static void __run_hrtimer(struct hrtimer *timer, ktime_t *now)
{
struct hrtimer_clock_base *base = timer->base;
struct hrtimer_cpu_base *cpu_base = base->cpu_base;
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
WARN_ON(!irqs_disabled());
debug_deactivate(timer);
__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
timer_stats_account_hrtimer(timer);
fn = timer->function;
/*
* Because we run timers from hardirq context, there is no chance
* they get migrated to another cpu, therefore its safe to unlock
* the timer base.
*/
raw_spin_unlock(&cpu_base->lock);
trace_hrtimer_expire_entry(timer, now);
restart = fn(timer);
trace_hrtimer_expire_exit(timer);
raw_spin_lock(&cpu_base->lock);
/*
* Note: We clear the CALLBACK bit after enqueue_hrtimer and
* we do not reprogramm the event hardware. Happens either in
* hrtimer_start_range_ns() or in hrtimer_interrupt()
*/
if (restart != HRTIMER_NORESTART) {
BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
enqueue_hrtimer(timer, base);
}
WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK));
timer->state &= ~HRTIMER_STATE_CALLBACK;
}
/*
* Retrigger next event is called after clock was set
*
* Called with interrupts disabled via on_each_cpu()
*/
static void retrigger_next_event(void *arg)
{
struct hrtimer_cpu_base *base = &__get_cpu_var(hrtimer_bases);
struct timespec realtime_offset, xtim, wtm, sleep;
if (!hrtimer_hres_active())
return;
/* Optimized out for !HIGH_RES */
get_xtime_and_monotonic_and_sleep_offset(&xtim, &wtm, &sleep);
set_normalized_timespec(&realtime_offset, -wtm.tv_sec, -wtm.tv_nsec);
/* Adjust CLOCK_REALTIME offset */
raw_spin_lock(&base->lock);
base->clock_base[HRTIMER_BASE_REALTIME].offset =
timespec_to_ktime(realtime_offset);
base->clock_base[HRTIMER_BASE_BOOTTIME].offset =
timespec_to_ktime(sleep);
hrtimer_force_reprogram(base, 0);
raw_spin_unlock(&base->lock);
}
static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
{
unsigned long timeout;
/*
* set synchronisation state between this boot processor
* and the secondary one
*/
raw_spin_lock(&boot_lock);
/*
* The secondary processor is waiting to be released from
* the holding pen - release it, then wait for it to flag
* that it has been released by resetting pen_release.
*
* Note that "pen_release" is the hardware CPU ID, whereas
* "cpu" is Linux's internal ID.
*/
pen_release = cpu;
flush_cache_all();
outer_flush_all();
timeout = jiffies + (1 * HZ);
while (time_before(jiffies, timeout)) {
smp_rmb();
if (pen_release == -1)
break;
udelay(10);
}
/*
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
/*
* The current CPU has been marked offline. Migrate IRQs off this CPU.
* If the affinity settings do not allow other CPUs, force them onto any
* available CPU.
*
* Note: we must iterate over all IRQs, whether they have an attached
* action structure or not, as we need to get chained interrupts too.
*/
void migrate_irqs(void)
{
unsigned int i;
struct irq_desc *desc;
unsigned long flags;
local_irq_save(flags);
for_each_irq_desc(i, desc) {
bool affinity_broken = false;
if (!desc)
continue;
raw_spin_lock(&desc->lock);
affinity_broken = migrate_one_irq(desc);
raw_spin_unlock(&desc->lock);
if (affinity_broken && printk_ratelimit())
pr_warning("IRQ%u no longer affine to CPU%u\n", i,
smp_processor_id());
}
void handle_level_irq(unsigned int irq, struct irq_desc *desc)
{
raw_spin_lock(&desc->lock);
mask_ack_irq(desc);
if (irqd_irq_inprogress(&desc->irq_data))
if (!irq_check_poll(desc))
goto out_unlock;
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
/* kstat_incr_irqs_this_cpu(irq, desc); */
if (!desc->action || irqd_irq_disabled(&desc->irq_data))
goto out_unlock;
handle_irq_event(desc);
if (!irqd_irq_disabled(&desc->irq_data) && !(desc->istate & IRQS_ONESHOT))
unmask_irq(desc);
out_unlock:
raw_spin_unlock(&desc->lock);
}
/**
* handle_fasteoi_irq - irq handler for transparent controllers
* @irq: the interrupt number
* @desc: the interrupt description structure for this irq
*
* Only a single callback will be issued to the chip: an ->eoi()
* call when the interrupt has been serviced. This enables support
* for modern forms of interrupt handlers, which handle the flow
* details in hardware, transparently.
*/
void
handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
{
raw_spin_lock(&desc->lock);
if (unlikely(irqd_irq_inprogress(&desc->irq_data)))
if (!irq_check_poll(desc))
goto out;
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
kstat_incr_irqs_this_cpu(irq, desc);
/*
* If its disabled or no action available
* then mask it and get out of here:
*/
if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
if (!irq_settings_is_level(desc))
desc->istate |= IRQS_PENDING;
mask_irq(desc);
goto out;
}
if (desc->istate & IRQS_ONESHOT)
mask_irq(desc);
preflow_handler(desc);
handle_irq_event(desc);
out_eoi:
desc->irq_data.chip->irq_eoi(&desc->irq_data);
out_unlock:
raw_spin_unlock(&desc->lock);
return;
out:
if (!(desc->irq_data.chip->flags & IRQCHIP_EOI_IF_HANDLED))
goto out_eoi;
goto out_unlock;
}
/**
* handle_simple_irq - Simple and software-decoded IRQs.
