Commit 39d61b46 authored by Sean Christopherson's avatar Sean Christopherson
Browse files

KVM: x86: Remove per-vCPU "cache" of its reference pvclock



Remove the per-vCPU "cache" of the reference pvclock and instead cache
only the TSC shift+multiplier.  All other fields in pvclock are fully
recomputed by kvm_guest_time_update(), i.e. aren't actually persisted.

In addition to shaving a few bytes, explicitly tracking the TSC shift/mul
fields makes it easier to see that those fields are tied to hw_tsc_khz
(they exist to avoid having to do expensive math in the common case).
And conversely, not tracking the other fields makes it easier to see that
things like the version number are pulled from the guest's copy, not from
KVM's reference.

Reviewed-by: default avatarPaul Durrant <paul@xen.org>
Link: https://lore.kernel.org/r/20250201013827.680235-10-seanjc@google.com


Signed-off-by: default avatarSean Christopherson <seanjc@google.com>
parent 46aed4d4
Loading
Loading
Loading
Loading
+2 −1
Original line number Diff line number Diff line
@@ -908,7 +908,8 @@ struct kvm_vcpu_arch {
	int (*complete_userspace_io)(struct kvm_vcpu *vcpu);

	gpa_t time;
	struct pvclock_vcpu_time_info hv_clock;
	s8  pvclock_tsc_shift;
	u32 pvclock_tsc_mul;
	unsigned int hw_tsc_khz;
	struct gfn_to_pfn_cache pv_time;
	/* set guest stopped flag in pvclock flags field */
+15 −12
Original line number Diff line number Diff line
@@ -3170,6 +3170,7 @@ static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock,

static int kvm_guest_time_update(struct kvm_vcpu *v)
{
	struct pvclock_vcpu_time_info hv_clock = {};
	unsigned long flags, tgt_tsc_khz;
	unsigned seq;
	struct kvm_vcpu_arch *vcpu = &v->arch;
@@ -3247,20 +3248,22 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)

	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
				   &vcpu->hv_clock.tsc_shift,
				   &vcpu->hv_clock.tsc_to_system_mul);
				   &vcpu->pvclock_tsc_shift,
				   &vcpu->pvclock_tsc_mul);
		vcpu->hw_tsc_khz = tgt_tsc_khz;
		kvm_xen_update_tsc_info(v);
	}

	vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
	hv_clock.tsc_shift = vcpu->pvclock_tsc_shift;
	hv_clock.tsc_to_system_mul = vcpu->pvclock_tsc_mul;
	hv_clock.tsc_timestamp = tsc_timestamp;
	hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
	vcpu->last_guest_tsc = tsc_timestamp;

	/* If the host uses TSC clocksource, then it is stable */
	vcpu->hv_clock.flags = 0;
	hv_clock.flags = 0;
	if (use_master_clock)
		vcpu->hv_clock.flags |= PVCLOCK_TSC_STABLE_BIT;
		hv_clock.flags |= PVCLOCK_TSC_STABLE_BIT;

	if (vcpu->pv_time.active) {
		/*
@@ -3269,24 +3272,24 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
		 * is active/enabled.
		 */
		if (vcpu->pvclock_set_guest_stopped_request) {
			vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
			hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
			vcpu->pvclock_set_guest_stopped_request = false;
		}
		kvm_setup_guest_pvclock(&vcpu->hv_clock, v, &vcpu->pv_time, 0, false);
		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->pv_time, 0, false);

		vcpu->hv_clock.flags &= ~PVCLOCK_GUEST_STOPPED;
		hv_clock.flags &= ~PVCLOCK_GUEST_STOPPED;
	}

#ifdef CONFIG_KVM_XEN
	if (vcpu->xen.vcpu_info_cache.active)
		kvm_setup_guest_pvclock(&vcpu->hv_clock, v, &vcpu->xen.vcpu_info_cache,
		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_info_cache,
					offsetof(struct compat_vcpu_info, time),
					xen_pvclock_tsc_unstable);
	if (vcpu->xen.vcpu_time_info_cache.active)
		kvm_setup_guest_pvclock(&vcpu->hv_clock, v, &vcpu->xen.vcpu_time_info_cache, 0,
		kvm_setup_guest_pvclock(&hv_clock, v, &vcpu->xen.vcpu_time_info_cache, 0,
					xen_pvclock_tsc_unstable);
#endif
	kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
	kvm_hv_setup_tsc_page(v->kvm, &hv_clock);
	return 0;
}

+4 −4
Original line number Diff line number Diff line
@@ -176,8 +176,8 @@ static int xen_get_guest_pvclock(struct kvm_vcpu *vcpu,
	 * Sanity check TSC shift+multiplier to verify the guest's view of time
	 * is more or less consistent.
	 */
	if (hv_clock->tsc_shift != vcpu->arch.hv_clock.tsc_shift ||
	    hv_clock->tsc_to_system_mul != vcpu->arch.hv_clock.tsc_to_system_mul)
	if (hv_clock->tsc_shift != vcpu->arch.pvclock_tsc_shift ||
	    hv_clock->tsc_to_system_mul != vcpu->arch.pvclock_tsc_mul)
		return -EINVAL;

	return 0;
@@ -2316,8 +2316,8 @@ void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu)

	entry = kvm_find_cpuid_entry_index(vcpu, function, 1);
	if (entry) {
		entry->ecx = vcpu->arch.hv_clock.tsc_to_system_mul;
		entry->edx = vcpu->arch.hv_clock.tsc_shift;
		entry->ecx = vcpu->arch.pvclock_tsc_mul;
		entry->edx = vcpu->arch.pvclock_tsc_shift;
	}

	entry = kvm_find_cpuid_entry_index(vcpu, function, 2);