KVM: x86: Use current rather than snapshotted TSC frequency if it is constant

Don't snapshot tsc_khz into per-cpu cpu_tsc_khz if the host TSC is
constant, in which case the actual TSC frequency will never change and thus
capturing TSC during initialization is unnecessary, KVM can simply use
tsc_khz.  This value is snapshotted from
kvm_timer_init->kvmclock_cpu_online->tsc_khz_changed(NULL)

On CPUs with constant TSC, but not a hardware-specified TSC frequency,
snapshotting cpu_tsc_khz and using that to set a VM's target TSC frequency
can lead to VM to think its TSC frequency is not what it actually is if
refining the TSC completes after KVM snapshots tsc_khz.  The actual
frequency never changes, only the kernel's calculation of what that
frequency is changes.

Ideally, KVM would not be able to race with TSC refinement, or would have
a hook into tsc_refine_calibration_work() to get an alert when refinement
is complete.  Avoiding the race altogether isn't practical as refinement
takes a relative eternity; it's deliberately put on a work queue outside of
the normal boot sequence to avoid unnecessarily delaying boot.

Adding a hook is doable, but somewhat gross due to KVM's ability to be
built as a module.  And if the TSC is constant, which is likely the case
for every VMX/SVM-capable CPU produced in the last decade, the race can be
hit if and only if userspace is able to create a VM before TSC refinement
completes; refinement is slow, but not that slow.

For now, punt on a proper fix, as not taking a snapshot can help some uses
cases and not taking a snapshot is arguably correct irrespective of the
race with refinement.

Signed-off-by: Anton Romanov <romanton@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20220608183525.1143682-1-romanton@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 33 insertions, 11 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ef12747ecb63..152ea4993b76 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2974,6 +2974,22 @@ static void kvm_update_masterclock(struct kvm *kvm)
 	kvm_end_pvclock_update(kvm);
 }
 
+/*
+ * Use the kernel's tsc_khz directly if the TSC is constant, otherwise use KVM's
+ * per-CPU value (which may be zero if a CPU is going offline).  Note, tsc_khz
+ * can change during boot even if the TSC is constant, as it's possible for KVM
+ * to be loaded before TSC calibration completes.  Ideally, KVM would get a
+ * notification when calibration completes, but practically speaking calibration
+ * will complete before userspace is alive enough to create VMs.
+ */
+static unsigned long get_cpu_tsc_khz(void)
+{
+	if (static_cpu_has(X86_FEATURE_CONSTANT_TSC))
+		return tsc_khz;
+	else
+		return __this_cpu_read(cpu_tsc_khz);
+}
+
 /* Called within read_seqcount_begin/retry for kvm->pvclock_sc.  */
 static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
 {
@@ -2984,7 +3000,8 @@ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
 	get_cpu();
 
 	data->flags = 0;
-	if (ka->use_master_clock && __this_cpu_read(cpu_tsc_khz)) {
+	if (ka->use_master_clock &&
+	    (static_cpu_has(X86_FEATURE_CONSTANT_TSC) || __this_cpu_read(cpu_tsc_khz))) {
 #ifdef CONFIG_X86_64
 		struct timespec64 ts;
 
@@ -2998,7 +3015,7 @@ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data)
 		data->flags |= KVM_CLOCK_TSC_STABLE;
 		hv_clock.tsc_timestamp = ka->master_cycle_now;
 		hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
-		kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+		kvm_get_time_scale(NSEC_PER_SEC, get_cpu_tsc_khz() * 1000LL,
 				   &hv_clock.tsc_shift,
 				   &hv_clock.tsc_to_system_mul);
 		data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc);
@@ -3108,7 +3125,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
-	tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz);
+	tgt_tsc_khz = get_cpu_tsc_khz();
 	if (unlikely(tgt_tsc_khz == 0)) {
 		local_irq_restore(flags);
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
@@ -9038,9 +9055,11 @@ static void tsc_khz_changed(void *data)
 	struct cpufreq_freqs *freq = data;
 	unsigned long khz = 0;
 
+	WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_CONSTANT_TSC));
+
 	if (data)
 		khz = freq->new;
-	else if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+	else
 		khz = cpufreq_quick_get(raw_smp_processor_id());
 	if (!khz)
 		khz = tsc_khz;
@@ -9061,8 +9080,10 @@ static void kvm_hyperv_tsc_notifier(void)
 	hyperv_stop_tsc_emulation();
 
 	/* TSC frequency always matches when on Hyper-V */
-	for_each_present_cpu(cpu)
-		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+		for_each_present_cpu(cpu)
+			per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	}
 	kvm_caps.max_guest_tsc_khz = tsc_khz;
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
@@ -9199,10 +9220,10 @@ static void kvm_timer_init(void)
 		}
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
-	}
 
-	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
-			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
+		cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online",
+				  kvmclock_cpu_online, kvmclock_cpu_down_prep);
+	}
 }
 
 #ifdef CONFIG_X86_64
@@ -9362,10 +9383,11 @@ void kvm_arch_exit(void)
 #endif
 	kvm_lapic_exit();
 
-	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
 					    CPUFREQ_TRANSITION_NOTIFIER);
-	cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
+		cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
+	}
 #ifdef CONFIG_X86_64
 	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
 	irq_work_sync(&pvclock_irq_work);