When a task's weight is being changed, set_load_weight() is called with @update_load set. As weight changes aren't trivial for the fair class, set_load_weight() calls fair.c::reweight_task() for fair class tasks. However, set_load_weight() first tests task_has_idle_policy() on entry and skips calling reweight_task() for SCHED_IDLE tasks. This is buggy as SCHED_IDLE tasks are just fair tasks with a very low weight and they would incorrectly skip load, vlag and position updates. Fix it by updating reweight_task() to take struct load_weight as idle weight can't be expressed with prio and making set_load_weight() call reweight_task() for SCHED_IDLE tasks too when @update_load is set. Signed-off-by: Tejun Heo <tj@xxxxxxxxxx> Suggested-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Link: http://lkml.kernel.org/r/20240624102331.GI31592@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Fixes: 9059393e4ec1 ("sched/fair: Use reweight_entity() for set_user_nice()") Cc: stable@xxxxxxxxxxxxxxx # v4.15+ --- Hello, Peter, I took the liberty to use struct load_weight instead of open coding weight and inv_weight. As it's an obviously user visible bug, I tagged it with the stable tag but given how long it's been broken, I'm not sure how urgent it is, so please use your discretion. I verified that the reweight_task() is called with the right weights on SCHED_IDLE switches. Thanks. kernel/sched/core.c | 23 ++++++++++------------- kernel/sched/fair.c | 7 +++---- kernel/sched/sched.h | 2 +- 3 files changed, 14 insertions(+), 18 deletions(-) --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1328,27 +1328,24 @@ int tg_nop(struct task_group *tg, void * void set_load_weight(struct task_struct *p, bool update_load) { int prio = p->static_prio - MAX_RT_PRIO; - struct load_weight *load = &p->se.load; + struct load_weight lw; - /* - * SCHED_IDLE tasks get minimal weight: - */ if (task_has_idle_policy(p)) { - load->weight = scale_load(WEIGHT_IDLEPRIO); - load->inv_weight = WMULT_IDLEPRIO; - return; + lw.weight = scale_load(WEIGHT_IDLEPRIO); + lw.inv_weight = WMULT_IDLEPRIO; + } else { + lw.weight = scale_load(sched_prio_to_weight[prio]); + lw.inv_weight = sched_prio_to_wmult[prio]; } /* * SCHED_OTHER tasks have to update their load when changing their * weight */ - if (update_load && p->sched_class == &fair_sched_class) { - reweight_task(p, prio); - } else { - load->weight = scale_load(sched_prio_to_weight[prio]); - load->inv_weight = sched_prio_to_wmult[prio]; - } + if (update_load && p->sched_class == &fair_sched_class) + reweight_task(p, &lw); + else + p->se.load = lw; } #ifdef CONFIG_UCLAMP_TASK --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3835,15 +3835,14 @@ static void reweight_entity(struct cfs_r } } -void reweight_task(struct task_struct *p, int prio) +void reweight_task(struct task_struct *p, const struct load_weight *lw) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); struct load_weight *load = &se->load; - unsigned long weight = scale_load(sched_prio_to_weight[prio]); - reweight_entity(cfs_rq, se, weight); - load->inv_weight = sched_prio_to_wmult[prio]; + reweight_entity(cfs_rq, se, lw->weight); + load->inv_weight = lw->inv_weight; } static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2509,7 +2509,7 @@ extern void init_sched_dl_class(void); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); -extern void reweight_task(struct task_struct *p, int prio); +extern void reweight_task(struct task_struct *p, const struct load_weight *lw); extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu);
