From: Rakie Kim <rakie.kim@xxxxxx>
This patch provides a way to set interleave weight information under
sysfs at /sys/kernel/mm/mempolicy/weighted_interleave/nodeN
The sysfs structure is designed as follows.
$ tree /sys/kernel/mm/mempolicy/
/sys/kernel/mm/mempolicy/ [1]
└── weighted_interleave [2]
├── node0 [3]
└── node1
Each file above can be explained as follows.
[1] mm/mempolicy: configuration interface for mempolicy subsystem
[2] weighted_interleave/: config interface for weighted interleave policy
[3] weighted_interleave/nodeN: weight for nodeN
If a node value is set to `0`, the system-default value will be used.
As of this patch, the system-default for all nodes is always 1.
Suggested-by: Huang Ying <ying.huang@xxxxxxxxx>
Signed-off-by: Rakie Kim <rakie.kim@xxxxxx>
Signed-off-by: Honggyu Kim <honggyu.kim@xxxxxx>
Co-developed-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
Signed-off-by: Gregory Price <gregory.price@xxxxxxxxxxxx>
Co-developed-by: Hyeongtak Ji <hyeongtak.ji@xxxxxx>
Signed-off-by: Hyeongtak Ji <hyeongtak.ji@xxxxxx>
---
.../ABI/testing/sysfs-kernel-mm-mempolicy | 4 +
...fs-kernel-mm-mempolicy-weighted-interleave | 25 ++
mm/mempolicy.c | 224 ++++++++++++++++++
3 files changed, 253 insertions(+)
create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm-mempolicy
create mode 100644 Documentation/ABI/testing/sysfs-kernel-mm-mempolicy-weighted-interleave
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy b/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy
new file mode 100644
index 000000000000..2dcf24f4384a
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy
@@ -0,0 +1,4 @@
+What: /sys/kernel/mm/mempolicy/
+Date: December 2023
+Contact: Linux memory management mailing list <linux-mm@xxxxxxxxx>
+Description: Interface for Mempolicy
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy-weighted-interleave b/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy-weighted-interleave
new file mode 100644
index 000000000000..0062b02703ff
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-mempolicy-weighted-interleave
@@ -0,0 +1,25 @@
+What: /sys/kernel/mm/mempolicy/weighted_interleave/
+Date: January 2024
+Contact: Linux memory management mailing list <linux-mm@xxxxxxxxx>
+Description: Configuration Interface for the Weighted Interleave policy
+
+What: /sys/kernel/mm/mempolicy/weighted_interleave/nodeN
+Date: January 2024
+Contact: Linux memory management mailing list <linux-mm@xxxxxxxxx>
+Description: Weight configuration interface for nodeN
+
+ The interleave weight for a memory node (N). These weights are
+ utilized by taskss which have set their mempolicy to
+ MPOL_WEIGHTED_INTERLEAVE.
+
+ These weights only affect new allocations, and changes at runtime
+ will not cause migrations on already allocated pages.
+
+ The minimum weight for a node is always 1.
+
+ Minimum weight: 1
+ Maximum weight: 255
+
+ Writing an empty string or `0` will reset the weight to the
+ system default. The system default may be set by the kernel
+ or drivers at boot or during hotplug events.
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 10a590ee1c89..f1627d45b0c8 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -131,6 +131,17 @@ static struct mempolicy default_policy = {
static struct mempolicy preferred_node_policy[MAX_NUMNODES];
+/*
+ * iw_table is the sysfs-set interleave weight table, a value of 0 denotes
+ * system-default value should be used. A NULL iw_table also denotes that
+ * system-default values should be used. Until the system-default table
+ * is implemented, the system-default is always 1.
+ *
+ * iw_table is RCU protected
+ */
+static u8 __rcu *iw_table;
+static DEFINE_MUTEX(iw_table_lock);
+
/**
* numa_nearest_node - Find nearest node by state
* @node: Node id to start the search
@@ -3067,3 +3078,216 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
p += scnprintf(p, buffer + maxlen - p, ":%*pbl",
nodemask_pr_args(&nodes));
}
+
+#ifdef CONFIG_SYSFS
+struct iw_node_attr {
+ struct kobj_attribute kobj_attr;
+ int nid;
+};
+
+static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ struct iw_node_attr *node_attr;
+ u8 weight;
+ u8 __rcu *table;
+
+ node_attr = container_of(attr, struct iw_node_attr, kobj_attr);
+
+ rcu_read_lock();
+ table = rcu_dereference(iw_table);
+ weight = table ? table[node_attr->nid] : 1;
+ rcu_read_unlock();
+
+ return sysfs_emit(buf, "%d\n", weight);
+}
+
+static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct iw_node_attr *node_attr;
+ u8 __rcu *new;
+ u8 __rcu *old;
+ u8 weight = 0;
+
+ node_attr = container_of(attr, struct iw_node_attr, kobj_attr);
+ if (count == 0 || sysfs_streq(buf, ""))
+ weight = 0;
+ else if (kstrtou8(buf, 0, &weight))
+ return -EINVAL;
+
+ /*
+ * The default weight is 1, for now. When the kernel-internal
+ * default weight array is implemented, 0 will be a directive to
+ * the allocators to use the system-default weight instead.
