[PATCH v11 6/8] mm/demotion: Add pg_data_t member to track node memory tier details

[Aneesh Kumar K.V]

Also update different helpes to use NODE_DATA()->memtier. Since
node specific memtier can change based on the reassignment of
NUMA node to a different memory tiers, accessing NODE_DATA()->memtier
needs to happen under an rcu read lock or memory_tier_lock.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
---
 include/linux/mmzone.h |  3 +++
 mm/memory-tiers.c      | 40 +++++++++++++++++++++++++++++++++++-----
 2 files changed, 38 insertions(+), 5 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index aab70355d64f..353812495a70 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -928,6 +928,9 @@ typedef struct pglist_data {
 	/* Per-node vmstats */
 	struct per_cpu_nodestat __percpu *per_cpu_nodestats;
 	atomic_long_t		vm_stat[NR_VM_NODE_STAT_ITEMS];
+#ifdef CONFIG_NUMA
+	struct memory_tier __rcu *memtier;
+#endif
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 60845aa74afc..f982ca6b3559 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -3,6 +3,7 @@
 #include <linux/lockdep.h>
 #include <linux/memory.h>
 #include <linux/random.h>
+#include <linux/mmzone.h>
 #include <linux/memory-tiers.h>
 
 #include "internal.h"
@@ -142,12 +143,18 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty
 
 static struct memory_tier *__node_get_memory_tier(int node)
 {
-	struct memory_dev_type *memtype;
+	pg_data_t *pgdat;
 
-	memtype = node_memory_types[node];
-	if (memtype)
-		return memtype->memtier;
-	return NULL;
+	pgdat = NODE_DATA(node);
+	if (!pgdat)
+		return NULL;
+	/*
+	 * Since we hold memory_tier_lock, we can avoid
+	 * RCU read locks when accessing the details. No
+	 * parallel updates are possible here.
+	 */
+	return rcu_dereference_check(pgdat->memtier,
+				     lockdep_is_held(&memory_tier_lock));
 }
 
 #ifdef CONFIG_MIGRATION
@@ -290,6 +297,7 @@ static inline void establish_demotion_targets(void) {}
 
 static void init_node_memory_tier(int node)
 {
+	pg_data_t *pgdat = NODE_DATA(node);
 	struct memory_tier *memtier;
 
 	mutex_lock(&memory_tier_lock);
@@ -311,8 +319,12 @@ static void init_node_memory_tier(int node)
 		}
 		memtype = node_memory_types[node];
 		memtier = find_create_memory_tier(memtype);
+		if (IS_ERR(memtier))
+			goto err_out;
+		rcu_assign_pointer(pgdat->memtier, memtier);
 	}
 	establish_demotion_targets();
+err_out:
 	mutex_unlock(&memory_tier_lock);
 }
 
@@ -324,13 +336,26 @@ static void destroy_memory_tier(struct memory_tier *memtier)
 
 static void clear_node_memory_tier(int node)
 {
+	pg_data_t *pgdat;
 	struct memory_tier *current_memtier;
 
+	pgdat = NODE_DATA(node);
+	if (!pgdat)
+		return;
+
 	mutex_lock(&memory_tier_lock);
+	/*
+	 * Make sure that anybody looking at NODE_DATA who finds
+	 * a valid memtier finds memory_dev_types with nodes still
+	 * linked to the memtier. We achieve this by waiting for
+	 * rcu read section to finish using synchronize_rcu.
+	 */
 	current_memtier = __node_get_memory_tier(node);
 	if (current_memtier) {
 		struct memory_dev_type *memtype;
 
+		rcu_assign_pointer(pgdat->memtier, NULL);
+		synchronize_rcu();
 		memtype = node_memory_types[node];
 		node_clear(node, memtype->nodes);
 		if (nodes_empty(memtype->nodes)) {
@@ -386,6 +411,7 @@ static int __meminit memtier_hotplug_callback(struct notifier_block *self,
 
 static int __init memory_tier_init(void)
 {
+	int node;
 	struct memory_tier *memtier;
 
 	mutex_lock(&memory_tier_lock);
@@ -396,6 +422,10 @@ static int __init memory_tier_init(void)
 	if (IS_ERR(memtier))
 		panic("%s() failed to register memory tier: %ld\n",
 		      __func__, PTR_ERR(memtier));
+
+	for_each_node_state(node, N_MEMORY)
+		rcu_assign_pointer(NODE_DATA(node)->memtier, memtier);
+
 	mutex_unlock(&memory_tier_lock);
 #ifdef CONFIG_MIGRATION
 	node_demotion = kcalloc(MAX_NUMNODES, sizeof(struct demotion_nodes),
-- 
2.37.1