1 files changed, 87 insertions, 50 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index be7bb6d20129..570e7f8cbf64 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -90,7 +90,6 @@
 #include "trace.h"
 
 #define MAX_IO_MSRS 256
-#define KVM_MAX_MCE_BANKS 32
 
 /*
  * Note, kvm_caps fields should *never* have default values, all fields must be
@@ -578,7 +577,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) {
 		values = &msrs->values[slot];
 		if (values->host != values->curr) {
-			wrmsrl(kvm_uret_msrs_list[slot], values->host);
+			wrmsrq(kvm_uret_msrs_list[slot], values->host);
 			values->curr = values->host;
 		}
 	}
@@ -590,10 +589,10 @@ static int kvm_probe_user_return_msr(u32 msr)
 	int ret;
 
 	preempt_disable();
-	ret = rdmsrl_safe(msr, &val);
+	ret = rdmsrq_safe(msr, &val);
 	if (ret)
 		goto out;
-	ret = wrmsrl_safe(msr, val);
+	ret = wrmsrq_safe(msr, val);
 out:
 	preempt_enable();
 	return ret;
@@ -630,12 +629,21 @@ static void kvm_user_return_msr_cpu_online(void)
 	int i;
 
 	for (i = 0; i < kvm_nr_uret_msrs; ++i) {
-		rdmsrl_safe(kvm_uret_msrs_list[i], &value);
+		rdmsrq_safe(kvm_uret_msrs_list[i], &value);
 		msrs->values[i].host = value;
 		msrs->values[i].curr = value;
 	}
 }
 
+static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs)
+{
+	if (!msrs->registered) {
+		msrs->urn.on_user_return = kvm_on_user_return;
+		user_return_notifier_register(&msrs->urn);
+		msrs->registered = true;
+	}
+}
+
 int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
 {
 	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
@@ -644,20 +652,25 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
 	value = (value & mask) | (msrs->values[slot].host & ~mask);
 	if (value == msrs->values[slot].curr)
 		return 0;
-	err = wrmsrl_safe(kvm_uret_msrs_list[slot], value);
+	err = wrmsrq_safe(kvm_uret_msrs_list[slot], value);
 	if (err)
 		return 1;
 
 	msrs->values[slot].curr = value;
-	if (!msrs->registered) {
-		msrs->urn.on_user_return = kvm_on_user_return;
-		user_return_notifier_register(&msrs->urn);
-		msrs->registered = true;
-	}
+	kvm_user_return_register_notifier(msrs);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);
 
+void kvm_user_return_msr_update_cache(unsigned int slot, u64 value)
+{
+	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
+
+	msrs->values[slot].curr = value;
+	kvm_user_return_register_notifier(msrs);
+}
+EXPORT_SYMBOL_GPL(kvm_user_return_msr_update_cache);
+
 static void drop_user_return_notifiers(void)
 {
 	struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
@@ -1174,7 +1187,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 
 		if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
 		    vcpu->arch.ia32_xss != kvm_host.xss)
-			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
+			wrmsrq(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
 
 	if (cpu_feature_enabled(X86_FEATURE_PKU) &&
@@ -1205,7 +1218,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 
 		if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
 		    vcpu->arch.ia32_xss != kvm_host.xss)
-			wrmsrl(MSR_IA32_XSS, kvm_host.xss);
+			wrmsrq(MSR_IA32_XSS, kvm_host.xss);
 	}
 
 }
@@ -1662,7 +1675,7 @@ static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
 		*data = MSR_PLATFORM_INFO_CPUID_FAULT;
 		break;
 	case MSR_IA32_UCODE_REV:
-		rdmsrl_safe(index, data);
+		rdmsrq_safe(index, data);
 		break;
 	default:
 		return kvm_x86_call(get_feature_msr)(index, data);
@@ -3829,7 +3842,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!data)
 			break;
 
-		wrmsrl(MSR_IA32_PRED_CMD, data);
+		wrmsrq(MSR_IA32_PRED_CMD, data);
 		break;
 	}
 	case MSR_IA32_FLUSH_CMD:
@@ -3842,7 +3855,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!data)
 			break;
 
-		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
 		break;
 	case MSR_EFER:
 		return set_efer(vcpu, msr_info);
@@ -4739,6 +4752,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
+		if (kvm)
+			r = kvm->max_vcpus;
 		break;
 	case KVM_CAP_MAX_VCPU_ID:
 		r = KVM_MAX_VCPU_IDS;
@@ -4794,7 +4809,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = enable_pmu ? KVM_CAP_PMU_VALID_MASK : 0;
 		break;
 	case KVM_CAP_DISABLE_QUIRKS2:
-		r = KVM_X86_VALID_QUIRKS;
+		r = kvm_caps.supported_quirks;
 		break;
 	case KVM_CAP_X86_NOTIFY_VMEXIT:
 		r = kvm_caps.has_notify_vmexit;
@@ -5117,6 +5132,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
+	if (vcpu->arch.apic->guest_apic_protected)
+		return -EINVAL;
+
 	kvm_x86_call(sync_pir_to_irr)(vcpu);
 
 	return kvm_apic_get_state(vcpu, s);
@@ -5127,6 +5145,9 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 {
 	int r;
 
