[v11,3/8] mm/demotion: Add hotplug callbacks to handle new numa node onlined

Commit Message

Aneesh Kumar K.V July 28, 2022, 7:04 p.m. UTC

If the new NUMA node onlined doesn't have a abstract distance assigned,
the kernel adds the NUMA node to default memory tier.

Signed-off-by: Aneesh Kumar K.V <[e-mail]>
---
 include/linux/memory-tiers.h |  1 +
 mm/memory-tiers.c            | 83 ++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+)

Patch

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index b85901c0caba..976f43a5e3be 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -13,6 +13,7 @@ 
 #define MEMTIER_ADISTANCE_DRAM	(1 << (MEMTIER_CHUNK_BITS + 2))
 /* leave one tier below this slow pmem */
 #define MEMTIER_ADISTANCE_PMEM	(1 << MEMTIER_CHUNK_BITS)
+#define MEMTIER_HOTPLUG_PRIO	100
 
 #ifdef CONFIG_NUMA
 #include <linux/types.h>
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 03e43f3dc942..c9854a394d9b 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -3,6 +3,7 @@ 
 #include <linux/nodemask.h>
 #include <linux/slab.h>
 #include <linux/lockdep.h>
+#include <linux/memory.h>
 #include <linux/memory-tiers.h>
 
 struct memory_tier {
@@ -83,6 +84,87 @@  static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty
 	return new_memtier;
 }
 
+static struct memory_tier *__node_get_memory_tier(int node)
+{
+	struct memory_dev_type *memtype;
+
+	memtype = node_memory_types[node];
+	if (memtype)
+		return memtype->memtier;
+	return NULL;
+}
+
+static void init_node_memory_tier(int node)
+{
+	struct memory_tier *memtier;
+
+	mutex_lock(&memory_tier_lock);
+
+	memtier = __node_get_memory_tier(node);
+	if (!memtier) {
+		struct memory_dev_type *memtype;
+
+		if (!node_memory_types[node]) {
+			node_memory_types[node] = &default_dram_type;
+			node_set(node, default_dram_type.nodes);
+		}
+		memtype = node_memory_types[node];
+		memtier = find_create_memory_tier(memtype);
+	}
+	mutex_unlock(&memory_tier_lock);
+}
+
+static void destroy_memory_tier(struct memory_tier *memtier)
+{
+	list_del(&memtier->list);
+	kfree(memtier);
+}
+
+static void clear_node_memory_tier(int node)
+{
+	struct memory_tier *current_memtier;
+
+	mutex_lock(&memory_tier_lock);
+	current_memtier = __node_get_memory_tier(node);
+	if (current_memtier) {
+		struct memory_dev_type *memtype;
+
+		memtype = node_memory_types[node];
+		node_clear(node, memtype->nodes);
+		if (nodes_empty(memtype->nodes)) {
+			list_del(&memtype->tier_sibiling);
+			memtype->memtier = NULL;
+			if (list_empty(&current_memtier->memory_types))
+				destroy_memory_tier(current_memtier);
+		}
+	}
+	mutex_unlock(&memory_tier_lock);
+}
+
+static int __meminit memtier_hotplug_callback(struct notifier_block *self,
+					      unsigned long action, void *_arg)
+{
+	struct memory_notify *arg = _arg;
+
+	/*
+	 * Only update the node migration order when a node is
+	 * changing status, like online->offline.
+	 */
+	if (arg->status_change_nid < 0)
+		return notifier_from_errno(0);
+
+	switch (action) {
+	case MEM_OFFLINE:
+		clear_node_memory_tier(arg->status_change_nid);
+		break;
+	case MEM_ONLINE:
+		init_node_memory_tier(arg->status_change_nid);
+		break;
+	}
+
+	return notifier_from_errno(0);
+}
+
 static int __init memory_tier_init(void)
 {
 	struct memory_tier *memtier;
@@ -97,6 +179,7 @@  static int __init memory_tier_init(void)
 		      __func__, PTR_ERR(memtier));
 	mutex_unlock(&memory_tier_lock);
 
+	hotplug_memory_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRIO);
 	return 0;
 }
 subsys_initcall(memory_tier_init);