1055 lines · 26.6 KB · C
RawDownload
/* * Common time routines among all ppc machines. * * Written by Cort Dougan (cort@cs.nmt.edu) to merge * Paul Mackerras' version and mine for PReP and Pmac. * MPC8xx/MBX changes by Dan Malek (dmalek@jlc.net). * Converted for 64-bit by Mike Corrigan (mikejc@us.ibm.com) * * First round of bugfixes by Gabriel Paubert (paubert@iram.es) * 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). (mikejc@us.ibm.com) * * TODO (not necessarily in this file): * - improve precision and reproducibility of timebase frequency * measurement at boot time. * - 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/export.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 <linux/delay.h>#include <linux/irq_work.h>#include <asm/trace.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>#include <asm/cputime.h> /* powerpc clocksource/clockevent code */ #include <linux/clockchips.h>#include <linux/timekeeper_internal.h> static cycle_t rtc_read(struct clocksource *);static struct clocksource clocksource_rtc = {	.name         = "rtc",	.rating       = 400,	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,	.mask         = CLOCKSOURCE_MASK(64),	.read         = rtc_read,}; static cycle_t timebase_read(struct clocksource *);static struct clocksource clocksource_timebase = {	.name         = "timebase",	.rating       = 400,	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,	.mask         = CLOCKSOURCE_MASK(64),	.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); struct clock_event_device decrementer_clockevent = {	.name           = "decrementer",	.rating         = 200,	.irq            = 0,	.set_next_event = decrementer_set_next_event,	.set_mode       = decrementer_set_mode,	.features       = CLOCK_EVT_FEAT_ONESHOT,};EXPORT_SYMBOL(decrementer_clockevent); DEFINE_PER_CPU(u64, decrementers_next_tb);static DEFINE_PER_CPU(struct clock_event_device, decrementers); #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 */ 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 u64 boot_tb __read_mostly; extern struct timezone sys_tz;static long timezone_offset; unsigned long ppc_proc_freq;EXPORT_SYMBOL_GPL(ppc_proc_freq);unsigned long ppc_tb_freq;EXPORT_SYMBOL_GPL(ppc_tb_freq); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE/* * Factors for converting from cputime_t (timebase ticks) to * jiffies, microseconds, 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_usec_factor;EXPORT_SYMBOL(__cputime_usec_factor);u64 __cputime_sec_factor;EXPORT_SYMBOL(__cputime_sec_factor);u64 __cputime_clockt_factor;EXPORT_SYMBOL(__cputime_clockt_factor);DEFINE_PER_CPU(unsigned long, cputime_last_delta);DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta); cputime_t cputime_one_jiffy; void (*dtl_consumer)(struct dtl_entry *, u64); 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(1000000, 0, tb_ticks_per_sec, &res);	__cputime_usec_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 SPURR on systems that have it, otherwise the PURR, * or if that doesn't exist return the timebase value passed in. */static u64 read_spurr(u64 tb){	if (cpu_has_feature(CPU_FTR_SPURR))		return mfspr(SPRN_SPURR);	if (cpu_has_feature(CPU_FTR_PURR))		return mfspr(SPRN_PURR);	return tb;} #ifdef CONFIG_PPC_SPLPAR /* * Scan the dispatch trace log and count up the stolen time. * Should be called with interrupts disabled. */static u64 scan_dispatch_log(u64 stop_tb){	u64 i = local_paca->dtl_ridx;	struct dtl_entry *dtl = local_paca->dtl_curr;	struct dtl_entry *dtl_end = local_paca->dispatch_log_end;	struct lppaca *vpa = local_paca->lppaca_ptr;	u64 tb_delta;	u64 stolen = 0;	u64 dtb; 	if (!dtl)		return 0; 	if (i == be64_to_cpu(vpa->dtl_idx))		return 0;	while (i < be64_to_cpu(vpa->dtl_idx)) {		dtb = be64_to_cpu(dtl->timebase);		tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +			be32_to_cpu(dtl->ready_to_enqueue_time);		barrier();		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {			/* buffer has overflowed */			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);			continue;		}		if (dtb > stop_tb)			break;		if (dtl_consumer)			dtl_consumer(dtl, i);		stolen += tb_delta;		++i;		++dtl;		if (dtl == dtl_end)			dtl = local_paca->dispatch_log;	}	local_paca->dtl_ridx = i;	local_paca->dtl_curr = dtl;	return stolen;} /* * Accumulate stolen time by scanning the dispatch trace log. * Called on entry from user mode. */void accumulate_stolen_time(void){	u64 sst, ust; 	u8 save_soft_enabled = local_paca->soft_enabled; 	/* We are called early in the exception entry, before	 * soft/hard_enabled are sync'ed to the expected state	 * for the exception. We are hard disabled but the PACA	 * needs to reflect that so various debug stuff doesn't	 * complain	 */	local_paca->soft_enabled = 0; 	sst = scan_dispatch_log(local_paca->starttime_user);	ust = scan_dispatch_log(local_paca->starttime);	local_paca->system_time -= sst;	local_paca->user_time -= ust;	local_paca->stolen_time += ust + sst; 	local_paca->soft_enabled = save_soft_enabled;} static inline u64 calculate_stolen_time(u64 stop_tb){	u64 stolen = 0; 	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {		stolen = scan_dispatch_log(stop_tb);		get_paca()->system_time -= stolen;	} 	stolen += get_paca()->stolen_time;	get_paca()->stolen_time = 0;	return stolen;} #else /* CONFIG_PPC_SPLPAR */static inline u64 calculate_stolen_time(u64 stop_tb){	return 0;} #endif /* CONFIG_PPC_SPLPAR */ /* * Account time for a transition between system, hard irq * or soft irq state. */static u64 vtime_delta(struct task_struct *tsk,			u64 *sys_scaled, u64 *stolen){	u64 now, nowscaled, deltascaled;	u64 udelta, delta, user_scaled; 	WARN_ON_ONCE(!irqs_disabled()); 	now = mftb();	nowscaled = read_spurr(now);	get_paca()->system_time += now - get_paca()->starttime;	get_paca()->starttime = now;	deltascaled = nowscaled - get_paca()->startspurr;	get_paca()->startspurr = nowscaled; 	*stolen = calculate_stolen_time(now); 	delta = get_paca()->system_time;	get_paca()->system_time = 0;	udelta = get_paca()->user_time - get_paca()->utime_sspurr;	get_paca()->utime_sspurr = get_paca()->user_time; 	/*	 * Because we don't read the SPURR on every kernel entry/exit,	 * deltascaled includes both user and system SPURR ticks.	 * Apportion these ticks to system SPURR ticks and user	 * SPURR ticks in the same ratio as the system time (delta)	 * and user time (udelta) values obtained from the timebase	 * over the same interval.  The system ticks get accounted here;	 * the user ticks get saved up in paca->user_time_scaled to be	 * used by account_process_tick.	 */	*sys_scaled = delta;	user_scaled = udelta;	if (deltascaled != delta + udelta) {		if (udelta) {			*sys_scaled = deltascaled * delta / (delta + udelta);			user_scaled = deltascaled - *sys_scaled;		} else {			*sys_scaled = deltascaled;		}	}	get_paca()->user_time_scaled += user_scaled; 	return delta;} void vtime_account_system(struct task_struct *tsk){	u64 delta, sys_scaled, stolen; 	delta = vtime_delta(tsk, &sys_scaled, &stolen);	account_system_time(tsk, 0, delta, sys_scaled);	if (stolen)		account_steal_time(stolen);}EXPORT_SYMBOL_GPL(vtime_account_system); void vtime_account_idle(struct task_struct *tsk){	u64 delta, sys_scaled, stolen; 	delta = vtime_delta(tsk, &sys_scaled, &stolen);	account_idle_time(delta + stolen);} /* * Transfer the user time accumulated in the paca * by the exception entry and exit code to the generic * process user time records. * Must be called with interrupts disabled. * Assumes that vtime_account_system/idle() has been called * recently (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */void vtime_account_user(struct task_struct *tsk){	cputime_t utime, utimescaled; 	utime = get_paca()->user_time;	utimescaled = get_paca()->user_time_scaled;	get_paca()->user_time = 0;	get_paca()->user_time_scaled = 0;	get_paca()->utime_sspurr = 0;	account_user_time(tsk, utime, utimescaled);} #else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */#define calc_cputime_factors()#endif 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); #ifdef CONFIG_SMPunsigned 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_IRQ_WORK /* * 64-bit uses a byte in the PACA, 32-bit uses a per-cpu variable... */#ifdef CONFIG_PPC64static inline unsigned long test_irq_work_pending(void){	unsigned long x; 	asm volatile("lbz %0,%1(13)"		: "=r" (x)		: "i" (offsetof(struct paca_struct, irq_work_pending)));	return x;} static inline void set_irq_work_pending_flag(void){	asm volatile("stb %0,%1(13)" : :		"r" (1),		"i" (offsetof(struct paca_struct, irq_work_pending)));} static inline void clear_irq_work_pending(void){	asm volatile("stb %0,%1(13)" : :		"r" (0),		"i" (offsetof(struct paca_struct, irq_work_pending)));} #else /* 32-bit */ DEFINE_PER_CPU(u8, irq_work_pending); #define set_irq_work_pending_flag()	__get_cpu_var(irq_work_pending) = 1#define test_irq_work_pending()		__get_cpu_var(irq_work_pending)#define clear_irq_work_pending()	__get_cpu_var(irq_work_pending) = 0 #endif /* 32 vs 64 bit */ void arch_irq_work_raise(void){	preempt_disable();	set_irq_work_pending_flag();	set_dec(1);	preempt_enable();} #else  /* CONFIG_IRQ_WORK */ #define test_irq_work_pending()	0#define clear_irq_work_pending() #endif /* CONFIG_IRQ_WORK */ /* * timer_interrupt - gets called when the decrementer overflows, * with interrupts disabled. */void timer_interrupt(struct pt_regs * regs){	struct pt_regs *old_regs;	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);	struct clock_event_device *evt = &__get_cpu_var(decrementers);	u64 now; 	/* Ensure a positive value is written to the decrementer, or else	 * some CPUs will continue to take decrementer exceptions.	 */	set_dec(DECREMENTER_MAX); 	/* Some implementations of hotplug will get timer interrupts while	 * offline, just ignore these and we also need to set	 * decrementers_next_tb as MAX to make sure __check_irq_replay	 * don't replay timer interrupt when return, otherwise we'll trap

Lines 1–500 of 1055.