x86/bugs, kvm: Introduce boot-time control of L1TF mitigations

Introduce the 'l1tf=' kernel command line option to allow for boot-time
switching of mitigation that is used on processors affected by L1TF.

The possible values are:

  full
	Provides all available mitigations for the L1TF vulnerability. Disables
	SMT and enables all mitigations in the hypervisors. SMT control via
	/sys/devices/system/cpu/smt/control is still possible after boot.
	Hypervisors will issue a warning when the first VM is started in
	a potentially insecure configuration, i.e. SMT enabled or L1D flush
	disabled.

  full,force
	Same as 'full', but disables SMT control. Implies the 'nosmt=force'
	command line option. sysfs control of SMT and the hypervisor flush
	control is disabled.

  flush
	Leaves SMT enabled and enables the conditional hypervisor mitigation.
	Hypervisors will issue a warning when the first VM is started in a
	potentially insecure configuration, i.e. SMT enabled or L1D flush
	disabled.

  flush,nosmt
	Disables SMT and enables the conditional hypervisor mitigation. SMT
	control via /sys/devices/system/cpu/smt/control is still possible
	after boot. If SMT is reenabled or flushing disabled at runtime
	hypervisors will issue a warning.

  flush,nowarn
	Same as 'flush', but hypervisors will not warn when
	a VM is started in a potentially insecure configuration.

  off
	Disables hypervisor mitigations and doesn't emit any warnings.

Default is 'flush'.

Let KVM adhere to these semantics, which means:

  - 'lt1f=full,force'	: Performe L1D flushes. No runtime control
    			  possible.

  - 'l1tf=full'
  - 'l1tf-flush'
  - 'l1tf=flush,nosmt'	: Perform L1D flushes and warn on VM start if
			  SMT has been runtime enabled or L1D flushing
			  has been run-time enabled
			  
  - 'l1tf=flush,nowarn'	: Perform L1D flushes and no warnings are emitted.
  
  - 'l1tf=off'		: L1D flushes are not performed and no warnings
			  are emitted.

KVM can always override the L1D flushing behavior using its 'vmentry_l1d_flush'
module parameter except when lt1f=full,force is set.

This makes KVM's private 'nosmt' option redundant, and as it is a bit
non-systematic anyway (this is something to control globally, not on
hypervisor level), remove that option.

Add the missing Documentation entry for the l1tf vulnerability sysfs file
while at it.

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142323.202758176@linutronix.de

1 files changed, 43 insertions, 13 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 08fcd59342ed..c5c0118b126d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -71,9 +71,6 @@ static const struct x86_cpu_id vmx_cpu_id[] = {
 };
 MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
 
-static bool __read_mostly nosmt;
-module_param(nosmt, bool, S_IRUGO);
-
 static bool __read_mostly enable_vpid = 1;
 module_param_named(vpid, enable_vpid, bool, 0444);
 
@@ -215,15 +212,31 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 {
 	struct page *page;
 
-	/* If set to 'auto' select 'cond' */
-	if (l1tf == VMENTER_L1D_FLUSH_AUTO)
-		l1tf = VMENTER_L1D_FLUSH_COND;
-
 	if (!enable_ept) {
 		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
 		return 0;
 	}
 
+	/* If set to auto use the default l1tf mitigation method */
+	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+			l1tf = VMENTER_L1D_FLUSH_NEVER;
+			break;
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+			l1tf = VMENTER_L1D_FLUSH_COND;
+			break;
+		case L1TF_MITIGATION_FULL:
+		case L1TF_MITIGATION_FULL_FORCE:
+			l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+			break;
+		}
+	} else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) {
+		l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+	}
+
 	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
 	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
 		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
@@ -10571,19 +10584,36 @@ free_vcpu:
 	return ERR_PTR(err);
 }
 
-#define L1TF_MSG "SMT enabled with L1TF CPU bug present. Refer to CVE-2018-3620 for details.\n"
+#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
 
 static int vmx_vm_init(struct kvm *kvm)
 {
 	if (!ple_gap)
 		kvm->arch.pause_in_guest = true;
 
-	if (boot_cpu_has(X86_BUG_L1TF) && cpu_smt_control == CPU_SMT_ENABLED) {
-		if (nosmt) {
-			pr_err(L1TF_MSG);
-			return -EOPNOTSUPP;
+	if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+			/* 'I explicitly don't care' is set */
+			break;
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+		case L1TF_MITIGATION_FULL:
+			/*
+			 * Warn upon starting the first VM in a potentially
+			 * insecure environment.
+			 */
+			if (cpu_smt_control == CPU_SMT_ENABLED)
+				pr_warn_once(L1TF_MSG_SMT);
+			if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
+				pr_warn_once(L1TF_MSG_L1D);
+			break;
+		case L1TF_MITIGATION_FULL_FORCE:
+			/* Flush is enforced */
+			break;
 		}
-		pr_warn(L1TF_MSG);
 	}
 	return 0;
 }