Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "Small update for KVM:

  ARM:
   - lazy context-switching of FPSIMD registers on arm64
   - "split" regions for vGIC redistributor

  s390:
   - cleanups for nested
   - clock handling
   - crypto
   - storage keys
   - control register bits

  x86:
   - many bugfixes
   - implement more Hyper-V super powers
   - implement lapic_timer_advance_ns even when the LAPIC timer is
     emulated using the processor's VMX preemption timer.
   - two security-related bugfixes at the top of the branch"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (79 commits)
  kvm: fix typo in flag name
  kvm: x86: use correct privilege level for sgdt/sidt/fxsave/fxrstor access
  KVM: x86: pass kvm_vcpu to kvm_read_guest_virt and kvm_write_guest_virt_system
  KVM: x86: introduce linear_{read,write}_system
  kvm: nVMX: Enforce cpl=0 for VMX instructions
  kvm: nVMX: Add support for "VMWRITE to any supported field"
  kvm: nVMX: Restrict VMX capability MSR changes
  KVM: VMX: Optimize tscdeadline timer latency
  KVM: docs: nVMX: Remove known limitations as they do not exist now
  KVM: docs: mmu: KVM support exposing SLAT to guests
  kvm: no need to check return value of debugfs_create functions
  kvm: Make VM ioctl do valloc for some archs
  kvm: Change return type to vm_fault_t
  KVM: docs: mmu: Fix link to NPT presentation from KVM Forum 2008
  kvm: x86: Amend the KVM_GET_SUPPORTED_CPUID API documentation
  KVM: x86: hyperv: declare KVM_CAP_HYPERV_TLBFLUSH capability
  KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}_EX implementation
  KVM: x86: hyperv: simplistic HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE} implementation
  KVM: introduce kvm_make_vcpus_request_mask() API
  KVM: x86: hyperv: do rep check for each hypercall separately
  ...

17 files changed, 813 insertions, 268 deletions

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 5f053d7d1bd9..de27615c51ea 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -13,22 +13,6 @@
 #define CREATE_TRACE_POINTS
 #include <asm/trace/hyperv.h>
 
-/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
-struct hv_flush_pcpu {
-	u64 address_space;
-	u64 flags;
-	u64 processor_mask;
-	u64 gva_list[];
-};
-
-/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
-struct hv_flush_pcpu_ex {
-	u64 address_space;
-	u64 flags;
-	struct hv_vpset hv_vp_set;
-	u64 gva_list[];
-};
-
 /* Each gva in gva_list encodes up to 4096 pages to flush */
 #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
 
@@ -67,8 +51,8 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 				    const struct flush_tlb_info *info)
 {
 	int cpu, vcpu, gva_n, max_gvas;
-	struct hv_flush_pcpu **flush_pcpu;
-	struct hv_flush_pcpu *flush;
+	struct hv_tlb_flush **flush_pcpu;
+	struct hv_tlb_flush *flush;
 	u64 status = U64_MAX;
 	unsigned long flags;
 
@@ -82,7 +66,7 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 
 	local_irq_save(flags);
 
-	flush_pcpu = (struct hv_flush_pcpu **)
+	flush_pcpu = (struct hv_tlb_flush **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	flush = *flush_pcpu;
@@ -152,8 +136,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 				       const struct flush_tlb_info *info)
 {
 	int nr_bank = 0, max_gvas, gva_n;
-	struct hv_flush_pcpu_ex **flush_pcpu;
-	struct hv_flush_pcpu_ex *flush;
+	struct hv_tlb_flush_ex **flush_pcpu;
+	struct hv_tlb_flush_ex *flush;
 	u64 status = U64_MAX;
 	unsigned long flags;
 
@@ -167,7 +151,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 
 	local_irq_save(flags);
 
-	flush_pcpu = (struct hv_flush_pcpu_ex **)
+	flush_pcpu = (struct hv_tlb_flush_ex **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	flush = *flush_pcpu;
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 3bfa92c2793c..b8c89265baf0 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -308,6 +308,9 @@ struct ms_hyperv_tsc_page {
 /* TSC emulation after migration */
 #define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
 
+/* Nested features (CPUID 0x4000000A) EAX */
+#define HV_X64_NESTED_MSR_BITMAP		BIT(19)
+
 struct hv_reenlightenment_control {
 	__u64 vector:8;
 	__u64 reserved1:8;
@@ -678,7 +681,11 @@ struct hv_enlightened_vmcs {
 	u32 hv_clean_fields;
 	u32 hv_padding_32;
 	u32 hv_synthetic_controls;
-	u32 hv_enlightenments_control;
+	struct {
+		u32 nested_flush_hypercall:1;
+		u32 msr_bitmap:1;
+		u32 reserved:30;
+	} hv_enlightenments_control;
 	u32 hv_vp_id;
 
 	u64 hv_vm_id;
@@ -734,4 +741,20 @@ struct ipi_arg_ex {
 	struct hv_vpset vp_set;
 };
 
+/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
+struct hv_tlb_flush {
+	u64 address_space;
+	u64 flags;
+	u64 processor_mask;
+	u64 gva_list[];
+};
+
+/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
+struct hv_tlb_flush_ex {
+	u64 address_space;
+	u64 flags;
+	struct hv_vpset hv_vp_set;
+	u64 gva_list[];
+};
+
 #endif
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index b24b1c8b3979..0f82cd91cd3c 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -107,11 +107,12 @@ struct x86_emulate_ops {
 	 *  @addr:  [IN ] Linear address from which to read.
 	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
 	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 *  @system:[IN ] Whether the access is forced to be at CPL0.
 	 */
 	int (*read_std)(struct x86_emulate_ctxt *ctxt,
 			unsigned long addr, void *val,
 			unsigned int bytes,
-			struct x86_exception *fault);
+			struct x86_exception *fault, bool system);
 
 	/*
 	 * read_phys: Read bytes of standard (non-emulated/special) memory.
@@ -129,10 +130,11 @@ struct x86_emulate_ops {
 	 *  @addr:  [IN ] Linear address to which to write.
 	 *  @val:   [OUT] Value write to memory, zero-extended to 'u_long'.
 	 *  @bytes: [IN ] Number of bytes to write to memory.
+	 *  @system:[IN ] Whether the access is forced to be at CPL0.
 	 */
 	int (*write_std)(struct x86_emulate_ctxt *ctxt,
 			 unsigned long addr, void *val, unsigned int bytes,
-			 struct x86_exception *fault);
+			 struct x86_exception *fault, bool system);
 	/*
 	 * fetch: Read bytes of standard (non-emulated/special) memory.
 	 *        Used for instruction fetch.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f4b2588865e9..c13cd28d9d1b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -258,7 +258,8 @@ union kvm_mmu_page_role {
 		unsigned smep_andnot_wp:1;
 		unsigned smap_andnot_wp:1;
 		unsigned ad_disabled:1;
-		unsigned :7;
+		unsigned guest_mode:1;
+		unsigned :6;
 
 		/*
 		 * This is left at the top of the word so that
@@ -476,6 +477,7 @@ struct kvm_vcpu_hv {
 	struct kvm_hyperv_exit exit;
 	struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT];
 	DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT);
+	cpumask_t tlb_lush;
 };
 
 struct kvm_vcpu_arch {
@@ -995,7 +997,7 @@ struct kvm_x86_ops {
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
-	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
+	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
 	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
@@ -1277,6 +1279,7 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu);
 gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
 			   struct x86_exception *exception);
 gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 997192131b7b..3cd14311edfa 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -269,7 +269,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 		return 0;
 
 	/*
-	 * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex
+	 * Clear all banks up to the maximum possible bank as hv_tlb_flush_ex
 	 * structs are not cleared between calls, we risk flushing unneeded
 	 * vCPUs otherwise.
 	 */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 5db8b0b10766..425e6b8b9547 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -207,7 +207,9 @@ enum vmcs_field {
 	EPTP_LIST_ADDRESS               = 0x00002024,
 	EPTP_LIST_ADDRESS_HIGH          = 0x00002025,
 	VMREAD_BITMAP                   = 0x00002026,
+	VMREAD_BITMAP_HIGH              = 0x00002027,
 	VMWRITE_BITMAP                  = 0x00002028,
+	VMWRITE_BITMAP_HIGH             = 0x00002029,
 	XSS_EXIT_BITMAP                 = 0x0000202C,
 	XSS_EXIT_BITMAP_HIGH            = 0x0000202D,
 	TSC_MULTIPLIER                  = 0x00002032,
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f4f30d0c25c4..5720e78b2f7b 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -404,7 +404,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	const u32 kvm_cpuid_7_0_ecx_x86_features =
 		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
-		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG);
+		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
+		F(CLDEMOTE);
 
 	/* cpuid 7.0.edx*/
 	const u32 kvm_cpuid_7_0_edx_x86_features =
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b3705ae52824..4c4f4263420c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -812,6 +812,19 @@ static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
 	return assign_eip_near(ctxt, ctxt->_eip + rel);
 }
 
+static int linear_read_system(struct x86_emulate_ctxt *ctxt, ulong linear,
+			      void *data, unsigned size)
+{
+	return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception, true);
+}
+
+static int linear_write_system(struct x86_emulate_ctxt *ctxt,
+			       ulong linear, void *data,
+			       unsigned int size)
+{
+	return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception, true);
+}
+
 static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
 			      struct segmented_address addr,
 			      void *data,
@@ -823,7 +836,7 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
 	rc = linearize(ctxt, addr, size, false, &linear);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
-	return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception);
+	return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception, false);
 }
 
 static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
@@ -837,7 +850,7 @@ static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
 	rc = linearize(ctxt, addr, size, true, &linear);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
-	return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception);
+	return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception, false);
 }
 
