mm/demotion: expose memory tier details via sysfs

Add /sys/devices/virtual/memory_tiering/ where all memory tier related details can be found. All allocated memory tiers will be listed there as /sys/devices/virtual/memory_tiering/memory_tierN/ The nodes which are part of a specific memory tier can be listed via /sys/devices/virtual/memory_tiering/memory_tierN/nodes A directory hierarchy looks like :/sys/devices/virtual/memory_tiering$ tree memory_tier4/ memory_tier4/ ├── nodes ├── subsystem -> ../../../../bus/memory_tiering └── uevent :/sys/devices/virtual/memory_tiering$ cat memory_tier4/nodes 0,2 [[email protected]: drop toptier_nodes from sysfs] Link: https://lkml.kernel.org/r/[email protected] Link: https://lkml.kernel.org/r/[email protected] Signed-off-by: Aneesh Kumar K.V <[email protected]> Cc: Alistair Popple <[email protected]> Cc: Bharata B Rao <[email protected]> Cc: Dan Williams <[email protected]> Cc: Dave Hansen <[email protected]> Cc: Davidlohr Bueso <[email protected]> Cc: Hesham Almatary <[email protected]> Cc: "Huang, Ying" <[email protected]> Cc: Jagdish Gediya <[email protected]> Cc: Johannes Weiner <[email protected]> Cc: Jonathan Cameron <[email protected]> Cc: Michal Hocko <[email protected]> Cc: Tim Chen <[email protected]> Cc: Wei Xu <[email protected]> Cc: Yang Shi <[email protected]> Signed-off-by: Andrew Morton <[email protected]>
ddstreet · Sep 27, 2022 · 9832fb8 · 9832fb8
1 parent 3e061d9
commit 9832fb8
Show file tree

Hide file tree

Showing 2 changed files with 112 additions and 22 deletions.
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers b/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers
@@ -0,0 +1,25 @@
+What:		/sys/devices/virtual/memory_tiering/
+Date:		August 2022
+Contact:	Linux memory management mailing list <[email protected]>
+Description:	A collection of all the memory tiers allocated.
+
+		Individual memory tier details are contained in subdirectories
+		named by the abstract distance of the memory tier.
+
+		/sys/devices/virtual/memory_tiering/memory_tierN/
+
+
+What:		/sys/devices/virtual/memory_tiering/memory_tierN/
+		/sys/devices/virtual/memory_tiering/memory_tierN/nodes
+Date:		August 2022
+Contact:	Linux memory management mailing list <[email protected]>
+Description:	Directory with details of a specific memory tier
+
+		This is the directory containing information about a particular
+		memory tier, memtierN, where N is derived based on abstract distance.
+
+		A smaller value of N implies a higher (faster) memory tier in the
+		hierarchy.
+
+		nodes: NUMA nodes that are part of this memory tier.
+
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
@@ -19,6 +19,7 @@ struct memory_tier {
 	 * adistance_start .. adistance_start + MEMTIER_CHUNK_SIZE
 	 */
 	int adistance_start;
+	struct device dev;
 	/* All the nodes that are part of all the lower memory tiers. */
 	nodemask_t lower_tier_mask;
 };
@@ -36,6 +37,12 @@ static DEFINE_MUTEX(memory_tier_lock);
 static LIST_HEAD(memory_tiers);
 static struct node_memory_type_map node_memory_types[MAX_NUMNODES];
 static struct memory_dev_type *default_dram_type;
+
+static struct bus_type memory_tier_subsys = {
+	.name = "memory_tiering",
+	.dev_name = "memory_tier",
+};
+
 #ifdef CONFIG_MIGRATION
 static int top_tier_adistance;
 /*
@@ -98,8 +105,63 @@ static int top_tier_adistance;
 static struct demotion_nodes *node_demotion __read_mostly;
 #endif /* CONFIG_MIGRATION */
 
