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;
}
static void __run_hrtimer(struct hrtimer *timer)
{
struct hrtimer_clock_base *base = timer->base;
struct hrtimer_cpu_base *cpu_base = base->cpu_base;
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
debug_hrtimer_deactivate(timer);
__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
timer_stats_account_hrtimer(timer);
fn = timer->function;
if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) {
/*
* Used for scheduler timers, avoid lock inversion with
* rq->lock and tasklist_lock.
*
* These timers are required to deal with enqueue expiry
* themselves and are not allowed to migrate.
*/
spin_unlock(&cpu_base->lock);
restart = fn(timer);
spin_lock(&cpu_base->lock);
} else
restart = fn(timer);
/*
* Note: We clear the CALLBACK bit after enqueue_hrtimer to avoid
* reprogramming of the event hardware. This happens at the end of this
* function anyway.
*/
if (restart != HRTIMER_NORESTART) {
BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
enqueue_hrtimer(timer, base, 0);
}
timer->state &= ~HRTIMER_STATE_CALLBACK;
}
/*
* remove hrtimer, called with base lock held
*/
static inline int
remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
{
if (hrtimer_is_queued(timer)) {
int reprogram;
/*
* Remove the timer and force reprogramming when high
* resolution mode is active and the timer is on the current
* CPU. If we remove a timer on another CPU, reprogramming is
* skipped. The interrupt event on this CPU is fired and
* reprogramming happens in the interrupt handler. This is a
* rare case and less expensive than a smp call.
*/
debug_deactivate(timer);
timer_stats_hrtimer_clear_start_info(timer);
reprogram = base->cpu_base == &__get_cpu_var(hrtimer_bases);
__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE,
reprogram);
return 1;
}
return 0;
}
/*
* 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);
struct hrtimer_clock_base *base;
ktime_t expires_next, now;
int i, raise = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
retry:
now = ktime_get();
expires_next.tv64 = KTIME_MAX;
base = cpu_base->clock_base;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
ktime_t basenow;
struct rb_node *node;
spin_lock(&cpu_base->lock);
basenow = ktime_add(now, base->offset);
while ((node = base->first)) {
struct hrtimer *timer;
timer = rb_entry(node, struct hrtimer, node);
if (basenow.tv64 < timer->expires.tv64) {
ktime_t expires;
expires = ktime_sub(timer->expires,
base->offset);
if (expires.tv64 < expires_next.tv64)
expires_next = expires;
break;
}
/* Move softirq callbacks to the pending list */
if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
__remove_hrtimer(timer, base,
HRTIMER_STATE_PENDING, 0);
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
raise = 1;
continue;
}
__run_hrtimer(timer);
}
spin_unlock(&cpu_base->lock);
base++;
}
cpu_base->expires_next = expires_next;
/* Reprogramming necessary ? */
if (expires_next.tv64 != KTIME_MAX) {
if (tick_program_event(expires_next, 0))
goto retry;
}
/* Raise softirq ? */
if (raise)
raise_softirq(HRTIMER_SOFTIRQ);
}
static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
struct hrtimer_clock_base *base,
struct hrtimer *timer, ktime_t *now)
{
enum hrtimer_restart (*fn)(struct hrtimer *);
int restart;
lockdep_assert_held(&cpu_base->lock);
debug_deactivate(timer);
cpu_base->running = timer;
/*
* Separate the ->running assignment from the ->state assignment.
*
* As with a regular write barrier, this ensures the read side in
* hrtimer_active() cannot observe cpu_base->running == NULL &&
* timer->state == INACTIVE.
*/
raw_write_seqcount_barrier(&cpu_base->seq);
__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
timer_stats_account_hrtimer(timer);
fn = timer->function;
/*
* Clear the 'is relative' flag for the TIME_LOW_RES case. If the
* timer is restarted with a period then it becomes an absolute
* timer. If its not restarted it does not matter.
*/
if (IS_ENABLED(CONFIG_TIME_LOW_RES))
timer->is_rel = false;
/*
* 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 running state after enqueue_hrtimer and
* we do not reprogramm the event hardware. Happens either in
* hrtimer_start_range_ns() or in hrtimer_interrupt()
*
* Note: Because we dropped the cpu_base->lock above,
* hrtimer_start_range_ns() can have popped in and enqueued the timer
* for us already.
*/
if (restart != HRTIMER_NORESTART &&
!(timer->state & HRTIMER_STATE_ENQUEUED))
enqueue_hrtimer(timer, base);
/*
* Separate the ->running assignment from the ->state assignment.
*
* As with a regular write barrier, this ensures the read side in
* hrtimer_active() cannot observe cpu_base->running == NULL &&
* timer->state == INACTIVE.
