From: Peter Zijlstra <peterz@infradead.org> mainline inclusion from mainline-v7.0-rc2 commit 6e3c0a4e1ad1e0455b7880fad02b3ee179f56c09 category: bugfix bugzilla: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Vincent reported that he was seeing undue lag clamping in a mixed slice workload. Implement the max_slice tracking as per the todo comment. Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy") Reported-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Vincent Guittot <vincent.guittot@linaro.org> Tested-by: K Prateek Nayak <kprateek.nayak@amd.com> Tested-by: Shubhang Kaushik <shubhang@os.amperecomputing.com> Link: https://patch.msgid.link/20250422101628.GA33555@noisy.programming.kicks-ass.... Conflicts: include/linux/sched.h kernel/sched/fair.c [context difference] Signed-off-by: Chen Jinghuang <chenjinghuang2@huawei.com> --- include/linux/sched.h | 1 + kernel/sched/fair.c | 39 +++++++++++++++++++++++++++++++++++---- 2 files changed, 36 insertions(+), 4 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 629c7d42110c..7f2eb0780b65 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -584,6 +584,7 @@ struct sched_entity { struct rb_node run_node; u64 deadline; u64 min_vruntime; + u64 max_slice; struct list_head group_node; unsigned int on_rq; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b6c847216af3..c70715c24bc8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -958,6 +958,8 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) return cfs_rq->zero_vruntime; } +static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq); + /* * lag_i = S - s_i = w_i * (V - v_i) * @@ -971,17 +973,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * EEVDF gives the following limit for a steady state system: * * -r_max < lag < max(r_max, q) - * - * XXX could add max_slice to the augmented data to track this. */ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) { + u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC; s64 vlag, limit; SCHED_WARN_ON(!se->on_rq); vlag = avg_vruntime(cfs_rq) - se->vruntime; - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); + limit = calc_delta_fair(max_slice, se); se->vlag = clamp(vlag, -limit, limit); } @@ -1075,6 +1076,21 @@ static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq) return min_slice; } +static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq) +{ + struct sched_entity *root = __pick_root_entity(cfs_rq); + struct sched_entity *curr = cfs_rq->curr; + u64 max_slice = 0ULL; + + if (curr && curr->on_rq) + max_slice = curr->slice; + + if (root) + max_slice = max(max_slice, root->max_slice); + + return max_slice; +} + static inline bool __entity_less(struct rb_node *a, const struct rb_node *b) { return entity_before(__node_2_se(a), __node_2_se(b)); @@ -1099,6 +1115,15 @@ static inline void __min_slice_update(struct sched_entity *se, struct rb_node *n } } +static inline void __max_slice_update(struct sched_entity *se, struct rb_node *node) +{ + if (node) { + struct sched_entity *rse = __node_2_se(node); + if (rse->max_slice > se->max_slice) + se->max_slice = rse->max_slice; + } +} + /* * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime) */ @@ -1106,6 +1131,7 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) { u64 old_min_vruntime = se->min_vruntime; u64 old_min_slice = se->min_slice; + u64 old_max_slice = se->max_slice; struct rb_node *node = &se->run_node; se->min_vruntime = se->vruntime; @@ -1116,8 +1142,13 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) __min_slice_update(se, node->rb_right); __min_slice_update(se, node->rb_left); + se->max_slice = se->slice; + __max_slice_update(se, node->rb_right); + __max_slice_update(se, node->rb_left); + return se->min_vruntime == old_min_vruntime && - se->min_slice == old_min_slice; + se->min_slice == old_min_slice && + se->max_slice == old_max_slice; } RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, -- 2.34.1