aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched_fair.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched_fair.c')
-rw-r--r--kernel/sched_fair.c598
1 files changed, 359 insertions, 239 deletions
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 0c26e2df450e..e32a9b70ee9c 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -22,6 +22,7 @@
#include <linux/latencytop.h>
#include <linux/sched.h>
+#include <linux/cpumask.h>
/*
* Targeted preemption latency for CPU-bound tasks:
@@ -69,14 +70,6 @@ static unsigned int sched_nr_latency = 8;
unsigned int sysctl_sched_child_runs_first __read_mostly;
/*
- * sys_sched_yield() compat mode
- *
- * This option switches the agressive yield implementation of the
- * old scheduler back on.
- */
-unsigned int __read_mostly sysctl_sched_compat_yield;
-
-/*
* SCHED_OTHER wake-up granularity.
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
@@ -365,6 +358,10 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
}
cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
+#ifndef CONFIG_64BIT
+ smp_wmb();
+ cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
+#endif
}
/*
@@ -419,7 +416,7 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
-static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = cfs_rq->rb_leftmost;
@@ -429,6 +426,17 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
return rb_entry(left, struct sched_entity, run_node);
}
+static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+{
+ struct rb_node *next = rb_next(&se->run_node);
+
+ if (!next)
+ return NULL;
+
+ return rb_entry(next, struct sched_entity, run_node);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
@@ -443,7 +451,6 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
* Scheduling class statistics methods:
*/
-#ifdef CONFIG_SCHED_DEBUG
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
@@ -540,7 +547,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
}
static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+static void update_cfs_shares(struct cfs_rq *cfs_rq);
/*
* Update the current task's runtime statistics. Skip current tasks that
@@ -733,6 +740,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
now - cfs_rq->load_last > 4 * period) {
cfs_rq->load_period = 0;
cfs_rq->load_avg = 0;
+ delta = period - 1;
}
cfs_rq->load_stamp = now;
@@ -763,16 +771,15 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
list_del_leaf_cfs_rq(cfs_rq);
}
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
- long weight_delta)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
long load_weight, load, shares;
- load = cfs_rq->load.weight + weight_delta;
+ load = cfs_rq->load.weight;
load_weight = atomic_read(&tg->load_weight);
- load_weight -= cfs_rq->load_contribution;
load_weight += load;
+ load_weight -= cfs_rq->load_contribution;
shares = (tg->shares * load);
if (load_weight)
@@ -790,7 +797,7 @@ static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
{
if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
}
# else /* CONFIG_SMP */
@@ -798,8 +805,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
{
}
-static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
- long weight_delta)
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
return tg->shares;
}
@@ -824,7 +830,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
account_entity_enqueue(cfs_rq, se);
}
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static void update_cfs_shares(struct cfs_rq *cfs_rq)
{
struct task_group *tg;
struct sched_entity *se;
@@ -838,7 +844,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
if (likely(se->load.weight == tg->shares))
return;
#endif
- shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
+ shares = calc_cfs_shares(cfs_rq, tg);
reweight_entity(cfs_rq_of(se), se, shares);
}
@@ -847,7 +853,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
{
}
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
{
}
@@ -978,8 +984,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
*/
update_curr(cfs_rq);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, se->load.weight);
account_entity_enqueue(cfs_rq, se);
+ update_cfs_shares(cfs_rq);
if (flags & ENQUEUE_WAKEUP) {
place_entity(cfs_rq, se, 0);
@@ -996,19 +1002,49 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
list_add_leaf_cfs_rq(cfs_rq);
}
-static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies_last(struct sched_entity *se)
{
- if (!se || cfs_rq->last == se)
- cfs_rq->last = NULL;
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->last == se)
+ cfs_rq->last = NULL;
+ else
+ break;
+ }
+}
- if (!se || cfs_rq->next == se)
- cfs_rq->next = NULL;
+static void __clear_buddies_next(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->next == se)
+ cfs_rq->next = NULL;
+ else
+ break;
+ }
+}
+
+static void __clear_buddies_skip(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->skip == se)
+ cfs_rq->skip = NULL;
+ else
+ break;
+ }
}
static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- for_each_sched_entity(se)
- __clear_buddies(cfs_rq_of(se), se);
+ if (cfs_rq->last == se)
+ __clear_buddies_last(se);
+
+ if (cfs_rq->next == se)
+ __clear_buddies_next(se);
+
+ if (cfs_rq->skip == se)
+ __clear_buddies_skip(se);
}
static void
@@ -1041,7 +1077,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
update_cfs_load(cfs_rq, 0);
account_entity_dequeue(cfs_rq, se);
update_min_vruntime(cfs_rq);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
/*
* Normalize the entity after updating the min_vruntime because the
@@ -1084,7 +1120,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
return;
if (cfs_rq->nr_running > 1) {
- struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
s64 delta = curr->vruntime - se->vruntime;
if (delta < 0)
@@ -1128,13 +1164,27 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
+/*
+ * Pick the next process, keeping these things in mind, in this order:
+ * 1) keep things fair between processes/task groups
+ * 2) pick the "next" process, since someone really wants that to run
+ * 3) pick the "last" process, for cache locality
+ * 4) do not run the "skip" process, if something else is available
+ */
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
struct sched_entity *left = se;
- if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
- se = cfs_rq->next;
+ /*
+ * Avoid running the skip buddy, if running something else can
+ * be done without getting too unfair.
