time.c

linux 内核源代码

/*
 * Common time routines among all ppc machines.
 *
 * Written by Cort Dougan ([e-mail]) to merge
 * Paul Mackerras' version and mine for PReP and Pmac.
 * MPC8xx/MBX changes by Dan Malek ([e-mail]).
 * Converted for 64-bit by Mike Corrigan ([e-mail])
 *
 * First round of bugfixes by Gabriel Paubert ([e-mail])
 * to make clock more stable (2.4.0-test5). The only thing
 * that this code assumes is that the timebases have been synchronized
 * by firmware on SMP and are never stopped (never do sleep
 * on SMP then, nap and doze are OK).
 * 
 * Speeded up do_gettimeofday by getting rid of references to
 * xtime (which required locks for consistency). ([e-mail])
 *
 * TODO (not necessarily in this file):
 * - improve precision and reproducibility of timebase frequency
 * measurement at boot time. (for iSeries, we calibrate the timebase
 * against the Titan chip's clock.)
 * - for astronomical applications: add a new function to get
 * non ambiguous timestamps even around leap seconds. This needs
 * a new timestamp format and a good name.
 *
 * 1997-09-10  Updated NTP code according to technical memorandum Jan '96
 *             "A Kernel Model for Precision Timekeeping" by Dave Mills
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#include <linux/errno.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/param.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/timex.h>
#include <linux/kernel_stat.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/profile.h>
#include <linux/cpu.h>
#include <linux/security.h>
#include <linux/percpu.h>
#include <linux/rtc.h>
#include <linux/jiffies.h>
#include <linux/posix-timers.h>
#include <linux/irq.h>

#include <asm/io.h>
#include <asm/processor.h>
#include <asm/nvram.h>
#include <asm/cache.h>
#include <asm/machdep.h>
#include <asm/uaccess.h>
#include <asm/time.h>
#include <asm/prom.h>
#include <asm/irq.h>
#include <asm/div64.h>
#include <asm/smp.h>
#include <asm/vdso_datapage.h>
#include <asm/firmware.h>
#ifdef CONFIG_PPC_ISERIES
#include <asm/iseries/it_lp_queue.h>
#include <asm/iseries/hv_call_xm.h>
#endif

/* powerpc clocksource/clockevent code */

#include <linux/clockchips.h>
#include <linux/clocksource.h>

static cycle_t rtc_read(void);
static struct clocksource clocksource_rtc = {
	.name         = "rtc",
	.rating       = 400,
	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
	.mask         = CLOCKSOURCE_MASK(64),
	.shift        = 22,
	.mult         = 0,	/* To be filled in */
	.read         = rtc_read,
};

static cycle_t timebase_read(void);
static struct clocksource clocksource_timebase = {
	.name         = "timebase",
	.rating       = 400,
	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
	.mask         = CLOCKSOURCE_MASK(64),
	.shift        = 22,
	.mult         = 0,	/* To be filled in */
	.read         = timebase_read,
};

#define DECREMENTER_MAX	0x7fffffff

static int decrementer_set_next_event(unsigned long evt,
				      struct clock_event_device *dev);
static void decrementer_set_mode(enum clock_event_mode mode,
				 struct clock_event_device *dev);

static struct clock_event_device decrementer_clockevent = {
       .name           = "decrementer",
       .rating         = 200,
       .shift          = 16,
       .mult           = 0,	/* To be filled in */
       .irq            = 0,
       .set_next_event = decrementer_set_next_event,
       .set_mode       = decrementer_set_mode,
       .features       = CLOCK_EVT_FEAT_ONESHOT,
};

static DEFINE_PER_CPU(struct clock_event_device, decrementers);
void init_decrementer_clockevent(void);
static DEFINE_PER_CPU(u64, decrementer_next_tb);

#ifdef CONFIG_PPC_ISERIES
static unsigned long __initdata iSeries_recal_titan;
static signed long __initdata iSeries_recal_tb;

/* Forward declaration is only needed for iSereis compiles */
void __init clocksource_init(void);
#endif