+static inline struct memory_tier *to_memory_tier(struct device *device)
+{
+	return container_of(device, struct memory_tier, dev);
+}
+
+static __always_inline nodemask_t get_memtier_nodemask(struct memory_tier *memtier)
+{
+	nodemask_t nodes = NODE_MASK_NONE;
+	struct memory_dev_type *memtype;
+
+	list_for_each_entry(memtype, &memtier->memory_types, tier_sibiling)
+		nodes_or(nodes, nodes, memtype->nodes);
+
+	return nodes;
+}
+
+static void memory_tier_device_release(struct device *dev)
+{
+	struct memory_tier *tier = to_memory_tier(dev);
+	/*
+	 * synchronize_rcu in clear_node_memory_tier makes sure
+	 * we don't have rcu access to this memory tier.
+	 */
+	kfree(tier);
+}
+
+static ssize_t nodes_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	int ret;
+	nodemask_t nmask;
+
+	mutex_lock(&memory_tier_lock);
+	nmask = get_memtier_nodemask(to_memory_tier(dev));
+	ret = sysfs_emit(buf, "%*pbl\n", nodemask_pr_args(&nmask));
+	mutex_unlock(&memory_tier_lock);
+	return ret;
+}
+static DEVICE_ATTR_RO(nodes);
+
+static struct attribute *memtier_dev_attrs[] = {
+	&dev_attr_nodes.attr,
+	NULL
+};
+
+static const struct attribute_group memtier_dev_group = {
+	.attrs = memtier_dev_attrs,
+};
+
+static const struct attribute_group *memtier_dev_groups[] = {
+	&memtier_dev_group,
+	NULL
+};
+
 static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype)
 {
+	int ret;
 	bool found_slot = false;
 	struct memory_tier *memtier, *new_memtier;
 	int adistance = memtype->adistance;
@@ -123,15 +185,14 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty
 
 	list_for_each_entry(memtier, &memory_tiers, list) {
 		if (adistance == memtier->adistance_start) {
-			list_add(&memtype->tier_sibiling, &memtier->memory_types);
-			return memtier;
+			goto link_memtype;
 		} else if (adistance < memtier->adistance_start) {
 			found_slot = true;
 			break;
 		}
 	}
 
-	new_memtier = kmalloc(sizeof(struct memory_tier), GFP_KERNEL);
+	new_memtier = kzalloc(sizeof(struct memory_tier), GFP_KERNEL);
 	if (!new_memtier)
 		return ERR_PTR(-ENOMEM);
 
@@ -142,8 +203,23 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty
 		list_add_tail(&new_memtier->list, &memtier->list);
 	else
 		list_add_tail(&new_memtier->list, &memory_tiers);
-	list_add(&memtype->tier_sibiling, &new_memtier->memory_types);
-	return new_memtier;
+
+	new_memtier->dev.id = adistance >> MEMTIER_CHUNK_BITS;
+	new_memtier->dev.bus = &memory_tier_subsys;
+	new_memtier->dev.release = memory_tier_device_release;
+	new_memtier->dev.groups = memtier_dev_groups;
+
+	ret = device_register(&new_memtier->dev);
+	if (ret) {
+		list_del(&memtier->list);
+		put_device(&memtier->dev);
+		return ERR_PTR(ret);
+	}
+	memtier = new_memtier;
+
+link_memtype:
+	list_add(&memtype->tier_sibiling, &memtier->memory_types);
+	return memtier;
 }
 
 static struct memory_tier *__node_get_memory_tier(int node)
@@ -275,17 +351,6 @@ static void disable_all_demotion_targets(void)
 	synchronize_rcu();
 }
 
-static __always_inline nodemask_t get_memtier_nodemask(struct memory_tier *memtier)
-{
-	nodemask_t nodes = NODE_MASK_NONE;
-	struct memory_dev_type *memtype;
-
-	list_for_each_entry(memtype, &memtier->memory_types, tier_sibiling)
-		nodes_or(nodes, nodes, memtype->nodes);
-
-	return nodes;
-}
-
 /*
  * Find an automatic demotion target for all memory
  * nodes. Failing here is OK.  It might just indicate
@@ -433,11 +498,7 @@ static struct memory_tier *set_node_memory_tier(int node)
 static void destroy_memory_tier(struct memory_tier *memtier)
 {
 	list_del(&memtier->list);
-	/*
-	 * synchronize_rcu in clear_node_memory_tier makes sure
-	 * we don't have rcu access to this memory tier.
-	 */
-	kfree(memtier);
+	device_unregister(&memtier->dev);
 }
 
 static bool clear_node_memory_tier(int node)
@@ -566,9 +627,13 @@ static int __meminit memtier_hotplug_callback(struct notifier_block *self,
 
 static int __init memory_tier_init(void)
 {
-	int node;
+	int ret, node;
 	struct memory_tier *memtier;
 
+	ret = subsys_virtual_register(&memory_tier_subsys, NULL);
+	if (ret)
+		panic("%s() failed to register memory tier subsystem\n", __func__);
+
 #ifdef CONFIG_MIGRATION
 	node_demotion = kcalloc(nr_node_ids, sizeof(struct demotion_nodes),
 				GFP_KERNEL);