#include <linux/timer.h>
#include <linux/acpi_pmtmr.h>
#include <linux/cpufreq.h>
-#include <linux/dmi.h>
#include <linux/delay.h>
#include <linux/clocksource.h>
#include <linux/percpu.h>
+#include <linux/timex.h>
#include <asm/hpet.h>
#include <asm/timer.h>
#include <asm/time.h>
#include <asm/delay.h>
#include <asm/hypervisor.h>
+#include <asm/nmi.h>
+#include <asm/x86_init.h>
unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
erroneous rdtsc usage on !cpu_has_tsc processors */
static int __read_mostly tsc_disabled = -1;
-static int tsc_clocksource_reliable;
+int tsc_clocksource_reliable;
/*
* Scheduler clock - returns current time in nanosec units.
*/
* unstable. We do this because unlike Time Of Day,
* the scheduler clock tolerates small errors and it's
* very important for it to be as fast as the platform
- * can achive it. )
+ * can achieve it. )
*/
if (unlikely(tsc_disabled)) {
/* No locking but a rare wrong value is not a big deal: */
__setup("notsc", notsc_setup);
+static int no_sched_irq_time;
+
static int __init tsc_setup(char *str)
{
if (!strcmp(str, "reliable"))
tsc_clocksource_reliable = 1;
+ if (!strncmp(str, "noirqtime", 9))
+ no_sched_irq_time = 1;
return 1;
}
}
#define CAL_MS 10
-#define CAL_LATCH (CLOCK_TICK_RATE / (1000 / CAL_MS))
+#define CAL_LATCH (PIT_TICK_RATE / (1000 / CAL_MS))
#define CAL_PIT_LOOPS 1000
#define CAL2_MS 50
-#define CAL2_LATCH (CLOCK_TICK_RATE / (1000 / CAL2_MS))
+#define CAL2_LATCH (PIT_TICK_RATE / (1000 / CAL2_MS))
#define CAL2_PIT_LOOPS 5000
* use the TSC value at the transitions to calculate a pretty
* good value for the TSC frequencty.
*/
-static inline int pit_expect_msb(unsigned char val)
+static inline int pit_verify_msb(unsigned char val)
+{
+ /* Ignore LSB */
+ inb(0x42);
+ return inb(0x42) == val;
+}
+
+static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap)
{
- int count = 0;
+ int count;
+ u64 tsc = 0, prev_tsc = 0;
for (count = 0; count < 50000; count++) {
- /* Ignore LSB */
- inb(0x42);
- if (inb(0x42) != val)
+ if (!pit_verify_msb(val))
break;
+ prev_tsc = tsc;
+ tsc = get_cycles();
}
- return count > 50;
+ *deltap = get_cycles() - prev_tsc;
+ *tscp = tsc;
+
+ /*
+ * We require _some_ success, but the quality control
+ * will be based on the error terms on the TSC values.
+ */
+ return count > 5;
}
/*
- * How many MSB values do we want to see? We aim for a
- * 15ms calibration, which assuming a 2us counter read
- * error should give us roughly 150 ppm precision for
- * the calibration.
+ * How many MSB values do we want to see? We aim for
+ * a maximum error rate of 500ppm (in practice the
+ * real error is much smaller), but refuse to spend
+ * more than 50ms on it.
*/
-#define QUICK_PIT_MS 15
-#define QUICK_PIT_ITERATIONS (QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
+#define MAX_QUICK_PIT_MS 50
+#define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
static unsigned long quick_pit_calibrate(void)
{
+ int i;
+ u64 tsc, delta;
+ unsigned long d1, d2;
+
/* Set the Gate high, disable speaker */
outb((inb(0x61) & ~0x02) | 0x01, 0x61);
outb(0xff, 0x42);
outb(0xff, 0x42);
- if (pit_expect_msb(0xff)) {
- int i;
- u64 t1, t2, delta;
- unsigned char expect = 0xfe;
-
- t1 = get_cycles();
- for (i = 0; i < QUICK_PIT_ITERATIONS; i++, expect--) {
- if (!pit_expect_msb(expect))
- goto failed;
+ /*
+ * The PIT starts counting at the next edge, so we
+ * need to delay for a microsecond. The easiest way
+ * to do that is to just read back the 16-bit counter
+ * once from the PIT.