 /*
@@ -1496,8 +1509,7 @@ static int read_interrupt_descriptor(struct x86_emulate_ctxt *ctxt,
 		return emulate_gp(ctxt, index << 3 | 0x2);
 
 	addr = dt.address + index * 8;
-	return ctxt->ops->read_std(ctxt, addr, desc, sizeof *desc,
-				   &ctxt->exception);
+	return linear_read_system(ctxt, addr, desc, sizeof *desc);
 }
 
 static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt,
@@ -1560,8 +1572,7 @@ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	return ctxt->ops->read_std(ctxt, *desc_addr_p, desc, sizeof(*desc),
-				   &ctxt->exception);
+	return linear_read_system(ctxt, *desc_addr_p, desc, sizeof(*desc));
 }
 
 /* allowed just for 8 bytes segments */
@@ -1575,8 +1586,7 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	return ctxt->ops->write_std(ctxt, addr, desc, sizeof *desc,
-				    &ctxt->exception);
+	return linear_write_system(ctxt, addr, desc, sizeof *desc);
 }
 
 static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
@@ -1737,8 +1747,7 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 				return ret;
 		}
 	} else if (ctxt->mode == X86EMUL_MODE_PROT64) {
-		ret = ctxt->ops->read_std(ctxt, desc_addr+8, &base3,
-				sizeof(base3), &ctxt->exception);
+		ret = linear_read_system(ctxt, desc_addr+8, &base3, sizeof(base3));
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
 		if (emul_is_noncanonical_address(get_desc_base(&seg_desc) |
@@ -2051,11 +2060,11 @@ static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq)
 	eip_addr = dt.address + (irq << 2);
 	cs_addr = dt.address + (irq << 2) + 2;
 
-	rc = ops->read_std(ctxt, cs_addr, &cs, 2, &ctxt->exception);
+	rc = linear_read_system(ctxt, cs_addr, &cs, 2);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = ops->read_std(ctxt, eip_addr, &eip, 2, &ctxt->exception);
+	rc = linear_read_system(ctxt, eip_addr, &eip, 2);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -2919,12 +2928,12 @@ static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt,
 #ifdef CONFIG_X86_64
 	base |= ((u64)base3) << 32;
 #endif
-	r = ops->read_std(ctxt, base + 102, &io_bitmap_ptr, 2, NULL);
+	r = ops->read_std(ctxt, base + 102, &io_bitmap_ptr, 2, NULL, true);
 	if (r != X86EMUL_CONTINUE)
 		return false;
 	if (io_bitmap_ptr + port/8 > desc_limit_scaled(&tr_seg))
 		return false;
-	r = ops->read_std(ctxt, base + io_bitmap_ptr + port/8, &perm, 2, NULL);
+	r = ops->read_std(ctxt, base + io_bitmap_ptr + port/8, &perm, 2, NULL, true);
 	if (r != X86EMUL_CONTINUE)
 		return false;
 	if ((perm >> bit_idx) & mask)
@@ -3053,35 +3062,30 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
 			  u16 tss_selector, u16 old_tss_sel,
 			  ulong old_tss_base, struct desc_struct *new_desc)
 {
-	const struct x86_emulate_ops *ops = ctxt->ops;
 	struct tss_segment_16 tss_seg;
 	int ret;
 	u32 new_tss_base = get_desc_base(new_desc);
 
-	ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
-			    &ctxt->exception);
+	ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
 	save_state_to_tss16(ctxt, &tss_seg);
 
-	ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
-			     &ctxt->exception);
+	ret = linear_write_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
-	ret = ops->read_std(ctxt, new_tss_base, &tss_seg, sizeof tss_seg,
-			    &ctxt->exception);
+	ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof tss_seg);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
 	if (old_tss_sel != 0xffff) {
 		tss_seg.prev_task_link = old_tss_sel;
 
-		ret = ops->write_std(ctxt, new_tss_base,
-				     &tss_seg.prev_task_link,
-				     sizeof tss_seg.prev_task_link,
-				     &ctxt->exception);
+		ret = linear_write_system(ctxt, new_tss_base,
+					  &tss_seg.prev_task_link,
+					  sizeof tss_seg.prev_task_link);
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
 	}
@@ -3197,38 +3201,34 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 			  u16 tss_selector, u16 old_tss_sel,
 			  ulong old_tss_base, struct desc_struct *new_desc)
 {
-	const struct x86_emulate_ops *ops = ctxt->ops;
 	struct tss_segment_32 tss_seg;
 	int ret;
 	u32 new_tss_base = get_desc_base(new_desc);
 	u32 eip_offset = offsetof(struct tss_segment_32, eip);
 	u32 ldt_sel_offset = offsetof(struct tss_segment_32, ldt_selector);
 
-	ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
-			    &ctxt->exception);
+	ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
 	save_state_to_tss32(ctxt, &tss_seg);
 
 	/* Only GP registers and segment selectors are saved */
-	ret = ops->write_std(ctxt, old_tss_base + eip_offset, &tss_seg.eip,
-			     ldt_sel_offset - eip_offset, &ctxt->exception);
+	ret = linear_write_system(ctxt, old_tss_base + eip_offset, &tss_seg.eip,
+				  ldt_sel_offset - eip_offset);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
-	ret = ops->read_std(ctxt, new_tss_base, &tss_seg, sizeof tss_seg,
-			    &ctxt->exception);
+	ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof tss_seg);
 	if (ret != X86EMUL_CONTINUE)
 		return ret;
 
 	if (old_tss_sel != 0xffff) {
 		tss_seg.prev_task_link = old_tss_sel;
 
-		ret = ops->write_std(ctxt, new_tss_base,
-				     &tss_seg.prev_task_link,
-				     sizeof tss_seg.prev_task_link,
-				     &ctxt->exception);
+		ret = linear_write_system(ctxt, new_tss_base,
+					  &tss_seg.prev_task_link,
+					  sizeof tss_seg.prev_task_link);
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
 	}
@@ -4189,7 +4189,9 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt)
 				maxphyaddr = eax & 0xff;
 			else
 				maxphyaddr = 36;
-			rsvd = rsvd_bits(maxphyaddr, 62);
+			rsvd = rsvd_bits(maxphyaddr, 63);
+			if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PCIDE)
+				rsvd &= ~CR3_PCID_INVD;
 		}
 
 		if (new_val & rsvd)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 46ff64da44ca..af8caf965baa 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1242,6 +1242,121 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		return kvm_hv_get_msr(vcpu, msr, pdata);
 }
 
+static __always_inline int get_sparse_bank_no(u64 valid_bank_mask, int bank_no)
+{
+	int i = 0, j;
+
+	if (!(valid_bank_mask & BIT_ULL(bank_no)))
+		return -1;
+
+	for (j = 0; j < bank_no; j++)
+		if (valid_bank_mask & BIT_ULL(j))
+			i++;
+
+	return i;
+}
+
+static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
+			    u16 rep_cnt, bool ex)
+{
+	struct kvm *kvm = current_vcpu->kvm;
+	struct kvm_vcpu_hv *hv_current = &current_vcpu->arch.hyperv;
+	struct hv_tlb_flush_ex flush_ex;
+	struct hv_tlb_flush flush;
+	struct kvm_vcpu *vcpu;
+	unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)] = {0};
+	unsigned long valid_bank_mask = 0;
+	u64 sparse_banks[64];
+	int sparse_banks_len, i;
+	bool all_cpus;
+
+	if (!ex) {
+		if (unlikely(kvm_read_guest(kvm, ingpa, &flush, sizeof(flush))))
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+		trace_kvm_hv_flush_tlb(flush.processor_mask,
+				       flush.address_space, flush.flags);
+
+		sparse_banks[0] = flush.processor_mask;
+		all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
+	} else {
+		if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex,
+					    sizeof(flush_ex))))
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+
+		trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask,
+					  flush_ex.hv_vp_set.format,
+					  flush_ex.address_space,
+					  flush_ex.flags);
+
+		valid_bank_mask = flush_ex.hv_vp_set.valid_bank_mask;
+		all_cpus = flush_ex.hv_vp_set.format !=
+			HV_GENERIC_SET_SPARSE_4K;
+
+		sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) *
+			sizeof(sparse_banks[0]);
+
+		if (!sparse_banks_len && !all_cpus)
+			goto ret_success;
+
+		if (!all_cpus &&
+		    kvm_read_guest(kvm,
+				   ingpa + offsetof(struct hv_tlb_flush_ex,
+						    hv_vp_set.bank_contents),
+				   sparse_banks,
+				   sparse_banks_len))
+			return HV_STATUS_INVALID_HYPERCALL_INPUT;
+	}
+
+	cpumask_clear(&hv_current->tlb_lush);
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
+		int bank = hv->vp_index / 64, sbank = 0;
+
+		if (!all_cpus) {
+			/* Banks >64 can't be represented */
+			if (bank >= 64)
+				continue;
+
+			/* Non-ex hypercalls can only address first 64 vCPUs */
+			if (!ex && bank)
+				continue;
+
+			if (ex) {
+				/*
+				 * Check is the bank of this vCPU is in sparse
+				 * set and get the sparse bank number.
+				 */
+				sbank = get_sparse_bank_no(valid_bank_mask,
+							   bank);
+
+				if (sbank < 0)
+					continue;
+			}
+
+			if (!(sparse_banks[sbank] & BIT_ULL(hv->vp_index % 64)))
+				continue;
+		}
+
+		/*
+		 * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we
+		 * can't analyze it here, flush TLB regardless of the specified
+		 * address space.
+		 */
+		__set_bit(i, vcpu_bitmap);
+	}
+
+	kvm_make_vcpus_request_mask(kvm,
+				    KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP,
+				    vcpu_bitmap, &hv_current->tlb_lush);
+
+ret_success:
+	/* We always do full TLB flush, set rep_done = rep_cnt. */
+	return (u64)HV_STATUS_SUCCESS |
+		((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET);
+}
+
 bool kvm_hv_hypercall_enabled(struct kvm *kvm)
 {
 	return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE;
@@ -1315,7 +1430,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 {
 	u64 param, ingpa, outgpa, ret = HV_STATUS_SUCCESS;
 	uint16_t code, rep_idx, rep_cnt;
-	bool fast, longmode;
+	bool fast, longmode, rep;
 
