static int resume_target_kernel(bool platform_mode)
{
int error;
error = dpm_suspend_noirq(PMSG_QUIESCE);
if (error) {
printk(KERN_ERR "PM: Some devices failed to power down, "
"aborting resume\n");
return error;
}
error = platform_pre_restore(platform_mode);
if (error)
goto Cleanup;
error = disable_nonboot_cpus();
if (error)
goto Enable_cpus;
local_irq_disable();
error = sysdev_suspend(PMSG_QUIESCE);
if (error)
goto Enable_irqs;
/* We'll ignore saved state, but this gets preempt count (etc) right */
save_processor_state();
error = restore_highmem();
if (!error) {
error = swsusp_arch_resume();
/*
* The code below is only ever reached in case of a failure.
* Otherwise execution continues at place where
* swsusp_arch_suspend() was called
*/
BUG_ON(!error);
/* This call to restore_highmem() undos the previous one */
restore_highmem();
}
/*
* The only reason why swsusp_arch_resume() can fail is memory being
* very tight, so we have to free it as soon as we can to avoid
* subsequent failures
*/
swsusp_free();
restore_processor_state();
touch_softlockup_watchdog();
sysdev_resume();
Enable_irqs:
local_irq_enable();
Enable_cpus:
enable_nonboot_cpus();
Cleanup:
platform_restore_cleanup(platform_mode);
dpm_resume_noirq(PMSG_RECOVER);
return error;
}
/**
* resume_target_kernel - Restore system state from a hibernation image.
* @platform_mode: Whether or not to use the platform driver.
*
* Execute device drivers' "noirq" and "late" freeze callbacks, restore the
* contents of highmem that have not been restored yet from the image and run
* the low-level code that will restore the remaining contents of memory and
* switch to the just restored target kernel.
*/
static int resume_target_kernel(bool platform_mode)
{
int error;
error = dpm_suspend_end(PMSG_QUIESCE);
if (error) {
pr_err("Some devices failed to power down, aborting resume\n");
return error;
}
error = platform_pre_restore(platform_mode);
if (error)
goto Cleanup;
error = hibernate_resume_nonboot_cpu_disable();
if (error)
goto Enable_cpus;
local_irq_disable();
error = syscore_suspend();
if (error)
goto Enable_irqs;
save_processor_state();
error = restore_highmem();
if (!error) {
error = swsusp_arch_resume();
/*
* The code below is only ever reached in case of a failure.
* Otherwise, execution continues at the place where
* swsusp_arch_suspend() was called.
*/
BUG_ON(!error);
/*
* This call to restore_highmem() reverts the changes made by
* the previous one.
*/
restore_highmem();
}
/*
* The only reason why swsusp_arch_resume() can fail is memory being
* very tight, so we have to free it as soon as we can to avoid
* subsequent failures.
*/
swsusp_free();
restore_processor_state();
touch_softlockup_watchdog();
syscore_resume();
Enable_irqs:
local_irq_enable();
Enable_cpus:
enable_nonboot_cpus();
Cleanup:
platform_restore_cleanup(platform_mode);
dpm_resume_start(PMSG_RECOVER);
return error;
}
/*
* We rearm the timer until we get disabled by the idle code.
* Called with interrupts disabled and timer->base->cpu_base->lock held.
*/
static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
{
struct tick_sched *ts =
container_of(timer, struct tick_sched, sched_timer);
struct pt_regs *regs = get_irq_regs();
ktime_t now = ktime_get();
int cpu = smp_processor_id();
#ifdef CONFIG_NO_HZ
/*
* Check if the do_timer duty was dropped. We don't care about
* concurrency: This happens only when the cpu in charge went
* into a long sleep. If two cpus happen to assign themself to
* this duty, then the jiffies update is still serialized by
* xtime_lock.
