In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
groups due to the previous fix simply taking the min. It should
reflect a limit imposed at that level or by an ancestor. Even
though cgroupv2 does not require child quota to be less than or
equal to that of its ancestors the task group will still be
constrained by such a quota so this should be shown here. Cgroupv1
continues to set this correctly.
In both cases, add initialization when a new task group is created
based on the current parent's value (or RUNTIME_INF in the case of
root_task_group). Otherwise, the field is wrong until a quota is
changed after creation and __cfs_schedulable() is called.
Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
Signed-off-by: Phil Auld <pauld@redhat.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
---
v2: Improve comment about how setting hierarchical_quota correctly
helps the scheduler. Remove extra parens.
kernel/sched/core.c | 13 +++++++++----
kernel/sched/fair.c | 7 ++++---
kernel/sched/sched.h | 2 +-
3 files changed, 14 insertions(+), 8 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a68d1276bab0..f80697a79baf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9904,7 +9904,7 @@ void __init sched_init(void)
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
- init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
+ init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -11038,11 +11038,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
/*
* Ensure max(child_quota) <= parent_quota. On cgroup2,
- * always take the min. On cgroup1, only inherit when no
- * limit is set:
+ * always take the non-RUNTIME_INF min. On cgroup1, only
+ * inherit when no limit is set. In cgroup2 this is used
+ * by the scheduler to determine if a given CFS task has a
+ * bandwidth constraint at some higher level.
*/
if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
- quota = min(quota, parent_quota);
+ if (quota == RUNTIME_INF)
+ quota = parent_quota;
+ else if (parent_quota != RUNTIME_INF)
+ quota = min(quota, parent_quota);
} else {
if (quota == RUNTIME_INF)
quota = parent_quota;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 373ff5f55884..d9b3d4617e16 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6005,13 +6005,14 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}
-void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent)
{
raw_spin_lock_init(&cfs_b->lock);
cfs_b->runtime = 0;
cfs_b->quota = RUNTIME_INF;
cfs_b->period = ns_to_ktime(default_cfs_period());
cfs_b->burst = 0;
+ cfs_b->hierarchical_quota = parent ? parent->hierarchical_quota : RUNTIME_INF;
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
@@ -6168,7 +6169,7 @@ static inline int throttled_lb_pair(struct task_group *tg,
return 0;
}
-void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
+void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent) {}
#ifdef CONFIG_FAIR_GROUP_SCHED
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
@@ -12373,7 +12374,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
tg->shares = NICE_0_LOAD;
- init_cfs_bandwidth(tg_cfs_bandwidth(tg));
+ init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent));
for_each_possible_cpu(i) {
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ec7b3e0a2b20..63822c9238cc 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -460,7 +460,7 @@ extern void unregister_fair_sched_group(struct task_group *tg);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
-extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
+extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent);
extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
--
2.31.1Phil Auld <pauld@redhat.com> writes:
> In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
> groups due to the previous fix simply taking the min. It should
> reflect a limit imposed at that level or by an ancestor. Even
> though cgroupv2 does not require child quota to be less than or
> equal to that of its ancestors the task group will still be
> constrained by such a quota so this should be shown here. Cgroupv1
> continues to set this correctly.
>
> In both cases, add initialization when a new task group is created
> based on the current parent's value (or RUNTIME_INF in the case of
> root_task_group). Otherwise, the field is wrong until a quota is
> changed after creation and __cfs_schedulable() is called.
>
> Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
> Signed-off-by: Phil Auld <pauld@redhat.com>
> Reviewed-by: Ben Segall <bsegall@google.com>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Vincent Guittot <vincent.guittot@linaro.org>
> Cc: Juri Lelli <juri.lelli@redhat.com>
> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> Cc: Valentin Schneider <vschneid@redhat.com>
> Cc: Ben Segall <bsegall@google.com>
> Cc: Frederic Weisbecker <frederic@kernel.org>
> Cc: Tejun Heo <tj@kernel.org>
> ---
>
> v2: Improve comment about how setting hierarchical_quota correctly
>
> helps the scheduler. Remove extra parens.
