3 files changed, 40 insertions, 25 deletions

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 24ff26a38ade..5fff00c70de0 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -4,6 +4,7 @@
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/smp.h>
+#include <linux/sched.h>
 #include <linux/thread_info.h>
 #include <linux/module.h>
 
@@ -56,11 +57,16 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 
         /*
          * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate
-         * with P/T states and does not stop in deep C-states
+         * with P/T states and does not stop in deep C-states.
+         *
+         * It is also reliable across cores and sockets. (but not across
+         * cabinets - we turn it off in that case explicitly.)
          */
         if (c->x86_power & (1 << 8)) {
                 set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
                 set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+                set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
+                sched_clock_stable = 1;
         }
 
 }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 426666dd8203..7702cb166e08 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1672,6 +1672,16 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
         return set_cpus_allowed_ptr(p, &new_mask);
 }
 
+/*
+ * Architectures can set this to 1 if they have specified
+ * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
+ * but then during bootup it turns out that sched_clock()
+ * is reliable after all:
+ */
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+extern int sched_clock_stable;
+#endif
+
 extern unsigned long long sched_clock(void);
 
 extern void sched_clock_init(void);
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index db69174b1178..7ec82c1c61c5 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -24,12 +24,12 @@
  * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat
  * consistent between cpus (never more than 2 jiffies difference).
  */
-#include <linux/sched.h>
-#include <linux/percpu.h>
 #include <linux/spinlock.h>
-#include <linux/ktime.h>
-#include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/ktime.h>
+#include <linux/sched.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -44,6 +44,10 @@ unsigned long long __attribute__((weak)) sched_clock(void)
 static __read_mostly int sched_clock_running;
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+__read_mostly int sched_clock_stable;
+#else
+static const int sched_clock_stable = 1;
+#endif
 
 struct sched_clock_data {
         /*
@@ -88,7 +92,7 @@ void sched_clock_init(void)
 }
 
 /*
- * min,max except they take wrapping into account
+ * min, max except they take wrapping into account
  */
 
 static inline u64 wrap_min(u64 x, u64 y)
@@ -117,10 +121,13 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
         if (unlikely(delta < 0))
                 delta = 0;
 
+        if (unlikely(!sched_clock_running))
+                return 0ull;
+
         /*
          * scd->clock = clamp(scd->tick_gtod + delta,
-         *                    max(scd->tick_gtod, scd->clock),
-         *                    scd->tick_gtod + TICK_NSEC);
+         *                    max(scd->tick_gtod, scd->clock),
+         *                    scd->tick_gtod + TICK_NSEC);
          */
 
         clock = scd->tick_gtod + delta;
@@ -149,8 +156,13 @@ static void lock_double_clock(struct sched_clock_data *data1,
 
 u64 sched_clock_cpu(int cpu)
 {
-        struct sched_clock_data *scd = cpu_sdc(cpu);
         u64 now, clock, this_clock, remote_clock;
+        struct sched_clock_data *scd;
+
+        if (sched_clock_stable)
+                return sched_clock();
+
+        scd = cpu_sdc(cpu);
 
         /*
          * Normally this is not called in NMI context - but if it is,
@@ -201,6 +213,8 @@ u64 sched_clock_cpu(int cpu)
         return clock;
 }
 
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+
 void sched_clock_tick(void)
 {
         struct sched_clock_data *scd = this_scd();
@@ -243,22 +257,7 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
-#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
-
-void sched_clock_init(void)
-{
-        sched_clock_running = 1;
-}
-
-u64 sched_clock_cpu(int cpu)
-{
-        if (unlikely(!sched_clock_running))
-                return 0;
-
-        return sched_clock();
-}
-
-#endif
+#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 unsigned long long cpu_clock(int cpu)
 {