[PATCH v10 6/8] mm/demotion: Add pg_data_t member to track node memory tier details

From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
To: linux-mm@kvack.org, akpm@linux-foundation.org
Cc: Wei Xu <weixugc@google.com>, Huang Ying <ying.huang@intel.com>,
	Yang Shi <shy828301@gmail.com>,
	Davidlohr Bueso <dave@stgolabs.net>,
	Tim C Chen <tim.c.chen@intel.com>,
	Michal Hocko <mhocko@kernel.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Hesham Almatary <hesham.almatary@huawei.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Alistair Popple <apopple@nvidia.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	jvgediya.oss@gmail.com,
	"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Subject: [PATCH v10 6/8] mm/demotion: Add pg_data_t member to track node memory tier details
Date: Wed, 20 Jul 2022 08:29:18 +0530	[thread overview]
Message-ID: <20220720025920.1373558-7-aneesh.kumar@linux.ibm.com> (raw)
In-Reply-To: <20220720025920.1373558-1-aneesh.kumar@linux.ibm.com>

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@linux.ibm.com>
---
 include/linux/mmzone.h |  3 ++
 mm/memory-tiers.c      | 65 +++++++++++++++++++++++++++++++++++-------
 2 files changed, 57 insertions(+), 11 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 a8cfe2ca3903..4715f9b96a44 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -138,13 +138,18 @@ static struct memory_tier *find_create_memory_tier(unsigned int perf_level)
 
 static struct memory_tier *__node_get_memory_tier(int node)
 {
-	struct memory_tier *memtier;
+	pg_data_t *pgdat;
 
-	list_for_each_entry(memtier, &memory_tiers, list) {
-		if (node_isset(node, memtier->nodelist))
-			return 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
@@ -277,6 +282,29 @@ static inline void disable_all_migrate_targets(void) {}
 static inline void establish_migration_targets(void) {}
 #endif /* CONFIG_MIGRATION */
 
+static void memtier_node_set(int node, struct memory_tier *memtier)
+{
+	pg_data_t *pgdat;
+	struct memory_tier *current_memtier;
+
+	pgdat = NODE_DATA(node);
+	if (!pgdat)
+		return;
+	/*
+	 * Make sure we mark the memtier NULL before we assign the new memory tier
+	 * to the NUMA node. This make sure that anybody looking at NODE_DATA
+	 * finds a NULL memtier or the one which is still valid.
+	 */
+	current_memtier = rcu_dereference_check(pgdat->memtier,
+						lockdep_is_held(&memory_tier_lock));
+	rcu_assign_pointer(pgdat->memtier, NULL);
+	synchronize_rcu();
+	if (current_memtier)
+		node_clear(node, current_memtier->nodelist);
+	node_set(node, memtier->nodelist);
+	rcu_assign_pointer(pgdat->memtier, memtier);
+}
+
 static void init_node_memory_tier(int node)
 {
 	int perf_level;
@@ -295,7 +323,7 @@ static void init_node_memory_tier(int node)
 	if (!memtier) {
 		perf_level = node_devices[node]->perf_level;
 		memtier = find_create_memory_tier(perf_level);
-		node_set(node, memtier->nodelist);
+		memtier_node_set(node, memtier);
 	}
 	establish_migration_targets();
 	mutex_unlock(&memory_tier_lock);
@@ -303,12 +331,25 @@ static void init_node_memory_tier(int node)
 
 static void clear_node_memory_tier(int node)
 {
-	struct memory_tier *memtier;
+	pg_data_t *pgdat;
+	struct memory_tier *current_memtier;
+
+	pgdat = NODE_DATA(node);
+	if (!pgdat)
+		return;
 
 	mutex_lock(&memory_tier_lock);
-	memtier = __node_get_memory_tier(node);
-	if (memtier) {
-		node_clear(node, memtier->nodelist);
+	/*
+	 * Make sure we mark the memtier NULL before we assign the new memory tier
+	 * to the NUMA node. This make sure that anybody looking at NODE_DATA
+	 * finds a NULL memtier or the one which is still valid.
+	 */
+	current_memtier = rcu_dereference_check(pgdat->memtier,
+						lockdep_is_held(&memory_tier_lock));
+	rcu_assign_pointer(pgdat->memtier, NULL);
+	synchronize_rcu();
+	if (current_memtier) {
+		node_clear(node, current_memtier->nodelist);
 		establish_migration_targets();
 	}
 	mutex_unlock(&memory_tier_lock);
@@ -383,6 +424,8 @@ static int __init memory_tier_init(void)
 
 		if (!node_property->perf_level)
 			node_property->perf_level = default_memtier_perf_level;
+
+		rcu_assign_pointer(NODE_DATA(node)->memtier, memtier);
 	}
 	mutex_unlock(&memory_tier_lock);
 
-- 
2.36.1

