CFS-devel, latest code
humm... I think, it'd be safer to have something like the following change in place.
The thing is that __pick_next_entity() must never be called when first_fair(cfs_rq) == NULL. It wouldn't be a problem, should 'run_node' be the very first field of 'struct sched_entity' (and it's the second).
The 'nr_running != 0' check is _not_ enough, due to the fact that 'current' is not within the tree. Generic paths are ok (e.g. schedule() as put_prev_task() is called previously)... I'm more worried about e.g. migration_call() -> CPU_DEAD_FROZEN -> migrate_dead_tasks()... if 'current' == rq->idle, no problems.. if it's one of the SCHED_NORMAL tasks (or imagine, some other use-cases in the future -- i.e. we should not make outer world dependent on internal details of sched_fair class) -- it may be "Houston, we've got a problem" case.
it's +16 bytes to the ".text". Another variant is to make 'run_node' the first data member of 'struct sched_entity' but an additional check (se ! = NULL) is still needed in pick_next_entity().
what do you think?
---
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index dae714a..33b2376 100644
kernel/sched_fair.c +6 -3
@@ -563,9 +563,12 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)static struct sched_entity *pick_next_entity (struct cfs_rq *cfs_rq) { -struct sched_entity *se =__pick_next_entity (cfs_rq); - -set_next_entity (cfs_rq, se); +struct sched_entity *se =NULL ; + +if (first_fair (cfs_rq)) { + se =__pick_next_entity (cfs_rq); +set_next_entity (cfs_rq, se); + }return se; }
---
Quoted 18 lines · Dmitry Adamushko
humm... I think, it'd be safer to have something like the following change in place.
The thing is that
__pick_next_entity()must never be called whenfirst_fair(cfs_rq)== NULL. It wouldn't be a problem, should 'run_node' be the very first field of 'structsched_entity' (and it's the second).The '
nr_running!= 0' check is _not_ enough, due to the fact that 'current' is not within the tree. Generic paths are ok (e.g.schedule()asput_prev_task()is called previously)... I'm more worried about e.g.migration_call()->CPU_DEAD_FROZEN->migrate_dead_tasks()... if 'current' ==rq->idle, no problems.. if it's one of theSCHED_NORMALtasks (or imagine, some other use-cases in the future -- i.e. we should not make outer world dependent on internal details ofsched_fairclass) -- it may be "Houston, we've got a problem" case.
Quoted 3 lines
it's +16 bytes to the ".text". Another variant is to make '
run_node' the first data member of 'structsched_entity' but an additional check (se ! = NULL) is still needed inpick_next_entity().
looks good to me - and we already have something similar in sched_rt.c. I've added your patch to the queue. (Can i add your SoB line too?)
Ingo