sched/deadline: Modify cpudl::free_cpus to reflect rd->online

Currently, cpudl::free_cpus contains all CPUs during init, see
cpudl_init(). When calling cpudl_find(), we have to add rd->span
to avoid selecting the cpu outside the current root domain, because
cpus_allowed cannot be depended on when performing clustered
scheduling using the cpuset, see find_later_rq().

This patch adds cpudl_set_freecpu() and cpudl_clear_freecpu() for
changing cpudl::free_cpus when doing rq_online_dl()/rq_offline_dl(),
so we can avoid the rd->span operation when calling cpudl_find()
in find_later_rq().

Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1421642980-10045-1-git-send-email-pang.xunlei@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/cpudeadline.c

@@ -107,7 +107,9 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	int best_cpu = -1;
 	const struct sched_dl_entity *dl_se = &p->dl;
 
-	if (later_mask && cpumask_and(later_mask, later_mask, cp->free_cpus)) {
+	if (later_mask &&
+	    cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed) &&
+	    cpumask_and(later_mask, later_mask, cpu_active_mask)) {
 		best_cpu = cpumask_any(later_mask);
 		goto out;
 	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
@@ -185,6 +187,26 @@ out:
 	raw_spin_unlock_irqrestore(&cp->lock, flags);
 }
 
+/*
+ * cpudl_set_freecpu - Set the cpudl.free_cpus
+ * @cp: the cpudl max-heap context
+ * @cpu: rd attached cpu
+ */
+void cpudl_set_freecpu(struct cpudl *cp, int cpu)
+{
+	cpumask_set_cpu(cpu, cp->free_cpus);
+}
+
+/*
+ * cpudl_clear_freecpu - Clear the cpudl.free_cpus
+ * @cp: the cpudl max-heap context
+ * @cpu: rd attached cpu
+ */
+void cpudl_clear_freecpu(struct cpudl *cp, int cpu)
+{
+	cpumask_clear_cpu(cpu, cp->free_cpus);
+}
+
 /*
  * cpudl_init - initialize the cpudl structure
  * @cp: the cpudl max-heap context
@@ -203,7 +225,7 @@ int cpudl_init(struct cpudl *cp)
 	if (!cp->elements)
 		return -ENOMEM;
 
-	if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
 		kfree(cp->elements);
 		return -ENOMEM;
 	}
@@ -211,8 +233,6 @@ int cpudl_init(struct cpudl *cp)
 	for_each_possible_cpu(i)
 		cp->elements[i].idx = IDX_INVALID;
 
-	cpumask_setall(cp->free_cpus);
-
 	return 0;
 }
 

kernel/sched/cpudeadline.h

@@ -24,6 +24,8 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	       struct cpumask *later_mask);
 void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
 int cpudl_init(struct cpudl *cp);
+void cpudl_set_freecpu(struct cpudl *cp, int cpu);
+void cpudl_clear_freecpu(struct cpudl *cp, int cpu);
 void cpudl_cleanup(struct cpudl *cp);
 #endif /* CONFIG_SMP */
 

kernel/sched/deadline.c

@@ -1165,9 +1165,6 @@ static int find_later_rq(struct task_struct *task)
 	 * We have to consider system topology and task affinity
 	 * first, then we can look for a suitable cpu.
 	 */
-	cpumask_copy(later_mask, task_rq(task)->rd->span);
-	cpumask_and(later_mask, later_mask, cpu_active_mask);
-	cpumask_and(later_mask, later_mask, &task->cpus_allowed);
 	best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
 			task, later_mask);
 	if (best_cpu == -1)
@@ -1562,6 +1559,7 @@ static void rq_online_dl(struct rq *rq)
 	if (rq->dl.overloaded)
 		dl_set_overload(rq);
 
+	cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu);
 	if (rq->dl.dl_nr_running > 0)
 		cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1);
 }
@@ -1573,6 +1571,7 @@ static void rq_offline_dl(struct rq *rq)
 		dl_clear_overload(rq);
 
 	cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+	cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
 }
 
 void init_sched_dl_class(void)