+ */
+ if (cfs_rq->skip == se) {
+ struct sched_entity *second = __pick_next_entity(se);
+ if (second && wakeup_preempt_entity(second, left) < 1)
+ se = second;
+ }
/*
* Prefer last buddy, try to return the CPU to a preempted task.
@@ -1142,6 +1192,12 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
se = cfs_rq->last;
+ /*
+ * Someone really wants this to run. If it's not unfair, run it.
+ */
+ if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+ se = cfs_rq->next;
+
clear_buddies(cfs_rq, se);
return se;
@@ -1282,12 +1338,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
struct cfs_rq *cfs_rq = cfs_rq_of(se);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
hrtick_update(rq);
}
+static void set_next_buddy(struct sched_entity *se);
+
/*
* The dequeue_task method is called before nr_running is
* decreased. We remove the task from the rbtree and
@@ -1297,14 +1355,22 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
+ int task_sleep = flags & DEQUEUE_SLEEP;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
dequeue_entity(cfs_rq, se, flags);
/* Don't dequeue parent if it has other entities besides us */
- if (cfs_rq->load.weight)
+ if (cfs_rq->load.weight) {
+ /*
+ * Bias pick_next to pick a task from this cfs_rq, as
+ * p is sleeping when it is within its sched_slice.
+ */
+ if (task_sleep && parent_entity(se))
+ set_next_buddy(parent_entity(se));
break;
+ }
flags |= DEQUEUE_SLEEP;
}
@@ -1312,66 +1378,33 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
struct cfs_rq *cfs_rq = cfs_rq_of(se);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
hrtick_update(rq);
}
-/*
- * sched_yield() support is very simple - we dequeue and enqueue.
- *
- * If compat_yield is turned on then we requeue to the end of the tree.
- */
-static void yield_task_fair(struct rq *rq)
-{
- struct task_struct *curr = rq->curr;
- struct cfs_rq *cfs_rq = task_cfs_rq(curr);
- struct sched_entity *rightmost, *se = &curr->se;
-
- /*
- * Are we the only task in the tree?
- */
- if (unlikely(cfs_rq->nr_running == 1))
- return;
-
- clear_buddies(cfs_rq, se);
-
- if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
- update_rq_clock(rq);
- /*
- * Update run-time statistics of the 'current'.
- */
- update_curr(cfs_rq);
-
- return;
- }
- /*
- * Find the rightmost entry in the rbtree:
- */
- rightmost = __pick_last_entity(cfs_rq);
- /*
- * Already in the rightmost position?
- */
- if (unlikely(!rightmost || entity_before(rightmost, se)))
- return;
-
- /*
- * Minimally necessary key value to be last in the tree:
- * Upon rescheduling, sched_class::put_prev_task() will place
- * 'current' within the tree based on its new key value.
- */
- se->vruntime = rightmost->vruntime + 1;
-}
-
#ifdef CONFIG_SMP
-static void task_waking_fair(struct rq *rq, struct task_struct *p)
+static void task_waking_fair(struct task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ u64 min_vruntime;
- se->vruntime -= cfs_rq->min_vruntime;
+#ifndef CONFIG_64BIT
+ u64 min_vruntime_copy;
+
+ do {
+ min_vruntime_copy = cfs_rq->min_vruntime_copy;
+ smp_rmb();
+ min_vruntime = cfs_rq->min_vruntime;
+ } while (min_vruntime != min_vruntime_copy);
+#else
+ min_vruntime = cfs_rq->min_vruntime;
+#endif
+
+ se->vruntime -= min_vruntime;
}
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1551,7 +1584,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
}
/* Adjust by relative CPU power of the group */
- avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+ avg_load = (avg_load * SCHED_POWER_SCALE) / group->cpu_power;
if (local_group) {
this_load = avg_load;
@@ -1616,6 +1649,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
/*
* Otherwise, iterate the domains and find an elegible idle cpu.
