};
struct rt_bandwidth {
- ktime_t rt_period;
- u64 rt_runtime;
- spinlock_t rt_runtime_lock;
- struct hrtimer rt_period_timer;
+ /* nests inside the rq lock: */
+ spinlock_t rt_runtime_lock;
+ ktime_t rt_period;
+ u64 rt_runtime;
+ struct hrtimer rt_period_timer;
};
static struct rt_bandwidth def_rt_bandwidth;
struct rcu_head rcu;
struct list_head list;
+
+ struct task_group *parent;
+ struct list_head siblings;
+ struct list_head children;
};
+#ifdef CONFIG_USER_SCHED
+
+/*
+ * Root task group.
+ * Every UID task group (including init_task_group aka UID-0) will
+ * be a child to this group.
+ */
+struct task_group root_task_group;
+
#ifdef CONFIG_FAIR_GROUP_SCHED
/* Default task group's sched entity on each cpu */
static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
#endif
+#else
+#define root_task_group init_task_group
+#endif
/* task_group_lock serializes add/remove of task groups and also changes to
* a task group's cpu shares.
int rt_throttled;
u64 rt_time;
u64 rt_runtime;
+ /* Nests inside the rq lock: */
spinlock_t rt_runtime_lock;
#ifdef CONFIG_RT_GROUP_SCHED
{ \
memset(sd, 0, sizeof(*sd)); \
*sd = SD_##type##_INIT; \
+ sd->level = SD_LV_##type; \
}
SD_INIT_FUNC(CPU)
#define SCHED_CPUMASK_VAR(v, a) cpumask_t *v = (cpumask_t *) \
((unsigned long)(a) + offsetof(struct allmasks, v))
+static int default_relax_domain_level = -1;
+
+static int __init setup_relax_domain_level(char *str)
+{
+ default_relax_domain_level = simple_strtoul(str, NULL, 0);
+ return 1;
+}
+__setup("relax_domain_level=", setup_relax_domain_level);
+
+static void set_domain_attribute(struct sched_domain *sd,
+ struct sched_domain_attr *attr)
+{
+ int request;
+
+ if (!attr || attr->relax_domain_level < 0) {
+ if (default_relax_domain_level < 0)
+ return;
+ else
+ request = default_relax_domain_level;
+ } else
+ request = attr->relax_domain_level;
+ if (request < sd->level) {
+ /* turn off idle balance on this domain */
+ sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE);
+ } else {
+ /* turn on idle balance on this domain */
+ sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE);
+ }
+}
+
/*
* Build sched domains for a given set of cpus and attach the sched domains
* to the individual cpus
*/
-static int build_sched_domains(const cpumask_t *cpu_map)
+static int __build_sched_domains(const cpumask_t *cpu_map,
+ struct sched_domain_attr *attr)
{
int i;
struct root_domain *rd;
SD_NODES_PER_DOMAIN*cpus_weight(*nodemask)) {
sd = &per_cpu(allnodes_domains, i);
SD_INIT(sd, ALLNODES);
+ set_domain_attribute(sd, attr);
sd->span = *cpu_map;
cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
p = sd;
sd = &per_cpu(node_domains, i);
SD_INIT(sd, NODE);
+ set_domain_attribute(sd, attr);
sched_domain_node_span(cpu_to_node(i), &sd->span);
sd->parent = p;
if (p)
p = sd;
sd = &per_cpu(phys_domains, i);
SD_INIT(sd, CPU);
+ set_domain_attribute(sd, attr);
sd->span = *nodemask;
sd->parent = p;
if (p)
p = sd;
sd = &per_cpu(core_domains, i);
SD_INIT(sd, MC);
+ set_domain_attribute(sd, attr);
sd->span = cpu_coregroup_map(i);
cpus_and(sd->span, sd->span, *cpu_map);
sd->parent = p;
p = sd;
sd = &per_cpu(cpu_domains, i);
SD_INIT(sd, SIBLING);
+ set_domain_attribute(sd, attr);
sd->span = per_cpu(cpu_sibling_map, i);
cpus_and(sd->span, sd->span, *cpu_map);
sd->parent = p;
#endif
}
+static int build_sched_domains(const cpumask_t *cpu_map)
+{
+ return __build_sched_domains(cpu_map, NULL);
+}
+
static cpumask_t *doms_cur; /* current sched domains */
static int ndoms_cur; /* number of sched domains in 'doms_cur' */
