blob: 800191d5768526f2fbcf996945b1e899287d8d63 [file] [log] [blame]
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 3 Jul 2009 08:44:31 -0500
Subject: hrtimer: fixup hrtimer callback changes for preempt-rt
In preempt-rt we can not call the callbacks which take sleeping locks
from the timer interrupt context.
Bring back the softirq split for now, until we fixed the signal
delivery problem for real.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
include/linux/hrtimer.h | 3
kernel/hrtimer.c | 220 ++++++++++++++++++++++++++++++++++++++++-------
kernel/sched/core.c | 1
kernel/sched/rt.c | 1
kernel/time/tick-sched.c | 1
kernel/watchdog.c | 1
6 files changed, 198 insertions(+), 29 deletions(-)
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -111,6 +111,8 @@ struct hrtimer {
enum hrtimer_restart (*function)(struct hrtimer *);
struct hrtimer_clock_base *base;
unsigned long state;
+ struct list_head cb_entry;
+ int irqsafe;
#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
ktime_t praecox;
#endif
@@ -150,6 +152,7 @@ struct hrtimer_clock_base {
int index;
clockid_t clockid;
struct timerqueue_head active;
+ struct list_head expired;
ktime_t resolution;
ktime_t (*get_time)(void);
ktime_t softirq_time;
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -590,8 +590,7 @@ static int hrtimer_reprogram(struct hrti
* When the callback is running, we do not reprogram the clock event
* device. The timer callback is either running on a different CPU or
* the callback is executed in the hrtimer_interrupt context. The
- * reprogramming is handled either by the softirq, which called the
- * callback or at the end of the hrtimer_interrupt.
+ * reprogramming is handled at the end of the hrtimer_interrupt.
*/
if (hrtimer_callback_running(timer))
return 0;
@@ -626,6 +625,9 @@ static int hrtimer_reprogram(struct hrti
return res;
}
+static void __run_hrtimer(struct hrtimer *timer, ktime_t *now);
+static int hrtimer_rt_defer(struct hrtimer *timer);
+
/*
* Initialize the high resolution related parts of cpu_base
*/
@@ -642,9 +644,18 @@ static inline void hrtimer_init_hres(str
* and expiry check is done in the hrtimer_interrupt or in the softirq.
*/
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ int wakeup)
{
- return base->cpu_base->hres_active && hrtimer_reprogram(timer, base);
+ if (!(base->cpu_base->hres_active && hrtimer_reprogram(timer, base)))
+ return 0;
+ if (!wakeup)
+ return -ETIME;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ if (!hrtimer_rt_defer(timer))
+ return -ETIME;
+#endif
+ return 1;
}
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
@@ -725,12 +736,18 @@ static inline int hrtimer_switch_to_hres
static inline void
hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { }
static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
- struct hrtimer_clock_base *base)
+ struct hrtimer_clock_base *base,
+ int wakeup)
{
return 0;
}
static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
static inline void retrigger_next_event(void *arg) { }
+static inline int hrtimer_reprogram(struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
+{
+ return 0;
+}
#endif /* CONFIG_HIGH_RES_TIMERS */
@@ -862,9 +879,9 @@ void hrtimer_wait_for_timer(const struct
{
struct hrtimer_clock_base *base = timer->base;
- if (base && base->cpu_base && !hrtimer_hres_active(base->cpu_base))
+ if (base && base->cpu_base && !timer->irqsafe)
wait_event(base->cpu_base->wait,
- !(timer->state & HRTIMER_STATE_CALLBACK));
+ !(timer->state & HRTIMER_STATE_CALLBACK));
}
#else
@@ -914,6 +931,11 @@ static void __remove_hrtimer(struct hrti
if (!(timer->state & HRTIMER_STATE_ENQUEUED))
goto out;
+ if (unlikely(!list_empty(&timer->cb_entry))) {
+ list_del_init(&timer->cb_entry);
+ goto out;
+ }
+
next_timer = timerqueue_getnext(&base->active);
timerqueue_del(&base->active, &timer->node);
if (&timer->node == next_timer) {
@@ -1021,9 +1043,19 @@ int __hrtimer_start_range_ns(struct hrti
*
* XXX send_remote_softirq() ?
*/
- if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)
- && hrtimer_enqueue_reprogram(timer, new_base)) {
- if (wakeup) {
+ if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) {
+ ret = hrtimer_enqueue_reprogram(timer, new_base, wakeup);
+ if (ret < 0) {
+ /*
+ * In case we failed to reprogram the timer (mostly
+ * because out current timer is already elapsed),
+ * remove it again and report a failure. This avoids
+ * stale base->first entries.