*/
+ rcu_read_lock();
for_each_domain(target, sd) {
if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
break;
@@ -1635,6 +1669,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
break;
}
+ rcu_read_unlock();
return target;
}
@@ -1651,7 +1686,7 @@ static int select_idle_sibling(struct task_struct *p, int target)
* preempt must be disabled.
*/
static int
-select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags)
+select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
int cpu = smp_processor_id();
@@ -1667,6 +1702,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
new_cpu = prev_cpu;
}
+ rcu_read_lock();
for_each_domain(cpu, tmp) {
if (!(tmp->flags & SD_LOAD_BALANCE))
continue;
@@ -1686,7 +1722,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
nr_running += cpu_rq(i)->cfs.nr_running;
}
- capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
+ capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE);
if (tmp->flags & SD_POWERSAVINGS_BALANCE)
nr_running /= 2;
@@ -1717,9 +1753,10 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
if (affine_sd) {
if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
- return select_idle_sibling(p, cpu);
- else
- return select_idle_sibling(p, prev_cpu);
+ prev_cpu = cpu;
+
+ new_cpu = select_idle_sibling(p, prev_cpu);
+ goto unlock;
}
while (sd) {
@@ -1760,6 +1797,8 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
}
/* while loop will break here if sd == NULL */
}
+unlock:
+ rcu_read_unlock();
return new_cpu;
}
@@ -1783,10 +1822,7 @@ wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
* This is especially important for buddies when the leftmost
* task is higher priority than the buddy.
*/
- if (unlikely(se->load.weight != NICE_0_LOAD))
- gran = calc_delta_fair(gran, se);
-
- return gran;
+ return calc_delta_fair(gran, se);
}
/*
@@ -1820,18 +1856,26 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
static void set_last_buddy(struct sched_entity *se)
{
- if (likely(task_of(se)->policy != SCHED_IDLE)) {
- for_each_sched_entity(se)
- cfs_rq_of(se)->last = se;
- }
+ if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+ return;
+
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->last = se;
}
static void set_next_buddy(struct sched_entity *se)
{
- if (likely(task_of(se)->policy != SCHED_IDLE)) {
- for_each_sched_entity(se)
- cfs_rq_of(se)->next = se;
- }
+ if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
+ return;
+
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->next = se;
+}
+
+static void set_skip_buddy(struct sched_entity *se)
+{
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->skip = se;
}
/*
@@ -1843,12 +1887,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
struct sched_entity *se = &curr->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
int scale = cfs_rq->nr_running >= sched_nr_latency;
+ int next_buddy_marked = 0;
if (unlikely(se == pse))
return;
- if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
+ if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) {
set_next_buddy(pse);
+ next_buddy_marked = 1;
+ }
/*
* We can come here with TIF_NEED_RESCHED already set from new task
@@ -1857,16 +1904,18 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
if (test_tsk_need_resched(curr))
return;
+ /* Idle tasks are by definition preempted by non-idle tasks. */
+ if (unlikely(curr->policy == SCHED_IDLE) &&
+ likely(p->policy != SCHED_IDLE))
+ goto preempt;
+
/*
- * Batch and idle tasks do not preempt (their preemption is driven by
- * the tick):
+ * Batch and idle tasks do not preempt non-idle tasks (their preemption
+ * is driven by the tick):
*/
if (unlikely(p->policy != SCHED_NORMAL))
return;
- /* Idle tasks are by definition preempted by everybody. */
- if (unlikely(curr->policy == SCHED_IDLE))
- goto preempt;
if (!sched_feat(WAKEUP_PREEMPT))
return;
@@ -1874,8 +1923,15 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
update_curr(cfs_rq);
find_matching_se(&se, &pse);
BUG_ON(!pse);
- if (wakeup_preempt_entity(se, pse) == 1)
+ if (wakeup_preempt_entity(se, pse) == 1) {
+ /*
+ * Bias pick_next to pick the sched entity that is
+ * triggering this preemption.
+ */
+ if (!next_buddy_marked)
+ set_next_buddy(pse);
goto preempt;
+ }
return;
@@ -1932,6 +1988,51 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
}
}
+/*
+ * sched_yield() is very simple
+ *
+ * The magic of dealing with the ->skip buddy is in pick_next_entity.
