summaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/clock.c46
-rw-r--r--kernel/sched/core.c11
-rw-r--r--kernel/sched/cpufreq_schedutil.c39
-rw-r--r--kernel/sched/cputime.c27
-rw-r--r--kernel/sched/deadline.c63
-rw-r--r--kernel/sched/fair.c2
-rw-r--r--kernel/sched/features.h5
-rw-r--r--kernel/sched/loadavg.c20
-rw-r--r--kernel/sched/sched.h9
-rw-r--r--kernel/sched/wait.c39
10 files changed, 188 insertions, 73 deletions
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index a08795e21628..00a45c45beca 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -96,10 +96,10 @@ static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
static int __sched_clock_stable_early = 1;
/*
- * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ * We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset
*/
-static __read_mostly u64 raw_offset;
-static __read_mostly u64 gtod_offset;
+__read_mostly u64 __sched_clock_offset;
+static __read_mostly u64 __gtod_offset;
struct sched_clock_data {
u64 tick_raw;
@@ -131,17 +131,24 @@ static void __set_sched_clock_stable(void)
/*
* Attempt to make the (initial) unstable->stable transition continuous.
*/
- raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
+ __sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
- scd->tick_gtod, gtod_offset,
- scd->tick_raw, raw_offset);
+ scd->tick_gtod, __gtod_offset,
+ scd->tick_raw, __sched_clock_offset);
static_branch_enable(&__sched_clock_stable);
tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
}
-static void __clear_sched_clock_stable(struct work_struct *work)
+static void __sched_clock_work(struct work_struct *work)
+{
+ static_branch_disable(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __sched_clock_work);
+
+static void __clear_sched_clock_stable(void)
{
struct sched_clock_data *scd = this_scd();
@@ -154,17 +161,17 @@ static void __clear_sched_clock_stable(struct work_struct *work)
*
* Still do what we can.
*/
- gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+ __gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod);
printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
- scd->tick_gtod, gtod_offset,
- scd->tick_raw, raw_offset);
+ scd->tick_gtod, __gtod_offset,
+ scd->tick_raw, __sched_clock_offset);
- static_branch_disable(&__sched_clock_stable);
tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
-}
-static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+ if (sched_clock_stable())
+ schedule_work(&sched_clock_work);
+}
void clear_sched_clock_stable(void)
{
@@ -173,7 +180,7 @@ void clear_sched_clock_stable(void)
smp_mb(); /* matches sched_clock_init_late() */
if (sched_clock_running == 2)
- schedule_work(&sched_clock_work);
+ __clear_sched_clock_stable();
}
void sched_clock_init_late(void)
@@ -214,7 +221,7 @@ static inline u64 wrap_max(u64 x, u64 y)
*/
static u64 sched_clock_local(struct sched_clock_data *scd)
{
- u64 now, clock, old_clock, min_clock, max_clock;
+ u64 now, clock, old_clock, min_clock, max_clock, gtod;
s64 delta;
again:
@@ -231,9 +238,10 @@ again:
* scd->tick_gtod + TICK_NSEC);
*/
- clock = scd->tick_gtod + gtod_offset + delta;
- min_clock = wrap_max(scd->tick_gtod, old_clock);
- max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
+ gtod = scd->tick_gtod + __gtod_offset;
+ clock = gtod + delta;
+ min_clock = wrap_max(gtod, old_clock);
+ max_clock = wrap_max(old_clock, gtod + TICK_NSEC);
clock = wrap_max(clock, min_clock);
clock = wrap_min(clock, max_clock);
@@ -317,7 +325,7 @@ u64 sched_clock_cpu(int cpu)
u64 clock;
if (sched_clock_stable())
- return sched_clock() + raw_offset;
+ return sched_clock() + __sched_clock_offset;
if (unlikely(!sched_clock_running))
return 0ull;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e62802c044e1..430b0460db89 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3287,10 +3287,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
struct task_struct *p;
/*
- * Optimization: we know that if all tasks are in
- * the fair class we can call that function directly:
+ * Optimization: we know that if all tasks are in the fair class we can
+ * call that function directly, but only if the @prev task wasn't of a
+ * higher scheduling class, because otherwise those loose the
+ * opportunity to pull in more work from other CPUs.
