When TSC is stable perf/sched clock is based on it.
However the conversion from cycles to nanoseconds
is not as accurate as it could be. Because
CYC2NS_SCALE_FACTOR is 10, the accuracy is +/- 1/2048
While I am not aware of any compelling reason to make
perf/sched clock accurate, I am not so sure there is
much reason for it to be inaccurate. Hence this RFC.
The change is to calculate the maximum shift that
results in a multiplier that is still a 32-bit number.
For example all frequencies over 1 GHz will have
a shift of 32, making the accuracy of the conversion
+/- 1/(2^33)
Signed-off-by: Adrian Hunter <adrian.hun...@intel.com>
---
arch/x86/kernel/tsc.c | 26 ++++++++++++++------------
1 file changed, 14 insertions(+), 12 deletions(-)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 505449700e0c..8e6e6b584db8 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -215,14 +215,14 @@ static inline unsigned long long cycles_2_ns(unsigned
long long cyc)
if (likely(data == tail)) {
ns = data->cyc2ns_offset;
- ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul,
CYC2NS_SCALE_FACTOR);
+ ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul,
data->cyc2ns_shift);
} else {
data->__count++;
barrier();
ns = data->cyc2ns_offset;
- ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul,
CYC2NS_SCALE_FACTOR);
+ ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul,
data->cyc2ns_shift);
barrier();
@@ -239,6 +239,8 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
unsigned long long tsc_now, ns_now;
struct cyc2ns_data *data;
unsigned long flags;
+ u64 mult;
+ u32 shft = 32;
local_irq_save(flags);
sched_clock_idle_sleep_event();
@@ -251,17 +253,17 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int
cpu)
rdtscll(tsc_now);
ns_now = cycles_2_ns(tsc_now);
- /*
- * Compute a new multiplier as per the above comment and ensure our
- * time function is continuous; see the comment near struct
- * cyc2ns_data.
- */
- data->cyc2ns_mul =
- DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR,
- cpu_khz);
- data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+ mult = (u64)NSEC_PER_MSEC << 32;
+ mult += cpu_khz / 2;
+ do_div(mult, cpu_khz);
+ while (mult > U32_MAX) {
+ mult >>= 1;
+ shft -= 1;
+ }
+ data->cyc2ns_mul = mult;
+ data->cyc2ns_shift = shft;
data->cyc2ns_offset = ns_now -
- mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+ mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift);
cyc2ns_write_end(cpu, data);
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
