diff options
Diffstat (limited to 'arch/powerpc/kernel/time.c')
| -rw-r--r-- | arch/powerpc/kernel/time.c | 1051 |
1 files changed, 529 insertions, 522 deletions
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 65ab9e909377..4bbeb8644d3d 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Common time routines among all ppc machines. * @@ -24,16 +25,13 @@ * * 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/sched/clock.h> +#include <linux/sched/cputime.h> #include <linux/kernel.h> #include <linux/param.h> #include <linux/string.h> @@ -53,64 +51,70 @@ #include <linux/irq.h> #include <linux/delay.h> #include <linux/irq_work.h> -#include <asm/trace.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/processor.h> #include <asm/nvram.h> #include <asm/cache.h> #include <asm/machdep.h> -#include <asm/uaccess.h> +#include <linux/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> +#include <asm/mce.h> +#include <asm/systemcfg.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 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_MAX 0x7fffffff +#define DECREMENTER_DEFAULT_MAX 0x7FFFFFFF +u64 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 void decrementer_set_mode(enum clock_event_mode mode, - 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_mode = decrementer_set_mode, - .features = CLOCK_EVT_FEAT_ONESHOT, + .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); -DEFINE_PER_CPU(u64, decrementers_next_tb); +/* + * 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 ~0ULL +DEFINE_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) @@ -126,14 +130,14 @@ 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 */ +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 __read_mostly; +static u64 boot_tb __ro_after_init; extern struct timezone sys_tz; static long timezone_offset; @@ -143,46 +147,14 @@ 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; -} +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 u64 read_spurr(u64 tb) +static inline unsigned long read_spurr(unsigned long tb) { if (cpu_has_feature(CPU_FTR_SPURR)) return mfspr(SPRN_SPURR); @@ -191,220 +163,243 @@ static u64 read_spurr(u64 tb) return tb; } -#ifdef CONFIG_PPC_SPLPAR - /* - * Scan the dispatch trace log and count up the stolen time. - * Should be called with interrupts disabled. + * Account time for a transition between system, hard irq + * or soft irq state. */ -static u64 scan_dispatch_log(u64 stop_tb) +static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct, + unsigned long now, unsigned long stime) { - 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 == vpa->dtl_idx) - return 0; - while (i < vpa->dtl_idx) { - if (dtl_consumer) - dtl_consumer(dtl, i); - dtb = dtl->timebase; - tb_delta = dtl->enqueue_to_dispatch_time + - dtl->ready_to_enqueue_time; - barrier(); - if (i + N_DISPATCH_LOG < vpa->dtl_idx) { - /* buffer has overflowed */ - i = vpa->dtl_idx - N_DISPATCH_LOG; - dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG); - continue; + 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; } - if (dtb > stop_tb) - break; - 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; + acct->utime_scaled += utime_scaled; +#endif + + return stime_scaled; } -/* - * Accumulate stolen time by scanning the dispatch trace log. - * Called on entry from user mode. - */ -void accumulate_stolen_time(void) +static unsigned long vtime_delta(struct cpu_accounting_data *acct, + unsigned long *stime_scaled, + unsigned long *steal_time) { - u64 sst, ust; - - u8 save_soft_enabled = local_paca->soft_enabled; + unsigned long now, stime; - /* 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; + WARN_ON_ONCE(!irqs_disabled()); - local_paca->soft_enabled = save_soft_enabled; -} + now = mftb(); + stime = now - acct->starttime; + acct->starttime = now; -static inline u64 calculate_stolen_time(u64 stop_tb) -{ - u64 stolen = 0; + *stime_scaled = vtime_delta_scaled(acct, now, stime); - if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) { - stolen = scan_dispatch_log(stop_tb); - get_paca()->system_time -= stolen; - } + if (IS_ENABLED(CONFIG_PPC_SPLPAR) && + firmware_has_feature(FW_FEATURE_SPLPAR)) + *steal_time = pseries_calculate_stolen_time(now); + else + *steal_time = 0; - stolen += get_paca()->stolen_time; - get_paca()->stolen_time = 0; - return stolen; + return stime; } -#else /* CONFIG_PPC_SPLPAR */ -static inline u64 calculate_stolen_time(u64 stop_tb) +static void vtime_delta_kernel(struct cpu_accounting_data *acct, + unsigned long *stime, unsigned long *stime_scaled) { - return 0; -} + unsigned long steal_time; -#endif /* CONFIG_PPC_SPLPAR */ + *stime = vtime_delta(acct, stime_scaled, &steal_time); + *stime -= min(*stime, steal_time); + acct->steal_time += steal_time; +} -/* - * 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) +void vtime_account_kernel(struct task_struct *tsk) { - u64 now, nowscaled, deltascaled; - u64 udelta, delta, user_scaled; + struct cpu_accounting_data *acct = get_accounting(tsk); + unsigned long stime, stime_scaled; - WARN_ON_ONCE(!irqs_disabled()); + vtime_delta_kernel(acct, &stime, &stime_scaled); - 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; + 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); - *stolen = calculate_stolen_time(now); +void vtime_account_idle(struct task_struct *tsk) +{ + unsigned long stime, stime_scaled, steal_time; + struct cpu_accounting_data *acct = get_accounting(tsk); - 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; + stime = vtime_delta(acct, &stime_scaled, &steal_time); + acct->idle_time += stime + steal_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; +static void vtime_account_irq_field(struct cpu_accounting_data *acct, + unsigned long *field) +{ + unsigned long stime, stime_scaled; - return delta; + vtime_delta_kernel(acct, &stime, &stime_scaled); + *field += stime; +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME + acct->stime_scaled += stime_scaled; +#endif } -void vtime_account_system(struct task_struct *tsk) +void vtime_account_softirq(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); + struct cpu_accounting_data *acct = get_accounting(tsk); + vtime_account_irq_field(acct, &acct->softirq_time); } -EXPORT_SYMBOL_GPL(vtime_account_system); -void vtime_account_idle(struct task_struct *tsk) +void vtime_account_hardirq(struct task_struct *tsk) { - u64 delta, sys_scaled, stolen; + struct cpu_accounting_data *acct = get_accounting(tsk); + vtime_account_irq_field(acct, &acct->hardirq_time); +} - delta = vtime_delta(tsk, &sys_scaled, &stolen); - account_idle_time(delta + stolen); +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 } /* - * Transfer the user time accumulated in the paca - * by the exception entry and exit code to the generic - * process user time records. + * Account the whole cputime accumulated in the paca * Must be called with interrupts disabled. - * Assumes that vtime_account_system/idle() has been called + * 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_account_user(struct task_struct *tsk) +void vtime_flush(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); + 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; } -#else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ -#define calc_cputime_factors() -#endif +/* + * 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); -void __delay(unsigned long loops) + acct->starttime = acct0->starttime; + } +} +#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ + +void __no_kcsan __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); + + 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 = get_tbl(); - while (get_tbl() - start < loops) - HMT_low(); - HMT_medium(); + start = mftb(); + while (mftb() - start < loops) + spin_cpu_relax(); } + spin_end(); } EXPORT_SYMBOL(__delay); -void udelay(unsigned long usecs) +void __no_kcsan udelay(unsigned long usecs) { __delay(tb_ticks_per_usec * usecs); } @@ -457,144 +452,181 @@ static inline void clear_irq_work_pending(void) 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 +#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 */ void arch_irq_work_raise(void) { + /* + * 64-bit code that uses irq soft-mask can just cause an immediate + * interrupt here that gets soft