KVM: VMX: Tell the nested hypervisor to skip L1D flush on vmentry

When nested virtualization is in use, VMENTER operations from the nested
hypervisor into the nested guest will always be processed by the bare metal
hypervisor, and KVM's "conditional cache flushes" mode in particular does a
flush on nested vmentry.  Therefore, include the "skip L1D flush on
vmentry" bit in KVM's suggested ARCH_CAPABILITIES setting.

Add the relevant Documentation.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Documentation/admin-guide/l1tf.rst

@@ -546,6 +546,27 @@ available:
     EPT can be disabled in the hypervisor via the 'kvm-intel.ept'
     parameter.
 
+3.4. Nested virtual machines
+""""""""""""""""""""""""""""
+
+When nested virtualization is in use, three operating systems are involved:
+the bare metal hypervisor, the nested hypervisor and the nested virtual
+machine.  VMENTER operations from the nested hypervisor into the nested
+guest will always be processed by the bare metal hypervisor. If KVM is the
+bare metal hypervisor it wiil:
+
+ - Flush the L1D cache on every switch from the nested hypervisor to the
+   nested virtual machine, so that the nested hypervisor's secrets are not
+   exposed to the nested virtual machine;
+
+ - Flush the L1D cache on every switch from the nested virtual machine to
+   the nested hypervisor; this is a complex operation, and flushing the L1D
+   cache avoids that the bare metal hypervisor's secrets are exposed to the
+   nested virtual machine;
+
+ - Instruct the nested hypervisor to not perform any L1D cache flush. This
+   is an optimization to avoid double L1D flushing.
+
 
 .. _default_mitigations:
 

arch/x86/include/asm/kvm_host.h

@@ -1418,6 +1418,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
 
+u64 kvm_get_arch_capabilities(void);
 void kvm_define_shared_msr(unsigned index, u32 msr);
 int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 

arch/x86/kvm/vmx.c

@@ -6465,8 +6465,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
+	vmx->arch_capabilities = kvm_get_arch_capabilities();
 
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 

arch/x86/kvm/x86.c

@@ -1103,11 +1103,35 @@ static u32 msr_based_features[] = {
 
 static unsigned int num_msr_based_features;
 
+u64 kvm_get_arch_capabilities(void)
+{
+	u64 data;
+
+	rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+
+	/*
+	 * If we're doing cache flushes (either "always" or "cond")
+	 * we will do one whenever the guest does a vmlaunch/vmresume.
+	 * If an outer hypervisor is doing the cache flush for us
+	 * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that
+	 * capability to the guest too, and if EPT is disabled we're not
+	 * vulnerable.  Overall, only VMENTER_L1D_FLUSH_NEVER will
+	 * require a nested hypervisor to do a flush of its own.
+	 */
+	if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
+		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
+
+	return data;
+}
+EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
+
 static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 {
 	switch (msr->index) {
-	case MSR_IA32_UCODE_REV:
 	case MSR_IA32_ARCH_CAPABILITIES:
+		msr->data = kvm_get_arch_capabilities();
+		break;
+	case MSR_IA32_UCODE_REV:
 		rdmsrl_safe(msr->index, &msr->data);
 		break;
 	default: