diff options
author | Peter Zijlstra <peterz@infradead.org> | 2013-11-29 14:39:25 (GMT) |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2014-01-13 12:47:39 (GMT) |
commit | 57c67da274f3fab38e08d2c9edf08b89e1d9c71d (patch) | |
tree | a473b9e84bfa0bf1fd1ccb407231c59a7815284a /arch/x86/kernel/tsc.c | |
parent | 5dd12c2152743747ca9f50ef80281e54cc416dc0 (diff) | |
download | linux-57c67da274f3fab38e08d2c9edf08b89e1d9c71d.tar.xz |
sched/clock, x86: Move some cyc2ns() code around
There are no __cycles_2_ns() users outside of arch/x86/kernel/tsc.c,
so move it there.
There are no cycles_2_ns() users.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-01lslnavfgo3kmbo4532zlcj@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch/x86/kernel/tsc.c')
-rw-r--r-- | arch/x86/kernel/tsc.c | 112 |
1 files changed, 61 insertions, 51 deletions
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 930e5d4..b4a04ac 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -38,6 +38,66 @@ static int __read_mostly tsc_unstable; static int __read_mostly tsc_disabled = -1; int tsc_clocksource_reliable; + +/* Accelerators for sched_clock() + * convert from cycles(64bits) => nanoseconds (64bits) + * basic equation: + * ns = cycles / (freq / ns_per_sec) + * ns = cycles * (ns_per_sec / freq) + * ns = cycles * (10^9 / (cpu_khz * 10^3)) + * ns = cycles * (10^6 / cpu_khz) + * + * Then we use scaling math (suggested by george@mvista.com) to get: + * ns = cycles * (10^6 * SC / cpu_khz) / SC + * ns = cycles * cyc2ns_scale / SC + * + * And since SC is a constant power of two, we can convert the div + * into a shift. + * + * We can use khz divisor instead of mhz to keep a better precision, since + * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. + * (mathieu.desnoyers@polymtl.ca) + * + * -johnstul@us.ibm.com "math is hard, lets go shopping!" + */ + +DEFINE_PER_CPU(unsigned long, cyc2ns); +DEFINE_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) +{ + unsigned long long ns = this_cpu_read(cyc2ns_offset); + ns += mul_u64_u32_shr(cyc, this_cpu_read(cyc2ns), CYC2NS_SCALE_FACTOR); + return ns; +} + +static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) +{ + 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) { + *scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) + + cpu_khz / 2) / cpu_khz; + *offset = ns_now - mult_frac(tsc_now, *scale, + (1UL << CYC2NS_SCALE_FACTOR)); + } + + sched_clock_idle_wakeup_event(0); + local_irq_restore(flags); +} + /* * Scheduler clock - returns current time in nanosec units. */ @@ -62,7 +122,7 @@ u64 native_sched_clock(void) rdtscll(this_offset); /* return the value in ns */ - return __cycles_2_ns(this_offset); + return cycles_2_ns(this_offset); } /* We need to define a real function for sched_clock, to override the @@ -589,56 +649,6 @@ int recalibrate_cpu_khz(void) EXPORT_SYMBOL(recalibrate_cpu_khz); -/* Accelerators for sched_clock() - * convert from cycles(64bits) => nanoseconds (64bits) - * basic equation: - * ns = cycles / (freq / ns_per_sec) - * ns = cycles * (ns_per_sec / freq) - * ns = cycles * (10^9 / (cpu_khz * 10^3)) - * ns = cycles * (10^6 / cpu_khz) - * - * Then we use scaling math (suggested by george@mvista.com) to get: - * ns = cycles * (10^6 * SC / cpu_khz) / SC - * ns = cycles * cyc2ns_scale / SC - * - * And since SC is a constant power of two, we can convert the div - * into a shift. - * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. - * (mathieu.desnoyers@polymtl.ca) - * - * -johnstul@us.ibm.com "math is hard, lets go shopping!" - */ - -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, *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) { - *scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) + - cpu_khz / 2) / cpu_khz; - *offset = ns_now - mult_frac(tsc_now, *scale, - (1UL << CYC2NS_SCALE_FACTOR)); - } - - sched_clock_idle_wakeup_event(0); - local_irq_restore(flags); -} - static unsigned long long cyc2ns_suspend; void tsc_save_sched_clock_state(void) |