[PATCH v5 01/36] mm: refactor find_next_best_node to find_next_best_node_in

Gregory Price <[email protected]> Mon, 20 Jul 2026 15:33:55 -0400
Newsgroups org.kernel.vger.linux-debuggers,dev.linux.lists.damon,dev.linux.lists.driver-core,dev.linux.lists.nvdimm,org.kernel.vger.cgroups,org.kernel.vger.kvm,org.kernel.vger.linux-cxl,org.kernel.vger.linux-doc,org.kernel.vger.linux-fsdevel,org.kernel.vger.linux-kernel,org.kernel.vger.linux-kselftest,org.kvack.linux-mm
Message-ID <[email protected]>
find_next_best_node() picks the next-closest node for a fallback list
from the full N_MEMORY set. Refactor it into find_next_best_node_in(),
which takes an explicit candidates nodemask.

This enables building fallback lists with non-N_MEMORY candidates.

No functional change: every caller still selects from N_MEMORY.

Signed-off-by: Gregory Price <[email protected]>
---
 mm/internal.h     |  6 ++++--
 mm/memory-tiers.c |  7 ++++---
 mm/page_alloc.c   | 13 ++++++++-----
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index f26423de4ca28..96d78a7778e88 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1103,7 +1103,8 @@ extern int node_reclaim_mode;
 
 extern unsigned long node_reclaim(struct pglist_data *pgdat,
 				  gfp_t gfp_mask, unsigned int order);
-extern int find_next_best_node(int node, nodemask_t *used_node_mask);
+extern int find_next_best_node_in(int node, nodemask_t *used_node_mask,
+				  const nodemask_t *candidates);
 #else
 #define node_reclaim_mode 0
 
@@ -1112,7 +1113,8 @@ static inline unsigned long node_reclaim(struct pglist_data *pgdat,
 {
 	return 0;
 }
-static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
+static inline int find_next_best_node_in(int node, nodemask_t *used_node_mask,
+					 const nodemask_t *candidates)
 {
 	return NUMA_NO_NODE;
 }
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 54851d8a195b0..25e121851b586 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -370,7 +370,7 @@ int next_demotion_node(int node, const nodemask_t *allowed_mask)
 	 * closest demotion target.
 	 */
 	nodes_complement(mask, *allowed_mask);
-	return find_next_best_node(node, &mask);
+	return find_next_best_node_in(node, &mask, &node_states[N_MEMORY]);
 }
 
 static void disable_all_demotion_targets(void)
@@ -450,7 +450,7 @@ static void establish_demotion_targets(void)
 		memtier = list_next_entry(memtier, list);
 		tier_nodes = get_memtier_nodemask(memtier);
 		/*
-		 * find_next_best_node, use 'used' nodemask as a skip list.
+		 * find_next_best_node_in, use 'used' nodemask as a skip list.
 		 * Add all memory nodes except the selected memory tier
 		 * nodelist to skip list so that we find the best node from the
 		 * memtier nodelist.
@@ -463,7 +463,8 @@ static void establish_demotion_targets(void)
 		 * in the preferred mask when allocating pages during demotion.
 		 */
 		do {
-			target = find_next_best_node(node, &tier_nodes);
+			target = find_next_best_node_in(node, &tier_nodes,
+							&node_states[N_MEMORY]);
 			if (target == NUMA_NO_NODE)
 				break;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f93a6bb9a872d..acf096f525f49 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5743,9 +5743,10 @@ static int numa_zonelist_order_handler(const struct ctl_table *table, int write,
 static int node_load[MAX_NUMNODES];
 
 /**
- * find_next_best_node - find the next node that should appear in a given node's fallback list
+ * find_next_best_node_in - find the next node that should appear in a given node's fallback list
  * @node: node whose fallback list we're appending
  * @used_node_mask: nodemask_t of already used nodes
+ * @candidates: nodemask_t of nodes eligible for selection
  *
  * We use a number of factors to determine which is the next node that should
  * appear on a given node's fallback list.  The node should not have appeared
@@ -5757,7 +5758,8 @@ static int node_load[MAX_NUMNODES];
  *
  * Return: node id of the found node or %NUMA_NO_NODE if no node is found.
  */
-int find_next_best_node(int node, nodemask_t *used_node_mask)
+int find_next_best_node_in(int node, nodemask_t *used_node_mask,
+			   const nodemask_t *candidates)
 {
 	int n, val;
 	int min_val = INT_MAX;
@@ -5767,12 +5769,12 @@ int find_next_best_node(int node, nodemask_t *used_node_mask)
 	 * Use the local node if we haven't already, but for memoryless local
 	 * node, we should skip it and fall back to other nodes.
 	 */
-	if (!node_isset(node, *used_node_mask) && node_state(node, N_MEMORY)) {
+	if (!node_isset(node, *used_node_mask) && node_isset(node, *candidates)) {
 		node_set(node, *used_node_mask);
 		return node;
 	}
 
-	for_each_node_state(n, N_MEMORY) {
+	for_each_node_mask(n, *candidates) {
 
 		/* Don't want a node to appear more than once */
 		if (node_isset(n, *used_node_mask))
@@ -5857,7 +5859,8 @@ static void build_zonelists(pg_data_t *pgdat)
 	prev_node = local_node;
 
 	memset(node_order, 0, sizeof(node_order));
-	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
+	while ((node = find_next_best_node_in(local_node, &used_mask,
+					      &node_states[N_MEMORY])) >= 0) {
 		/*
 		 * We don't want to pressure a particular node.
 		 * So adding penalty to the first node in same
-- 
2.53.0-Meta