Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5d53052..f1a0eeb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,6 +92,8 @@
 static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
+static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
+
 #define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
 #define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
@@ -100,6 +102,7 @@
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
+static void process_smi(struct kvm_vcpu *vcpu);
 static void enter_smm(struct kvm_vcpu *vcpu);
 static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 static void store_regs(struct kvm_vcpu *vcpu);
@@ -205,7 +208,6 @@
 	{ "l1d_flush", VCPU_STAT(l1d_flush) },
 	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
 	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
-	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
 	{ "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) },
 	{ "mmu_flooded", VM_STAT(mmu_flooded) },
 	{ "mmu_recycled", VM_STAT(mmu_recycled) },
@@ -300,13 +302,14 @@
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 	int err;
 
-	if (((value ^ smsr->values[slot].curr) & mask) == 0)
+	value = (value & mask) | (smsr->values[slot].host & ~mask);
+	if (value == smsr->values[slot].curr)
 		return 0;
-	smsr->values[slot].curr = value;
 	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
+	smsr->values[slot].curr = value;
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
@@ -442,6 +445,14 @@
 		 * for #DB exceptions under VMX.
 		 */
 		vcpu->arch.dr6 ^= payload & DR6_RTM;
+
+		/*
+		 * The #DB payload is defined as compatible with the 'pending
+		 * debug exceptions' field under VMX, not DR6. While bit 12 is
+		 * defined in the 'pending debug exceptions' field (enabled
+		 * breakpoint), it is reserved and must be zero in DR6.
+		 */
+		vcpu->arch.dr6 &= ~BIT(12);
 		break;
 	case PF_VECTOR:
 		vcpu->arch.cr2 = payload;
@@ -464,8 +475,6 @@
 
 	if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
 	queue:
-		if (has_error && !is_protmode(vcpu))
-			has_error = false;
 		if (reinject) {
 			/*
 			 * On vmentry, vcpu->arch.exception.pending is only
@@ -821,11 +830,25 @@
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
 		vcpu->guest_xcr0_loaded = 1;
 	}
+
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
+	    vcpu->arch.pkru != vcpu->arch.host_pkru)
+		__write_pkru(vcpu->arch.pkru);
 }
 EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
 
 void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 {
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
+		vcpu->arch.pkru = rdpkru();
+		if (vcpu->arch.pkru != vcpu->arch.host_pkru)
+			__write_pkru(vcpu->arch.host_pkru);
+	}
+
 	if (vcpu->guest_xcr0_loaded) {
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
@@ -885,9 +908,38 @@
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
+static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c)
+{
+	u64 reserved_bits = CR4_RESERVED_BITS;
+
+	if (!cpu_has(c, X86_FEATURE_XSAVE))
+		reserved_bits |= X86_CR4_OSXSAVE;
+
+	if (!cpu_has(c, X86_FEATURE_SMEP))
+		reserved_bits |= X86_CR4_SMEP;
+
+	if (!cpu_has(c, X86_FEATURE_SMAP))
+		reserved_bits |= X86_CR4_SMAP;
+
+	if (!cpu_has(c, X86_FEATURE_FSGSBASE))
+		reserved_bits |= X86_CR4_FSGSBASE;
+
+	if (!cpu_has(c, X86_FEATURE_PKU))
+		reserved_bits |= X86_CR4_PKE;
+
+	if (!cpu_has(c, X86_FEATURE_LA57) &&
+	    !(cpuid_ecx(0x7) & bit(X86_FEATURE_LA57)))
+		reserved_bits |= X86_CR4_LA57;
+
+	if (!cpu_has(c, X86_FEATURE_UMIP) && !kvm_x86_ops->umip_emulated())
+		reserved_bits |= X86_CR4_UMIP;
+
+	return reserved_bits;
+}
+
 static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	if (cr4 & CR4_RESERVED_BITS)
+	if (cr4 & cr4_reserved_bits)
 		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
@@ -918,7 +970,8 @@
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
-				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+				   X86_CR4_SMEP;
+	unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
 
