Skip to contentSkip to conversation

scheduler fixes

GIT PULL Ingo Molnar 1 participant 1 message Mar 16, 2014 Scheduler

lore
Share & tools
lore
#0 lore raw

Linus,

Please pull the latest sched-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched-urgent-for-linus

# HEAD: 96b3d28bf4b00f62fc8386ff5d487d1830793a3d sched/clock: Prevent tracing recursion in sched_clock_cpu()

Three small fixes.

Thanks,

Ingo

------------------>
Fernando Luis Vazquez Cao (1):
sched/clock: Prevent tracing recursion in sched_clock_cpu()

Juri Lelli (1):
sched/deadline: Deny unprivileged users to set/change SCHED_DEADLINE policy

Peter Zijlstra (1):
stop_machine: Fix^2 race between stop_two_cpus() and stop_cpus()

 kernel/sched/clock.c  | 4 ++--
 kernel/sched/core.c   | 9 +++++++++
 kernel/stop_machine.c | 2 +-
 3 files changed, 12 insertions(+), 3 deletions(-)
kernel/sched/clock.c +2 -2
index 43c2bcc..b30a292 100644
@@ -301,14 +301,14 @@ u64 sched_clock_cpu(int cpu)
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
-	preempt_disable();
+	preempt_disable_notrace();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
-	preempt_enable();
+	preempt_enable_notrace();
 
 	return clock;
 }
kernel/sched/core.c +9 -0
index 6edbef2..f5c6635 100644
@@ -3338,6 +3338,15 @@ recheck:
 				return -EPERM;
 		}
 
+		 /*
+		  * Can't set/change SCHED_DEADLINE policy at all for now
+		  * (safest behavior); in the future we would like to allow
+		  * unprivileged DL tasks to increase their relative deadline
+		  * or reduce their runtime (both ways reducing utilization)
+		  */
+		if (dl_policy(policy))
+			return -EPERM;
+
 		/*
 		 * Treat SCHED_IDLE as nice 20. Only allow a switch to
 		 * SCHED_NORMAL if the RLIMIT_NICE would normally permit it.
kernel/stop_machine.c +1 -1
index 84571e0..01fbae5 100644
@@ -293,7 +293,7 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *
 	 */
 	smp_call_function_single(min(cpu1, cpu2),
 				 &irq_cpu_stop_queue_work,
-				 &call_args, 0);
+				 &call_args, 1);
 	lg_local_unlock(&stop_cpus_lock);
 	preempt_enable();