[DEBUG 18/21] mm: Add debugfs interface to dump each node's zonelist information

[Anshuman Khandual]

Each individual node in the system has a ZONELIST_FALLBACK zonelist
and a ZONELIST_NOFALLBACK zonelist. These zonelists decide fallback
order of zones during memory allocations. Sometimes it helps to dump
these zonelists to see the priority order of various zones in them.

Particularly platforms which support memory hotplug into previously
non existing zones (at boot), this interface helps in visualizing
which all zonelists of the system at what priority level, the new
hot added memory ends up in. POWER is such a platform where all the
memory detected during boot time remains with ZONE_DMA for good but
then hot plug process can actually get new memory into ZONE_MOVABLE.
So having a way to get the snapshot of the zonelists on the system
after memory or node hot[un]plug is desirable. This change adds one
new debugfs interface (/sys/kernel/debug/zonelists) which will fetch
and dump this information.

Example zonelist information from a KVM guest with four NUMA nodes
on a POWER8 platform.

[NODE (0)]
	ZONELIST_FALLBACK
		(0) (Node 0) (DMA)
		(1) (Node 1) (DMA)
		(2) (Node 2) (DMA)
		(3) (Node 3) (DMA)
	ZONELIST_NOFALLBACK
		(0) (Node 0) (DMA)
[NODE (1)]
	ZONELIST_FALLBACK
		(0) (Node 1) (DMA)
		(1) (Node 2) (DMA)
		(2) (Node 3) (DMA)
		(3) (Node 0) (DMA)
	ZONELIST_NOFALLBACK
		(0) (Node 1) (DMA)
[NODE (2)]
	ZONELIST_FALLBACK
		(0) (Node 2) (DMA)
		(1) (Node 3) (DMA)
		(2) (Node 0) (DMA)
		(3) (Node 1) (DMA)
	ZONELIST_NOFALLBACK
		(0) (Node 2) (DMA)
[NODE (3)]
	ZONELIST_FALLBACK
		(0) (Node 3) (DMA)
		(1) (Node 0) (DMA)
		(2) (Node 1) (DMA)
		(3) (Node 2) (DMA)
	ZONELIST_NOFALLBACK
		(0) (Node 3) (DMA)

Signed-off-by: Anshuman Khandual <khandual@xxxxxxxxxxxxxxxxxx>
---
 mm/memory.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/mm/memory.c b/mm/memory.c
index 6bf2b47..1099d35 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -64,6 +64,7 @@
 #include <linux/debugfs.h>
 #include <linux/userfaultfd_k.h>
 #include <linux/dax.h>
+#include <linux/mmzone.h>
 
 #include <asm/io.h>
 #include <asm/mmu_context.h>
@@ -3153,6 +3154,68 @@ static int __init fault_around_debugfs(void)
 		pr_warn("Failed to create fault_around_bytes in debugfs");
 	return 0;
 }
+
+#ifdef CONFIG_NUMA
+static void show_zonelist(struct seq_file *m, struct zonelist *zonelist)
+{
+	unsigned int i;
+
+	for (i = 0; zonelist->_zonerefs[i].zone; i++) {
+		seq_printf(m, "\t\t(%d) (Node %d) (%-7s 0x%pK)\n", i,
+			zonelist->_zonerefs[i].zone->zone_pgdat->node_id,
+			zone_names[zonelist->_zonerefs[i].zone_idx],
+			(void *) zonelist->_zonerefs[i].zone);
+	}
+}
+
+static int zonelists_show(struct seq_file *m, void *v)
+{
+	struct zonelist *zonelist;
+	unsigned int node;
+
+	for_each_online_node(node) {
+		zonelist = &(NODE_DATA(node)->
+				node_zonelists[ZONELIST_FALLBACK]);
+		seq_printf(m, "[NODE (%d)]\n", node);
+		seq_puts(m, "\tZONELIST_FALLBACK ");
+		seq_printf(m, "(0x%pK)\n", zonelist);
+		show_zonelist(m, zonelist);
+
+		zonelist = &(NODE_DATA(node)->
+				node_zonelists[ZONELIST_NOFALLBACK]);
+		seq_puts(m, "\tZONELIST_NOFALLBACK ");
+		seq_printf(m, "(0x%pK)\n", zonelist);
+		show_zonelist(m, zonelist);
+	}
+	return 0;
+}
+
+static int zonelists_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, zonelists_show, NULL);
+}
+
+static const struct file_operations zonelists_fops = {
+	.open		= zonelists_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init zonelists_debugfs(void)
+{
+	void *ret;
+
+	ret = debugfs_create_file("zonelists", 0444, NULL, NULL,
+			&zonelists_fops);
+	if (!ret)
+		pr_warn("Failed to create zonelists in debugfs");
+	return 0;
+}
+
+late_initcall(zonelists_debugfs);
+#endif /* CONFIG_NUMA */
+
 late_initcall(fault_around_debugfs);
 #endif
 
-- 
2.9.3