 	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
@@ -926,6 +979,8 @@
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
+		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
+			return 1;
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
@@ -944,7 +999,7 @@
 	if (kvm_x86_ops->set_cr4(vcpu, cr4))
 		return 1;
 
-	if (((cr4 ^ old_cr4) & pdptr_bits) ||
+	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
@@ -1053,9 +1108,11 @@
 
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 {
+	size_t size = ARRAY_SIZE(vcpu->arch.db);
+
 	switch (dr) {
 	case 0 ... 3:
-		vcpu->arch.db[dr] = val;
+		vcpu->arch.db[array_index_nospec(dr, size)] = val;
 		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
 			vcpu->arch.eff_db[dr] = val;
 		break;
@@ -1092,9 +1149,11 @@
 
 int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
 {
+	size_t size = ARRAY_SIZE(vcpu->arch.db);
+
 	switch (dr) {
 	case 0 ... 3:
-		*val = vcpu->arch.db[dr];
+		*val = vcpu->arch.db[array_index_nospec(dr, size)];
 		break;
 	case 4:
 		/* fall through */
@@ -1327,10 +1386,15 @@
 	 * If TSX is disabled on the system, guests are also mitigated against
 	 * TAA and clear CPU buffer mitigation is not required for guests.
 	 */
-	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
-	    (data & ARCH_CAP_TSX_CTRL_MSR))
+	if (!boot_cpu_has(X86_FEATURE_RTM))
+		data &= ~ARCH_CAP_TAA_NO;
+	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+		data |= ARCH_CAP_TAA_NO;
+	else if (data & ARCH_CAP_TSX_CTRL_MSR)
 		data &= ~ARCH_CAP_MDS_NO;
 
+	/* KVM does not emulate MSR_IA32_TSX_CTRL.  */
+	data &= ~ARCH_CAP_TSX_CTRL_MSR;
 	return data;
 }
 
@@ -2484,7 +2548,10 @@
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MCx_CTL(bank_num)) {
-			u32 offset = msr - MSR_IA32_MC0_CTL;
+			u32 offset = array_index_nospec(
+				msr - MSR_IA32_MC0_CTL,
+				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
 			/* only 0 or all 1s can be written to IA32_MCi_CTL
 			 * some Linux kernels though clear bit 10 in bank 4 to
 			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
@@ -2580,45 +2647,47 @@
 
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
+	/* -EAGAIN is returned in atomic context so we can just return. */
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT,
+			&map, &vcpu->arch.st.cache, false))
 		return;
 
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
 	/*
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
 	trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
-		vcpu->arch.st.steal.preempted & KVM_VCPU_FLUSH_TLB);
-	if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB)
+		st->preempted & KVM_VCPU_FLUSH_TLB);
+	if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
 		kvm_vcpu_flush_tlb(vcpu, false);
 
-	if (vcpu->arch.st.steal.version & 1)
-		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
+	vcpu->arch.st.preempted = 0;
 
-	vcpu->arch.st.steal.version += 1;
+	if (st->version & 1)
+		st->version += 1;  /* first time write, random junk */
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	st->version += 1;
 
 	smp_wmb();
 
-	vcpu->arch.st.steal.steal += current->sched_info.run_delay -
+	st->steal += current->sched_info.run_delay -
 		vcpu->arch.st.last_steal;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
-
 	smp_wmb();
 