* @irq: the interrupt number
* @desc: the interrupt description structure for this irq
*
* Simple interrupts are either sent from a demultiplexing interrupt
* handler or come from hardware, where no interrupt hardware control
* is necessary.
*
* Note: The caller is expected to handle the ack, clear, mask and
* unmask issues if necessary.
*/
void
handle_simple_irq(unsigned int irq, struct irq_desc *desc)
{
raw_spin_lock(&desc->lock);
if (unlikely(irqd_irq_inprogress(&desc->irq_data)))
if (!irq_check_poll(desc))
goto out_unlock;
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
kstat_incr_irqs_this_cpu(irq, desc);
if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
desc->istate |= IRQS_PENDING;
goto out_unlock;
}
handle_irq_event(desc);
out_unlock:
raw_spin_unlock(&desc->lock);
}
static unsigned int steal_context_smp(unsigned int id)
{
struct mm_struct *mm;
unsigned int cpu, max, i;
max = last_context - first_context;
while (max--) {
mm = context_mm[id];
if (mm->context.active) {
id++;
if (id > last_context)
id = first_context;
continue;
}
pr_hardcont(" | steal %d from 0x%p", id, mm);
mm->context.id = MMU_NO_CONTEXT;
for_each_cpu(cpu, mm_cpumask(mm)) {
for (i = cpu_first_thread_sibling(cpu);
i <= cpu_last_thread_sibling(cpu); i++)
__set_bit(id, stale_map[i]);
cpu = i - 1;
}
return id;
}
raw_spin_unlock(&context_lock);
cpu_relax();
raw_spin_lock(&context_lock);
return MMU_NO_CONTEXT;
}
asmlinkage int vstlog(const char *fmt, va_list args)
{
static char textbuf[RINGBUF_LINE_MAX];
char *text = textbuf;
size_t text_len;
enum ringbuf_flags lflags = 0;
unsigned long flags;
int this_cpu;
int printed_len = 0;
bool stored = false;
local_irq_save(flags);
this_cpu = smp_processor_id();
lockdep_off();
raw_spin_lock(&ringbuf_lock);
ringbuf_cpu = this_cpu;
text_len = vscnprintf(text, sizeof(textbuf), fmt, args);
/* mark and strip a trailing newline */
if (text_len && text[text_len-1] == '\n') {
text_len--;
lflags |= RINGBUF_NEWLINE;
}
if (!stored)
ringbuf_store(lflags,text, text_len, ringbuf_cpu, current);
printed_len += text_len;
raw_spin_unlock(&ringbuf_lock);
local_irq_restore(flags);
return printed_len;
}
/**
* __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
* @lock: the rt_mutex to take
* @state: the state the task should block in (TASK_INTERRUPTIBLE
* or TASK_UNINTERRUPTIBLE)
* @timeout: the pre-initialized and started timer, or NULL for none
* @waiter: the pre-initialized rt_mutex_waiter
*
* lock->wait_lock must be held by the caller.
*/
static int __sched
__rt_mutex_slowlock(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
struct rt_mutex_waiter *waiter)
{
int ret = 0;
for (;;) {
/* Try to acquire the lock: */
if (try_to_take_rt_mutex(lock, current, waiter))
break;
/*
* TASK_INTERRUPTIBLE checks for signals and
* timeout. Ignored otherwise.
*/
if (unlikely(state == TASK_INTERRUPTIBLE)) {
/* Signal pending? */
if (signal_pending(current))
ret = -EINTR;
if (timeout && !timeout->task)
ret = -ETIMEDOUT;
if (ret)
break;
}
raw_spin_unlock(&lock->wait_lock);
debug_rt_mutex_print_deadlock(waiter);
schedule_rt_mutex(lock);
raw_spin_lock(&lock->wait_lock);
set_current_state(state);
}
return ret;
}
/**
* irq_migrate_all_off_this_cpu - Migrate irqs away from offline cpu
*
* The current CPU has been marked offline. Migrate IRQs off this CPU.
* If the affinity settings do not allow other CPUs, force them onto any
* available CPU.
*
* Note: we must iterate over all IRQs, whether they have an attached
* action structure or not, as we need to get chained interrupts too.
*/
void irq_migrate_all_off_this_cpu(void)
{
unsigned int irq;
struct irq_desc *desc;
unsigned long flags;
local_irq_save(flags);
for_each_active_irq(irq) {
bool affinity_broken;
desc = irq_to_desc(irq);
raw_spin_lock(&desc->lock);
affinity_broken = migrate_one_irq(desc);
raw_spin_unlock(&desc->lock);
if (affinity_broken)
pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n",
irq, smp_processor_id());
}
local_irq_restore(flags);
}
void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
int psize)
{
unsigned long pid;
unsigned long ap = mmu_get_ap(psize);
preempt_disable();
pid = mm ? mm->context.id : 0;
if (unlikely(pid == MMU_NO_CONTEXT))
goto bail;
if (!mm_is_thread_local(mm)) {
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
_tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
if (lock_tlbie)
raw_spin_unlock(&native_tlbie_lock);
} else
_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
bail:
preempt_enable();
}
/*
* Try to get console ownership to actually show the kernel
* messages from a 'printk'. Return true (and with the
* console_mutex held, and 'console_locked' set) if it
* is successful, false otherwise.
