time.c

linux 内核源代码

 * Called when a cpu comes up after the system has finished booting,
 * i.e. as a result of a hotplug cpu action.
 */
void snapshot_timebase(void)
{
	__get_cpu_var(last_jiffy) = get_tb_or_rtc();
	snapshot_purr();
}

void __delay(unsigned long loops)
{
	unsigned long start;
	int diff;

	if (__USE_RTC()) {
		start = get_rtcl();
		do {
			/* the RTCL register wraps at 1000000000 */
			diff = get_rtcl() - start;
			if (diff < 0)
				diff += 1000000000;
		} while (diff < loops);
	} else {
		start = get_tbl();
		while (get_tbl() - start < loops)
			HMT_low();
		HMT_medium();
	}
}
EXPORT_SYMBOL(__delay);

void udelay(unsigned long usecs)
{
	__delay(tb_ticks_per_usec * usecs);
}
EXPORT_SYMBOL(udelay);


/*
 * There are two copies of tb_to_xs and stamp_xsec so that no
 * lock is needed to access and use these values in
 * do_gettimeofday.  We alternate the copies and as long as a
 * reasonable time elapses between changes, there will never
 * be inconsistent values.  ntpd has a minimum of one minute
 * between updates.
 */
static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
			       u64 new_tb_to_xs)
{
	unsigned temp_idx;
	struct gettimeofday_vars *temp_varp;

	temp_idx = (do_gtod.var_idx == 0);
	temp_varp = &do_gtod.vars[temp_idx];

	temp_varp->tb_to_xs = new_tb_to_xs;
	temp_varp->tb_orig_stamp = new_tb_stamp;
	temp_varp->stamp_xsec = new_stamp_xsec;
	smp_mb();
	do_gtod.varp = temp_varp;
	do_gtod.var_idx = temp_idx;

	/*
	 * tb_update_count is used to allow the userspace gettimeofday code
	 * to assure itself that it sees a consistent view of the tb_to_xs and
	 * stamp_xsec variables.  It reads the tb_update_count, then reads
	 * tb_to_xs and stamp_xsec and then reads tb_update_count again.  If
	 * the two values of tb_update_count match and are even then the
	 * tb_to_xs and stamp_xsec values are consistent.  If not, then it
	 * loops back and reads them again until this criteria is met.
	 * We expect the caller to have done the first increment of
	 * vdso_data->tb_update_count already.
	 */
	vdso_data->tb_orig_stamp = new_tb_stamp;
	vdso_data->stamp_xsec = new_stamp_xsec;
	vdso_data->tb_to_xs = new_tb_to_xs;
	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
	smp_wmb();
	++(vdso_data->tb_update_count);
}

#ifdef CONFIG_SMP
unsigned long profile_pc(struct pt_regs *regs)
{
	unsigned long pc = instruction_pointer(regs);

	if (in_lock_functions(pc))
		return regs->link;

	return pc;
}
EXPORT_SYMBOL(profile_pc);
#endif

#ifdef CONFIG_PPC_ISERIES

/* 
 * This function recalibrates the timebase based on the 49-bit time-of-day
 * value in the Titan chip.  The Titan is much more accurate than the value
 * returned by the service processor for the timebase frequency.  
 */

static int __init iSeries_tb_recal(void)
{
	struct div_result divres;
	unsigned long titan, tb;

	/* Make sure we only run on iSeries */
	if (!firmware_has_feature(FW_FEATURE_ISERIES))
		return -ENODEV;

	tb = get_tb();
	titan = HvCallXm_loadTod();
	if ( iSeries_recal_titan ) {
		unsigned long tb_ticks = tb - iSeries_recal_tb;
		unsigned long titan_usec = (titan - iSeries_recal_titan) >> 12;
		unsigned long new_tb_ticks_per_sec   = (tb_ticks * USEC_PER_SEC)/titan_usec;
		unsigned long new_tb_ticks_per_jiffy = (new_tb_ticks_per_sec+(HZ/2))/HZ;
		long tick_diff = new_tb_ticks_per_jiffy - tb_ticks_per_jiffy;
		char sign = '+';		
		/* make sure tb_ticks_per_sec and tb_ticks_per_jiffy are consistent */
		new_tb_ticks_per_sec = new_tb_ticks_per_jiffy * HZ;

