[PATCH V5 0/2] pseries/nodes: Fix issues with memoryless nodes

@@ -892,6 +892,35 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	NODE_DATA(nid)->node_spanned_pages = spanned_pages;
 }
 
+static void __init find_possible_nodes(void)
+{
+	struct device_node *rtas;
+	u32 numnodes, i;
+
+	if (min_common_depth <= 0)
+		return;
+
+	rtas = of_find_node_by_path("/rtas");
+	if (!rtas)
+		return;
+
+	if (of_property_read_u32_index(rtas,
+				"ibm,max-associativity-domains",
+				min_common_depth, &numnodes))
+		goto out;
+
+	pr_info("numa: Nodes = %d (mcd = %d)\n", numnodes,
+		min_common_depth);
+
+	for (i = 0; i < numnodes; i++) {
+		if (!node_possible(i))
+			node_set(i, node_possible_map);
+	}
+
+out:
+	of_node_put(rtas);
+}
+
 void __init initmem_init(void)
 {
 	int nid, cpu;

@@ -905,12 +934,15 @@ void __init initmem_init(void)
 	memblock_dump_all();
 
 	/*
-	 * Reduce the possible NUMA nodes to the online NUMA nodes,
-	 * since we do not support node hotplug. This ensures that  we
-	 * lower the maximum NUMA node ID to what is actually present.
+	 * Modify the set of possible NUMA nodes to reflect information
+	 * available about the set of online nodes, and the set of nodes
+	 * that we expect to make use of for this platform's affinity
+	 * calculations.
 	 */
 	nodes_and(node_possible_map, node_possible_map, node_online_map);
 
+	find_possible_nodes();
+
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;
 

@@ -551,7 +551,7 @@ static int numa_setup_cpu(unsigned long lcpu)
 	nid = of_node_to_nid_single(cpu);
 
 out_present:
-	if (nid < 0 || !node_online(nid))
+	if (nid < 0 || !node_possible(nid))
 		nid = first_online_node;
 
 	map_cpu_to_node(lcpu, nid);

@@ -867,7 +867,7 @@ void __init dump_numa_cpu_topology(void)
 }
 
 /* Initialize NODE_DATA for a node on the local memory */
-static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
+static void setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 {
 	u64 spanned_pages = end_pfn - start_pfn;
 	const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES);

@@ -1310,6 +1310,40 @@ static long vphn_get_associativity(unsigned long cpu,
 	return rc;
 }
 
+static inline int find_cpu_nid(int cpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	int new_nid;
+
+	/* Use associativity from first thread for all siblings */
+	vphn_get_associativity(cpu, associativity);
+	new_nid = associativity_to_nid(associativity);
+	if (new_nid < 0 || !node_possible(new_nid))
+		new_nid = first_online_node;
+
+	/*
+	 * Need to ensure that NODE_DATA is allocated/initialized for
+	 * a node from available memory (see memblock_alloc_try_nid).
+	 * Code executed after boot (like local_memory_node) may not
+	 * know enough to recover fully for memoryless nodes. 
+	 */
+	if (NODE_DATA(new_nid) == NULL) {
+		setup_node_data(new_nid, 0, 0);
+		try_online_node(new_nid);
+
+		/*
+		 * Node structures successfully initialized, but
+		 * we still need the memoryliess node to be offline.
+		 */
+		node_set_offline(new_nid);
+	}
+
+	if (NODE_DATA(new_nid)->node_spanned_pages == 0)
+		return first_online_node;
+
+	return new_nid;
+}
+
 /*
  * Update the CPU maps and sysfs entries for a single CPU when its NUMA
  * characteristics change. This function doesn't perform any locking and is

@@ -1377,7 +1411,6 @@ int numa_update_cpu_topology(bool cpus_locked)
 {
 	unsigned int cpu, sibling, changed = 0;
 	struct topology_update_data *updates, *ud;
-	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	cpumask_t updated_cpus;
 	struct device *dev;
 	int weight, new_nid, i = 0;

@@ -1415,11 +1448,7 @@ int numa_update_cpu_topology(bool cpus_locked)
 			continue;
 		}
 
-		/* Use associativity from first thread for all siblings */
-		vphn_get_associativity(cpu, associativity);
-		new_nid = associativity_to_nid(associativity);
-		if (new_nid < 0 || !node_online(new_nid))
-			new_nid = first_online_node;
+		new_nid = find_cpu_nid(cpu);
 
 		if (new_nid == numa_cpu_lookup_table[cpu]) {
 			cpumask_andnot(&cpu_associativity_changes_mask,