+ */
+ debug_deactivate(timer);
+ __remove_hrtimer(timer, new_base,
+ timer->state & HRTIMER_STATE_CALLBACK, 0);
+ } else if (ret > 0) {
/*
* We need to drop cpu_base->lock to avoid a
* lock ordering issue vs. rq->lock.
@@ -1031,9 +1063,7 @@ int __hrtimer_start_range_ns(struct hrti
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);
+ return 0;
}
}
@@ -1200,6 +1230,7 @@ static void __hrtimer_init(struct hrtime
base = hrtimer_clockid_to_base(clock_id);
timer->base = &cpu_base->clock_base[base];
+ INIT_LIST_HEAD(&timer->cb_entry);
timerqueue_init(&timer->node);
#ifdef CONFIG_TIMER_STATS
@@ -1283,10 +1314,128 @@ static void __run_hrtimer(struct hrtimer
timer->state &= ~HRTIMER_STATE_CALLBACK;
}
-#ifdef CONFIG_HIGH_RES_TIMERS
-
static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer);
+#ifdef CONFIG_PREEMPT_RT_BASE
+static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer,
+ struct hrtimer_clock_base *base)
+{
+ /*
+ * Note, we clear the callback flag before we requeue the
+ * timer otherwise we trigger the callback_running() check
+ * in hrtimer_reprogram().
+ */
+ timer->state &= ~HRTIMER_STATE_CALLBACK;
+
+ if (restart != HRTIMER_NORESTART) {
+ BUG_ON(hrtimer_active(timer));
+ /*
+ * Enqueue the timer, if it's the leftmost timer then
+ * we need to reprogram it.
+ */
+ if (!enqueue_hrtimer(timer, base))
+ return;
+
+#ifndef CONFIG_HIGH_RES_TIMERS
+ }
+#else
+ if (base->cpu_base->hres_active &&
+ hrtimer_reprogram(timer, base))
+ goto requeue;
+
+ } else if (hrtimer_active(timer)) {
+ /*
+ * If the timer was rearmed on another CPU, reprogram
+ * the event device.
+ */
+ if (&timer->node == base->active.next &&
+ base->cpu_base->hres_active &&
+ hrtimer_reprogram(timer, base))
+ goto requeue;
+ }
+ return;
+
+requeue:
+ /*
+ * Timer is expired. Thus move it from tree to pending list
+ * again.
+ */
+ __remove_hrtimer(timer, base, timer->state, 0);
+ list_add_tail(&timer->cb_entry, &base->expired);
+#endif
+}
+
+/*
+ * The changes in mainline which removed the callback modes from
+ * hrtimer are not yet working with -rt. The non wakeup_process()
+ * based callbacks which involve sleeping locks need to be treated
+ * seperately.
+ */
+static void hrtimer_rt_run_pending(void)
+{
+ enum hrtimer_restart (*fn)(struct hrtimer *);
+ struct hrtimer_cpu_base *cpu_base;
+ struct hrtimer_clock_base *base;
+ struct hrtimer *timer;
+ int index, restart;
+
+ local_irq_disable();
+ cpu_base = &per_cpu(hrtimer_bases, smp_processor_id());
+
+ raw_spin_lock(&cpu_base->lock);
+
+ for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
+ base = &cpu_base->clock_base[index];
+
+ while (!list_empty(&base->expired)) {
+ timer = list_first_entry(&base->expired,
+ struct hrtimer, cb_entry);
+
+ /*
+ * Same as the above __run_hrtimer function
+ * just we run with interrupts enabled.