*
* This gets called with the 'logbuf_lock' spinlock held and
* interrupts disabled. It should return with 'lockbuf_lock'
* released but interrupts still disabled.
*/
static int acquire_console_mutex_for_printk(unsigned int cpu)
{
int retval = 0;
if (!try_acquire_console_mutex()) {
retval = 1;
/*
* If we can't use the console, we need to release
* the console mutex by hand to avoid flushing
* the buffer. We need to hold the console mutex
* in order to do this test safely.
*/
if (!can_use_console(cpu)) {
console_locked = 0;
mutex_unlock(&console_mutex);
retval = 0;
}
}
printk_cpu = UINT_MAX;
raw_spin_unlock(&logbuf_lock);
return retval;
}
/**
* rt_mutex_finish_proxy_lock() - Complete lock acquisition
* @lock: the rt_mutex we were woken on
* @to: the timeout, null if none. hrtimer should already have
* been started.
* @waiter: the pre-initialized rt_mutex_waiter
* @detect_deadlock: perform deadlock detection (1) or not (0)
*
* Complete the lock acquisition started our behalf by another thread.
*
* Returns:
* 0 - success
* <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
*
* Special API call for PI-futex requeue support
*/
int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *to,
struct rt_mutex_waiter *waiter,
int detect_deadlock)
{
int ret;
raw_spin_lock(&lock->wait_lock);
set_current_state(TASK_INTERRUPTIBLE);
ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
detect_deadlock);
set_current_state(TASK_RUNNING);
if (unlikely(waiter->task))
remove_waiter(lock, waiter);
/*
* try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
* have to fix that up.
*/
fixup_rt_mutex_waiters(lock);
raw_spin_unlock(&lock->wait_lock);
/*
* Readjust priority, when we did not get the lock. We might have been
* the pending owner and boosted. Since we did not take the lock, the
* PI boost has to go.
*/
if (unlikely(ret))
rt_mutex_adjust_prio(current);
return ret;
}
static int panic_flush(struct notifier_block *nb,
unsigned long l, void *buf)
{
int i;
raw_spin_lock(&panic_lock);
pr_emerg("EMMD: ready to perform memory dump\n");
for (i = 0; i < nr_cpu_ids; i++)
coresight_dump_pcsr(i);
set_emmd_indicator();
ramtag_setup();
kmsg_dump(KMSG_DUMP_PANIC);
dump_task_info();
#ifdef CONFIG_PXA_RAMDUMP
ramdump_panic();
#endif
#ifdef CONFIG_REGDUMP
dump_reg_to_console();
#endif
pr_emerg("EMMD: done\n");
arm_machine_flush_console();
flush_cache_all();
#ifdef CONFIG_ARM
outer_flush_all();
#endif
drain_mc_buffer();
raw_spin_unlock(&panic_lock);
return NOTIFY_DONE;
}
/**
* handle_edge_eoi_irq - edge eoi type IRQ handler
* @irq: the interrupt number
* @desc: the interrupt description structure for this irq
*
* Similar as the above handle_edge_irq, but using eoi and w/o the
* mask/unmask logic.
*/
bool handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc)
{
bool handled = false;
struct irq_chip *chip = irq_desc_get_chip(desc);
raw_spin_lock(&desc->lock);
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
/*
* If we're currently running this IRQ, or its disabled,
* we shouldn't process the IRQ. Mark it pending, handle
* the necessary masking and go out
*/
if (unlikely(irqd_irq_disabled(&desc->irq_data) ||
irqd_irq_inprogress(&desc->irq_data) || !desc->action)) {
if (!irq_check_poll(desc)) {
desc->istate |= IRQS_PENDING;
goto out_eoi;
}
}
kstat_incr_irqs_this_cpu(irq, desc);
do {
if (unlikely(!desc->action))
goto out_eoi;
handle_irq_event(desc);
handled = true;
} while ((desc->istate & IRQS_PENDING) &&
!irqd_irq_disabled(&desc->irq_data));
out_eoi:
chip->irq_eoi(&desc->irq_data);
raw_spin_unlock(&desc->lock);
return handled;
}
/**
* handle_edge_eoi_irq - edge eoi type IRQ handler
* @desc: the interrupt description structure for this irq
*
* Similar as the above handle_edge_irq, but using eoi and w/o the
* mask/unmask logic.
*/
void handle_edge_eoi_irq(struct irq_desc *desc)
{
struct irq_chip *chip = irq_desc_get_chip(desc);
raw_spin_lock(&desc->lock);
desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
if (!irq_may_run(desc)) {
desc->istate |= IRQS_PENDING;
goto out_eoi;
}
/*
* If its disabled or no action available then mask it and get
* out of here.
