diff options
Diffstat (limited to 'arch/powerpc/kernel/time.c')
| -rw-r--r-- | arch/powerpc/kernel/time.c | 320 |
1 files changed, 137 insertions, 183 deletions
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 567dd7c3ac2..9fff9cdcc51 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -17,8 +17,7 @@ * * TODO (not necessarily in this file): * - improve precision and reproducibility of timebase frequency - * measurement at boot time. (for iSeries, we calibrate the timebase - * against the Titan chip's clock.) + * 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. @@ -43,6 +42,7 @@ #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> @@ -70,15 +70,11 @@ #include <asm/vdso_datapage.h> #include <asm/firmware.h> #include <asm/cputime.h> -#ifdef CONFIG_PPC_ISERIES -#include <asm/iseries/it_lp_queue.h> -#include <asm/iseries/hv_call_xm.h> -#endif /* powerpc clocksource/clockevent code */ #include <linux/clockchips.h> -#include <linux/clocksource.h> +#include <linux/timekeeper_internal.h> static cycle_t rtc_read(struct clocksource *); static struct clocksource clocksource_rtc = { @@ -105,26 +101,19 @@ static int decrementer_set_next_event(unsigned long evt, static void decrementer_set_mode(enum clock_event_mode mode, struct clock_event_device *dev); -static struct clock_event_device decrementer_clockevent = { +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, + .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP, }; +EXPORT_SYMBOL(decrementer_clockevent); DEFINE_PER_CPU(u64, decrementers_next_tb); static DEFINE_PER_CPU(struct clock_event_device, decrementers); -#ifdef CONFIG_PPC_ISERIES -static unsigned long __initdata iSeries_recal_titan; -static signed long __initdata iSeries_recal_tb; - -/* Forward declaration is only needed for iSereis compiles */ -static void __init clocksource_init(void); -#endif - #define XSEC_PER_SEC (1024*1024) #ifdef CONFIG_PPC64 @@ -155,7 +144,7 @@ EXPORT_SYMBOL_GPL(ppc_proc_freq); unsigned long ppc_tb_freq; EXPORT_SYMBOL_GPL(ppc_tb_freq); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING +#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). @@ -222,23 +211,23 @@ static u64 scan_dispatch_log(u64 stop_tb) if (!dtl) return 0; - if (i == vpa->dtl_idx) + if (i == be64_to_cpu(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; + 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 < vpa->dtl_idx) { + if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) { /* buffer has overflowed */ - i = vpa->dtl_idx - N_DISPATCH_LOG; + 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; @@ -259,7 +248,6 @@ void accumulate_stolen_time(void) u64 sst, ust; u8 save_soft_enabled = local_paca->soft_enabled; - u8 save_hard_enabled = local_paca->hard_enabled; /* We are called early in the exception entry, before * soft/hard_enabled are sync'ed to the expected state @@ -268,7 +256,6 @@ void accumulate_stolen_time(void) * complain */ local_paca->soft_enabled = 0; - local_paca->hard_enabled = 0; sst = scan_dispatch_log(local_paca->starttime_user); ust = scan_dispatch_log(local_paca->starttime); @@ -277,14 +264,13 @@ void accumulate_stolen_time(void) local_paca->stolen_time += ust + sst; local_paca->soft_enabled = save_soft_enabled; - local_paca->hard_enabled = save_hard_enabled; } static inline u64 calculate_stolen_time(u64 stop_tb) { u64 stolen = 0; - if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) { + if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) { stolen = scan_dispatch_log(stop_tb); get_paca()->system_time -= stolen; } @@ -306,13 +292,14 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * Account time for a transition between system, hard irq * or soft irq state. */ -void account_system_vtime(struct task_struct *tsk) +static u64 vtime_delta(struct task_struct *tsk, + u64 *sys_scaled, u64 *stolen) { - u64 now, nowscaled, delta, deltascaled; - unsigned long flags; - u64 stolen, udelta, sys_scaled, user_scaled; + u64 now, nowscaled, deltascaled; + u64 udelta, delta, user_scaled; + + WARN_ON_ONCE(!irqs_disabled()); - local_irq_save(flags); now = mftb(); nowscaled = read_spurr(now); get_paca()->system_time += now - get_paca()->starttime; @@ -320,7 +307,7 @@ void account_system_vtime(struct task_struct *tsk) deltascaled = nowscaled - get_paca()->startspurr; get_paca()->startspurr = nowscaled; - stolen = calculate_stolen_time(now); + *stolen = calculate_stolen_time(now); delta = get_paca()->system_time; get_paca()->system_time = 0; @@ -337,39 +324,50 @@ void