+	if (vcpu->arch.apic->guest_apic_protected)
+		return -EINVAL;
+
 	r = kvm_apic_set_state(vcpu, s);
 	if (r)
 		return r;
@@ -6304,6 +6325,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_SET_DEVICE_ATTR:
 		r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp);
 		break;
+	case KVM_MEMORY_ENCRYPT_OP:
+		r = -ENOTTY;
+		if (!kvm_x86_ops.vcpu_mem_enc_ioctl)
+			goto out;
+		r = kvm_x86_ops.vcpu_mem_enc_ioctl(vcpu, argp);
+		break;
 	default:
 		r = -EINVAL;
 	}
@@ -6491,7 +6518,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 	struct kvm_vcpu *vcpu;
 	unsigned long i;
 
-	if (!kvm_x86_ops.cpu_dirty_log_size)
+	if (!kvm->arch.cpu_dirty_log_size)
 		return;
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
@@ -6521,11 +6548,11 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	switch (cap->cap) {
 	case KVM_CAP_DISABLE_QUIRKS2:
 		r = -EINVAL;
-		if (cap->args[0] & ~KVM_X86_VALID_QUIRKS)
+		if (cap->args[0] & ~kvm_caps.supported_quirks)
 			break;
 		fallthrough;
 	case KVM_CAP_DISABLE_QUIRKS:
-		kvm->arch.disabled_quirks = cap->args[0];
+		kvm->arch.disabled_quirks |= cap->args[0] & kvm_caps.supported_quirks;
 		r = 0;
 		break;
 	case KVM_CAP_SPLIT_IRQCHIP: {
@@ -7300,10 +7327,6 @@ set_pit2_out:
 		goto out;
 	}
 	case KVM_MEMORY_ENCRYPT_OP: {
-		r = -ENOTTY;
-		if (!kvm_x86_ops.mem_enc_ioctl)
-			goto out;
-
 		r = kvm_x86_call(mem_enc_ioctl)(kvm, argp);
 		break;
 	}
@@ -9738,7 +9761,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 	 * with an exception.  PAT[0] is set to WB on RESET and also by the
 	 * kernel, i.e. failure indicates a kernel bug or broken firmware.
 	 */
-	if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) ||
+	if (rdmsrq_safe(MSR_IA32_CR_PAT, &host_pat) ||
 	    (host_pat & GENMASK(2, 0)) != 6) {
 		pr_err("host PAT[0] is not WB\n");
 		return -EIO;
@@ -9771,16 +9794,18 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 		kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 		kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0;
 	}
+	kvm_caps.supported_quirks = KVM_X86_VALID_QUIRKS;
+	kvm_caps.inapplicable_quirks = KVM_X86_CONDITIONAL_QUIRKS;
 
-	rdmsrl_safe(MSR_EFER, &kvm_host.efer);
+	rdmsrq_safe(MSR_EFER, &kvm_host.efer);
 
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
-		rdmsrl(MSR_IA32_XSS, kvm_host.xss);
+		rdmsrq(MSR_IA32_XSS, kvm_host.xss);
 
 	kvm_init_pmu_capability(ops->pmu_ops);
 
 	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
+		rdmsrq(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
 
 	r = ops->hardware_setup();
 	if (r != 0)
@@ -9815,6 +9840,10 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
 	if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled)
 		kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM);
 
+	/* KVM always ignores guest PAT for shadow paging.  */
+	if (!tdp_enabled)
+		kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT;
+
 	if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
 		kvm_caps.supported_xss = 0;
 
@@ -10023,13 +10052,16 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
 	return kvm_skip_emulated_instruction(vcpu);
 }
 
-int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
-			      unsigned long a0, unsigned long a1,
-			      unsigned long a2, unsigned long a3,
-			      int op_64_bit, int cpl,
+int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl,
 			      int (*complete_hypercall)(struct kvm_vcpu *))
 {
 	unsigned long ret;
+	unsigned long nr = kvm_rax_read(vcpu);
+	unsigned long a0 = kvm_rbx_read(vcpu);
+	unsigned long a1 = kvm_rcx_read(vcpu);
+	unsigned long a2 = kvm_rdx_read(vcpu);
+	unsigned long a3 = kvm_rsi_read(vcpu);
+	int op_64_bit = is_64_bit_hypercall(vcpu);
 
 	++vcpu->stat.hypercalls;
 
@@ -10132,9 +10164,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	if (kvm_hv_hypercall_enabled(vcpu))
 		return kvm_hv_hypercall(vcpu);
 
-	return __kvm_emulate_hypercall(vcpu, rax, rbx, rcx, rdx, rsi,
-				       is_64_bit_hypercall(vcpu),
-				       kvm_x86_call(get_cpl)(vcpu),
+	return __kvm_emulate_hypercall(vcpu, kvm_x86_call(get_cpl)(vcpu),
 				       complete_hypercall_exit);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
@@ -10976,9 +11006,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		switch_fpu_return();
 
 	if (vcpu->arch.guest_fpu.xfd_err)
-		wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+		wrmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
 