+ */
+ pit_verify_msb(0);
+
+ if (pit_expect_msb(0xff, &tsc, &d1)) {
+ for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) {
+ if (!pit_expect_msb(0xff-i, &delta, &d2))
+ break;
+
+ /*
+ * Iterate until the error is less than 500 ppm
+ */
+ delta -= tsc;
+ if (d1+d2 >= delta >> 11)
+ continue;
+
+ /*
+ * Check the PIT one more time to verify that
+ * all TSC reads were stable wrt the PIT.
+ *
+ * This also guarantees serialization of the
+ * last cycle read ('d2') in pit_expect_msb.
+ */
+ if (!pit_verify_msb(0xfe - i))
+ break;
+ goto success;
}
- t2 = get_cycles();
-
- /*
- * Make sure we can rely on the second TSC timestamp:
- */
- if (!pit_expect_msb(expect))
- goto failed;
-
- /*
- * Ok, if we get here, then we've seen the
- * MSB of the PIT decrement QUICK_PIT_ITERATIONS
- * times, and each MSB had many hits, so we never
- * had any sudden jumps.
- *
- * As a result, we can depend on there not being
- * any odd delays anywhere, and the TSC reads are
- * reliable.
- *
- * kHz = ticks / time-in-seconds / 1000;
- * kHz = (t2 - t1) / (QPI * 256 / PIT_TICK_RATE) / 1000
- * kHz = ((t2 - t1) * PIT_TICK_RATE) / (QPI * 256 * 1000)
- */
- delta = (t2 - t1)*PIT_TICK_RATE;
- do_div(delta, QUICK_PIT_ITERATIONS*256*1000);
- printk("Fast TSC calibration using PIT\n");
- return delta;
}
-failed:
+ printk("Fast TSC calibration failed\n");
return 0;
+
+success:
+ /*
+ * Ok, if we get here, then we've seen the
+ * MSB of the PIT decrement 'i' times, and the
+ * error has shrunk to less than 500 ppm.
+ *
+ * As a result, we can depend on there not being
+ * any odd delays anywhere, and the TSC reads are
+ * reliable (within the error).
+ *
+ * kHz = ticks / time-in-seconds / 1000;
+ * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000
+ * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000)
+ */
+ delta *= PIT_TICK_RATE;
+ do_div(delta, i*256*1000);
+ printk("Fast TSC calibration using PIT\n");
+ return delta;
}
/**
{
u64 tsc1, tsc2, delta, ref1, ref2;
unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
- unsigned long flags, latch, ms, fast_calibrate, tsc_khz;
+ unsigned long flags, latch, ms, fast_calibrate;
int hpet = is_hpet_enabled(), i, loopmin;
- tsc_khz = get_hypervisor_tsc_freq();
- if (tsc_khz) {
- printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
- return tsc_khz;
- }
-
local_irq_save(flags);
fast_calibrate = quick_pit_calibrate();
local_irq_restore(flags);
* the delta to the previous read. We keep track of the min
* and max values of that delta. The delta is mostly defined
* by the IO time of the PIT access, so we can detect when a
- * SMI/SMM disturbance happend between the two reads. If the
+ * SMI/SMM disturbance happened between the two reads. If the
* maximum time is significantly larger than the minimum time,
* then we discard the result and have another try.