*/
if (irqd_irq_disabled(&desc->irq_data) || !desc->action) {
desc->istate |= IRQS_PENDING;
goto out_eoi;
}
kstat_incr_irqs_this_cpu(desc);
do {
if (unlikely(!desc->action))
goto out_eoi;
handle_irq_event(desc);
} while ((desc->istate & IRQS_PENDING) &&
!irqd_irq_disabled(&desc->irq_data));
out_eoi:
chip->irq_eoi(&desc->irq_data);
raw_spin_unlock(&desc->lock);
}
static int allocate_gic_irq(struct irq_domain *domain, unsigned virq,
irq_hw_number_t hwirq)
{
struct irq_fwspec fwspec;
int i;
int err;
if (!irq_domain_get_of_node(domain->parent))
return -EINVAL;
raw_spin_lock(&cb->lock);
for (i = cb->int_max - 1; i >= 0; i--) {
if (cb->irq_map[i] == IRQ_FREE) {
cb->irq_map[i] = hwirq;
break;
}
}
raw_spin_unlock(&cb->lock);
if (i < 0)
return -ENODEV;
fwspec.fwnode = domain->parent->fwnode;
fwspec.param_count = 3;
fwspec.param[0] = 0; /* SPI */
fwspec.param[1] = i;
fwspec.param[2] = IRQ_TYPE_LEVEL_HIGH;
err = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
if (err)
cb->irq_map[i] = IRQ_FREE;
else
cb->write(i, hwirq);
return err;
}
void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
{
unsigned long pid;
struct mm_struct *mm = tlb->mm;
preempt_disable();
pid = mm->context.id;
if (unlikely(pid == MMU_NO_CONTEXT))
goto no_context;
if (!mm_is_thread_local(mm)) {
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
_tlbie_pid(pid, RIC_FLUSH_PWC);
if (lock_tlbie)
raw_spin_unlock(&native_tlbie_lock);
} else
_tlbiel_pid(pid, RIC_FLUSH_PWC);
no_context:
preempt_enable();
}
/**
* rt_mutex_start_proxy_lock() - Start lock acquisition for another task
* @lock: the rt_mutex to take
* @waiter: the pre-initialized rt_mutex_waiter
* @task: the task to prepare
* @detect_deadlock: perform deadlock detection (1) or not (0)
*
* Returns:
* 0 - task blocked on lock
* 1 - acquired the lock for task, caller should wake it up
* <0 - error
*
* Special API call for FUTEX_REQUEUE_PI support.
*/
int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
struct task_struct *task, int detect_deadlock)
{
unsigned long flags;
int ret;
raw_spin_lock_irqsave(&lock->wait_lock, flags);
if (try_to_take_rt_mutex(lock, task, NULL)) {
raw_spin_unlock(&lock->wait_lock);
return 1;
}
ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock,
flags, 0);
if (ret == -EDEADLK && !rt_mutex_owner(lock)) {
/*
* Reset the return value. We might have
* returned with -EDEADLK and the owner
* released the lock while we were walking the
* pi chain. Let the waiter sort it out.
*/
ret = 0;
}
if (unlikely(ret))
remove_waiter(lock, waiter, flags);
raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
debug_rt_mutex_print_deadlock(waiter);
return ret;
}
/*
* Called from hardirq context every jiffy
*/
void hrtimer_run_queues(void)
{
struct rb_node *node;
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
struct hrtimer_clock_base *base;
int index, gettime = 1;
if (hrtimer_hres_active())
return;
for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
base = &cpu_base->clock_base[index];
if (!base->first)
continue;
if (gettime) {
hrtimer_get_softirq_time(cpu_base);
gettime = 0;
}
raw_spin_lock(&cpu_base->lock);
while ((node = base->first)) {
struct hrtimer *timer;
timer = rb_entry(node, struct hrtimer, node);
if (base->softirq_time.tv64 <=
hrtimer_get_expires_tv64(timer))
break;
__run_hrtimer(timer, &base->softirq_time);
}
raw_spin_unlock(&cpu_base->lock);
}
}
/* applies to both peripheral and syswake interrupts */
static int pdc_irq_set_wake(struct irq_data *data, unsigned int on)
{
struct pdc_intc_priv *priv = irqd_to_priv(data);
irq_hw_number_t hw = data->hwirq;
unsigned int mask = (1 << 16) << hw;
unsigned int dst_irq;
raw_spin_lock(&priv->lock);
if (on)
priv->irq_route |= mask;
else
priv->irq_route &= ~mask;
pdc_write(priv, PDC_IRQ_ROUTE, priv->irq_route);
raw_spin_unlock(&priv->lock);
/* control the destination IRQ wakeup too for standby mode */
if (hwirq_is_syswake(hw))
dst_irq = priv->syswake_irq;
else
dst_irq = priv->perip_irqs[hw];
irq_set_irq_wake(dst_irq, on);
return 0;
}
int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
unsigned long delta_ns, const enum hrtimer_mode mode,
int wakeup)
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
int ret, leftmost;
base = lock_hrtimer_base(timer, &flags);
/* Remove an active timer from the queue: */
ret = remove_hrtimer(timer, base);
if (mode & HRTIMER_MODE_REL) {
tim = ktime_add_safe(tim, base->get_time());
/*
* CONFIG_TIME_LOW_RES is a temporary way for architectures
* to signal that they simply return xtime in
* do_gettimeoffset(). In this case we want to round up by
* resolution when starting a relative timer, to avoid short
* timeouts. This will go away with the GTOD framework.