> kernel/sched/core.c | 13 +++++++++----
> kernel/sched/fair.c | 7 ++++---
> kernel/sched/sched.h | 2 +-
> 3 files changed, 14 insertions(+), 8 deletions(-)
>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index a68d1276bab0..f80697a79baf 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -9904,7 +9904,7 @@ void __init sched_init(void)
> ptr += nr_cpu_ids * sizeof(void **);
>
> root_task_group.shares = ROOT_TASK_GROUP_LOAD;
> - init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
> + init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
> #endif /* CONFIG_FAIR_GROUP_SCHED */
> #ifdef CONFIG_RT_GROUP_SCHED
> root_task_group.rt_se = (struct sched_rt_entity **)ptr;
> @@ -11038,11 +11038,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
>
> /*
> * Ensure max(child_quota) <= parent_quota. On cgroup2,
> - * always take the min. On cgroup1, only inherit when no
> - * limit is set:
> + * always take the non-RUNTIME_INF min. On cgroup1, only
> + * inherit when no limit is set. In cgroup2 this is used
> + * by the scheduler to determine if a given CFS task has a
> + * bandwidth constraint at some higher level.
> */
It's still used for determining this on cgroup1 (and the cgroup1 code
still works for that), right?
> if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
> - quota = min(quota, parent_quota);
> + if (quota == RUNTIME_INF)
> + quota = parent_quota;
> + else if (parent_quota != RUNTIME_INF)
> + quota = min(quota, parent_quota);
> } else {
> if (quota == RUNTIME_INF)
> quota = parent_quota;
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 373ff5f55884..d9b3d4617e16 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6005,13 +6005,14 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
> return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
> }
>
> -void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
> +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent)
> {
> raw_spin_lock_init(&cfs_b->lock);
> cfs_b->runtime = 0;
> cfs_b->quota = RUNTIME_INF;
> cfs_b->period = ns_to_ktime(default_cfs_period());
> cfs_b->burst = 0;
> + cfs_b->hierarchical_quota = parent ? parent->hierarchical_quota : RUNTIME_INF;
>
> INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
> hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
> @@ -6168,7 +6169,7 @@ static inline int throttled_lb_pair(struct task_group *tg,
> return 0;
> }
>
> -void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
> +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent) {}
>
> #ifdef CONFIG_FAIR_GROUP_SCHED
> static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
> @@ -12373,7 +12374,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
>
> tg->shares = NICE_0_LOAD;
>
> - init_cfs_bandwidth(tg_cfs_bandwidth(tg));
> + init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent));
>
> for_each_possible_cpu(i) {
> cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index ec7b3e0a2b20..63822c9238cc 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -460,7 +460,7 @@ extern void unregister_fair_sched_group(struct task_group *tg);
> extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
> struct sched_entity *se, int cpu,
> struct sched_entity *parent);
> -extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
> +extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent);
>
> extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
> extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
On Wed, Jul 12, 2023 at 03:09:31PM -0700 Benjamin Segall wrote:
> Phil Auld <pauld@redhat.com> writes:
>
> > In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
> > groups due to the previous fix simply taking the min. It should
> > reflect a limit imposed at that level or by an ancestor. Even
> > though cgroupv2 does not require child quota to be less than or
> > equal to that of its ancestors the task group will still be
> > constrained by such a quota so this should be shown here. Cgroupv1
> > continues to set this correctly.
> >
> > In both cases, add initialization when a new task group is created
> > based on the current parent's value (or RUNTIME_INF in the case of
> > root_task_group). Otherwise, the field is wrong until a quota is
> > changed after creation and __cfs_schedulable() is called.
> >
> > Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
> > Signed-off-by: Phil Auld <pauld@redhat.com>
> > Reviewed-by: Ben Segall <bsegall@google.com>
> > Cc: Ingo Molnar <mingo@redhat.com>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Vincent Guittot <vincent.guittot@linaro.org>
> > Cc: Juri Lelli <juri.lelli@redhat.com>
> > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> > Cc: Valentin Schneider <vschneid@redhat.com>
> > Cc: Ben Segall <bsegall@google.com>
> > Cc: Frederic Weisbecker <frederic@kernel.org>
> > Cc: Tejun Heo <tj@kernel.org>
> > ---
> >
> > v2: Improve comment about how setting hierarchical_quota correctly
> >
> > helps the scheduler. Remove extra parens.
