Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this cycle were:

   - tickless load average calculation enhancements (Byungchul Park)

   - vtime handling enhancements (Frederic Weisbecker)

   - scalability improvement via properly aligning a key structure field
     (Jiri Olsa)

   - various stop_machine() fixes (Oleg Nesterov)

   - sched/numa enhancement (Rik van Riel)

   - various fixes and improvements (Andi Kleen, Dietmar Eggemann,
     Geliang Tang, Hiroshi Shimamoto, Joonwoo Park, Peter Zijlstra,
     Waiman Long, Wanpeng Li, Yuyang Du)"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  sched/fair: Fix new task's load avg removed from source CPU in wake_up_new_task()
  sched/core: Move sched_entity::avg into separate cache line
  x86/fpu: Properly align size in CHECK_MEMBER_AT_END_OF() macro
  sched/deadline: Fix the earliest_dl.next logic
  sched/fair: Disable the task group load_avg update for the root_task_group
  sched/fair: Move the cache-hot 'load_avg' variable into its own cacheline
  sched/fair: Avoid redundant idle_cpu() call in update_sg_lb_stats()
  sched/core: Move the sched_to_prio[] arrays out of line
  sched/cputime: Convert vtime_seqlock to seqcount
  sched/cputime: Introduce vtime accounting check for readers
  sched/cputime: Rename vtime_accounting_enabled() to vtime_accounting_cpu_enabled()
  sched/cputime: Correctly handle task guest time on housekeepers
  sched/cputime: Clarify vtime symbols and document them
  sched/cputime: Remove extra cost in task_cputime()
  sched/fair: Make it possible to account fair load avg consistently
  sched/fair: Modify the comment about lock assumptions in migrate_task_rq_fair()
  stop_machine: Clean up the usage of the preemption counter in cpu_stopper_thread()
  stop_machine: Shift the 'done != NULL' check from cpu_stop_signal_done() to callers
  stop_machine: Kill cpu_stop_done->executed
  stop_machine: Change __stop_cpus() to rely on cpu_stop_queue_work()
  ...
This commit is contained in:
Linus Torvalds
2016-01-11 15:13:38 -08:00
17 changed files with 487 additions and 308 deletions