*/
#ifdef CONFIG_TIME_LOW_RES
tim = ktime_add_safe(tim, base->resolution);
#endif
}
hrtimer_set_expires_range_ns(timer, tim, delta_ns);
/* Switch the timer base, if necessary: */
new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
timer_stats_hrtimer_set_start_info(timer);
leftmost = enqueue_hrtimer(timer, new_base);
/*
* Only allow reprogramming if the new base is on this CPU.
* (it might still be on another CPU if the timer was pending)
*
* XXX send_remote_softirq() ?
*/
if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)
&& hrtimer_enqueue_reprogram(timer, new_base)) {
if (wakeup) {
/*
* We need to drop cpu_base->lock to avoid a
* lock ordering issue vs. rq->lock.
*/
raw_spin_unlock(&new_base->cpu_base->lock);
raise_softirq_irqoff(HRTIMER_SOFTIRQ);
local_irq_restore(flags);
return ret;
} else {
__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
}
}
unlock_hrtimer_base(timer, &flags);
return ret;
}
/*
* High resolution timer interrupt
* Called with interrupts disabled
*/
void hrtimer_interrupt(struct clock_event_device *dev)
{
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
ktime_t expires_next, now, entry_time, delta;
int i, retries = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
raw_spin_lock(&cpu_base->lock);
entry_time = now = hrtimer_update_base(cpu_base);
retry:
expires_next.tv64 = KTIME_MAX;
/*
* We set expires_next to KTIME_MAX here with cpu_base->lock
* held to prevent that a timer is enqueued in our queue via
* the migration code. This does not affect enqueueing of
* timers which run their callback and need to be requeued on
* this CPU.
*/
cpu_base->expires_next.tv64 = KTIME_MAX;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
struct hrtimer_clock_base *base;
struct timerqueue_node *node;
ktime_t basenow;
if (!(cpu_base->active_bases & (1 << i)))
continue;
base = cpu_base->clock_base + i;
basenow = ktime_add(now, base->offset);
while ((node = timerqueue_getnext(&base->active))) {
struct hrtimer *timer;
timer = container_of(node, struct hrtimer, node);
/*
* The immediate goal for using the softexpires is
* minimizing wakeups, not running timers at the
* earliest interrupt after their soft expiration.
* This allows us to avoid using a Priority Search
* Tree, which can answer a stabbing querry for
* overlapping intervals and instead use the simple
* BST we already have.
* We don't add extra wakeups by delaying timers that
* are right-of a not yet expired timer, because that
* timer will have to trigger a wakeup anyway.
*/
if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
ktime_t expires;
expires = ktime_sub(hrtimer_get_expires(timer),
base->offset);
if (expires.tv64 < 0)
expires.tv64 = KTIME_MAX;
if (expires.tv64 < expires_next.tv64)
expires_next = expires;
break;
}
__run_hrtimer(timer, &basenow);
}
}
/*
* Store the new expiry value so the migration code can verify
* against it.
*/
cpu_base->expires_next = expires_next;
raw_spin_unlock(&cpu_base->lock);
/* Reprogramming necessary ? */
if (expires_next.tv64 == KTIME_MAX ||
!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
return;
}
/*
* The next timer was already expired due to:
* - tracing
* - long lasting callbacks
* - being scheduled away when running in a VM
*
* We need to prevent that we loop forever in the hrtimer
* interrupt routine. We give it 3 attempts to avoid
* overreacting on some spurious event.
*
* Acquire base lock for updating the offsets and retrieving
* the current time.
*/
raw_spin_lock(&cpu_base->lock);
now = hrtimer_update_base(cpu_base);
cpu_base->nr_retries++;
if (++retries < 3)
goto retry;
/*
* Give the system a chance to do something else than looping
* here. We stored the entry time, so we know exactly how long
* we spent here. We schedule the next event this amount of
* time away.
*/
cpu_base->nr_hangs++;
cpu_base->hang_detected = 1;
raw_spin_unlock(&cpu_base->lock);
delta = ktime_sub(now, entry_time);
if (delta.tv64 > cpu_base->max_hang_time.tv64)
cpu_base->max_hang_time = delta;
/*
* Limit it to a sensible value as we enforce a longer
* delay. Give the CPU at least 100ms to catch up.
