[RFC,21/67] KVM: x86: Add flag to mark TSC as immutable (for TDX)

Commit Message

Isaku Yamahata Nov. 16, 2020, 6:26 p.m. UTC

From: Sean Christopherson <[e-mail]>

The TSC for TDX1 guests is fixed at TD creation time.  Add tsc_immutable
to reflect that the TSC of the guest cannot be changed in any way, and
use it to short circuit all paths that lead to one of the myriad TSC
adjustment flows.

Suggested-by: Kai Huang <[e-mail]>
Signed-off-by: Sean Christopherson <[e-mail]>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/x86.c              | 35 +++++++++++++++++++++++++--------
 2 files changed, 28 insertions(+), 8 deletions(-)

Patch

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 00b34d8f038b..e5b706889d09 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -968,6 +968,7 @@  struct kvm_arch {
 	int audit_point;
 	#endif
 
+	bool tsc_immutable;
 	bool backwards_tsc_observed;
 	bool boot_vcpu_runs_old_kvmclock;
 	u32 bsp_vcpu_id;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2f4b226d5b89..01380f057d9f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2040,7 +2040,9 @@  static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 	u64 ratio;
 
 	/* Guest TSC same frequency as host TSC? */
-	if (!scale) {
+	if (!scale || vcpu->kvm->arch.tsc_immutable) {
+		if (scale)
+			pr_warn_ratelimited("Guest TSC immutable, scaling not supported\n");
 		vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
 		return 0;
 	}
@@ -2216,6 +2218,9 @@  static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 	bool already_matched;
 	bool synchronizing = false;
 
+	if (WARN_ON_ONCE(vcpu->kvm->arch.tsc_immutable))
+		return;
+
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
 	offset = kvm_compute_tsc_offset(vcpu, data);
 	ns = get_kvmclock_base_ns();
@@ -2641,6 +2646,10 @@  static int kvm_guest_time_update(struct kvm_vcpu *v)
 	u8 pvclock_flags;
 	bool use_master_clock;
 
+	/* Unable to update guest time if the TSC is immutable. */
+	if (ka->tsc_immutable)
+		return 0;
+
 	kernel_ns = 0;
 	host_tsc = 0;
 
@@ -3915,7 +3924,8 @@  void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		if (tsc_delta < 0)
 			mark_tsc_unstable("KVM discovered backwards TSC");
 
-		if (kvm_check_tsc_unstable()) {
+		if (kvm_check_tsc_unstable() &&
+		    !vcpu->kvm->arch.tsc_immutable) {
 			u64 offset = kvm_compute_tsc_offset(vcpu,
 						vcpu->arch.last_guest_tsc);
 			kvm_vcpu_write_tsc_offset(vcpu, offset);
@@ -3929,7 +3939,8 @@  void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		 * On a host with synchronized TSC, there is no need to update
 		 * kvmclock on vcpu->cpu migration
 		 */
-		if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1)
+		if ((!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1) &&
+		    !vcpu->kvm->arch.tsc_immutable)
 			kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 		if (vcpu->cpu != cpu)
 			kvm_make_request(KVM_REQ_MIGRATE_TIMER, vcpu);
@@ -4888,10 +4899,11 @@  long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_SET_TSC_KHZ: {
-		u32 user_tsc_khz;
+		u32 user_tsc_khz = (u32)arg;
 
 		r = -EINVAL;
-		user_tsc_khz = (u32)arg;
+		if (vcpu->kvm->arch.tsc_immutable)
+			goto out;
 
 		if (kvm_has_tsc_control &&
 		    user_tsc_khz >= kvm_max_guest_tsc_khz)
@@ -10013,9 +10025,12 @@  void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 	if (mutex_lock_killable(&vcpu->mutex))
 		return;
-	vcpu_load(vcpu);
-	kvm_synchronize_tsc(vcpu, 0);
-	vcpu_put(vcpu);
+
+	if (!kvm->arch.tsc_immutable) {
+		vcpu_load(vcpu);
+		kvm_synchronize_tsc(vcpu, 0);
+		vcpu_put(vcpu);
+	}
 
 	/* poll control enabled by default */
 	vcpu->arch.msr_kvm_poll_control = 1;
@@ -10209,6 +10224,10 @@  int kvm_arch_hardware_enable(void)
 	if (backwards_tsc) {
 		u64 delta_cyc = max_tsc - local_tsc;
 		list_for_each_entry(kvm, &vm_list, vm_list) {
+			if (vcpu->kvm->arch.tsc_immutable) {
+				pr_warn_ratelimited("Backwards TSC observed and guest with immutable TSC active\n");
+				continue;
+			}
 			kvm->arch.backwards_tsc_observed = true;
 			kvm_for_each_vcpu(i, vcpu, kvm) {
 				vcpu->arch.tsc_offset_adjustment += delta_cyc;