summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorSalman Qazi <sqazi@google.com>2011-11-15 14:12:06 -0800
committerIngo Molnar <mingo@elte.hu>2011-11-16 19:51:25 +0100
commit4cecf6d401a01d054afc1e5f605bcbfe553cb9b9 (patch)
tree58978cec1b0757fde61e53c974dff062010713df /arch
parentfccfdc6f0d8c83c854eeb6d93aa158f0e551bd49 (diff)
downloadblackbird-op-linux-4cecf6d401a01d054afc1e5f605bcbfe553cb9b9.tar.gz
blackbird-op-linux-4cecf6d401a01d054afc1e5f605bcbfe553cb9b9.zip
sched, x86: Avoid unnecessary overflow in sched_clock
(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> Cc: stable@kernel.org 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>
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/include/asm/timer.h23
1 files changed, 22 insertions, 1 deletions
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index fa7b9176b76c..431793e5d484 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -32,6 +32,22 @@ 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);
@@ -41,9 +57,14 @@ 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;
}
OpenPOWER on IntegriCloud