diff options
Diffstat (limited to 'arch/powerpc/kernel/time.c')
| -rw-r--r-- | arch/powerpc/kernel/time.c | 839 |
1 files changed, 315 insertions, 524 deletions
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index fe6f3a285455..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. * @@ -24,17 +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> @@ -43,7 +40,6 @@ #include <linux/timex.h> #include <linux/kernel_stat.h> #include <linux/time.h> -#include <linux/clockchips.h> #include <linux/init.h> #include <linux/profile.h> #include <linux/cpu.h> @@ -55,40 +51,31 @@ #include <linux/irq.h> #include <linux/delay.h> #include <linux/irq_work.h> -#include <linux/clk-provider.h> +#include <linux/of_clk.h> #include <linux/suspend.h> -#include <linux/rtc.h> -#include <linux/sched/cputime.h> #include <linux/processor.h> -#include <asm/trace.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/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/asm-prototypes.h> +#include <asm/mce.h> +#include <asm/systemcfg.h> /* powerpc clocksource/clockevent code */ #include <linux/clockchips.h> -#include <linux/timekeeper_internal.h> - -static u64 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 u64 timebase_read(struct clocksource *); static struct clocksource clocksource_timebase = { @@ -97,10 +84,12 @@ static struct clocksource clocksource_timebase = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, .mask = CLOCKSOURCE_MASK(64), .read = timebase_read, + .vdso_clock_mode = VDSO_CLOCKMODE_ARCHTIMER, }; #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); @@ -111,6 +100,7 @@ struct clock_event_device decrementer_clockevent = { .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 | @@ -118,7 +108,13 @@ struct clock_event_device decrementer_clockevent = { }; 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) @@ -134,14 +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; @@ -151,37 +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 -/* - * Factor for converting from cputime_t (timebase ticks) to - * microseconds. This is stored as 0.64 fixed-point binary fraction. - */ -u64 __cputime_usec_factor; -EXPORT_SYMBOL(__cputime_usec_factor); - -#ifdef CONFIG_PPC_SPLPAR -void (*dtl_consumer)(struct dtl_entry *, u64); -#endif - -#ifdef CONFIG_PPC64 -#define get_accounting(tsk) (&get_paca()->accounting) -#else -#define get_accounting(tsk) (&task_thread_info(tsk)->accounting) -#endif - -static void calc_cputime_factors(void) -{ - struct div_result res; - - div128_by_32(1000000, 0, tb_ticks_per_sec, &res); - __cputime_usec_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 unsigned long read_spurr(unsigned long tb) +static inline unsigned long read_spurr(unsigned long tb) { if (cpu_has_feature(CPU_FTR_SPURR)) return mfspr(SPRN_SPURR); @@ -190,120 +163,21 @@ static unsigned long read_spurr(unsigned long tb) 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; - struct cpu_accounting_data *acct = &local_paca->accounting; - - /* 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(acct->starttime_user); - ust = scan_dispatch_log(acct->starttime); - acct->stime -= sst; - acct->utime -= ust; - acct->steal_time += ust + sst; - - local_paca->soft_enabled = save_soft_enabled; -} - -static inline u64 calculate_stolen_time(u64 stop_tb) -{ - if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) - return scan_dispatch_log(stop_tb); - - return 0; -} - -#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 unsigned long vtime_delta(struct task_struct *tsk, - unsigned long *stime_scaled, - unsigned long *steal_time) +static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct, + unsigned long now, unsigned long stime) { - unsigned long now, nowscaled, deltascaled; - unsigned long stime; + unsigned long stime_scaled = 0; +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME + unsigned long nowscaled, deltascaled; unsigned long utime, utime_scaled; - struct cpu_accounting_data *acct = get_accounting(tsk); - WARN_ON_ONCE(!irqs_disabled()); - - now = mftb(); nowscaled = read_spurr(now); - stime = now - acct->starttime; - acct->starttime = now; deltascaled = nowscaled - acct->startspurr; acct->startspurr = nowscaled; - - *steal_time = calculate_stolen_time(now); - utime = acct->utime - acct->utime_sspurr; acct->utime_sspurr = acct->utime; @@ -317,60 +191,128 @@ static unsigned long vtime_delta(struct task_struct *tsk, * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - *stime_scaled = stime; + stime_scaled = stime; utime_scaled = utime; if (deltascaled != stime + utime) { if (utime) { - *stime_scaled = deltascaled * stime / (stime + utime); - utime_scaled = deltascaled - *stime_scaled; + stime_scaled = deltascaled * stime / (stime + utime); + utime_scaled = deltascaled - stime_scaled; } else { - *stime_scaled = deltascaled; + stime_scaled = deltascaled; } } acct->utime_scaled += utime_scaled; +#endif - return stime; + return stime_scaled; } -void vtime_account_system(struct task_struct *tsk) +static unsigned long vtime_delta(struct cpu_accounting_data *acct, + unsigned long *stime_scaled, + unsigned long *steal_time) { - unsigned long stime, stime_scaled, steal_time; - struct cpu_accounting_data *acct = get_accounting(tsk); + 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; +} - stime = vtime_delta(tsk, &stime_scaled, &steal_time); +static void vtime_delta_kernel(struct cpu_accounting_data *acct, + unsigned long *stime, unsigned long *stime_scaled) +{ + unsigned long steal_time; - stime -= min(stime, 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; - if ((tsk->flags & PF_VCPU) && !irq_count()) { + 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 { - if (hardirq_count()) - acct->hardirq_time += stime; - else if (in_serving_softirq()) - acct->softirq_time += stime; - else - acct->stime += stime; - + acct->stime += stime; +#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME acct->stime_scaled += stime_scaled; +#endif } } -EXPORT_SYMBOL_GPL(vtime_account_system); +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(tsk, &stime_scaled, &steal_time); + 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_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. */ @@ -381,14 +323,13 @@ void vtime_flush(struct task_struct *tsk) if (acct->utime) account_user_time(tsk, cputime_to_nsecs(acct->utime)); - if (acct->utime_scaled) - tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled); - if (acct->gtime) account_guest_time(tsk, cputime_to_nsecs(acct->gtime)); - if (acct->steal_time) + 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)); @@ -396,8 +337,6 @@ void vtime_flush(struct task_struct *tsk) if (acct->stime) account_system_index_time(tsk, cputime_to_nsecs(acct->stime), CPUTIME_SYSTEM); - if (acct->stime_scaled) - tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled); if (acct->hardirq_time) account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time), @@ -406,62 +345,61 @@ void vtime_flush(struct task_struct *tsk) account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time), CPUTIME_SOFTIRQ); + vtime_flush_scaled(tsk, acct); + acct->utime = 0; - acct->utime_scaled = 0; - acct->utime_sspurr = 0; acct->gtime = 0; - acct->steal_time = 0; acct->idle_time = 0; acct->stime = 0; - acct->stime_scaled = 0; acct->hardirq_time = 0; acct->softirq_time = 0; } -#ifdef CONFIG_PPC32 /* * 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 arch_vtime_task_switch(struct task_struct *prev) +void vtime_task_switch(struct task_struct *prev) { - struct cpu_accounting_data *acct = get_accounting(current); + if (is_idle_task(prev)) + vtime_account_idle(prev); + else + vtime_account_kernel(prev); - acct->starttime = get_accounting(prev)->starttime; - acct->startspurr = get_accounting(prev)->startspurr; -} -#endif /* CONFIG_PPC32 */ + vtime_flush(prev); -#else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ -#define calc_cputime_factors() -#endif + 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; spin_begin(); - if (__USE_RTC()) { - start = get_rtcl(); - do { - /* the RTCL register wraps at 1000000000 */ - diff = get_rtcl() - start; - if (diff < 0) - diff += 1000000000; - spin_cpu_relax(); - } while (diff < loops); + 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) + 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); } @@ -522,117 +460,148 @@ DEFINE_PER_CPU(u8, irq_work_pending); 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 */ -static void __timer_interrupt(void) +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +void timer_rearm_host_dec(u64 now) { - struct pt_regs *regs = get_irq_regs(); u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); - struct clock_event_device *evt = this_cpu_ptr(&decrementers); - u64 now; - trace_timer_interrupt_entry(regs); + WARN_ON_ONCE(!arch_irqs_disabled()); + WARN_ON_ONCE(mfmsr() & MSR_EE); - if (test_irq_work_pending()) { - clear_irq_work_pending(); - irq_work_run(); - } - - now = get_tb_or_rtc(); if (now >= *next_tb) { - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); - __this_cpu_inc(irq_stat.timer_irqs_event); + local_paca->irq_happened |= PACA_IRQ_DEC; } else { now = *next_tb - now; - if (now <= decrementer_max) - set_dec(now); - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); - __this_cpu_inc(irq_stat.timer_irqs_others); + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); } - -#ifdef CONFIG_PPC64 - /* collect purr register values often, for accurate calculations */ - if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array); - cu->current_tb = mfspr(SPRN_PURR); - } -#endif - - trace_timer_interrupt_exit(regs); } +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 pt_regs *old_regs; + struct clock_event_device *evt = this_cpu_ptr(&decrementers); u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + struct pt_regs *old_regs; + 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(); + /* 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_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(); - __timer_interrupt(); - irq_exit(); + 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(); + if (now >= *next_tb) { + evt->event_handler(evt); + __this_cpu_inc(irq_stat.timer_irqs_event); + } else { + now = *next_tb - now; + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); + __this_cpu_inc(irq_stat.timer_irqs_others); + } + + trace_timer_interrupt_exit(regs); + 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. */ @@ -642,23 +611,11 @@ static void generic_suspend_disable_irqs(void) 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(); -} - /* 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(); } @@ -679,11 +636,15 @@ EXPORT_SYMBOL_GPL(tb_to_ns); */ 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 @@ -740,7 +701,7 @@ static int __init get_freq(char *name, int cells, unsigned long *val) static void start_cpu_decrementer(void) { -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) +#ifdef CONFIG_BOOKE unsigned int tcr; /* Clear any pending timer interrupts */ @@ -778,27 +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) @@ -816,11 +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); @@ -833,111 +791,14 @@ void read_persistent_clock(struct timespec *ts) } /* clocksource code */ -static notrace u64 rtc_read(struct clocksource *cs) -{ - return (u64)get_rtc(); -} - static notrace u64 timebase_read(struct clocksource *cs) { return (u64)get_tb(); } - -void update_vsyscall(struct timekeeper *tk) -{ - struct timespec xt; - struct clocksource *clock = tk->tkr_mono.clock; - u32 mult = tk->tkr_mono.mult; - u32 shift = tk->tkr_mono.shift; - u64 cycle_last = tk->tkr_mono.cycle_last; - u64 new_tb_to_xs, new_stamp_xsec; - u64 frac_sec; - - if (clock != &clocksource_timebase) - return; - - xt.tv_sec = tk->xtime_sec; - xt.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); - - /* Make userspace gettimeofday spin until we're done. */ - ++vdso_data->tb_update_count; - smp_mb(); - - /* - * This computes ((2^20 / 1e9) * mult) >> shift as a - * 0.64 fixed-point fraction. - * The computation in the else clause below won't overflow - * (as long as the timebase frequency is >= 1.049 MHz) - * but loses precision because we lose the low bits of the constant - * in the shift. Note that 19342813113834067 ~= 2^(20+64) / 1e9. - * For a shift of 24 the error is about 0.5e-9, or about 0.5ns - * over a second. (Shift values are usually 22, 23 or 24.) - * For high frequency clocks such as the 512MHz timebase clock - * on POWER[6789], the mult value is small (e.g. 32768000) - * and so we can shift the constant by 16 initially - * (295147905179 ~= 2^(20+64-16) / 1e9) and then do the - * remaining shifts after the multiplication, which gives a - * more accurate result (e.g. with mult = 32768000, shift = 24, - * the error