 	/*
 	 * hypercall generates UD from non zero cpl and real mode
@@ -1345,31 +1460,34 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 #endif
 
 	code = param & 0xffff;
-	fast = (param >> 16) & 0x1;
-	rep_cnt = (param >> 32) & 0xfff;
-	rep_idx = (param >> 48) & 0xfff;
+	fast = !!(param & HV_HYPERCALL_FAST_BIT);
+	rep_cnt = (param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff;
+	rep_idx = (param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff;
+	rep = !!(rep_cnt || rep_idx);
 
 	trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa);
 
-	/* Hypercall continuation is not supported yet */
-	if (rep_cnt || rep_idx) {
-		ret = HV_STATUS_INVALID_HYPERCALL_CODE;
-		goto out;
-	}
-
 	switch (code) {
 	case HVCALL_NOTIFY_LONG_SPIN_WAIT:
+		if (unlikely(rep)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+			break;
+		}
 		kvm_vcpu_on_spin(vcpu, true);
 		break;
 	case HVCALL_SIGNAL_EVENT:
+		if (unlikely(rep)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+			break;
+		}
 		ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
 		if (ret != HV_STATUS_INVALID_PORT_ID)
 			break;
 		/* maybe userspace knows this conn_id: fall through */
 	case HVCALL_POST_MESSAGE:
 		/* don't bother userspace if it has no way to handle it */
-		if (!vcpu_to_synic(vcpu)->active) {
-			ret = HV_STATUS_INVALID_HYPERCALL_CODE;
+		if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
 			break;
 		}
 		vcpu->run->exit_reason = KVM_EXIT_HYPERV;
@@ -1380,12 +1498,39 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		vcpu->arch.complete_userspace_io =
 				kvm_hv_hypercall_complete_userspace;
 		return 0;
+	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST:
+		if (unlikely(fast || !rep_cnt || rep_idx)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+			break;
+		}
+		ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false);
+		break;
+	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE:
+		if (unlikely(fast || rep)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+			break;
+		}
+		ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false);
+		break;
+	case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX:
+		if (unlikely(fast || !rep_cnt || rep_idx)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+			break;
+		}
+		ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true);
+		break;
+	case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX:
+		if (unlikely(fast || rep)) {
+			ret = HV_STATUS_INVALID_HYPERCALL_INPUT;
+			break;
+		}
+		ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true);
+		break;
 	default:
 		ret = HV_STATUS_INVALID_HYPERCALL_CODE;
 		break;
 	}
 
-out:
 	return kvm_hv_hypercall_complete(vcpu, ret);
 }
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3773c4625114..b5cd8465d44f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2002,13 +2002,11 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		}
 	}
 
-	if ((old_value ^ value) & X2APIC_ENABLE) {
-		if (value & X2APIC_ENABLE) {
-			kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id);
-			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true);
-		} else
-			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false);
-	}
+	if (((old_value ^ value) & X2APIC_ENABLE) && (value & X2APIC_ENABLE))
+		kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id);
+
+	if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE))
+		kvm_x86_ops->set_virtual_apic_mode(vcpu);
 
 	apic->base_address = apic->vcpu->arch.apic_base &
 			     MSR_IA32_APICBASE_BASE;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index edce055e9fd7..ed0ed39abd36 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -16,6 +16,13 @@
 #define APIC_BUS_CYCLE_NS       1
 #define APIC_BUS_FREQUENCY      (1000000000ULL / APIC_BUS_CYCLE_NS)
 
+enum lapic_mode {
+	LAPIC_MODE_DISABLED = 0,
+	LAPIC_MODE_INVALID = X2APIC_ENABLE,
+	LAPIC_MODE_XAPIC = MSR_IA32_APICBASE_ENABLE,
+	LAPIC_MODE_X2APIC = MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE,
+};
+
 struct kvm_timer {
 	struct hrtimer timer;
 	s64 period; 				/* unit: ns */
@@ -89,6 +96,7 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
 int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
 int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
+enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
@@ -220,4 +228,10 @@ void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu);
 void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu);
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu);
 void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu);
+
+static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
+{
+	return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
+}
+
 #endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d634f0332c0f..d594690d8b95 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -222,7 +222,6 @@ static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK |
 static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT;
 
 static void mmu_spte_set(u64 *sptep, u64 spte);
-static void mmu_free_roots(struct kvm_vcpu *vcpu);
 
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value)
 {
@@ -3343,51 +3342,48 @@ out_unlock:
 	return RET_PF_RETRY;
 }
 
-
-static void mmu_free_roots(struct kvm_vcpu *vcpu)
+static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
+			       struct list_head *invalid_list)
 {
-	int i;
 	struct kvm_mmu_page *sp;
-	LIST_HEAD(invalid_list);
 
-	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+	if (!VALID_PAGE(*root_hpa))
 		return;
 
-	if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL &&
-	    (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL ||
-	     vcpu->arch.mmu.direct_map)) {
-		hpa_t root = vcpu->arch.mmu.root_hpa;
+	sp = page_header(*root_hpa & PT64_BASE_ADDR_MASK);
+	--sp->root_count;
+	if (!sp->root_count && sp->role.invalid)
+		kvm_mmu_prepare_zap_page(kvm, sp, invalid_list);
 
-		spin_lock(&vcpu->kvm->mmu_lock);
-		sp = page_header(root);
-		--sp->root_count;
-		if (!sp->root_count && sp->role.invalid) {
-			kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list);
-			kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
-		}
-		spin_unlock(&vcpu->kvm->mmu_lock);
-		vcpu->arch.mmu.root_hpa = INVALID_PAGE;
+	*root_hpa = INVALID_PAGE;
+}
+
+void kvm_mmu_free_roots(struct kvm_vcpu *vcpu)
+{
+	int i;
+	LIST_HEAD(invalid_list);
+	struct kvm_mmu *mmu = &vcpu->arch.mmu;
+
+	if (!VALID_PAGE(mmu->root_hpa))
 		return;
-	}
 
 	spin_lock(&vcpu->kvm->mmu_lock);
-	for (i = 0; i < 4; ++i) {
-		hpa_t root = vcpu->arch.mmu.pae_root[i];
 
-		if (root) {
-			root &= PT64_BASE_ADDR_MASK;
-			sp = page_header(root);
-			--sp->root_count;
-			if (!sp->root_count && sp->role.invalid)
-				kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
-							 &invalid_list);
-		}
-		vcpu->arch.mmu.pae_root[i] = INVALID_PAGE;
+	if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL &&
+	    (mmu->root_level >= PT64_ROOT_4LEVEL || mmu->direct_map)) {
+		mmu_free_root_page(vcpu->kvm, &mmu->root_hpa, &invalid_list);
+	} else {
+		for (i = 0; i < 4; ++i)
+			if (mmu->pae_root[i] != 0)
+				mmu_free_root_page(vcpu->kvm, &mmu->pae_root[i],
+						   &invalid_list);
+		mmu->root_hpa = INVALID_PAGE;
 	}
+
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
 	spin_unlock(&vcpu->kvm->mmu_lock);
-	vcpu->arch.mmu.root_hpa = INVALID_PAGE;
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_free_roots);
 
 static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn)
 {
@@ -3720,7 +3716,6 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
 	 */
 	return RET_PF_RETRY;
 }
-EXPORT_SYMBOL_GPL(handle_mmio_page_fault);
 
 static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu,
 					 u32 error_code, gfn_t gfn)
@@ -3812,6 +3807,14 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	struct kvm_memory_slot *slot;
 	bool async;
 
