Fix the insertion of cfs_rq in rq->leaf_cfs_rq_list to ensure that a child will always be called before its parent.

The hierarchical order in shares update list has been introduced by commit 67e86250f8ea ("sched: Introduce hierarchal order on shares update list")

With the current implementation a child can be still put after its parent.

Lets take the example of root \ b /\ c d* | e*

with root -> b -> c already enqueued but not d -> e so the leaf_cfs_rq_list looks like: head -> c -> b -> root -> tail

The branch d -> e will be added the first time that they are enqueued, starting with e then d.

When e is added, its parents is not already on the list so e is put at the tail : head -> c -> b -> root -> e -> tail

Then, d is added at the head because its parent is already on the list: head -> d -> c -> b -> root -> e -> tail

e is not placed at the right position and will be called the last whereas it should be called at the beginning.

Because it follows the bottom-up enqueue sequence, we are sure that we will finished to add either a cfs_rq without parent or a cfs_rq with a parent that is already on the list. We can use this event to detect when we have finished to add a new branch. For the others, whose parents are not already added, we have to ensure that they will be added after their children that have just been inserted the steps before, and after any potential parents that are already in the list. The easiest way is to put the cfs_rq just after the last inserted one and to keep track of it untl the branch is fully added.

Signed-off-by: Vincent Guittot vincent.guittot@linaro.org --- kernel/sched/core.c | 1 + kernel/sched/fair.c | 54 +++++++++++++++++++++++++++++++++++++++++++++------- kernel/sched/sched.h | 1 + 3 files changed, 49 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c index aae08ce..59bce4f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7582,6 +7582,7 @@ void __init sched_init(void) #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.shares = ROOT_TASK_GROUP_LOAD; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; /* * How much cpu bandwidth does root_task_group get? * diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 584b86f..ecc66d6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -290,19 +290,59 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { if (!cfs_rq->on_list) { + struct rq *rq = rq_of(cfs_rq); + int cpu = cpu_of(rq); /* * Ensure we either appear before our parent (if already * enqueued) or force our parent to appear after us when it is - * enqueued. The fact that we always enqueue bottom-up - * reduces this to two cases. + * enqueued. The fact that we always enqueue bottom-up + * reduces this to two cases and a special case for the root + * cfs_rq. Furthermore, it also means that we will always reset + * tmp_alone_branch either when the branch is connected + * to a tree or when we reach the beg of the tree */ if (cfs_rq->tg->parent && - cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) { - list_add_rcu(&cfs_rq->leaf_cfs_rq_list, - &rq_of(cfs_rq)->leaf_cfs_rq_list); - } else { + cfs_rq->tg->parent->cfs_rq[cpu]->on_list) { + /* + * If parent is already on the list, we add the child + * just before. Thanks to circular linked property of + * the list, this means to put the child at the tail + * of the list that starts by parent. + */ + list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, + &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list)); + /* + * The branch is now connected to its tree so we can + * reset tmp_alone_branch to the beginning of the + * list. + */ + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; + } else if (!cfs_rq->tg->parent) { + /* + * cfs rq without parent should be put + * at the tail of the list. + */ list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, - &rq_of(cfs_rq)->leaf_cfs_rq_list); + &rq->leaf_cfs_rq_list); + /* + * We have reach the beg of a tree so we can reset + * tmp_alone_branch to the beginning of the list. + */ + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; + } else { + /* + * The parent has not already been added so we want to + * make sure that it will be put after us. + * tmp_alone_branch points to the beg of the branch + * where we will add parent. + */ + list_add_rcu(&cfs_rq->leaf_cfs_rq_list, + rq->tmp_alone_branch); + /* + * update tmp_alone_branch to points to the new beg + * of the branch + */ + rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list; }

cfs_rq->on_list = 1; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 19b9986..f1185c3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -623,6 +623,7 @@ struct rq { #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this cpu: */ struct list_head leaf_cfs_rq_list; + struct list_head *tmp_alone_branch; #endif /* CONFIG_FAIR_GROUP_SCHED */

/*

When a task moves from/to a cfs_rq, we set a flag which is then used to propagate the change at parent level (sched_entity and cfs_rq) during next update. If the cfs_rq is throttled, the flag will stay pending until the cfs_rw is unthrottled.

For propagating the utilization, we copy the utilization of group cfs_rq to the sched_entity.

For propagating the load, we have to take into account the load of the whole task group in order to evaluate the load of the sched_entity. Similarly to what was done before the rewrite of PELT, we add a correction factor in case the task group's load is greater than its share so it will contribute the same load of a task of equal weight.