masked, if this is called under + * local_irq_disable(). It might be possible to prevent that happening + * by noticing interrupts are disabled and setting decrementer pending + * to be replayed when irqs are enabled. The problem there is that + * tracing can call irq_work_raise, including in code that does low + * level manipulations of irq soft-mask state (e.g., trace_hardirqs_on) + * which could get tangled up if we're messing with the same state + * here. + */ preempt_disable(); set_irq_work_pending_flag(); set_dec(1); preempt_enable(); } +static void set_dec_or_work(u64 val) +{ + set_dec(val); + /* We may have raced with new irq work */ + if (unlikely(test_irq_work_pending())) + set_dec(1); +} + #else /* CONFIG_IRQ_WORK */ #define test_irq_work_pending() 0 #define clear_irq_work_pending() +static void set_dec_or_work(u64 val) +{ + set_dec(val); +} #endif /* CONFIG_IRQ_WORK */ +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now) +{ + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + + WARN_ON_ONCE(!arch_irqs_disabled()); + WARN_ON_ONCE(mfmsr() & MSR_EE); + + if (now >= *next_tb) { + local_paca->irq_happened |= PACA_IRQ_DEC; + } else { + now = *next_tb - now; + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); + } +} +EXPORT_SYMBOL_GPL(timer_rearm_host_dec); +#endif + /* * timer_interrupt - gets called when the decrementer overflows, * with interrupts disabled. */ -void timer_interrupt(struct pt_regs * regs) +DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) { + struct clock_event_device *evt = this_cpu_ptr(&decrementers); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); 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 - * here infinitely :( + /* + * Some implementations of hotplug will get timer interrupts while + * offline, just ignore these. */ - if (!cpu_online(smp_processor_id())) { - *next_tb = ~(u64)0; + if (unlikely(!cpu_online(smp_processor_id()))) { + set_dec(decrementer_max); return; } - /* Conditionally hard-enable interrupts now that the DEC has been - * bumped to its maximum value - */ - may_hard_irq_enable(); - - __get_cpu_var(irq_stat).timer_irqs++; + /* Conditionally hard-enable interrupts. */ + if (should_hard_irq_enable(regs)) { + /* + * Ensure a positive value is written to the decrementer, or + * else some CPUs will continue to take decrementer exceptions. + * When the PPC_WATCHDOG (decrementer based) is configured, + * keep this at most 31 bits, which is about 4 seconds on most + * systems, which gives the watchdog a chance of catching timer + * interrupt hard lockups. + */ + if (IS_ENABLED(CONFIG_PPC_WATCHDOG)) + set_dec(0x7fffffff); + else + set_dec(decrementer_max); + + do_hard_irq_enable(); + } -#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC) +#if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) - do_IRQ(regs); + __do_IRQ(regs); #endif old_regs = set_irq_regs(regs); - irq_enter(); trace_timer_interrupt_entry(regs); if (test_irq_work_pending()) { clear_irq_work_pending(); + mce_run_irq_context_handlers(); irq_work_run(); } - now = get_tb_or_rtc(); + now = get_tb(); if (now >= *next_tb) { - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); + evt->event_handler(evt); + __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; - if (now <= DECREMENTER_MAX) - set_dec((int)now); + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); + __this_cpu_inc(irq_stat.timer_irqs_others); } -#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 - trace_timer_interrupt_exit(regs); - irq_exit(); set_irq_regs(old_regs); } +EXPORT_SYMBOL(timer_interrupt); -/* - * Hypervisor decrementer interrupts shouldn't occur but are sometimes - * left pending on exit from a KVM guest. We don't need to do anything - * to clear them, as they are edge-triggered. - */ -void hdec_interrupt(struct pt_regs *regs) +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +void timer_broadcast_interrupt(void) { + tick_receive_broadcast(); + __this_cpu_inc(irq_stat.broadcast_irqs_event); } +#endif #ifdef CONFIG_SUSPEND -static void generic_suspend_disable_irqs(void) +/* Overrides the weak version in kernel/power/main.c */ +void arch_suspend_disable_irqs(void) { + if (ppc_md.suspend_disable_irqs) + ppc_md.suspend_disable_irqs(); + /* Disable the decrementer, so that it doesn't interfere * with suspending. */ - set_dec(DECREMENTER_MAX); + set_dec(decrementer_max); local_irq_disable(); - set_dec(DECREMENTER_MAX); -} - -static void generic_suspend_enable_irqs(void) -{ - local_irq_enable(); -} - -/* Overrides the weak version in kernel/power/main.c */ -void arch_suspend_disable_irqs(void) -{ - if (ppc_md.suspend_disable_irqs) - ppc_md.suspend_disable_irqs(); - generic_suspend_disable_irqs(); + set_dec(decrementer_max); } /* Overrides the weak version in kernel/power/main.c */ void arch_suspend_enable_irqs(void) { - generic_suspend_enable_irqs(); + local_irq_enable(); + if (ppc_md.suspend_enable_irqs) ppc_md.suspend_enable_irqs(); } #endif +unsigned long long tb_to_ns(unsigned long long ticks) +{ + return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift; +} +EXPORT_SYMBOL_GPL(tb_to_ns); + /* * Scheduler clock - returns current time in nanosec units. * @@ -602,17 +634,53 @@ void arch_suspend_enable_irqs(void) * 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) +notrace 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; } +#ifdef CONFIG_PPC_SPLPAR +u64 get_boot_tb(void) +{ + return boot_tb; +} +#endif + +#ifdef CONFIG_PPC_PSERIES + +/* + * Running clock - attempts to give a view of time passing for a virtualised + * kernels. + * Uses the VTB register if available otherwise a next best guess. + */ +unsigned long long running_clock(void) +{ + /* + * Don't read the VTB as a host since KVM does not switch in host + * timebase into the VTB when it takes a guest off the CPU, reading the + * VTB would result in reading 'last switched out' guest VTB. + * + * Host kernels are often compiled with CONFIG_PPC_PSERIES checked, it + * would be unsafe to rely only on the #ifdef above. + */ + if (firmware_has_feature(FW_FEATURE_LPAR) && + cpu_has_feature(CPU_FTR_ARCH_207S)) + return mulhdu(get_vtb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift; + + /* + * This is a next best approximation without a VTB. + * On a host which is running bare metal there should never be any stolen + * time and on a host which doesn't do any virtualisation TB *should* equal + * VTB so it makes no difference anyway. + */ + return local_clock() - kcpustat_this_cpu->cpustat[CPUTIME_STEAL]; +} +#endif + static int __init get_freq(char *name, int cells, unsigned long *val) { struct device_node *cpu; - const unsigned int *fp; + const __be32 *fp; int found = 0; /* The cpu node should have timebase and clock frequency properties */ @@ -631,15 +699,23 @@ static int __init get_freq(char *name, int cells, unsigned long *val) return found; } -void start_cpu_decrementer(void) +static void start_cpu_decrementer(void) { -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE + unsigned int tcr; + /* 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 /* defined(CONFIG_BOOKE) || defined(CONFIG_40x) */ + tcr = mfspr(SPRN_TCR); + /* + * The watchdog may have already been enabled by u-boot. So leave + * TRC[WP] (Watchdog Period) alone. + */ + tcr &= TCR_WP_MASK; /* Clear all bits except for TCR[WP] */ + tcr |= TCR_DIE; /* Enable decrementer */ + mtspr(SPRN_TCR, tcr); +#endif } void __init generic_calibrate_decr(void) @@ -663,27 +739,25 @@ void __init generic_calibrate_decr(void) } } -int update_persistent_clock(struct timespec now) +int update_persistent_clock64(struct timespec64 now) { struct rtc_time tm; if (!ppc_md.set_rtc_time) return -ENODEV; - to_tm(now.tv_sec + 1 + timezone_offset, &tm); - tm.tm_year -= 1900; - tm.tm_mon -= 1; + rtc_time64_to_tm(now.tv_sec + 1 + timezone_offset, &tm); return ppc_md.set_rtc_time(&tm); } -static void __read_persistent_clock(struct timespec *ts) +static void __read_persistent_clock(struct timespec64 *ts) { struct rtc_time tm; static int first = 1; ts->tv_nsec = 0; - /* XXX this is a litle fragile but will work okay in the short term */ + /* XXX this is a little fragile but will work okay in the short term */ if (first) { first = 0; if (ppc_md.time_init) @@ -701,11 +775,10 @@ static void __read_persistent_clock(struct timespec *ts) } ppc_md.get_rtc_time(&tm); - ts->tv_sec = mktime(tm.tm_year+1900, tm.tm_mon+1, tm.tm_mday, - tm.tm_hour, tm.tm_min, tm.tm_sec); + ts->tv_sec = rtc_tm_to_time64(&tm); } -void read_persistent_clock(struct timespec *ts) +void read_persistent_clock64(struct timespec64 *ts) { __read_persistent_clock(ts); @@ -718,75 +791,14 @@ void read_persistent_clock(struct timespec *ts) } /* clocksource code */ -static cycle_t rtc_read(struct clocksource *cs) +static notrace u64 timebase_read(struct clocksource *cs) { - return (cycle_t)get_rtc(); -} - -static cycle_t timebase_read(struct clocksource *cs) -{ - return (cycle_t)get_tb(); -} - -void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, - struct clocksource *clock, u32 mult) -{ - u64 new_tb_to_xs, new_stamp_xsec; - u32 frac_sec; - - if (clock != &clocksource_timebase) - return; - - /* Make userspace gettimeofday spin until we're done. */ - ++vdso_data->tb_update_count; - smp_mb(); - - /* 19342813113834067 ~= 2^(20+64) / 1e9 */ - new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift); - new_stamp_xsec = (u64) wall_time->tv_nsec * XSEC_PER_SEC; - do_div(new_stamp_xsec, 1000000000); - new_stamp_xsec += (u64) wall_time->tv_sec * XSEC_PER_SEC; - - BUG_ON(wall_time->tv_nsec >= NSEC_PER_SEC); - /* this is tv_nsec / 1e9 as a 0.32 fraction */ - frac_sec = ((u64) wall_time->tv_nsec * 18446744073ULL) >> 32; - - /* - * 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 = clock->cycle_last; - vdso_data->stamp_xsec = new_stamp_xsec; - vdso_data->tb_to_xs = new_tb_to_xs; - vdso_data->wtom_clock_sec = wtm->tv_sec; - vdso_data->wtom_clock_nsec = wtm->tv_nsec; - vdso_data->stamp_xtime = *wall_time; - vdso_data->stamp_sec_fraction = frac_sec; - smp_wmb(); - ++(vdso_data->tb_update_count); -} - -void update_vsyscall_tz(void) -{ - vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; - vdso_data->tz_dsttime = sys_tz.tz_dsttime; + return (u64)get_tb(); } static void __init clocksource_init(void) { - struct clocksource *clock; - - if (__USE_RTC()) - clock = &clocksource_rtc; - else - clock = &clocksource_timebase; + struct clocksource *clock = &clocksource_timebase; if (clocksource_register_hz(clock, tb_ticks_per_sec)) { printk(KERN_ERR "clocksource: %s is already registered\n", @@ -801,16 +813,18 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { - __get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt; - set_dec(evt); + __this_cpu_write(decrementers_next_tb, get_tb() + evt); + set_dec_or_work(evt); + return 0; } -static void decrementer_set_mode(enum clock_event_mode mode, - struct clock_event_device *dev) +static int decrementer_shutdown(struct clock_event_device *dev) { - if (mode != CLOCK_EVT_MODE_ONESHOT) - decrementer_set_next_event(DECREMENTER_MAX, dev); + __this_cpu_write(decrementers_next_tb, DEC_CLOCKEVENT_STOPPED); + set_dec_or_work(decrementer_max); + + return 0; } static void register_decrementer_clockevent(int cpu) @@ -820,38 +834,111 @@ static void register_decrementer_clockevent(int cpu) *dec = decrementer_clockevent; dec->cpumask = cpumask_of(cpu); + clockevents_config_and_register(dec, ppc_tb_freq, 2, decrementer_max); + printk_once(KERN_DEBUG "clockevent: %s mult[%x] shift[%d] cpu[%d]\n", dec->name, dec->mult, dec->shift, cpu); - clockevents_register_device(dec); + /* Set values for KVM, see kvm_emulate_dec() */ + decrementer_clockevent.mult = dec->mult; + decrementer_clockevent.shift = dec->shift; } -static void __init init_decrementer_clockevent(void) +static void enable_large_decrementer(void) +{ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + if (decrementer_max <= DECREMENTER_DEFAULT_MAX) + return; + + /* + * If we're running as the hypervisor we need to enable the LD manually + * otherwise firmware should have done it for us. + */ + if (cpu_has_feature(CPU_FTR_HVMODE)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_LD); +} + +static void __init set_decrementer_max(void) { - int cpu = smp_processor_id(); + struct device_node *cpu; + u32 bits = 32; - clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4); + /* Prior