1 files changed, 62 insertions, 22 deletions

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 3b181b22cd46..b9d1dfdbe5bb 100644
--- 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>
@@ -538,7 +540,7 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
  */
 static int numa_setup_cpu(unsigned long lcpu)
 {
-        int nid;
+        int nid = -1;
         struct device_node *cpu;
 
         /*
@@ -555,19 +557,21 @@ static int numa_setup_cpu(unsigned long lcpu)
 
         if (!cpu) {
                 WARN_ON(1);
-                nid = 0;
-                goto out;
+                if (cpu_present(lcpu))
+                        goto out_present;
+                else
+                        goto out;
         }
 
         nid = of_node_to_nid_single(cpu);
 
+out_present:
         if (nid < 0 || !node_online(nid))
                 nid = first_online_node;
-out:
-        map_cpu_to_node(lcpu, nid);
 
+        map_cpu_to_node(lcpu, nid);
         of_node_put(cpu);
-
+out:
         return nid;
 }
 
@@ -611,8 +615,8 @@ static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action,
         case CPU_UP_CANCELED:
         case CPU_UP_CANCELED_FROZEN:
                 unmap_cpu_from_node(lcpu);
-                break;
                 ret = NOTIFY_OK;
+                break;
 #endif
         }
         return ret;
@@ -1049,7 +1053,7 @@ static void __init mark_reserved_regions_for_nid(int nid)
 
 void __init do_init_bootmem(void)
 {
-        int nid;
+        int nid, cpu;
 
         min_low_pfn = 0;
         max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
@@ -1122,16 +1126,14 @@ void __init do_init_bootmem(void)
 
         reset_numa_cpu_lookup_table();
         register_cpu_notifier(&ppc64_numa_nb);
-        cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
-                          (void *)(unsigned long)boot_cpuid);
-}
-
-void __init paging_init(void)
-{
-        unsigned long max_zone_pfns[MAX_NR_ZONES];
-        memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-        max_zone_pfns[ZONE_DMA] = memblock_end_of_DRAM() >> PAGE_SHIFT;
-        free_area_init_nodes(max_zone_pfns);
+        /*
+         * We need the numa_cpu_lookup_table to be accurate for all CPUs,
+         * even before we online them, so that we can use cpu_to_{node,mem}
+         * early in boot, cf. smp_prepare_cpus().
+         */
+        for_each_present_cpu(cpu) {
+                numa_setup_cpu((unsigned long)cpu);
+        }
 }
 
 static int __init early_numa(char *p)
@@ -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
@@ -1442,8 +1460,11 @@ static long hcall_vphn(unsigned long cpu, __be32 *associativity)
         long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
         u64 flags = 1;
         int hwcpu = get_hard_smp_processor_id(cpu);
+        int i;
 
         rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
+        for (i = 0; i < 6; i++)
+                retbuf[i] = cpu_to_be64(retbuf[i]);
         vphn_unpack_associativity(retbuf, associativity);
 
         return rc;
@@ -1488,11 +1509,14 @@ static int update_cpu_topology(void *data)
         cpu = smp_processor_id();
 
         for (update = data; update; update = update->next) {
+                int new_nid = update->new_nid;
                 if (cpu != update->cpu)
                         continue;
 
-                unmap_cpu_from_node(update->cpu);
-                map_cpu_to_node(update->cpu, update->new_nid);
+                unmap_cpu_from_node(cpu);
+                map_cpu_to_node(cpu, new_nid);
+                set_cpu_numa_node(cpu, new_nid);
+                set_cpu_numa_mem(cpu, local_memory_node(new_nid));
                 vdso_getcpu_init();
         }
 
@@ -1539,6 +1563,9 @@ 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 +1619,15 @@ 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),
@@ -1800,8 +1836,12 @@ 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);
+        /* 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;
 
         return 0;
 }