[PATCH 6/7] sched: Use an accessor to read rq clock

From: Frederic Weisbecker
Date: Sat Apr 06 2013 - 12:46:43 EST

Read the runqueue clock through an accessor. This way
we'll be able to detect and debug stale rq clocks on
full dynticks CPUs.

Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Alessio Igor Bogani <abogani@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Chris Metcalf <cmetcalf@xxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Geoff Levand <geoff@xxxxxxxxxxxxx>
Cc: Gilad Ben Yossef <gilad@xxxxxxxxxxxxx>
Cc: Hakan Akkan <hakanakkan@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Li Zhong <zhong@xxxxxxxxxxxxxxxxxx>
Cc: Namhyung Kim <namhyung.kim@xxxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Paul Turner <pjt@xxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
---
kernel/sched/core.c | 6 +++---
kernel/sched/fair.c | 44 ++++++++++++++++++++++----------------------
kernel/sched/rt.c | 8 ++++----
kernel/sched/sched.h | 10 ++++++++++
kernel/sched/stats.h | 8 ++++----
kernel/sched/stop_task.c | 8 ++++----
6 files changed, 47 insertions(+), 37 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e4ec9d5..9f3f611 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -654,7 +654,7 @@ void sched_avg_update(struct rq *rq)
{
s64 period = sched_avg_period();

- while ((s64)(rq->clock - rq->age_stamp) > period) {
+ while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
/*
* Inline assembly required to prevent the compiler
* optimising this loop into a divmod call.
@@ -1315,7 +1315,7 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
p->sched_class->task_woken(rq, p);

if (rq->idle_stamp) {
- u64 delta = rq->clock - rq->idle_stamp;
+ u64 delta = rq_clock(rq) - rq->idle_stamp;
u64 max = 2*sysctl_sched_migration_cost;

if (delta > max)
@@ -2669,7 +2669,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)

if (task_current(rq, p)) {
update_rq_clock(rq);
- ns = rq->clock_task - p->se.exec_start;
+ ns = rq_clock_task(rq) - p->se.exec_start;
if ((s64)ns < 0)
ns = 0;
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f90e1d8..b765ffa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -686,7 +686,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
- u64 now = rq_of(cfs_rq)->clock_task;
+ u64 now = rq_clock_task(rq_of(cfs_rq));
unsigned long delta_exec;

if (unlikely(!curr))
@@ -718,7 +718,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);
+ schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
}

/*
@@ -738,14 +738,14 @@ static void
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
- rq_of(cfs_rq)->clock - se->statistics.wait_start));
+ rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
- rq_of(cfs_rq)->clock - se->statistics.wait_start);
+ rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
trace_sched_stat_wait(task_of(se),
- rq_of(cfs_rq)->clock - se->statistics.wait_start);
+ rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
}
#endif
schedstat_set(se->statistics.wait_start, 0);
@@ -771,7 +771,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
/*
* We are starting a new run period:
*/
- se->exec_start = rq_of(cfs_rq)->clock_task;
+ se->exec_start = rq_clock_task(rq_of(cfs_rq));
}

/**************************************************
@@ -1497,7 +1497,7 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)

static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
{
- __update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
+ __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
__update_tg_runnable_avg(&rq->avg, &rq->cfs);
}

@@ -1512,7 +1512,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
* accumulated while sleeping.
*/
if (unlikely(se->avg.decay_count <= 0)) {
- se->avg.last_runnable_update = rq_of(cfs_rq)->clock_task;
+ se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq));
if (se->avg.decay_count) {
/*
* In a wake-up migration we have to approximate the
@@ -1586,7 +1586,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
tsk = task_of(se);

if (se->statistics.sleep_start) {
- u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;
+ u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start;

if ((s64)delta < 0)
delta = 0;
@@ -1603,7 +1603,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
}
if (se->statistics.block_start) {
- u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;
+ u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start;

if ((s64)delta < 0)
delta = 0;
@@ -1784,9 +1784,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
struct task_struct *tsk = task_of(se);

if (tsk->state & TASK_INTERRUPTIBLE)
- se->statistics.sleep_start = rq_of(cfs_rq)->clock;
+ se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
if (tsk->state & TASK_UNINTERRUPTIBLE)
- se->statistics.block_start = rq_of(cfs_rq)->clock;
+ se->statistics.block_start = rq_clock(rq_of(cfs_rq));
}
#endif
}
@@ -2061,7 +2061,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
if (unlikely(cfs_rq->throttle_count))
return cfs_rq->throttled_clock_task;

