[tip:sched/urgent] sched/rt, sched/dl: Don't push if task's scheduling class was changed

[tip-bot for Xunlei Pang]

Commit-ID:  13b5ab02ae118fc8dfdc2b8597688ec4a11d5b53
Gitweb:     http://git.kernel.org/tip/13b5ab02ae118fc8dfdc2b8597688ec4a11d5b53
Author:     Xunlei Pang <xlpang@xxxxxxxxxx>
AuthorDate: Mon, 9 May 2016 12:11:31 +0800
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 10 May 2016 10:02:46 +0200

sched/rt, sched/dl: Don't push if task's scheduling class was changed

We got this warning:

    WARNING: CPU: 1 PID: 2468 at kernel/sched/core.c:1161 set_task_cpu+0x1af/0x1c0
    [...]
    Call Trace:

    dump_stack+0x63/0x87
    __warn+0xd1/0xf0
    warn_slowpath_null+0x1d/0x20
    set_task_cpu+0x1af/0x1c0
    push_dl_task.part.34+0xea/0x180
    push_dl_tasks+0x17/0x30
    __balance_callback+0x45/0x5c
    __sched_setscheduler+0x906/0xb90
    SyS_sched_setattr+0x150/0x190
    do_syscall_64+0x62/0x110
    entry_SYSCALL64_slow_path+0x25/0x25

This corresponds to:

    WARN_ON_ONCE(p->state == TASK_RUNNING &&
             p->sched_class == &fair_sched_class &&
             (p->on_rq && !task_on_rq_migrating(p)))

It happens because in find_lock_later_rq(), the task whose scheduling
class was changed to fair class is still pushed away as if it were
a deadline task ...

So, check in find_lock_later_rq() after double_lock_balance(), if the
scheduling class of the deadline task was changed, break and retry.

Apply the same logic to RT tasks.

Signed-off-by: Xunlei Pang <xlpang@xxxxxxxxxx>
Reviewed-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxx>
Link: http://lkml.kernel.org/r/1462767091-1215-1-git-send-email-xlpang@xxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/sched/deadline.c | 1 +
 kernel/sched/rt.c       | 1 +
 2 files changed, 2 insertions(+)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index affd97e..686ec8a 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1394,6 +1394,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(later_rq->cpu,
 				                       &task->cpus_allowed) ||
 				     task_running(rq, task) ||
+				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {
 				double_unlock_balance(rq, later_rq);
 				later_rq = NULL;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c41ea7a..ec4f538d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1729,6 +1729,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 				     !cpumask_test_cpu(lowest_rq->cpu,
 						       tsk_cpus_allowed(task)) ||
 				     task_running(rq, task) ||
+				     !rt_task(task) ||
 				     !task_on_rq_queued(task))) {
 
 				double_unlock_balance(rq, lowest_rq);