On Tue, Dec 10, 2019 at 11:13:30AM +0530, Srikar Dronamraju wrote:
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 44123b4d14e8..82126cbf62cd 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2664,7 +2664,12 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
> */
> int wake_up_process(struct task_struct *p)
> {
> - return try_to_wake_up(p, TASK_NORMAL, 0);
> + int wake_flags = 0;
> +
> + if (is_per_cpu_kthread(p))
> + wake_flags = WF_KTHREAD;
> +
> + return try_to_wake_up(p, TASK_NORMAL, wake_flags);
> }
> EXPORT_SYMBOL(wake_up_process);
Why wake_up_process() and not try_to_wake_up() ? This way
wake_up_state(.state = TASK_NORMAL() is no longer the same as
wake_up_process(), and that's weird!
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 69a81a5709ff..36486f71e59f 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6660,6 +6660,27 @@ static void set_skip_buddy(struct sched_entity *se)
> cfs_rq_of(se)->skip = se;
> }
>
> +static int kthread_wakeup_preempt(struct rq *rq, struct task_struct *p, int wake_flags)
> +{
> + struct task_struct *curr = rq->curr;
> + struct cfs_rq *cfs_rq = task_cfs_rq(curr);
> +
> + if (!(wake_flags & WF_KTHREAD))
> + return 0;
> +
> + if (p->nr_cpus_allowed != 1 || curr->nr_cpus_allowed == 1)
> + return 0;
Per the above, WF_KTHREAD already implies p->nr_cpus_allowed == 1.
> + if (cfs_rq->nr_running > 2)
> + return 0;
> +
> + /*
> + * Don't preempt, if the waking kthread is more CPU intensive than
> + * the current thread.
> + */
> + return p->nvcsw * curr->nivcsw >= p->nivcsw * curr->nvcsw;
Both these conditions seem somewhat arbitrary. The number of context
switch does not correspond to CPU usage _at_all_.
vtime OTOH does reflect exactly that, if it runs a lot, it will be ahead
in the tree.
> +}
> +
> /*
> * Preempt the current task with a newly woken task if needed:
> */
> @@ -6716,7 +6737,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
> find_matching_se(&se, &pse);
> update_curr(cfs_rq_of(se));
> BUG_ON(!pse);
> - if (wakeup_preempt_entity(se, pse) == 1) {
> + if (wakeup_preempt_entity(se, pse) == 1 || kthread_wakeup_preempt(rq, p, wake_flags)) {
> /*
> * Bias pick_next to pick the sched entity that is
> * triggering this preemption.
How about something like:
if (wakeup_preempt_entity(se, pse) >= 1-!!(wake_flags & WF_KTHREAD))
instead? Then we allow kthreads a little more preemption room.