to ISAv3 the decrementer is always 32 bit */ + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return; - decrementer_clockevent.max_delta_ns = - clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent); - decrementer_clockevent.min_delta_ns = - clockevent_delta2ns(2, &decrementer_clockevent); + cpu = of_find_node_by_type(NULL, "cpu"); - register_decrementer_clockevent(cpu); + if (of_property_read_u32(cpu, "ibm,dec-bits", &bits) == 0) { + if (bits > 64 || bits < 32) { + pr_warn("time_init: firmware supplied invalid ibm,dec-bits"); + bits = 32; + } + + /* calculate the signed maximum given this many bits */ + decrementer_max = (1ul << (bits - 1)) - 1; + } + + of_node_put(cpu); + + pr_info("time_init: %u bit decrementer (max: %llx)\n", + bits, decrementer_max); +} + +static void __init init_decrementer_clockevent(void) +{ + register_decrementer_clockevent(smp_processor_id()); } void secondary_cpu_time_init(void) { + /* Enable and test the large decrementer for this cpu */ + enable_large_decrementer(); + /* Start the decrementer on CPUs that have manual control * such as BookE */ start_cpu_decrementer(); - /* FIME: Should make unrelatred change to move snapshot_timebase + /* FIME: Should make unrelated change to move snapshot_timebase * call here ! */ register_decrementer_clockevent(smp_processor_id()); } +/* + * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit + * result. + */ +static __init void div128_by_32(u64 dividend_high, u64 dividend_low, + unsigned int divisor, struct div_result *dr) +{ + unsigned long a, b, c, d; + unsigned long w, x, y, z; + u64 ra, rb, rc; + + a = dividend_high >> 32; + b = dividend_high & 0xffffffff; + c = dividend_low >> 32; + d = dividend_low & 0xffffffff; + + w = a / divisor; + ra = ((u64)(a - (w * divisor)) << 32) + b; + + rb = ((u64)do_div(ra, divisor) << 32) + c; + x = ra; + + rc = ((u64)do_div(rb, divisor) << 32) + d; + y = rb; + + do_div(rc, divisor); + z = rc; + + dr->result_high = ((u64)w << 32) + x; + dr->result_low = ((u64)y << 32) + z; +} + /* This function is only called on the boot processor */ void __init time_init(void) { @@ -859,23 +946,20 @@ void __init time_init(void) u64 scale; unsigned shift; - if (__USE_RTC()) { - /* 601 processor: dec counts down by 128 every 128ns */ - ppc_tb_freq = 1000000000; - } else { - /* Normal PowerPC with timebase register */ + /* Normal PowerPC with timebase register */ + if (ppc_md.calibrate_decr) ppc_md.calibrate_decr(); - printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n", - ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); - printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", - ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); - } + else + generic_calibrate_decr(); + + printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n", + ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); + printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", + ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); tb_ticks_per_jiffy = ppc_tb_freq / HZ; tb_ticks_per_sec = ppc_tb_freq; tb_ticks_per_usec = ppc_tb_freq / 1000000; - calc_cputime_factors(); - setup_cputime_one_jiffy(); /* * Compute scale factor for sched_clock. @@ -896,7 +980,7 @@ void __init time_init(void) tb_to_ns_scale = scale; tb_to_ns_shift = shift; /* Save the current timebase to pretty up CONFIG_PRINTK_TIME */ - boot_tb = get_tb_or_rtc(); + boot_tb = get_tb(); /* If platform provided a timezone (pmac), we correct the time */ if (timezone_offset) { @@ -904,8 +988,14 @@ void __init time_init(void) sys_tz.tz_dsttime = 0; } - vdso_data->tb_update_count = 0; - vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; + vdso_k_arch_data->tb_ticks_per_sec = tb_ticks_per_sec; +#ifdef CONFIG_PPC64_PROC_SYSTEMCFG + systemcfg->tb_ticks_per_sec = tb_ticks_per_sec; +#endif + + /* initialise and enable the large decrementer (if we have one) */ + set_decrementer_max(); + enable_large_decrementer(); /* Start the decrementer on CPUs that have manual control * such as BookE @@ -916,129 +1006,43 @@ void __init time_init(void) clocksource_init(); init_decrementer_clockevent(); -} + tick_setup_hrtimer_broadcast(); + of_clk_init(NULL); + enable_sched_clock_irqtime(); +} -#define FEBRUARY 2 -#define STARTOFTIME 1970 -#define SECDAY 86400L -#define SECYR (SECDAY * 365) -#define leapyear(year) ((year) % 4 == 0 && \ - ((year) % 100 != 0 || (year) % 400 == 0)) -#define days_in_year(a) (leapyear(a) ? 