[PATCH v5 2/9] mm/demotion: Expose per node memory tier 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, writing to the above file
creates the tier and assign the NUMA node to that tier.

mutex memory_tier_lock is introduced to protect memory tier
related chanegs as it can happen from sysfs as well on hot
plug events.

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            | 123 ++++++++++++++++++++++++++++++++++-
 3 files changed, 164 insertions(+), 1 deletion(-)

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 e17f6b4ee177..91f071804476 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -15,6 +15,9 @@
 #define DEFAULT_MEMORY_TIER	MEMORY_TIER_DRAM
 #define MAX_MEMORY_TIERS  3
 
+int node_get_memory_tier_id(int node);
+int node_set_memory_tier(int node, int tier);
+int node_reset_memory_tier(int node, int tier);
 #endif	/* CONFIG_TIERED_MEMORY */
 
 #endif
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 7de18d94a08d..9c78c47ad030 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -126,7 +126,6 @@ static struct memory_tier *register_memory_tier(unsigned int tier)
 	return memtier;
 }
 
-__maybe_unused // temporay to prevent warnings during bisects
 static void unregister_memory_tier(struct memory_tier *memtier)
 {
 	list_del(&memtier->list);
@@ -162,6 +161,128 @@ static const struct attribute_group *memory_tier_attr_groups[] = {
 	NULL,
 };
 
+static struct memory_tier *__node_get_memory_tier(int node)
+{
+	struct memory_tier *memtier;
+
+	list_for_each_entry(memtier, &memory_tiers, list) {
+		if (node_isset(node, memtier->nodelist))
+			return memtier;
+	}
+	return NULL;
+}
+
+static struct memory_tier *__get_memory_tier_from_id(int id)
+{
+	struct memory_tier *memtier;
+
+	list_for_each_entry(memtier, &memory_tiers, list) {
+		if (memtier->dev.id == id)
+			return memtier;
+	}
+	return NULL;
+}
+
+__maybe_unused // temporay to prevent warnings during bisects
+static void node_remove_from_memory_tier(int node)
+{
+	struct memory_tier *memtier;
+
+	mutex_lock(&memory_tier_lock);
+
+	memtier = __node_get_memory_tier(node);
+	if (!memtier)
+		goto out;
+	/*
+	 * Remove node from tier, if tier becomes
+	 * empty then unregister it to make it invisible
+	 * in sysfs.
+	 */
+	node_clear(node, memtier->nodelist);
+	if (nodes_empty(memtier->nodelist))
+		unregister_memory_tier(memtier);
+
+out:
+	mutex_unlock(&memory_tier_lock);
+}
+
+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;
+}
+
+static int __node_set_memory_tier(int node, int tier)
+{
+	int ret = 0;
+	struct memory_tier *memtier;
+
+	memtier = __get_memory_tier_from_id(tier);
+	if (!memtier) {
+		memtier = register_memory_tier(tier);
+		if (!memtier) {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+	node_set(node, memtier->nodelist);
+out:
+	return ret;
+}
+
+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;
+	}
+
+	if (nodes_empty(current_tier->nodelist))
+		unregister_memory_tier(current_tier);
+out:
+	mutex_unlock(&memory_tier_lock);
+
+	return ret;
+}
+
+int node_set_memory_tier(int node, int tier)
+{
+	struct memory_tier *memtier;
+	int ret = 0;
+
+	mutex_lock(&memory_tier_lock);
+	memtier = __node_get_memory_tier(node);
+	if (!memtier)
+		ret = __node_set_memory_tier(node, tier);
+	mutex_unlock(&memory_tier_lock);
+
+	return ret;
+}
+
 static int __init memory_tier_init(void)
 {
 	int ret;
-- 
2.36.1