*/
if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
tick_do_timer_cpu = cpu;
#endif
/* Check, if the jiffies need an update */
if (tick_do_timer_cpu == cpu)
tick_do_update_jiffies64(now);
/*
* Do not call, when we are not in irq context and have
* no valid regs pointer
*/
if (regs) {
/*
* When we are idle and the tick is stopped, we have to touch
* the watchdog as we might not schedule for a really long
* time. This happens on complete idle SMP systems while
* waiting on the login prompt. We also increment the "start of
* idle" jiffy stamp so the idle accounting adjustment we do
* when we go busy again does not account too much ticks.
*/
if (ts->tick_stopped) {
touch_softlockup_watchdog();
ts->idle_jiffies++;
}
update_process_times(user_mode(regs));
profile_tick(CPU_PROFILING);
if ((rq_info.init == 1) && (tick_do_timer_cpu == cpu)) {
/*
* update run queue statistics
*/
update_rq_stats();
/*
* wakeup user if needed
*/
wakeup_user();
}
}
hrtimer_forward(timer, now, tick_period);
return HRTIMER_RESTART;
}
void ia64_init_itm(void)
{
unsigned long platform_base_freq, itc_freq;
struct pal_freq_ratio itc_ratio, proc_ratio;
long status, platform_base_drift, itc_drift;
/*
* According to SAL v2.6, we need to use a SAL call to determine the platform base
* frequency and then a PAL call to determine the frequency ratio between the ITC
* and the base frequency.
*/
status = ia64_sal_freq_base(SAL_FREQ_BASE_PLATFORM,
&platform_base_freq, &platform_base_drift);
if (status != 0) {
printk(KERN_ERR "SAL_FREQ_BASE_PLATFORM failed: %s\n", ia64_sal_strerror(status));
} else {
status = ia64_pal_freq_ratios(&proc_ratio, NULL, &itc_ratio);
if (status != 0)
printk(KERN_ERR "PAL_FREQ_RATIOS failed with status=%ld\n", status);
}
if (status != 0) {
/* invent "random" values */
printk(KERN_ERR
"SAL/PAL failed to obtain frequency info---inventing reasonable values\n");
platform_base_freq = 100000000;
platform_base_drift = -1; /* no drift info */
itc_ratio.num = 3;
itc_ratio.den = 1;
}
if (platform_base_freq < 40000000) {
printk(KERN_ERR "Platform base frequency %lu bogus---resetting to 75MHz!\n",
platform_base_freq);
platform_base_freq = 75000000;
platform_base_drift = -1;
}
if (!proc_ratio.den)
proc_ratio.den = 1; /* avoid division by zero */
if (!itc_ratio.den)
itc_ratio.den = 1; /* avoid division by zero */
itc_freq = (platform_base_freq*itc_ratio.num)/itc_ratio.den;
local_cpu_data->itm_delta = (itc_freq + HZ/2) / HZ;
printk(KERN_DEBUG "CPU %d: base freq=%lu.%03luMHz, ITC ratio=%u/%u, "
"ITC freq=%lu.%03luMHz", smp_processor_id(),
platform_base_freq / 1000000, (platform_base_freq / 1000) % 1000,
itc_ratio.num, itc_ratio.den, itc_freq / 1000000, (itc_freq / 1000) % 1000);
if (platform_base_drift != -1) {
itc_drift = platform_base_drift*itc_ratio.num/itc_ratio.den;
printk("+/-%ldppm\n", itc_drift);
} else {
itc_drift = -1;
printk("\n");
}
local_cpu_data->proc_freq = (platform_base_freq*proc_ratio.num)/proc_ratio.den;
local_cpu_data->itc_freq = itc_freq;
local_cpu_data->cyc_per_usec = (itc_freq + USEC_PER_SEC/2) / USEC_PER_SEC;
local_cpu_data->nsec_per_cyc = ((NSEC_PER_SEC<<IA64_NSEC_PER_CYC_SHIFT)
+ itc_freq/2)/itc_freq;
if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT)) {
#ifdef CONFIG_SMP
/* On IA64 in an SMP configuration ITCs are never accurately synchronized.
* Jitter compensation requires a cmpxchg which may limit
* the scalability of the syscalls for retrieving time.
