1107 lines · 27.8 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-or-later/* * 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 */ #include <linux/errno.h>#include <linux/export.h>#include <linux/sched.h>#include <linux/sched/clock.h>#include <linux/sched/cputime.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 <linux/of_clk.h>#include <linux/suspend.h>#include <linux/processor.h>#include <linux/mc146818rtc.h>#include <linux/platform_device.h> #include <asm/trace.h>#include <asm/interrupt.h>#include <asm/io.h>#include <asm/nvram.h>#include <asm/cache.h>#include <asm/machdep.h>#include <linux/uaccess.h>#include <asm/time.h>#include <asm/irq.h>#include <asm/div64.h>#include <asm/smp.h>#include <asm/vdso_datapage.h>#include <asm/firmware.h>#include <asm/mce.h>#include <asm/systemcfg.h> /* powerpc clocksource/clockevent code */ #include <linux/clockchips.h> static u64 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,	.vdso_clock_mode	= VDSO_CLOCKMODE_ARCHTIMER,}; #define DECREMENTER_DEFAULT_MAX 0x7FFFFFFFu64 decrementer_max = DECREMENTER_DEFAULT_MAX;EXPORT_SYMBOL_GPL(decrementer_max); /* for KVM HDEC */ static int decrementer_set_next_event(unsigned long evt,				      struct clock_event_device *dev);static int decrementer_shutdown(struct clock_event_device *evt); struct clock_event_device decrementer_clockevent = {	.name			= "decrementer",	.rating			= 200,	.irq			= 0,	.set_next_event		= decrementer_set_next_event,	.set_state_oneshot_stopped = decrementer_shutdown,	.set_state_shutdown	= decrementer_shutdown,	.tick_resume		= decrementer_shutdown,	.features		= CLOCK_EVT_FEAT_ONESHOT |				  CLOCK_EVT_FEAT_C3STOP,};EXPORT_SYMBOL(decrementer_clockevent); /* * This always puts next_tb beyond now, so the clock event will never fire * with the usual comparison, no need for a separate test for stopped. */#define DEC_CLOCKEVENT_STOPPED ~0ULLDEFINE_PER_CPU(u64, decrementers_next_tb) = DEC_CLOCKEVENT_STOPPED;EXPORT_SYMBOL_GPL(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 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 __ro_after_init; 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); bool tb_invalid; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE/* * Read the SPURR on systems that have it, otherwise the PURR, * or if that doesn't exist return the timebase value passed in. */static inline unsigned long read_spurr(unsigned long 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;} /* * Account time for a transition between system, hard irq * or soft irq state. */static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,					unsigned long now, unsigned long stime){	unsigned long stime_scaled = 0;#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME	unsigned long nowscaled, deltascaled;	unsigned long utime, utime_scaled; 	nowscaled = read_spurr(now);	deltascaled = nowscaled - acct->startspurr;	acct->startspurr = nowscaled;	utime = acct->utime - acct->utime_sspurr;	acct->utime_sspurr = acct->utime; 	/*	 * 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.	 */	stime_scaled = stime;	utime_scaled = utime;	if (deltascaled != stime + utime) {		if (utime) {			stime_scaled = deltascaled * stime / (stime + utime);			utime_scaled = deltascaled - stime_scaled;		} else {			stime_scaled = deltascaled;		}	}	acct->utime_scaled += utime_scaled;#endif 	return stime_scaled;} static unsigned long vtime_delta(struct cpu_accounting_data *acct,				 unsigned long *stime_scaled,				 unsigned long *steal_time){	unsigned long now, stime; 	WARN_ON_ONCE(!irqs_disabled()); 	now = mftb();	stime = now - acct->starttime;	acct->starttime = now; 	*stime_scaled = vtime_delta_scaled(acct, now, stime); 	if (IS_ENABLED(CONFIG_PPC_SPLPAR) &&			firmware_has_feature(FW_FEATURE_SPLPAR))		*steal_time = pseries_calculate_stolen_time(now);	else		*steal_time = 0; 	return stime;} static void vtime_delta_kernel(struct cpu_accounting_data *acct,			       unsigned long *stime, unsigned long *stime_scaled){	unsigned long steal_time; 	*stime = vtime_delta(acct, stime_scaled, &steal_time);	*stime -= min(*stime, steal_time);	acct->steal_time += steal_time;} void vtime_account_kernel(struct task_struct *tsk){	struct cpu_accounting_data *acct = get_accounting(tsk);	unsigned long stime, stime_scaled; 	vtime_delta_kernel(acct, &stime, &stime_scaled); 	if (tsk->flags & PF_VCPU) {		acct->gtime += stime;#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME		acct->utime_scaled += stime_scaled;#endif	} else {		acct->stime += stime;#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME		acct->stime_scaled += stime_scaled;#endif	}}EXPORT_SYMBOL_GPL(vtime_account_kernel); void vtime_account_idle(struct task_struct *tsk){	unsigned