is only about 1.2e-12, or 0.7ns over 10 minutes). - */ - if (mult <= 62500000 && clock->shift >= 16) - new_tb_to_xs = ((u64) mult * 295147905179ULL) >> (clock->shift - 16); - else - new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift); - - /* - * Compute the fractional second in units of 2^-32 seconds. - * The fractional second is tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift - * in nanoseconds, so multiplying that by 2^32 / 1e9 gives - * it in units of 2^-32 seconds. - * We assume shift <= 32 because clocks_calc_mult_shift() - * generates shift values in the range 0 - 32. - */ - frac_sec = tk->tkr_mono.xtime_nsec << (32 - shift); - do_div(frac_sec, NSEC_PER_SEC); - - /* - * Work out new stamp_xsec value for any legacy users of systemcfg. - * stamp_xsec is in units of 2^-20 seconds. - */ - new_stamp_xsec = frac_sec >> 12; - new_stamp_xsec += tk->xtime_sec * XSEC_PER_SEC; - - /* - * 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. - */ - vdso_data->tb_orig_stamp = cycle_last; - vdso_data->stamp_xsec = new_stamp_xsec; - vdso_data->tb_to_xs = new_tb_to_xs; - vdso_data->wtom_clock_sec = tk->wall_to_monotonic.tv_sec; - vdso_data->wtom_clock_nsec = tk->wall_to_monotonic.tv_nsec; - vdso_data->stamp_xtime = xt; - 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; -} - 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", @@ -952,29 +813,18 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { - __this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt); - set_dec(evt); - - /* We may have raced with new irq work */ - if (test_irq_work_pending()) - set_dec(1); + __this_cpu_write(decrementers_next_tb, get_tb() + evt); + set_dec_or_work(evt); return 0; } static int decrementer_shutdown(struct clock_event_device *dev) { - decrementer_set_next_event(decrementer_max, dev); - return 0; -} - -/* Interrupt handler for the timer broadcast IPI */ -void tick_broadcast_ipi_handler(void) -{ - u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + __this_cpu_write(decrementers_next_tb, DEC_CLOCKEVENT_STOPPED); + set_dec_or_work(decrementer_max); - *next_tb = get_tb_or_rtc(); - __timer_interrupt(); + return 0; } static void register_decrementer_clockevent(int cpu) @@ -984,10 +834,14 @@ 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 enable_large_decrementer(void) @@ -1035,18 +889,7 @@ static void __init set_decrementer_max(void) static void __init init_decrementer_clockevent(void) { - int cpu = smp_processor_id(); - - clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4); - - decrementer_clockevent.max_delta_ns = - clockevent_delta2ns(decrementer_max, &decrementer_clockevent); - decrementer_clockevent.max_delta_ticks = decrementer_max; - decrementer_clockevent.min_delta_ns = - clockevent_delta2ns(2, &decrementer_clockevent); - decrementer_clockevent.min_delta_ticks = 2; - - register_decrementer_clockevent(cpu); + register_decrementer_clockevent(smp_processor_id()); } void secondary_cpu_time_init(void) @@ -1059,11 +902,43 @@ void secondary_cpu_time_init(void) */ 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) { @@ -1071,22 +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(); /* * Compute scale factor for sched_clock. @@ -1107,7 +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) { @@ -1115,8 +988,10 @@ 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(); @@ -1133,92 +1008,8 @@ void __init time_init(void) init_decrementer_clockevent(); tick_setup_hrtimer_broadcast(); -#ifdef CONFIG_COMMON_CLK of_clk_init(NULL); -#endif -} - - -#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 -}; - -void to_tm(int tim, 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; - - /* - * No-one uses the day of the week. - */ - tm->tm_wday = -1; -} -EXPORT_SYMBOL(to_tm); - -/* - * 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) -{ - 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; - + enable_sched_clock_irqtime(); } /* We don't need to calibrate delay, we use the CPU timebase for that */ @@ -1234,7 +1025,7 @@ void calibrate_delay(void) static int rtc_generic_get_time(struct device *dev, struct rtc_time *tm) { ppc_md.get_rtc_time(tm); - return rtc_valid_tm(tm); + return 0; } static int rtc_generic_set_time(struct device *dev, struct rtc_time *tm) |