*/
if (delta.tv64 > 100 * NSEC_PER_MSEC)
expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC);
else
expires_next = ktime_add(now, delta);
tick_program_event(expires_next, 1);
printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
ktime_to_ns(delta));
}
static
void dec_pjobs_rtws(struct rtws_rq *rtws_rq, struct sched_rtws_entity *rtws_se)
{
struct rq *rq = rq_of_rtws_rq(rtws_rq);
struct task_struct *p = task_of_rtws_se(rtws_se);
struct sched_rtws_entity *stealable;
struct global_rq * global_rq = rtws_rq->global_rq;
int ret = 0;
WARN_ON(!rtws_prio(p->prio));
WARN_ON(!rtws_rq->nr_running);
rtws_rq->nr_running--;
if (!rtws_rq->nr_running) {
/* If there are no more pjobs to run, we declare this rq idle */
rtws_rq->earliest_dl = 0;
cpudl_set(&rq->rd->rtwsc_cpudl, rq->cpu, 0, 0, 0);
smp_wmb();
} else {
if (!RB_EMPTY_NODE(&rtws_se->stealable_pjob_node))
return;
if (rtws_rq->earliest_dl != rtws_se->job.deadline)
return;
if (!has_stealable_pjobs(rtws_rq))
return;
/* The leftmost stealable pjob and our next pjob share the same deadline */
stealable = rb_entry(rtws_rq->leftmost_stealable_pjob, struct sched_rtws_entity, stealable_pjob_node);
if (stealable->job.deadline > rtws_rq->earliest_dl) {
/*
* If the next pjob has lower priority than the highest priority task on
* global rq, we try to pull that task.
* Clearing the earlieast deadline value (earliest_dl=0) on the rq is
* a trick to allow next's rq statistics update, keeping the current ones.
*/
if (priority_inversion_rtws(rtws_rq, stealable)) {
rtws_rq->earliest_dl = 0;
raw_spin_lock(&global_rq->lock);
ret = pull_task_rtws(rq);
raw_spin_unlock(&global_rq->lock);
if (ret)
return;
}
}
/*
* We update statistics about this rq when next
* pjob has a different deadline than the dequeueing one.
*/
if (rtws_rq->earliest_dl != stealable->job.deadline) {
rtws_rq->earliest_dl = stealable->job.deadline;
cpudl_set(&rq->rd->rtwsc_cpudl, rq->cpu, rtws_rq->earliest_dl, 0, 1);
smp_wmb();
}
}
printk(KERN_INFO "dequeing task %d on cpu %d, current deadline %llu, remaining tasks %lu\n", p->pid, rq->cpu, rtws_rq->earliest_dl, rtws_rq->nr_running);
}
/*
* Task blocks on lock.
*
* Prepare waiter and propagate pi chain
*
* This must be called with lock->wait_lock held.
*/
static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
struct task_struct *task,
int detect_deadlock)
{
struct task_struct *owner = rt_mutex_owner(lock);
struct rt_mutex_waiter *top_waiter = waiter;
unsigned long flags;
int chain_walk = 0, res;
raw_spin_lock_irqsave(&task->pi_lock, flags);
__rt_mutex_adjust_prio(task);
waiter->task = task;
waiter->lock = lock;
plist_node_init(&waiter->list_entry, task->prio);
plist_node_init(&waiter->pi_list_entry, task->prio);
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
top_waiter = rt_mutex_top_waiter(lock);
plist_add(&waiter->list_entry, &lock->wait_list);
task->pi_blocked_on = waiter;
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
if (!owner)
return 0;
if (waiter == rt_mutex_top_waiter(lock)) {
raw_spin_lock_irqsave(&owner->pi_lock, flags);
plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
__rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
chain_walk = 1;
raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
}
else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock))
chain_walk = 1;
if (!chain_walk)
return 0;
/*
* The owner can't disappear while holding a lock,
* so the owner struct is protected by wait_lock.
* Gets dropped in rt_mutex_adjust_prio_chain()!
*/
get_task_struct(owner);
raw_spin_unlock(&lock->wait_lock);
res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock, waiter,
task);
raw_spin_lock(&lock->wait_lock);
return res;
}
/*
* Adjust the priority chain. Also used for deadlock detection.
* Decreases task's usage by one - may thus free the task.
* Returns 0 or -EDEADLK.
*/
static int rt_mutex_adjust_prio_chain(struct task_struct *task,
int deadlock_detect,
struct rt_mutex *orig_lock,
struct rt_mutex_waiter *orig_waiter,
struct task_struct *top_task)
{
struct rt_mutex *lock;
struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
int detect_deadlock, ret = 0, depth = 0;
unsigned long flags;
detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
deadlock_detect);
/*
* The (de)boosting is a step by step approach with a lot of
* pitfalls. We want this to be preemptible and we want hold a
* maximum of two locks per step. So we have to check
* carefully whether things change under us.
*/
again:
if (++depth > max_lock_depth) {
static int prev_max;
/*
* Print this only once. If the admin changes the limit,
* print a new message when reaching the limit again.
*/
if (prev_max != max_lock_depth) {
prev_max = max_lock_depth;
printk(KERN_WARNING "Maximum lock depth %d reached "
"task: %s (%d)\n", max_lock_depth,
top_task->comm, task_pid_nr(top_task));
}
put_task_struct(task);
return deadlock_detect ? -EDEADLK : 0;
}
retry:
/*
* Task can not go away as we did a get_task() before !
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
waiter = task->pi_blocked_on;
/*
* Check whether the end of the boosting chain has been
* reached or the state of the chain has changed while we
* dropped the locks.
*/
if (!waiter)
goto out_unlock_pi;
/*
* Check the orig_waiter state. After we dropped the locks,
* the previous owner of the lock might have released the lock.