-	if (unlikely(vcpu->arch.switch_db_regs)) {
+	if (unlikely(vcpu->arch.switch_db_regs &&
+		     !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) {
 		set_debugreg(0, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
 		set_debugreg(vcpu->arch.eff_db[1], 1);
@@ -11030,6 +11061,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 */
 	if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
 		WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
+		WARN_ON(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH);
 		kvm_x86_call(sync_dirty_debug_regs)(vcpu);
 		kvm_update_dr0123(vcpu);
 		kvm_update_dr7(vcpu);
@@ -11062,7 +11094,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_call(handle_exit_irqoff)(vcpu);
 
 	if (vcpu->arch.guest_fpu.xfd_err)
-		wrmsrl(MSR_IA32_XFD_ERR, 0);
+		wrmsrq(MSR_IA32_XFD_ERR, 0);
 
 	/*
 	 * Consume any pending interrupts, including the possible source of
@@ -11134,7 +11166,7 @@ static bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
 		!vcpu->arch.apf.halted);
 }
 
-static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
+bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 {
 	if (!list_empty_careful(&vcpu->async_pf.done))
 		return true;
@@ -11143,9 +11175,6 @@ static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 	    kvm_apic_init_sipi_allowed(vcpu))
 		return true;
 
-	if (vcpu->arch.pv.pv_unhalted)
-		return true;
-
 	if (kvm_is_exception_pending(vcpu))
 		return true;
 
@@ -11183,10 +11212,12 @@ static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_has_events);
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
+	return kvm_vcpu_running(vcpu) || vcpu->arch.pv.pv_unhalted ||
+	       kvm_vcpu_has_events(vcpu);
 }
 
 /* Called within kvm->srcu read side.  */
@@ -11320,7 +11351,7 @@ static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason)
 	 */
 	++vcpu->stat.halt_exits;
 	if (lapic_in_kernel(vcpu)) {
-		if (kvm_vcpu_has_events(vcpu))
+		if (kvm_vcpu_has_events(vcpu) || vcpu->arch.pv.pv_unhalted)
 			state = KVM_MP_STATE_RUNNABLE;
 		kvm_set_mp_state(vcpu, state);
 		return 1;
@@ -12694,6 +12725,7 @@ bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id;
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp);
 
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 {
@@ -12723,6 +12755,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	/* Decided by the vendor code for other VM types.  */
 	kvm->arch.pre_fault_allowed =
 		type == KVM_X86_DEFAULT_VM || type == KVM_X86_SW_PROTECTED_VM;
+	kvm->arch.disabled_quirks = kvm_caps.inapplicable_quirks & kvm_caps.supported_quirks;
 
 	ret = kvm_page_track_init(kvm);
 	if (ret)
@@ -12876,6 +12909,7 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 	kvm_free_pit(kvm);
 
 	kvm_mmu_pre_destroy_vm(kvm);
+	static_call_cond(kvm_x86_vm_pre_destroy)(kvm);
 }
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
@@ -13073,7 +13107,7 @@ static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable)
 {
 	int nr_slots;
 
-	if (!kvm_x86_ops.cpu_dirty_log_size)
+	if (!kvm->arch.cpu_dirty_log_size)
 		return;
 
 	nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging);
@@ -13145,7 +13179,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
 		if (READ_ONCE(eager_page_split))
 			kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K);
 
-		if (kvm_x86_ops.cpu_dirty_log_size) {
+		if (kvm->arch.cpu_dirty_log_size) {
 			kvm_mmu_slot_leaf_clear_dirty(kvm, new);
 			kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M);
 		} else {
@@ -13534,8 +13568,10 @@ static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm)
 	 * due to toggling the "ignore PAT" bit.  Zap all SPTEs when the first
 	 * (or last) non-coherent device is (un)registered to so that new SPTEs
 	 * with the correct "ignore guest PAT" setting are created.
+	 *
+	 * If KVM always honors guest PAT, however, there is nothing to do.
 	 */
-	if (kvm_mmu_may_ignore_guest_pat())
+	if (kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT))
 		kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL));
 }
 
@@ -13668,12 +13704,12 @@ int kvm_spec_ctrl_test_value(u64 value)
 
 	local_irq_save(flags);
 
-	if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value))
+	if (rdmsrq_safe(MSR_IA32_SPEC_CTRL, &saved_value))
 		ret = 1;
-	else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value))
+	else if (wrmsrq_safe(MSR_IA32_SPEC_CTRL, value))
 		ret = 1;
 	else
-		wrmsrl(MSR_IA32_SPEC_CTRL, saved_value);
+		wrmsrq(MSR_IA32_SPEC_CTRL, saved_value);
 
 	local_irq_restore(flags);
 
@@ -14012,6 +14048,7 @@ EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);