1 files changed, 93 insertions, 75 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index aafcc9881e88..40aa29204baf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,7 +51,7 @@
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/mmu_context.h>
-#include <asm/nospec-branch.h>
+#include <asm/spec-ctrl.h>
 #include <asm/mshyperv.h>
 
 #include "trace.h"
@@ -1494,6 +1494,12 @@ static inline bool cpu_has_vmx_vmfunc(void)
 		SECONDARY_EXEC_ENABLE_VMFUNC;
 }
 
+static bool vmx_umip_emulated(void)
+{
+	return vmcs_config.cpu_based_2nd_exec_ctrl &
+		SECONDARY_EXEC_DESC;
+}
+
 static inline bool report_flexpriority(void)
 {
 	return flexpriority_enabled;
@@ -2880,18 +2886,15 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 		vmx_update_msr_bitmap(&vmx->vcpu);
 }
 
-/*
- * reads and returns guest's timestamp counter "register"
- * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
- * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
- */
-static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
+static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 {
-	u64 host_tsc, tsc_offset;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	host_tsc = rdtsc();
-	tsc_offset = vmcs_read64(TSC_OFFSET);
-	return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
+	if (is_guest_mode(vcpu) &&
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
+
+	return vcpu->arch.tsc_offset;
 }
 
 /*
@@ -3524,12 +3527,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
-	case MSR_IA32_TSC:
-		msr_info->data = guest_read_tsc(vcpu);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
@@ -3646,17 +3645,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
-	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr_info);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
 		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP))
+		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
 			return 1;
 
 		vmx->spec_ctrl = data;
@@ -3682,7 +3677,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_IBPB) &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
 			return 1;
 
@@ -4553,12 +4547,6 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
 	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa);
 }
 
-static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
-{
-	if (enable_ept)
-		vmx_flush_tlb(vcpu, true);
-}
-
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -4776,14 +4764,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	else
 		hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
 
-	if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
-		vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
-			      SECONDARY_EXEC_DESC);
-		hw_cr4 &= ~X86_CR4_UMIP;
-	} else if (!is_guest_mode(vcpu) ||
-	           !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
-		vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+	if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
+		if (cr4 & X86_CR4_UMIP) {
+			vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
 				SECONDARY_EXEC_DESC);
+			hw_cr4 &= ~X86_CR4_UMIP;
+		} else if (!is_guest_mode(vcpu) ||
+			!nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC))
+			vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+					SECONDARY_EXEC_DESC);
+	}
 
 	if (cr4 & X86_CR4_VMXE) {
 		/*
@@ -9287,7 +9277,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	} else {
 		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
@@ -9315,7 +9305,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
 			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 }
 
@@ -9495,9 +9485,21 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 }
 STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
 
-static bool vmx_has_high_real_mode_segbase(void)
+static bool vmx_has_emulated_msr(int index)
 {
-	return enable_unrestricted_guest || emulate_invalid_guest_state;
+	switch (index) {
+	case MSR_IA32_SMBASE:
+		/*
+		 * We cannot do SMM unless we can run the guest in big
+		 * real mode.
+		 */
+		return enable_unrestricted_guest || emulate_invalid_guest_state;
+	case MSR_AMD64_VIRT_SPEC_CTRL:
+		/* This is AMD only.  */
+		return false;
+	default:
+		return true;
+	}
 }
 
 static bool vmx_mpx_supported(void)
@@ -9512,12 +9514,6 @@ static bool vmx_xsaves_supported(void)
 		SECONDARY_EXEC_XSAVES;
 }
 
-static bool vmx_umip_emulated(void)
-{
-	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_DESC;
-}
-
 static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 {
 	u32 exit_intr_info;
@@ -9735,8 +9731,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	 * is no need to worry about the conditional branch over the wrmsr
 	 * being speculatively taken.
 	 */
-	if (vmx->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, vmx->spec_ctrl);
+	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 
@@ -9884,8 +9879,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
 		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
 
