Re: [RFC PATCH] powerpc/numa: add ability to disable and debug topology updates

We have hit a few customer issues with the topology update code (VPHN
and PRRN). It would be nice to be able to debug the notifications coming
from the hypervisor in both cases to the LPAR, as well as to disable
reacting to the notifications, to narrow down the source of the
problems. Add a basic level of such functionality, similar to the numa=
command-line parameter.

Signed-off-by: Nishanth Aravamudan <redacted>
---
This is pretty rough, but has been useful in the field already. I'm not
sure if more information would be useful than this basic amount.

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 5ae8608ca9f5..6e3b9e3a2ab4 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt

@@ -3370,6 +3370,13 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			e.g. base its process migration decisions on it.
 			Default is on.
 
+	topology_updates= [KNL, PPC, NUMA]
+			Format: {off | debug}
+			Specify if the kernel should ignore (off) or
+			emit more information (debug) when the
+			hypervisor sends NUMA topology updates to an
+			LPAR.

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index d7737a542fd7..72c5ad313cbe 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c

@@ -1160,6 +1160,28 @@ static int __init early_numa(char *p)
 }
 early_param("numa", early_numa);
 
+static int topology_updates_enabled = 1;
+static int topology_updates_debug = 0;
+
+static int __init early_topology_updates(char *p)
+{
+	if (!p)
+		return 0;
+
+	if (strstr(p, "off")) {
+		printk(KERN_INFO "Disabling topology updates\n");
+		topology_updates_enabled = 0;
+	}

+	if (strstr(p, "debug")) {
+		printk(KERN_INFO "Enabling topology updates debug\n");
+		topology_updates_debug = 1;
+	}
+
+	return 0;
+}
+early_param("topology_updates", early_topology_updates);
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Find the node associated with a hot added memory section for

@@ -1546,6 +1568,9 @@ int arch_update_cpu_topology(void)
 	struct device *dev;
 	int weight, new_nid, i = 0;
 
+	if (!topology_updates_enabled)
+		return 0;
+

	weight = cpumask_weight(&cpu_associativity_changes_mask);
	if (!weight)
		return 0;

@@ -1610,6 +1635,25 @@ int arch_update_cpu_topology(void)
 	 *
 	 * And for the similar reason, we will skip all the following updating.
 	 */

+		if (cpumask_weight(&updated_cpus)) {
+			for (ud = &updates[0]; ud; ud = ud->next) {
+				printk(KERN_DEBUG "cpu %d moving from node %d "
+						  "to %d\n", ud->cpu,
+						  ud->old_nid, ud->new_nid);
+			}
+		}
+		kfree(buf);
+	}
+
 	if (!cpumask_weight(&updated_cpus))
 		goto out;
 

@@ -1807,8 +1851,10 @@ static const struct file_operations topology_ops = {
 
 static int topology_update_init(void)
 {
-	start_topology_update();
-	proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops);
+	if (topology_updates_enabled) {
+		start_topology_update();
+		proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops);
+	}