From: Tejun Heo <tj@kernel.org> mainline inclusion from mainline-v6.12-rc1 commit 8b1451f2f723f845c05b8bad3d4c45de284338b5 category: feature bugzilla: https://atomgit.com/openeuler/kernel/issues/8335 Reference: https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commi... -------------------------------- SCX_TASK_BAL_KEEP is used by balance_one() to tell pick_next_task_scx() to keep running the current task. It's not really a task property. Replace it with SCX_RQ_BAL_KEEP which resides in rq->scx.flags and is a better fit for the usage. Also, the existing clearing rule is unnecessarily strict and makes it difficult to use with core-sched. Just clear it on entry to balance_one(). Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Zicheng Qu <quzicheng@huawei.com> Signed-off-by: cheliequan <cheliequan@inspur.com> Signed-off-by: Luo Gengkun <luogengkun2@huawei.com> --- include/linux/sched/ext.h | 1 - kernel/sched/ext.c | 20 +++++++++----------- kernel/sched/sched.h | 1 + 3 files changed, 10 insertions(+), 12 deletions(-) diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index 69f68e2121a8..db2a266113ac 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -71,7 +71,6 @@ struct scx_dispatch_q { /* scx_entity.flags */ enum scx_ent_flags { SCX_TASK_QUEUED = 1 << 0, /* on ext runqueue */ - SCX_TASK_BAL_KEEP = 1 << 1, /* balance decided to keep current */ SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */ SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 89144e5ea060..aac9b75a459f 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2517,6 +2517,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev, bool local) lockdep_assert_rq_held(rq); rq->scx.flags |= SCX_RQ_IN_BALANCE; + rq->scx.flags &= ~SCX_RQ_BAL_KEEP; if (static_branch_unlikely(&scx_ops_cpu_preempt) && unlikely(rq->scx.cpu_released)) { @@ -2532,7 +2533,6 @@ static int balance_one(struct rq *rq, struct task_struct *prev, bool local) } if (prev_on_scx) { - WARN_ON_ONCE(local && (prev->scx.flags & SCX_TASK_BAL_KEEP)); update_curr_scx(rq); /* @@ -2547,13 +2547,13 @@ static int balance_one(struct rq *rq, struct task_struct *prev, bool local) * * When balancing a remote CPU for core-sched, there won't be a * following put_prev_task_scx() call and we don't own - * %SCX_TASK_BAL_KEEP. Instead, pick_task_scx() will test the - * same conditions later and pick @rq->curr accordingly. + * %SCX_RQ_BAL_KEEP. Instead, pick_task_scx() will test the same + * conditions later and pick @rq->curr accordingly. */ if ((prev->scx.flags & SCX_TASK_QUEUED) && prev->scx.slice && !scx_ops_bypassing()) { if (local) - prev->scx.flags |= SCX_TASK_BAL_KEEP; + rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; } } @@ -2613,7 +2613,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev, bool local) if ((prev->scx.flags & SCX_TASK_QUEUED) && (!static_branch_unlikely(&scx_ops_enq_last) || scx_ops_bypassing())) { if (local) - prev->scx.flags |= SCX_TASK_BAL_KEEP; + rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; } rq->scx.flags &= ~SCX_RQ_IN_BALANCE; @@ -2735,8 +2735,6 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true); if (p->scx.flags & SCX_TASK_QUEUED) { - p->scx.flags &= ~SCX_TASK_BAL_KEEP; - set_task_runnable(rq, p); /* @@ -2781,8 +2779,8 @@ static struct task_struct *pick_next_task_scx(struct rq *rq, * if necessary and keep running @prev. Otherwise, pop the first one * from the local DSQ. */ - if (prev->scx.flags & SCX_TASK_BAL_KEEP) { - prev->scx.flags &= ~SCX_TASK_BAL_KEEP; + if ((rq->scx.flags & SCX_RQ_BAL_KEEP) && + !WARN_ON_ONCE(prev->sched_class != &ext_sched_class)) { p = prev; if (!p->scx.slice) p->scx.slice = SCX_SLICE_DFL; @@ -2850,7 +2848,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, * * As put_prev_task_scx() hasn't been called on remote CPUs, we can't just look * at the first task in the local dsq. @rq->curr has to be considered explicitly - * to mimic %SCX_TASK_BAL_KEEP. + * to mimic %SCX_RQ_BAL_KEEP. */ static struct task_struct *pick_task_scx(struct rq *rq) { @@ -3880,7 +3878,7 @@ bool task_should_scx(struct task_struct *p) * * b. ops.dispatch() is ignored. * - * c. balance_scx() does not set %SCX_TASK_BAL_KEEP on non-zero slice as slice + * c. balance_scx() does not set %SCX_RQ_BAL_KEEP on non-zero slice as slice * can't be trusted. Whenever a tick triggers, the running task is rotated to * the tail of the queue with core_sched_at touched. * diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index ddc24d5affe2..b052b5cf6926 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -840,6 +840,7 @@ enum scx_rq_flags { */ SCX_RQ_ONLINE = 1 << 0, SCX_RQ_CAN_STOP_TICK = 1 << 1, + SCX_RQ_BAL_KEEP = 1 << 2, /* balance decided to keep current */ SCX_RQ_IN_WAKEUP = 1 << 16, SCX_RQ_IN_BALANCE = 1 << 17, -- 2.34.1