sched: Validate CFS quota hierarchies
Add constraints validation for CFS bandwidth hierarchies. Validate that: max(child bandwidth) <= parent_bandwidth In a quota limited hierarchy, an unconstrained entity (e.g. bandwidth==RUNTIME_INF) inherits the bandwidth of its parent. This constraint is chosen over sum(child_bandwidth) as notion of over-commit is valuable within SCHED_OTHER. Some basic code from the RT case is re-factored for reuse. Signed-off-by: Paul Turner <pjt@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20110721184757.083774572@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
parent
ab84d31e15
commit
a790de9959
112
kernel/sched.c
112
kernel/sched.c
|
@ -252,6 +252,7 @@ struct cfs_bandwidth {
|
|||
raw_spinlock_t lock;
|
||||
ktime_t period;
|
||||
u64 quota;
|
||||
s64 hierarchal_quota;
|
||||
#endif
|
||||
};
|
||||
|
||||
|
@ -1518,7 +1519,8 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load)
|
|||
update_load_sub(&rq->load, load);
|
||||
}
|
||||
|
||||
#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
|
||||
#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
|
||||
(defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH)))
|
||||
typedef int (*tg_visitor)(struct task_group *, void *);
|
||||
|
||||
/*
|
||||
|
@ -8708,12 +8710,7 @@ unsigned long sched_group_shares(struct task_group *tg)
|
|||
}
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_RT_GROUP_SCHED
|
||||
/*
|
||||
* Ensure that the real time constraints are schedulable.
|
||||
*/
|
||||
static DEFINE_MUTEX(rt_constraints_mutex);
|
||||
|
||||
#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH)
|
||||
static unsigned long to_ratio(u64 period, u64 runtime)
|
||||
{
|
||||
if (runtime == RUNTIME_INF)
|
||||
|
@ -8721,6 +8718,13 @@ static unsigned long to_ratio(u64 period, u64 runtime)
|
|||
|
||||
return div64_u64(runtime << 20, period);
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifdef CONFIG_RT_GROUP_SCHED
|
||||
/*
|
||||
* Ensure that the real time constraints are schedulable.
|
||||
*/
|
||||
static DEFINE_MUTEX(rt_constraints_mutex);
|
||||
|
||||
/* Must be called with tasklist_lock held */
|
||||
static inline int tg_has_rt_tasks(struct task_group *tg)
|
||||
|
@ -8741,7 +8745,7 @@ struct rt_schedulable_data {
|
|||
u64 rt_runtime;
|
||||
};
|
||||
|
||||
static int tg_schedulable(struct task_group *tg, void *data)
|
||||
static int tg_rt_schedulable(struct task_group *tg, void *data)
|
||||
{
|
||||
struct rt_schedulable_data *d = data;
|
||||
struct task_group *child;
|
||||
|
@ -8805,7 +8809,7 @@ static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
|
|||
.rt_runtime = runtime,
|
||||
};
|
||||
|
||||
return walk_tg_tree(tg_schedulable, tg_nop, &data);
|
||||
return walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
|
||||
}
|
||||
|
||||
static int tg_set_rt_bandwidth(struct task_group *tg,
|
||||
|
@ -9064,14 +9068,17 @@ static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
|
|||
}
|
||||
|
||||
#ifdef CONFIG_CFS_BANDWIDTH
|
||||
static DEFINE_MUTEX(cfs_constraints_mutex);
|
||||
|
||||
const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
|
||||
const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
|
||||
|
||||
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
|
||||
|
||||
static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
|
||||
{
|
||||
int i;
|
||||
int i, ret = 0;
|
||||
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
|
||||
static DEFINE_MUTEX(mutex);
|
||||
|
||||
if (tg == &root_task_group)
|
||||
return -EINVAL;
|
||||
|
@ -9092,7 +9099,11 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
|
|||
if (period > max_cfs_quota_period)
|
||||
return -EINVAL;
|
||||
|
||||
mutex_lock(&mutex);
|
||||
mutex_lock(&cfs_constraints_mutex);
|
||||
ret = __cfs_schedulable(tg, period, quota);
|
||||
if (ret)
|
||||
goto out_unlock;
|
||||
|
||||
raw_spin_lock_irq(&cfs_b->lock);
|
||||
cfs_b->period = ns_to_ktime(period);
|
||||
cfs_b->quota = quota;
|
||||
|
@ -9107,9 +9118,10 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
|
|||
cfs_rq->runtime_remaining = 0;
|
||||
raw_spin_unlock_irq(&rq->lock);
|
||||
}
|
||||
mutex_unlock(&mutex);
|
||||
out_unlock:
|
||||
mutex_unlock(&cfs_constraints_mutex);
|
||||
|
||||
return 0;
|
||||
return ret;
|
||||
}
|
||||
|
||||
int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
|
||||
|
@ -9183,6 +9195,78 @@ static int cpu_cfs_period_write_u64(struct cgroup *cgrp, struct cftype *cftype,
|
|||
return tg_set_cfs_period(cgroup_tg(cgrp), cfs_period_us);
|
||||
}
|
||||
|
||||
struct cfs_schedulable_data {
|
||||
struct task_group *tg;
|
||||
u64 period, quota;
|
||||
};
|
||||
|
||||
/*
|
||||
* normalize group quota/period to be quota/max_period
|
||||
* note: units are usecs
|
||||
*/
|
||||
static u64 normalize_cfs_quota(struct task_group *tg,
|
||||
struct cfs_schedulable_data *d)
|
||||
{
|
||||
u64 quota, period;
|
||||
|
||||
if (tg == d->tg) {
|
||||
period = d->period;
|
||||
quota = d->quota;
|
||||
} else {
|
||||
period = tg_get_cfs_period(tg);
|
||||
quota = tg_get_cfs_quota(tg);
|
||||
}
|
||||
|
||||
/* note: these should typically be equivalent */
|
||||
if (quota == RUNTIME_INF || quota == -1)
|
||||
return RUNTIME_INF;
|
||||
|
||||
return to_ratio(period, quota);
|
||||
}
|
||||
|
||||
static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
|
||||
{
|
||||
struct cfs_schedulable_data *d = data;
|
||||
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
|
||||
s64 quota = 0, parent_quota = -1;
|
||||
|
||||
if (!tg->parent) {
|
||||
quota = RUNTIME_INF;
|
||||
} else {
|
||||
struct cfs_bandwidth *parent_b = tg_cfs_bandwidth(tg->parent);
|
||||
|
||||
quota = normalize_cfs_quota(tg, d);
|
||||
parent_quota = parent_b->hierarchal_quota;
|
||||
|
||||
/*
|
||||
* ensure max(child_quota) <= parent_quota, inherit when no
|
||||
* limit is set
|
||||
*/
|
||||
if (quota == RUNTIME_INF)
|
||||
quota = parent_quota;
|
||||
else if (parent_quota != RUNTIME_INF && quota > parent_quota)
|
||||
return -EINVAL;
|
||||
}
|
||||
cfs_b->hierarchal_quota = quota;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
|
||||
{
|
||||
struct cfs_schedulable_data data = {
|
||||
.tg = tg,
|
||||
.period = period,
|
||||
.quota = quota,
|
||||
};
|
||||
|
||||
if (quota != RUNTIME_INF) {
|
||||
do_div(data.period, NSEC_PER_USEC);
|
||||
do_div(data.quota, NSEC_PER_USEC);
|
||||
}
|
||||
|
||||
return walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
|
||||
}
|
||||
#endif /* CONFIG_CFS_BANDWIDTH */
|
||||
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
||||
|
||||
|
|
Loading…
Reference in New Issue