366 : 365) -#define days_in_month(a) (month_days[(a) - 1]) - -static int month_days[12] = { - 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 -}; - -/* - * This only works for the Gregorian calendar - i.e. after 1752 (in the UK) - */ -void GregorianDay(struct rtc_time * tm) +/* We don't need to calibrate delay, we use the CPU timebase for that */ +void calibrate_delay(void) { - int leapsToDate; - int lastYear; - int day; - int MonthOffset[] = { 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334 }; - - lastYear = tm->tm_year - 1; - - /* - * Number of leap corrections to apply up to end of last year - */ - leapsToDate = lastYear / 4 - lastYear / 100 + lastYear / 400; - - /* - * This year is a leap year if it is divisible by 4 except when it is - * divisible by 100 unless it is divisible by 400 - * - * e.g. 1904 was a leap year, 1900 was not, 1996 is, and 2000 was + /* Some generic code (such as spinlock debug) use loops_per_jiffy + * as the number of __delay(1) in a jiffy, so make it so */ - day = tm->tm_mon > 2 && leapyear(tm->tm_year); - - day += lastYear*365 + leapsToDate + MonthOffset[tm->tm_mon-1] + - tm->tm_mday; - - tm->tm_wday = day % 7; + loops_per_jiffy = tb_ticks_per_jiffy; } -void to_tm(int tim, struct rtc_time * tm) +#if IS_ENABLED(CONFIG_RTC_DRV_GENERIC) +static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm) { - register int i; - register long hms, day; - - day = tim / SECDAY; - hms = tim % SECDAY; - - /* Hours, minutes, seconds are easy */ - tm->tm_hour = hms / 3600; - tm->tm_min = (hms % 3600) / 60; - tm->tm_sec = (hms % 3600) % 60; - - /* Number of years in days */ - for (i = STARTOFTIME; day >= days_in_year(i); i++) - day -= days_in_year(i); - tm->tm_year = i; - - /* Number of months in days left */ - if (leapyear(tm->tm_year)) - days_in_month(FEBRUARY) = 29; - for (i = 1; day >= days_in_month(i); i++) - day -= days_in_month(i); - days_in_month(FEBRUARY) = 28; - tm->tm_mon = i; - - /* Days are what is left over (+1) from all that. */ - tm->tm_mday = day + 1; - - /* - * Determine the day of week - */ - GregorianDay(tm); + ppc_md.get_rtc_time(tm); + return 0; } -/* - * Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit - * result. - */ -void div128_by_32(u64 dividend_high, u64 dividend_low, - unsigned divisor, struct div_result *dr) +static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm) { - unsigned long a, b, c, d; - unsigned long w, x, y, z; - u64 ra, rb, rc; - - a = dividend_high >> 32; - b = dividend_high & 0xffffffff; - c = dividend_low >> 32; - d = dividend_low & 0xffffffff; - - w = a / divisor; - ra = ((u64)(a - (w * divisor)) << 32) + b; - - rb = ((u64) do_div(ra, divisor) << 32) + c; - x = ra; - - rc = ((u64) do_div(rb, divisor) << 32) + d; - y = rb; - - do_div(rc, divisor); - z = rc; + if (!ppc_md.set_rtc_time) + return -EOPNOTSUPP; - dr->result_high = ((u64)w << 32) + x; - dr->result_low = ((u64)y << 32) + z; + if (ppc_md.set_rtc_time(tm) < 0) + return -EOPNOTSUPP; + return 0; } -/* We don't need to calibrate delay, we use the CPU timebase for that */ -void calibrate_delay(void) -{ - /* Some generic code (such as spinlock debug) use loops_per_jiffy - * as the number of __delay(1) in a jiffy, so make it so - */ - loops_per_jiffy = tb_ticks_per_jiffy; -} +static const struct rtc_class_ops rtc_generic_ops = { + .read_time = rtc_generic_get_time, + .set_time = rtc_generic_set_time, +}; static int __init rtc_init(void) { @@ -1047,9 +1051,12 @@ static int __init rtc_init(void) if (!ppc_md.get_rtc_time) return -ENODEV; - pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); + pdev = platform_device_register_data(NULL, "rtc-generic", -1, + &rtc_generic_ops, + sizeof(rtc_generic_ops)); - return PTR_RET(pdev); + return PTR_ERR_OR_ZERO(pdev); } -module_init(rtc_init); +device_initcall(rtc_init); +#endif |