+ */
+static void yield_task_fair(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+ struct sched_entity *se = &curr->se;
+
+ /*
+ * Are we the only task in the tree?
+ */
+ if (unlikely(rq->nr_running == 1))
+ return;
+
+ clear_buddies(cfs_rq, se);
+
+ if (curr->policy != SCHED_BATCH) {
+ update_rq_clock(rq);
+ /*
+ * Update run-time statistics of the 'current'.
+ */
+ update_curr(cfs_rq);
+ }
+
+ set_skip_buddy(se);
+}
+
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+ struct sched_entity *se = &p->se;
+
+ if (!se->on_rq)
+ return false;
+
+ /* Tell the scheduler that we'd really like pse to run next. */
+ set_next_buddy(se);
+
+ yield_task_fair(rq);
+
+ return true;
+}
+
#ifdef CONFIG_SMP
/**************************************************
* Fair scheduling class load-balancing methods:
@@ -2041,23 +2142,22 @@ static unsigned long
balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move, struct sched_domain *sd,
enum cpu_idle_type idle, int *all_pinned,
- int *this_best_prio, struct cfs_rq *busiest_cfs_rq)
+ struct cfs_rq *busiest_cfs_rq)
{
- int loops = 0, pulled = 0, pinned = 0;
+ int loops = 0, pulled = 0;
long rem_load_move = max_load_move;
struct task_struct *p, *n;
if (max_load_move == 0)
goto out;
- pinned = 1;
-
list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) {
if (loops++ > sysctl_sched_nr_migrate)
break;
if ((p->se.load.weight >> 1) > rem_load_move ||
- !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned))
+ !can_migrate_task(p, busiest, this_cpu, sd, idle,
+ all_pinned))
continue;
pull_task(busiest, p, this_rq, this_cpu);
@@ -2080,9 +2180,6 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
*/
if (rem_load_move <= 0)
break;
-
- if (p->prio < *this_best_prio)
- *this_best_prio = p->prio;
}
out:
/*
@@ -2092,9 +2189,6 @@ out:
*/
schedstat_add(sd, lb_gained[idle], pulled);
- if (all_pinned)
- *all_pinned = pinned;
-
return max_load_move - rem_load_move;
}
@@ -2123,7 +2217,7 @@ static int update_shares_cpu(struct task_group *tg, int cpu)
* We need to update shares after updating tg->load_weight in
* order to adjust the weight of groups with long running tasks.
*/
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -2145,7 +2239,7 @@ static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, int *this_best_prio)
+ int *all_pinned)
{
long rem_load_move = max_load_move;
int busiest_cpu = cpu_of(busiest);
@@ -2170,7 +2264,7 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
rem_load = div_u64(rem_load, busiest_h_load + 1);
moved_load = balance_tasks(this_rq, this_cpu, busiest,
- rem_load, sd, idle, all_pinned, this_best_prio,
+ rem_load, sd, idle, all_pinned,
busiest_cfs_rq);
if (!moved_load)
@@ -2196,11 +2290,11 @@ static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, int *this_best_prio)
+ int *all_pinned)
{
return balance_tasks(this_rq, this_cpu, busiest,
max_load_move, sd, idle, all_pinned,
- this_best_prio, &busiest->cfs);
+ &busiest->cfs);
}
#endif
@@ -2217,12 +2311,11 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
int *all_pinned)
{
unsigned long total_load_moved = 0, load_moved;
- int this_best_prio = this_rq->curr->prio;
do {
load_moved = load_balance_fair(this_rq, this_cpu, busiest,
max_load_move - total_load_moved,
- sd, idle, all_pinned, &this_best_prio);
+ sd, idle, all_pinned);
total_load_moved += load_moved;
@@ -2477,7 +2570,7 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
{
- return SCHED_LOAD_SCALE;
+ return SCHED_POWER_SCALE;
}
unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
@@ -2514,10 +2607,10 @@ unsigned long scale_rt_power(int cpu)
available = total - rq->rt_avg;
}
- if (unlikely((s64)total < SCHED_LOAD_SCALE))
- total = SCHED_LOAD_SCALE;
+ if (unlikely((s64)total < SCHED_POWER_SCALE))
+ total = SCHED_POWER_SCALE;
- total >>= SCHED_LOAD_SHIFT;
+ total >>= SCHED_POWER_SHIFT;
return div_u64(available, total);
}
@@ -2525,7 +2618,7 @@ unsigned long scale_rt_power(int cpu)
static void update_cpu_power(struct sched_domain *sd, int cpu)
{
unsigned long weight = sd->span_weight;
- unsigned long power = SCHED_LOAD_SCALE;
+ unsigned long power = SCHED_POWER_SCALE;
struct sched_group *sdg = sd->groups;
if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
@@ -2534,7 +2627,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
else
power *= default_scale_smt_power(sd, cpu);
- power >>= SCHED_LOAD_SHIFT;
+ power >>= SCHED_POWER_SHIFT;
}
sdg->cpu_power_orig = power;
@@ -2544,10 +2637,10 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
else
power *= default_scale_freq_power(sd, cpu);
- power >>= SCHED_LOAD_SHIFT;
+ power >>= SCHED_POWER_SHIFT;
power *= scale_rt_power(cpu);
- power >>= SCHED_LOAD_SHIFT;
+ power >>= SCHED_POWER_SHIFT;
if (!power)
power = 1;
@@ -2589,9 +2682,9 @@ static inline int
fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
{
/*
- * Only siblings can have significantly less than SCHED_LOAD_SCALE
+ * Only siblings can have significantly less than SCHED_POWER_SCALE
*/
- if (sd->level != SD_LV_SIBLING)
+ if (!(sd->flags & SD_SHARE_CPUPOWER))
return 0;
/*
@@ -2610,7 +2703,6 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
* @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @sd_idle: Idle status of the sched_domain containing group.
