On 06/06/2014 09:36 PM, Peter Zijlstra wrote:
> On Thu, Jun 05, 2014 at 06:54:35PM +0800, Lai Jiangshan wrote:
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index 268a45e..d05a5a1 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -1474,20 +1474,24 @@ static int ttwu_remote(struct task_struct *p, int
>> wake_flags)
>> }
>>
>> #ifdef CONFIG_SMP
>> -static void sched_ttwu_pending(void)
>> +static void sched_ttwu_pending_locked(struct rq *rq)
>> {
>> - struct rq *rq = this_rq();
>> struct llist_node *llist = llist_del_all(&rq->wake_list);
>> struct task_struct *p;
>>
>> - raw_spin_lock(&rq->lock);
>> -
>> while (llist) {
>> p = llist_entry(llist, struct task_struct, wake_entry);
>> llist = llist_next(llist);
>> ttwu_do_activate(rq, p, 0);
>> }
>> +}
>>
>> +static void sched_ttwu_pending(void)
>> +{
>> + struct rq *rq = this_rq();
>> +
>> + raw_spin_lock(&rq->lock);
>> + sched_ttwu_pending_locked(rq);
>> raw_spin_unlock(&rq->lock);
>> }
>
> OK, so this won't apply to a recent kernel.
Thank you for review.
The code here was already changed in the recent kernel?
or I touched too much to apply it?
>
>> @@ -4530,6 +4534,11 @@ int set_cpus_allowed_ptr(struct task_struct *p, const
>> struct cpumask *new_mask)
>> goto out;
>>
>> dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
>> +
>> + /* Ensure it is on rq for migration if it is waking */
>> + if (p->state == TASK_WAKING)
>> + sched_ttwu_pending_locked(rq);
>
> So I would really rather like to avoid this if possible, its doing full
> remote queueing, exactly what we tried to avoid.
set_cpus_allowed_ptr() is slow path, the bad effect introduced by this
change is limited.
>
>> +
>> if (p->on_rq) {
>> struct migration_arg arg = { p, dest_cpu };
>> /* Need help from migration thread: drop lock and wait. */
>> @@ -4576,6 +4585,10 @@ static int __migrate_task(struct task_struct *p, int
>> src_cpu, int dest_cpu)
>> if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
>> goto fail;
>>
>> + /* Ensure it is on rq for migration if it is waking */
>> + if (p->state == TASK_WAKING)
>> + sched_ttwu_pending_locked(rq_src);
>> +
>> /*
>> * If we're not on a rq, the next wake-up will ensure we're
>> * placed properly.
>
> Oh man, another variant.. why did you change it again? And without
> explanation for why you changed it.
>
> I don't see a reason to call sched_ttwu_pending() with rq->lock held,
> seeing as how we append to that list without it held.
sched_ttwu_pending() requires rq->lock to do actual work.
I swapped the order of "llist_del_all(&rq->wake_list)" and
"raw_spin_lock(&rq->lock);"
that it makes the lock section of rq->lock is slightly extend.
>
> I'm still thinking the previous version is good, can you explain why you
> changed it?
There was a window in the previous version.
sched_ttwu_pending();
<----------------window here, the task can be in WAKING state again.
__migrate_task();
When I thought deeply, it was still correct in current code for all
migration_cpu_stop()'s
callers. But we need a big chunk of comments to explain it. And I felt nervous
with that window, it would be a bug if something else changed without regarding
this window. I don't want to leave a fragile code.
The new version patch is much straight and it is self comment.
Migration: if the task is waken-up, migrate it, otherwise it is next wakeup's
responsibility.
Original code simply considered p->on_rq <==> waken-up.
New patch just fixes up p->on_rq before considering it.
How about this (slight changed without touching original sched_ttwu_pending())
---
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 268a45e..cd224ea 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1474,6 +1474,18 @@ static int ttwu_remote(struct task_struct *p, int
wake_flags)
}
#ifdef CONFIG_SMP
+static void sched_ttwu_pending_locked(struct rq *rq)
+{
+ struct llist_node *llist = llist_del_all(&rq->wake_list);
+ struct task_struct *p;
+
+ while (llist) {
+ p = llist_entry(llist, struct task_struct, wake_entry);
+ llist = llist_next(llist);
+ ttwu_do_activate(rq, p, 0);
+ }
+}
+
static void sched_ttwu_pending(void)
{
struct rq *rq = this_rq();
@@ -4530,7 +4542,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const
struct cpumask *new_mask)
goto out;
dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
- if (p->on_rq) {
+ if (p->on_rq || p->state == TASK_WAKING) {
struct migration_arg arg = { p, dest_cpu };
/* Need help from migration thread: drop lock and wait. */
task_rq_unlock(rq, p, &flags);
@@ -4576,6 +4588,10 @@ static int __migrate_task(struct task_struct *p, int
src_cpu, int dest_cpu)
if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
goto fail;
+ /* Ensure it is on rq for migration if it is waking */
+ if (p->state == TASK_WAKING)
+ sched_ttwu_pending_locked(rq_src);
+
/*
* If we're not on a rq, the next wake-up will ensure we're
* placed properly.
>
>
>
>
>
>
> .
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