account_system_vtime(struct task_struct *tsk) * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - sys_scaled = delta; + *sys_scaled = delta; user_scaled = udelta; if (deltascaled != delta + udelta) { if (udelta) { - sys_scaled = deltascaled * delta / (delta + udelta); - user_scaled = deltascaled - sys_scaled; + *sys_scaled = deltascaled * delta / (delta + udelta); + user_scaled = deltascaled - *sys_scaled; } else { - sys_scaled = deltascaled; + *sys_scaled = deltascaled; } } get_paca()->user_time_scaled += user_scaled; - if (in_interrupt() || idle_task(smp_processor_id()) != tsk) { - account_system_time(tsk, 0, delta, sys_scaled); - if (stolen) - account_steal_time(stolen); - } else { - account_idle_time(delta + stolen); - } - local_irq_restore(flags); + 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); } -EXPORT_SYMBOL_GPL(account_system_vtime); /* - * Transfer the user and system times accumulated in the paca - * by the exception entry and exit code to the generic process - * user and system time records. + * 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 account_system_vtime() has been called recently - * (i.e. since the last entry from usermode) so that + * 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 account_process_tick(struct task_struct *tsk, int user_tick) +void vtime_account_user(struct task_struct *tsk) { cputime_t utime, utimescaled; @@ -381,7 +379,7 @@ void account_process_tick(struct task_struct *tsk, int user_tick) account_user_time(tsk, utime, utimescaled); } -#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */ +#else /* ! CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #define calc_cputime_factors() #endif @@ -426,74 +424,6 @@ unsigned long profile_pc(struct pt_regs *regs) EXPORT_SYMBOL(profile_pc); #endif -#ifdef CONFIG_PPC_ISERIES - -/* - * This function recalibrates the timebase based on the 49-bit time-of-day - * value in the Titan chip. The Titan is much more accurate than the value - * returned by the service processor for the timebase frequency. - */ - -static int __init iSeries_tb_recal(void) -{ - unsigned long titan, tb; - - /* Make sure we only run on iSeries */ - if (!firmware_has_feature(FW_FEATURE_ISERIES)) - return -ENODEV; - - tb = get_tb(); - titan = HvCallXm_loadTod(); - if ( iSeries_recal_titan ) { - unsigned long tb_ticks = tb - iSeries_recal_tb; - unsigned long titan_usec = (titan - iSeries_recal_titan) >> 12; - unsigned long new_tb_ticks_per_sec = (tb_ticks * USEC_PER_SEC)/titan_usec; - unsigned long new_tb_ticks_per_jiffy = - DIV_ROUND_CLOSEST(new_tb_ticks_per_sec, HZ); - long tick_diff = new_tb_ticks_per_jiffy - tb_ticks_per_jiffy; - char sign = '+'; - /* make sure tb_ticks_per_sec and tb_ticks_per_jiffy are consistent */ - new_tb_ticks_per_sec = new_tb_ticks_per_jiffy * HZ; - - if ( tick_diff < 0 ) { - tick_diff = -tick_diff; - sign = '-'; - } - if ( tick_diff ) { - if ( tick_diff < tb_ticks_per_jiffy/25 ) { - printk( "Titan recalibrate: new tb_ticks_per_jiffy = %lu (%c%ld)\n", - new_tb_ticks_per_jiffy, sign, tick_diff ); - tb_ticks_per_jiffy = new_tb_ticks_per_jiffy; - tb_ticks_per_sec = new_tb_ticks_per_sec; - calc_cputime_factors(); - vdso_data->tb_ticks_per_sec = tb_ticks_per_sec; - setup_cputime_one_jiffy(); - } - else { - printk( "Titan recalibrate: FAILED (difference > 4 percent)\n" - " new tb_ticks_per_jiffy = %lu\n" - " old tb_ticks_per_jiffy = %lu\n", - new_tb_ticks_per_jiffy, tb_ticks_per_jiffy ); - } - } - } - iSeries_recal_titan = titan; - iSeries_recal_tb = tb; - - /* Called here as now we know accurate values for the timebase */ - clocksource_init(); - return 0; -} -late_initcall(iSeries_tb_recal); - -/* Called from platform early init */ -void __init iSeries_time_init_early(void) -{ - iSeries_recal_tb = get_tb(); - iSeries_recal_titan = HvCallXm_loadTod(); -} -#endif /* CONFIG_PPC_ISERIES */ - #ifdef CONFIG_IRQ_WORK /* @@ -549,15 +479,46 @@ void arch_irq_work_raise(void) #endif /* CONFIG_IRQ_WORK */ -/* - * For iSeries shared processors, we have to let the hypervisor - * set the hardware decrementer. We set a virtual decrementer - * in the lppaca and call the hypervisor if the virtual - * decrementer is less than the current value in the hardware - * decrementer. (almost always the new decrementer value will - * be greater than the current hardware decementer so the hypervisor - * call will not be needed) - */ +void __timer_interrupt(void) +{ + struct pt_regs *regs = get_irq_regs(); + u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + struct clock_event_device *evt = &__get_cpu_var(decrementers); + u64 now; + + trace_timer_interrupt_entry(regs); + + 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); + __get_cpu_var(irq_stat).timer_irqs_event++; + } else { + now = *next_tb - now; + if (now <= DECREMENTER_MAX) + set_dec((int)now); + /* We may have raced with new irq work */ + if (test_irq_work_pending()) + set_dec(1); + __get_cpu_var(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); +} /* * timer_interrupt - gets called when the decrementer overflows, @@ -567,7 +528,6 @@ 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); /* Ensure a positive value is written to the decrementer, or else * some CPUs will continue to take decrementer exceptions. @@ -575,16 +535,23 @@ void timer_interrupt(struct pt_regs * regs) set_dec(DECREMENTER_MAX); /* Some implementations of hotplug will get timer interrupts while - * offline, just ignore these + * 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 :( */ - if (!cpu_online(smp_processor_id())) + if (!cpu_online(smp_processor_id())) { + *next_tb = ~(u64)0; return; + } - trace_timer_interrupt_entry(regs); + /* 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++; -#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); #endif @@ -592,37 +559,18 @@ void timer_interrupt(struct pt_regs * regs) old_regs = set_irq_regs(regs); irq_enter(); - if (test_irq_work_pending()) { - clear_irq_work_pending(); - irq_work_run(); - } - -#ifdef CONFIG_PPC_ISERIES - if (firmware_has_feature(FW_FEATURE_ISERIES)) - get_lppaca()->int_dword.fields.decr_int = 0; -#endif - - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); - -#ifdef CONFIG_PPC_ISERIES - if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending()) - process_hvlpevents(); -#endif - -#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 - + __timer_interrupt(); irq_exit(); set_irq_regs(old_regs); +} - trace_timer_interrupt_exit(regs); +/* + * 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_SUSPEND @@ -676,7 +624,7 @@ unsigned long long sched_clock(void) 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 */ @@ -695,7 +643,6 @@ static int __init get_freq(char *name, int cells, unsigned long *val) return found; } -/* should become __cpuinit when secondary_cpu_time_init also is */ void start_cpu_decrementer(void) { #if defined(CONFIG_BOOKE) || defined(CONFIG_40x) @@ -733,7 +680,7 @@ int update_persistent_clock(struct timespec now) struct rtc_time tm; if (!ppc_md.set_rtc_time) - return 0; + return -ENODEV; to_tm(now.tv_sec + 1 + timezone_offset, &tm); tm.tm_year -= 1900; @@ -793,7 +740,7 @@ static cycle_t timebase_read(struct clocksource *cs) return (cycle_t)get_tb(); } -void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, +void update_vsyscall_old(struct timespec *wall_time, struct timespec *wtm, struct clocksource *clock, u32 mult) { u64 new_tb_to_xs, new_stamp_xsec; @@ -840,13 +787,8 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm, void update_vsyscall_tz(void) { - /* Make userspace gettimeofday spin until we're done. */ - ++vdso_data->tb_update_count; - smp_mb(); vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; vdso_data->tz_dsttime = sys_tz.tz_dsttime; - smp_mb(); - ++vdso_data->tb_update_count; } static void __init clocksource_init(void) @@ -873,6 +815,11 @@ static int decrementer_set_next_event(unsigned long evt, { __get_cpu_var(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); + return 0; } @@ -883,6 +830,15 @@ static void decrementer_set_mode(enum clock_event_mode mode, decrementer_set_next_event(DECREMENTER_MAX, dev); } +/* Interrupt handler for the timer broadcast IPI */ +void tick_broadcast_ipi_handler(void) +{ + u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + + *next_tb = get_tb_or_rtc(); + __timer_interrupt(); +} + static void register_decrementer_clockevent(int cpu) { struct clock_event_device *dec = &per_cpu(decrementers, cpu); @@ -982,11 +938,11 @@ void __init time_init(void) */ start_cpu_decrementer(); - /* Register the clocksource, if we're not running on iSeries */ - if (!firmware_has_feature(FW_FEATURE_ISERIES)) - clocksource_init(); + /* Register the clocksource */ + clocksource_init(); init_decrementer_clockevent(); + tick_setup_hrtimer_broadcast(); } @@ -1119,10 +1075,8 @@ static int __init rtc_init(void) return -ENODEV; pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); - if (IS_ERR(pdev)) - return PTR_ERR(pdev); - return 0; + return PTR_ERR_OR_ZERO(pdev); } module_init(rtc_init); |