*/
if (orig_waiter && !rt_mutex_owner(orig_lock))
goto out_unlock_pi;
/*
* Drop out, when the task has no waiters. Note,
* top_waiter can be NULL, when we are in the deboosting
* mode!
*/
if (top_waiter && (!task_has_pi_waiters(task) ||
top_waiter != task_top_pi_waiter(task)))
goto out_unlock_pi;
/*
* When deadlock detection is off then we check, if further
* priority adjustment is necessary.
*/
if (!detect_deadlock && waiter->list_entry.prio == task->prio)
goto out_unlock_pi;
lock = waiter->lock;
if (!raw_spin_trylock(&lock->wait_lock)) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
cpu_relax();
goto retry;
}
/* Deadlock detection */
if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
raw_spin_unlock(&lock->wait_lock);
ret = deadlock_detect ? -EDEADLK : 0;
goto out_unlock_pi;
}
top_waiter = rt_mutex_top_waiter(lock);
/* Requeue the waiter */
plist_del(&waiter->list_entry, &lock->wait_list);
waiter->list_entry.prio = task->prio;
plist_add(&waiter->list_entry, &lock->wait_list);
/* Release the task */
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
if (!rt_mutex_owner(lock)) {
/*
* If the requeue above changed the top waiter, then we need
* to wake the new top waiter up to try to get the lock.
*/
if (top_waiter != rt_mutex_top_waiter(lock))
wake_up_process(rt_mutex_top_waiter(lock)->task);
raw_spin_unlock(&lock->wait_lock);
goto out_put_task;
}
put_task_struct(task);
/* Grab the next task */
task = rt_mutex_owner(lock);
get_task_struct(task);
raw_spin_lock_irqsave(&task->pi_lock, flags);
if (waiter == rt_mutex_top_waiter(lock)) {
/* Boost the owner */
plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
waiter->pi_list_entry.prio = waiter->list_entry.prio;
plist_add(&waiter->pi_list_entry, &task->pi_waiters);
__rt_mutex_adjust_prio(task);
} else if (top_waiter == waiter) {
/* Deboost the owner */
plist_del(&waiter->pi_list_entry, &task->pi_waiters);
waiter = rt_mutex_top_waiter(lock);
waiter->pi_list_entry.prio = waiter->list_entry.prio;
plist_add(&waiter->pi_list_entry, &task->pi_waiters);
__rt_mutex_adjust_prio(task);
}
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
top_waiter = rt_mutex_top_waiter(lock);
raw_spin_unlock(&lock->wait_lock);
if (!detect_deadlock && waiter != top_waiter)
goto out_put_task;
goto again;
out_unlock_pi:
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
out_put_task:
put_task_struct(task);
return ret;
}
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
{
unsigned int irq, vector;
static int warned;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
for_each_irq_desc(irq, desc) {
int break_affinity = 0;
int set_affinity = 1;
const struct cpumask *affinity;
if (!desc)
continue;
if (irq == 2)
continue;
/* interrupt's are disabled at this point */
raw_spin_lock(&desc->lock);
data = irq_desc_get_irq_data(desc);
affinity = data->affinity;
if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
cpumask_subset(affinity, cpu_online_mask)) {
raw_spin_unlock(&desc->lock);
continue;
}
/*
* Complete the irq move. This cpu is going down and for
* non intr-remapping case, we can't wait till this interrupt
* arrives at this cpu before completing the irq move.
*/
irq_force_complete_move(irq);
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
break_affinity = 1;
affinity = cpu_online_mask;
}
chip = irq_data_get_irq_chip(data);
if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
chip->irq_mask(data);
if (chip->irq_set_affinity)
chip->irq_set_affinity(data, affinity, true);
else if (!(warned++))
set_affinity = 0;
/*
* We unmask if the irq was not marked masked by the
* core code. That respects the lazy irq disable
* behaviour.
*/
if (!irqd_can_move_in_process_context(data) &&
!irqd_irq_masked(data) && chip->irq_unmask)
chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
if (break_affinity && set_affinity)
pr_notice("Broke affinity for irq %i\n", irq);
else if (!set_affinity)
pr_notice("Cannot set affinity for irq %i\n", irq);
}
int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
{
struct clock_event_device *bc, *dev;
int cpu, ret = 0;
ktime_t now;
/*
* If there is no broadcast device, tell the caller not to go
* into deep idle.
*/
if (!tick_broadcast_device.evtdev)
return -EBUSY;
dev = this_cpu_ptr(&tick_cpu_device)->evtdev;
raw_spin_lock(&tick_broadcast_lock);
bc = tick_broadcast_device.evtdev;
cpu = smp_processor_id();
if (state == TICK_BROADCAST_ENTER) {
/*
* If the current CPU owns the hrtimer broadcast
* mechanism, it cannot go deep idle and we do not add
* the CPU to the broadcast mask. We don't have to go
* through the EXIT path as the local timer is not
* shutdown.
*/
ret = broadcast_needs_cpu(bc, cpu);
if (ret)
goto out;
/*
* If the broadcast device is in periodic mode, we
* return.
