From: David Woodhouse <[email protected]> Both kvm_track_tsc_matching() and pvclock_update_vm_gtod_copy() make a decision about whether the KVM clock should be in master clock mode. They used *different* criteria for the decision though. This isn't really a problem; it only has the potential to cause unnecessary invocations of KVM_REQ_MASTERCLOCK_UPDATE if the masterclock was disabled due to TSC going backwards, or the guest using the old MSR. But it isn't pretty.
Factor the decision out to a single function. And document the historical reason why it's disabled for guests that use the old MSR_KVM_SYSTEM_TIME. Signed-off-by: David Woodhouse <[email protected]> Reviewed-by: Paul Durrant <[email protected]> --- arch/x86/kvm/x86.c | 33 ++++++++++++++++++++++++++------- 1 file changed, 26 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d36d03b8268e..0656d901fe79 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2640,6 +2640,27 @@ static inline bool gtod_is_based_on_tsc(int mode) } #endif +static bool kvm_use_master_clock(struct kvm *kvm) +{ + struct kvm_arch *ka = &kvm->arch; + + /* + * The 'old kvmclock' check is a workaround (from 2015) for a + * SUSE 2.6.16 kernel that didn't boot if the system_time in + * its kvmclock was too far behind the current time. So the + * mode of just setting the reference point and allowing time + * to proceed linearly from there makes it fail to boot. + * Despite that being kind of the *point* of the way the clock + * is exposed to the guest. By coincidence, the offending + * kernels used the old MSR_KVM_SYSTEM_TIME, which was moved + * only because it resided in the wrong number range. So the + * workaround is activated for *all* guests using the old MSR. + */ + return ka->all_vcpus_matched_freq && + !ka->backwards_tsc_observed && + !ka->boot_vcpu_runs_old_kvmclock; +} + static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation) { #ifdef CONFIG_X86_64 @@ -2662,7 +2683,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation) * are fine — each vCPU's pvclock has its own tsc_timestamp that * accounts for its offset. */ - bool use_master_clock = ka->all_vcpus_matched_freq && + bool use_master_clock = kvm_use_master_clock(vcpu->kvm) && gtod_is_based_on_tsc(gtod->clock.vclock_mode); /* @@ -3190,10 +3211,9 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) #ifdef CONFIG_X86_64 struct kvm_arch *ka = &kvm->arch; int vclock_mode; - bool host_tsc_clocksource, vcpus_matched; + bool host_tsc_clocksource; lockdep_assert_held(&kvm->arch.tsc_write_lock); - vcpus_matched = ka->all_vcpus_matched_freq; /* * If the host uses TSC clock, then passthrough TSC as stable @@ -3203,9 +3223,8 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) &ka->master_kernel_ns, &ka->master_cycle_now); - ka->use_master_clock = host_tsc_clocksource && vcpus_matched - && !ka->backwards_tsc_observed - && !ka->boot_vcpu_runs_old_kvmclock; + ka->use_master_clock = host_tsc_clocksource && + kvm_use_master_clock(kvm); if (ka->use_master_clock) { u64 tsc_hz; @@ -3231,7 +3250,7 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) vclock_mode = pvclock_gtod_data.clock.vclock_mode; trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode, - vcpus_matched); + ka->all_vcpus_matched_freq); #endif } -- 2.51.0
