_bits,
 	.decache_cr4_guest_bits = svm_decache_cr4_guest_bits,
 	.set_cr0 = svm_set_cr0,
 	.set_cr3 = svm_set_cr3,
@@ -2866,6 +3091,8 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
+	.fpu_activate = svm_fpu_activate,
+	.fpu_deactivate = svm_fpu_deactivate,
 
 	.tlb_flush = svm_flush_tlb,
 
@@ -2880,6 +3107,8 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.queue_exception = svm_queue_exception,
 	.interrupt_allowed = svm_interrupt_allowed,
 	.nmi_allowed = svm_nmi_allowed,
+	.get_nmi_mask = svm_get_nmi_mask,
+	.set_nmi_mask = svm_set_nmi_mask,
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
@@ -2889,7 +3118,11 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.get_mt_mask = svm_get_mt_mask,
 
 	.exit_reasons_str = svm_exit_reasons_str,
-	.gb_page_enable = svm_gb_page_enable,
+	.get_lpage_level = svm_get_lpage_level,
+
+	.cpuid_update = svm_cpuid_update,
+
+	.rdtscp_supported = svm_rdtscp_supported,
 };
 
 static int __init svm_init(void)