*
tsc_pit_min = min(tsc_pit_min, tsc_pit_khz);
/* hpet or pmtimer available ? */
- if (!hpet && !ref1 && !ref2)
+ if (ref1 == ref2)
continue;
/* Check, whether the sampling was disturbed by an SMI */
return tsc_pit_min;
}
-#ifdef CONFIG_X86_32
-/* Only called from the Powernow K7 cpu freq driver */
int recalibrate_cpu_khz(void)
{
#ifndef CONFIG_SMP
unsigned long cpu_khz_old = cpu_khz;
if (cpu_has_tsc) {
- tsc_khz = calibrate_tsc();
+ tsc_khz = x86_platform.calibrate_tsc();
cpu_khz = tsc_khz;
cpu_data(0).loops_per_jiffy =
cpufreq_scale(cpu_data(0).loops_per_jiffy,
EXPORT_SYMBOL(recalibrate_cpu_khz);
-#endif /* CONFIG_X86_32 */
/* Accelerators for sched_clock()
* convert from cycles(64bits) => nanoseconds (64bits)
*/
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;
+ 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)
+ if (cpu_khz) {
*scale = (NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR)/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)
+{
+ if (!sched_clock_stable)
+ return;
+
+ cyc2ns_suspend = sched_clock();
+}
+
+/*
+ * Even on processors with invariant TSC, TSC gets reset in some the
+ * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to
+ * arbitrary value (still sync'd across cpu's) during resume from such sleep
+ * states. To cope up with this, recompute the cyc2ns_offset for each cpu so
+ * that sched_clock() continues from the point where it was left off during
+ * suspend.
+ */
+void tsc_restore_sched_clock_state(void)
+{
+ unsigned long long offset;
+ unsigned long flags;
+ int cpu;
+
+ if (!sched_clock_stable)
+ return;
+
+ local_irq_save(flags);
+
+ __this_cpu_write(cyc2ns_offset, 0);
+ offset = cyc2ns_suspend - sched_clock();
+
+ for_each_possible_cpu(cpu)
+ per_cpu(cyc2ns_offset, cpu) = offset;
+
+ local_irq_restore(flags);
+}
+
#ifdef CONFIG_CPU_FREQ
/* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
void *data)
{
struct cpufreq_freqs *freq = data;
- unsigned long *lpj, dummy;
+ unsigned long *lpj;
if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC))
return 0;
- lpj = &dummy;
- if (!(freq->flags & CPUFREQ_CONST_LOOPS))
+ lpj = &boot_cpu_data.loops_per_jiffy;
#ifdef CONFIG_SMP
+ if (!(freq->flags & CPUFREQ_CONST_LOOPS))
lpj = &cpu_data(freq->cpu).loops_per_jiffy;
-#else
- lpj = &boot_cpu_data.loops_per_jiffy;
#endif
if (!ref_freq) {
if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) ||
(val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
(val == CPUFREQ_RESUMECHANGE)) {
- *lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
+ *lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
if (!(freq->flags & CPUFREQ_CONST_LOOPS))
* code, which is necessary to support wrapping clocksources like pm
* timer.
*/
-static cycle_t read_tsc(void)
+static cycle_t read_tsc(struct clocksource *cs)
{
cycle_t ret = (cycle_t)get_cycles();
ret : clocksource_tsc.cycle_last;
}
-#ifdef CONFIG_X86_64
-static cycle_t __vsyscall_fn vread_tsc(void)
+static void resume_tsc(struct clocksource *cs)
{
- cycle_t ret = (cycle_t)vget_cycles();
-
- return ret >= __vsyscall_gtod_data.clock.cycle_last ?
