1 files changed, 123 insertions, 32 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index a07e8cd753ec..be7c19374fdd 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -229,6 +229,9 @@ static const struct {
 #define L1D_CACHE_ORDER 4
 static void *vmx_l1d_flush_pages;
 
+/* Control for disabling CPU Fill buffer clear */
+static bool __read_mostly vmx_fb_clear_ctrl_available;
+
 static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 {
 	struct page *page;
@@ -360,6 +363,60 @@ static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
 	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
 }
 
+static void vmx_setup_fb_clear_ctrl(void)
+{
+	u64 msr;
+
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES) &&
+	    !boot_cpu_has_bug(X86_BUG_MDS) &&
+	    !boot_cpu_has_bug(X86_BUG_TAA)) {
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+		if (msr & ARCH_CAP_FB_CLEAR_CTRL)
+			vmx_fb_clear_ctrl_available = true;
+	}
+}
+
+static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
+{
+	u64 msr;
+
+	if (!vmx->disable_fb_clear)
+		return;
+
+	msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL);
+	msr |= FB_CLEAR_DIS;
+	native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+	/* Cache the MSR value to avoid reading it later */
+	vmx->msr_ia32_mcu_opt_ctrl = msr;
+}
+
+static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
+{
+	if (!vmx->disable_fb_clear)
+		return;
+
+	vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS;
+	native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
+}
+
+static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
+{
+	vmx->disable_fb_clear = vmx_fb_clear_ctrl_available;
+
+	/*
+	 * If guest will not execute VERW, there is no need to set FB_CLEAR_DIS
+	 * at VMEntry. Skip the MSR read/write when a guest has no use case to
+	 * execute VERW.
+	 */
+	if ((vcpu->arch.arch_capabilities & ARCH_CAP_FB_CLEAR) ||
+	   ((vcpu->arch.arch_capabilities & ARCH_CAP_MDS_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_TAA_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_PSDP_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_FBSDP_NO) &&
+	    (vcpu->arch.arch_capabilities & ARCH_CAP_SBDR_SSDP_NO)))
+		vmx->disable_fb_clear = false;
+}
+
 static const struct kernel_param_ops vmentry_l1d_flush_ops = {
 	.set = vmentry_l1d_flush_set,
 	.get = vmentry_l1d_flush_get,
@@ -782,6 +839,24 @@ static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr)
 					 MSR_IA32_SPEC_CTRL);
 }
 
+unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx)
+{
+	unsigned int flags = 0;
+
+	if (vmx->loaded_vmcs->launched)
+		flags |= VMX_RUN_VMRESUME;
+
+	/*
+	 * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free
+	 * to change it directly without causing a vmexit.  In that case read
+	 * it after vmexit and store it in vmx->spec_ctrl.
+	 */
+	if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)))
+		flags |= VMX_RUN_SAVE_SPEC_CTRL;
+
+	return flags;
+}
+
 static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 		unsigned long entry, unsigned long exit)
 {
@@ -2252,6 +2327,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			ret = kvm_set_msr_common(vcpu, msr_info);
 	}
 
+	/* FB_CLEAR may have changed, also update the FB_CLEAR_DIS behavior */
+	if (msr_index == MSR_IA32_ARCH_CAPABILITIES)
+		vmx_update_fb_clear_dis(vcpu, vmx);
+
 	return ret;
 }
 
@@ -4553,6 +4632,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
 	vpid_sync_context(vmx->vpid);
+
+	vmx_update_fb_clear_dis(vcpu, vmx);
 }
 
 static void vmx_enable_irq_window(struct kvm_vcpu *vcpu)
@@ -6547,6 +6628,7 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 		return;
 
 	handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc));
+	vcpu->arch.at_instruction_boundary = true;
 }
 
 static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
@@ -6749,6 +6831,31 @@ void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp)
 	}
 }
 
+void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
+					unsigned int flags)
+{
+	u64 hostval = this_cpu_read(x86_spec_ctrl_current);
+
+	if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL))
+		return;
+
+	if (flags & VMX_RUN_SAVE_SPEC_CTRL)
+		vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL);
+
+	/*
+	 * If the guest/host SPEC_CTRL values differ, restore the host value.
+	 *
+	 * For legacy IBRS, the IBRS bit always needs to be written after
+	 * transitioning from a less privileged predictor mode, regardless of
+	 * whether the guest/host values differ.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) ||
+	    vmx->spec_ctrl != hostval)
+		native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval);
+
+	barrier_nospec();
+}
+
 static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 {
 	switch (to_vmx(vcpu)->exit_reason.basic) {
@@ -6762,7 +6869,8 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 }
 
 static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
-					struct vcpu_vmx *vmx)
+					struct vcpu_vmx *vmx,
+					unsigned long flags)
 {
 	guest_state_enter_irqoff();
 
@@ -6771,15 +6879,22 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 		vmx_l1d_flush(vcpu);
 	else if (static_branch_unlikely(&mds_user_clear))
 		mds_clear_cpu_buffers();
+	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
+		 kvm_arch_has_assigned_device(vcpu->kvm))
+		mds_clear_cpu_buffers();
+
+	vmx_disable_fb_clear(vmx);
 
 	if (vcpu->arch.cr2 != native_read_cr2())
 		native_write_cr2(vcpu->arch.cr2);
 
 	vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
-				   vmx->loaded_vmcs->launched);
+				   flags);
 
 	vcpu->arch.cr2 = native_read_cr2();
 
+	vmx_enable_fb_clear(vmx);
+
 	guest_state_exit_irqoff();
 }
 
@@ -6873,36 +6988,8 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	kvm_wait_lapic_expire(vcpu);
 
-	/*
-	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
-	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
-	 * is no need to worry about the conditional branch over the wrmsr
-	 * being speculatively taken.
-	 */
-	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
-
 	/* The actual VMENTER/EXIT is in the .noinstr.text section. */
-	vmx_vcpu_enter_exit(vcpu, vmx);
-
-	/*
-	 * We do not use IBRS in the kernel. If this vCPU has used the
-	 * SPEC_CTRL MSR it may have left it on; save the value and
-	 * turn it off. This is much more efficient than blindly adding
-	 * it to the atomic save/restore list. Especially as the former
-	 * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
-	 *
-	 * For non-nested case:
-	 * If the L01 MSR bitmap does not intercept the MSR, then we need to
-	 * save it.
-	 *
-	 * For nested case:
-	 * If the L02 MSR bitmap does not intercept the MSR, then we need to
-	 * save it.
-	 */
-	if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)))
-		vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
-
-	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
+	vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx));
 
 	/* All fields are clean at this point */
 	if (static_branch_unlikely(&enable_evmcs)) {
@@ -7708,7 +7795,9 @@ static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
 			  BIT(APICV_INHIBIT_REASON_ABSENT) |
 			  BIT(APICV_INHIBIT_REASON_HYPERV) |
-			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
+			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
+			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
+			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
 
 	return supported & BIT(reason);
 }
@@ -8211,6 +8300,8 @@ static int __init vmx_init(void)
 		return r;
 	}
 
+	vmx_setup_fb_clear_ctrl();
+
 	for_each_possible_cpu(cpu) {
 		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));