sched: Allow users with sufficient RLIMIT_NICE to change from SCHED_IDLE policy

The current scheduler implementation returns -EPERM when trying to
change from SCHED_IDLE to SCHED_OTHER or SCHED_BATCH. Since SCHED_IDLE
is considered to be a nice 20 on steroids, changing to another policy
should be allowed provided the RLIMIT_NICE is accounted for.

This patch allows the following test-case to pass with RLIMIT_NICE=40,
but still fail with RLIMIT_NICE=10 when the calling process is run
from a typical shell (nice 0, or 20 in rlimit terms).

int main()
{
	int ret;
	struct sched_param sp;
	sp.sched_priority = 0;

	/* switch to SCHED_IDLE */
	ret = sched_setscheduler(0, SCHED_IDLE, &sp);
	printf("setscheduler IDLE: %d\n", ret);
	if (ret) return ret;

	/* switch back to SCHED_OTHER */
	ret = sched_setscheduler(0, SCHED_OTHER, &sp);
	printf("setscheduler OTHER: %d\n", ret);

	return ret;
}

 $ ulimit -e
 40
 $ ./test
 setscheduler IDLE: 0
 setscheduler OTHER: 0

 $ ulimit -e 10
 $ ulimit -e
 10
 $ ./test
 setscheduler IDLE: 0
 setscheduler OTHER: -1

Signed-off-by: Darren Hart <dvhart@linux.intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Richard Purdie <richard.purdie@linuxfoundation.org>
LKML-Reference: <4D657BEE.4040608@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index 0c8712630f05b23c36171936d56eadd8ca0ed4c5..f3030709d82660f0fbe803adc31881c1ef5646b0 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4981,12 +4981,15 @@ recheck:
                            param->sched_priority > rlim_rtprio)
                                return -EPERM;
                }
+
                /*
-                * Like positive nice levels, dont allow tasks to
-                * move out of SCHED_IDLE either:
+                * Treat SCHED_IDLE as nice 20. Only allow a switch to
+                * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
                 */
-               if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
-                       return -EPERM;
+               if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) {
+                       if (!can_nice(p, TASK_NICE(p)))
+                               return -EPERM;
+               }
 
                /* can't change other user's priorities */
                if (!check_same_owner(p))