+	/*
+	 * Don't expose private memslots to L2.
+	 */
+	if (is_guest_mode(vcpu) && !kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+		*pfn = KVM_PFN_NOSLOT;
+		return false;
+	}
+
 	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	async = false;
 	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable);
@@ -3951,7 +3954,7 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu,
 
 void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu)
 {
-	mmu_free_roots(vcpu);
+	kvm_mmu_free_roots(vcpu);
 }
 
 static unsigned long get_cr3(struct kvm_vcpu *vcpu)
@@ -4473,6 +4476,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	struct kvm_mmu *context = &vcpu->arch.mmu;
 
 	context->base_role.word = 0;
+	context->base_role.guest_mode = is_guest_mode(vcpu);
 	context->base_role.smm = is_smm(vcpu);
 	context->base_role.ad_disabled = (shadow_accessed_mask == 0);
 	context->page_fault = tdp_page_fault;
@@ -4539,6 +4543,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 		= smep && !is_write_protection(vcpu);
 	context->base_role.smap_andnot_wp
 		= smap && !is_write_protection(vcpu);
+	context->base_role.guest_mode = is_guest_mode(vcpu);
 	context->base_role.smm = is_smm(vcpu);
 	reset_shadow_zero_bits_mask(vcpu, context);
 }
@@ -4564,7 +4569,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = false;
 	context->base_role.ad_disabled = !accessed_dirty;
-
+	context->base_role.guest_mode = 1;
 	update_permission_bitmask(vcpu, context, true);
 	update_pkru_bitmask(vcpu, context, true);
 	update_last_nonleaf_level(vcpu, context);
@@ -4664,7 +4669,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load);
 
 void kvm_mmu_unload(struct kvm_vcpu *vcpu)
 {
-	mmu_free_roots(vcpu);
+	kvm_mmu_free_roots(vcpu);
 	WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unload);
@@ -4825,6 +4830,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	mask.smep_andnot_wp = 1;
 	mask.smap_andnot_wp = 1;
 	mask.smm = 1;
+	mask.guest_mode = 1;
 	mask.ad_disabled = 1;
 
 	/*
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 950ec50f77c3..695b0bd02220 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1768,7 +1768,10 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
 	unsigned long npages, npinned, size;
 	unsigned long locked, lock_limit;
 	struct page **pages;
-	int first, last;
+	unsigned long first, last;
+
+	if (ulen == 0 || uaddr + ulen < uaddr)
+		return NULL;
 
 	/* Calculate number of pages. */
 	first = (uaddr & PAGE_MASK) >> PAGE_SHIFT;
@@ -1855,13 +1858,13 @@ static void __unregister_enc_region_locked(struct kvm *kvm,
 
 static struct kvm *svm_vm_alloc(void)
 {
-	struct kvm_svm *kvm_svm = kzalloc(sizeof(struct kvm_svm), GFP_KERNEL);
+	struct kvm_svm *kvm_svm = vzalloc(sizeof(struct kvm_svm));
 	return &kvm_svm->kvm;
 }
 
 static void svm_vm_free(struct kvm *kvm)
 {
-	kfree(to_kvm_svm(kvm));
+	vfree(to_kvm_svm(kvm));
 }
 
 static void sev_vm_destroy(struct kvm *kvm)
@@ -5062,7 +5065,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 		set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
 }
 
-static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
+static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 {
 	return;
 }
@@ -6949,6 +6952,9 @@ static int svm_register_enc_region(struct kvm *kvm,
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 
+	if (range->addr > ULONG_MAX || range->size > ULONG_MAX)
+		return -EINVAL;
+
 	region = kzalloc(sizeof(*region), GFP_KERNEL);
 	if (!region)
 		return -ENOMEM;
@@ -7100,7 +7106,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
-	.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
+	.set_virtual_apic_mode = svm_set_virtual_apic_mode,
 	.get_enable_apicv = svm_get_enable_apicv,
 	.refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 9807c314c478..0f997683404f 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1367,6 +1367,57 @@ TRACE_EVENT(kvm_hv_timer_state,
 			__entry->vcpu_id,
 			__entry->hv_timer_in_use)
 );
+
+/*
+ * Tracepoint for kvm_hv_flush_tlb.
+ */
+TRACE_EVENT(kvm_hv_flush_tlb,
+	TP_PROTO(u64 processor_mask, u64 address_space, u64 flags),
+	TP_ARGS(processor_mask, address_space, flags),
+
+	TP_STRUCT__entry(
+		__field(u64, processor_mask)
+		__field(u64, address_space)
+		__field(u64, flags)
+	),
+
+	TP_fast_assign(
+		__entry->processor_mask = processor_mask;
+		__entry->address_space = address_space;
+		__entry->flags = flags;
+	),
+
+	TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx",
+		  __entry->processor_mask, __entry->address_space,
+		  __entry->flags)
+);
+
+/*
+ * Tracepoint for kvm_hv_flush_tlb_ex.
+ */
+TRACE_EVENT(kvm_hv_flush_tlb_ex,
+	TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags),
+	TP_ARGS(valid_bank_mask, format, address_space, flags),
+
+	TP_STRUCT__entry(
+		__field(u64, valid_bank_mask)
+		__field(u64, format)
+		__field(u64, address_space)
+		__field(u64, flags)
+	),
+
+	TP_fast_assign(
+		__entry->valid_bank_mask = valid_bank_mask;
+		__entry->format = format;
+		__entry->address_space = address_space;
+		__entry->flags = flags;
+	),
+
+	TP_printk("valid_bank_mask 0x%llx format 0x%llx "
+		  "address_space 0x%llx flags 0x%llx",
+		  __entry->valid_bank_mask, __entry->format,
+		  __entry->address_space, __entry->flags)
+);
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 40aa29204baf..fc61e25966e4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -242,7 +242,11 @@ struct shared_msr_entry {
  * underlying hardware which will be used to run L2.
  * This structure is packed to ensure that its layout is identical across
  * machines (necessary for live migration).
- * If there are changes in this struct, VMCS12_REVISION must be changed.
+ *
+ * IMPORTANT: Changing the layout of existing fields in this structure
+ * will break save/restore compatibility with older kvm releases. When
+ * adding new fields, either use space in the reserved padding* arrays
+ * or add the new fields to the end of the structure.
  */
 typedef u64 natural_width;
 struct __packed vmcs12 {
@@ -265,17 +269,14 @@ struct __packed vmcs12 {
 	u64 virtual_apic_page_addr;
 	u64 apic_access_addr;
 	u64 posted_intr_desc_addr;
-	u64 vm_function_control;
 	u64 ept_pointer;
 	u64 eoi_exit_bitmap0;
 	u64 eoi_exit_bitmap1;
 	u64 eoi_exit_bitmap2;
 	u64 eoi_exit_bitmap3;
-	u64 eptp_list_address;
 	u64 xss_exit_bitmap;
 	u64 guest_physical_address;
 	u64 vmcs_link_pointer;
-	u64 pml_address;
 	u64 guest_ia32_debugctl;
 	u64 guest_ia32_pat;
 	u64 guest_ia32_efer;
@@ -288,7 +289,12 @@ struct __packed vmcs12 {
 	u64 host_ia32_pat;
 	u64 host_ia32_efer;
 	u64 host_ia32_perf_global_ctrl;
-	u64 padding64[8]; /* room for future expansion */
+	u64 vmread_bitmap;
+	u64 vmwrite_bitmap;
+	u64 vm_function_control;
+	u64 eptp_list_address;
+	u64 pml_address;
+	u64 padding64[3]; /* room for future expansion */
 	/*
 	 * To allow migration of L1 (complete with its L2 guests) between
 	 * machines of different natural widths (32 or 64 bit), we cannot have
@@ -397,7 +403,6 @@ struct __packed vmcs12 {
 	u16 guest_ldtr_selector;
 	u16 guest_tr_selector;
 	u16 guest_intr_status;
-	u16 guest_pml_index;
 	u16 host_es_selector;
 	u16 host_cs_selector;
 	u16 host_ss_selector;
@@ -405,12 +410,172 @@ struct __packed vmcs12 {
 	u16 host_fs_selector;
 	u16 host_gs_selector;
 	u16 host_tr_selector;
+	u16 guest_pml_index;
 };
 