*/
raw_write_seqcount_barrier(&cpu_base->seq);
WARN_ON_ONCE(cpu_base->running != timer);
cpu_base->running = NULL;
}
/*
* 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);
struct hrtimer_clock_base *base;
ktime_t expires_next, now;
int i, raise = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
retry:
now = ktime_get();
expires_next.tv64 = KTIME_MAX;
base = cpu_base->clock_base;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
ktime_t basenow;
struct rb_node *node;
spin_lock(&cpu_base->lock);
basenow = ktime_add(now, base->offset);
while ((node = base->first)) {
struct hrtimer *timer;
timer = rb_entry(node, struct hrtimer, node);
if (basenow.tv64 < timer->expires.tv64) {
ktime_t expires;
expires = ktime_sub(timer->expires,
base->offset);
if (expires.tv64 < expires_next.tv64)
expires_next = expires;
break;
}
/* Move softirq callbacks to the pending list */
if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
__remove_hrtimer(timer, base,
HRTIMER_STATE_PENDING, 0);
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
raise = 1;
continue;
}
__remove_hrtimer(timer, base,
HRTIMER_STATE_CALLBACK, 0);
timer_stats_account_hrtimer(timer);
/*
* Note: We clear the CALLBACK bit after
* enqueue_hrtimer to avoid reprogramming of
* the event hardware. This happens at the end
* of this function anyway.
*/
if (timer->function(timer) != HRTIMER_NORESTART) {
BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
enqueue_hrtimer(timer, base, 0);
}
timer->state &= ~HRTIMER_STATE_CALLBACK;
}
spin_unlock(&cpu_base->lock);
base++;
}
cpu_base->expires_next = expires_next;
/* Reprogramming necessary ? */
if (expires_next.tv64 != KTIME_MAX) {
if (tick_program_event(expires_next, 0))
goto retry;
}
/* Raise softirq ? */
if (raise)
raise_softirq(HRTIMER_SOFTIRQ);
}
/*
* 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);
struct hrtimer_clock_base *base;
ktime_t expires_next, now;
int i, raise = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
dev->next_event.tv64 = KTIME_MAX;
retry:
now = ktime_get();
expires_next.tv64 = KTIME_MAX;
base = cpu_base->clock_base;
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
ktime_t basenow;
struct rb_node *node;
spin_lock(&cpu_base->lock);
basenow = ktime_add(now, base->offset);
while ((node = base->first)) {
struct hrtimer *timer;
timer = rb_entry(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 < expires_next.tv64)
expires_next = expires;
break;
}
/* Move softirq callbacks to the pending list */
if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
__remove_hrtimer(timer, base,
HRTIMER_STATE_PENDING, 0);
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
raise = 1;
continue;
}
__run_hrtimer(timer);
}
spin_unlock(&cpu_base->lock);
base++;
}
cpu_base->expires_next = expires_next;
/* Reprogramming necessary ? */
if (expires_next.tv64 != KTIME_MAX) {
if (tick_program_event(expires_next, 0))
goto retry;
}
/* Raise softirq ? */
if (raise)
raise_softirq(HRTIMER_SOFTIRQ);
}
static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
{
spin_lock_irq(&cpu_base->lock);
while (!list_empty(&cpu_base->cb_pending)) {
enum hrtimer_restart (*fn)(struct hrtimer *);
struct hrtimer *timer;
int restart;
int emulate_hardirq_ctx = 0;
timer = list_entry(cpu_base->cb_pending.next,
struct hrtimer, cb_entry);
debug_hrtimer_deactivate(timer);
timer_stats_account_hrtimer(timer);
fn = timer->function;
/*
* A timer might have been added to the cb_pending list
* when it was migrated during a cpu-offline operation.
* Emulate hardirq context for such timers.
*/
if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED)
emulate_hardirq_ctx = 1;
__remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
spin_unlock_irq(&cpu_base->lock);
if (unlikely(emulate_hardirq_ctx)) {
local_irq_disable();
restart = fn(timer);
local_irq_enable();
} else
restart = fn(timer);
spin_lock_irq(&cpu_base->lock);
timer->state &= ~HRTIMER_STATE_CALLBACK;
if (restart == HRTIMER_RESTART) {
BUG_ON(hrtimer_active(timer));
/*
* Enqueue the timer, allow reprogramming of the event
* device
*/
enqueue_hrtimer(timer, timer->base, 1);
} else if (hrtimer_active(timer)) {
/*
* If the timer was rearmed on another CPU, reprogram
* the event device.
*/
struct hrtimer_clock_base *base = timer->base;
if (base->first == &timer->node &&
hrtimer_reprogram(timer, base)) {
/*
* Timer is expired. Thus move it from tree to
* pending list again.
*/
__remove_hrtimer(timer, base,
HRTIMER_STATE_PENDING, 0);
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
}
}
}
spin_unlock_irq(&cpu_base->lock);
}