		if ( tick_diff < 0 ) {
			tick_diff = -tick_diff;
			sign = '-';
		}
		if ( tick_diff ) {
			if ( tick_diff < tb_ticks_per_jiffy/25 ) {
				printk( "Titan recalibrate: new tb_ticks_per_jiffy = %lu (%c%ld)\n",
						new_tb_ticks_per_jiffy, sign, tick_diff );
				tb_ticks_per_jiffy = new_tb_ticks_per_jiffy;
				tb_ticks_per_sec   = new_tb_ticks_per_sec;
				calc_cputime_factors();
				div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
				tb_to_xs = divres.result_low;
				do_gtod.varp->tb_to_xs = tb_to_xs;
				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
				vdso_data->tb_to_xs = tb_to_xs;
			}
			else {
				printk( "Titan recalibrate: FAILED (difference > 4 percent)\n"
					"                   new tb_ticks_per_jiffy = %lu\n"
					"                   old tb_ticks_per_jiffy = %lu\n",
					new_tb_ticks_per_jiffy, tb_ticks_per_jiffy );
			}
		}
	}
	iSeries_recal_titan = titan;
	iSeries_recal_tb = tb;

	/* Called here as now we know accurate values for the timebase */
	clocksource_init();
	return 0;
}
late_initcall(iSeries_tb_recal);

/* Called from platform early init */
void __init iSeries_time_init_early(void)
{
	iSeries_recal_tb = get_tb();
	iSeries_recal_titan = HvCallXm_loadTod();
}
#endif /* CONFIG_PPC_ISERIES */

/*
 * For iSeries shared processors, we have to let the hypervisor
 * set the hardware decrementer.  We set a virtual decrementer
 * in the lppaca and call the hypervisor if the virtual
 * decrementer is less than the current value in the hardware
 * decrementer. (almost always the new decrementer value will
 * be greater than the current hardware decementer so the hypervisor
 * call will not be needed)
 */

/*
 * timer_interrupt - gets called when the decrementer overflows,
 * with interrupts disabled.
 */
void timer_interrupt(struct pt_regs * regs)
{
	struct pt_regs *old_regs;
	int cpu = smp_processor_id();
	struct clock_event_device *evt = &per_cpu(decrementers, cpu);
	u64 now;

	/* Ensure a positive value is written to the decrementer, or else
	 * some CPUs will continuue to take decrementer exceptions */
	set_dec(DECREMENTER_MAX);

#ifdef CONFIG_PPC32
	if (atomic_read(&ppc_n_lost_interrupts) != 0)
		do_IRQ(regs);
#endif

	now = get_tb_or_rtc();
	if (now < per_cpu(decrementer_next_tb, cpu)) {
		/* not time for this event yet */
		now = per_cpu(decrementer_next_tb, cpu) - now;
		if (now <= DECREMENTER_MAX)
			set_dec((int)now);
		return;
	}
	old_regs = set_irq_regs(regs);
	irq_enter();

	calculate_steal_time();

#ifdef CONFIG_PPC_ISERIES
	if (firmware_has_feature(FW_FEATURE_ISERIES))
		get_lppaca()->int_dword.fields.decr_int = 0;
#endif

	if (evt->event_handler)
		evt->event_handler(evt);

#ifdef CONFIG_PPC_ISERIES
	if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending())
		process_hvlpevents();
#endif

#ifdef CONFIG_PPC64
	/* collect purr register values often, for accurate calculations */
	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
		cu->current_tb = mfspr(SPRN_PURR);
	}
#endif

	irq_exit();
	set_irq_regs(old_regs);
}

void wakeup_decrementer(void)
{
	unsigned long ticks;

