KVM: x86: require matched TSC offsets for master clock

With master clock, a pvclock clock read calculates:

ret = system_timestamp + [ (rdtsc + tsc_offset) - tsc_timestamp ]

Where 'rdtsc' is the host TSC.

system_timestamp and tsc_timestamp are unique, one tuple
per VM: the "master clock".

Given a host with synchronized TSCs, its obvious that
guest TSC must be matched for the above to guarantee monotonicity.

Allow master clock usage only if guest TSCs are synchronized.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

3 files changed, 89 insertions, 8 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 32f0e4a063b7..9fb6d8da7a43 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -561,6 +561,7 @@ struct kvm_arch {
         u64 cur_tsc_write;
         u64 cur_tsc_offset;
         u8  cur_tsc_generation;
+        int nr_vcpus_matched_tsc;
 
         spinlock_t pvclock_gtod_sync_lock;
         bool use_master_clock;
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 1d6526856080..fe5e00ed7036 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -764,21 +764,54 @@ TRACE_EVENT(
         {VCLOCK_HPET, "hpet"}                           \
 
 TRACE_EVENT(kvm_update_master_clock,
-        TP_PROTO(bool use_master_clock, unsigned int host_clock),
-        TP_ARGS(use_master_clock, host_clock),
+        TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched),
+        TP_ARGS(use_master_clock, host_clock, offset_matched),
 
         TP_STRUCT__entry(
                 __field(                bool,   use_master_clock        )
                 __field(        unsigned int,   host_clock              )
+                __field(                bool,   offset_matched          )
         ),
 
         TP_fast_assign(
                 __entry->use_master_clock       = use_master_clock;
                 __entry->host_clock             = host_clock;
+                __entry->offset_matched         = offset_matched;
         ),
 
-        TP_printk("masterclock %d hostclock %s",
+        TP_printk("masterclock %d hostclock %s offsetmatched %u",
                   __entry->use_master_clock,
+                  __print_symbolic(__entry->host_clock, host_clocks),
+                  __entry->offset_matched)
+);
+
+TRACE_EVENT(kvm_track_tsc,
+        TP_PROTO(unsigned int vcpu_id, unsigned int nr_matched,
+                 unsigned int online_vcpus, bool use_master_clock,
+                 unsigned int host_clock),
+        TP_ARGS(vcpu_id, nr_matched, online_vcpus, use_master_clock,
+                host_clock),
+
+        TP_STRUCT__entry(
+                __field(        unsigned int,   vcpu_id                 )
+                __field(        unsigned int,   nr_vcpus_matched_tsc    )
+                __field(        unsigned int,   online_vcpus            )
+                __field(        bool,           use_master_clock        )
+                __field(        unsigned int,   host_clock              )
+        ),
+
+        TP_fast_assign(
+                __entry->vcpu_id                = vcpu_id;
+                __entry->nr_vcpus_matched_tsc   = nr_matched;
+                __entry->online_vcpus           = online_vcpus;
+                __entry->use_master_clock       = use_master_clock;
+                __entry->host_clock             = host_clock;
+        ),
+
+        TP_printk("vcpu_id %u masterclock %u offsetmatched %u nr_online %u"
+                  " hostclock %s",
+                  __entry->vcpu_id, __entry->use_master_clock,
+                  __entry->nr_vcpus_matched_tsc, __entry->online_vcpus,
                   __print_symbolic(__entry->host_clock, host_clocks))
 );
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f3c069efc72a..422ef5ed2194 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1103,12 +1103,40 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
         return tsc;
 }
 
+void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_X86_64
+        bool vcpus_matched;
+        bool do_request = false;
+        struct kvm_arch *ka = &vcpu->kvm->arch;
+        struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+
+        vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
+                         atomic_read(&vcpu->kvm->online_vcpus));
+
+        if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC)
+                if (!ka->use_master_clock)
+                        do_request = 1;
+
+        if (!vcpus_matched && ka->use_master_clock)
+                        do_request = 1;
+
+        if (do_request)
+                kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
+
+        trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
+                            atomic_read(&vcpu->kvm->online_vcpus),
+                            ka->use_master_clock, gtod->clock.vclock_mode);
+#endif
+}
+
 void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 {
         struct kvm *kvm = vcpu->kvm;
         u64 offset, ns, elapsed;
         unsigned long flags;
         s64 usdiff;
+        bool matched;
 
         raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
         offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
@@ -1151,6 +1179,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
                         offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
                         pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
                 }
+                matched = true;
         } else {
                 /*
                  * We split periods of matched TSC writes into generations.
@@ -1165,6 +1194,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
                 kvm->arch.cur_tsc_nsec = ns;
                 kvm->arch.cur_tsc_write = data;
                 kvm->arch.cur_tsc_offset = offset;
+                matched = false;
                 pr_debug("kvm: new tsc generation %u, clock %llu\n",
                          kvm->arch.cur_tsc_generation, data);
         }
@@ -1188,6 +1218,15 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 
         kvm_x86_ops->write_tsc_offset(vcpu, offset);
         raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+
+        spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
+        if (matched)
+                kvm->arch.nr_vcpus_matched_tsc++;
+        else
+                kvm->arch.nr_vcpus_matched_tsc = 0;
+
+        kvm_track_tsc_matching(vcpu);
+        spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
 }
 
 EXPORT_SYMBOL_GPL(kvm_write_tsc);
@@ -1279,8 +1318,9 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now)
 
 /*
  *
- * Assuming a stable TSC across physical CPUS, the following condition
- * is possible. Each numbered line represents an event visible to both
+ * Assuming a stable TSC across physical CPUS, and a stable TSC
+ * across virtual CPUs, the following condition is possible.
+ * Each numbered line represents an event visible to both
  * CPUs at the next numbered event.
  *
  * "timespecX" represents host monotonic time. "tscX" represents
@@ -1313,7 +1353,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, cycle_t *cycle_now)
  * copy of host monotonic time values. Update that master copy
  * in lockstep.
  *
- * Rely on synchronization of host TSCs for monotonicity.
+ * Rely on synchronization of host TSCs and guest TSCs for monotonicity.
  *
  */
 
@@ -1322,20 +1362,27 @@ 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;
+
+        vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
+                        atomic_read(&kvm->online_vcpus));
 
         /*
          * If the host uses TSC clock, then passthrough TSC as stable
          * to the guest.
          */
-        ka->use_master_clock = kvm_get_time_and_clockread(
+        host_tsc_clocksource = kvm_get_time_and_clockread(
                                         &ka->master_kernel_ns,
                                         &ka->master_cycle_now);
 
+        ka->use_master_clock = host_tsc_clocksource & vcpus_matched;
+
         if (ka->use_master_clock)
                 atomic_set(&kvm_guest_has_master_clock, 1);
 
         vclock_mode = pvclock_gtod_data.clock.vclock_mode;
-        trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode);
+        trace_kvm_update_master_clock(ka->use_master_clock, vclock_mode,
+                                        vcpus_matched);
 #endif
 }