*/
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
/* If it is a hrtimer based broadcast, return busy */
if (bc->features & CLOCK_EVT_FEAT_HRTIMER)
ret = -EBUSY;
goto out;
}
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
/* Conditionally shut down the local timer. */
broadcast_shutdown_local(bc, dev);
/*
* We only reprogram the broadcast timer if we
* did not mark ourself in the force mask and
* if the cpu local event is earlier than the
* broadcast event. If the current CPU is in
* the force mask, then we are going to be
* woken by the IPI right away; we return
* busy, so the CPU does not try to go deep
* idle.
*/
if (cpumask_test_cpu(cpu, tick_broadcast_force_mask)) {
ret = -EBUSY;
} else if (dev->next_event < bc->next_event) {
tick_broadcast_set_event(bc, cpu, dev->next_event);
/*
* In case of hrtimer broadcasts the
* programming might have moved the
* timer to this cpu. If yes, remove
* us from the broadcast mask and
* return busy.
*/
ret = broadcast_needs_cpu(bc, cpu);
if (ret) {
cpumask_clear_cpu(cpu,
tick_broadcast_oneshot_mask);
}
}
}
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
/*
* The cpu which was handling the broadcast
* timer marked this cpu in the broadcast
* pending mask and fired the broadcast
* IPI. So we are going to handle the expired
* event anyway via the broadcast IPI
* handler. No need to reprogram the timer
* with an already expired event.
*/
if (cpumask_test_and_clear_cpu(cpu,
tick_broadcast_pending_mask))
goto out;
/*
* Bail out if there is no next event.
*/
if (dev->next_event == KTIME_MAX)
goto out;
/*
* If the pending bit is not set, then we are
* either the CPU handling the broadcast
* interrupt or we got woken by something else.
*
* We are not longer in the broadcast mask, so
* if the cpu local expiry time is already
* reached, we would reprogram the cpu local
* timer with an already expired event.
*
* This can lead to a ping-pong when we return
* to idle and therefor rearm the broadcast
* timer before the cpu local timer was able
* to fire. This happens because the forced
* reprogramming makes sure that the event
* will happen in the future and depending on
* the min_delta setting this might be far
* enough out that the ping-pong starts.
*
* If the cpu local next_event has expired
* then we know that the broadcast timer
* next_event has expired as well and
* broadcast is about to be handled. So we
* avoid reprogramming and enforce that the
* broadcast handler, which did not run yet,
* will invoke the cpu local handler.
*
* We cannot call the handler directly from
* here, because we might be in a NOHZ phase
* and we did not go through the irq_enter()
* nohz fixups.
*/
now = ktime_get();
if (dev->next_event <= now) {
cpumask_set_cpu(cpu, tick_broadcast_force_mask);
goto out;
}
/*
* We got woken by something else. Reprogram
* the cpu local timer device.
*/
tick_program_event(dev->next_event, 1);
}
}
out:
raw_spin_unlock(&tick_broadcast_lock);
return ret;
}
/*
* Handle oneshot mode broadcasting
*/
static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
{
struct tick_device *td;
ktime_t now, next_event;
int cpu, next_cpu = 0;
bool bc_local;
raw_spin_lock(&tick_broadcast_lock);
dev->next_event = KTIME_MAX;
next_event = KTIME_MAX;
cpumask_clear(tmpmask);
now = ktime_get();
/* Find all expired events */
for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
/*
* Required for !SMP because for_each_cpu() reports
* unconditionally CPU0 as set on UP kernels.
*/
if (!IS_ENABLED(CONFIG_SMP) &&
cpumask_empty(tick_broadcast_oneshot_mask))
break;
td = &per_cpu(tick_cpu_device, cpu);
if (td->evtdev->next_event <= now) {
cpumask_set_cpu(cpu, tmpmask);
/*
* Mark the remote cpu in the pending mask, so
* it can avoid reprogramming the cpu local
* timer in tick_broadcast_oneshot_control().
*/
cpumask_set_cpu(cpu, tick_broadcast_pending_mask);
} else if (td->evtdev->next_event < next_event) {
next_event = td->evtdev->next_event;
next_cpu = cpu;
}
}
/*
* Remove the current cpu from the pending mask. The event is
* delivered immediately in tick_do_broadcast() !
*/
cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask);
/* Take care of enforced broadcast requests */
cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask);
cpumask_clear(tick_broadcast_force_mask);
/*
* Sanity check. Catch the case where we try to broadcast to
* offline cpus.
*/
if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask)))
cpumask_and(tmpmask, tmpmask, cpu_online_mask);
/*
* Wakeup the cpus which have an expired event.
*/
bc_local = tick_do_broadcast(tmpmask);
/*
* Two reasons for reprogram:
*
* - The global event did not expire any CPU local
* events. This happens in dyntick mode, as the maximum PIT
* delta is quite small.
*
* - There are pending events on sleeping CPUs which were not
* in the event mask
*/
if (next_event != KTIME_MAX)
tick_broadcast_set_event(dev, next_cpu, next_event);
raw_spin_unlock(&tick_broadcast_lock);
if (bc_local) {
td = this_cpu_ptr(&tick_cpu_device);
td->evtdev->event_handler(td->evtdev);
}
}