	/*
	 * The timebase gets saved on sleep and restored on wakeup,
	 * so all we need to do is to reset the decrementer.
	 */
	ticks = tb_ticks_since(__get_cpu_var(last_jiffy));
	if (ticks < tb_ticks_per_jiffy)
		ticks = tb_ticks_per_jiffy - ticks;
	else
		ticks = 1;
	set_dec(ticks);
}

#ifdef CONFIG_SMP
void __init smp_space_timers(unsigned int max_cpus)
{
	int i;
	u64 previous_tb = per_cpu(last_jiffy, boot_cpuid);

	/* make sure tb > per_cpu(last_jiffy, cpu) for all cpus always */
	previous_tb -= tb_ticks_per_jiffy;

	for_each_possible_cpu(i) {
		if (i == boot_cpuid)
			continue;
		per_cpu(last_jiffy, i) = previous_tb;
	}
}
#endif

/*
 * Scheduler clock - returns current time in nanosec units.
 *
 * Note: mulhdu(a, b) (multiply high double unsigned) returns
 * the high 64 bits of a * b, i.e. (a * b) >> 64, where a and b
 * are 64-bit unsigned numbers.
 */
unsigned long long sched_clock(void)
{
	if (__USE_RTC())
		return get_rtc();
	return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
}

static int __init get_freq(char *name, int cells, unsigned long *val)
{
	struct device_node *cpu;
	const unsigned int *fp;
	int found = 0;

	/* The cpu node should have timebase and clock frequency properties */
	cpu = of_find_node_by_type(NULL, "cpu");

	if (cpu) {
		fp = of_get_property(cpu, name, NULL);
		if (fp) {
			found = 1;
			*val = of_read_ulong(fp, cells);
		}

		of_node_put(cpu);
	}

	return found;
}

void __init generic_calibrate_decr(void)
{
	ppc_tb_freq = DEFAULT_TB_FREQ;		/* hardcoded default */

	if (!get_freq("ibm,extended-timebase-frequency", 2, &ppc_tb_freq) &&
	    !get_freq("timebase-frequency", 1, &ppc_tb_freq)) {

		printk(KERN_ERR "WARNING: Estimating decrementer frequency "
				"(not found)\n");
	}

	ppc_proc_freq = DEFAULT_PROC_FREQ;	/* hardcoded default */

	if (!get_freq("ibm,extended-clock-frequency", 2, &ppc_proc_freq) &&
	    !get_freq("clock-frequency", 1, &ppc_proc_freq)) {

		printk(KERN_ERR "WARNING: Estimating processor frequency "
				"(not found)\n");
	}

#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
	/* Set the time base to zero */
	mtspr(SPRN_TBWL, 0);
	mtspr(SPRN_TBWU, 0);

	/* Clear any pending timer interrupts */
	mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);

	/* Enable decrementer interrupt */
	mtspr(SPRN_TCR, TCR_DIE);
#endif
}

int update_persistent_clock(struct timespec now)
{
	struct rtc_time tm;

	if (!ppc_md.set_rtc_time)
		return 0;

	to_tm(now.tv_sec + 1 + timezone_offset, &tm);
	tm.tm_year -= 1900;
	tm.tm_mon -= 1;

	return ppc_md.set_rtc_time(&tm);
}

unsigned long read_persistent_clock(void)
{
	struct rtc_time tm;
	static int first = 1;

	/* XXX this is a litle fragile but will work okay in the short term */
	if (first) {
		first = 0;
		if (ppc_md.time_init)
			timezone_offset = ppc_md.time_init();

		/* get_boot_time() isn't guaranteed to be safe to call late */
		if (ppc_md.get_boot_time)
			return ppc_md.get_boot_time() -timezone_offset;
	}
	if (!ppc_md.get_rtc_time)
		return 0;
	ppc_md.get_rtc_time(&tm);
	return mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday,
		      tm.tm_hour, tm.tm_min, tm.tm_sec);
}

/* clocksource code */