- ret : __vsyscall_gtod_data.clock.cycle_last;
+ clocksource_tsc.cycle_last = 0;
}
-#endif
static struct clocksource clocksource_tsc = {
.name = "tsc",
.rating = 300,
.read = read_tsc,
+ .resume = resume_tsc,
.mask = CLOCKSOURCE_MASK(64),
- .shift = 22,
.flags = CLOCK_SOURCE_IS_CONTINUOUS |
CLOCK_SOURCE_MUST_VERIFY,
#ifdef CONFIG_X86_64
- .vread = vread_tsc,
+ .archdata = { .vclock_mode = VCLOCK_TSC },
#endif
};
{
if (!tsc_unstable) {
tsc_unstable = 1;
- printk("Marking TSC unstable due to %s\n", reason);
+ sched_clock_stable = 0;
+ disable_sched_clock_irqtime();
+ printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
/* Change only the rating, when not registered */
if (clocksource_tsc.mult)
- clocksource_change_rating(&clocksource_tsc, 0);
- else
+ clocksource_mark_unstable(&clocksource_tsc);
+ else {
+ clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
clocksource_tsc.rating = 0;
+ }
}
}
EXPORT_SYMBOL_GPL(mark_tsc_unstable);
-static int __init dmi_mark_tsc_unstable(const struct dmi_system_id *d)
-{
- printk(KERN_NOTICE "%s detected: marking TSC unstable.\n",
- d->ident);
- tsc_unstable = 1;
- return 0;
-}
-
-/* List of systems that have known TSC problems */
-static struct dmi_system_id __initdata bad_tsc_dmi_table[] = {
- {
- .callback = dmi_mark_tsc_unstable,
- .ident = "IBM Thinkpad 380XD",
- .matches = {
- DMI_MATCH(DMI_BOARD_VENDOR, "IBM"),
- DMI_MATCH(DMI_BOARD_NAME, "2635FA0"),
- },
- },
- {}
-};
-
static void __init check_system_tsc_reliable(void)
{
#ifdef CONFIG_MGEODE_LX
unsigned long res_low, res_high;
rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
- /* Geode_LX - the OLPC CPU has a possibly a very reliable TSC */
+ /* Geode_LX - the OLPC CPU has a very reliable TSC */
if (res_low & RTSC_SUSP)
tsc_clocksource_reliable = 1;
#endif
if (!cpu_has_tsc || tsc_unstable)
return 1;
-#ifdef CONFIG_X86_SMP
+#ifdef CONFIG_SMP
if (apic_is_clustered_box())
return 1;
#endif
if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
return 0;
+
+ if (tsc_clocksource_reliable)
+ return 0;
/*
* Intel systems are normally all synchronized.
* Exceptions must mark TSC as unstable:
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
/* assume multi socket systems are not synchronized: */
if (num_possible_cpus() > 1)
- tsc_unstable = 1;
+ return 1;
}
- return tsc_unstable;
+ return 0;
}
-static void __init init_tsc_clocksource(void)
+
+static void tsc_refine_calibration_work(struct work_struct *work);
+static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
+/**
+ * tsc_refine_calibration_work - Further refine tsc freq calibration
+ * @work - ignored.
+ *
+ * This functions uses delayed work over a period of a
+ * second to further refine the TSC freq value. Since this is
+ * timer based, instead of loop based, we don't block the boot
+ * process while this longer calibration is done.
+ *
+ * If there are any calibration anomalies (too many SMIs, etc),
+ * or the refined calibration is off by 1% of the fast early
+ * calibration, we throw out the new calibration and use the
+ * early calibration.
+ */
+static void tsc_refine_calibration_work(struct work_struct *work)
{
- clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
- clocksource_tsc.shift);
+ static u64 tsc_start = -1, ref_start;
+ static int hpet;
+ u64 tsc_stop, ref_stop, delta;
+ unsigned long freq;
+
+ /* Don't bother refining TSC on unstable systems */
+ if (check_tsc_unstable())
+ goto out;
+
+ /*
+ * Since the work is started early in boot, we may be
+ * delayed the first time we expire. So set the workqueue
+ * again once we know timers are working.
+ */
+ if (tsc_start == -1) {
+ /*
+ * Only set hpet once, to avoid mixing hardware
+ * if the hpet becomes enabled later.