 /*
+ * For save/restore compatibility, the vmcs12 field offsets must not change.
+ */
+#define CHECK_OFFSET(field, loc)				\
+	BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc),	\
+		"Offset of " #field " in struct vmcs12 has changed.")
+
+static inline void vmx_check_vmcs12_offsets(void) {
+	CHECK_OFFSET(revision_id, 0);
+	CHECK_OFFSET(abort, 4);
+	CHECK_OFFSET(launch_state, 8);
+	CHECK_OFFSET(io_bitmap_a, 40);
+	CHECK_OFFSET(io_bitmap_b, 48);
+	CHECK_OFFSET(msr_bitmap, 56);
+	CHECK_OFFSET(vm_exit_msr_store_addr, 64);
+	CHECK_OFFSET(vm_exit_msr_load_addr, 72);
+	CHECK_OFFSET(vm_entry_msr_load_addr, 80);
+	CHECK_OFFSET(tsc_offset, 88);
+	CHECK_OFFSET(virtual_apic_page_addr, 96);
+	CHECK_OFFSET(apic_access_addr, 104);
+	CHECK_OFFSET(posted_intr_desc_addr, 112);
+	CHECK_OFFSET(ept_pointer, 120);
+	CHECK_OFFSET(eoi_exit_bitmap0, 128);
+	CHECK_OFFSET(eoi_exit_bitmap1, 136);
+	CHECK_OFFSET(eoi_exit_bitmap2, 144);
+	CHECK_OFFSET(eoi_exit_bitmap3, 152);
+	CHECK_OFFSET(xss_exit_bitmap, 160);
+	CHECK_OFFSET(guest_physical_address, 168);
+	CHECK_OFFSET(vmcs_link_pointer, 176);
+	CHECK_OFFSET(guest_ia32_debugctl, 184);
+	CHECK_OFFSET(guest_ia32_pat, 192);
+	CHECK_OFFSET(guest_ia32_efer, 200);
+	CHECK_OFFSET(guest_ia32_perf_global_ctrl, 208);
+	CHECK_OFFSET(guest_pdptr0, 216);
+	CHECK_OFFSET(guest_pdptr1, 224);
+	CHECK_OFFSET(guest_pdptr2, 232);
+	CHECK_OFFSET(guest_pdptr3, 240);
+	CHECK_OFFSET(guest_bndcfgs, 248);
+	CHECK_OFFSET(host_ia32_pat, 256);
+	CHECK_OFFSET(host_ia32_efer, 264);
+	CHECK_OFFSET(host_ia32_perf_global_ctrl, 272);
+	CHECK_OFFSET(vmread_bitmap, 280);
+	CHECK_OFFSET(vmwrite_bitmap, 288);
+	CHECK_OFFSET(vm_function_control, 296);
+	CHECK_OFFSET(eptp_list_address, 304);
+	CHECK_OFFSET(pml_address, 312);
+	CHECK_OFFSET(cr0_guest_host_mask, 344);
+	CHECK_OFFSET(cr4_guest_host_mask, 352);
+	CHECK_OFFSET(cr0_read_shadow, 360);
+	CHECK_OFFSET(cr4_read_shadow, 368);
+	CHECK_OFFSET(cr3_target_value0, 376);
+	CHECK_OFFSET(cr3_target_value1, 384);
+	CHECK_OFFSET(cr3_target_value2, 392);
+	CHECK_OFFSET(cr3_target_value3, 400);
+	CHECK_OFFSET(exit_qualification, 408);
+	CHECK_OFFSET(guest_linear_address, 416);
+	CHECK_OFFSET(guest_cr0, 424);
+	CHECK_OFFSET(guest_cr3, 432);
+	CHECK_OFFSET(guest_cr4, 440);
+	CHECK_OFFSET(guest_es_base, 448);
+	CHECK_OFFSET(guest_cs_base, 456);
+	CHECK_OFFSET(guest_ss_base, 464);
+	CHECK_OFFSET(guest_ds_base, 472);
+	CHECK_OFFSET(guest_fs_base, 480);
+	CHECK_OFFSET(guest_gs_base, 488);
+	CHECK_OFFSET(guest_ldtr_base, 496);
+	CHECK_OFFSET(guest_tr_base, 504);
+	CHECK_OFFSET(guest_gdtr_base, 512);
+	CHECK_OFFSET(guest_idtr_base, 520);
+	CHECK_OFFSET(guest_dr7, 528);
+	CHECK_OFFSET(guest_rsp, 536);
+	CHECK_OFFSET(guest_rip, 544);
+	CHECK_OFFSET(guest_rflags, 552);
+	CHECK_OFFSET(guest_pending_dbg_exceptions, 560);
+	CHECK_OFFSET(guest_sysenter_esp, 568);
+	CHECK_OFFSET(guest_sysenter_eip, 576);
+	CHECK_OFFSET(host_cr0, 584);
+	CHECK_OFFSET(host_cr3, 592);
+	CHECK_OFFSET(host_cr4, 600);
+	CHECK_OFFSET(host_fs_base, 608);
+	CHECK_OFFSET(host_gs_base, 616);
+	CHECK_OFFSET(host_tr_base, 624);
+	CHECK_OFFSET(host_gdtr_base, 632);
+	CHECK_OFFSET(host_idtr_base, 640);
+	CHECK_OFFSET(host_ia32_sysenter_esp, 648);
+	CHECK_OFFSET(host_ia32_sysenter_eip, 656);
+	CHECK_OFFSET(host_rsp, 664);
+	CHECK_OFFSET(host_rip, 672);
+	CHECK_OFFSET(pin_based_vm_exec_control, 744);
+	CHECK_OFFSET(cpu_based_vm_exec_control, 748);
+	CHECK_OFFSET(exception_bitmap, 752);
+	CHECK_OFFSET(page_fault_error_code_mask, 756);
+	CHECK_OFFSET(page_fault_error_code_match, 760);
+	CHECK_OFFSET(cr3_target_count, 764);
+	CHECK_OFFSET(vm_exit_controls, 768);
+	CHECK_OFFSET(vm_exit_msr_store_count, 772);
+	CHECK_OFFSET(vm_exit_msr_load_count, 776);
+	CHECK_OFFSET(vm_entry_controls, 780);
+	CHECK_OFFSET(vm_entry_msr_load_count, 784);
+	CHECK_OFFSET(vm_entry_intr_info_field, 788);
+	CHECK_OFFSET(vm_entry_exception_error_code, 792);
+	CHECK_OFFSET(vm_entry_instruction_len, 796);
+	CHECK_OFFSET(tpr_threshold, 800);
+	CHECK_OFFSET(secondary_vm_exec_control, 804);
+	CHECK_OFFSET(vm_instruction_error, 808);
+	CHECK_OFFSET(vm_exit_reason, 812);
+	CHECK_OFFSET(vm_exit_intr_info, 816);
+	CHECK_OFFSET(vm_exit_intr_error_code, 820);
+	CHECK_OFFSET(idt_vectoring_info_field, 824);
+	CHECK_OFFSET(idt_vectoring_error_code, 828);
+	CHECK_OFFSET(vm_exit_instruction_len, 832);
+	CHECK_OFFSET(vmx_instruction_info, 836);
+	CHECK_OFFSET(guest_es_limit, 840);
+	CHECK_OFFSET(guest_cs_limit, 844);
+	CHECK_OFFSET(guest_ss_limit, 848);
+	CHECK_OFFSET(guest_ds_limit, 852);
+	CHECK_OFFSET(guest_fs_limit, 856);
+	CHECK_OFFSET(guest_gs_limit, 860);
+	CHECK_OFFSET(guest_ldtr_limit, 864);
+	CHECK_OFFSET(guest_tr_limit, 868);
+	CHECK_OFFSET(guest_gdtr_limit, 872);
+	CHECK_OFFSET(guest_idtr_limit, 876);
+	CHECK_OFFSET(guest_es_ar_bytes, 880);
+	CHECK_OFFSET(guest_cs_ar_bytes, 884);
+	CHECK_OFFSET(guest_ss_ar_bytes, 888);
+	CHECK_OFFSET(guest_ds_ar_bytes, 892);
+	CHECK_OFFSET(guest_fs_ar_bytes, 896);
+	CHECK_OFFSET(guest_gs_ar_bytes, 900);
+	CHECK_OFFSET(guest_ldtr_ar_bytes, 904);
+	CHECK_OFFSET(guest_tr_ar_bytes, 908);
+	CHECK_OFFSET(guest_interruptibility_info, 912);
+	CHECK_OFFSET(guest_activity_state, 916);
+	CHECK_OFFSET(guest_sysenter_cs, 920);
+	CHECK_OFFSET(host_ia32_sysenter_cs, 924);
+	CHECK_OFFSET(vmx_preemption_timer_value, 928);
+	CHECK_OFFSET(virtual_processor_id, 960);
+	CHECK_OFFSET(posted_intr_nv, 962);
+	CHECK_OFFSET(guest_es_selector, 964);
+	CHECK_OFFSET(guest_cs_selector, 966);
+	CHECK_OFFSET(guest_ss_selector, 968);
+	CHECK_OFFSET(guest_ds_selector, 970);
+	CHECK_OFFSET(guest_fs_selector, 972);
+	CHECK_OFFSET(guest_gs_selector, 974);
+	CHECK_OFFSET(guest_ldtr_selector, 976);
+	CHECK_OFFSET(guest_tr_selector, 978);
+	CHECK_OFFSET(guest_intr_status, 980);
+	CHECK_OFFSET(host_es_selector, 982);
+	CHECK_OFFSET(host_cs_selector, 984);
+	CHECK_OFFSET(host_ss_selector, 986);
+	CHECK_OFFSET(host_ds_selector, 988);
+	CHECK_OFFSET(host_fs_selector, 990);
+	CHECK_OFFSET(host_gs_selector, 992);
+	CHECK_OFFSET(host_tr_selector, 994);
+	CHECK_OFFSET(guest_pml_index, 996);
+}
+
+/*
  * VMCS12_REVISION is an arbitrary id that should be changed if the content or
  * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and
  * VMPTRLD verifies that the VMCS region that L1 is loading contains this id.
+ *
+ * IMPORTANT: Changing this value will break save/restore compatibility with
+ * older kvm releases.
  */
 #define VMCS12_REVISION 0x11e57ed0
 
@@ -481,7 +646,8 @@ struct nested_vmx {
 	bool sync_shadow_vmcs;
 	bool dirty_vmcs12;
 
-	bool change_vmcs01_virtual_x2apic_mode;
+	bool change_vmcs01_virtual_apic_mode;
+
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
 
