Re: [PATCH] sched: fix tsk->pi_lock isn't held when do_set_cpus_allowed()

Hi, On Tue, Aug 25, 2015 at 03:59:54PM +0800, Wanpeng Li wrote: > [ 15.273708] [ cut here ] > [ 15.274097] WARNING: CPU: 0 PID: 13 at kernel/sched/core.c:1156 > do_set_cpus_allowed+0x7e/0x80() > [ 15.274857] Modules linked in: > [ 15.275101] CPU: 0 PID: 13 Comm: mi

Re: [PATCH v2 1/3] sched: sync a se with its cfs_rq when attaching and dettaching

Hi, On Mon, Aug 17, 2015 at 04:45:50PM +0900, byungchul.p...@lge.com wrote: > From: Byungchul Park > > current code is wrong with cfs_rq's avg loads when changing a task's > cfs_rq to another. i tested with "echo pid > cgroup" and found that > e.g. cfs_rq->avg.load_avg became larger and larger w

Re: [PATCH] sched: sync with the cfs_rq when changing sched class

Hi, On Thu, Aug 13, 2015 at 02:55:55PM +0900, byungchul.p...@lge.com wrote: > +static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct > sched_entity *se) > +{ > + se->avg.last_update_time = cfs_rq->avg.last_update_time; > + cfs_rq->avg.load_avg += se->avg.load_avg; > + cfs_r

Re: [PATCH 2/2] sched: make task_move_group_fair simple by using switched_to(from)_fair

Hi, On Thu, Aug 13, 2015 at 07:49:19PM +0900, byungchul.p...@lge.com wrote: > +static inline int need_vruntime_adjust(struct task_struct *p, int queued) > +{ > + struct sched_entity *se = &p->se; > + > + /* > + * When !queued, vruntime of the task has usually NOT been normalized. > +

Re: [PATCH] sched: sync with the cfs_rq when changing sched class

On Sat, Aug 15, 2015 at 01:24:12PM +0900, Byungchul Park wrote: > On Fri, Aug 14, 2015 at 08:59:02PM +0800, T. Zhou wrote: > > Hi, > > > > On Thu, Aug 13, 2015 at 02:55:55PM +0900, byungchul.p...@lge.com wrote: > > > +static void attach_entity_load_avg