sched/core: Introduce 'struct sched_domain_shared'

Since struct sched_domain is strictly per cpu; introduce a structure
that is shared between all 'identical' sched_domains.

Limit to SD_SHARE_PKG_RESOURCES domains for now, as we'll only use it
for shared cache state; if another use comes up later we can easily
relax this.

While the sched_group's are normally shared between CPUs, these are
not natural to use when we need some shared state on a domain level --
since that would require the domain to have a parent, which is not a
given.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched.h

@@ -1067,6 +1067,10 @@ extern int sched_domain_level_max;
 
 struct sched_group;
 
+struct sched_domain_shared {
+	atomic_t	ref;
+};
+
 struct sched_domain {
 	/* These fields must be setup */
 	struct sched_domain *parent;	/* top domain must be null terminated */
@@ -1135,6 +1139,7 @@ struct sched_domain {
 		void *private;		/* used during construction */
 		struct rcu_head rcu;	/* used during destruction */
 	};
+	struct sched_domain_shared *shared;
 
 	unsigned int span_weight;
 	/*
@@ -1168,6 +1173,7 @@ typedef int (*sched_domain_flags_f)(void);
 
 struct sd_data {
 	struct sched_domain **__percpu sd;
+	struct sched_domain_shared **__percpu sds;
 	struct sched_group **__percpu sg;
 	struct sched_group_capacity **__percpu sgc;
 };

kernel/sched/core.c

@@ -5947,6 +5947,8 @@ static void destroy_sched_domain(struct sched_domain *sd)
 		kfree(sd->groups->sgc);
 		kfree(sd->groups);
 	}
+	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
+		kfree(sd->shared);
 	kfree(sd);
 }
 
@@ -6385,6 +6387,9 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
 	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
 	*per_cpu_ptr(sdd->sd, cpu) = NULL;
 
+	if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref))
+		*per_cpu_ptr(sdd->sds, cpu) = NULL;
+
 	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
 		*per_cpu_ptr(sdd->sg, cpu) = NULL;
 
@@ -6429,10 +6434,12 @@ static int sched_domains_curr_level;
 
 static struct sched_domain *
 sd_init(struct sched_domain_topology_level *tl,
+	const struct cpumask *cpu_map,
 	struct sched_domain *child, int cpu)
 {
-	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
-	int sd_weight, sd_flags = 0;
+	struct sd_data *sdd = &tl->data;
+	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+	int sd_id, sd_weight, sd_flags = 0;
 
 #ifdef CONFIG_NUMA
 	/*
@@ -6487,6 +6494,9 @@ sd_init(struct sched_domain_topology_level *tl,
 #endif
 	};
 
+	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
+	sd_id = cpumask_first(sched_domain_span(sd));
+
 	/*
 	 * Convert topological properties into behaviour.
 	 */
@@ -6529,7 +6539,16 @@ sd_init(struct sched_domain_topology_level *tl,
 		sd->idle_idx = 1;
 	}
 
-	sd->private = &tl->data;
+	/*
+	 * For all levels sharing cache; connect a sched_domain_shared
+	 * instance.
+	 */
+	if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+		sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
+		atomic_inc(&sd->shared->ref);
+	}
+
+	sd->private = sdd;
 
 	return sd;
 }
@@ -6839,6 +6858,10 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 		if (!sdd->sd)
 			return -ENOMEM;
 
+		sdd->sds = alloc_percpu(struct sched_domain_shared *);
+		if (!sdd->sds)
+			return -ENOMEM;
+
 		sdd->sg = alloc_percpu(struct sched_group *);
 		if (!sdd->sg)
 			return -ENOMEM;
@@ -6849,6 +6872,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 
 		for_each_cpu(j, cpu_map) {
 			struct sched_domain *sd;
+			struct sched_domain_shared *sds;
 			struct sched_group *sg;
 			struct sched_group_capacity *sgc;
 
@@ -6859,6 +6883,13 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 
 			*per_cpu_ptr(sdd->sd, j) = sd;
 
+			sds = kzalloc_node(sizeof(struct sched_domain_shared),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sds)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sds, j) = sds;
+
 			sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
 					GFP_KERNEL, cpu_to_node(j));
 			if (!sg)
@@ -6898,6 +6929,8 @@ static void __sdt_free(const struct cpumask *cpu_map)
 				kfree(*per_cpu_ptr(sdd->sd, j));
 			}
 
+			if (sdd->sds)
+				kfree(*per_cpu_ptr(sdd->sds, j));
 			if (sdd->sg)
 				kfree(*per_cpu_ptr(sdd->sg, j));
 			if (sdd->sgc)
@@ -6905,6 +6938,8 @@ static void __sdt_free(const struct cpumask *cpu_map)
 		}
 		free_percpu(sdd->sd);
 		sdd->sd = NULL;
+		free_percpu(sdd->sds);
+		sdd->sds = NULL;
 		free_percpu(sdd->sg);
 		sdd->sg = NULL;
 		free_percpu(sdd->sgc);
@@ -6916,9 +6951,8 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
 		struct sched_domain *child, int cpu)
 {
-	struct sched_domain *sd = sd_init(tl, child, cpu);
+	struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
 
-	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
 	if (child) {
 		sd->level = child->level + 1;
 		sched_domain_level_max = max(sched_domain_level_max, sd->level);