-	vcpu->arch.st.steal.version += 1;
+	st->version += 1;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false);
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
@@ -2685,7 +2754,7 @@
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
@@ -2695,6 +2764,10 @@
 			if (!msr_info->host_initiated) {
 				s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
 				adjust_tsc_offset_guest(vcpu, adj);
+				/* Before back to guest, tsc_timestamp must be adjusted
+				 * as well, otherwise guest's percpu pvclock time could jump.
+				 */
+				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 			}
 			vcpu->arch.ia32_tsc_adjust_msr = data;
 		}
@@ -2771,11 +2844,6 @@
 		if (data & KVM_STEAL_RESERVED_MASK)
 			return 1;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
-						data & KVM_STEAL_VALID_BITS,
-						sizeof(struct kvm_steal_time)))
-			return 1;
-
 		vcpu->arch.st.msr_val = data;
 
 		if (!(data & KVM_MSR_ENABLED))
@@ -2911,7 +2979,10 @@
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MCx_CTL(bank_num)) {
-			u32 offset = msr - MSR_IA32_MC0_CTL;
+			u32 offset = array_index_nospec(
+				msr - MSR_IA32_MC0_CTL,
+				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
 			data = vcpu->arch.mce_banks[offset];
 			break;
 		}
@@ -2991,7 +3062,7 @@
 	case MSR_IA32_APICBASE:
 		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_TSCDEADLINE:
@@ -3437,10 +3508,6 @@
 
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
 
-	fpregs_assert_state_consistent();
-	if (test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_return();
-
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
@@ -3480,15 +3547,25 @@
 
 static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
+	if (vcpu->arch.st.preempted)
+		return;
 
-	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
-			&vcpu->arch.st.steal.preempted,
-			offsetof(struct kvm_steal_time, preempted),
-			sizeof(vcpu->arch.st.steal.preempted));
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map,
+			&vcpu->arch.st.cache, true))
+		return;
+
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
+	st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
+
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -3549,22 +3626,33 @@
 
 static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * We can accept userspace's request for interrupt injection
+	 * as long as we have a place to store the interrupt number.
+	 * The actual injection will happen when the CPU is able to
+	 * deliver the interrupt.
+	 */
+	if (kvm_cpu_has_extint(vcpu))
+		return false;
+
+	/* Acknowledging ExtINT does not happen if LINT0 is masked.  */
 	return (!lapic_in_kernel(vcpu) ||
 		kvm_apic_accept_pic_intr(vcpu));
 }
 
-/*
- * if userspace requested an interrupt window, check that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
-	return kvm_arch_interrupt_allowed(vcpu) &&
-		!kvm_cpu_has_interrupt(vcpu) &&
+	/*
+	 * Do not cause an interrupt window exit if an exception
+	 * is pending or an event needs reinjection; userspace
+	 * might want to inject the interrupt manually using KVM_SET_REGS
+	 * or KVM_SET_SREGS.  For that to work, we must be at an
+	 * instruction boundary and with no events half-injected.
+	 */
+	return (kvm_arch_interrupt_allowed(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu) &&
 		!kvm_event_needs_reinjection(vcpu) &&
-		kvm_cpu_accept_dm_intr(vcpu);
+		!vcpu->arch.exception.pending);
 }
 
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
@@ -3624,7 +3712,7 @@
 	unsigned bank_num = mcg_cap & 0xff, bank;
 
 	r = -EINVAL;
-	if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
+	if (!bank_num || bank_num > KVM_MAX_MCE_BANKS)
 		goto out;
 	if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000))
 		goto out;
@@ -3695,6 +3783,10 @@
 {
 	process_nmi(vcpu);
 
+
+	if (kvm_check_request(KVM_REQ_SMI, vcpu))
+		process_smi(vcpu);
+
 	/*
 	 * The API doesn't provide the instruction length for software
 	 * exceptions, so don't report them. As long as the guest RIP
@@ -4421,6 +4513,7 @@
 	case KVM_SET_NESTED_STATE: {
 		struct kvm_nested_state __user *user_kvm_nested_state = argp;
 		struct kvm_nested_state kvm_state;
+		int idx;
 