+ */
+ hpet = is_hpet_enabled();
+ schedule_delayed_work(&tsc_irqwork, HZ);
+ tsc_start = tsc_read_refs(&ref_start, hpet);
+ return;
+ }
+
+ tsc_stop = tsc_read_refs(&ref_stop, hpet);
+
+ /* hpet or pmtimer available ? */
+ if (ref_start == ref_stop)
+ goto out;
+
+ /* Check, whether the sampling was disturbed by an SMI */
+ if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
+ goto out;
+
+ delta = tsc_stop - tsc_start;
+ delta *= 1000000LL;
+ if (hpet)
+ freq = calc_hpet_ref(delta, ref_start, ref_stop);
+ else
+ freq = calc_pmtimer_ref(delta, ref_start, ref_stop);
+
+ /* Make sure we're within 1% */
+ if (abs(tsc_khz - freq) > tsc_khz/100)
+ goto out;
+
+ tsc_khz = freq;
+ printk(KERN_INFO "Refined TSC clocksource calibration: "
+ "%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000,
+ (unsigned long)tsc_khz % 1000);
+
+out:
+ clocksource_register_khz(&clocksource_tsc, tsc_khz);
+}
+
+
+static int __init init_tsc_clocksource(void)
+{
+ if (!cpu_has_tsc || tsc_disabled > 0 || !tsc_khz)
+ return 0;
+
if (tsc_clocksource_reliable)
clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
/* lower the rating if we already know its unstable: */
clocksource_tsc.rating = 0;
clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
}
- clocksource_register(&clocksource_tsc);
+
+ /*
+ * Trust the results of the earlier calibration on systems
+ * exporting a reliable TSC.
+ */
+ if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+ clocksource_register_khz(&clocksource_tsc, tsc_khz);
+ return 0;
+ }
+
+ schedule_delayed_work(&tsc_irqwork, 0);
+ return 0;
}
+/*
+ * We use device_initcall here, to ensure we run after the hpet
+ * is fully initialized, which may occur at fs_initcall time.
+ */
+device_initcall(init_tsc_clocksource);
void __init tsc_init(void)
{
u64 lpj;
int cpu;
+ x86_init.timers.tsc_pre_init();
+
if (!cpu_has_tsc)
return;
- tsc_khz = calibrate_tsc();
+ tsc_khz = x86_platform.calibrate_tsc();
cpu_khz = tsc_khz;
if (!tsc_khz) {
return;
}
-#ifdef CONFIG_X86_64
- if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
- (boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
- cpu_khz = calibrate_cpu();
-#endif
-
printk("Detected %lu.%03lu MHz processor.\n",
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);
/* now allow native_sched_clock() to use rdtsc */
tsc_disabled = 0;
+ if (!no_sched_irq_time)
+ enable_sched_clock_irqtime();
+
lpj = ((u64)tsc_khz * 1000);
do_div(lpj, HZ);
lpj_fine = lpj;
use_tsc_delay();
- /* Check and install the TSC clocksource */
- dmi_check_system(bad_tsc_dmi_table);
if (unsynchronized_tsc())
mark_tsc_unstable("TSCs unsynchronized");
check_system_tsc_reliable();
- init_tsc_clocksource();
}
+#ifdef CONFIG_SMP
+/*
+ * If we have a constant TSC and are using the TSC for the delay loop,
+ * we can skip clock calibration if another cpu in the same socket has already
+ * been calibrated. This assumes that CONSTANT_TSC applies to all
+ * cpus in the socket - this should be a safe assumption.
+ */
+unsigned long __cpuinit calibrate_delay_is_known(void)
+{
+ int i, cpu = smp_processor_id();
+
+ if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC))
+ return 0;
+
+ for_each_online_cpu(i)
+ if (cpu_data(i).phys_proc_id == cpu_data(cpu).phys_proc_id)
+ return cpu_data(i).loops_per_jiffy;
+ return 0;
+}
+#endif