--- zzzz-none-000/linux-3.10.107/arch/x86/xen/time.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/x86/xen/time.c 2021-02-04 17:41:59.000000000 +0000 @@ -14,6 +14,8 @@ #include #include #include +#include +#include #include #include @@ -78,7 +80,7 @@ BUG_ON(preemptible()); - state = &__get_cpu_var(xen_runstate); + state = this_cpu_ptr(&xen_runstate); /* * The runstate info is always updated by the hypervisor on @@ -121,7 +123,7 @@ WARN_ON(state.state != RUNSTATE_running); - snap = &__get_cpu_var(xen_runstate_snapshot); + snap = this_cpu_ptr(&xen_runstate_snapshot); /* work out how much time the VCPU has not been runn*ing* */ runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; @@ -156,7 +158,7 @@ cycle_t ret; preempt_disable_notrace(); - src = &__get_cpu_var(xen_vcpu)->time; + src = &__this_cpu_read(xen_vcpu)->time; ret = pvclock_clocksource_read(src); preempt_enable_notrace(); return ret; @@ -178,34 +180,56 @@ put_cpu_var(xen_vcpu); } -static unsigned long xen_get_wallclock(void) +static void xen_get_wallclock(struct timespec *now) { - struct timespec ts; + xen_read_wallclock(now); +} - xen_read_wallclock(&ts); - return ts.tv_sec; +static int xen_set_wallclock(const struct timespec *now) +{ + return -1; } -static int xen_set_wallclock(unsigned long now) +static int xen_pvclock_gtod_notify(struct notifier_block *nb, + unsigned long was_set, void *priv) { + /* Protected by the calling core code serialization */ + static struct timespec next_sync; + struct xen_platform_op op; - int rc; + struct timespec now; - /* do nothing for domU */ - if (!xen_initial_domain()) - return -1; + now = __current_kernel_time(); + + /* + * We only take the expensive HV call when the clock was set + * or when the 11 minutes RTC synchronization time elapsed. + */ + if (!was_set && timespec_compare(&now, &next_sync) < 0) + return NOTIFY_OK; op.cmd = XENPF_settime; - op.u.settime.secs = now; - op.u.settime.nsecs = 0; + op.u.settime.secs = now.tv_sec; + op.u.settime.nsecs = now.tv_nsec; op.u.settime.system_time = xen_clocksource_read(); - rc = HYPERVISOR_dom0_op(&op); - WARN(rc != 0, "XENPF_settime failed: now=%ld\n", now); + (void)HYPERVISOR_dom0_op(&op); - return rc; + /* + * Move the next drift compensation time 11 minutes + * ahead. That's emulating the sync_cmos_clock() update for + * the hardware RTC. + */ + next_sync = now; + next_sync.tv_sec += 11 * 60; + + return NOTIFY_OK; } +static struct notifier_block xen_pvclock_gtod_notifier = { + .notifier_call = xen_pvclock_gtod_notify, +}; + static struct clocksource xen_clocksource __read_mostly = { .name = "xen", .rating = 400, @@ -250,30 +274,18 @@ return xen_clocksource_read() + delta; } -static void xen_timerop_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int xen_timerop_shutdown(struct clock_event_device *evt) { - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - /* unsupported */ - WARN_ON(1); - break; - - case CLOCK_EVT_MODE_ONESHOT: - case CLOCK_EVT_MODE_RESUME: - break; - - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - HYPERVISOR_set_timer_op(0); /* cancel timeout */ - break; - } + /* cancel timeout */ + HYPERVISOR_set_timer_op(0); + + return 0; } static int xen_timerop_set_next_event(unsigned long delta, struct clock_event_device *evt) { - WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT); + WARN_ON(!clockevent_state_oneshot(evt)); if (HYPERVISOR_set_timer_op(get_abs_timeout(delta)) < 0) BUG(); @@ -286,46 +298,39 @@ } static const struct clock_event_device xen_timerop_clockevent = { - .name = "xen", - .features = CLOCK_EVT_FEAT_ONESHOT, + .name = "xen", + .features = CLOCK_EVT_FEAT_ONESHOT, - .max_delta_ns = 0xffffffff, - .min_delta_ns = TIMER_SLOP, + .max_delta_ns = 0xffffffff, + .min_delta_ns = TIMER_SLOP, - .mult = 1, - .shift = 0, - .rating = 500, + .mult = 1, + .shift = 0, + .rating = 500, - .set_mode = xen_timerop_set_mode, - .set_next_event = xen_timerop_set_next_event, + .set_state_shutdown = xen_timerop_shutdown, + .set_next_event = xen_timerop_set_next_event, }; +static int xen_vcpuop_shutdown(struct clock_event_device *evt) +{ + int cpu = smp_processor_id(); + if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) || + HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) + BUG(); -static void xen_vcpuop_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) + return 0; +} + +static int xen_vcpuop_set_oneshot(struct