[PATCH v2 3/3] mm/page_owner: add NUMA node filter with nodelist support

[Zhen Ni]

Add NUMA node filtering functionality to page_owner to allow
filtering pages by specific NUMA node(s) using nodelist format.

The filter allows users to focus on pages from specific NUMA nodes,
which is useful for NUMA-aware memory allocation analysis and debugging.

Supported input formats:
- Single node: echo "2" > nid
- Multiple nodes: echo "0,2,3" > nid
- Node range: echo "0-3" > nid
- Mixed format: echo "0,2-4,7" > nid
- Disable filter: echo "-1" > nid

Link: https://lore.kernel.org/linux-mm/20260417154638.22370-4-zhen.ni@xxxxxxxxxxxx/
Suggested-by: Zi Yan <ziy@xxxxxxxxxx>
Signed-off-by: Zhen Ni <zhen.ni@xxxxxxxxxxxx>
---

Changes in v2:
- Use nodemask_t instead of int to support multiple nodes
- Implement nodelist_parse() to support flexible input formats
  * Single node: "0", "2"
  * Multiple nodes: "0,2,3"
  * Ranges: "0-3"
  * Mixed: "0,2-4,7"
- Use %*pbl format for output (e.g., "0-2", "0,2-4,7")
- Use dynamic memory allocation (kmalloc) to handle variable-length input
- Follow cpuset's max_write_len pattern: (100 + 6 * MAX_NUMNODES)
---
 mm/page_owner.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index 6d87b6948cfa..8c13bb3798d8 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -707,6 +707,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		 * user through copy_to_user() or GFP_KERNEL allocations.
 		 */
 		struct page_owner page_owner_tmp;
+		nodemask_t mask;
 
 		/*
 		 * If the new page is in a new MAX_ORDER_NR_PAGES area,
@@ -730,6 +731,15 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		if (unlikely(!page_ext))
 			continue;
 
+		/* NUMA node filter using bitmask */
+		mask = READ_ONCE(owner_filter.nid_mask);
+		if (!nodes_empty(mask)) {
+			int nid = page_to_nid(page);
+
+			if (!node_isset(nid, mask))
+				goto ext_put_continue;
+		}
+
 		/*
 		 * Some pages could be missed by concurrent allocation or free,
 		 * because we don't hold the zone lock.
@@ -1009,6 +1019,70 @@ DEFINE_SIMPLE_ATTRIBUTE(page_owner_print_mode_fops,
 			&page_owner_print_mode_get,
 			&page_owner_print_mode_set, "%lld");
 
+static ssize_t nid_filter_write(struct file *file,
+				 const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	char *kbuf;
+	nodemask_t mask;
+	int ret;
+
+	/* Limit input size to handle worst-case nodelist (all nodes) */
+	if (count > (100 + 6 * MAX_NUMNODES))
+		return -EINVAL;
+
+	kbuf = kmalloc(count + 1, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
+
+	if (copy_from_user(kbuf, buf, count)) {
+		ret = -EFAULT;
+		goto out_free;
+	}
+	kbuf[count] = '\0';
+
+	/* Support: "-1" to clear, or nodelist format like "0", "0,2", "0-3" */
+	if (strcmp(kbuf, "-1\n") == 0 || strcmp(kbuf, "-1") == 0)
+		nodes_clear(mask);
+	else if (nodelist_parse(kbuf, mask)) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	WRITE_ONCE(owner_filter.nid_mask, mask);
+	ret = count;
+
+out_free:
+	kfree(kbuf);
+	return ret;
+}
+
+static int nid_filter_show(struct seq_file *m, void *v)
+{
+	nodemask_t mask = READ_ONCE(owner_filter.nid_mask);
+
+	if (nodes_empty(mask))
+		seq_puts(m, "-1\n");
+	else
+		seq_printf(m, "%*pbl\n", nodemask_pr_args(&mask));
+
+	return 0;
+}
+
+static int nid_filter_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nid_filter_show, NULL);
+}
+
+static const struct file_operations nid_filter_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nid_filter_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.write		= nid_filter_write,
+	.release	= single_release,
+};
+
 
 static int __init pageowner_init(void)
 {
@@ -1024,6 +1098,8 @@ static int __init pageowner_init(void)
 	filter_dir = debugfs_create_dir("page_owner_filter", NULL);
 	debugfs_create_file("print_mode", 0600, filter_dir, NULL,
 			    &page_owner_print_mode_fops);
+	debugfs_create_file("nid", 0600, filter_dir, NULL,
+			    &nid_filter_fops);
 
 	dir = debugfs_create_dir("page_owner_stacks", NULL);
 	debugfs_create_file("show_stacks", 0400, dir,
-- 
2.20.1