+static struct sched_domain_attr *dattr_cur; /* attribues of custom domains
+ in 'doms_cur' */
/*
* Special case: If a kmalloc of a doms_cur partition (array of
if (!doms_cur)
doms_cur = &fallback_doms;
cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map);
+ dattr_cur = NULL;
err = build_sched_domains(doms_cur);
register_sched_domain_sysctl();
arch_destroy_sched_domains(cpu_map, &tmpmask);
}
+/* handle null as "default" */
+static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
+ struct sched_domain_attr *new, int idx_new)
+{
+ struct sched_domain_attr tmp;
+
+ /* fast path */
+ if (!new && !cur)
+ return 1;
+
+ tmp = SD_ATTR_INIT;
+ return !memcmp(cur ? (cur + idx_cur) : &tmp,
+ new ? (new + idx_new) : &tmp,
+ sizeof(struct sched_domain_attr));
+}
+
/*
* Partition sched domains as specified by the 'ndoms_new'
* cpumasks in the array doms_new[] of cpumasks. This compares
*
* Call with hotplug lock held
*/
-void partition_sched_domains(int ndoms_new, cpumask_t *doms_new)
+void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+ struct sched_domain_attr *dattr_new)
{
int i, j;
ndoms_new = 1;
doms_new = &fallback_doms;
cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+ dattr_new = NULL;
}
/* Destroy deleted domains */
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < ndoms_new; j++) {
- if (cpus_equal(doms_cur[i], doms_new[j]))
+ if (cpus_equal(doms_cur[i], doms_new[j])
+ && dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
/* no match - a current sched domain not in new doms_new[] */
/* Build new domains */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < ndoms_cur; j++) {
- if (cpus_equal(doms_new[i], doms_cur[j]))
+ if (cpus_equal(doms_new[i], doms_cur[j])
+ && dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
/* no match - add a new doms_new */
- build_sched_domains(doms_new + i);
+ __build_sched_domains(doms_new + i,
+ dattr_new ? dattr_new + i : NULL);
match2:
;
}
/* Remember the new sched domains */
if (doms_cur != &fallback_doms)
kfree(doms_cur);
+ kfree(dattr_cur); /* kfree(NULL) is safe */
doms_cur = doms_new;
+ dattr_cur = dattr_new;
ndoms_cur = ndoms_new;
register_sched_domain_sysctl();
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-static void init_tg_cfs_entry(struct rq *rq, struct task_group *tg,
- struct cfs_rq *cfs_rq, struct sched_entity *se,
- int cpu, int add)
+static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
+ struct sched_entity *se, int cpu, int add,
+ struct sched_entity *parent)
{
+ struct rq *rq = cpu_rq(cpu);
tg->cfs_rq[cpu] = cfs_rq;
init_cfs_rq(cfs_rq, rq);
cfs_rq->tg = tg;
list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
tg->se[cpu] = se;
- se->cfs_rq = &rq->cfs;
+ /* se could be NULL for init_task_group */
+ if (!se)
+ return;
+
+ if (!parent)
+ se->cfs_rq = &rq->cfs;
+ else
+ se->cfs_rq = parent->my_q;
+
se->my_q = cfs_rq;
se->load.weight = tg->shares;
se->load.inv_weight = div64_64(1ULL<<32, se->load.weight);
- se->parent = NULL;
+ se->parent = parent;
}
#endif
#ifdef CONFIG_RT_GROUP_SCHED
-static void init_tg_rt_entry(struct rq *rq, struct task_group *tg,
- struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
- int cpu, int add)
+static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
+ struct sched_rt_entity *rt_se, int cpu, int add,
+ struct sched_rt_entity *parent)
{
+ struct rq *rq = cpu_rq(cpu);
+
tg->rt_rq[cpu] = rt_rq;
init_rt_rq(rt_rq, rq);
rt_rq->tg = tg;
list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