> > kernel/sched/core.c | 13 +++++++++----
> > kernel/sched/fair.c | 7 ++++---
> > kernel/sched/sched.h | 2 +-
> > 3 files changed, 14 insertions(+), 8 deletions(-)
> >
> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > index a68d1276bab0..f80697a79baf 100644
> > --- a/kernel/sched/core.c
> > +++ b/kernel/sched/core.c
> > @@ -9904,7 +9904,7 @@ void __init sched_init(void)
> > ptr += nr_cpu_ids * sizeof(void **);
> >
> > root_task_group.shares = ROOT_TASK_GROUP_LOAD;
> > - init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
> > + init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
> > #endif /* CONFIG_FAIR_GROUP_SCHED */
> > #ifdef CONFIG_RT_GROUP_SCHED
> > root_task_group.rt_se = (struct sched_rt_entity **)ptr;
> > @@ -11038,11 +11038,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
> >
> > /*
> > * Ensure max(child_quota) <= parent_quota. On cgroup2,
> > - * always take the min. On cgroup1, only inherit when no
> > - * limit is set:
> > + * always take the non-RUNTIME_INF min. On cgroup1, only
> > + * inherit when no limit is set. In cgroup2 this is used
> > + * by the scheduler to determine if a given CFS task has a
> > + * bandwidth constraint at some higher level.
> > */
>
> It's still used for determining this on cgroup1 (and the cgroup1 code
> still works for that), right?
>
It would, except that the enforcement of child quota <= parent quota
means that cfs_rq->runtime_enabled will be set and we'll hit that first
on cgroup1. So we don't really use it for this determination in cgroup1.
But I could generalize that comment if you want.
Thanks,
Phil
> > if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
> > - quota = min(quota, parent_quota);
> > + if (quota == RUNTIME_INF)
> > + quota = parent_quota;
> > + else if (parent_quota != RUNTIME_INF)
> > + quota = min(quota, parent_quota);
> > } else {
> > if (quota == RUNTIME_INF)
> > quota = parent_quota;
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 373ff5f55884..d9b3d4617e16 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -6005,13 +6005,14 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
> > return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
> > }
> >
> > -void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
> > +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent)
> > {
> > raw_spin_lock_init(&cfs_b->lock);
> > cfs_b->runtime = 0;
> > cfs_b->quota = RUNTIME_INF;
> > cfs_b->period = ns_to_ktime(default_cfs_period());
> > cfs_b->burst = 0;
> > + cfs_b->hierarchical_quota = parent ? parent->hierarchical_quota : RUNTIME_INF;
> >
> > INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
> > hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
> > @@ -6168,7 +6169,7 @@ static inline int throttled_lb_pair(struct task_group *tg,
> > return 0;
> > }
> >
> > -void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
> > +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent) {}
> >
> > #ifdef CONFIG_FAIR_GROUP_SCHED
> > static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
> > @@ -12373,7 +12374,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
> >
> > tg->shares = NICE_0_LOAD;
> >
> > - init_cfs_bandwidth(tg_cfs_bandwidth(tg));
> > + init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent));
> >
> > for_each_possible_cpu(i) {
> > cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
> > diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> > index ec7b3e0a2b20..63822c9238cc 100644
> > --- a/kernel/sched/sched.h
> > +++ b/kernel/sched/sched.h
> > @@ -460,7 +460,7 @@ extern void unregister_fair_sched_group(struct task_group *tg);
> > extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
> > struct sched_entity *se, int cpu,
> > struct sched_entity *parent);
> > -extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
> > +extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent);
> >
> > extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
> > extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
>
--
Phil Auld <pauld@redhat.com> writes:
> On Wed, Jul 12, 2023 at 03:09:31PM -0700 Benjamin Segall wrote:
>> Phil Auld <pauld@redhat.com> writes:
>>
>> > In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
>> > groups due to the previous fix simply taking the min. It should
>> > reflect a limit imposed at that level or by an ancestor. Even
>> > though cgroupv2 does not require child quota to be less than or
>> > equal to that of its ancestors the task group will still be
>> > constrained by such a quota so this should be shown here. Cgroupv1
>> > continues to set this correctly.
>> >
>> > In both cases, add initialization when a new task group is created
>> > based on the current parent's value (or RUNTIME_INF in the case of
>> > root_task_group). Otherwise, the field is wrong until a quota is
>> > changed after creation and __cfs_schedulable() is called.