* @local_group: Does group contain this_cpu.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
@@ -2618,7 +2710,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
*/
static inline void update_sg_lb_stats(struct sched_domain *sd,
struct sched_group *group, int this_cpu,
- enum cpu_idle_type idle, int load_idx, int *sd_idle,
+ enum cpu_idle_type idle, int load_idx,
int local_group, const struct cpumask *cpus,
int *balance, struct sg_lb_stats *sgs)
{
@@ -2638,9 +2730,6 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
for_each_cpu_and(i, sched_group_cpus(group), cpus) {
struct rq *rq = cpu_rq(i);
- if (*sd_idle && rq->nr_running)
- *sd_idle = 0;
-
/* Bias balancing toward cpus of our domain */
if (local_group) {
if (idle_cpu(i) && !first_idle_cpu) {
@@ -2681,11 +2770,11 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
}
/* Adjust by relative CPU power of the group */
- sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
+ sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->cpu_power;
/*
* Consider the group unbalanced when the imbalance is larger
- * than the average weight of two tasks.
+ * than the average weight of a task.
*
* APZ: with cgroup the avg task weight can vary wildly and
* might not be a suitable number - should we keep a
@@ -2695,10 +2784,11 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
if (sgs->sum_nr_running)
avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
- if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
+ if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
sgs->group_imb = 1;
- sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+ sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power,
+ SCHED_POWER_SCALE);
if (!sgs->group_capacity)
sgs->group_capacity = fix_small_capacity(sd, group);
sgs->group_weight = group->group_weight;
@@ -2755,15 +2845,13 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
* @sd: sched_domain whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
- * @sd_idle: Idle status of the sched_domain containing sg.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
*/
static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
- enum cpu_idle_type idle, int *sd_idle,
- const struct cpumask *cpus, int *balance,
- struct sd_lb_stats *sds)
+ enum cpu_idle_type idle, const struct cpumask *cpus,
+ int *balance, struct sd_lb_stats *sds)
{
struct sched_domain *child = sd->child;
struct sched_group *sg = sd->groups;
@@ -2781,7 +2869,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg));
memset(&sgs, 0, sizeof(sgs));
- update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, sd_idle,
+ update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx,
local_group, cpus, balance, &sgs);
if (local_group && !(*balance))
@@ -2874,7 +2962,7 @@ static int check_asym_packing(struct sched_domain *sd,
return 0;
*imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->cpu_power,
- SCHED_LOAD_SCALE);
+ SCHED_POWER_SCALE);
return 1;
}
@@ -2903,7 +2991,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
cpu_avg_load_per_task(this_cpu);
scaled_busy_load_per_task = sds->busiest_load_per_task
- * SCHED_LOAD_SCALE;
+ * SCHED_POWER_SCALE;
scaled_busy_load_per_task /= sds->busiest->cpu_power;
if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
@@ -2922,10 +3010,10 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
min(sds->busiest_load_per_task, sds->max_load);
pwr_now += sds->this->cpu_power *
min(sds->this_load_per_task, sds->this_load);
- pwr_now /= SCHED_LOAD_SCALE;
+ pwr_now /= SCHED_POWER_SCALE;
/* Amount of load we'd subtract */
- tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+ tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
sds->busiest->cpu_power;
if (sds->max_load > tmp)
pwr_move += sds->busiest->cpu_power *
@@ -2933,15 +3021,15 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
/* Amount of load we'd add */
if (sds->max_load * sds->busiest->cpu_power <
- sds->busiest_load_per_task * SCHED_LOAD_SCALE)
+ sds->busiest_load_per_task * SCHED_POWER_SCALE)
tmp = (sds->max_load * sds->busiest->cpu_power) /
sds->this->cpu_power;
else
- tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+ tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
sds->this->cpu_power;
pwr_move += sds->this->cpu_power *
min(sds->this_load_per_task, sds->this_load + tmp);
- pwr_move /= SCHED_LOAD_SCALE;
+ pwr_move /= SCHED_POWER_SCALE;
