]> git.kernelconcepts.de Git - karo-tx-linux.git/commitdiff
sched, x86: Avoid unnecessary overflow in sched_clock
authorSalman Qazi <sqazi@google.com>
Tue, 15 Nov 2011 22:12:06 +0000 (14:12 -0800)
committerGreg Kroah-Hartman <gregkh@suse.de>
Fri, 9 Dec 2011 17:21:48 +0000 (09:21 -0800)
commit 4cecf6d401a01d054afc1e5f605bcbfe553cb9b9 upstream.

(Added the missing signed-off-by line)

In hundreds of days, the __cycles_2_ns calculation in sched_clock
has an overflow.  cyc * per_cpu(cyc2ns, cpu) exceeds 64 bits, causing
the final value to become zero.  We can solve this without losing
any precision.

We can decompose TSC into quotient and remainder of division by the
scale factor, and then use this to convert TSC into nanoseconds.

Signed-off-by: Salman Qazi <sqazi@google.com>
Acked-by: John Stultz <johnstul@us.ibm.com>
Reviewed-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111115221121.7262.88871.stgit@dungbeetle.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
arch/x86/include/asm/timer.h

index 5469630b27f56d732b10036ba381df39f28ca52b..b93a9aaf8baeff43ff7ae508514da0f00b9e5cdb 100644 (file)
@@ -38,6 +38,22 @@ extern int no_timer_check;
  *  (mathieu.desnoyers@polymtl.ca)
  *
  *                     -johnstul@us.ibm.com "math is hard, lets go shopping!"
+ *
+ * In:
+ *
+ * ns = cycles * cyc2ns_scale / SC
+ *
+ * Although we may still have enough bits to store the value of ns,
+ * in some cases, we may not have enough bits to store cycles * cyc2ns_scale,
+ * leading to an incorrect result.
+ *
+ * To avoid this, we can decompose 'cycles' into quotient and remainder
+ * of division by SC.  Then,
+ *
+ * ns = (quot * SC + rem) * cyc2ns_scale / SC
+ *    = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC
+ *
+ *                     - sqazi@google.com
  */
 
 DECLARE_PER_CPU(unsigned long, cyc2ns);
@@ -47,9 +63,14 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 
 static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
 {
+       unsigned long long quot;
+       unsigned long long rem;
        int cpu = smp_processor_id();
        unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
-       ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR;
+       quot = (cyc >> CYC2NS_SCALE_FACTOR);
+       rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1);
+       ns += quot * per_cpu(cyc2ns, cpu) +
+               ((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR);
        return ns;
 }