[PATCH v15 04/10] mm/demotion/dax/kmem: Set node's abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE

[Aneesh Kumar K.V]

By default, all nodes are assigned to the default memory tier which
is the memory tier designated for nodes with DRAM

Set dax kmem device node's tier to slower memory tier by assigning
abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE. Low-level drivers
like papr_scm or ACPI NFIT can initialize memory device type to a
more accurate value based on device tree details or HMAT. If the
kernel doesn't find the memory type initialized, a default slower
memory type is assigned by the kmem driver.

Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
---
 drivers/dax/kmem.c           | 42 +++++++++++++++--
 include/linux/memory-tiers.h | 42 ++++++++++++++++-
 mm/memory-tiers.c            | 91 +++++++++++++++++++++++++++---------
 3 files changed, 149 insertions(+), 26 deletions(-)

diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index a37622060fff..4852a2dbdb27 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -11,9 +11,17 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
+#include <linux/memory-tiers.h>
 #include "dax-private.h"
 #include "bus.h"
 
+/*
+ * Default abstract distance assigned to the NUMA node onlined
+ * by DAX/kmem if the low level platform driver didn't initialize
+ * one for this NUMA node.
+ */
+#define MEMTIER_DEFAULT_DAX_ADISTANCE	(MEMTIER_ADISTANCE_DRAM * 5)
+
 /* Memory resource name used for add_memory_driver_managed(). */
 static const char *kmem_name;
 /* Set if any memory will remain added when the driver will be unloaded. */
@@ -41,6 +49,7 @@ struct dax_kmem_data {
 	struct resource *res[];
 };
 
+static struct memory_dev_type *dax_slowmem_type;
 static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 {
 	struct device *dev = &dev_dax->dev;
@@ -79,11 +88,13 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 		return -EINVAL;
 	}
 
+	init_node_memory_type(numa_node, dax_slowmem_type);
+
+	rc = -ENOMEM;
 	data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL);
 	if (!data)
-		return -ENOMEM;
+		goto err_dax_kmem_data;
 
-	rc = -ENOMEM;
 	data->res_name = kstrdup(dev_name(dev), GFP_KERNEL);
 	if (!data->res_name)
 		goto err_res_name;
@@ -155,6 +166,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	kfree(data->res_name);
 err_res_name:
 	kfree(data);
+err_dax_kmem_data:
+	clear_node_memory_type(numa_node, dax_slowmem_type);
 	return rc;
 }
 
@@ -162,6 +175,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 {
 	int i, success = 0;
+	int node = dev_dax->target_node;
 	struct device *dev = &dev_dax->dev;
 	struct dax_kmem_data *data = dev_get_drvdata(dev);
 
@@ -198,6 +212,14 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 		kfree(data->res_name);
 		kfree(data);
 		dev_set_drvdata(dev, NULL);
+		/*
+		 * Clear the memtype association on successful unplug.
+		 * If not, we have memory blocks left which can be
+		 * offlined/onlined later. We need to keep memory_dev_type
+		 * for that. This implies this reference will be around
+		 * till next reboot.
+		 */
+		clear_node_memory_type(node, dax_slowmem_type);
 	}
 }
 #else
@@ -228,9 +250,22 @@ static int __init dax_kmem_init(void)
 	if (!kmem_name)
 		return -ENOMEM;
 
+	dax_slowmem_type = alloc_memory_type(MEMTIER_DEFAULT_DAX_ADISTANCE);
+	if (IS_ERR(dax_slowmem_type)) {
+		rc = PTR_ERR(dax_slowmem_type);
+		goto err_dax_slowmem_type;
+	}
+
 	rc = dax_driver_register(&device_dax_kmem_driver);
 	if (rc)
-		kfree_const(kmem_name);
+		goto error_dax_driver;
+
+	return rc;
+
+error_dax_driver:
+	destroy_memory_type(dax_slowmem_type);
+err_dax_slowmem_type:
+	kfree_const(kmem_name);
 	return rc;
 }
 
@@ -239,6 +274,7 @@ static void __exit dax_kmem_exit(void)
 	dax_driver_unregister(&device_dax_kmem_driver);
 	if (!any_hotremove_failed)
 		kfree_const(kmem_name);
+	destroy_memory_type(dax_slowmem_type);
 }
 
 MODULE_AUTHOR("Intel Corporation");
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 17b41e592be6..30aecff9ae79 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -2,6 +2,9 @@
 #ifndef _LINUX_MEMORY_TIERS_H
 #define _LINUX_MEMORY_TIERS_H
 
+#include <linux/types.h>
+#include <linux/nodemask.h>
+#include <linux/kref.h>
 /*
  * Each tier cover a abstrace distance chunk size of 128
  */
@@ -16,12 +19,49 @@
 #define MEMTIER_ADISTANCE_DRAM	((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1))
 #define MEMTIER_HOTPLUG_PRIO	100
 
+struct memory_tier;
+struct memory_dev_type {
+	/* list of memory types that are part of same tier as this type */
+	struct list_head tier_sibiling;
+	/* abstract distance for this specific memory type */
+	int adistance;
+	/* Nodes of same abstract distance */
+	nodemask_t nodes;
+	struct kref kref;
+	struct memory_tier *memtier;
+};
+
 #ifdef CONFIG_NUMA
-#include <linux/types.h>
 extern bool numa_demotion_enabled;
+struct memory_dev_type *alloc_memory_type(int adistance);
+void destroy_memory_type(struct memory_dev_type *memtype);
+void init_node_memory_type(int node, struct memory_dev_type *default_type);
+void clear_node_memory_type(int node, struct memory_dev_type *memtype);
 
