thanks. This does has the appearance of a userspace race condition of
some sorts. Can you trigger this hang with the patch below applied to
the vanilla tree as well? (with no CFS patch applied)
if yes then this would suggest that Kaffeine has some sort of
child-runs-first problem. (which CFS changes to parent-runs-first.
Kaffeine starts a couple of threads and the futex calls are a sign of
thread<->thread communication.)
[ i have also Cc:-ed the Kaffeine folks - maybe your strace gives them
an idea about what the problem could be :) ]
Ingo
---
kernel/sched.c | 70 ++-------------------------------------------------------
1 file changed, 3 insertions(+), 67 deletions(-)
Index: linux/kernel/sched.c
===================================================================
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
@@ -1653,77 +1653,13 @@ void fastcall sched_fork(struct task_str
*/
void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
{
- struct rq *rq, *this_rq;
unsigned long flags;
- int this_cpu, cpu;
+ struct rq *rq;
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
- this_cpu = smp_processor_id();
- cpu = task_cpu(p);
-
- /*
- * We decrease the sleep average of forking parents
- * and children as well, to keep max-interactive tasks
- * from forking tasks that are max-interactive. The parent
- * (current) is done further down, under its lock.
- */
- p->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(p) *
- CHILD_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
-
- p->prio = effective_prio(p);
-
- if (likely(cpu == this_cpu)) {
- if (!(clone_flags & CLONE_VM)) {
- /*
- * The VM isn't cloned, so we're in a good position to
- * do child-runs-first in anticipation of an exec. This
- * usually avoids a lot of COW overhead.
- */
- if (unlikely(!current->array))
- __activate_task(p, rq);
- else {
- p->prio = current->prio;
- p->normal_prio = current->normal_prio;
- list_add_tail(&p->run_list, ¤t->run_list);
- p->array = current->array;
- p->array->nr_active++;
- inc_nr_running(p, rq);
- }
- set_need_resched();
- } else
- /* Run child last */
- __activate_task(p, rq);
- /*
- * We skip the following code due to cpu == this_cpu
- *
- * task_rq_unlock(rq, &flags);
- * this_rq = task_rq_lock(current, &flags);
- */
- this_rq = rq;
- } else {
- this_rq = cpu_rq(this_cpu);
-
- /*
- * Not the local CPU - must adjust timestamp. This should
- * get optimised away in the !CONFIG_SMP case.
- */
- p->timestamp = (p->timestamp - this_rq->most_recent_timestamp)
- + rq->most_recent_timestamp;
- __activate_task(p, rq);
- if (TASK_PREEMPTS_CURR(p, rq))
- resched_task(rq->curr);
-
- /*
- * Parent and child are on different CPUs, now get the
- * parent runqueue to update the parent's ->sleep_avg:
- */
- task_rq_unlock(rq, &flags);
- this_rq = task_rq_lock(current, &flags);
- }
- current->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(current) *
- PARENT_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
- task_rq_unlock(this_rq, &flags);
+ __activate_task(p, rq);
+ task_rq_unlock(rq, &flags);
}
/*
-
