kvm: nvmx: limit atomic switch MSRs

Allowing an unlimited number of MSRs to be specified via the VMX
load/store MSR lists (e.g., vm-entry MSR load list) is bad for two
reasons. First, a guest can specify an unreasonable number of MSRs,
forcing KVM to process all of them in software. Second, the SDM bounds
the number of MSRs allowed to be packed into the atomic switch MSR lists.
Quoting the "Miscellaneous Data" section in the "VMX Capability
Reporting Facility" appendix:

"Bits 27:25 is used to compute the recommended maximum number of MSRs
that should appear in the VM-exit MSR-store list, the VM-exit MSR-load
list, or the VM-entry MSR-load list. Specifically, if the value bits
27:25 of IA32_VMX_MISC is N, then 512 * (N + 1) is the recommended
maximum number of MSRs to be included in each list. If the limit is
exceeded, undefined processor behavior may result (including a machine
check during the VMX transition)."

Because KVM needs to protect itself and can't model "undefined processor
behavior", arbitrarily force a VM-entry to fail due to MSR loading when
the MSR load list is too large. Similarly, trigger an abort during a VM
exit that encounters an MSR load list or MSR store list that is too large.

The MSR list size is intentionally not pre-checked so as to maintain
compatibility with hardware inasmuch as possible.

Test these new checks with the kvm-unit-test "x86: nvmx: test max atomic
switch MSRs".
Suggested-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Signed-off-by: Marc Orr <marcorr@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/vmx.h

@@ -111,6 +111,7 @@
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 #define VMX_MISC_ACTIVITY_HLT			0x00000040
 #define VMX_MISC_ZERO_LEN_INS			0x40000000
+#define VMX_MISC_MSR_LIST_MULTIPLIER		512
 
 /* VMFUNC functions */
 #define VMX_VMFUNC_EPTP_SWITCHING               0x00000001

arch/x86/kvm/vmx/nested.c

@@ -198,6 +198,16 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
 	pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator);
 }
 
+static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
+{
+	return fixed_bits_valid(control, low, high);
+}
+
+static inline u64 vmx_control_msr(u32 low, u32 high)
+{
+	return low | ((u64)high << 32);
+}
+
 static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
 {
 	secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_SHADOW_VMCS);
@@ -866,16 +876,34 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
+				       vmx->nested.msrs.misc_high);
+
+	return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
+}
+
 /*
  * Load guest's/host's msr at nested entry/exit.
  * return 0 for success, entry index for failure.
+ *
+ * One of the failure modes for MSR load/store is when a list exceeds the
+ * virtual hardware's capacity. To maintain compatibility with hardware inasmuch
+ * as possible, process all valid entries before failing rather than precheck
+ * for a capacity violation.
  */
 static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 {
 	u32 i;
 	struct vmx_msr_entry e;
+	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
 
 	for (i = 0; i < count; i++) {
+		if (unlikely(i >= max_msr_list_size))
+			goto fail;
+
 		if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
 					&e, sizeof(e))) {
 			pr_debug_ratelimited(
@@ -906,8 +934,12 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	u64 data;
 	u32 i;
 	struct vmx_msr_entry e;
+	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
 
 	for (i = 0; i < count; i++) {
+		if (unlikely(i >= max_msr_list_size))
+			return -EINVAL;
+
 		if (kvm_vcpu_read_guest(vcpu,
 					gpa + i * sizeof(e),
 					&e, 2 * sizeof(u32))) {
@@ -1013,17 +1045,6 @@ static u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
 	return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid;
 }
 
-
-static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
-{
-	return fixed_bits_valid(control, low, high);
-}
-
-static inline u64 vmx_control_msr(u32 low, u32 high)
-{
-	return low | ((u64)high << 32);
-}
-
 static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
 {
 	superset &= mask;