-	if (vmx->spec_ctrl)
-		native_wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
 
 	/* Eliminate branch target predictions from guest mode */
 	vmexit_fill_RSB();
@@ -10608,6 +10602,16 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+	    !page_address_valid(vcpu, vmcs12->apic_access_addr))
+		return -EINVAL;
+	else
+		return 0;
+}
+
 static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
 					   struct vmcs12 *vmcs12)
 {
@@ -11176,11 +11180,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 	}
 
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
-		vmcs_write64(TSC_OFFSET,
-			vcpu->arch.tsc_offset + vmcs12->tsc_offset);
-	else
-		vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
 
@@ -11222,7 +11223,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		}
 	} else if (nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 
 	/*
@@ -11299,6 +11300,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
+	if (nested_vmx_check_apic_access_controls(vcpu, vmcs12))
+		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
 	if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
@@ -11420,6 +11424,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	u32 msr_entry_idx;
 	u32 exit_qual;
+	int r;
 
 	enter_guest_mode(vcpu);
 
@@ -11429,26 +11434,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
 	vmx_segment_cache_clear(vmx);
 
-	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
-		leave_guest_mode(vcpu);
-		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-		nested_vmx_entry_failure(vcpu, vmcs12,
-					 EXIT_REASON_INVALID_STATE, exit_qual);
-		return 1;
-	}
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
+
+	r = EXIT_REASON_INVALID_STATE;
+	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+		goto fail;
 
 	nested_get_vmcs12_pages(vcpu, vmcs12);
 
+	r = EXIT_REASON_MSR_LOAD_FAIL;
 	msr_entry_idx = nested_vmx_load_msr(vcpu,
 					    vmcs12->vm_entry_msr_load_addr,
 					    vmcs12->vm_entry_msr_load_count);
-	if (msr_entry_idx) {
-		leave_guest_mode(vcpu);
-		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-		nested_vmx_entry_failure(vcpu, vmcs12,
-				EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
-		return 1;
-	}
+	if (msr_entry_idx)
+		goto fail;
 
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
@@ -11457,6 +11457,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
 	 */
 	return 0;
+
+fail:
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+	leave_guest_mode(vcpu);
+	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+	nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual);
+	return 1;
 }
 
 /*
@@ -12028,6 +12036,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	leave_guest_mode(vcpu);
 
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+
 	if (likely(!vmx->fail)) {
 		if (exit_reason == -1)
 			sync_vmcs12(vcpu, vmcs12);
@@ -12065,7 +12076,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	} else if (!nested_cpu_has_ept(vmcs12) &&
 		   nested_cpu_has2(vmcs12,
 				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
-		vmx_flush_tlb_ept_only(vcpu);
+		vmx_flush_tlb(vcpu, true);
 	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
@@ -12224,10 +12235,16 @@ 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 = to_vmx(vcpu);
-	u64 tscl = rdtsc();
-	u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
-	u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+	struct vcpu_vmx *vmx;
+	u64 tscl, guest_tscl, delta_tsc;
+
+	if (kvm_mwait_in_guest(vcpu->kvm))
+		return -EOPNOTSUPP;
+
+	vmx = to_vmx(vcpu);
+	tscl = rdtsc();
+	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
 
 	/* Convert to host delta tsc if tsc scaling is enabled */
 	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
@@ -12533,7 +12550,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
 
-		trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
+		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
 		if (set)
@@ -12622,7 +12639,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.hardware_enable = hardware_enable,
 	.hardware_disable = hardware_disable,
 	.cpu_has_accelerated_tpr = report_flexpriority,
-	.cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
+	.has_emulated_msr = vmx_has_emulated_msr,
 
 	.vm_init = vmx_vm_init,
 	.vm_alloc = vmx_vm_alloc,
@@ -12712,6 +12729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
+	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
 	.write_tsc_offset = vmx_write_tsc_offset,
 
 	.set_tdp_cr3 = vmx_set_cr3,