*/
- if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+ if (likely((prev->sched_class == &idle_sched_class ||
+ prev->sched_class == &fair_sched_class) &&
+ rq->nr_running == rq->cfs.h_nr_running)) {
+
p = fair_sched_class.pick_next_task(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
goto again;
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 8f8de3d4d6b7..54c577578da6 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -36,6 +36,7 @@ struct sugov_policy {
u64 last_freq_update_time;
s64 freq_update_delay_ns;
unsigned int next_freq;
+ unsigned int cached_raw_freq;
/* The next fields are only needed if fast switch cannot be used. */
struct irq_work irq_work;
@@ -52,7 +53,6 @@ struct sugov_cpu {
struct update_util_data update_util;
struct sugov_policy *sg_policy;
- unsigned int cached_raw_freq;
unsigned long iowait_boost;
unsigned long iowait_boost_max;
u64 last_update;
@@ -116,7 +116,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
/**
* get_next_freq - Compute a new frequency for a given cpufreq policy.
- * @sg_cpu: schedutil cpu object to compute the new frequency for.
+ * @sg_policy: schedutil policy object to compute the new frequency for.
* @util: Current CPU utilization.
* @max: CPU capacity.
*
@@ -136,19 +136,18 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
* next_freq (as calculated above) is returned, subject to policy min/max and
* cpufreq driver limitations.
*/
-static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util,
- unsigned long max)
+static unsigned int get_next_freq(struct sugov_policy *sg_policy,
+ unsigned long util, unsigned long max)
{
- struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
unsigned int freq = arch_scale_freq_invariant() ?
policy->cpuinfo.max_freq : policy->cur;
freq = (freq + (freq >> 2)) * util / max;
- if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
+ if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX)
return sg_policy->next_freq;
- sg_cpu->cached_raw_freq = freq;
+ sg_policy->cached_raw_freq = freq;
return cpufreq_driver_resolve_freq(policy, freq);
}
@@ -213,7 +212,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
} else {
sugov_get_util(&util, &max);
sugov_iowait_boost(sg_cpu, &util, &max);
- next_f = get_next_freq(sg_cpu, util, max);
+ next_f = get_next_freq(sg_policy, util, max);
}
sugov_update_commit(sg_policy, time, next_f);
}
@@ -267,7 +266,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu,
sugov_iowait_boost(j_sg_cpu, &util, &max);
}
- return get_next_freq(sg_cpu, util, max);
+ return get_next_freq(sg_policy, util, max);
}
static void sugov_update_shared(struct update_util_data *hook, u64 time,
@@ -580,25 +579,19 @@ static int sugov_start(struct cpufreq_policy *policy)
sg_policy->next_freq = UINT_MAX;
sg_policy->work_in_progress = false;
sg_policy->need_freq_update = false;
+ sg_policy->cached_raw_freq = 0;
for_each_cpu(cpu, policy->cpus) {
struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);
+ memset(sg_cpu, 0, sizeof(*sg_cpu));
sg_cpu->sg_policy = sg_policy;
- if (policy_is_shared(policy)) {
- sg_cpu->util = 0;
- sg_cpu->max = 0;
- sg_cpu->flags = SCHED_CPUFREQ_RT;
- sg_cpu->last_update = 0;
- sg_cpu->cached_raw_freq = 0;
- sg_cpu->iowait_boost = 0;
- sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
- cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
- sugov_update_shared);
- } else {
- cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
- sugov_update_single);
- }
+ sg_cpu->flags = SCHED_CPUFREQ_RT;
+ sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq;
+ cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
+ policy_is_shared(policy) ?
+ sugov_update_shared :
+ sugov_update_single);
}
return 0;
}
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index f3778e2b46c8..aea3135c5d90 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -34,6 +34,18 @@ void disable_sched_clock_irqtime(void)
sched_clock_irqtime = 0;
}
+static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
+ enum cpu_usage_stat idx)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ u64_stats_update_begin(&irqtime->sync);
+ cpustat[idx] += delta;
+ irqtime->total += delta;
+ irqtime->tick_delta += delta;
+ u64_stats_update_end(&irqtime->sync);
+}
+
/*
* Called before incrementing preempt_count on {soft,}irq_enter
* and before decrementing preempt_count on {soft,}irq_exit.
@@ -41,7 +53,6 @@ void disable_sched_clock_irqtime(void)
void irqtime_account_irq(struct task_struct *curr)
{
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
- u64 *cpustat = kcpustat_this_cpu->cpustat;
s64 delta;
int cpu;
@@ -52,22 +63,16 @@ void irqtime_account_irq(struct task_struct *curr)
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
- u64_stats_update_begin(&irqtime->sync);
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
* in that case, so as not to confuse scheduler with a special task
* that do not consume any time, but still wants to run.
