3 files changed, 73 insertions, 21 deletions

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index feaeb0d3aa4f..eb9b76c716c2 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -29,6 +29,8 @@
 #define KVM_SCALE 22
 
 static int kvmclock = 1;
+static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
 
 static int parse_no_kvmclock(char *arg)
 {
@@ -54,7 +56,8 @@ static unsigned long kvm_get_wallclock(void)
 
         low = (int)__pa_symbol(&wall_clock);
         high = ((u64)__pa_symbol(&wall_clock) >> 32);
-        native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
+
+        native_write_msr(msr_kvm_wall_clock, low, high);
 
         vcpu_time = &get_cpu_var(hv_clock);
         pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
@@ -130,7 +133,8 @@ static int kvm_register_clock(char *txt)
         high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
         printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
                cpu, high, low, txt);
-        return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
+
+        return native_write_msr_safe(msr_kvm_system_time, low, high);
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -165,14 +169,14 @@ static void __init kvm_smp_prepare_boot_cpu(void)
 #ifdef CONFIG_KEXEC
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
-        native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+        native_write_msr(msr_kvm_system_time, 0, 0);
         native_machine_crash_shutdown(regs);
 }
 #endif
 
 static void kvm_shutdown(void)
 {
-        native_write_msr_safe(MSR_KVM_SYSTEM_TIME, 0, 0);
+        native_write_msr(msr_kvm_system_time, 0, 0);
         native_machine_shutdown();
 }
 
@@ -181,27 +185,37 @@ void __init kvmclock_init(void)
         if (!kvm_para_available())
                 return;
 
-        if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-                if (kvm_register_clock("boot clock"))
-                        return;
-                pv_time_ops.sched_clock = kvm_clock_read;
-                x86_platform.calibrate_tsc = kvm_get_tsc_khz;
-                x86_platform.get_wallclock = kvm_get_wallclock;
-                x86_platform.set_wallclock = kvm_set_wallclock;
+        if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+                msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
+                msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
+        } else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
+                return;
+
+        printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+                msr_kvm_system_time, msr_kvm_wall_clock);
+
+        if (kvm_register_clock("boot clock"))
+                return;
+        pv_time_ops.sched_clock = kvm_clock_read;
+        x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+        x86_platform.get_wallclock = kvm_get_wallclock;
+        x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-                x86_cpuinit.setup_percpu_clockev =
-                        kvm_setup_secondary_clock;
+        x86_cpuinit.setup_percpu_clockev =
+                kvm_setup_secondary_clock;
 #endif
 #ifdef CONFIG_SMP
-                smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
+        smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 #endif
-                machine_ops.shutdown  = kvm_shutdown;
+        machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
-                machine_ops.crash_shutdown  = kvm_crash_shutdown;
+        machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
-                kvm_get_preset_lpj();
-                clocksource_register(&kvm_clock);
-                pv_info.paravirt_enabled = 1;
-                pv_info.name = "KVM";
-        }
+        kvm_get_preset_lpj();
+        clocksource_register(&kvm_clock);
+        pv_info.paravirt_enabled = 1;
+        pv_info.name = "KVM";
+
+        if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
+                pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 }
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 03801f2f761f..239427ca02af 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -31,8 +31,16 @@ struct pvclock_shadow_time {
         u32 tsc_to_nsec_mul;
         int tsc_shift;
         u32 version;
+        u8  flags;
 };
 
+static u8 valid_flags __read_mostly = 0;
+
+void pvclock_set_flags(u8 flags)
+{
+        valid_flags = flags;
+}
+
 /*
  * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
  * yielding a 64-bit result.
@@ -91,6 +99,7 @@ static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst,
                 dst->system_timestamp  = src->system_time;
                 dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
                 dst->tsc_shift         = src->tsc_shift;
+                dst->flags             = src->flags;
                 rmb();          /* test version after fetching data */
         } while ((src->version & 1) || (dst->version != src->version));
 
@@ -109,11 +118,14 @@ unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src)
         return pv_tsc_khz;
 }
 
+static atomic64_t last_value = ATOMIC64_INIT(0);
+
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
 {
         struct pvclock_shadow_time shadow;
         unsigned version;
         cycle_t ret, offset;
+        u64 last;
 
         do {
                 version = pvclock_get_time_values(&shadow, src);
@@ -123,6 +135,31 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
                 barrier();
         } while (version != src->version);
 
+        if ((valid_flags & PVCLOCK_TSC_STABLE_BIT) &&
+                (shadow.flags & PVCLOCK_TSC_STABLE_BIT))
+                return ret;
+
+        /*
+         * Assumption here is that last_value, a global accumulator, always goes
+         * forward. If we are less than that, we should not be much smaller.
+         * We assume there is an error marging we're inside, and then the correction
+         * does not sacrifice accuracy.
+         *
+         * For reads: global may have changed between test and return,
+         * but this means someone else updated poked the clock at a later time.
+         * We just need to make sure we are not seeing a backwards event.
+         *
+         * For updates: last_value = ret is not enough, since two vcpus could be
+         * updating at the same time, and one of them could be slightly behind,
+         * making the assumption that last_value always go forward fail to hold.
+         */
+        last = atomic64_read(&last_value);
+        do {
+                if (ret < last)
+                        return last;
+                last = atomic64_cmpxchg(&last_value, last, ret);
+        } while (unlikely(last != ret));
+
         return ret;
 }
 
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index cc2c60474fd0..c2f1b26141e2 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -46,6 +46,7 @@
 
 /* Global pointer to shared data; NULL means no measured launch. */
 struct tboot *tboot __read_mostly;
+EXPORT_SYMBOL(tboot);
 
 /* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */
 #define AP_WAIT_TIMEOUT         1