@@ -761,6 +927,7 @@ static const unsigned short vmcs_field_to_offset_table[] = {
 	FIELD64(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr),
 	FIELD64(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr),
 	FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr),
+	FIELD64(PML_ADDRESS, pml_address),
 	FIELD64(TSC_OFFSET, tsc_offset),
 	FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr),
 	FIELD64(APIC_ACCESS_ADDR, apic_access_addr),
@@ -772,10 +939,11 @@ static const unsigned short vmcs_field_to_offset_table[] = {
 	FIELD64(EOI_EXIT_BITMAP2, eoi_exit_bitmap2),
 	FIELD64(EOI_EXIT_BITMAP3, eoi_exit_bitmap3),
 	FIELD64(EPTP_LIST_ADDRESS, eptp_list_address),
+	FIELD64(VMREAD_BITMAP, vmread_bitmap),
+	FIELD64(VMWRITE_BITMAP, vmwrite_bitmap),
 	FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
 	FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
 	FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
-	FIELD64(PML_ADDRESS, pml_address),
 	FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
 	FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
 	FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
@@ -1089,6 +1257,16 @@ static inline u16 evmcs_read16(unsigned long field)
 	return *(u16 *)((char *)current_evmcs + offset);
 }
 
+static inline void evmcs_touch_msr_bitmap(void)
+{
+	if (unlikely(!current_evmcs))
+		return;
+
+	if (current_evmcs->hv_enlightenments_control.msr_bitmap)
+		current_evmcs->hv_clean_fields &=
+			~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
+}
+
 static void evmcs_load(u64 phys_addr)
 {
 	struct hv_vp_assist_page *vp_ap =
@@ -1173,6 +1351,7 @@ static inline u32 evmcs_read32(unsigned long field) { return 0; }
 static inline u16 evmcs_read16(unsigned long field) { return 0; }
 static inline void evmcs_load(u64 phys_addr) {}
 static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
+static inline void evmcs_touch_msr_bitmap(void) {}
 #endif /* IS_ENABLED(CONFIG_HYPERV) */
 
 static inline bool is_exception_n(u32 intr_info, u8 vector)
@@ -1393,6 +1572,11 @@ static inline bool cpu_has_vmx_invept_global(void)
 	return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
 }
 
+static inline bool cpu_has_vmx_invvpid_individual_addr(void)
+{
+	return vmx_capability.vpid & VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT;
+}
+
 static inline bool cpu_has_vmx_invvpid_single(void)
 {
 	return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT;
@@ -1510,6 +1694,17 @@ static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
 	return vmx_misc_cr3_count(to_vmx(vcpu)->nested.msrs.misc_low);
 }
 
+/*
+ * Do the virtual VMX capability MSRs specify that L1 can use VMWRITE
+ * to modify any valid field of the VMCS, or are the VM-exit
+ * information fields read-only?
+ */
+static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu)
+{
+	return to_vmx(vcpu)->nested.msrs.misc_low &
+		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
+}
+
 static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
 {
 	return vmcs12->cpu_based_vm_exec_control & bit;
@@ -3127,6 +3322,7 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		msrs->misc_high);
 	msrs->misc_low &= VMX_MISC_SAVE_EFER_LMA;
 	msrs->misc_low |=
+		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
 		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
 		VMX_MISC_ACTIVITY_HLT;
 	msrs->misc_high = 0;
@@ -3300,6 +3496,15 @@ static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
 
 	vmx->nested.msrs.misc_low = data;
 	vmx->nested.msrs.misc_high = data >> 32;
+
+	/*
+	 * If L1 has read-only VM-exit information fields, use the
+	 * less permissive vmx_vmwrite_bitmap to specify write
+	 * permissions for the shadow VMCS.
+	 */
+	if (enable_shadow_vmcs && !nested_cpu_has_vmwrite_any_field(&vmx->vcpu))
+		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
+
 	return 0;
 }
 
@@ -3354,6 +3559,13 @@ static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	/*
+	 * Don't allow changes to the VMX capability MSRs while the vCPU
+	 * is in VMX operation.
+	 */
+	if (vmx->nested.vmxon)
+		return -EBUSY;
+
 	switch (msr_index) {
 	case MSR_IA32_VMX_BASIC:
 		return vmx_restore_vmx_basic(vmx, data);
@@ -4216,6 +4428,14 @@ static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs)
 		if (!loaded_vmcs->msr_bitmap)
 			goto out_vmcs;
 		memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
+
+		if (static_branch_unlikely(&enable_evmcs) &&
+		    (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
+			struct hv_enlightened_vmcs *evmcs =
+				(struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;
+
+			evmcs->hv_enlightenments_control.msr_bitmap = 1;
+		}
 	}
 	return 0;
 
@@ -5329,6 +5549,9 @@ static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bit
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
 
+	if (static_branch_unlikely(&enable_evmcs))
+		evmcs_touch_msr_bitmap();
+
 	/*
 	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
 	 * have the write-low and read-high bitmap offsets the wrong way round.
@@ -5364,6 +5587,9 @@ static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitm
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
 
+	if (static_branch_unlikely(&enable_evmcs))
+		evmcs_touch_msr_bitmap();
+
 	/*
 	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
 	 * have the write-low and read-high bitmap offsets the wrong way round.
@@ -5946,8 +6172,14 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	int i;
 
 	if (enable_shadow_vmcs) {
+		/*
+		 * At vCPU creation, "VMWRITE to any supported field
+		 * in the VMCS" is supported, so use the more
+		 * permissive vmx_vmread_bitmap to specify both read
+		 * and write permissions for the shadow VMCS.
+		 */
 		vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
-		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmwrite_bitmap));
+		vmcs_write64(VMWRITE_BITMAP, __pa(vmx_vmread_bitmap));
 	}
 	if (cpu_has_vmx_msr_bitmap())
 		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
@@ -7588,8 +7820,7 @@ static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
 			vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
 		return 1;
 
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
-				sizeof(*vmpointer), &e)) {
+	if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -7670,6 +7901,12 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
+	/* CPL=0 must be checked manually. */
+	if (vmx_get_cpl(vcpu)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
 	if (vmx->nested.vmxon) {
 		nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
 		return kvm_skip_emulated_instruction(vcpu);
@@ -7729,6 +7966,11 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
  */
 static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
 {
+	if (vmx_get_cpl(vcpu)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 0;
+	}
+
 	if (!to_vmx(vcpu)->nested.vmxon) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 0;
@@ -7928,23 +8170,42 @@ static inline int vmcs12_write_any(struct kvm_vcpu *vcpu,
 
 }
 
+/*
+ * Copy the writable VMCS shadow fields back to the VMCS12, in case
+ * they have been modified by the L1 guest. Note that the "read-only"
+ * VM-exit information fields are actually writable if the vCPU is
+ * configured to support "VMWRITE to any supported field in the VMCS."
+ */
 static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
 {
-	int i;
+	const u16 *fields[] = {
+		shadow_read_write_fields,
+		shadow_read_only_fields
+	};
+	const int max_fields[] = {
+		max_shadow_read_write_fields,
+		max_shadow_read_only_fields
+	};
+	int i, q;
 	unsigned long field;
 	u64 field_value;
 	struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs;
-	const u16 *fields = shadow_read_write_fields;
-	const int num_fields = max_shadow_read_write_fields;
 
 	preempt_disable();
 
 	vmcs_load(shadow_vmcs);
 
-	for (i = 0; i < num_fields; i++) {
-		field = fields[i];
-		field_value = __vmcs_readl(field);
-		vmcs12_write_any(&vmx->vcpu, field, field_value);
+	for (q = 0; q < ARRAY_SIZE(fields); q++) {
+		for (i = 0; i < max_fields[q]; i++) {
+			field = fields[q][i];
+			field_value = __vmcs_readl(field);
+			vmcs12_write_any(&vmx->vcpu, field, field_value);
+		}
+		/*
+		 * Skip the VM-exit information fields if they are read-only.
+		 */
+		if (!nested_cpu_has_vmwrite_any_field(&vmx->vcpu))
+			break;
 	}
 
 	vmcs_clear(shadow_vmcs);
@@ -8029,9 +8290,9 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 		if (get_vmx_mem_address(vcpu, exit_qualification,
 				vmx_instruction_info, true, &gva))
 			return 1;
-		/* _system ok, as hardware has verified cpl=0 */
-		kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
-			     &field_value, (is_long_mode(vcpu) ? 8 : 4), NULL);
+		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
+		kvm_write_guest_virt_system(vcpu, gva, &field_value,
+					    (is_long_mode(vcpu) ? 8 : 4), NULL);
 	}
 
 	nested_vmx_succeed(vcpu);
@@ -8069,8 +8330,8 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 		if (get_vmx_mem_address(vcpu, exit_qualification,
 				vmx_instruction_info, false, &gva))
 			return 1;
-		if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva,
-			   &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
+		if (kvm_read_guest_virt(vcpu, gva, &field_value,
+					(is_64_bit_mode(vcpu) ? 8 : 4), &e)) {
 			kvm_inject_page_fault(vcpu, &e);
 			return 1;
 		}
@@ -8078,7 +8339,12 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 
 