long stime, stime_scaled, steal_time;	struct cpu_accounting_data *acct = get_accounting(tsk); 	stime = vtime_delta(acct, &stime_scaled, &steal_time);	acct->idle_time += stime + steal_time;} static void vtime_account_irq_field(struct cpu_accounting_data *acct,				    unsigned long *field){	unsigned long stime, stime_scaled; 	vtime_delta_kernel(acct, &stime, &stime_scaled);	*field += stime;#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME	acct->stime_scaled += stime_scaled;#endif} void vtime_account_softirq(struct task_struct *tsk){	struct cpu_accounting_data *acct = get_accounting(tsk);	vtime_account_irq_field(acct, &acct->softirq_time);} void vtime_account_hardirq(struct task_struct *tsk){	struct cpu_accounting_data *acct = get_accounting(tsk);	vtime_account_irq_field(acct, &acct->hardirq_time);} static void vtime_flush_scaled(struct task_struct *tsk,			       struct cpu_accounting_data *acct){#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME	if (acct->utime_scaled)		tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);	if (acct->stime_scaled)		tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled); 	acct->utime_scaled = 0;	acct->utime_sspurr = 0;	acct->stime_scaled = 0;#endif} /* * Account the whole cputime accumulated in the paca * Must be called with interrupts disabled. * Assumes that vtime_account_kernel/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_flush(struct task_struct *tsk){	struct cpu_accounting_data *acct = get_accounting(tsk); 	if (acct->utime)		account_user_time(tsk, cputime_to_nsecs(acct->utime)); 	if (acct->gtime)		account_guest_time(tsk, cputime_to_nsecs(acct->gtime)); 	if (IS_ENABLED(CONFIG_PPC_SPLPAR) && acct->steal_time) {		account_steal_time(cputime_to_nsecs(acct->steal_time));		acct->steal_time = 0;	} 	if (acct->idle_time)		account_idle_time(cputime_to_nsecs(acct->idle_time)); 	if (acct->stime)		account_system_index_time(tsk, cputime_to_nsecs(acct->stime),					  CPUTIME_SYSTEM); 	if (acct->hardirq_time)		account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time),					  CPUTIME_IRQ);	if (acct->softirq_time)		account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time),					  CPUTIME_SOFTIRQ); 	vtime_flush_scaled(tsk, acct); 	acct->utime = 0;	acct->gtime = 0;	acct->idle_time = 0;	acct->stime = 0;	acct->hardirq_time = 0;	acct->softirq_time = 0;} /* * Called from the context switch with interrupts disabled, to charge all * accumulated times to the current process, and to prepare accounting on * the next process. */void vtime_task_switch(struct task_struct *prev){	if (is_idle_task(prev))		vtime_account_idle(prev);	else		vtime_account_kernel(prev); 	vtime_flush(prev); 	if (!IS_ENABLED(CONFIG_PPC64)) {		struct cpu_accounting_data *acct = get_accounting(current);		struct cpu_accounting_data *acct0 = get_accounting(prev); 		acct->starttime = acct0->starttime;	}} /** * vtime_reset - Fast forward vtime entry clocks * * Called from dynticks idle IRQ entry to fast-forward the clocks to current time * so that the IRQ time is still accounted by vtime while nohz cputime is paused. */void vtime_reset(void){	struct cpu_accounting_data *acct = get_accounting(current); 	acct->starttime = mftb();#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME	acct->startspurr = read_spurr(acct->starttime);#endif} #ifdef CONFIG_NO_HZ_COMMON/** * vtime_dyntick_start - Inform vtime about entry to idle-dynticks * * Called when idle enters in dyntick mode. The idle cputime that elapsed so far * is accumulated and the tick subsystem takes over the idle cputime accounting. */void vtime_dyntick_start(void){	vtime_account_idle(current);} /** * vtime_dyntick_stop - Inform vtime about exit from idle-dynticks * * Called when idle exits from dyntick mode. The vtime entry clocks are * fast-forward to current time so that idle accounting restarts elapsing from * now. */void vtime_dyntick_stop(void){	vtime_reset();}#endif /* CONFIG_NO_HZ_COMMON */#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ void __no_kcsan __delay(unsigned long loops){	unsigned long start; 	spin_begin();	if (tb_invalid) {		/*		 * TB is in error state and isn't ticking anymore.		 * HMI handler was unable to recover from TB error.		 * Return immediately, so that kernel won't get stuck here.		 */		spin_cpu_relax();	} else {		start = mftb();		while (mftb() - start < loops)			spin_cpu_relax();	}	spin_end();}EXPORT_SYMBOL(__delay); void __no_kcsan 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()	__this_cpu_write(irq_work_pending, 1)#define test_irq_work_pending()		__this_cpu_read(irq_work_pending)#define clear_irq_work_pending()	__this_cpu_write(irq_work_pending, 0) #endif /* 32 vs 64 bit */

Lines 1–500 of 1107.