From: Tejun Heo <tj@kernel.org> mainline inclusion from mainline-v6.12-rc1 commit d8c7bc2e209170ff78b88b85258546aa6e337af9 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IDC9YK Reference: https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commi... -------------------------------- When a task switches to a new sched_class, the prev and new classes are notified through ->switched_from() and ->switched_to(), respectively, after the switching is done. A new BPF extensible sched_class will have callbacks that allow the BPF scheduler to keep track of relevant task states (like priority and cpumask). Those callbacks aren't called while a task is on a different sched_class. When a task comes back, we wanna tell the BPF progs the up-to-date state before the task gets enqueued, so we need a hook which is called before the switching is committed. This patch adds ->switching_to() which is called during sched_class switch through check_class_changing() before the task is restored. Also, this patch exposes check_class_changing/changed() in kernel/sched/sched.h. They will be used by the new BPF extensible sched_class to implement implicit sched_class switching which is used e.g. when falling back to CFS when the BPF scheduler fails or unloads. This is a prep patch and doesn't cause any behavior changes. The new operation and exposed functions aren't used yet. v3: Refreshed on top of tip:sched/core. v2: Improve patch description w/ details on planned use. Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: David Vernet <dvernet@meta.com> Acked-by: Josh Don <joshdon@google.com> Acked-by: Hao Luo <haoluo@google.com> Acked-by: Barret Rhoden <brho@google.com> Signed-off-by: Zicheng Qu <quzicheng@huawei.com> --- kernel/sched/core.c | 12 ++++++++++++ kernel/sched/sched.h | 3 +++ kernel/sched/syscalls.c | 1 + 3 files changed, 16 insertions(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0a2cd4558a1f..139a0541ee7c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2040,6 +2040,17 @@ inline int task_curr(const struct task_struct *p) return cpu_curr(task_cpu(p)) == p; } +/* + * ->switching_to() is called with the pi_lock and rq_lock held and must not + * mess with locking. + */ +void check_class_changing(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class) +{ + if (prev_class != p->sched_class && p->sched_class->switching_to) + p->sched_class->switching_to(rq, p); +} + /* * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock, * use the balance_callback list if you want balancing. @@ -7021,6 +7032,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) } __setscheduler_prio(p, prio); + check_class_changing(rq, p, prev_class); if (queued) enqueue_task(rq, p, queue_flag); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d133efd5f3e5..4ec836045ce3 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2482,6 +2482,7 @@ struct sched_class { * cannot assume the switched_from/switched_to pair is serialized by * rq->lock. They are however serialized by p->pi_lock. */ + void (*switching_to) (struct rq *this_rq, struct task_struct *task); void (*switched_from)(struct rq *this_rq, struct task_struct *task); void (*switched_to) (struct rq *this_rq, struct task_struct *task); void (*prio_changed) (struct rq *this_rq, struct task_struct *task, @@ -3878,6 +3879,8 @@ extern void set_load_weight(struct task_struct *p, bool update_load); extern void enqueue_task(struct rq *rq, struct task_struct *p, int flags); extern void dequeue_task(struct rq *rq, struct task_struct *p, int flags); +extern void check_class_changing(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class); extern void check_class_changed(struct rq *rq, struct task_struct *p, const struct sched_class *prev_class, int oldprio); diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index a0efcc8661e5..f3b3acec7a3d 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -790,6 +790,7 @@ int __sched_setscheduler(struct task_struct *p, __setscheduler_prio(p, newprio); } __setscheduler_uclamp(p, attr); + check_class_changing(rq, p, prev_class); if (queued) { /* -- 2.34.1