x86: kvmclock: abstract save/restore sched_clock_state

Upon resume from hibernation, CPU 0's hvclock area contains the old
values for system_time and tsc_timestamp. It is necessary for the
hypervisor to update these values with uptodate ones before the CPU uses
them.

Abstract TSC's save/restore sched_clock_state functions and use
restore_state to write to KVM_SYSTEM_TIME MSR, forcing an update.

Also move restore_sched_clock_state before __restore_processor_state,
since the later calls CONFIG_LOCK_STAT's lockstat_clock (also for TSC).
Thanks to Igor Mammedov for tracking it down.

Fixes suspend-to-disk with kvmclock.

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

3 files changed, 16 insertions, 3 deletions

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index ca4e735adc54..f8492da65bfc 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -136,6 +136,15 @@ int kvm_register_clock(char *txt)
         return ret;
 }
 
+static void kvm_save_sched_clock_state(void)
+{
+}
+
+static void kvm_restore_sched_clock_state(void)
+{
+        kvm_register_clock("primary cpu clock, resume");
+}
+
 #ifdef CONFIG_X86_LOCAL_APIC
 static void __cpuinit kvm_setup_secondary_clock(void)
 {
@@ -195,6 +204,8 @@ void __init kvmclock_init(void)
         x86_cpuinit.early_percpu_clock_init =
                 kvm_setup_secondary_clock;
 #endif
+        x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
+        x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
         machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC
         machine_ops.crash_shutdown  = kvm_crash_shutdown;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index a62c201c97ec..aed2aa1088f1 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -629,7 +629,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 
 static unsigned long long cyc2ns_suspend;
 
-void save_sched_clock_state(void)
+void tsc_save_sched_clock_state(void)
 {
         if (!sched_clock_stable)
                 return;
@@ -645,7 +645,7 @@ void save_sched_clock_state(void)
  * that sched_clock() continues from the point where it was left off during
  * suspend.
  */
-void restore_sched_clock_state(void)
+void tsc_restore_sched_clock_state(void)
 {
         unsigned long long offset;
         unsigned long flags;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 6f2ec53deed0..e9f265fd79ae 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -108,7 +108,9 @@ struct x86_platform_ops x86_platform = {
         .is_untracked_pat_range         = is_ISA_range,
         .nmi_init                       = default_nmi_init,
         .get_nmi_reason                 = default_get_nmi_reason,
-        .i8042_detect                   = default_i8042_detect
+        .i8042_detect                   = default_i8042_detect,
+        .save_sched_clock_state         = tsc_save_sched_clock_state,
+        .restore_sched_clock_state      = tsc_restore_sched_clock_state,
 };
 
 EXPORT_SYMBOL_GPL(x86_platform);