From e52d3fb7c83d6cb569f343a3db9b45decc801f59 Mon Sep 17 00:00:00 2001 From: Salman Qazi Date: Tue, 15 Nov 2011 14:12:06 -0800 Subject: sched, x86: Avoid unnecessary overflow in sched_clock 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 Acked-by: John Stultz Reviewed-by: Paul Turner Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20111115221121.7262.88871.stgit@dungbeetle.mtv.corp.google.com Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/timer.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 5469630b27f5..b93a9aaf8bae 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -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; } -- cgit v1.2.3