>> >
>> > Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
>> > Signed-off-by: Phil Auld <pauld@redhat.com>
>> > Reviewed-by: Ben Segall <bsegall@google.com>
>> > Cc: Ingo Molnar <mingo@redhat.com>
>> > Cc: Peter Zijlstra <peterz@infradead.org>
>> > Cc: Vincent Guittot <vincent.guittot@linaro.org>
>> > Cc: Juri Lelli <juri.lelli@redhat.com>
>> > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
>> > Cc: Valentin Schneider <vschneid@redhat.com>
>> > Cc: Ben Segall <bsegall@google.com>
>> > Cc: Frederic Weisbecker <frederic@kernel.org>
>> > Cc: Tejun Heo <tj@kernel.org>
>> > ---
>> >
>> > v2: Improve comment about how setting hierarchical_quota correctly
>> >
>> > helps the scheduler. Remove extra parens.
>> > kernel/sched/core.c | 13 +++++++++----
>> > kernel/sched/fair.c | 7 ++++---
>> > kernel/sched/sched.h | 2 +-
>> > 3 files changed, 14 insertions(+), 8 deletions(-)
>> >
>> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> > index a68d1276bab0..f80697a79baf 100644
>> > --- a/kernel/sched/core.c
>> > +++ b/kernel/sched/core.c
>> > @@ -9904,7 +9904,7 @@ void __init sched_init(void)
>> > ptr += nr_cpu_ids * sizeof(void **);
>> >
>> > root_task_group.shares = ROOT_TASK_GROUP_LOAD;
>> > - init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
>> > + init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
>> > #endif /* CONFIG_FAIR_GROUP_SCHED */
>> > #ifdef CONFIG_RT_GROUP_SCHED
>> > root_task_group.rt_se = (struct sched_rt_entity **)ptr;
>> > @@ -11038,11 +11038,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
>> >
>> > /*
>> > * Ensure max(child_quota) <= parent_quota. On cgroup2,
>> > - * always take the min. On cgroup1, only inherit when no
>> > - * limit is set:
>> > + * always take the non-RUNTIME_INF min. On cgroup1, only
>> > + * inherit when no limit is set. In cgroup2 this is used
>> > + * by the scheduler to determine if a given CFS task has a
>> > + * bandwidth constraint at some higher level.
>> > */
>>
>> It's still used for determining this on cgroup1 (and the cgroup1 code
>> still works for that), right?
>>
>
> It would, except that the enforcement of child quota <= parent quota
> means that cfs_rq->runtime_enabled will be set and we'll hit that first
> on cgroup1. So we don't really use it for this determination in
> cgroup1.
cgroup1 tg_cfs_schedulable_down only constricts child quota when it's
set. You can set quota=RUNTIME_INF on any cgroup, no matter what its
parent is. (The schedulable constraint is a little silly)
On Thu, Jul 13, 2023 at 01:12:04PM -0700 Benjamin Segall wrote:
> Phil Auld <pauld@redhat.com> writes:
>
> > On Wed, Jul 12, 2023 at 03:09:31PM -0700 Benjamin Segall wrote:
> >> Phil Auld <pauld@redhat.com> writes:
> >>
> >> > In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
> >> > groups due to the previous fix simply taking the min. It should
> >> > reflect a limit imposed at that level or by an ancestor. Even
> >> > though cgroupv2 does not require child quota to be less than or
> >> > equal to that of its ancestors the task group will still be
> >> > constrained by such a quota so this should be shown here. Cgroupv1
> >> > continues to set this correctly.
> >> >
> >> > In both cases, add initialization when a new task group is created
> >> > based on the current parent's value (or RUNTIME_INF in the case of
> >> > root_task_group). Otherwise, the field is wrong until a quota is
> >> > changed after creation and __cfs_schedulable() is called.
> >> >
> >> > Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
> >> > Signed-off-by: Phil Auld <pauld@redhat.com>
> >> > Reviewed-by: Ben Segall <bsegall@google.com>
> >> > Cc: Ingo Molnar <mingo@redhat.com>
> >> > Cc: Peter Zijlstra <peterz@infradead.org>
> >> > Cc: Vincent Guittot <vincent.guittot@linaro.org>
> >> > Cc: Juri Lelli <juri.lelli@redhat.com>
> >> > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> >> > Cc: Valentin Schneider <vschneid@redhat.com>
> >> > Cc: Ben Segall <bsegall@google.com>
> >> > Cc: Frederic Weisbecker <frederic@kernel.org>
> >> > Cc: Tejun Heo <tj@kernel.org>
> >> > ---
> >> >
> >> > v2: Improve comment about how setting hierarchical_quota correctly
> >> >
> >> > helps the scheduler. Remove extra parens.