*/
- if (hardirq_count()) {
- cpustat[CPUTIME_IRQ] += delta;
- irqtime->tick_delta += delta;
- } else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) {
- cpustat[CPUTIME_SOFTIRQ] += delta;
- irqtime->tick_delta += delta;
- }
-
- u64_stats_update_end(&irqtime->sync);
+ if (hardirq_count())
+ irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+ irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 99b2c33a9fbc..a2ce59015642 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -445,13 +445,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
*
* This function returns true if:
*
- * runtime / (deadline - t) > dl_runtime / dl_period ,
+ * runtime / (deadline - t) > dl_runtime / dl_deadline ,
*
* IOW we can't recycle current parameters.
*
- * Notice that the bandwidth check is done against the period. For
+ * Notice that the bandwidth check is done against the deadline. For
* task with deadline equal to period this is the same of using
- * dl_deadline instead of dl_period in the equation above.
+ * dl_period instead of dl_deadline in the equation above.
*/
static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
struct sched_dl_entity *pi_se, u64 t)
@@ -476,7 +476,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
* of anything below microseconds resolution is actually fiction
* (but still we want to give the user that illusion >;).
*/
- left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+ left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
right = ((dl_se->deadline - t) >> DL_SCALE) *
(pi_se->dl_runtime >> DL_SCALE);
@@ -505,10 +505,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
}
}
+static inline u64 dl_next_period(struct sched_dl_entity *dl_se)
+{
+ return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period;
+}
+
/*
* If the entity depleted all its runtime, and if we want it to sleep
* while waiting for some new execution time to become available, we
- * set the bandwidth enforcement timer to the replenishment instant
+ * set the bandwidth replenishment timer to the replenishment instant
* and try to activate it.
*
* Notice that it is important for the caller to know if the timer
@@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p)
* that it is actually coming from rq->clock and not from
* hrtimer's time base reading.
*/
- act = ns_to_ktime(dl_se->deadline);
+ act = ns_to_ktime(dl_next_period(dl_se));
now = hrtimer_cb_get_time(timer);
delta = ktime_to_ns(now) - rq_clock(rq);
act = ktime_add_ns(act, delta);
@@ -638,6 +643,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
lockdep_unpin_lock(&rq->lock, rf.cookie);
rq = dl_task_offline_migration(rq, p);
rf.cookie = lockdep_pin_lock(&rq->lock);
+ update_rq_clock(rq);
/*
* Now that the task has been migrated to the new RQ and we
@@ -689,6 +695,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
timer->function = dl_task_timer;
}
+/*
+ * During the activation, CBS checks if it can reuse the current task's
+ * runtime and period. If the deadline of the task is in the past, CBS
+ * cannot use the runtime, and so it replenishes the task. This rule
+ * works fine for implicit deadline tasks (deadline == period), and the
+ * CBS was designed for implicit deadline tasks. However, a task with
+ * constrained deadline (deadine < period) might be awakened after the
+ * deadline, but before the next period. In this case, replenishing the
+ * task would allow it to run for runtime / deadline. As in this case
+ * deadline < period, CBS enables a task to run for more than the
+ * runtime / period. In a very loaded system, this can cause a domino
+ * effect, making other tasks miss their deadlines.
+ *
+ * To avoid this problem, in the activation of a constrained deadline
+ * task after the deadline but before the next period, throttle the
+ * task and set the replenishing timer to the begin of the next period,
+ * unless it is boosted.
+ */
+static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
+{
+ struct task_struct *p = dl_task_of(dl_se);
+ struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se));
+
+ if (dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+ dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
+ if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
+ return;
+ dl_se->dl_throttled = 1;
+ }
+}
+
static
int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
{
@@ -922,6 +959,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
__dequeue_dl_entity(dl_se);
}
+static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
+{
+ return dl_se->dl_deadline < dl_se->dl_period;
+}
+
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
{
struct task_struct *pi_task = rt_mutex_get_top_task(p);
@@ -948,6 +990,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
}
/*
+ * Check if a constrained deadline task was activated
+ * after the deadline but before the next period.
+ * If that is the case, the task will be throttled and
+ * the replenishment timer will be set to the next period.
+ */
+ if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+ dl_check_constrained_dl(&p->dl);
+
+ /*
* If p is throttled, we do nothing. In fact, if it exhausted
* its budget it needs a replenishment and, since it now is on
* its rq, the bandwidth timer callback (which clearly has not
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3e88b35ac157..dea138964b91 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5799,7 +5799,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
* Due to large variance we need a large fuzz factor; hackbench in
* particularly is sensitive here.
