From: Steve Sistare <steven.sistare@oracle.com>

Add functions sd_llc_alloc_all() and sd_llc_free_all() to allocate and
free data pointed to by struct sched_domain_shared at the last-level-cache
domain.  sd_llc_alloc_all() is called after the SD hierarchy is known, to
eliminate the unnecessary allocations that would occur if we instead
allocated in __sdt_alloc() and then figured out which shared nodes are
redundant.

Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Signed-off-by: Chen Jinghuang <chenjinghuang2@huawei.com>
---
 kernel/sched/topology.c | 75 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 74 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 32dcddaead82..fac1b9155b6e 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -21,6 +21,12 @@ void sched_domains_mutex_unlock(void)
 static cpumask_var_t sched_domains_tmpmask;
 static cpumask_var_t sched_domains_tmpmask2;
 
+struct s_data;
+static int sd_llc_alloc(struct sched_domain *sd);
+static void sd_llc_free(struct sched_domain *sd);
+static int sd_llc_alloc_all(const struct cpumask *cpu_map, struct s_data *d);
+static void sd_llc_free_all(const struct cpumask *cpu_map);
+
 static int __init sched_debug_setup(char *str)
 {
 	sched_debug_verbose = true;
@@ -630,8 +636,10 @@ static void destroy_sched_domain(struct sched_domain *sd)
 	 */
 	free_sched_groups(sd->groups, 1);
 
-	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
+	if (sd->shared && atomic_dec_and_test(&sd->shared->ref)) {
+		sd_llc_free(sd);
 		kfree(sd->shared);
+	}
 	kfree(sd);
 }
 
@@ -1546,6 +1554,7 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 		free_percpu(d->sd);
 		fallthrough;
 	case sa_sd_storage:
+		sd_llc_free_all(cpu_map);
 		__sdt_free(cpu_map);
 		fallthrough;
 	case sa_none:
@@ -2463,6 +2472,62 @@ static void __sdt_free(const struct cpumask *cpu_map)
 	}
 }
 
+static int sd_llc_alloc(struct sched_domain *sd)
+{
+	/* Allocate sd->shared data here. Empty for now. */
+
+	return 0;
+}
+
+static void sd_llc_free(struct sched_domain *sd)
+{
+	struct sched_domain_shared *sds = sd->shared;
+
+	if (!sds)
+		return;
+
+	/* Free data here. Empty for now. */
+}
+
+static int sd_llc_alloc_all(const struct cpumask *cpu_map, struct s_data *d)
+{
+	struct sched_domain *sd, *hsd;
+	int i;
+
+	for_each_cpu(i, cpu_map) {
+		/* Find highest domain that shares resources */
+		hsd = NULL;
+		for (sd = *per_cpu_ptr(d->sd, i); sd; sd = sd->parent) {
+			if (!(sd->flags & SD_SHARE_LLC))
+				break;
+			hsd = sd;
+		}
+		if (hsd && sd_llc_alloc(hsd))
+			return 1;
+	}
+
+	return 0;
+}
+
+static void sd_llc_free_all(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	struct sched_domain *sd;
+	struct sd_data *sdd;
+	int j;
+
+	for_each_sd_topology(tl) {
+		sdd = &tl->data;
+		if (!sdd || !sdd->sd)
+			continue;
+		for_each_cpu(j, cpu_map) {
+			sd = *per_cpu_ptr(sdd->sd, j);
+			if (sd)
+				sd_llc_free(sd);
+		}
+	}
+}
+
 static 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)
@@ -2674,6 +2739,14 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 		}
 	}
 
+	/*
+	 * Allocate shared sd data at last level cache.  Must be done after
+	 * domains are built above, but before the data is used in
+	 * cpu_attach_domain and descendants below.
+	 */
+	if (sd_llc_alloc_all(cpu_map, &d))
+		goto error;
+
 	/* Attach the domains */
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map) {
-- 
2.34.1