time.c

来自「LINUX 2.6.17.4的源码」· C语言 代码 · 共 1,200 行 · 第 1/3 页

         * We should have an rtc call that only sets the minutes and
         * seconds like on Intel to avoid problems with non UTC clocks.
         */
        if (ppc_md.set_rtc_time && ntp_synced() &&
	    xtime.tv_sec - last_rtc_update >= 659 &&
	    abs((xtime.tv_nsec/1000) - (1000000-1000000/HZ)) < 500000/HZ) {
		struct rtc_time tm;
		to_tm(xtime.tv_sec + 1 + timezone_offset, &tm);
		tm.tm_year -= 1900;
		tm.tm_mon -= 1;
		if (ppc_md.set_rtc_time(&tm) == 0)
			last_rtc_update = xtime.tv_sec + 1;
		else
			/* Try again one minute later */
			last_rtc_update += 60;
        }
}

/*
 * This version of gettimeofday has microsecond resolution.
 */
static inline void __do_gettimeofday(struct timeval *tv, u64 tb_val)
{
	unsigned long sec, usec;
	u64 tb_ticks, xsec;
	struct gettimeofday_vars *temp_varp;
	u64 temp_tb_to_xs, temp_stamp_xsec;

	/*
	 * These calculations are faster (gets rid of divides)
	 * if done in units of 1/2^20 rather than microseconds.
	 * The conversion to microseconds at the end is done
	 * without a divide (and in fact, without a multiply)
	 */
	temp_varp = do_gtod.varp;
	tb_ticks = tb_val - temp_varp->tb_orig_stamp;
	temp_tb_to_xs = temp_varp->tb_to_xs;
	temp_stamp_xsec = temp_varp->stamp_xsec;
	xsec = temp_stamp_xsec + mulhdu(tb_ticks, temp_tb_to_xs);
	sec = xsec / XSEC_PER_SEC;
	usec = (unsigned long)xsec & (XSEC_PER_SEC - 1);
	usec = SCALE_XSEC(usec, 1000000);

	tv->tv_sec = sec;
	tv->tv_usec = usec;
}

void do_gettimeofday(struct timeval *tv)
{
	if (__USE_RTC()) {
		/* do this the old way */
		unsigned long flags, seq;
		unsigned int sec, nsec, usec;

		do {
			seq = read_seqbegin_irqsave(&xtime_lock, flags);
			sec = xtime.tv_sec;
			nsec = xtime.tv_nsec + tb_ticks_since(tb_last_stamp);
		} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
		usec = nsec / 1000;
		while (usec >= 1000000) {
			usec -= 1000000;
			++sec;
		}
		tv->tv_sec = sec;
		tv->tv_usec = usec;
		return;
	}
	__do_gettimeofday(tv, get_tb());
}

EXPORT_SYMBOL(do_gettimeofday);

/*
 * 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);
}

/*
 * When the timebase - tb_orig_stamp gets too big, we do a manipulation
 * between tb_orig_stamp and stamp_xsec. The goal here is to keep the
 * difference tb - tb_orig_stamp small enough to always fit inside a
 * 32 bits number. This is a requirement of our fast 32 bits userland
 * implementation in the vdso. If we "miss" a call to this function
 * (interrupt latency, CPU locked in a spinlock, ...) and we end up
 * with a too big difference, then the vdso will fallback to calling
 * the syscall
 */
static __inline__ void timer_recalc_offset(u64 cur_tb)
{
	unsigned long offset;
	u64 new_stamp_xsec;
	u64 tlen, t2x;
	u64 tb, xsec_old, xsec_new;
	struct gettimeofday_vars *varp;

	if (__USE_RTC())
		return;
	tlen = current_tick_length();
	offset = cur_tb - do_gtod.varp->tb_orig_stamp;
	if (tlen == last_tick_len && offset < 0x80000000u)
		return;
	if (tlen != last_tick_len) {
		t2x = mulhdu(tlen << TICKLEN_SHIFT, ticklen_to_xs);
		last_tick_len = tlen;
	} else
		t2x = do_gtod.varp->tb_to_xs;
	new_stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC;
	do_div(new_stamp_xsec, 1000000000);
	new_stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC;

	++vdso_data->tb_update_count;
	smp_mb();

	/*
	 * Make sure time doesn't go backwards for userspace gettimeofday.
	 */
	tb = get_tb();
	varp = do_gtod.varp;
	xsec_old = mulhdu(tb - varp->tb_orig_stamp, varp->tb_to_xs)
		+ varp->stamp_xsec;
	xsec_new = mulhdu(tb - cur_tb, t2x) + new_stamp_xsec;
	if (xsec_new < xsec_old)
		new_stamp_xsec += xsec_old - xsec_new;

	update_gtod(cur_tb, new_stamp_xsec, t2x);
}

#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 void iSeries_tb_recal(void)
{
	struct div_result divres;
	unsigned long titan, tb;
	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;
}
#endif

/*
 * 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)
{
	int next_dec;
	int cpu = smp_processor_id();
	unsigned long ticks;

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

	irq_enter();

	profile_tick(CPU_PROFILING, regs);
	calculate_steal_time();

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

	while ((ticks = tb_ticks_since(per_cpu(last_jiffy, cpu)))
	       >= tb_ticks_per_jiffy) {
		/* Update last_jiffy */
		per_cpu(last_jiffy, cpu) += tb_ticks_per_jiffy;
		/* Handle RTCL overflow on 601 */
		if (__USE_RTC() && per_cpu(last_jiffy, cpu) >= 1000000000)
			per_cpu(last_jiffy, cpu) -= 1000000000;

		/*
		 * We cannot disable the decrementer, so in the period
		 * between this cpu's being marked offline in cpu_online_map
		 * and calling stop-self, it is taking timer interrupts.
		 * Avoid calling into the scheduler rebalancing code if this
		 * is the case.
		 */
		if (!cpu_is_offline(cpu))
			account_process_time(regs);

		/*
		 * No need to check whether cpu is offline here; boot_cpuid
		 * should have been fixed up by now.
		 */
		if (cpu != boot_cpuid)
			continue;

		write_seqlock(&xtime_lock);
		tb_last_jiffy += tb_ticks_per_jiffy;
		tb_last_stamp = per_cpu(last_jiffy, cpu);
		do_timer(regs);
		timer_recalc_offset(tb_last_jiffy);
		timer_check_rtc();
		write_sequnlock(&xtime_lock);
	}
	
	next_dec = tb_ticks_per_jiffy - ticks;
	set_dec(next_dec);

#ifdef CONFIG_PPC_ISERIES
	if (hvlpevent_is_pending())
		process_hvlpevents(regs);
#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();
}

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;
	unsigned long half = tb_ticks_per_jiffy / 2;
	unsigned long offset = tb_ticks_per_jiffy / max_cpus;
	unsigned long 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;
	/*
	 * The stolen time calculation for POWER5 shared-processor LPAR
	 * systems works better if the two threads' timebase interrupts
	 * are staggered by half a jiffy with respect to each other.
	 */
	for_each_possible_cpu(i) {
		if (i == boot_cpuid)
			continue;
		if (i == (boot_cpuid ^ 1))
			per_cpu(last_jiffy, i) =
				per_cpu(last_jiffy, boot_cpuid) - half;
		else if (i & 1)
			per_cpu(last_jiffy, i) =
				per_cpu(last_jiffy, i ^ 1) + half;
		else {
			previous_tb += offset;
			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(), tb_to_ns_scale) << tb_to_ns_shift;
}

int do_settimeofday(struct timespec *tv)
{
	time_t wtm_sec, new_sec = tv->tv_sec;
	long wtm_nsec, new_nsec = tv->tv_nsec;
	unsigned long flags;
	u64 new_xsec;
	unsigned long tb_delta;

	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
		return -EINVAL;

	write_seqlock_irqsave(&xtime_lock, flags);

	/*
	 * Updating the RTC is not the job of this code. If the time is
	 * stepped under NTP, the RTC will be updated after STA_UNSYNC