sched/deadline: Do not reclaim the whole CPU bandwidth

Original GRUB tends to reclaim 100% of the CPU time... And this
allows a CPU hog to starve non-deadline tasks.
To address this issue, allow the scheduler to reclaim only a
specified fraction of CPU time, stored in the new "bw_ratio"
field of the dl runqueue structure.

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: Claudio Scordino <claudio@evidence.eu.com>
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/1495138417-6203-6-git-send-email-luca.abeni@santannapisa.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/core.c

@@ -6759,6 +6759,16 @@ static int sched_dl_global_validate(void)
 	return ret;
 }
 
+void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
+{
+	if (global_rt_runtime() == RUNTIME_INF) {
+		dl_rq->bw_ratio = 1 << RATIO_SHIFT;
+	} else {
+		dl_rq->bw_ratio = to_ratio(global_rt_runtime(),
+			  global_rt_period()) >> (BW_SHIFT - RATIO_SHIFT);
+	}
+}
+
 static void sched_dl_do_global(void)
 {
 	u64 new_bw = -1;
@@ -6784,6 +6794,7 @@ static void sched_dl_do_global(void)
 		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 
 		rcu_read_unlock_sched();
+		init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl);
 	}
 }
 

kernel/sched/deadline.c

@@ -268,6 +268,7 @@ void init_dl_rq(struct dl_rq *dl_rq)
 #endif
 
 	dl_rq->running_bw = 0;
+	init_dl_rq_bw_ratio(dl_rq);
 }
 
 #ifdef CONFIG_SMP
@@ -924,11 +925,20 @@ extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
  * Uact is the (per-runqueue) active utilization.
  * Since rq->dl.running_bw contains Uact * 2^BW_SHIFT, the result
  * has to be shifted right by BW_SHIFT.
+ * To reclaim only a fraction Umax of the CPU time, the
+ * runtime accounting rule is modified as
+ * "dq = -Uact / Umax dt"; since rq->dl.bw_ratio contains
+ * 2^RATIO_SHIFT / Umax, delta is multiplied by bw_ratio and shifted
+ * right by RATIO_SHIFT.
+ * Since delta is a 64 bit variable, to have an overflow its value
+ * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
+ * So, overflow is not an issue here.
  */
 u64 grub_reclaim(u64 delta, struct rq *rq)
 {
 	delta *= rq->dl.running_bw;
-	delta >>= BW_SHIFT;
+	delta *= rq->dl.bw_ratio;
+	delta >>= BW_SHIFT + RATIO_SHIFT;
 
 	return delta;
 }

kernel/sched/sched.h

@@ -565,6 +565,12 @@ struct dl_rq {
 	 * task blocks
 	 */
 	u64 running_bw;
+
+	/*
+	 * Inverse of the fraction of CPU utilization that can be reclaimed
+	 * by the GRUB algorithm.
+	 */
+	u64 bw_ratio;
 };
 
 #ifdef CONFIG_SMP
@@ -1495,9 +1501,11 @@ 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);
+extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
 
 #define BW_SHIFT	20
 #define BW_UNIT		(1 << BW_SHIFT)
+#define RATIO_SHIFT	8
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);