 #else
 
 #define numa_demotion_enabled	false
+/*
+ * CONFIG_NUMA implementation returns non NULL error.
+ */
+static inline struct memory_dev_type *alloc_memory_type(int adistance)
+{
+	return NULL;
+}
+
+static inline void destroy_memory_type(struct memory_dev_type *memtype)
+{
+
+}
+
+static inline void init_node_memory_type(int node, struct memory_dev_type *default_type)
+{
+
+}
+
+static inline void clear_node_memory_type(int node, struct memory_dev_type *memtype)
+{
+
+}
 #endif	/* CONFIG_NUMA */
 #endif  /* _LINUX_MEMORY_TIERS_H */
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 05f05395468a..3ddf305df7d1 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -1,6 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/types.h>
-#include <linux/nodemask.h>
 #include <linux/slab.h>
 #include <linux/lockdep.h>
 #include <linux/sysfs.h>
@@ -21,27 +19,10 @@ struct memory_tier {
 	int adistance_start;
 };
 
-struct memory_dev_type {
-	/* list of memory types that are part of same tier as this type */
-	struct list_head tier_sibiling;
-	/* abstract distance for this specific memory type */
-	int adistance;
-	/* Nodes of same abstract distance */
-	nodemask_t nodes;
-	struct memory_tier *memtier;
-};
-
 static DEFINE_MUTEX(memory_tier_lock);
 static LIST_HEAD(memory_tiers);
 static struct memory_dev_type *node_memory_types[MAX_NUMNODES];
-/*
- * For now we can have 4 faster memory tiers with smaller adistance
- * than default DRAM tier.
- */
-static struct memory_dev_type default_dram_type  = {
-	.adistance = MEMTIER_ADISTANCE_DRAM,
-	.tier_sibiling = LIST_HEAD_INIT(default_dram_type.tier_sibiling),
-};
+static struct memory_dev_type *default_dram_type;
 
 static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memtype)
 {
@@ -87,6 +68,14 @@ static struct memory_tier *find_create_memory_tier(struct memory_dev_type *memty
 	return new_memtier;
 }
 
+static inline void __init_node_memory_type(int node, struct memory_dev_type *memtype)
+{
+	if (!node_memory_types[node]) {
+		node_memory_types[node] = memtype;
+		kref_get(&memtype->kref);
+	}
+}
+
 static struct memory_tier *set_node_memory_tier(int node)
 {
 	struct memory_tier *memtier;
@@ -97,8 +86,7 @@ static struct memory_tier *set_node_memory_tier(int node)
 	if (!node_state(node, N_MEMORY))
 		return ERR_PTR(-EINVAL);
 
-	if (!node_memory_types[node])
-		node_memory_types[node] = &default_dram_type;
+	__init_node_memory_type(node, default_dram_type);
 
 	memtype = node_memory_types[node];
 	node_set(node, memtype->nodes);
@@ -144,6 +132,57 @@ static bool clear_node_memory_tier(int node)
 	return cleared;
 }
 
+static void release_memtype(struct kref *kref)
+{
+	struct memory_dev_type *memtype;
+
+	memtype = container_of(kref, struct memory_dev_type, kref);
+	kfree(memtype);
+}
+
+struct memory_dev_type *alloc_memory_type(int adistance)
+{
+	struct memory_dev_type *memtype;
+
+	memtype = kmalloc(sizeof(*memtype), GFP_KERNEL);
+	if (!memtype)
+		return ERR_PTR(-ENOMEM);
+
+	memtype->adistance = adistance;
+	INIT_LIST_HEAD(&memtype->tier_sibiling);
+	memtype->nodes  = NODE_MASK_NONE;
+	memtype->memtier = NULL;
+	kref_init(&memtype->kref);
+	return memtype;
+}
+EXPORT_SYMBOL_GPL(alloc_memory_type);
+
+void destroy_memory_type(struct memory_dev_type *memtype)
+{
+	kref_put(&memtype->kref, release_memtype);
+}
+EXPORT_SYMBOL_GPL(destroy_memory_type);
+
+void init_node_memory_type(int node, struct memory_dev_type *memtype)
+{
+
+	mutex_lock(&memory_tier_lock);
+	__init_node_memory_type(node, memtype);
+	mutex_unlock(&memory_tier_lock);
+}
+EXPORT_SYMBOL_GPL(init_node_memory_type);
+
+void clear_node_memory_type(int node, struct memory_dev_type *memtype)
+{
+	mutex_lock(&memory_tier_lock);
+	if (node_memory_types[node] == memtype) {
+		node_memory_types[node] = NULL;
+		kref_put(&memtype->kref, release_memtype);
+	}
+	mutex_unlock(&memory_tier_lock);
+}
+EXPORT_SYMBOL_GPL(clear_node_memory_type);
+
 static int __meminit memtier_hotplug_callback(struct notifier_block *self,
 					      unsigned long action, void *_arg)
 {
@@ -178,6 +217,14 @@ static int __init memory_tier_init(void)
 	struct memory_tier *memtier;
 
 	mutex_lock(&memory_tier_lock);
+	/*
+	 * For now we can have 4 faster memory tiers with smaller adistance
+	 * than default DRAM tier.
+	 */
+	default_dram_type = alloc_memory_type(MEMTIER_ADISTANCE_DRAM);
+	if (!default_dram_type)
+		panic("%s() failed to allocate default DRAM tier\n", __func__);
+
 	/*
 	 * Look at all the existing N_MEMORY nodes and add them to
 	 * default memory tier or to a tier if we already have memory
-- 
2.37.2