Merge: hugetlb: force allocating surplus hugepages on mempolicy allowed nodes

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/4827

JIRA: https://issues.redhat.com/browse/RHEL-38605

Signed-off-by: Aristeu Rozanski <arozansk@redhat.com>

Approved-by: Waiman Long <longman@redhat.com>
Approved-by: Rafael Aquini <aquini@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Scott Weaver <scweaver@redhat.com>

Author: swvrrh

mm/hugetlb.c

@@ -2591,6 +2591,23 @@ struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *v
 	return folio;
 }
 
+static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
+{
+#ifdef CONFIG_NUMA
+	struct mempolicy *mpol = get_task_policy(current);
+
+	/*
+	 * Only enforce MPOL_BIND policy which overlaps with cpuset policy
+	 * (from policy_nodemask) specifically for hugetlb case
+	 */
+	if (mpol->mode == MPOL_BIND &&
+		(apply_policy_zone(mpol, gfp_zone(gfp)) &&
+		 cpuset_nodemask_valid_mems_allowed(&mpol->nodes)))
+		return &mpol->nodes;
+#endif
+	return NULL;
+}
+
 /*
  * Increase the hugetlb pool such that it can accommodate a reservation
  * of size 'delta'.
@@ -2605,6 +2622,8 @@ static int gather_surplus_pages(struct hstate *h, long delta)
 	long i;
 	long needed, allocated;
 	bool alloc_ok = true;
+	int node;
+	nodemask_t *mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h));
 
 	lockdep_assert_held(&hugetlb_lock);
 	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
@@ -2619,8 +2638,15 @@ static int gather_surplus_pages(struct hstate *h, long delta)
 retry:
 	spin_unlock_irq(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
-		folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
-				NUMA_NO_NODE, NULL);
+		folio = NULL;
+		for_each_node_mask(node, cpuset_current_mems_allowed) {
+			if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) {
+				folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
+						node, NULL);
+				if (folio)
+					break;
+			}
+		}
 		if (!folio) {
 			alloc_ok = false;
 			break;
@@ -4608,23 +4634,6 @@ static int __init default_hugepagesz_setup(char *s)
 }
 __setup("default_hugepagesz=", default_hugepagesz_setup);
 
-static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
-{
-#ifdef CONFIG_NUMA
-	struct mempolicy *mpol = get_task_policy(current);
-
-	/*
-	 * Only enforce MPOL_BIND policy which overlaps with cpuset policy
-	 * (from policy_nodemask) specifically for hugetlb case
-	 */
-	if (mpol->mode == MPOL_BIND &&
-		(apply_policy_zone(mpol, gfp_zone(gfp)) &&
-		 cpuset_nodemask_valid_mems_allowed(&mpol->nodes)))
-		return &mpol->nodes;
-#endif
-	return NULL;
-}
-
 static unsigned int allowed_mems_nr(struct hstate *h)
 {
 	int node;