> >> > kernel/sched/core.c | 13 +++++++++----
> >> > kernel/sched/fair.c | 7 ++++---
> >> > kernel/sched/sched.h | 2 +-
> >> > 3 files changed, 14 insertions(+), 8 deletions(-)
> >> >
> >> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> >> > index a68d1276bab0..f80697a79baf 100644
> >> > --- a/kernel/sched/core.c
> >> > +++ b/kernel/sched/core.c
> >> > @@ -9904,7 +9904,7 @@ void __init sched_init(void)
> >> > ptr += nr_cpu_ids * sizeof(void **);
> >> >
> >> > root_task_group.shares = ROOT_TASK_GROUP_LOAD;
> >> > - init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
> >> > + init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
> >> > #endif /* CONFIG_FAIR_GROUP_SCHED */
> >> > #ifdef CONFIG_RT_GROUP_SCHED
> >> > root_task_group.rt_se = (struct sched_rt_entity **)ptr;
> >> > @@ -11038,11 +11038,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
> >> >
> >> > /*
> >> > * Ensure max(child_quota) <= parent_quota. On cgroup2,
> >> > - * always take the min. On cgroup1, only inherit when no
> >> > - * limit is set:
> >> > + * always take the non-RUNTIME_INF min. On cgroup1, only
> >> > + * inherit when no limit is set. In cgroup2 this is used
> >> > + * by the scheduler to determine if a given CFS task has a
> >> > + * bandwidth constraint at some higher level.
> >> > */
> >>
> >> It's still used for determining this on cgroup1 (and the cgroup1 code
> >> still works for that), right?
> >>
> >
> > It would, except that the enforcement of child quota <= parent quota
> > means that cfs_rq->runtime_enabled will be set and we'll hit that first
> > on cgroup1. So we don't really use it for this determination in
> > cgroup1.
>
> cgroup1 tg_cfs_schedulable_down only constricts child quota when it's
> set. You can set quota=RUNTIME_INF on any cgroup, no matter what its
> parent is. (The schedulable constraint is a little silly)
>
Aargh :) I had "In both cases this ..." there before I talked myself out
of it.
I'll update this one.
Cheers,
Phil
--
In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
groups due to the previous fix simply taking the min. It should
reflect a limit imposed at that level or by an ancestor. Even
though cgroupv2 does not require child quota to be less than or
equal to that of its ancestors the task group will still be
constrained by such a quota so this should be shown here. Cgroupv1
continues to set this correctly.
In both cases, add initialization when a new task group is created
based on the current parent's value (or RUNTIME_INF in the case of
root_task_group). Otherwise, the field is wrong until a quota is
changed after creation and __cfs_schedulable() is called.
Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
Signed-off-by: Phil Auld <pauld@redhat.com>
Reviewed-by: Ben Segall <bsegall@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
---
v3: Make comment apply to both cgroup1 and 2.
v2: Improve comment about how setting hierarchical_quota correctly
helps the scheduler. Remove extra parens.
kernel/sched/core.c | 13 +++++++++----
kernel/sched/fair.c | 7 ++++---
kernel/sched/sched.h | 2 +-
3 files changed, 14 insertions(+), 8 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a68d1276bab0..f7c1510fdac1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9904,7 +9904,7 @@ void __init sched_init(void)
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
- init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
+ init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -11038,11 +11038,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
/*
* Ensure max(child_quota) <= parent_quota. On cgroup2,
- * always take the min. On cgroup1, only inherit when no
- * limit is set:
+ * always take the non-RUNTIME_INF min. On cgroup1, only
+ * inherit when no limit is set. In both cases this is used
+ * by the scheduler to determine if a given CFS task has a
+ * bandwidth constraint at some higher level.
