sched, x86: Fix cpufreq + sched_clock() TSC scaling

For freqency dependent TSCs we only scale the cycles, we do not account
for the discrepancy in absolute value.

Our current formula is: time = cycles * mult

(where mult is a function of the cpu-speed on variable tsc machines)

Suppose our current cycle count is 10, and we have a multiplier of 5,
then our time value would end up being 50.

Now cpufreq comes along and changes the multiplier to say 3 or 7,
which would result in our time being resp. 30 or 70.

That means that we can observe random jumps in the time value due to
frequency changes in both fwd and bwd direction.

So what this patch does is change the formula to:

  time = cycles * frequency + offset

And we calculate offset so that time_before == time_after, thereby
ridding us of these jumps in time.

[ Impact: fix/reduce sched_clock() jumps across frequency changing events ]

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Chucked-on-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 11 insertions, 3 deletions

diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index bd37ed444a21..20ca9c4d4686 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -45,12 +45,16 @@ extern int no_timer_check;
  */
 
 DECLARE_PER_CPU(unsigned long, cyc2ns);
+DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 
 #define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
 
 static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
 {
-        return cyc * per_cpu(cyc2ns, smp_processor_id()) >> CYC2NS_SCALE_FACTOR;
+        int cpu = smp_processor_id();
+        unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
+        ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR;
+        return ns;
 }
 
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 3e1c057e98fe..ef4dac50143f 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -589,22 +589,26 @@ EXPORT_SYMBOL(recalibrate_cpu_khz);
  */
 
 DEFINE_PER_CPU(unsigned long, cyc2ns);
+DEFINE_PER_CPU(unsigned long long, cyc2ns_offset);
 
 static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 {
-        unsigned long long tsc_now, ns_now;
+        unsigned long long tsc_now, ns_now, *offset;
         unsigned long flags, *scale;
 
         local_irq_save(flags);
         sched_clock_idle_sleep_event();
 
         scale = &per_cpu(cyc2ns, cpu);
+        offset = &per_cpu(cyc2ns_offset, cpu);
 
         rdtscll(tsc_now);
         ns_now = __cycles_2_ns(tsc_now);
 
-        if (cpu_khz)
+        if (cpu_khz) {
                 *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz;
+                *offset = ns_now - (tsc_now * *scale >> CYC2NS_SCALE_FACTOR);
+        }
 
         sched_clock_idle_wakeup_event(0);
         local_irq_restore(flags);