- return rq_of(cfs_rq)->clock_task - cfs_rq->throttled_clock_task_time;
+ return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
}

/* returns 0 on failure to allocate runtime */
@@ -2120,7 +2120,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);

/* if the deadline is ahead of our clock, nothing to do */
- if (likely((s64)(rq->clock - cfs_rq->runtime_expires) < 0))
+ if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
return;

if (cfs_rq->runtime_remaining < 0)
@@ -2209,7 +2209,7 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
#ifdef CONFIG_SMP
if (!cfs_rq->throttle_count) {
/* adjust cfs_rq_clock_task() */
- cfs_rq->throttled_clock_task_time += rq->clock_task -
+ cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
cfs_rq->throttled_clock_task;
}
#endif
@@ -2224,7 +2224,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)

/* group is entering throttled state, stop time */
if (!cfs_rq->throttle_count)
- cfs_rq->throttled_clock_task = rq->clock_task;
+ cfs_rq->throttled_clock_task = rq_clock_task(rq);
cfs_rq->throttle_count++;

return 0;
@@ -2263,7 +2263,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
rq->nr_running -= task_delta;

cfs_rq->throttled = 1;
- cfs_rq->throttled_clock = rq->clock;
+ cfs_rq->throttled_clock = rq_clock(rq);
raw_spin_lock(&cfs_b->lock);
list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
raw_spin_unlock(&cfs_b->lock);
@@ -2283,7 +2283,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
update_rq_clock(rq);

raw_spin_lock(&cfs_b->lock);
- cfs_b->throttled_time += rq->clock - cfs_rq->throttled_clock;
+ cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
list_del_rcu(&cfs_rq->throttled_list);
raw_spin_unlock(&cfs_b->lock);

@@ -2686,7 +2686,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
#else /* CONFIG_CFS_BANDWIDTH */
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
{
- return rq_of(cfs_rq)->clock_task;
+ return rq_clock_task(rq_of(cfs_rq));
}

static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
@@ -3919,7 +3919,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
* 2) too many balance attempts have failed.
*/

- tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
+ tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
if (!tsk_cache_hot ||
env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
#ifdef CONFIG_SCHEDSTATS
@@ -4284,7 +4284,7 @@ static unsigned long scale_rt_power(int cpu)
age_stamp = ACCESS_ONCE(rq->age_stamp);
avg = ACCESS_ONCE(rq->rt_avg);

- total = sched_avg_period() + (rq->clock - age_stamp);
+ total = sched_avg_period() + (rq_clock(rq) - age_stamp);

if (unlikely(total < avg)) {
/* Ensures that power won't end up being negative */
@@ -5217,7 +5217,7 @@ void idle_balance(int this_cpu, struct rq *this_rq)
unsigned long next_balance = jiffies + HZ;

update_nohz_rq_clock(this_rq);
- this_rq->idle_stamp = this_rq->clock;
+ this_rq->idle_stamp = rq_clock(this_rq);

if (this_rq->avg_idle < sysctl_sched_migration_cost)
return;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 127a2c4..3dfffc4 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -926,7 +926,7 @@ static void update_curr_rt(struct rq *rq)
if (curr->sched_class != &rt_sched_class)
return;

- delta_exec = rq->clock_task - curr->se.exec_start;
+ delta_exec = rq_clock_task(rq) - curr->se.exec_start;
if (unlikely((s64)delta_exec <= 0))
return;

@@ -936,7 +936,7 @@ static void update_curr_rt(struct rq *rq)
curr->se.sum_exec_runtime += delta_exec;
account_group_exec_runtime(curr, delta_exec);