#define XSEC_PER_SEC (1024*1024)

#ifdef CONFIG_PPC64
#define SCALE_XSEC(xsec, max)	(((xsec) * max) / XSEC_PER_SEC)
#else
/* compute ((xsec << 12) * max) >> 32 */
#define SCALE_XSEC(xsec, max)	mulhwu((xsec) << 12, max)
#endif

unsigned long tb_ticks_per_jiffy;
unsigned long tb_ticks_per_usec = 100; /* sane default */
EXPORT_SYMBOL(tb_ticks_per_usec);
unsigned long tb_ticks_per_sec;
EXPORT_SYMBOL(tb_ticks_per_sec);	/* for cputime_t conversions */
u64 tb_to_xs;
unsigned tb_to_us;

#define TICKLEN_SCALE	TICK_LENGTH_SHIFT
u64 last_tick_len;	/* units are ns / 2^TICKLEN_SCALE */
u64 ticklen_to_xs;	/* 0.64 fraction */

/* If last_tick_len corresponds to about 1/HZ seconds, then
   last_tick_len << TICKLEN_SHIFT will be about 2^63. */
#define TICKLEN_SHIFT	(63 - 30 - TICKLEN_SCALE + SHIFT_HZ)

DEFINE_SPINLOCK(rtc_lock);
EXPORT_SYMBOL_GPL(rtc_lock);

static u64 tb_to_ns_scale __read_mostly;
static unsigned tb_to_ns_shift __read_mostly;
static unsigned long boot_tb __read_mostly;

struct gettimeofday_struct do_gtod;

extern struct timezone sys_tz;
static long timezone_offset;

unsigned long ppc_proc_freq;
EXPORT_SYMBOL(ppc_proc_freq);
unsigned long ppc_tb_freq;

static u64 tb_last_jiffy __cacheline_aligned_in_smp;
static DEFINE_PER_CPU(u64, last_jiffy);

#ifdef CONFIG_VIRT_CPU_ACCOUNTING
/*
 * Factors for converting from cputime_t (timebase ticks) to
 * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds).
 * These are all stored as 0.64 fixed-point binary fractions.
 */
u64 __cputime_jiffies_factor;
EXPORT_SYMBOL(__cputime_jiffies_factor);
u64 __cputime_msec_factor;
EXPORT_SYMBOL(__cputime_msec_factor);
u64 __cputime_sec_factor;
EXPORT_SYMBOL(__cputime_sec_factor);
u64 __cputime_clockt_factor;
EXPORT_SYMBOL(__cputime_clockt_factor);

static void calc_cputime_factors(void)
{
	struct div_result res;

	div128_by_32(HZ, 0, tb_ticks_per_sec, &res);
	__cputime_jiffies_factor = res.result_low;
	div128_by_32(1000, 0, tb_ticks_per_sec, &res);
	__cputime_msec_factor = res.result_low;
	div128_by_32(1, 0, tb_ticks_per_sec, &res);
	__cputime_sec_factor = res.result_low;
	div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res);
	__cputime_clockt_factor = res.result_low;
}

/*
 * Read the PURR on systems that have it, otherwise the timebase.
 */
static u64 read_purr(void)
{
	if (cpu_has_feature(CPU_FTR_PURR))
		return mfspr(SPRN_PURR);
	return mftb();
}

/*
 * Read the SPURR on systems that have it, otherwise the purr
 */
static u64 read_spurr(u64 purr)
{
	if (cpu_has_feature(CPU_FTR_SPURR))
		return mfspr(SPRN_SPURR);
	return purr;
}

