sched/deadline: Improve the tracking of active utilization

This patch implements a more theoretically sound algorithm for
tracking active utilization: instead of decreasing it when a
task blocks, use a timer (the "inactive timer", named after the
"Inactive" task state of the GRUB algorithm) to decrease the
active utilization at the so called "0-lag time".
Tested-by: Claudio Scordino <claudio@evidence.eu.com>
Tested-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Luca Abeni <luca.abeni@santannapisa.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/1495138417-6203-3-git-send-email-luca.abeni@santannapisa.itSigned-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched.h

@@ -445,16 +445,33 @@ struct sched_dl_entity {
 	 *
 	 * @dl_yielded tells if task gave up the CPU before consuming
 	 * all its available runtime during the last job.
+	 *
+	 * @dl_non_contending tells if the task is inactive while still
+	 * contributing to the active utilization. In other words, it
+	 * indicates if the inactive timer has been armed and its handler
+	 * has not been executed yet. This flag is useful to avoid race
+	 * conditions between the inactive timer handler and the wakeup
+	 * code.
 	 */
 	int				dl_throttled;
 	int				dl_boosted;
 	int				dl_yielded;
+	int				dl_non_contending;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
 	 * own bandwidth to be enforced, thus we need one timer per task.
 	 */
 	struct hrtimer			dl_timer;
+
+	/*
+	 * Inactive timer, responsible for decreasing the active utilization
+	 * at the "0-lag time". When a -deadline task blocks, it contributes
+	 * to GRUB's active utilization until the "0-lag time", hence a
+	 * timer is needed to decrease the active utilization at the correct
+	 * time.
+	 */
+	struct hrtimer inactive_timer;
 };
 
 union rcu_special {

kernel/sched/core.c

@@ -2153,6 +2153,7 @@ void __dl_clear_params(struct task_struct *p)
 
 	dl_se->dl_throttled = 0;
 	dl_se->dl_yielded = 0;
+	dl_se->dl_non_contending = 0;
 }
 
 /*
@@ -2184,6 +2185,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
 	init_dl_task_timer(&p->dl);
+	init_dl_inactive_task_timer(&p->dl);
 	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -2506,6 +2508,7 @@ static int dl_overflow(struct task_struct *p, int policy,
 		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
 		__dl_clear(dl_b, p->dl.dl_bw);
 		__dl_add(dl_b, new_bw);
+		dl_change_utilization(p, new_bw);
 		err = 0;
 	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
 		__dl_clear(dl_b, p->dl.dl_bw);

kernel/sched/sched.h

@@ -244,6 +244,7 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
 	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
 }
 
+void dl_change_utilization(struct task_struct *p, u64 new_bw);
 extern void init_dl_bw(struct dl_bw *dl_b);
 
 #ifdef CONFIG_CGROUP_SCHED
@@ -1493,6 +1494,7 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime
 extern struct dl_bandwidth def_dl_bandwidth;
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
 
 unsigned long to_ratio(u64 period, u64 runtime);