 		r = -EINVAL;
 		if (!kvm_x86_ops->set_nested_state)
@@ -4444,7 +4537,9 @@
 		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
 			break;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_GET_SUPPORTED_HV_CPUID: {
@@ -4973,10 +5068,13 @@
 		r = -EFAULT;
 		if (copy_from_user(&u.ps, argp, sizeof(u.ps)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit_out;
 		r = kvm_vm_ioctl_set_pit(kvm, &u.ps);
+set_pit_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_GET_PIT2: {
@@ -4996,10 +5094,13 @@
 		r = -EFAULT;
 		if (copy_from_user(&u.ps2, argp, sizeof(u.ps2)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit2_out;
 		r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2);
+set_pit2_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_REINJECT_CONTROL: {
@@ -5151,6 +5252,10 @@
 			if (!kvm_x86_ops->rdtscp_supported())
 				continue;
 			break;
+		case MSR_IA32_UMWAIT_CONTROL:
+			if (!boot_cpu_has(X86_FEATURE_WAITPKG))
+				continue;
+			break;
 		case MSR_IA32_RTIT_CTL:
 		case MSR_IA32_RTIT_STATUS:
 			if (!kvm_x86_ops->pt_supported())
@@ -6185,7 +6290,10 @@
 
 static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
 {
-	emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+	vcpu->arch.hflags = emul_flags;
+	kvm_mmu_reset_context(vcpu);
 }
 
 static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
@@ -6356,11 +6464,11 @@
 	return 1;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				  bool write_fault_to_shadow_pgtable,
 				  int emulation_type)
 {
-	gpa_t gpa = cr2;
+	gpa_t gpa = cr2_or_gpa;
 	kvm_pfn_t pfn;
 
 	if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
@@ -6374,7 +6482,7 @@
 		 * Write permission should be allowed since only
 		 * write access need to be emulated.
 		 */
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 		/*
 		 * If the mapping is invalid in guest, let cpu retry
@@ -6431,10 +6539,10 @@
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
-			      unsigned long cr2,  int emulation_type)
+			      gpa_t cr2_or_gpa,  int emulation_type)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	unsigned long last_retry_eip, last_retry_addr, gpa = cr2;
+	unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa;
 
 	last_retry_eip = vcpu->arch.last_retry_eip;
 	last_retry_addr = vcpu->arch.last_retry_addr;
@@ -6463,14 +6571,14 @@
 	if (x86_page_table_writing_insn(ctxt))
 		return false;
 
-	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2)
+	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa)
 		return false;
 
 	vcpu->arch.last_retry_eip = ctxt->eip;
-	vcpu->arch.last_retry_addr = cr2;
+	vcpu->arch.last_retry_addr = cr2_or_gpa;
 
 	if (!vcpu->arch.mmu->direct_map)
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
 
@@ -6616,11 +6724,8 @@
 	return false;
 }
 
-int x86_emulate_instruction(struct kvm_vcpu *vcpu,
-			    unsigned long cr2,
-			    int emulation_type,
-			    void *insn,
-			    int insn_len)
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			    int emulation_type, void *insn, int insn_len)
 {
 	int r;
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
@@ -6666,8 +6771,9 @@
 				kvm_queue_exception(vcpu, UD_VECTOR);
 				return 1;
 			}
-			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
-						emulation_type))
+			if (reexecute_instruction(vcpu, cr2_or_gpa,
+						  write_fault_to_spt,
+						  emulation_type))
 				return 1;
 			if (ctxt->have_exception) {
 				/*
@@ -6701,7 +6807,7 @@
 		return 1;
 	}
 
-	if (retry_instruction(ctxt, cr2, emulation_type))
+	if (retry_instruction(ctxt, cr2_or_gpa, emulation_type))
 		return 1;
 
 	/* this is needed for vmware backdoor interface to work since it
@@ -6713,7 +6819,7 @@
 
 restart:
 	/* Save the faulting GPA (cr2) in the address field */
-	ctxt->exception.address = cr2;
+	ctxt->exception.address = cr2_or_gpa;
 
 	r = x86_emulate_insn(ctxt);
 
@@ -6721,7 +6827,7 @@
 		return 1;
 
 	if (r == EMULATION_FAILED) {
-		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
+		if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt,
 					emulation_type))
 			return 1;
 