 	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
-	if (vmcs_field_readonly(field)) {
+	/*
+	 * If the vCPU supports "VMWRITE to any supported field in the
+	 * VMCS," then the "read-only" fields are actually read/write.
+	 */
+	if (vmcs_field_readonly(field) &&
+	    !nested_cpu_has_vmwrite_any_field(vcpu)) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
 		return kvm_skip_emulated_instruction(vcpu);
@@ -8189,10 +8455,10 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 	if (get_vmx_mem_address(vcpu, exit_qualification,
 			vmx_instruction_info, true, &vmcs_gva))
 		return 1;
-	/* ok to use *_system, as hardware has verified cpl=0 */
-	if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
-				 (void *)&to_vmx(vcpu)->nested.current_vmptr,
-				 sizeof(u64), &e)) {
+	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
+	if (kvm_write_guest_virt_system(vcpu, vmcs_gva,
+					(void *)&to_vmx(vcpu)->nested.current_vmptr,
+					sizeof(u64), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -8239,8 +8505,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
 			vmx_instruction_info, false, &gva))
 		return 1;
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
-				sizeof(operand), &e)) {
+	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -8304,8 +8569,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
 			vmx_instruction_info, false, &gva))
 		return 1;
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
-				sizeof(operand), &e)) {
+	if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
@@ -8317,12 +8581,19 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 
 	switch (type) {
 	case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
-		if (is_noncanonical_address(operand.gla, vcpu)) {
+		if (!operand.vpid ||
+		    is_noncanonical_address(operand.gla, vcpu)) {
 			nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 			return kvm_skip_emulated_instruction(vcpu);
 		}
-		/* fall through */
+		if (cpu_has_vmx_invvpid_individual_addr() &&
+		    vmx->nested.vpid02) {
+			__invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR,
+				vmx->nested.vpid02, operand.gla);
+		} else
+			__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
+		break;
 	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
 	case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
 		if (!operand.vpid) {
@@ -8330,15 +8601,16 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 			return kvm_skip_emulated_instruction(vcpu);
 		}
+		__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
 		break;
 	case VMX_VPID_EXTENT_ALL_CONTEXT:
+		__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		return kvm_skip_emulated_instruction(vcpu);
 	}
 
-	__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
 	nested_vmx_succeed(vcpu);
 
 	return kvm_skip_emulated_instruction(vcpu);
@@ -8842,11 +9114,13 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
 	case EXIT_REASON_TPR_BELOW_THRESHOLD:
 		return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
 	case EXIT_REASON_APIC_ACCESS:
-		return nested_cpu_has2(vmcs12,
-			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
 	case EXIT_REASON_APIC_WRITE:
 	case EXIT_REASON_EOI_INDUCED:
-		/* apic_write and eoi_induced should exit unconditionally. */
+		/*
+		 * The controls for "virtualize APIC accesses," "APIC-
+		 * register virtualization," and "virtual-interrupt
+		 * delivery" only come from vmcs12.
+		 */
 		return true;
 	case EXIT_REASON_EPT_VIOLATION:
 		/*
@@ -9253,31 +9527,43 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 	vmcs_write32(TPR_THRESHOLD, irr);
 }
 
-static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
+static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 {
 	u32 sec_exec_control;
 
+	if (!lapic_in_kernel(vcpu))
+		return;
+
 	/* Postpone execution until vmcs01 is the current VMCS. */
 	if (is_guest_mode(vcpu)) {
-		to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+		to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
 		return;
 	}
 
-	if (!cpu_has_vmx_virtualize_x2apic_mode())
-		return;
-
 	if (!cpu_need_tpr_shadow(vcpu))
 		return;
 
 	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
+	sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+			      SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
 
-	if (set) {
-		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
-	} else {
-		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
-		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-		vmx_flush_tlb(vcpu, true);
+	switch (kvm_get_apic_mode(vcpu)) {
+	case LAPIC_MODE_INVALID:
+		WARN_ONCE(true, "Invalid local APIC state");
+	case LAPIC_MODE_DISABLED:
+		break;
+	case LAPIC_MODE_XAPIC:
+		if (flexpriority_enabled) {
+			sec_exec_control |=
+				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+			vmx_flush_tlb(vcpu, true);
+		}
+		break;
+	case LAPIC_MODE_X2APIC:
+		if (cpu_has_vmx_virtualize_x2apic_mode())
+			sec_exec_control |=
+				SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
+		break;
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
@@ -9286,24 +9572,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 
 static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
-	/*
-	 * Currently we do not handle the nested case where L2 has an
-	 * APIC access page of its own; that page is still pinned.
-	 * Hence, we skip the case where the VCPU is in guest mode _and_
-	 * L1 prepared an APIC access page for L2.
-	 *
-	 * For the case where L1 and L2 share the same APIC access page
-	 * (flexpriority=Y but SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES clear
-	 * in the vmcs12), this function will only update either the vmcs01
-	 * or the vmcs02.  If the former, the vmcs02 will be updated by
-	 * prepare_vmcs02.  If the latter, the vmcs01 will be updated in
-	 * the next L2->L1 exit.
-	 */
-	if (!is_guest_mode(vcpu) ||
-	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
-			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+	if (!is_guest_mode(vcpu)) {
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
 		vmx_flush_tlb(vcpu, true);
 	}
@@ -9943,13 +10212,13 @@ STACK_FRAME_NON_STANDARD(vmx_vcpu_run);
 
 static struct kvm *vmx_vm_alloc(void)
 {
-	struct kvm_vmx *kvm_vmx = kzalloc(sizeof(struct kvm_vmx), GFP_KERNEL);
+	struct kvm_vmx *kvm_vmx = vzalloc(sizeof(struct kvm_vmx));
 	return &kvm_vmx->kvm;
 }
 
 static void vmx_vm_free(struct kvm *kvm)
 {
-	kfree(to_kvm_vmx(kvm));
+	vfree(to_kvm_vmx(kvm));
 }
 
 static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
@@ -10387,11 +10656,6 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
 			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
 					SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
 		}
-	} else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) &&
-		   cpu_need_virtualize_apic_accesses(&vmx->vcpu)) {
-		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
-			      SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
-		kvm_vcpu_reload_apic_access_page(vcpu);
 	}
 
 	if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
@@ -10871,8 +11135,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
 	return 0;
 }
 
-static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
-			       bool from_vmentry)
+static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
@@ -11006,13 +11269,13 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
  * is assigned to entry_failure_code on failure.
  */
 static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
-			  bool from_vmentry, u32 *entry_failure_code)
+			  u32 *entry_failure_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control, vmcs12_exec_ctrl;
 
 	if (vmx->nested.dirty_vmcs12) {
-		prepare_vmcs02_full(vcpu, vmcs12, from_vmentry);
+		prepare_vmcs02_full(vcpu, vmcs12);
 		vmx->nested.dirty_vmcs12 = false;
 	}
 
@@ -11032,7 +11295,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * HOST_FS_BASE, HOST_GS_BASE.
 	 */
 
-	if (from_vmentry &&
+	if (vmx->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
 		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
 		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
@@ -11040,7 +11303,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
 		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl);
 	}
-	if (from_vmentry) {
+	if (vmx->nested.nested_run_pending) {
 		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
 			     vmcs12->vm_entry_intr_info_field);
 		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE,
@@ -11172,7 +11435,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			~VM_ENTRY_IA32E_MODE) |
 		(vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
 
-	if (from_vmentry &&
+	if (vmx->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) {
 		vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
 		vcpu->arch.pat = vmcs12->guest_ia32_pat;
@@ -11197,7 +11460,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
 			if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
 				vmx->nested.last_vpid = vmcs12->virtual_processor_id;
-				__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true);
+				__vmx_flush_tlb(vcpu, vmx->nested.vpid02, true);
 			}
 		} else {
 			vmx_flush_tlb(vcpu, true);
@@ -11240,7 +11503,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmx_set_cr4(vcpu, vmcs12->guest_cr4);
 	vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12));
 
-	if (from_vmentry &&
+	if (vmx->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER))
 		vcpu->arch.efer = vmcs12->guest_ia32_efer;
 	else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
@@ -11418,7 +11681,7 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	return 0;
 }
 
-static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
+static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -11438,7 +11701,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
 
 	r = EXIT_REASON_INVALID_STATE;
-	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+	if (prepare_vmcs02(vcpu, vmcs12, &exit_qual))
 		goto fail;
 
 	nested_get_vmcs12_pages(vcpu, vmcs12);
@@ -11540,20 +11803,22 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * the nested entry.
 	 */
 
-	ret = enter_vmx_non_root_mode(vcpu, true);
-	if (ret)
+	vmx->nested.nested_run_pending = 1;
+	ret = enter_vmx_non_root_mode(vcpu);
+	if (ret) {
+		vmx->nested.nested_run_pending = 0;
 		return ret;
+	}
 
 	/*
 	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
 	 * by event injection, halt vcpu.
 	 */
 	if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
-	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK))
+	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) {
+		vmx->nested.nested_run_pending = 0;
 		return kvm_vcpu_halt(vcpu);
-
-	vmx->nested.nested_run_pending = 1;
-
+	}
 	return 1;
 
 out:
@@ -11925,12 +12190,20 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 
 	load_vmcs12_mmu_host_state(vcpu, vmcs12);
 
-	if (enable_vpid) {
-		/*
-		 * Trivially support vpid by letting L2s share their parent
-		 * L1's vpid. TODO: move to a more elaborate solution, giving
-		 * each L2 its own vpid and exposing the vpid feature to L1.
-		 */
+	/*
+	 * If vmcs01 don't use VPID, CPU flushes TLB on every
+	 * VMEntry/VMExit. Thus, no need to flush TLB.
+	 *
+	 * If vmcs12 uses VPID, TLB entries populated by L2 are
+	 * tagged with vmx->nested.vpid02 while L1 entries are tagged
+	 * with vmx->vpid. Thus, no need to flush TLB.
+	 *
+	 * Therefore, flush TLB only in case vmcs01 uses VPID and
+	 * vmcs12 don't use VPID as in this case L1 & L2 TLB entries
+	 * are both tagged with vmx->vpid.
+	 */
+	if (enable_vpid &&
+	    !(nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02)) {
 		vmx_flush_tlb(vcpu, true);
 	}
 