*/
if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
- quota = min(quota, parent_quota);
+ if (quota == RUNTIME_INF)
+ quota = parent_quota;
+ else if (parent_quota != RUNTIME_INF)
+ quota = min(quota, parent_quota);
} else {
if (quota == RUNTIME_INF)
quota = parent_quota;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 373ff5f55884..d9b3d4617e16 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6005,13 +6005,14 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}
-void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent)
{
raw_spin_lock_init(&cfs_b->lock);
cfs_b->runtime = 0;
cfs_b->quota = RUNTIME_INF;
cfs_b->period = ns_to_ktime(default_cfs_period());
cfs_b->burst = 0;
+ cfs_b->hierarchical_quota = parent ? parent->hierarchical_quota : RUNTIME_INF;
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
@@ -6168,7 +6169,7 @@ static inline int throttled_lb_pair(struct task_group *tg,
return 0;
}
-void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
+void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent) {}
#ifdef CONFIG_FAIR_GROUP_SCHED
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
@@ -12373,7 +12374,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
tg->shares = NICE_0_LOAD;
- init_cfs_bandwidth(tg_cfs_bandwidth(tg));
+ init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent));
for_each_possible_cpu(i) {
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ec7b3e0a2b20..63822c9238cc 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -460,7 +460,7 @@ extern void unregister_fair_sched_group(struct task_group *tg);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
-extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
+extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent);
extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
--
2.31.1On Fri, Jul 14, 2023 at 08:57:46AM -0400, Phil Auld wrote:
> In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
> groups due to the previous fix simply taking the min. It should
> reflect a limit imposed at that level or by an ancestor. Even
> though cgroupv2 does not require child quota to be less than or
> equal to that of its ancestors the task group will still be
> constrained by such a quota so this should be shown here. Cgroupv1
> continues to set this correctly.
>
> In both cases, add initialization when a new task group is created
> based on the current parent's value (or RUNTIME_INF in the case of
> root_task_group). Otherwise, the field is wrong until a quota is
> changed after creation and __cfs_schedulable() is called.
>
> Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
Does this really fix anything observable? I wonder whether this is more
misleading than helpful. In cgroup2, the value simply wasn't being used,
right?
> Signed-off-by: Phil Auld <pauld@redhat.com>
> Reviewed-by: Ben Segall <bsegall@google.com>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Vincent Guittot <vincent.guittot@linaro.org>
> Cc: Juri Lelli <juri.lelli@redhat.com>
> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> Cc: Valentin Schneider <vschneid@redhat.com>
> Cc: Ben Segall <bsegall@google.com>
> Cc: Frederic Weisbecker <frederic@kernel.org>
> Cc: Tejun Heo <tj@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
> + * always take the non-RUNTIME_INF min. On cgroup1, only
> + * inherit when no limit is set. In both cases this is used
> + * by the scheduler to determine if a given CFS task has a
> + * bandwidth constraint at some higher level.
The discussion on this comment is stretching too long and this is fine too
but what's worth commenting for cgroup2 is that the limit value itself
doesn't mean anything and we're just latching onto the value used by cgroup1
to track whether there's any limit active or not.
Thanks.
--
tejun
On Mon, Jul 17, 2023 at 08:27:24AM -1000 Tejun Heo wrote:
> On Fri, Jul 14, 2023 at 08:57:46AM -0400, Phil Auld wrote:
> > In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
> > groups due to the previous fix simply taking the min. It should
> > reflect a limit imposed at that level or by an ancestor. Even
> > though cgroupv2 does not require child quota to be less than or
> > equal to that of its ancestors the task group will still be
> > constrained by such a quota so this should be shown here. Cgroupv1
> > continues to set this correctly.
> >
> > In both cases, add initialization when a new task group is created
> > based on the current parent's value (or RUNTIME_INF in the case of
> > root_task_group). Otherwise, the field is wrong until a quota is
> > changed after creation and __cfs_schedulable() is called.
> >
> > Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
>
> Does this really fix anything observable? I wonder whether this is more
> misleading than helpful. In cgroup2, the value simply wasn't being used,
> right?
>
It wasn't being used but was actively being set wrong. I mean if we are
going to bother doing the __cfs_schedulable() tg tree walk we might as
well have not been setting a bogus value. But that said, no it was not
observable until I tried to use it.