/* Move if we gain throughput */
if (pwr_move > pwr_now)
@@ -2983,7 +3071,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
load_above_capacity = (sds->busiest_nr_running -
sds->busiest_group_capacity);
- load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE);
+ load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE);
load_above_capacity /= sds->busiest->cpu_power;
}
@@ -3003,11 +3091,11 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
/* How much load to actually move to equalise the imbalance */
*imbalance = min(max_pull * sds->busiest->cpu_power,
(sds->avg_load - sds->this_load) * sds->this->cpu_power)
- / SCHED_LOAD_SCALE;
+ / SCHED_POWER_SCALE;
/*
* if *imbalance is less than the average load per runnable task
- * there is no gaurantee that any tasks will be moved so we'll have
+ * there is no guarantee that any tasks will be moved so we'll have
* a think about bumping its value to force at least one task to be
* moved
*/
@@ -3033,7 +3121,6 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
* @imbalance: Variable which stores amount of weighted load which should
* be moved to restore balance/put a group to idle.
* @idle: The idle status of this_cpu.
- * @sd_idle: The idleness of sd
* @cpus: The set of CPUs under consideration for load-balancing.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
@@ -3046,7 +3133,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
unsigned long *imbalance, enum cpu_idle_type idle,
- int *sd_idle, const struct cpumask *cpus, int *balance)
+ const struct cpumask *cpus, int *balance)
{
struct sd_lb_stats sds;
@@ -3056,22 +3143,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
* Compute the various statistics relavent for load balancing at
* this level.
*/
- update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
- balance, &sds);
-
- /* Cases where imbalance does not exist from POV of this_cpu */
- /* 1) this_cpu is not the appropriate cpu to perform load balancing
- * at this level.
- * 2) There is no busy sibling group to pull from.
- * 3) This group is the busiest group.
- * 4) This group is more busy than the avg busieness at this
- * sched_domain.
- * 5) The imbalance is within the specified limit.
- *
- * Note: when doing newidle balance, if the local group has excess
- * capacity (i.e. nr_running < group_capacity) and the busiest group
- * does not have any capacity, we force a load balance to pull tasks
- * to the local group. In this case, we skip past checks 3, 4 and 5.
+ update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds);
+
+ /*
+ * this_cpu is not the appropriate cpu to perform load balancing at
+ * this level.
*/
if (!(*balance))
goto ret;
@@ -3080,41 +3156,56 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
check_asym_packing(sd, &sds, this_cpu, imbalance))
return sds.busiest;
+ /* There is no busy sibling group to pull tasks from */
if (!sds.busiest || sds.busiest_nr_running == 0)
goto out_balanced;
- /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+ sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr;
+
+ /*
+ * If the busiest group is imbalanced the below checks don't
+ * work because they assumes all things are equal, which typically
+ * isn't true due to cpus_allowed constraints and the like.
+ */
+ if (sds.group_imb)
+ goto force_balance;
+
+ /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
!sds.busiest_has_capacity)
goto force_balance;
+ /*
+ * If the local group is more busy than the selected busiest group
+ * don't try and pull any tasks.
+ */
if (sds.this_load >= sds.max_load)
goto out_balanced;
- sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
-
+ /*
+ * Don't pull any tasks if this group is already above the domain
+ * average load.
+ */
if (sds.this_load >= sds.avg_load)
goto out_balanced;
- /*
- * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
- * And to check for busy balance use !idle_cpu instead of
- * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
- * even when they are idle.
- */
- if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
- if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
- goto out_balanced;
- } else {
+ if (idle == CPU_IDLE) {
/*
* This cpu is idle. If the busiest group load doesn't
* have more tasks than the number of available cpu's and
* there is no imbalance between this and busiest group
* wrt to idle cpu's, it is balanced.