+ */
+ debug_hrtimer_deactivate(timer);
+ __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+ timer_stats_account_hrtimer(timer);
+ fn = timer->function;
+
+ raw_spin_unlock_irq(&cpu_base->lock);
+ restart = fn(timer);
+ raw_spin_lock_irq(&cpu_base->lock);
+
+ hrtimer_rt_reprogram(restart, timer, base);
+ }
+ }
+
+ raw_spin_unlock_irq(&cpu_base->lock);
+
+ wake_up_timer_waiters(cpu_base);
+}
+
+static int hrtimer_rt_defer(struct hrtimer *timer)
+{
+ if (timer->irqsafe)
+ return 0;
+
+ __remove_hrtimer(timer, timer->base, timer->state, 0);
+ list_add_tail(&timer->cb_entry, &timer->base->expired);
+ return 1;
+}
+
+#else
+
+static inline void hrtimer_rt_run_pending(void)
+{
+ hrtimer_peek_ahead_timers();
+}
+
+static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; }
+
+#endif
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+
/*
* High resolution timer interrupt
* Called with interrupts disabled
@@ -1295,7 +1444,7 @@ void hrtimer_interrupt(struct clock_even
{
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
ktime_t expires_next, now, entry_time, delta;
- int i, retries = 0;
+ int i, retries = 0, raise = 0;
BUG_ON(!cpu_base->hres_active);
cpu_base->nr_events++;
@@ -1362,7 +1511,10 @@ retry:
break;
}
- __run_hrtimer(timer, &basenow);
+ if (!hrtimer_rt_defer(timer))
+ __run_hrtimer(timer, &basenow);
+ else
+ raise = 1;
}
}
@@ -1377,6 +1529,10 @@ retry:
if (expires_next.tv64 == KTIME_MAX ||
!tick_program_event(expires_next, 0)) {
cpu_base->hang_detected = 0;
+
+ if (raise)
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+
return;
}
@@ -1457,24 +1613,26 @@ void hrtimer_peek_ahead_timers(void)
local_irq_restore(flags);
}
+#else /* CONFIG_HIGH_RES_TIMERS */
+
+static inline void __hrtimer_peek_ahead_timers(void) { }
+
+#endif /* !CONFIG_HIGH_RES_TIMERS */
+
static void run_hrtimer_softirq(struct softirq_action *h)
{
+#ifdef CONFIG_HIGH_RES_TIMERS
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
if (cpu_base->clock_was_set) {
cpu_base->clock_was_set = 0;
clock_was_set();
}
+#endif
- hrtimer_peek_ahead_timers();
+ hrtimer_rt_run_pending();
}
-#else /* CONFIG_HIGH_RES_TIMERS */
-
-static inline void __hrtimer_peek_ahead_timers(void) { }
-
-#endif /* !CONFIG_HIGH_RES_TIMERS */
-
/*
* Called from timer softirq every jiffy, expire hrtimers:
*
@@ -1507,7 +1665,7 @@ void hrtimer_run_queues(void)
struct timerqueue_node *node;
struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
struct hrtimer_clock_base *base;
- int index, gettime = 1;
+ int index, gettime = 1, raise = 0;
if (hrtimer_hres_active())
return;
@@ -1532,12 +1690,16 @@ void hrtimer_run_queues(void)
hrtimer_get_expires_tv64(timer))
break;
- __run_hrtimer(timer, &base->softirq_time);
+ if (!hrtimer_rt_defer(timer))
+ __run_hrtimer(timer, &base->softirq_time);
+ else
+ raise = 1;
}
raw_spin_unlock(&cpu_base->lock);
}
- wake_up_timer_waiters(cpu_base);
+ if (raise)
+ raise_softirq_irqoff(HRTIMER_SOFTIRQ);
}
/*
@@ -1559,6 +1721,7 @@ static enum hrtimer_restart hrtimer_wake
void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
{
sl->timer.function = hrtimer_wakeup;
+ sl->timer.irqsafe = 1;
sl->task = task;
}
EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
@@ -1695,6 +1858,7 @@ static void __cpuinit init_hrtimers_cpu(
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
cpu_base->clock_base[i].cpu_base = cpu_base;
timerqueue_init_head(&cpu_base->clock_base[i].active);
+ INIT_LIST_HEAD(&cpu_base->clock_base[i].expired);
}
hrtimer_init_hres(cpu_base);
@@ -1813,9 +1977,7 @@ void __init hrtimers_init(void)
hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
register_cpu_notifier(&hrtimers_nb);
-#ifdef CONFIG_HIGH_RES_TIMERS
open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
}
/**
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -489,6 +489,7 @@ static void init_rq_hrtick(struct rq *rq
hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
rq->hrtick_timer.function = hrtick;
+ rq->hrtick_timer.irqsafe = 1;
}
#else /* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -41,6 +41,7 @@ void init_rt_bandwidth(struct rt_bandwid
hrtimer_init(&rt_b->rt_period_timer,
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ rt_b->rt_period_timer.irqsafe = 1;
rt_b->rt_period_timer.function = sched_rt_period_timer;
}
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -867,6 +867,7 @@ void tick_setup_sched_timer(void)
* Emulate tick processing via per-CPU hrtimers:
*/
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ ts->sched_timer.irqsafe = 1;
ts->sched_timer.function = tick_sched_timer;
/* Get the next period (per cpu) */
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -358,6 +358,7 @@ static void watchdog_enable(unsigned int
/* kick off the timer for the hardlockup detector */
hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
hrtimer->function = watchdog_timer_fn;
+ hrtimer->irqsafe = 1;
if (!watchdog_enabled) {
kthread_park(current);