I'm fine if that's dropped. I just wanted it set right going forward :)
> > Signed-off-by: Phil Auld <pauld@redhat.com>
> > Reviewed-by: Ben Segall <bsegall@google.com>
> > Cc: Ingo Molnar <mingo@redhat.com>
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Vincent Guittot <vincent.guittot@linaro.org>
> > Cc: Juri Lelli <juri.lelli@redhat.com>
> > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> > Cc: Valentin Schneider <vschneid@redhat.com>
> > Cc: Ben Segall <bsegall@google.com>
> > Cc: Frederic Weisbecker <frederic@kernel.org>
> > Cc: Tejun Heo <tj@kernel.org>
>
> Acked-by: Tejun Heo <tj@kernel.org>
>
Thanks!
> > + * always take the non-RUNTIME_INF min. On cgroup1, only
> > + * inherit when no limit is set. In both cases this is used
> > + * by the scheduler to determine if a given CFS task has a
> > + * bandwidth constraint at some higher level.
>
> The discussion on this comment is stretching too long and this is fine too
> but what's worth commenting for cgroup2 is that the limit value itself
> doesn't mean anything and we're just latching onto the value used by cgroup1
> to track whether there's any limit active or not.
I thought that was implied by the wording. "If a given task has a bandwidth
contraint" not "what a given task's bandwidth constraint is". In both cases
that's how the other parts of the scheduler are using it. The actual
non-RUNTIME_INF value only matters in this function (and only for cgroup1
indeed).
But... the value is just as accurate for cgroup2 and cgroup1. The task is
still going to be limited by that bandwidth constraint even if its own
bandwidth limit is nominally higher, right?
Cheers,
Phil
>
> Thanks.
>
> --
> tejun
>
--
Hi Tejun,
On Tue, Jul 18, 2023 at 08:57:59AM -0400 Phil Auld wrote:
> On Mon, Jul 17, 2023 at 08:27:24AM -1000 Tejun Heo wrote:
> > On Fri, Jul 14, 2023 at 08:57:46AM -0400, Phil Auld wrote:
> > > In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
> > > groups due to the previous fix simply taking the min. It should
> > > reflect a limit imposed at that level or by an ancestor. Even
> > > though cgroupv2 does not require child quota to be less than or
> > > equal to that of its ancestors the task group will still be
> > > constrained by such a quota so this should be shown here. Cgroupv1
> > > continues to set this correctly.
> > >
> > > In both cases, add initialization when a new task group is created
> > > based on the current parent's value (or RUNTIME_INF in the case of
> > > root_task_group). Otherwise, the field is wrong until a quota is
> > > changed after creation and __cfs_schedulable() is called.
> > >
> > > Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
> >
> > Does this really fix anything observable? I wonder whether this is more
> > misleading than helpful. In cgroup2, the value simply wasn't being used,
> > right?
> >
(Sorry, my editor bit me...I had added:)
I don't feel strongly about the fixes. What was there seemed broken to me
so ... "Fixes". But it doesn't matter.
>
> It wasn't being used but was actively being set wrong. I mean if we are
> going to bother doing the __cfs_schedulable() tg tree walk we might as
> well have not been setting a bogus value. But that said, no it was not
> observable until I tried to use it.
>
We have a field called hierarchical_quota, that was being unconditionally
set to -1 for cgroup2. I figured it would be more correct to reflect
the hieratchical quota. :)
> I'm fine if that's dropped. I just wanted it set right going forward :)
>
>
> > > Signed-off-by: Phil Auld <pauld@redhat.com>
> > > Reviewed-by: Ben Segall <bsegall@google.com>
> > > Cc: Ingo Molnar <mingo@redhat.com>
> > > Cc: Peter Zijlstra <peterz@infradead.org>
> > > Cc: Vincent Guittot <vincent.guittot@linaro.org>
> > > Cc: Juri Lelli <juri.lelli@redhat.com>
> > > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> > > Cc: Valentin Schneider <vschneid@redhat.com>
> > > Cc: Ben Segall <bsegall@google.com>
> > > Cc: Frederic Weisbecker <frederic@kernel.org>
> > > Cc: Tejun Heo <tj@kernel.org>
> >
> > Acked-by: Tejun Heo <tj@kernel.org>
> >
>
> Thanks!
>
>
> > > + * always take the non-RUNTIME_INF min. On cgroup1, only
> > > + * inherit when no limit is set. In both cases this is used
> > > + * by the scheduler to determine if a given CFS task has a
> > > + * bandwidth constraint at some higher level.
