Prepare for the kernel to auto-migrate pages to other memory nodes with a
user defined node migration table. A user may create a single target for
each NUMA node to enable the kernel to do NUMA page migrations instead
of simply reclaiming colder pages. A node with no target is a "terminal
node", so reclaim acts normally there. The migration target does not
fundamentally _need_ to be a single node, but this implementation starts
there to limit complexity.
If you consider the migration path as a graph, cycles (loops) in the graph
are disallowed. This avoids wasting resources by constantly migrating
(A->B, B->A, A->B ...). The expectation is that cycles will never be
allowed.
Signed-off-by: Keith Busch <keith.busch@xxxxxxxxx>
---
Documentation/ABI/stable/sysfs-devices-node | 11 ++++-
drivers/base/node.c | 73 +++++++++++++++++++++++++++++
include/linux/node.h | 6 +++
3 files changed, 89 insertions(+), 1 deletion(-)
diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
index 3e90e1f3bf0a..7439e1845e5d 100644
--- a/Documentation/ABI/stable/sysfs-devices-node
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -90,4 +90,13 @@ Date: December 2009
Contact: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
Description:
The node's huge page size control/query attributes.
- See Documentation/admin-guide/mm/hugetlbpage.rst
\ No newline at end of file
+ See Documentation/admin-guide/mm/hugetlbpage.rst
+
+What: /sys/devices/system/node/nodeX/migration_path
+Data March 2019
+Contact: Linux Memory Management list <linux-mm@xxxxxxxxx>
+Description:
+ Defines which node the kernel should attempt to migrate this
+ node's pages to when this node requires memory reclaim. A
+ negative value means this is a terminal node and memory can not
+ be reclaimed through kernel managed migration.
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 86d6cd92ce3d..20a90905555f 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -59,6 +59,10 @@ static inline ssize_t node_read_cpulist(struct device *dev,
static DEVICE_ATTR(cpumap, S_IRUGO, node_read_cpumask, NULL);
static DEVICE_ATTR(cpulist, S_IRUGO, node_read_cpulist, NULL);
+#define TERMINAL_NODE -1
+static int node_migration[MAX_NUMNODES] = {[0 ... MAX_NUMNODES - 1] = TERMINAL_NODE};
+static DEFINE_SPINLOCK(node_migration_lock);
+
#define K(x) ((x) << (PAGE_SHIFT - 10))
static ssize_t node_read_meminfo(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -233,6 +237,74 @@ static ssize_t node_read_distance(struct device *dev,
}
static DEVICE_ATTR(distance, S_IRUGO, node_read_distance, NULL);
+static ssize_t migration_path_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", node_migration[dev->id]);
+}
+
+static ssize_t migration_path_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ int i, err, nid = dev->id;
+ nodemask_t visited = NODE_MASK_NONE;
+ long next;
+
+ err = kstrtol(buf, 0, &next);
+ if (err)
+ return -EINVAL;
+
+ if (next < 0) {
+ spin_lock(&node_migration_lock);
+ WRITE_ONCE(node_migration[nid], TERMINAL_NODE);
+ spin_unlock(&node_migration_lock);
+ return count;
+ }
+ if (next > MAX_NUMNODES || !node_online(next))
+ return -EINVAL;
+
+ /*
+ * Follow the entire migration path from 'nid' through the point where
+ * we hit a TERMINAL_NODE.
+ *
+ * Don't allow looped migration cycles in the path.
+ */
+ node_set(nid, visited);
+ spin_lock(&node_migration_lock);
+ for (i = next; node_migration[i] != TERMINAL_NODE;
+ i = node_migration[i]) {
+ /* Fail if we have visited this node already */
+ if (node_test_and_set(i, visited)) {
+ spin_unlock(&node_migration_lock);
+ return -EINVAL;
+ }
+ }
+ WRITE_ONCE(node_migration[nid], next);
+ spin_unlock(&node_migration_lock);
+
+ return count;
+}
+static DEVICE_ATTR_RW(migration_path);
+
+/**
+ * next_migration_node() - Get the next node in the migration path
+ * @current_node: The starting node to lookup the next node
+ *
+ * @returns: node id for next memory node in the migration path hierarchy from
+ * @current_node; -1 if @current_node is terminal or its migration
+ * node is not online.
+ */
+int next_migration_node(int current_node)
+{
+ int nid = READ_ONCE(node_migration[current_node]);
+
+ if (nid >= 0 && node_online(nid))
+ return nid;
+ return TERMINAL_NODE;
+}
+
static struct attribute *node_dev_attrs[] = {
&dev_attr_cpumap.attr,
&dev_attr_cpulist.attr,
@@ -240,6 +312,7 @@ static struct attribute *node_dev_attrs[] = {
&dev_attr_numastat.attr,
&dev_attr_distance.attr,
&dev_attr_vmstat.attr,
+ &dev_attr_migration_path.attr,
NULL
};
ATTRIBUTE_GROUPS(node_dev);
diff --git a/include/linux/node.h b/include/linux/node.h
index 257bb3d6d014..af46c7a8b94f 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -67,6 +67,7 @@ static inline int register_one_node(int nid)
return error;
}
+extern int next_migration_node(int current_node);
extern void unregister_one_node(int nid);
extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
@@ -115,6 +116,11 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
node_registration_func_t unreg)
{
}
+
+static inline int next_migration_node(int current_node)
+{
+ return -1;
+}
#endif
#define to_node(device) container_of(device, struct node, dev)
--
2.14.4
