diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-13 10:47:34 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-13 10:47:34 -0700 |
commit | 49d2953c72c64182ef2dcac64f6979c0b4e25db7 (patch) | |
tree | d339e498799617c8f79c760020f8442507cc381b /kernel/sched/core.c | |
parent | cc76ee75a9d3201eeacc576d17fbc1511f673010 (diff) | |
parent | 62a935b256f68a71697716595347209fb5275426 (diff) |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler changes from Ingo Molnar:
"Major changes:
- Reworked CPU capacity code, for better SMP load balancing on
systems with assymetric CPUs. (Vincent Guittot, Morten Rasmussen)
- Reworked RT task SMP balancing to be push based instead of pull
based, to reduce latencies on large CPU count systems. (Steven
Rostedt)
- SCHED_DEADLINE support updates and fixes. (Juri Lelli)
- SCHED_DEADLINE task migration support during CPU hotplug. (Wanpeng Li)
- x86 mwait-idle optimizations and fixes. (Mike Galbraith, Len Brown)
- sched/numa improvements. (Rik van Riel)
- various cleanups"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
sched/core: Drop debugging leftover trace_printk call
sched/deadline: Support DL task migration during CPU hotplug
sched/core: Check for available DL bandwidth in cpuset_cpu_inactive()
sched/deadline: Always enqueue on previous rq when dl_task_timer() fires
sched/core: Remove unused argument from init_[rt|dl]_rq()
sched/deadline: Fix rt runtime corruption when dl fails its global constraints
sched/deadline: Avoid a superfluous check
sched: Improve load balancing in the presence of idle CPUs
sched: Optimize freq invariant accounting
sched: Move CFS tasks to CPUs with higher capacity
sched: Add SD_PREFER_SIBLING for SMT level
sched: Remove unused struct sched_group_capacity::capacity_orig
sched: Replace capacity_factor by usage
sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage
sched: Add struct rq::cpu_capacity_orig
sched: Make scale_rt invariant with frequency
sched: Make sched entity usage tracking scale-invariant
sched: Remove frequency scaling from cpu_capacity
sched: Track group sched_entity usage contributions
sched: Add sched_avg::utilization_avg_contrib
...
Diffstat (limited to 'kernel/sched/core.c')
-rw-r--r-- | kernel/sched/core.c | 96 |
1 files changed, 50 insertions, 46 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3d5f6f6d14c2..261af7bfcb67 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -690,6 +690,23 @@ static inline bool got_nohz_idle_kick(void) bool sched_can_stop_tick(void) { /* + * FIFO realtime policy runs the highest priority task. Other runnable + * tasks are of a lower priority. The scheduler tick does nothing. + */ + if (current->policy == SCHED_FIFO) + return true; + + /* + * Round-robin realtime tasks time slice with other tasks at the same + * realtime priority. Is this task the only one at this priority? + */ + if (current->policy == SCHED_RR) { + struct sched_rt_entity *rt_se = ¤t->rt; + + return rt_se->run_list.prev == rt_se->run_list.next; + } + + /* * More than one running task need preemption. * nr_running update is assumed to be visible * after IPI is sent from wakers. @@ -5335,36 +5352,13 @@ static int sched_cpu_active(struct notifier_block *nfb, static int sched_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - unsigned long flags; - long cpu = (long)hcpu; - struct dl_bw *dl_b; - switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: - set_cpu_active(cpu, false); - - /* explicitly allow suspend */ - if (!(action & CPU_TASKS_FROZEN)) { - bool overflow; - int cpus; - - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); - - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(cpu); - overflow = __dl_overflow(dl_b, cpus, 0, 0); - raw_spin_unlock_irqrestore(&dl_b->lock, flags); - - rcu_read_unlock_sched(); - - if (overflow) - return notifier_from_errno(-EBUSY); - } + set_cpu_active((long)hcpu, false); return NOTIFY_OK; + default: + return NOTIFY_DONE; } - - return NOTIFY_DONE; } static int __init migration_init(void) @@ -5445,17 +5439,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - /* - * Even though we initialize ->capacity to something semi-sane, - * we leave capacity_orig unset. This allows us to detect if - * domain iteration is still funny without causing /0 traps. - */ - if (!group->sgc->capacity_orig) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n"); - break; - } - if (!cpumask_weight(sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: empty group\n"); @@ -5939,7 +5922,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) * die on a /0 trap. */ sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); - sg->sgc->capacity_orig = sg->sgc->capacity; /* * Make sure the first group of this domain contains the @@ -6250,6 +6232,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu) */ if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; sd->imbalance_pct = 110; sd->smt_gain = 1178; /* ~15% */ @@ -7015,7 +6998,6 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, */ case CPU_ONLINE: - case CPU_DOWN_FAILED: cpuset_update_active_cpus(true); break; default: @@ -7027,8 +7009,30 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action) { + unsigned long flags; + long cpu = (long)hcpu; + struct dl_bw *dl_b; + + switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: + /* explicitly allow suspend */ + if (!(action & CPU_TASKS_FROZEN)) { + bool overflow; + int cpus; + + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + rcu_read_unlock_sched(); + + if (overflow) + return notifier_from_errno(-EBUSY); + } cpuset_update_active_cpus(false); break; case CPU_DOWN_PREPARE_FROZEN: @@ -7173,8 +7177,8 @@ void __init sched_init(void) rq->calc_load_active = 0; rq->calc_load_update = jiffies + LOAD_FREQ; init_cfs_rq(&rq->cfs); - init_rt_rq(&rq->rt, rq); - init_dl_rq(&rq->dl, rq); + init_rt_rq(&rq->rt); + init_dl_rq(&rq->dl); #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.shares = ROOT_TASK_GROUP_LOAD; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); @@ -7214,7 +7218,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_capacity = SCHED_CAPACITY_SCALE; + rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; @@ -7813,7 +7817,7 @@ static int sched_rt_global_constraints(void) } #endif /* CONFIG_RT_GROUP_SCHED */ -static int sched_dl_global_constraints(void) +static int sched_dl_global_validate(void) { u64 runtime = global_rt_runtime(); u64 period = global_rt_period(); @@ -7914,11 +7918,11 @@ int sched_rt_handler(struct ctl_table *table, int write, if (ret) goto undo; - ret = sched_rt_global_constraints(); + ret = sched_dl_global_validate(); if (ret) goto undo; - ret = sched_dl_global_constraints(); + ret = sched_rt_global_constraints(); if (ret) goto undo; |