/*
 * Account time for a transition between system, hard irq
 * or soft irq state.
 */
void account_system_vtime(struct task_struct *tsk)
{
	u64 now, nowscaled, delta, deltascaled;
	unsigned long flags;

	local_irq_save(flags);
	now = read_purr();
	delta = now - get_paca()->startpurr;
	get_paca()->startpurr = now;
	nowscaled = read_spurr(now);
	deltascaled = nowscaled - get_paca()->startspurr;
	get_paca()->startspurr = nowscaled;
	if (!in_interrupt()) {
		/* deltascaled includes both user and system time.
		 * Hence scale it based on the purr ratio to estimate
		 * the system time */
		if (get_paca()->user_time)
			deltascaled = deltascaled * get_paca()->system_time /
			     (get_paca()->system_time + get_paca()->user_time);
		delta += get_paca()->system_time;
		get_paca()->system_time = 0;
	}
	account_system_time(tsk, 0, delta);
	get_paca()->purrdelta = delta;
	account_system_time_scaled(tsk, deltascaled);
	get_paca()->spurrdelta = deltascaled;
	local_irq_restore(flags);
}

/*
 * Transfer the user and system times accumulated in the paca
 * by the exception entry and exit code to the generic process
 * user and system time records.
 * Must be called with interrupts disabled.
 */
void account_process_tick(struct task_struct *tsk, int user_tick)
{
	cputime_t utime, utimescaled;

	utime = get_paca()->user_time;
	get_paca()->user_time = 0;
	account_user_time(tsk, utime);

	/* Estimate the scaled utime by scaling the real utime based
	 * on the last spurr to purr ratio */
	utimescaled = utime * get_paca()->spurrdelta / get_paca()->purrdelta;
	get_paca()->spurrdelta = get_paca()->purrdelta = 0;
	account_user_time_scaled(tsk, utimescaled);
}

/*
 * Stuff for accounting stolen time.
 */
struct cpu_purr_data {
	int	initialized;			/* thread is running */
	u64	tb;			/* last TB value read */
	u64	purr;			/* last PURR value read */
	u64	spurr;			/* last SPURR value read */
};

/*
 * Each entry in the cpu_purr_data array is manipulated only by its
 * "owner" cpu -- usually in the timer interrupt but also occasionally
 * in process context for cpu online.  As long as cpus do not touch
 * each others' cpu_purr_data, disabling local interrupts is
 * sufficient to serialize accesses.
 */
static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);

static void snapshot_tb_and_purr(void *data)
{
	unsigned long flags;
	struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);

	local_irq_save(flags);
	p->tb = get_tb_or_rtc();
	p->purr = mfspr(SPRN_PURR);
	wmb();
	p->initialized = 1;
	local_irq_restore(flags);
}

/*
 * Called during boot when all cpus have come up.
 */
void snapshot_timebases(void)
{
	if (!cpu_has_feature(CPU_FTR_PURR))
		return;
	on_each_cpu(snapshot_tb_and_purr, NULL, 0, 1);
}

/*
 * Must be called with interrupts disabled.
 */
void calculate_steal_time(void)
{
	u64 tb, purr;
	s64 stolen;
	struct cpu_purr_data *pme;

	if (!cpu_has_feature(CPU_FTR_PURR))
		return;
	pme = &per_cpu(cpu_purr_data, smp_processor_id());
	if (!pme->initialized)
		return;		/* this can happen in early boot */
	tb = mftb();
	purr = mfspr(SPRN_PURR);
	stolen = (tb - pme->tb) - (purr - pme->purr);
	if (stolen > 0)
		account_steal_time(current, stolen);
	pme->tb = tb;
	pme->purr = purr;
}

#ifdef CONFIG_PPC_SPLPAR
/*
 * Must be called before the cpu is added to the online map when
 * a cpu is being brought up at runtime.
 */
static void snapshot_purr(void)
{
	struct cpu_purr_data *pme;
	unsigned long flags;

	if (!cpu_has_feature(CPU_FTR_PURR))
		return;
	local_irq_save(flags);
	pme = &per_cpu(cpu_purr_data, smp_processor_id());
	pme->tb = mftb();
	pme->purr = mfspr(SPRN_PURR);
	pme->initialized = 1;
	local_irq_restore(flags);
}

#endif /* CONFIG_PPC_SPLPAR */

#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
#define calc_cputime_factors()
#define calculate_steal_time()		do { } while (0)
#endif

#if !(defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR))
#define snapshot_purr()			do { } while (0)
#endif

/*