View File

@@ -731,7 +731,7 @@ bool sched_can_stop_tick(void)
if (current->policy == SCHED_RR) {
struct sched_rt_entity *rt_se = &current->rt;
return rt_se->run_list.prev == rt_se->run_list.next;
return list_is_singular(&rt_se->run_list);
}
/*
@@ -823,8 +823,8 @@ static void set_load_weight(struct task_struct *p)
return;
}
load->weight = scale_load(prio_to_weight[prio]);
load->inv_weight = prio_to_wmult[prio];
load->weight = scale_load(sched_prio_to_weight[prio]);
load->inv_weight = sched_prio_to_wmult[prio];
}
static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
@@ -1071,8 +1071,8 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new
{
lockdep_assert_held(&rq->lock);
dequeue_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_MIGRATING;
dequeue_task(rq, p, 0);
set_task_cpu(p, new_cpu);
raw_spin_unlock(&rq->lock);
@@ -1080,8 +1080,8 @@ static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new
raw_spin_lock(&rq->lock);
BUG_ON(task_cpu(p) != new_cpu);
p->on_rq = TASK_ON_RQ_QUEUED;
enqueue_task(rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(rq, p, 0);
return rq;
@@ -1274,6 +1274,15 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
!p->on_rq);
/*
* Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING,
* because schedstat_wait_{start,end} rebase migrating task's wait_start
* time relying on p->on_rq.
*/
WARN_ON_ONCE(p->state == TASK_RUNNING &&
p->sched_class == &fair_sched_class &&
(p->on_rq && !task_on_rq_migrating(p)));
#ifdef CONFIG_LOCKDEP
/*
* The caller should hold either p->pi_lock or rq->lock, when changing
@@ -1310,9 +1319,11 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
src_rq = task_rq(p);
dst_rq = cpu_rq(cpu);
p->on_rq = TASK_ON_RQ_MIGRATING;
deactivate_task(src_rq, p, 0);
set_task_cpu(p, cpu);
activate_task(dst_rq, p, 0);
p->on_rq = TASK_ON_RQ_QUEUED;
check_preempt_curr(dst_rq, p, 0);
} else {
/*
@@ -2194,6 +2205,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
p->se.vruntime = 0;
INIT_LIST_HEAD(&p->se.group_node);
#ifdef CONFIG_FAIR_GROUP_SCHED
p->se.cfs_rq = NULL;
#endif
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
#endif
@@ -7442,6 +7457,9 @@ int in_sched_functions(unsigned long addr)
*/
struct task_group root_task_group;
LIST_HEAD(task_groups);
/* Cacheline aligned slab cache for task_group */
static struct kmem_cache *task_group_cache __read_mostly;
#endif
DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
@@ -7499,11 +7517,12 @@ void __init sched_init(void)
#endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_CGROUP_SCHED
task_group_cache = KMEM_CACHE(task_group, 0);
list_add(&root_task_group.list, &task_groups);
INIT_LIST_HEAD(&root_task_group.children);
INIT_LIST_HEAD(&root_task_group.siblings);
autogroup_init(&init_task);
#endif /* CONFIG_CGROUP_SCHED */
for_each_possible_cpu(i) {
@@ -7784,7 +7803,7 @@ static void free_sched_group(struct task_group *tg)
free_fair_sched_group(tg);
free_rt_sched_group(tg);
autogroup_free(tg);
kfree(tg);
kmem_cache_free(task_group_cache, tg);
}
/* allocate runqueue etc for a new task group */
@@ -7792,7 +7811,7 @@ struct task_group *sched_create_group(struct task_group *parent)
{
struct task_group *tg;
tg = kzalloc(sizeof(*tg), GFP_KERNEL);
tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
if (!tg)
return ERR_PTR(-ENOMEM);
@@ -8697,3 +8716,44 @@ void dump_cpu_task(int cpu)
pr_info("Task dump for CPU %d:\n", cpu);
sched_show_task(cpu_curr(cpu));
}
/*
* Nice levels are multiplicative, with a gentle 10% change for every
* nice level changed. I.e. when a CPU-bound task goes from nice 0 to
* nice 1, it will get ~10% less CPU time than another CPU-bound task
* that remained on nice 0.
*
* The "10% effect" is relative and cumulative: from _any_ nice level,
* if you go up 1 level, it's -10% CPU usage, if you go down 1 level
* it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
* If a task goes up by ~10% and another task goes down by ~10% then
* the relative distance between them is ~25%.)
*/
const int sched_prio_to_weight[40] = {
/* -20 */ 88761, 71755, 56483, 46273, 36291,
/* -15 */ 29154, 23254, 18705, 14949, 11916,
/* -10 */ 9548, 7620, 6100, 4904, 3906,
/* -5 */ 3121, 2501, 1991, 1586, 1277,
/* 0 */ 1024, 820, 655, 526, 423,
/* 5 */ 335, 272, 215, 172, 137,
/* 10 */ 110, 87, 70, 56, 45,
/* 15 */ 36, 29, 23, 18, 15,
};
/*
* Inverse (2^32/x) values of the sched_prio_to_weight[] array, precalculated.
*
* In cases where the weight does not change often, we can use the
* precalculated inverse to speed up arithmetics by turning divisions
* into multiplications:
*/
const u32 sched_prio_to_wmult[40] = {
/* -20 */ 48388, 59856, 76040, 92818, 118348,
/* -15 */ 147320, 184698, 229616, 287308, 360437,
/* -10 */ 449829, 563644, 704093, 875809, 1099582,
/* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326,
/* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587,
/* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126,
/* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717,
/* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};