Signed-off-by: Vincent Guittot vincent.guittot@linaro.org --- kernel/sched/fair.c | 200 ++++++++++++++++++++++++++++++++++++++++++++++++++- kernel/sched/sched.h | 1 + 2 files changed, 200 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 52cbc92..91fc949 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3031,6 +3031,162 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) }

/* + * Signed add and clamp on underflow. + * + * Explicitly do a load-store to ensure the intermediate value never hits + * memory. This allows lockless observations without ever seeing the negative + * values. + */ +#define add_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + typeof(_val) res, val = (_val); \ + typeof(*ptr) var = READ_ONCE(*ptr); \ + res = var + val; \ + if (res < 0) \ + res = 0; \ + WRITE_ONCE(*ptr, res); \ +} while (0) + +#ifdef CONFIG_FAIR_GROUP_SCHED +/* Take into account change of utilization of a child task group */ +static inline void +update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct cfs_rq *gcfs_rq = group_cfs_rq(se); + long delta = gcfs_rq->avg.util_avg - se->avg.util_avg; + + /* Nothing to update */ + if (!delta) + return; + + /* Set new sched_entity's utilization */ + se->avg.util_avg = gcfs_rq->avg.util_avg; + se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX; + + /* Update parent cfs_rq utilization */ + add_positive(&cfs_rq->avg.util_avg, delta); + cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX; +} + +/* Take into account change of load of a child task group */ +static inline void +update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct cfs_rq *gcfs_rq = group_cfs_rq(se); + long delta, load = gcfs_rq->avg.load_avg; + + /* + * If the load of group cfs_rq is null, the load of the + * sched_entity will also be null so we can skip the formula + */ + if (load) { + long tg_load; + + /* Get tg's load and ensure tg_load > 0 */ + tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1; + + /* Ensure tg_load >= load and updated with current load*/ + tg_load -= gcfs_rq->tg_load_avg_contrib; + tg_load += load; + + /* + * We need to compute a correction term in the case that the + * task group is consuming more cpu than a task of equal + * weight. A task with a weight equals to tg->shares will have + * a load less or equal to scale_load_down(tg->shares). + * Similarly, the sched_entities that represent the task group + * at parent level, can't have a load higher than + * scale_load_down(tg->shares). And the Sum of sched_entities' + * load must be <= scale_load_down(tg->shares). + */ + if (tg_load > scale_load_down(gcfs_rq->tg->shares)) { + /* scale gcfs_rq's load into tg's shares*/ + load *= scale_load_down(gcfs_rq->tg->shares); + load /= tg_load; + } + } + + delta = load - se->avg.load_avg; + + /* Nothing to update */ + if (!delta) + return; + + /* Set new sched_entity's load */ + se->avg.load_avg = load; + se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX; + + /* Update parent cfs_rq load */ + add_positive(&cfs_rq->avg.load_avg, delta); + cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX; + + /* + * If the sched_entity is already enqueued, we also have to update the + * runnable load avg. + */ + if (se->on_rq) { + /* Update parent cfs_rq runnable_load_avg */ + add_positive(&cfs_rq->runnable_load_avg, delta); + cfs_rq->runnable_load_sum = cfs_rq->runnable_load_avg * LOAD_AVG_MAX; + } +} + +static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) +{ + /* set cfs_rq's flag */ + cfs_rq->propagate_avg = 1; +} + +static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se) +{ + /* Get my cfs_rq */ + struct cfs_rq *cfs_rq = group_cfs_rq(se); + + /* Nothing to propagate */ + if (!cfs_rq->propagate_avg) + return 0; + + /* Clear my cfs_rq's flag */ + cfs_rq->propagate_avg = 0; + + return 1; +} + +/* Update task and its cfs_rq load average */ +static inline int propagate_entity_load_avg(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq; + + if (entity_is_task(se)) + return 0; + + if (!test_and_clear_tg_cfs_propagate(se)) + return 0; + + /* Get parent cfs_rq */ + cfs_rq = cfs_rq_of(se); + + /* Propagate to parent */ + set_tg_cfs_propagate(cfs_rq); + + /* Update utilization */ + update_tg_cfs_util(cfs_rq, se); + + /* Update load */ + update_tg_cfs_load(cfs_rq, se); + + return 1; +} +#else +static inline int propagate_entity_load_avg(struct sched_entity *se) +{ + return 0; +} + +static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {} +#endif + +/* * Unsigned subtract and clamp on underflow. * * Explicitly do a load-store to ensure the intermediate value never hits @@ -3111,6 +3267,7 @@ static inline void update_load_avg(struct sched_entity *se, int flags) u64 now = cfs_rq_clock_task(cfs_rq); struct rq *rq = rq_of(cfs_rq); int cpu = cpu_of(rq); + int decayed;