*/
- if ((avg_idle / 512) < avg_cost)
+ if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
return -1;
time = local_clock();
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 69631fa46c2f..1b3c8189b286 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
*/
SCHED_FEAT(TTWU_QUEUE, true)
+/*
+ * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
+ */
+SCHED_FEAT(SIS_AVG_CPU, false)
+
#ifdef HAVE_RT_PUSH_IPI
/*
* In order to avoid a thundering herd attack of CPUs that are
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 7296b7308eca..f15fb2bdbc0d 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -169,7 +169,7 @@ static inline int calc_load_write_idx(void)
* If the folding window started, make sure we start writing in the
* next idle-delta.
*/
- if (!time_before(jiffies, calc_load_update))
+ if (!time_before(jiffies, READ_ONCE(calc_load_update)))
idx++;
return idx & 1;
@@ -202,8 +202,9 @@ void calc_load_exit_idle(void)
struct rq *this_rq = this_rq();
/*
- * If we're still before the sample window, we're done.
+ * If we're still before the pending sample window, we're done.
*/
+ this_rq->calc_load_update = READ_ONCE(calc_load_update);
if (time_before(jiffies, this_rq->calc_load_update))
return;
@@ -212,7 +213,6 @@ void calc_load_exit_idle(void)
* accounted through the nohz accounting, so skip the entire deal and
* sync up for the next window.
*/
- this_rq->calc_load_update = calc_load_update;
if (time_before(jiffies, this_rq->calc_load_update + 10))
this_rq->calc_load_update += LOAD_FREQ;
}
@@ -308,13 +308,15 @@ calc_load_n(unsigned long load, unsigned long exp,
*/
static void calc_global_nohz(void)
{
+ unsigned long sample_window;
long delta, active, n;
- if (!time_before(jiffies, calc_load_update + 10)) {
+ sample_window = READ_ONCE(calc_load_update);
+ if (!time_before(jiffies, sample_window + 10)) {
/*
* Catch-up, fold however many we are behind still
*/
- delta = jiffies - calc_load_update - 10;
+ delta = jiffies - sample_window - 10;
n = 1 + (delta / LOAD_FREQ);
active = atomic_long_read(&calc_load_tasks);
@@ -324,7 +326,7 @@ static void calc_global_nohz(void)
avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
- calc_load_update += n * LOAD_FREQ;
+ WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ);
}
/*
@@ -352,9 +354,11 @@ static inline void calc_global_nohz(void) { }
*/
void calc_global_load(unsigned long ticks)
{
+ unsigned long sample_window;
long active, delta;
- if (time_before(jiffies, calc_load_update + 10))
+ sample_window = READ_ONCE(calc_load_update);
+ if (time_before(jiffies, sample_window + 10))
return;
/*
@@ -371,7 +375,7 @@ void calc_global_load(unsigned long ticks)
avenrun[1] = calc_load(avenrun[1], EXP_5, active);
avenrun[2] = calc_load(avenrun[2], EXP_15, active);
- calc_load_update += LOAD_FREQ;
+ WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
/*
* In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5cbf92214ad8..767aab3505a8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1869,6 +1869,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { }
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
struct irqtime {
+ u64 total;
u64 tick_delta;
u64 irq_start_time;
struct u64_stats_sync sync;
@@ -1876,16 +1877,20 @@ struct irqtime {
DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
+/*
+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * and never move forward.
+ */
static inline u64 irq_time_read(int cpu)
{
struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
- u64 *cpustat = kcpustat_cpu(cpu).cpustat;
unsigned int seq;
u64 total;
do {
seq = __u64_stats_fetch_begin(&irqtime->sync);
- total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ];
+ total = irqtime->total;
} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
return total;
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4d2ea6f25568..b8c84c6dee64 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -242,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
}
EXPORT_SYMBOL(prepare_to_wait_event);
+/*
+ * Note! These two wait functions are entered with the
+ * wait-queue lock held (and interrupts off in the _irq
+ * case), so there is no race with testing the wakeup
+ * condition in the caller before they add the wait
+ * entry to the wake queue.
+ */
+int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+ if (likely(list_empty(&wait->task_list)))
+ __add_wait_queue_tail(wq, wait);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (signal_pending(current))
+ return -ERESTARTSYS;
+
+ spin_unlock(&wq->lock);
+ schedule();
+ spin_lock(&wq->lock);
+ return 0;
+}
+EXPORT_SYMBOL(do_wait_intr);
+
+int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait)
+{
+ if (likely(list_empty(&wait->task_list)))
+ __add_wait_queue_tail(wq, wait);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (signal_pending(current))
+ return -ERESTARTSYS;
+
+ spin_unlock_irq(&wq->lock);
+ schedule();
+ spin_lock_irq(&wq->lock);
+ return 0;
+}
+EXPORT_SYMBOL(do_wait_intr_irq);
+
/**
* finish_wait - clean up after waiting in a queue
* @q: waitqueue waited on