tg->rt_se[cpu] = rt_se;
+ if (!rt_se)
+ return;
+
+ if (!parent)
+ rt_se->rt_rq = &rq->rt;
+ else
+ rt_se->rt_rq = parent->my_q;
+
rt_se->rt_rq = &rq->rt;
rt_se->my_q = rt_rq;
- rt_se->parent = NULL;
+ rt_se->parent = parent;
INIT_LIST_HEAD(&rt_se->run_list);
}
#endif
#endif
#ifdef CONFIG_RT_GROUP_SCHED
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+#endif
+#ifdef CONFIG_USER_SCHED
+ alloc_size *= 2;
#endif
/*
* As sched_init() is called before page_alloc is setup,
init_task_group.cfs_rq = (struct cfs_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
+
+#ifdef CONFIG_USER_SCHED
+ root_task_group.se = (struct sched_entity **)ptr;
+ ptr += nr_cpu_ids * sizeof(void **);
+
+ root_task_group.cfs_rq = (struct cfs_rq **)ptr;
+ ptr += nr_cpu_ids * sizeof(void **);
+#endif
#endif
#ifdef CONFIG_RT_GROUP_SCHED
init_task_group.rt_se = (struct sched_rt_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
init_task_group.rt_rq = (struct rt_rq **)ptr;
+ ptr += nr_cpu_ids * sizeof(void **);
+
+#ifdef CONFIG_USER_SCHED
+ root_task_group.rt_se = (struct sched_rt_entity **)ptr;
+ ptr += nr_cpu_ids * sizeof(void **);
+
+ root_task_group.rt_rq = (struct rt_rq **)ptr;
+ ptr += nr_cpu_ids * sizeof(void **);
+#endif
#endif
}
#ifdef CONFIG_RT_GROUP_SCHED
init_rt_bandwidth(&init_task_group.rt_bandwidth,
global_rt_period(), global_rt_runtime());
+#ifdef CONFIG_USER_SCHED
+ init_rt_bandwidth(&root_task_group.rt_bandwidth,
+ global_rt_period(), RUNTIME_INF);
+#endif
#endif
#ifdef CONFIG_GROUP_SCHED
list_add(&init_task_group.list, &task_groups);
+ INIT_LIST_HEAD(&init_task_group.children);
+
+#ifdef CONFIG_USER_SCHED
+ INIT_LIST_HEAD(&root_task_group.children);
+ init_task_group.parent = &root_task_group;
+ list_add(&init_task_group.siblings, &root_task_group.children);
+#endif
#endif
for_each_possible_cpu(i) {
#ifdef CONFIG_FAIR_GROUP_SCHED
init_task_group.shares = init_task_group_load;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
- init_tg_cfs_entry(rq, &init_task_group,
+#ifdef CONFIG_CGROUP_SCHED
+ /*
+ * How much cpu bandwidth does init_task_group get?
+ *
+ * In case of task-groups formed thr' the cgroup filesystem, it
+ * gets 100% of the cpu resources in the system. This overall
+ * system cpu resource is divided among the tasks of
+ * init_task_group and its child task-groups in a fair manner,
+ * based on each entity's (task or task-group's) weight
+ * (se->load.weight).
+ *
+ * In other words, if init_task_group has 10 tasks of weight
+ * 1024) and two child groups A0 and A1 (of weight 1024 each),
+ * then A0's share of the cpu resource is:
+ *
+ * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
+ *
+ * We achieve this by letting init_task_group's tasks sit
+ * directly in rq->cfs (i.e init_task_group->se[] = NULL).
+ */
+ init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
+#elif defined CONFIG_USER_SCHED
+ root_task_group.shares = NICE_0_LOAD;
+ init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL);
+ /*
+ * In case of task-groups formed thr' the user id of tasks,
+ * init_task_group represents tasks belonging to root user.
+ * Hence it forms a sibling of all subsequent groups formed.
+ * In this case, init_task_group gets only a fraction of overall
+ * system cpu resource, based on the weight assigned to root
+ * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
+ * by letting tasks of init_task_group sit in a separate cfs_rq
+ * (init_cfs_rq) and having one entity represent this group of
+ * tasks in rq->cfs (i.e init_task_group->se[] != NULL).