@@ -12069,10 +12342,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
 
-	if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
-		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
-		vmx_set_virtual_x2apic_mode(vcpu,
-				vcpu->arch.apic_base & X2APIC_ENABLE);
+	if (vmx->nested.change_vmcs01_virtual_apic_mode) {
+		vmx->nested.change_vmcs01_virtual_apic_mode = false;
+		vmx_set_virtual_apic_mode(vcpu);
 	} else if (!nested_cpu_has_ept(vmcs12) &&
 		   nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
@@ -12236,7 +12508,7 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
 static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 {
 	struct vcpu_vmx *vmx;
-	u64 tscl, guest_tscl, delta_tsc;
+	u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
 
 	if (kvm_mwait_in_guest(vcpu->kvm))
 		return -EOPNOTSUPP;
@@ -12245,6 +12517,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 	tscl = rdtsc();
 	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
 	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+	lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
+
+	if (delta_tsc > lapic_timer_advance_cycles)
+		delta_tsc -= lapic_timer_advance_cycles;
+	else
+		delta_tsc = 0;
 
 	/* Convert to host delta tsc if tsc scaling is enabled */
 	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
@@ -12615,7 +12893,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
 
 	if (vmx->nested.smm.guest_mode) {
 		vcpu->arch.hflags &= ~HF_SMM_MASK;
-		ret = enter_vmx_non_root_mode(vcpu, false);
+		ret = enter_vmx_non_root_mode(vcpu);
 		vcpu->arch.hflags |= HF_SMM_MASK;
 		if (ret)
 			return ret;
@@ -12700,7 +12978,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
-	.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
+	.set_virtual_apic_mode = vmx_set_virtual_apic_mode,
 	.set_apic_access_page_addr = vmx_set_apic_access_page_addr,
 	.get_enable_apicv = vmx_get_enable_apicv,
 	.refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
@@ -12812,6 +13090,7 @@ static int __init vmx_init(void)
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);
 #endif
+	vmx_check_vmcs12_offsets();
 
 	return 0;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 71e7cda6d014..cc8c8be1e92d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -138,6 +138,7 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 /* lapic timer advance (tscdeadline mode only) in nanoseconds */
 unsigned int __read_mostly lapic_timer_advance_ns = 0;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
+EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
 
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
@@ -318,23 +319,27 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_apic_base);
 
+enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
+{
+	return kvm_apic_mode(kvm_get_apic_base(vcpu));
+}
+EXPORT_SYMBOL_GPL(kvm_get_apic_mode);
+
 int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
-	u64 old_state = vcpu->arch.apic_base &
-		(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
-	u64 new_state = msr_info->data &
-		(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
+	enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
+	enum lapic_mode new_mode = kvm_apic_mode(msr_info->data);
 	u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff |
 		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
 
-	if ((msr_info->data & reserved_bits) || new_state == X2APIC_ENABLE)
-		return 1;
-	if (!msr_info->host_initiated &&
-	    ((new_state == MSR_IA32_APICBASE_ENABLE &&
-	      old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) ||
-	     (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) &&
-	      old_state == 0)))
+	if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
 		return 1;
+	if (!msr_info->host_initiated) {
+		if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC)
+			return 1;
+		if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC)
+			return 1;
+	}
 
 	kvm_lapic_set_base(vcpu, msr_info->data);
 	return 0;
@@ -856,7 +861,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	}
 
 	if (is_long_mode(vcpu) &&
-	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 62)))
+	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
 		return 1;
 	else if (is_pae(vcpu) && is_paging(vcpu) &&
 		   !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
@@ -1761,7 +1766,7 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
 	return mode;
 }
 
-static int do_realtime(struct timespec *ts, u64 *tsc_timestamp)
+static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp)
 {
 	struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
 	unsigned long seq;
@@ -1794,7 +1799,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
 }
 
 /* returns true if host is using TSC based clocksource */
-static bool kvm_get_walltime_and_clockread(struct timespec *ts,
+static bool kvm_get_walltime_and_clockread(struct timespec64 *ts,
 					   u64 *tsc_timestamp)
 {
 	/* checked again under seqlock below */
@@ -2868,6 +2873,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_SYNIC2:
 	case KVM_CAP_HYPERV_VP_INDEX:
 	case KVM_CAP_HYPERV_EVENTFD:
+	case KVM_CAP_HYPERV_TLBFLUSH:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -2894,7 +2900,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_CLOCK_TSC_STABLE;
 		break;
 	case KVM_CAP_X86_DISABLE_EXITS:
-		r |=  KVM_X86_DISABLE_EXITS_HTL | KVM_X86_DISABLE_EXITS_PAUSE;
+		r |=  KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE;
 		if(kvm_can_mwait_in_guest())
 			r |= KVM_X86_DISABLE_EXITS_MWAIT;
 		break;
@@ -3962,7 +3968,7 @@ out_nofree:
 	return r;
 }
 
-int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
 }
@@ -4248,7 +4254,7 @@ split_irqchip_unlock:
 		if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) &&
 			kvm_can_mwait_in_guest())
 			kvm->arch.mwait_in_guest = true;
-		if (cap->args[0] & KVM_X86_DISABLE_EXITS_HTL)
+		if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT)
 			kvm->arch.hlt_in_guest = true;
 		if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
 			kvm->arch.pause_in_guest = true;
@@ -4787,11 +4793,10 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
 	return X86EMUL_CONTINUE;
 }
 
-int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,
+int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
 			       gva_t addr, void *val, unsigned int bytes,
 			       struct x86_exception *exception)
 {
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
@@ -4799,12 +4804,17 @@ int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,
 }
 EXPORT_SYMBOL_GPL(kvm_read_guest_virt);
 
-static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt,
-				      gva_t addr, void *val, unsigned int bytes,
-				      struct x86_exception *exception)
+static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
+			     gva_t addr, void *val, unsigned int bytes,
+			     struct x86_exception *exception, bool system)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception);
+	u32 access = 0;
+
+	if (!system && kvm_x86_ops->get_cpl(vcpu) == 3)
+		access |= PFERR_USER_MASK;
+
+	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
 }
 
 static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
@@ -4816,18 +4826,16 @@ static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
 	return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE;
 }
 
-int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
-				       gva_t addr, void *val,
-				       unsigned int bytes,
-				       struct x86_exception *exception)
+static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
+				      struct kvm_vcpu *vcpu, u32 access,
+				      struct x86_exception *exception)
 {
-	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
 
 	while (bytes) {
 		gpa_t gpa =  vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr,
-							     PFERR_WRITE_MASK,
+							     access,
 							     exception);
 		unsigned offset = addr & (PAGE_SIZE-1);
 		unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
@@ -4848,6 +4856,27 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 out:
 	return r;
 }
+
+static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val,
+			      unsigned int bytes, struct x86_exception *exception,
+			      bool system)
+{
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	u32 access = PFERR_WRITE_MASK;
+
+	if (!system && kvm_x86_ops->get_cpl(vcpu) == 3)
+		access |= PFERR_USER_MASK;
+
+	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
+					   access, exception);
+}
+
+int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
+				unsigned int bytes, struct x86_exception *exception)
+{
+	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
+					   PFERR_WRITE_MASK, exception);
+}
 EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
 
 int handle_ud(struct kvm_vcpu *vcpu)
@@ -4858,8 +4887,8 @@ int handle_ud(struct kvm_vcpu *vcpu)
 	struct x86_exception e;
 
 	if (force_emulation_prefix &&
-	    kvm_read_guest_virt(&vcpu->arch.emulate_ctxt,
-				kvm_get_linear_rip(vcpu), sig, sizeof(sig), &e) == 0 &&
+	    kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu),
+				sig, sizeof(sig), &e) == 0 &&
 	    memcmp(sig, "\xf\xbkvm", sizeof(sig)) == 0) {
 		kvm_rip_write(vcpu, kvm_rip_read(vcpu) + sizeof(sig));
 		emul_type = 0;
@@ -5600,8 +5629,8 @@ static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
 static const struct x86_emulate_ops emulate_ops = {
 	.read_gpr            = emulator_read_gpr,
 	.write_gpr           = emulator_write_gpr,
-	.read_std            = kvm_read_guest_virt_system,
-	.write_std           = kvm_write_guest_virt_system,
+	.read_std            = emulator_read_std,
+	.write_std           = emulator_write_std,
 	.read_phys           = kvm_read_guest_phys_system,
 	.fetch               = kvm_fetch_guest_virt,
 	.read_emulated       = emulator_read_emulated,
@@ -6617,7 +6646,7 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr,
 			        unsigned long clock_type)
 {
 	struct kvm_clock_pairing clock_pairing;
-	struct timespec ts;
+	struct timespec64 ts;
 	u64 cycle;
 	int ret;
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index c9492f764902..331993c49dae 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -247,11 +247,11 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr);
 u64 get_kvmclock_ns(struct kvm *kvm);
 
-int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,
+int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
 	gva_t addr, void *val, unsigned int bytes,
 	struct x86_exception *exception);
 
-int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
+int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu,
 	gva_t addr, void *val, unsigned int bytes,
 	struct x86_exception *exception);