* The ITC synchronization is usually successful to within a few
* ITC ticks but this is not a sure thing. If you need to improve
* timer performance in SMP situations then boot the kernel with the
* "nojitter" option. However, doing so may result in time fluctuating (maybe
* even going backward) if the ITC offsets between the individual CPUs
* are too large.
*/
if (!nojitter)
itc_jitter_data.itc_jitter = 1;
#endif
} else
/*
* ITC is drifty and we have not synchronized the ITCs in smpboot.c.
* ITC values may fluctuate significantly between processors.
* Clock should not be used for hrtimers. Mark itc as only
* useful for boot and testing.
*
* Note that jitter compensation is off! There is no point of
* synchronizing ITCs since they may be large differentials
* that change over time.
*
* The only way to fix this would be to repeatedly sync the
* ITCs. Until that time we have to avoid ITC.
*/
clocksource_itc.rating = 50;
paravirt_init_missing_ticks_accounting(smp_processor_id());
/* avoid softlock up message when cpu is unplug and plugged again. */
touch_softlockup_watchdog();
/* Setup the CPU local timer tick */
ia64_cpu_local_tick();
if (!itc_clocksource) {
clocksource_register_hz(&clocksource_itc,
local_cpu_data->itc_freq);
itc_clocksource = &clocksource_itc;
}
}
NORET_TYPE void panic(const char * fmt, ...)
{
long i;
static char buf[1024];
va_list args;
#if defined(CONFIG_S390)
unsigned long caller = (unsigned long) __builtin_return_address(0);
#endif
/*
* It's possible to come here directly from a panic-assertion and not
* have preempt disabled. Some functions called from here want
* preempt to be disabled. No point enabling it later though...
*/
preempt_disable();
bust_spinlocks(1);
va_start(args, fmt);
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
bust_spinlocks(0);
/*
* If we have crashed and we have a crash kernel loaded let it handle
* everything else.
* Do we want to call this before we try to display a message?
*/
crash_kexec(NULL);
#ifdef CONFIG_SMP
/*
* Note smp_send_stop is the usual smp shutdown function, which
* unfortunately means it may not be hardened to work in a panic
* situation.
*/
smp_send_stop();
#endif
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
if (!panic_blink)
panic_blink = no_blink;
if (panic_timeout > 0) {
/*
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked..
*/
printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout);
for (i = 0; i < panic_timeout*1000; ) {
touch_nmi_watchdog();
i += panic_blink(i);
mdelay(1);
i++;
}
/* This will not be a clean reboot, with everything
* shutting down. But if there is a chance of
* rebooting the system it will be rebooted.
*/
emergency_restart();
}
#ifdef __sparc__
{
extern int stop_a_enabled;
/* Make sure the user can actually press Stop-A (L1-A) */
stop_a_enabled = 1;
printk(KERN_EMERG "Press Stop-A (L1-A) to return to the boot prom\n");
}
#endif
#if defined(CONFIG_S390)
disabled_wait(caller);
#endif
local_irq_enable();
for (i = 0;;) {
touch_softlockup_watchdog();
i += panic_blink(i);
mdelay(1);
i++;
}
}
void tick_nohz_restart_sched_tick(void)
#endif
{
int cpu = smp_processor_id();
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
unsigned long ticks;
#endif
ktime_t now;
local_irq_disable();
if (ts->idle_active || (ts->inidle && ts->tick_stopped))
now = ktime_get();
if (ts->idle_active)
tick_nohz_stop_idle(cpu, now);
if (!ts->inidle || !ts->tick_stopped) {
ts->inidle = 0;
#ifdef CONFIG_DATAPLANE
if (!user_idle)
#endif
local_irq_enable();
return;
}
ts->inidle = 0;
rcu_exit_nohz();
/* Update jiffies first */
select_nohz_load_balancer(0);
tick_do_update_jiffies64(now);
cpumask_clear_cpu(cpu, nohz_cpu_mask);
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
/*
* We stopped the tick in idle. Update process times would miss the
* time we slept as update_process_times does only a 1 tick
* accounting. Enforce that this is accounted to idle !