/* * Track task load average for carrying it to new CPU after migrated, and @@ -3121,7 +3278,11 @@ static inline void update_load_avg(struct sched_entity *se, int flags) se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL);

- if (update_cfs_rq_load_avg(now, cfs_rq, true) && (flags & UPDATE_TG)) + decayed = update_cfs_rq_load_avg(now, cfs_rq, true); + + decayed |= propagate_entity_load_avg(se); + + if (decayed && (flags & UPDATE_TG)) update_tg_load_avg(cfs_rq, 0); }

@@ -3140,6 +3301,7 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s cfs_rq->avg.load_sum += se->avg.load_sum; cfs_rq->avg.util_avg += se->avg.util_avg; cfs_rq->avg.util_sum += se->avg.util_sum; + set_tg_cfs_propagate(cfs_rq);

cfs_rq_util_change(cfs_rq); } @@ -3159,6 +3321,7 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + set_tg_cfs_propagate(cfs_rq);

cfs_rq_util_change(cfs_rq); } @@ -8704,6 +8867,22 @@ static void detach_task_cfs_rq(struct task_struct *p) update_load_avg(se, 0); detach_entity_load_avg(cfs_rq, se); update_tg_load_avg(cfs_rq, false); + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* + * Propagate the detach across the tg tree to make it visible to the + * root + */ + se = se->parent; + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + + if (cfs_rq_throttled(cfs_rq)) + break; + + update_load_avg(se, UPDATE_TG); + } +#endif }

static void attach_entity_cfs_rq(struct sched_entity *se) @@ -8722,6 +8901,22 @@ static void attach_entity_cfs_rq(struct sched_entity *se) update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD); attach_entity_load_avg(cfs_rq, se); update_tg_load_avg(cfs_rq, false); + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* + * Propagate the attach across the tg tree to make it visible to the + * root + */ + se = se->parent; + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + + if (cfs_rq_throttled(cfs_rq)) + break; + + update_load_avg(se, UPDATE_TG); + } +#endif }

static void attach_task_cfs_rq(struct task_struct *p) @@ -8783,6 +8978,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq) cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; #endif #ifdef CONFIG_SMP +#ifdef CONFIG_FAIR_GROUP_SCHED + cfs_rq->propagate_avg = 0; +#endif atomic_long_set(&cfs_rq->removed_load_avg, 0); atomic_long_set(&cfs_rq->removed_util_avg, 0); #endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f1185c3..47385e2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -404,6 +404,7 @@ struct cfs_rq { unsigned long runnable_load_avg; #ifdef CONFIG_FAIR_GROUP_SCHED unsigned long tg_load_avg_contrib; + unsigned long propagate_avg; #endif atomic_long_t removed_load_avg, removed_util_avg; #ifndef CONFIG_64BIT

A task can be asynchronously detached from cfs_rq when migrating between CPUs. The load of the migrated task is then removed from source cfs_rq during its next update. We use this event to set propagation flag.

During the load balance, we take advanatge of the update of blocked load to propagate any pending changes.The propagation relies on patch "sched: fix hierarchical order in rq->leaf_cfs_rq_list", which orders children and parents, to ensure that it's done in one pass.

Signed-off-by: Vincent Guittot vincent.guittot@linaro.org --- kernel/sched/fair.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 91fc949..4c0a404 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3231,6 +3231,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) sub_positive(&sa->load_avg, r); sub_positive(&sa->load_sum, r * LOAD_AVG_MAX); removed_load = 1; + set_tg_cfs_propagate(cfs_rq); }

if (atomic_long_read(&cfs_rq->removed_util_avg)) { @@ -3238,6 +3239,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) sub_positive(&sa->util_avg, r); sub_positive(&sa->util_sum, r * LOAD_AVG_MAX); removed_util = 1; + set_tg_cfs_propagate(cfs_rq); }

decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa, @@ -6803,6 +6805,10 @@ static void update_blocked_averages(int cpu)

if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true)) update_tg_load_avg(cfs_rq, 0); + + /* Propagate pending load changes to the parent */ + if (cfs_rq->tg->se[cpu]) + update_load_avg(cfs_rq->tg->se[cpu], 0); } raw_spin_unlock_irqrestore(&rq->lock, flags); }