[PATCH v6 07/13] mm/demotion: Add per node memory tier attribute to sysfs

[Aneesh Kumar K.V]

Add support to modify the memory tier for a NUMA node.

/sys/devices/system/node/nodeN/memtier

where N = node id

When read, It list the memory tier that the node belongs to.

When written, the kernel moves the node into the specified
memory tier, the tier assignment of all other nodes are not
affected.

If the memory tier does not exist an error is returned.

Suggested-by: Wei Xu <weixugc@xxxxxxxxxx>
Signed-off-by: Jagdish Gediya <jvgediya@xxxxxxxxxxxxx>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
---
 drivers/base/node.c          | 39 ++++++++++++++++++++++++++++++++
 include/linux/memory-tiers.h |  3 +++
 mm/memory-tiers.c            | 44 ++++++++++++++++++++++++++++++++++++
 3 files changed, 86 insertions(+)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 0ac6376ef7a1..599ed64d910f 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -20,6 +20,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
+#include <linux/memory-tiers.h>
 
 static struct bus_type node_subsys = {
 	.name = "node",
@@ -560,11 +561,49 @@ static ssize_t node_read_distance(struct device *dev,
 }
 static DEVICE_ATTR(distance, 0444, node_read_distance, NULL);
 
+#ifdef CONFIG_TIERED_MEMORY
+static ssize_t memtier_show(struct device *dev,
+			    struct device_attribute *attr,
+			    char *buf)
+{
+	int node = dev->id;
+	int tier_index = node_get_memory_tier_id(node);
+
+	if (tier_index != -1)
+		return sysfs_emit(buf, "%d\n", tier_index);
+	return 0;
+}
+
+static ssize_t memtier_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	unsigned long tier;
+	int node = dev->id;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &tier);
+	if (ret)
+		return ret;
+
+	ret = node_reset_memory_tier(node, tier);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(memtier);
+#endif
+
 static struct attribute *node_dev_attrs[] = {
 	&dev_attr_meminfo.attr,
 	&dev_attr_numastat.attr,
 	&dev_attr_distance.attr,
 	&dev_attr_vmstat.attr,
+#ifdef CONFIG_TIERED_MEMORY
+	&dev_attr_memtier.attr,
+#endif
 	NULL
 };
 
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 18dd1ab7b96e..e70f0040d845 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -20,6 +20,9 @@
 extern bool numa_demotion_enabled;
 int node_create_and_set_memory_tier(int node, int tier);
 int next_demotion_node(int node);
+int node_set_memory_tier(int node, int tier);
+int node_get_memory_tier_id(int node);
+int node_reset_memory_tier(int node, int tier);
 #else
 #define numa_demotion_enabled	false
 static inline int next_demotion_node(int node)
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 51210f5efc1f..7bfdfac4d43e 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -313,6 +313,50 @@ int node_set_memory_tier(int node, int tier)
 	return ret;
 }
 
+int node_get_memory_tier_id(int node)
+{
+	int tier = -1;
+	struct memory_tier *memtier;
+	/*
+	 * Make sure memory tier is not unregistered
+	 * while it is being read.
+	 */
+	mutex_lock(&memory_tier_lock);
+	memtier = __node_get_memory_tier(node);
+	if (memtier)
+		tier = memtier->dev.id;
+	mutex_unlock(&memory_tier_lock);
+
+	return tier;
+}
+
+int node_reset_memory_tier(int node, int tier)
+{
+	struct memory_tier *current_tier;
+	int ret = 0;
+
+	mutex_lock(&memory_tier_lock);
+
+	current_tier = __node_get_memory_tier(node);
+	if (!current_tier || current_tier->dev.id == tier)
+		goto out;
+
+	node_clear(node, current_tier->nodelist);
+
+	ret = __node_set_memory_tier(node, tier);
+	if (ret) {
+		/* reset it back to older tier */
+		node_set(node, current_tier->nodelist);
+		goto out;
+	}
+
+	establish_migration_targets();
+out:
+	mutex_unlock(&memory_tier_lock);
+
+	return ret;
+}
+
 /**
  * next_demotion_node() - Get the next node in the demotion path
  * @node: The starting node to lookup the next node
-- 
2.36.1