*/
ticks = jiffies - ts->idle_jiffies;
/*
* We might be one off. Do not randomly account a huge number of ticks!
*/
if (ticks && ticks < LONG_MAX)
#ifdef CONFIG_DATAPLANE
{
if (user_idle) {
cputime_t cpu_time = jiffies_to_cputime(ticks);
account_user_time(current, cpu_time,
cputime_to_scaled(cpu_time));
} else {
account_idle_ticks(ticks);
}
}
#else
account_idle_ticks(ticks);
#endif
#endif
touch_softlockup_watchdog();
/*
* Cancel the scheduled timer and restore the tick
*/
ts->tick_stopped = 0;
ts->idle_exittime = now;
tick_nohz_restart(ts, now);
#ifdef CONFIG_DATAPLANE
if (!user_idle)
#endif
local_irq_enable();
}
void touch_nmi_watchdog(void)
{
__get_cpu_var(watchdog_nmi_touch) = true;
touch_softlockup_watchdog();
}
/**
* __do_IRQ - original all in one highlevel IRQ handler
* @irq: the interrupt number
*
* __do_IRQ handles all normal device IRQ's (the special
* SMP cross-CPU interrupts have their own specific
* handlers).
*
* This is the original x86 implementation which is used for every
* interrupt type.
*/
fastcall notrace unsigned int __do_IRQ(unsigned int irq)
{
struct irq_desc *desc = irq_desc + irq;
struct irqaction *action;
unsigned int status;
kstat_this_cpu.irqs[irq]++;
if (CHECK_IRQ_PER_CPU(desc->status)) {
irqreturn_t action_ret;
/*
* No locking required for CPU-local interrupts:
*/
if (desc->chip->ack)
desc->chip->ack(irq);
action_ret = handle_IRQ_event(irq, desc->action);
desc->chip->end(irq);
return 1;
}
/*
* If the task is currently running in user mode, don't
* detect soft lockups. If CONFIG_DETECT_SOFTLOCKUP is not
* configured, this should be optimized out.
*/
if (user_mode(get_irq_regs()))
touch_softlockup_watchdog();
spin_lock(&desc->lock);
if (desc->chip->ack)
desc->chip->ack(irq);
/*
* REPLAY is when Linux resends an IRQ that was dropped earlier
* WAITING is used by probe to mark irqs that are being tested
*/
status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING);
status |= IRQ_PENDING; /* we _want_ to handle it */
/*
* If the IRQ is disabled for whatever reason, we cannot
* use the action we have.
*/
action = NULL;
if (likely(!(status & (IRQ_DISABLED | IRQ_INPROGRESS)))) {
action = desc->action;
status &= ~IRQ_PENDING; /* we commit to handling */
status |= IRQ_INPROGRESS; /* we are handling it */
}
desc->status = status;
/*
* If there is no IRQ handler or it was disabled, exit early.
* Since we set PENDING, if another processor is handling
* a different instance of this same irq, the other processor
* will take care of it.
*/
if (unlikely(!action))
goto out;
/*
* Edge triggered interrupts need to remember
* pending events.
* This applies to any hw interrupts that allow a second
* instance of the same irq to arrive while we are in do_IRQ
* or in the handler. But the code here only handles the _second_
* instance of the irq, not the third or fourth. So it is mostly
* useful for irq hardware that does not mask cleanly in an
* SMP environment.
*/
for (;;) {
irqreturn_t action_ret;
spin_unlock(&desc->lock);
action_ret = handle_IRQ_event(irq, action);
if (!noirqdebug)
note_interrupt(irq, desc, action_ret);
spin_lock(&desc->lock);
if (likely(!(desc->status & IRQ_PENDING)))
break;
desc->status &= ~IRQ_PENDING;
}
desc->status &= ~IRQ_INPROGRESS;
out:
/*
* The ->end() handler has to deal with interrupts which got
* disabled while the handler was running.
*/
desc->chip->end(irq);
spin_unlock(&desc->lock);
return 1;
}
