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
responding to the notifications at boot-time, to narrow down the source
of the problems. Add a basic level of such functionality, similar to the
numa= command-line parameter. We already have a toggle in
/proc/powerpc/topology_updates that allows run-time enabling/disabling,
so the updates can be started at run-time if desired. But the bugs we've
run into have occured during boot or very shortly after coming to login,
and have resulted in a broken NUMA topology.

Signed-off-by: Nishanth Aravamudan <nacc@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 10d51c2f10d712b179f5e6f67d0b9032bb42b75c..c536e1c74320567efb9186fcbca5882edd0ea3c8 100644 (file)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3370,6 +3370,12 @@ 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}
+                       Specify if the kernel should ignore (off)
+                       topology updates sent by the hypervisor to this
+                       LPAR.
+
        tp720=          [HW,PS2]
 
        tpm_suspend_pcr=[HW,TPM]

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 51d707d85b2d5232cf21123ec5b1b5f55a51938d..177659050fa0ab852da9d96a90bbddf8bbba407a 100644 (file)
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -8,6 +8,8 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
+#define pr_fmt(fmt) "numa: " fmt
+
 #include <linux/threads.h>
 #include <linux/bootmem.h>
 #include <linux/init.h>
@@ -1153,6 +1155,22 @@ static int __init early_numa(char *p)
 }
 early_param("numa", early_numa);
 
+static bool topology_updates_enabled = true;
+
+static int __init early_topology_updates(char *p)
+{
+       if (!p)
+               return 0;
+
+       if (!strcmp(p, "off")) {
+               pr_info("Disabling topology updates\n");
+               topology_updates_enabled = false;
+       }
+
+       return 0;
+}
+early_param("topology_updates", early_topology_updates);
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Find the node associated with a hot added memory section for
@@ -1539,6 +1557,9 @@ int arch_update_cpu_topology(void)
        struct device *dev;
        int weight, new_nid, i = 0;
 
+       if (!prrn_enabled && !vphn_enabled)
+               return 0;
+
        weight = cpumask_weight(&cpu_associativity_changes_mask);
        if (!weight)
                return 0;
@@ -1592,6 +1613,15 @@ int arch_update_cpu_topology(void)
                cpu = cpu_last_thread_sibling(cpu);
        }
 
+       pr_debug("Topology update for the following CPUs:\n");
+       if (cpumask_weight(&updated_cpus)) {
+               for (ud = &updates[0]; ud; ud = ud->next) {
+                       pr_debug("cpu %d moving from node %d "
+                                         "to %d\n", ud->cpu,
+                                         ud->old_nid, ud->new_nid);
+               }
+       }
+
        /*
         * In cases where we have nothing to update (because the updates list
         * is too short or because the new topology is same as the old one),
@@ -1800,7 +1830,10 @@ static const struct file_operations topology_ops = {
 
 static int topology_update_init(void)
 {
-       start_topology_update();
+       /* Do not poll for changes if disabled at boot */
+       if (topology_updates_enabled)
+               start_topology_update();
+
        if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_ops))
                return -ENOMEM;