- curr->se.exec_start = rq->clock_task;
+ curr->se.exec_start = rq_clock_task(rq);
cpuacct_charge(curr, delta_exec);

sched_rt_avg_update(rq, delta_exec);
@@ -1385,7 +1385,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
} while (rt_rq);

p = rt_task_of(rt_se);
- p->se.exec_start = rq->clock_task;
+ p->se.exec_start = rq_clock_task(rq);

return p;
}
@@ -2037,7 +2037,7 @@ static void set_curr_task_rt(struct rq *rq)
{
struct task_struct *p = rq->curr;

- p->se.exec_start = rq->clock_task;
+ p->se.exec_start = rq_clock_task(rq);

/* The running task is never eligible for pushing */
dequeue_pushable_task(rq, p);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 96f7333..529e318 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -536,6 +536,16 @@ DECLARE_PER_CPU(struct rq, runqueues);
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() (&__raw_get_cpu_var(runqueues))

+static inline u64 rq_clock(struct rq *rq)
+{
+ return rq->clock;
+}
+
+static inline u64 rq_clock_task(struct rq *rq)
+{
+ return rq->clock_task;
+}
+
#ifdef CONFIG_SMP

#define rcu_dereference_check_sched_domain(p) \
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 2ef90a5..17d7065 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -61,7 +61,7 @@ static inline void sched_info_reset_dequeued(struct task_struct *t)
*/
static inline void sched_info_dequeued(struct task_struct *t)
{
- unsigned long long now = task_rq(t)->clock, delta = 0;
+ unsigned long long now = rq_clock(task_rq(t)), delta = 0;

if (unlikely(sched_info_on()))
if (t->sched_info.last_queued)
@@ -79,7 +79,7 @@ static inline void sched_info_dequeued(struct task_struct *t)
*/
static void sched_info_arrive(struct task_struct *t)
{
- unsigned long long now = task_rq(t)->clock, delta = 0;
+ unsigned long long now = rq_clock(task_rq(t)), delta = 0;

if (t->sched_info.last_queued)
delta = now - t->sched_info.last_queued;
@@ -100,7 +100,7 @@ static inline void sched_info_queued(struct task_struct *t)
{
if (unlikely(sched_info_on()))
if (!t->sched_info.last_queued)
- t->sched_info.last_queued = task_rq(t)->clock;
+ t->sched_info.last_queued = rq_clock(task_rq(t));
}

/*
@@ -112,7 +112,7 @@ static inline void sched_info_queued(struct task_struct *t)
*/
static inline void sched_info_depart(struct task_struct *t)
{
- unsigned long long delta = task_rq(t)->clock -
+ unsigned long long delta = rq_clock(task_rq(t)) -
t->sched_info.last_arrival;

rq_sched_info_depart(task_rq(t), delta);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index da5eb5b..e08fbee 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -28,7 +28,7 @@ static struct task_struct *pick_next_task_stop(struct rq *rq)
struct task_struct *stop = rq->stop;

if (stop && stop->on_rq) {
- stop->se.exec_start = rq->clock_task;
+ stop->se.exec_start = rq_clock_task(rq);
return stop;
}

@@ -57,7 +57,7 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
struct task_struct *curr = rq->curr;
u64 delta_exec;

- delta_exec = rq->clock_task - curr->se.exec_start;
+ delta_exec = rq_clock_task(rq) - curr->se.exec_start;
if (unlikely((s64)delta_exec < 0))
delta_exec = 0;

@@ -67,7 +67,7 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
curr->se.sum_exec_runtime += delta_exec;
account_group_exec_runtime(curr, delta_exec);

- curr->se.exec_start = rq->clock_task;
+ curr->se.exec_start = rq_clock_task(rq);
cpuacct_charge(curr, delta_exec);
}

@@ -79,7 +79,7 @@ static void set_curr_task_stop(struct rq *rq)
{
struct task_struct *stop = rq->stop;

- stop->se.exec_start = rq->clock_task;
+ stop->se.exec_start = rq_clock_task(rq);
}

static void switched_to_stop(struct rq *rq, struct task_struct *p)
--
1.7.5.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/