[PATCH v3 2/8] sched/topology: Allocate per-CPU sched_domain_shared in s_data

[K Prateek Nayak <kprateek.nayak@amd.com>]

The "sched_domain_shared" object is allocated for every topology level
in __sdt_alloc() and is freed post sched domain rebuild if they aren't
assigned during sd_init().

"sd->shared" is only assigned for SD_SHARE_LLC domains and out of all
the assigned objects, only "sd_llc_shared" is ever used by the
scheduler.

Since only "sd_llc_shared" is ever used, and since SD_SHARE_LLC domains
never overlap, allocate only a single range of per-CPU
"sched_domain_shared" object with s_data instead of doing it per
topology level.

The subsequent commit uses the degeneration path to correctly assign the
"sd->shared" to the topmost SD_SHARE_LLC domain.

No functional changes are expected at this point.

Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
---
Changelog rfc v2..v3:

o Broke off from a single large patch. Previously
  https://lore.kernel.org/lkml/20251208092744.32737-3-kprateek.nayak@amd.com/
---
 kernel/sched/topology.c | 48 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 47 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 649674bb6c3c..623e8835d322 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -776,6 +776,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 }
 
 struct s_data {
+	struct sched_domain_shared * __percpu *sds;
 	struct sched_domain * __percpu *sd;
 	struct root_domain	*rd;
 };
@@ -783,6 +784,7 @@ struct s_data {
 enum s_alloc {
 	sa_rootdomain,
 	sa_sd,
+	sa_sd_shared,
 	sa_sd_storage,
 	sa_none,
 };
@@ -1529,6 +1531,9 @@ static void set_domain_attribute(struct sched_domain *sd,
 static void __sdt_free(const struct cpumask *cpu_map);
 static int __sdt_alloc(const struct cpumask *cpu_map);
 
+static void __sds_free(struct s_data *d, const struct cpumask *cpu_map);
+static int __sds_alloc(struct s_data *d, const struct cpumask *cpu_map);
+
 static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 				 const struct cpumask *cpu_map)
 {
@@ -1540,6 +1545,9 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
 	case sa_sd:
 		free_percpu(d->sd);
 		fallthrough;
+	case sa_sd_shared:
+		__sds_free(d, cpu_map);
+		fallthrough;
 	case sa_sd_storage:
 		__sdt_free(cpu_map);
 		fallthrough;
@@ -1555,9 +1563,11 @@ __visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map)
 
 	if (__sdt_alloc(cpu_map))
 		return sa_sd_storage;
+	if (__sds_alloc(d, cpu_map))
+		return sa_sd_shared;
 	d->sd = alloc_percpu(struct sched_domain *);
 	if (!d->sd)
-		return sa_sd_storage;
+		return sa_sd_shared;
 	d->rd = alloc_rootdomain();
 	if (!d->rd)
 		return sa_sd;
@@ -2458,6 +2468,42 @@ static void __sdt_free(const struct cpumask *cpu_map)
 	}
 }
 
+static int __sds_alloc(struct s_data *d, const struct cpumask *cpu_map)
+{
+	int j;
+
+	d->sds = alloc_percpu(struct sched_domain_shared *);
+	if (!d->sds)
+		return -ENOMEM;
+
+	for_each_cpu(j, cpu_map) {
+		struct sched_domain_shared *sds;
+
+		sds = kzalloc_node(sizeof(struct sched_domain_shared),
+				GFP_KERNEL, cpu_to_node(j));
+		if (!sds)
+			return -ENOMEM;
+
+		*per_cpu_ptr(d->sds, j) = sds;
+	}
+
+	return 0;
+}
+
+static void __sds_free(struct s_data *d, const struct cpumask *cpu_map)
+{
+	int j;
+
+	if (!d->sds)
+		return;
+
+	for_each_cpu(j, cpu_map)
+		kfree(*per_cpu_ptr(d->sds, j));
+
+	free_percpu(d->sds);
+	d->sds = NULL;
+}
+
 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)
-- 
2.34.1