+ */
+ init_tg_cfs_entry(&init_task_group,
&per_cpu(init_cfs_rq, i),
- &per_cpu(init_sched_entity, i), i, 1);
+ &per_cpu(init_sched_entity, i), i, 1,
+ root_task_group.se[i]);
#endif
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+ rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
- init_tg_rt_entry(rq, &init_task_group,
+#ifdef CONFIG_CGROUP_SCHED
+ init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
+#elif defined CONFIG_USER_SCHED
+ init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
+ init_tg_rt_entry(&init_task_group,
&per_cpu(init_rt_rq, i),
- &per_cpu(init_sched_rt_entity, i), i, 1);
-#else
- rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
+ &per_cpu(init_sched_rt_entity, i), i, 1,
+ root_task_group.rt_se[i]);
+#endif
#endif
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
kfree(tg->se);
}
-static int alloc_fair_sched_group(struct task_group *tg)
+static
+int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
struct cfs_rq *cfs_rq;
- struct sched_entity *se;
+ struct sched_entity *se, *parent_se;
struct rq *rq;
int i;
if (!se)
goto err;
- init_tg_cfs_entry(rq, tg, cfs_rq, se, i, 0);
+ parent_se = parent ? parent->se[i] : NULL;
+ init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent_se);
}
return 1;
{
}
-static inline int alloc_fair_sched_group(struct task_group *tg)
+static inline
+int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
return 1;
}
kfree(tg->rt_se);
}
-static int alloc_rt_sched_group(struct task_group *tg)
+static
+int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
struct rt_rq *rt_rq;
- struct sched_rt_entity *rt_se;
+ struct sched_rt_entity *rt_se, *parent_se;
struct rq *rq;
int i;
if (!rt_se)
goto err;
- init_tg_rt_entry(rq, tg, rt_rq, rt_se, i, 0);
+ parent_se = parent ? parent->rt_se[i] : NULL;
+ init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent_se);
}
return 1;
{
}
-static inline int alloc_rt_sched_group(struct task_group *tg)
+static inline
+int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
return 1;
}
}
/* allocate runqueue etc for a new task group */
-struct task_group *sched_create_group(void)
+struct task_group *sched_create_group(struct task_group *parent)
{
struct task_group *tg;
unsigned long flags;
if (!tg)
return ERR_PTR(-ENOMEM);
- if (!alloc_fair_sched_group(tg))
+ if (!alloc_fair_sched_group(tg, parent))
goto err;
- if (!alloc_rt_sched_group(tg))
+ if (!alloc_rt_sched_group(tg, parent))
goto err;
spin_lock_irqsave(&task_group_lock, flags);
register_rt_sched_group(tg, i);
}
list_add_rcu(&tg->list, &task_groups);
+
+ WARN_ON(!parent); /* root should already exist */
+
+ tg->parent = parent;
+ list_add_rcu(&tg->siblings, &parent->children);
+ INIT_LIST_HEAD(&tg->children);
spin_unlock_irqrestore(&task_group_lock, flags);
return tg;
unregister_rt_sched_group(tg, i);
}
list_del_rcu(&tg->list);
+ list_del_rcu(&tg->siblings);
spin_unlock_irqrestore(&task_group_lock, flags);
/* wait for possible concurrent references to cfs_rqs complete */
int i;
unsigned long flags;
+ /*
+ * We can't change the weight of the root cgroup.
+ */
+ if (!tg->se[0])
+ return -EINVAL;
+
/*
* A weight of 0 or 1 can cause arithmetics problems.
* (The default weight is 1024 - so there's no practical
spin_lock_irqsave(&task_group_lock, flags);
for_each_possible_cpu(i)
unregister_fair_sched_group(tg, i);
+ list_del_rcu(&tg->siblings);
spin_unlock_irqrestore(&task_group_lock, flags);
/* wait for any ongoing reference to this group to finish */
spin_lock_irqsave(&task_group_lock, flags);
for_each_possible_cpu(i)
register_fair_sched_group(tg, i);
+ list_add_rcu(&tg->siblings, &tg->parent->children);
spin_unlock_irqrestore(&task_group_lock, flags);
done:
mutex_unlock(&shares_mutex);
return div64_64(runtime << 16, period);
}
+#ifdef CONFIG_CGROUP_SCHED
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+{
+ struct task_group *tgi, *parent = tg->parent;
+ unsigned long total = 0;
+
+ if (!parent) {
+ if (global_rt_period() < period)
+ return 0;
+
+ return to_ratio(period, runtime) <
+ to_ratio(global_rt_period(), global_rt_runtime());
+ }
+
+ if (ktime_to_ns(parent->rt_bandwidth.rt_period) < period)
+ return 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(tgi, &parent->children, siblings) {
+ if (tgi == tg)
+ continue;
+
+ total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period),
+ tgi->rt_bandwidth.rt_runtime);
+ }
+ rcu_read_unlock();
+
+ return total + to_ratio(period, runtime) <
+ to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period),
+ parent->rt_bandwidth.rt_runtime);
+}
+#elif defined CONFIG_USER_SCHED
static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
{
struct task_group *tgi;
return total + to_ratio(period, runtime) < global_ratio;
}
+#endif
/* Must be called with tasklist_lock held */
static inline int tg_has_rt_tasks(struct task_group *tg)
static struct cgroup_subsys_state *
cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
- struct task_group *tg;
+ struct task_group *tg, *parent;
if (!cgrp->parent) {
/* This is early initialization for the top cgroup */
return &init_task_group.css;
}
- /* we support only 1-level deep hierarchical scheduler atm */
- if (cgrp->parent->parent)
- return ERR_PTR(-EINVAL);
-
- tg = sched_create_group();
+ parent = cgroup_tg(cgrp->parent);
+ tg = sched_create_group(parent);
if (IS_ERR(tg))
return ERR_PTR(-ENOMEM);