clock_event_device *evt) { int cpu = smp_processor_id(); - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - WARN_ON(1); /* unsupported */ - break; - - case CLOCK_EVT_MODE_ONESHOT: - if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) - BUG(); - break; + if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) + BUG(); - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) || - HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) - BUG(); - break; - case CLOCK_EVT_MODE_RESUME: - break; - } + return 0; } static int xen_vcpuop_set_next_event(unsigned long delta, @@ -335,14 +340,14 @@ struct vcpu_set_singleshot_timer single; int ret; - WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT); + WARN_ON(!clockevent_state_oneshot(evt)); single.timeout_abs_ns = get_abs_timeout(delta); - /* Get an event anyway, even if the timeout is already expired */ - single.flags = 0; + single.flags = VCPU_SSHOTTMR_future; ret = HYPERVISOR_vcpu_op(VCPUOP_set_singleshot_timer, cpu, &single); - BUG_ON(ret != 0); + + BUG_ON(ret != 0 && ret != -ETIME); return ret; } @@ -358,17 +363,23 @@ .shift = 0, .rating = 500, - .set_mode = xen_vcpuop_set_mode, + .set_state_shutdown = xen_vcpuop_shutdown, + .set_state_oneshot = xen_vcpuop_set_oneshot, .set_next_event = xen_vcpuop_set_next_event, }; static const struct clock_event_device *xen_clockevent = &xen_timerop_clockevent; -static DEFINE_PER_CPU(struct clock_event_device, xen_clock_events) = { .irq = -1 }; + +struct xen_clock_event_device { + struct clock_event_device evt; + char name[16]; +}; +static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.irq = -1 }; static irqreturn_t xen_timer_interrupt(int irq, void *dev_id) { - struct clock_event_device *evt = &__get_cpu_var(xen_clock_events); + struct clock_event_device *evt = this_cpu_ptr(&xen_clock_events.evt); irqreturn_t ret; ret = IRQ_NONE; @@ -382,26 +393,37 @@ return ret; } -void xen_setup_timer(int cpu) +void xen_teardown_timer(int cpu) { - const char *name; struct clock_event_device *evt; + BUG_ON(cpu == 0); + evt = &per_cpu(xen_clock_events, cpu).evt; + + if (evt->irq >= 0) { + unbind_from_irqhandler(evt->irq, NULL); + evt->irq = -1; + } +} + +void xen_setup_timer(int cpu) +{ + struct xen_clock_event_device *xevt = &per_cpu(xen_clock_events, cpu); + struct clock_event_device *evt = &xevt->evt; int irq; - evt = &per_cpu(xen_clock_events, cpu); WARN(evt->irq >= 0, "IRQ%d for CPU%d is already allocated\n", evt->irq, cpu); + if (evt->irq >= 0) + xen_teardown_timer(cpu); printk(KERN_INFO "installing Xen timer for CPU %d\n", cpu); - name = kasprintf(GFP_KERNEL, "timer%d", cpu); - if (!name) - name = ""; + snprintf(xevt->name, sizeof(xevt->name), "timer%d", cpu); irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, - IRQF_DISABLED|IRQF_PERCPU| - IRQF_NOBALANCING|IRQF_TIMER| - IRQF_FORCE_RESUME, - name, NULL); + IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER| + IRQF_FORCE_RESUME|IRQF_EARLY_RESUME, + xevt->name, NULL); + (void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX); memcpy(evt, xen_clockevent, sizeof(*evt)); @@ -409,20 +431,10 @@ evt->irq = irq; } -void xen_teardown_timer(int cpu) -{ - struct clock_event_device *evt; - BUG_ON(cpu == 0); - evt = &per_cpu(xen_clock_events, cpu); - unbind_from_irqhandler(evt->irq, NULL); - evt->irq = -1; -} void xen_setup_cpu_clockevents(void) { - BUG_ON(preemptible()); - - clockevents_register_device(&__get_cpu_var(xen_clock_events)); + clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt)); } void xen_timer_resume(void) @@ -449,6 +461,10 @@ int cpu = smp_processor_id(); struct timespec tp; + /* As Dom0 is never moved, no penalty on using TSC there */ + if (xen_initial_domain()) + xen_clocksource.rating = 275; + clocksource_register_hz(&xen_clocksource, NSEC_PER_SEC); if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) { @@ -467,6 +483,9 @@ xen_setup_runstate_info(cpu); xen_setup_timer(cpu); xen_setup_cpu_clockevents(); + + if (xen_initial_domain()) + pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); } void __init xen_init_time_ops(void) @@ -479,7 +498,9 @@ x86_platform.calibrate_tsc = xen_tsc_khz; x86_platform.get_wallclock = xen_get_wallclock; - x86_platform.set_wallclock = xen_set_wallclock; + /* Dom0 uses the native method to set the hardware RTC. */ + if (!xen_initial_domain()) + x86_platform.set_wallclock = xen_set_wallclock; } #ifdef CONFIG_XEN_PVHVM