#include <linux/jiffies.h>
#include <linux/init.h>
#include <linux/dmi.h>
+#include <linux/percpu.h>
#include <asm/delay.h>
#include <asm/tsc.h>
}
EXPORT_SYMBOL_GPL(check_tsc_unstable);
-/* Accellerators for sched_clock()
+/* Accelerators for sched_clock()
* convert from cycles(64bits) => nanoseconds (64bits)
* basic equation:
* ns = cycles / (freq / ns_per_sec)
* 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 percision, since
+ * 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!"
*/
-unsigned long cyc2ns_scale __read_mostly;
-#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
+DEFINE_PER_CPU(unsigned long, cyc2ns);
-static inline void set_cyc2ns_scale(unsigned long cpu_khz)
+static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
{
- cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR)/cpu_khz;
+ unsigned long flags, prev_scale, *scale;
+ unsigned long long tsc_now, ns_now;
+
+ local_irq_save(flags);
+ sched_clock_idle_sleep_event();
+
+ scale = &per_cpu(cyc2ns, cpu);
+
+ rdtscll(tsc_now);
+ ns_now = __cycles_2_ns(tsc_now);
+
+ prev_scale = *scale;
+ if (cpu_khz)
+ *scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/cpu_khz;
+
+ /*
+ * Start smoothly with the new frequency:
+ */
+ sched_clock_idle_wakeup_event(0);
+ local_irq_restore(flags);
}
/*
{
unsigned long long start, end;
unsigned long count;
- u64 delta64;
+ u64 delta64 = (u64)ULLONG_MAX;
int i;
unsigned long flags;
local_irq_save(flags);
- /* run 3 times to ensure the cache is warm */
+ /* run 3 times to ensure the cache is warm and to get an accurate reading */
for (i = 0; i < 3; i++) {
mach_prepare_counter();
rdtscll(start);
mach_countup(&count);
rdtscll(end);
- }
- /*
- * Error: ECTCNEVERSET
- * The CTC wasn't reliable: we got a hit on the very first read,
- * or the CPU was so fast/slow that the quotient wouldn't fit in
- * 32 bits..
- */
- if (count <= 1)
- goto err;
- delta64 = end - start;
+ /*
+ * Error: ECTCNEVERSET
+ * The CTC wasn't reliable: we got a hit on the very first read,
+ * or the CPU was so fast/slow that the quotient wouldn't fit in
+ * 32 bits..
+ */
+ if (count <= 1)
+ continue;
+
+ /* cpu freq too slow: */
+ if ((end - start) <= CALIBRATE_TIME_MSEC)
+ continue;
+
+ /*
+ * We want the minimum time of all runs in case one of them
+ * is inaccurate due to SMI or other delay
+ */
+ delta64 = min(delta64, (end - start));
+ }
- /* cpu freq too fast: */
+ /* cpu freq too fast (or every run was bad): */
if (delta64 > (1ULL<<32))
goto err;
- /* cpu freq too slow: */
- if (delta64 <= CALIBRATE_TIME_MSEC)
- goto err;
-
delta64 += CALIBRATE_TIME_MSEC/2; /* round for do_div */
do_div(delta64,CALIBRATE_TIME_MSEC);
if (cpu_has_tsc) {
cpu_khz = calculate_cpu_khz();
tsc_khz = cpu_khz;
- cpu_data[0].loops_per_jiffy =
- cpufreq_scale(cpu_data[0].loops_per_jiffy,
+ cpu_data(0).loops_per_jiffy =
+ cpufreq_scale(cpu_data(0).loops_per_jiffy,
cpu_khz_old, cpu_khz);
return 0;
} else
return 0;
}
ref_freq = freq->old;
- loops_per_jiffy_ref = cpu_data[freq->cpu].loops_per_jiffy;
+ loops_per_jiffy_ref = cpu_data(freq->cpu).loops_per_jiffy;
cpu_khz_ref = cpu_khz;
}
(val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
(val == CPUFREQ_RESUMECHANGE)) {
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
- cpu_data[freq->cpu].loops_per_jiffy =
+ cpu_data(freq->cpu).loops_per_jiffy =
cpufreq_scale(loops_per_jiffy_ref,
ref_freq, freq->new);
ref_freq, freq->new);
if (!(freq->flags & CPUFREQ_CONST_LOOPS)) {
tsc_khz = cpu_khz;
- set_cyc2ns_scale(cpu_khz);
+ preempt_disable();
+ set_cyc2ns_scale(cpu_khz, smp_processor_id());
+ preempt_enable();
/*
* TSC based sched_clock turns
* to junk w/ cpufreq
void __init tsc_init(void)
{
+ int cpu;
+
if (!cpu_has_tsc || tsc_disable)
goto out_no_tsc;
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);
- set_cyc2ns_scale(cpu_khz);
+ /*
+ * Secondary CPUs do not run through tsc_init(), so set up
+ * all the scale factors for all CPUs, assuming the same
+ * speed as the bootup CPU. (cpufreq notifiers will fix this
+ * up if their speed diverges)
+ */
+ for_each_possible_cpu(cpu)
+ set_cyc2ns_scale(cpu_khz, cpu);
+
use_tsc_delay();
/* Check and install the TSC clocksource */