> >
> > The discussion on this comment is stretching too long and this is fine too
> > but what's worth commenting for cgroup2 is that the limit value itself
> > doesn't mean anything and we're just latching onto the value used by cgroup1
> > to track whether there's any limit active or not.
>
> I thought that was implied by the wording. "If a given task has a bandwidth
> contraint" not "what a given task's bandwidth constraint is". In both cases
> that's how the other parts of the scheduler are using it. The actual
> non-RUNTIME_INF value only matters in this function (and only for cgroup1
> indeed).
>
> But... the value is just as accurate for cgroup2 and cgroup1. The task is
> still going to be limited by that bandwidth constraint even if its own
> bandwidth limit is nominally higher, right?
>
>
> Cheers,
> Phil
>
> >
> > Thanks.
> >
> > --
> > tejun
> >
>
> --
>
--
The following commit has been merged into the sched/core branch of tip:
Commit-ID: c98c18270be115678f4295b10a5af5dcc9c4efa0
Gitweb: https://git.kernel.org/tip/c98c18270be115678f4295b10a5af5dcc9c4efa0
Author: Phil Auld <pauld@redhat.com>
AuthorDate: Fri, 14 Jul 2023 08:57:46 -04:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 02 Aug 2023 16:19:26 +02:00
sched, cgroup: Restore meaning to hierarchical_quota
In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
groups due to the previous fix simply taking the min. It should
reflect a limit imposed at that level or by an ancestor. Even
though cgroupv2 does not require child quota to be less than or
equal to that of its ancestors the task group will still be
constrained by such a quota so this should be shown here. Cgroupv1
continues to set this correctly.
In both cases, add initialization when a new task group is created
based on the current parent's value (or RUNTIME_INF in the case of
root_task_group). Otherwise, the field is wrong until a quota is
changed after creation and __cfs_schedulable() is called.
Fixes: c53593e5cb69 ("sched, cgroup: Don't reject lower cpu.max on ancestors")
Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230714125746.812891-1-pauld@redhat.com
---
kernel/sched/core.c | 13 +++++++++----
kernel/sched/fair.c | 7 ++++---
kernel/sched/sched.h | 2 +-
3 files changed, 14 insertions(+), 8 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 83e3654..3af25ca 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9953,7 +9953,7 @@ void __init sched_init(void)
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
- init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
+ init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -11087,11 +11087,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
/*
* Ensure max(child_quota) <= parent_quota. On cgroup2,
- * always take the min. On cgroup1, only inherit when no
- * limit is set:
+ * always take the non-RUNTIME_INF min. On cgroup1, only
+ * inherit when no limit is set. In both cases this is used
+ * by the scheduler to determine if a given CFS task has a
+ * bandwidth constraint at some higher level.
*/
if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
- quota = min(quota, parent_quota);
+ if (quota == RUNTIME_INF)
+ quota = parent_quota;
+ else if (parent_quota != RUNTIME_INF)
+ quota = min(quota, parent_quota);
} else {
if (quota == RUNTIME_INF)
quota = parent_quota;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f55b0a7..26bfbb6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6045,13 +6045,14 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}
-void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
+void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent)
{
raw_spin_lock_init(&cfs_b->lock);
cfs_b->runtime = 0;
cfs_b->quota = RUNTIME_INF;
cfs_b->period = ns_to_ktime(default_cfs_period());
cfs_b->burst = 0;
+ cfs_b->hierarchical_quota = parent ? parent->hierarchical_quota : RUNTIME_INF;
INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
@@ -6217,7 +6218,7 @@ static inline int throttled_lb_pair(struct task_group *tg,
return 0;
}
-void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
+void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent) {}
#ifdef CONFIG_FAIR_GROUP_SCHED
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
@@ -12599,7 +12600,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
tg->shares = NICE_0_LOAD;
- init_cfs_bandwidth(tg_cfs_bandwidth(tg));
+ init_cfs_bandwidth(tg_cfs_bandwidth(tg), tg_cfs_bandwidth(parent));
for_each_possible_cpu(i) {
cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9baeb1a..602de71 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -454,7 +454,7 @@ extern void unregister_fair_sched_group(struct task_group *tg);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
struct sched_entity *se, int cpu,
struct sched_entity *parent);
-extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
+extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, struct cfs_bandwidth *parent);
extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);© 2016 - 2026 Red Hat, Inc.