*/
- if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
+ if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
sds.busiest_nr_running <= sds.busiest_group_weight)
goto out_balanced;
+ } else {
+ /*
+ * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
+ * imbalance_pct to be conservative.
+ */
+ if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+ goto out_balanced;
}
force_balance:
@@ -3148,7 +3239,8 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
for_each_cpu(i, sched_group_cpus(group)) {
unsigned long power = power_of(i);
- unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
+ unsigned long capacity = DIV_ROUND_CLOSEST(power,
+ SCHED_POWER_SCALE);
unsigned long wl;
if (!capacity)
@@ -3173,7 +3265,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
* the load can be moved away from the cpu that is potentially
* running at a lower capacity.
*/
- wl = (wl * SCHED_LOAD_SCALE) / power;
+ wl = (wl * SCHED_POWER_SCALE) / power;
if (wl > max_load) {
max_load = wl;
@@ -3193,7 +3285,7 @@ find_busiest_queue(struct sched_domain *sd, struct sched_group *group,
/* Working cpumask for load_balance and load_balance_newidle. */
static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
-static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
+static int need_active_balance(struct sched_domain *sd, int idle,
int busiest_cpu, int this_cpu)
{
if (idle == CPU_NEWLY_IDLE) {
@@ -3225,10 +3317,6 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
* move_tasks() will succeed. ld_moved will be true and this
* active balance code will not be triggered.
*/
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- return 0;
-
if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
return 0;
}
@@ -3246,7 +3334,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
- int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+ int ld_moved, all_pinned = 0, active_balance = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
@@ -3255,20 +3343,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
cpumask_copy(cpus, cpu_active_mask);
- /*
- * When power savings policy is enabled for the parent domain, idle
- * sibling can pick up load irrespective of busy siblings. In this case,
- * let the state of idle sibling percolate up as CPU_IDLE, instead of
- * portraying it as CPU_NOT_IDLE.
- */
- if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- sd_idle = 1;
-
schedstat_inc(sd, lb_count[idle]);
redo:
- group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+ group = find_busiest_group(sd, this_cpu, &imbalance, idle,
cpus, balance);
if (*balance == 0)
@@ -3297,6 +3375,7 @@ redo:
* still unbalanced. ld_moved simply stays zero, so it is
* correctly treated as an imbalance.
*/
+ all_pinned = 1;
local_irq_save(flags);
double_rq_lock(this_rq, busiest);
ld_moved = move_tasks(this_rq, this_cpu, busiest,
@@ -3330,8 +3409,7 @@ redo:
if (idle != CPU_NEWLY_IDLE)
sd->nr_balance_failed++;
- if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
- this_cpu)) {
+ if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) {
raw_spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the active_load_balance_cpu_stop,
@@ -3386,10 +3464,6 @@ redo:
sd->balance_interval *= 2;
}
- if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- ld_moved = -1;
-
goto out;
out_balanced:
@@ -3403,11 +3477,7 @@ out_one_pinned:
(sd->balance_interval < sd->max_interval))
sd->balance_interval *= 2;
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- ld_moved = -1;
- else
- ld_moved = 0;
+ ld_moved = 0;
out:
return ld_moved;
}
@@ -3433,6 +3503,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
raw_spin_unlock(&this_rq->lock);
update_shares(this_cpu);
+ rcu_read_lock();
for_each_domain(this_cpu, sd) {
unsigned long interval;
int balance = 1;
@@ -3454,6 +3525,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
break;
}
}
+ rcu_read_unlock();
raw_spin_lock(&this_rq->lock);
@@ -3502,6 +3574,7 @@ static int active_load_balance_cpu_stop(void *data)
double_lock_balance(busiest_rq, target_rq);
/* Search for an sd spanning us and the target CPU. */
+ rcu_read_lock();
for_each_domain(target_cpu, sd) {
if ((sd->flags & SD_LOAD_BALANCE) &&
cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
@@ -3517,6 +3590,7 @@ static int active_load_balance_cpu_stop(void *data)
else
schedstat_inc(sd, alb_failed);
}
+ rcu_read_unlock();
double_unlock_balance(busiest_rq, target_rq);
out_unlock:
busiest_rq->active_balance = 0;
@@ -3643,6 +3717,7 @@ static int find_new_ilb(int cpu)
{
struct sched_domain *sd;
struct sched_group *ilb_group;
+ int ilb = nr_cpu_ids;
/*
* Have idle load balancer selection from semi-idle packages only
@@ -3658,20 +3733,25 @@ static int find_new_ilb(int cpu)
if (cpumask_weight(nohz.idle_cpus_mask) < 2)
goto out_done;
+ rcu_read_lock();
for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
ilb_group = sd->groups;
do {
- if (is_semi_idle_group(ilb_group))
- return cpumask_first(nohz.grp_idle_mask);
+ if (is_semi_idle_group(ilb_group)) {
+ ilb = cpumask_first(nohz.grp_idle_mask);
+ goto unlock;
+ }
ilb_group = ilb_group->next;
} while (ilb_group != sd->groups);
}
+unlock:
+ rcu_read_unlock();
out_done:
- return nr_cpu_ids;
+ return ilb;
}
#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
static inline int find_new_ilb(int call_cpu)
@@ -3786,6 +3866,17 @@ void select_nohz_load_balancer(int stop_tick)
static DEFINE_SPINLOCK(balancing);
+static unsigned long __read_mostly max_load_balance_interval = HZ/10;
+
+/*
+ * Scale the max load_balance interval with the number of CPUs in the system.