+ */
+ if (!weight)
+ weight = 1;
+
+ new = kmalloc(nr_node_ids, GFP_KERNEL);
+ if (!new)
+ return -ENOMEM;
+
+ mutex_lock(&iw_table_lock);
+ old = rcu_dereference_protected(iw_table,
+ lockdep_is_held(&iw_table_lock));
+ if (old)
+ memcpy(new, old, nr_node_ids);
+ else
+ memset(new, 1, nr_node_ids);
+ new[node_attr->nid] = weight;
+ rcu_assign_pointer(iw_table, new);
+ mutex_unlock(&iw_table_lock);
+ synchronize_rcu();
+ kfree(old);
+ return count;
+}
+
+static struct iw_node_attr **node_attrs;
+
+static void sysfs_wi_node_release(struct iw_node_attr *node_attr,
+ struct kobject *parent)
+{
+ if (!node_attr)
+ return;
+ sysfs_remove_file(parent, &node_attr->kobj_attr.attr);
+ kfree(node_attr->kobj_attr.attr.name);
+ kfree(node_attr);
+}
+
+static void sysfs_wi_release(struct kobject *wi_kobj)
+{
+ int i;
+
+ for (i = 0; i < nr_node_ids; i++)
+ sysfs_wi_node_release(node_attrs[i], wi_kobj);
+ kobject_put(wi_kobj);
+}
+
+static const struct kobj_type wi_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .release = sysfs_wi_release,
+};
+
+static int add_weight_node(int nid, struct kobject *wi_kobj)
+{
+ struct iw_node_attr *node_attr;
+ char *name;
+
+ node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL);
+ if (!node_attr)
+ return -ENOMEM;
+
+ name = kasprintf(GFP_KERNEL, "node%d", nid);
+ if (!name) {
+ kfree(node_attr);
+ return -ENOMEM;
+ }
+
+ sysfs_attr_init(&node_attr->kobj_attr.attr);
+ node_attr->kobj_attr.attr.name = name;
+ node_attr->kobj_attr.attr.mode = 0644;
+ node_attr->kobj_attr.show = node_show;
+ node_attr->kobj_attr.store = node_store;
+ node_attr->nid = nid;
+
+ if (sysfs_create_file(wi_kobj, &node_attr->kobj_attr.attr)) {
+ kfree(node_attr->kobj_attr.attr.name);
+ kfree(node_attr);
+ pr_err("failed to add attribute to weighted_interleave\n");
+ return -ENOMEM;
+ }
+
+ node_attrs[nid] = node_attr;
+ return 0;
+}
+
+static int add_weighted_interleave_group(struct kobject *root_kobj)
+{
+ struct kobject *wi_kobj;
+ int nid, err;
+
+ wi_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL);
+ if (!wi_kobj)
+ return -ENOMEM;
+
+ err = kobject_init_and_add(wi_kobj, &wi_ktype, root_kobj,
+ "weighted_interleave");
+ if (err) {
+ kfree(wi_kobj);
+ return err;
+ }
+
+ for_each_node_state(nid, N_POSSIBLE) {
+ err = add_weight_node(nid, wi_kobj);
+ if (err) {
+ pr_err("failed to add sysfs [node%d]\n", nid);
+ break;
+ }
+ }
+ if (err)
+ kobject_put(wi_kobj);
+ return 0;
+}
+
+static void mempolicy_kobj_release(struct kobject *kobj)
+{
+ u8 __rcu *old;
+
+ mutex_lock(&iw_table_lock);
+ old = rcu_dereference_protected(iw_table,
+ lockdep_is_held(&iw_table_lock));
+ rcu_assign_pointer(iw_table, NULL);
+ mutex_unlock(&iw_table_lock);
+ synchronize_rcu();
+ kfree(old);
+ kfree(node_attrs);
+ kfree(kobj);
+}
+
+static const struct kobj_type mempolicy_ktype = {
+ .release = mempolicy_kobj_release
+};
+
+static int __init mempolicy_sysfs_init(void)
+{
+ int err;
+ static struct kobject *mempolicy_kobj;
+
+ mempolicy_kobj = kzalloc(sizeof(*mempolicy_kobj), GFP_KERNEL);
+ if (!mempolicy_kobj) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ node_attrs = kcalloc(nr_node_ids, sizeof(struct iw_node_attr *),
+ GFP_KERNEL);
+ if (!node_attrs) {
+ err = -ENOMEM;
+ goto mempol_out;
+ }
+
+ err = kobject_init_and_add(mempolicy_kobj, &mempolicy_ktype, mm_kobj,
+ "mempolicy");
+ if (err)
+ goto node_out;
+
+ err = add_weighted_interleave_group(mempolicy_kobj);
+ if (err) {
+ pr_err("mempolicy sysfs structure failed to initialize\n");
+ kobject_put(mempolicy_kobj);
+ return err;
+ }
+
+ return err;
+node_out:
+ kfree(node_attrs);
+mempol_out:
+ kfree(mempolicy_kobj);
+err_out:
+ pr_err("failed to add mempolicy kobject to the system\n");
+ return err;
+}
+
+late_initcall(mempolicy_sysfs_init);
+#endif /* CONFIG_SYSFS */
--
2.39.1