@@ -6760,7 +6866,7 @@
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
 			kvm_rip_write(vcpu, ctxt->eip);
-			if (r && ctxt->tf)
+			if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
 				r = kvm_vcpu_do_singlestep(vcpu);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
 		}
@@ -7264,6 +7370,7 @@
 	cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
 #ifdef CONFIG_X86_64
 	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
+	cancel_work_sync(&pvclock_gtod_work);
 #endif
 	kvm_x86_ops = NULL;
 	kvm_mmu_module_exit();
@@ -7496,14 +7603,21 @@
 	kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
 }
 
-static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
+static void kvm_inject_exception(struct kvm_vcpu *vcpu)
+{
+       if (vcpu->arch.exception.error_code && !is_protmode(vcpu))
+               vcpu->arch.exception.error_code = false;
+       kvm_x86_ops->queue_exception(vcpu);
+}
+
+static int inject_pending_event(struct kvm_vcpu *vcpu)
 {
 	int r;
 
 	/* try to reinject previous events if any */
 
 	if (vcpu->arch.exception.injected)
-		kvm_x86_ops->queue_exception(vcpu);
+		kvm_inject_exception(vcpu);
 	/*
 	 * Do not inject an NMI or interrupt if there is a pending
 	 * exception.  Exceptions and interrupts are recognized at
@@ -7532,7 +7646,7 @@
 	 * from L2 to L1.
 	 */
 	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
-		r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+		r = kvm_x86_ops->check_nested_events(vcpu);
 		if (r != 0)
 			return r;
 	}
@@ -7569,7 +7683,7 @@
 			}
 		}
 
-		kvm_x86_ops->queue_exception(vcpu);
+		kvm_inject_exception(vcpu);
 	}
 
 	/* Don't consider new event if we re-injected an event */
@@ -7594,7 +7708,7 @@
 		 * KVM_REQ_EVENT only on certain events and not unconditionally?
 		 */
 		if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
-			r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+			r = kvm_x86_ops->check_nested_events(vcpu);
 			if (r != 0)
 				return r;
 		}
@@ -7905,9 +8019,8 @@
 	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
 }
 
-int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end,
-		bool blockable)
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+					    unsigned long start, unsigned long end)
 {
 	unsigned long apic_address;
 
@@ -7918,8 +8031,6 @@
 	apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
 	if (start <= apic_address && apic_address < end)
 		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
-
-	return 0;
 }
 
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
@@ -8071,7 +8182,7 @@
 			goto out;
 		}
 
-		if (inject_pending_event(vcpu, req_int_win) != 0)
+		if (inject_pending_event(vcpu) != 0)
 			req_immediate_exit = true;
 		else {
 			/* Enable SMI/NMI/IRQ window open exits if needed.
@@ -8163,8 +8274,12 @@
 	trace_kvm_entry(vcpu->vcpu_id);
 	guest_enter_irqoff();
 
-	/* The preempt notifier should have taken care of the FPU already.  */
-	WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
+	/* Save host pkru register if supported */
+	vcpu->arch.host_pkru = read_pkru();
+
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -8174,6 +8289,8 @@
 		set_debugreg(vcpu->arch.eff_db[3], 3);
 		set_debugreg(vcpu->arch.dr6, 6);
 		vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
+	} else if (unlikely(hw_breakpoint_active())) {
+		set_debugreg(0, 7);
 	}
 
 	kvm_x86_ops->run(vcpu);
@@ -8300,7 +8417,7 @@
 static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
 {
 	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
-		kvm_x86_ops->check_nested_events(vcpu, false);
+		kvm_x86_ops->check_nested_events(vcpu);
 
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
 		!vcpu->arch.apf.halted);
@@ -8436,12 +8553,26 @@
 	return 0;
 }
 