+ * This trades load-balance latency on larger machines for less cross talk.
+ */
+static void update_max_interval(void)
+{
+ max_load_balance_interval = HZ*num_online_cpus()/10;
+}
+
/*
* It checks each scheduling domain to see if it is due to be balanced,
* and initiates a balancing operation if so.
@@ -3805,6 +3896,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
update_shares(cpu);
+ rcu_read_lock();
for_each_domain(cpu, sd) {
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
@@ -3815,10 +3907,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
/* scale ms to jiffies */
interval = msecs_to_jiffies(interval);
- if (unlikely(!interval))
- interval = 1;
- if (interval > HZ*NR_CPUS/10)
- interval = HZ*NR_CPUS/10;
+ interval = clamp(interval, 1UL, max_load_balance_interval);
need_serialize = sd->flags & SD_SERIALIZE;
@@ -3831,8 +3920,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
if (load_balance(cpu, rq, sd, idle, &balance)) {
/*
* We've pulled tasks over so either we're no
- * longer idle, or one of our SMT siblings is
- * not idle.
+ * longer idle.
*/
idle = CPU_NOT_IDLE;
}
@@ -3854,6 +3942,7 @@ out:
if (!balance)
break;
}
+ rcu_read_unlock();
/*
* next_balance will be updated only when there is a need.
@@ -4079,33 +4168,62 @@ static void task_fork_fair(struct task_struct *p)
* Priority of the task has changed. Check to see if we preempt
* the current task.
*/
-static void prio_changed_fair(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
{
+ if (!p->se.on_rq)
+ return;
+
/*
* Reschedule if we are currently running on this runqueue and
* our priority decreased, or if we are not currently running on
* this runqueue and our priority is higher than the current's
*/
- if (running) {
+ if (rq->curr == p) {
if (p->prio > oldprio)
resched_task(rq->curr);
} else
check_preempt_curr(rq, p, 0);
}
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+ struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /*
+ * Ensure the task's vruntime is normalized, so that when its
+ * switched back to the fair class the enqueue_entity(.flags=0) will
+ * do the right thing.
+ *
+ * If it was on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it was !on_rq, then only when
+ * the task is sleeping will it still have non-normalized vruntime.
+ */
+ if (!se->on_rq && p->state != TASK_RUNNING) {
+ /*
+ * Fix up our vruntime so that the current sleep doesn't
+ * cause 'unlimited' sleep bonus.
+ */
+ place_entity(cfs_rq, se, 0);
+ se->vruntime -= cfs_rq->min_vruntime;
+ }
+}
+
/*
* We switched to the sched_fair class.
*/
-static void switched_to_fair(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
{
+ if (!p->se.on_rq)
+ return;
+
/*
* We were most likely switched from sched_rt, so
* kick off the schedule if running, otherwise just see
* if we can still preempt the current task.
*/
- if (running)
+ if (rq->curr == p)
resched_task(rq->curr);
else
check_preempt_curr(rq, p, 0);
@@ -4171,6 +4289,7 @@ static const struct sched_class fair_sched_class = {
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
+ .yield_to_task = yield_to_task_fair,
.check_preempt_curr = check_preempt_wakeup,
@@ -4191,6 +4310,7 @@ static const struct sched_class fair_sched_class = {
.task_fork = task_fork_fair,
.prio_changed = prio_changed_fair,
+ .switched_from = switched_from_fair,
.switched_to = switched_to_fair,
.get_rr_interval = get_rr_interval_fair,