x86/KVM/VMX: Add module argument for L1TF mitigation

Add a mitigation mode parameter "vmentry_l1d_flush" for CVE-2018-3620, aka
L1 terminal fault. The valid arguments are:

 - "always" 	L1D cache flush on every VMENTER.
 - "cond"	Conditional L1D cache flush, explained below
 - "never"	Disable the L1D cache flush mitigation

"cond" is trying to avoid L1D cache flushes on VMENTER if the code executed
between VMEXIT and VMENTER is considered safe, i.e. is not bringing any
interesting information into L1D which might exploited.

[ tglx: Split out from a larger patch ]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

CVE-2018-3620
CVE-2018-3646

[smb: Minor context adjustments]
Signed-off-by: Stefan Bader <stefan.bader@canonical.com>

Documentation/kernel-parameters.txt

@@ -1814,6 +1814,18 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			(virtualized real and unpaged mode) on capable
 			Intel chips. Default is 1 (enabled)
 
+	kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
+			CVE-2018-3620.
+
+			Valid arguments: never, cond, always
+
+			always: L1D cache flush on every VMENTER.
+			cond:	Flush L1D on VMENTER only when the code between
+				VMEXIT and VMENTER can leak host memory.
+			never:	Disables the mitigation
+
+			Default is cond (do L1 cache flush in specific instances)
+
 	kvm-intel.vpid=	[KVM,Intel] Disable Virtual Processor Identification
 			feature (tagged TLBs) on capable Intel chips.
 			Default is 1 (enabled)

arch/x86/kvm/vmx.c

@@ -176,6 +176,54 @@ module_param(ple_window_max, int, S_IRUGO);
 
 extern const ulong vmx_return;
 
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+
+/* These MUST be in sync with vmentry_l1d_param order. */
+enum vmx_l1d_flush_state {
+	VMENTER_L1D_FLUSH_NEVER,
+	VMENTER_L1D_FLUSH_COND,
+	VMENTER_L1D_FLUSH_ALWAYS,
+};
+
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush = VMENTER_L1D_FLUSH_COND;
+
+static const struct {
+	const char *option;
+	enum vmx_l1d_flush_state cmd;
+} vmentry_l1d_param[] = {
+	{"never",	VMENTER_L1D_FLUSH_NEVER},
+	{"cond",	VMENTER_L1D_FLUSH_COND},
+	{"always",	VMENTER_L1D_FLUSH_ALWAYS},
+};
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+	unsigned int i;
+
+	if (!s)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+		if (!strcmp(s, vmentry_l1d_param[i].option)) {
+			vmentry_l1d_flush = vmentry_l1d_param[i].cmd;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
+{
+	return sprintf(s, "%s\n", vmentry_l1d_param[vmentry_l1d_flush].option);
+}
+
+static const struct kernel_param_ops vmentry_l1d_flush_ops = {
+	.set = vmentry_l1d_flush_set,
+	.get = vmentry_l1d_flush_get,
+};
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, &vmentry_l1d_flush, S_IRUGO);
+
 #define NR_AUTOLOAD_MSRS 8
 #define VMCS02_POOL_SIZE 1
 
@@ -11031,8 +11079,19 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.update_pi_irte = vmx_update_pi_irte,
 };
 
+static void __init vmx_setup_l1d_flush(void)
+{
+	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
+	    !boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+	static_branch_enable(&vmx_l1d_should_flush);
+}
+
 static int __init vmx_init(void)
 {
+	vmx_setup_l1d_flush();
+
 	int r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
                      __alignof__(struct vcpu_vmx), THIS_MODULE);
 	if (r)