[RFC PATCH 3/4] mm/memory-tiers: add next_promotion_node to find promotion target

[Honggyu Kim]

From: Hyeongtak Ji <hyeongtak.ji@xxxxxx>

This patch adds next_promotion_node that can be used to identify the
appropriate promotion target based on memory tiers.  When multiple
promotion target nodes are available, the nearest node is selected based
on numa distance.

Signed-off-by: Hyeongtak Ji <hyeongtak.ji@xxxxxx>
---
 include/linux/memory-tiers.h | 11 +++++++++
 mm/memory-tiers.c            | 43 ++++++++++++++++++++++++++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 1e39d27bee41..0788e435fc50 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -50,6 +50,7 @@ int mt_set_default_dram_perf(int nid, struct node_hmem_attrs *perf,
 int mt_perf_to_adistance(struct node_hmem_attrs *perf, int *adist);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
+int next_promotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
 bool node_is_toptier(int node);
 #else
@@ -58,6 +59,11 @@ static inline int next_demotion_node(int node)
 	return NUMA_NO_NODE;
 }
 
+static inline int next_promotion_node(int node)
+{
+	return NUMA_NO_NODE;
+}
+
 static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
 {
 	*targets = NODE_MASK_NONE;
@@ -101,6 +107,11 @@ static inline int next_demotion_node(int node)
 	return NUMA_NO_NODE;
 }
 
+static inline int next_promotion_node(int node)
+{
+	return NUMA_NO_NODE;
+}
+
 static inline void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets)
 {
 	*targets = NODE_MASK_NONE;
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 8d5291add2bc..0060ee571cf4 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -335,6 +335,49 @@ int next_demotion_node(int node)
 	return target;
 }
 
+/*
+ * Select a promotion target that is close to the from node among the given
+ * two nodes.
+ *
+ * TODO: consider other decision policy as node_distance may not be precise.
+ */
+static int select_promotion_target(int a, int b, int from)
+{
+	if (node_distance(from, a) < node_distance(from, b))
+		return a;
+	else
+		return b;
+}
+
+/**
+ * next_promotion_node() - Get the next node in the promotion path
+ * @node: The starting node to lookup the next node
+ *
+ * Return: node id for next memory node in the promotion path hierarchy
+ * from @node; NUMA_NO_NODE if @node is the toptier.
+ */
+int next_promotion_node(int node)
+{
+	int target = NUMA_NO_NODE;
+	int nid;
+
+	if (node_is_toptier(node))
+		return NUMA_NO_NODE;
+
+	rcu_read_lock();
+	for_each_node_state(nid, N_MEMORY) {
+		if (node_isset(node, node_demotion[nid].preferred)) {
+			if (target == NUMA_NO_NODE)
+				target = nid;
+			else
+				target = select_promotion_target(nid, target, node);
+		}
+	}
+	rcu_read_unlock();
+
+	return target;
+}
+
 static void disable_all_demotion_targets(void)
 {
 	struct memory_tier *memtier;
-- 
2.34.1