+static void kvm_save_current_fpu(struct fpu *fpu)
+{
+	/*
+	 * If the target FPU state is not resident in the CPU registers, just
+	 * memcpy() from current, else save CPU state directly to the target.
+	 */
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		memcpy(&fpu->state, &current->thread.fpu.state,
+		       fpu_kernel_xstate_size);
+	else
+		copy_fpregs_to_fpstate(fpu);
+}
+
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
+	kvm_save_current_fpu(vcpu->arch.user_fpu);
+
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
@@ -8457,7 +8588,8 @@
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
+	kvm_save_current_fpu(vcpu->arch.guest_fpu);
+
 	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
 	fpregs_mark_activate();
@@ -8679,6 +8811,8 @@
 				    struct kvm_mp_state *mp_state)
 {
 	vcpu_load(vcpu);
+	if (kvm_mpx_supported())
+		kvm_load_guest_fpu(vcpu);
 
 	kvm_apic_accept_events(vcpu);
 	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
@@ -8687,6 +8821,8 @@
 	else
 		mp_state->mp_state = vcpu->arch.mp_state;
 
+	if (kvm_mpx_supported())
+		kvm_put_guest_fpu(vcpu);
 	vcpu_put(vcpu);
 	return 0;
 }
@@ -9046,6 +9182,9 @@
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+	struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache;
+
+	kvm_release_pfn(cache->pfn, cache->dirty, cache);
 
 	kvmclock_reset(vcpu);
 
@@ -9110,13 +9249,7 @@
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.apf.msr_val = 0;
-
-	vcpu_load(vcpu);
-	kvm_mmu_unload(vcpu);
-	vcpu_put(vcpu);
-
-	kvm_x86_ops->vcpu_free(vcpu);
+	kvm_arch_vcpu_free(vcpu);
 }
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -9308,6 +9441,8 @@
 	if (r != 0)
 		return r;
 
+	cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data);
+
 	if (kvm_has_tsc_control) {
 		/*
 		 * Make sure the user can only configure tsc_khz values that
@@ -9648,6 +9783,13 @@
 {
 	int i;
 
+	/*
+	 * Clear out the previous array pointers for the KVM_MR_MOVE case.  The
+	 * old arrays will be freed by __kvm_set_memory_region() if installing
+	 * the new memslot is successful.
+	 */
+	memset(&slot->arch, 0, sizeof(slot->arch));
+
 	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
 		struct kvm_lpage_info *linfo;
 		unsigned long ugfn;
@@ -9710,11 +9852,18 @@
 
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 {
+	struct kvm_vcpu *vcpu;
+	int i;
+
 	/*
 	 * memslots->generation has been incremented.
 	 * mmio generation may have reached its maximum value.
 	 */
 	kvm_mmu_invalidate_mmio_sptes(kvm, gen);
+
+	/* Force re-initialization of steal_time cache */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vcpu_kick(vcpu);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -9722,6 +9871,10 @@
 				const struct kvm_userspace_memory_region *mem,
 				enum kvm_mr_change change)
 {
+	if (change == KVM_MR_MOVE)
+		return kvm_arch_create_memslot(kvm, memslot,
+					       mem->memory_size >> PAGE_SHIFT);
+
 	return 0;
 }
 
@@ -9966,7 +10119,7 @@
 	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
+	vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
@@ -10079,7 +10232,7 @@
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
+	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
 	if (kvm_can_deliver_async_pf(vcpu) &&
@@ -10114,7 +10267,7 @@
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
+	trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa);
 
 	if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
 	    !apf_get_user(vcpu, &val)) {
@@ -10245,6 +10398,32 @@
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
 
+int kvm_spec_ctrl_test_value(u64 value)
+{
+	/*
+	 * test that setting IA32_SPEC_CTRL to given value
+	 * is allowed by the host processor
+	 */
+
+	u64 saved_value;
+	unsigned long flags;
+	int ret = 0;
+
+	local_irq_save(flags);
+
+	if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value))
+		ret = 1;
+	else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value))
+		ret = 1;
+	else
+		wrmsrl(MSR_IA32_SPEC_CTRL, saved_value);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);