@@ -113,6 +113,7 @@
#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include <linux/uaccess.h>
+#include <linux/memory.h>
#include "internal.h"
@@ -3390,6 +3391,7 @@ struct iw_node_attr {
struct sysfs_wi_group {
struct kobject wi_kobj;
+ struct mutex kobj_lock;
struct iw_node_attr *nattrs[];
};
@@ -3439,12 +3441,24 @@ static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr,
static void sysfs_wi_node_release(int nid)
{
- if (!sgrp->nattrs[nid])
+ struct iw_node_attr *attr;
+
+ if (nid < 0 || nid >= nr_node_ids)
+ return;
+
+ mutex_lock(&sgrp->kobj_lock);
+ attr = sgrp->nattrs[nid];
+ if (!attr) {
+ mutex_unlock(&sgrp->kobj_lock);
return;
+ }
+
+ sgrp->nattrs[nid] = NULL;
+ mutex_unlock(&sgrp->kobj_lock);
- sysfs_remove_file(&sgrp->wi_kobj, &sgrp->nattrs[nid]->kobj_attr.attr);
- kfree(sgrp->nattrs[nid]->kobj_attr.attr.name);
- kfree(sgrp->nattrs[nid]);
+ sysfs_remove_file(&sgrp->wi_kobj, &attr->kobj_attr.attr);
+ kfree(attr->kobj_attr.attr.name);
+ kfree(attr);
}
static void sysfs_wi_release(struct kobject *wi_kobj)
@@ -3463,35 +3477,80 @@ static const struct kobj_type wi_ktype = {
static int sysfs_wi_node_add(int nid)
{
- struct iw_node_attr *node_attr;
+ int ret = 0;
char *name;
+ struct iw_node_attr *new_attr = NULL;
+
+ if (nid < 0 || nid >= nr_node_ids) {
+ pr_err("Invalid node id: %d\n", nid);
+ return -EINVAL;
+ }
- node_attr = kzalloc(sizeof(*node_attr), GFP_KERNEL);
- if (!node_attr)
+ new_attr = kzalloc(sizeof(struct iw_node_attr), GFP_KERNEL);
+ if (!new_attr)
return -ENOMEM;
name = kasprintf(GFP_KERNEL, "node%d", nid);
if (!name) {
- kfree(node_attr);
+ kfree(new_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;
+ mutex_lock(&sgrp->kobj_lock);
+ if (sgrp->nattrs[nid]) {
+ mutex_unlock(&sgrp->kobj_lock);
+ pr_info("Node [%d] already exists\n", nid);
+ kfree(new_attr);
+ kfree(name);
+ return 0;
+ }
- if (sysfs_create_file(&sgrp->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;
+ sgrp->nattrs[nid] = new_attr;
+ mutex_unlock(&sgrp->kobj_lock);
+
+ sysfs_attr_init(&sgrp->nattrs[nid]->kobj_attr.attr);
+ sgrp->nattrs[nid]->kobj_attr.attr.name = name;
+ sgrp->nattrs[nid]->kobj_attr.attr.mode = 0644;
+ sgrp->nattrs[nid]->kobj_attr.show = node_show;
+ sgrp->nattrs[nid]->kobj_attr.store = node_store;
+ sgrp->nattrs[nid]->nid = nid;
+
+ ret = sysfs_create_file(&sgrp->wi_kobj, &sgrp->nattrs[nid]->kobj_attr.attr);
+ if (ret) {
+ kfree(sgrp->nattrs[nid]->kobj_attr.attr.name);
+ kfree(sgrp->nattrs[nid]);
+ sgrp->nattrs[nid] = NULL;
+ pr_err("Failed to add attribute to weighted_interleave: %d\n", ret);
}
- sgrp->nattrs[nid] = node_attr;
- return 0;
+ return ret;
+}
+
+static int wi_node_notifier(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ int err;
+ struct memory_notify *arg = data;
+ int nid = arg->status_change_nid;
+
+ if (nid < 0)
+ goto notifier_end;
+
+ switch(action) {
+ case MEM_ONLINE:
+ err = sysfs_wi_node_add(nid);
+ if (err) {
+ pr_err("failed to add sysfs [node%d]\n", nid);
+ return NOTIFY_BAD;
+ }
+ break;
+ case MEM_OFFLINE:
+ sysfs_wi_node_release(nid);
+ break;
+ }
+
+notifier_end:
+ return NOTIFY_OK;
}
static int add_weighted_interleave_group(struct kobject *mempolicy_kobj)
@@ -3503,13 +3562,17 @@ static int add_weighted_interleave_group(struct kobject *mempolicy_kobj)
GFP_KERNEL);
if (!sgrp)
return -ENOMEM;
+ mutex_init(&sgrp->kobj_lock);
err = kobject_init_and_add(&sgrp->wi_kobj, &wi_ktype, mempolicy_kobj,
"weighted_interleave");
if (err)
goto err_out;
- for_each_node_state(nid, N_POSSIBLE) {
+ for_each_online_node(nid) {
+ if (!node_state(nid, N_MEMORY))
+ continue;
+
err = sysfs_wi_node_add(nid);
if (err) {
pr_err("failed to add sysfs [node%d]\n", nid);
@@ -3517,6 +3580,7 @@ static int add_weighted_interleave_group(struct kobject *mempolicy_kobj)
}
}
+ hotplug_memory_notifier(wi_node_notifier, DEFAULT_CALLBACK_PRI);
return 0;
err_out:
The weighted interleave policy distributes page allocations across multiple NUMA nodes based on their performance weight, thereby improving memory bandwidth utilization. The weight values for each node are configured through sysfs. Previously, sysfs entries for configuring weighted interleave were created for all possible nodes (N_POSSIBLE) at initialization, including nodes that might not have memory. However, not all nodes in N_POSSIBLE are usable at runtime, as some may remain memoryless or offline. This led to sysfs entries being created for unusable nodes, causing potential misconfiguration issues. To address this issue, this patch modifies the sysfs creation logic to: 1) Limit sysfs entries to nodes that are online and have memory, reducing the creation of sysfs attributes for unusable nodes. 2) Support memory hotplug by dynamically adding and removing sysfs entries based on whether a node transitions into or out of the N_MEMORY state. Additionally, the patch ensures that sysfs attributes are properly managed when nodes go offline, preventing stale or redundant entries from persisting in the system. By making these changes, the weighted interleave policy now manages its sysfs entries more efficiently, ensuring that only relevant nodes are considered for interleaving, and dynamically adapting to memory hotplug events. Signed-off-by: Rakie Kim <rakie.kim@sk.com> --- mm/mempolicy.c | 108 +++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 86 insertions(+), 22 deletions(-)