1 files changed, 398 insertions, 206 deletions

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index f2bf98bdcea2..603a0f652ba6 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -16,6 +16,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/pfn.h>
 #include <linux/cpuset.h>
 #include <linux/node.h>
@@ -26,7 +27,6 @@
 #include <linux/slab.h>
 #include <asm/cputhreads.h>
 #include <asm/sparsemem.h>
-#include <asm/prom.h>
 #include <asm/smp.h>
 #include <asm/topology.h>
 #include <asm/firmware.h>
@@ -34,31 +34,35 @@
 #include <asm/hvcall.h>
 #include <asm/setup.h>
 #include <asm/vdso.h>
+#include <asm/vphn.h>
 #include <asm/drmem.h>
 
 static int numa_enabled = 1;
 
 static char *cmdline __initdata;
 
-static int numa_debug;
-#define dbg(args...) if (numa_debug) { printk(KERN_INFO args); }
-
 int numa_cpu_lookup_table[NR_CPUS];
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
-struct pglist_data *node_data[MAX_NUMNODES];
 
 EXPORT_SYMBOL(numa_cpu_lookup_table);
 EXPORT_SYMBOL(node_to_cpumask_map);
-EXPORT_SYMBOL(node_data);
 
-static int min_common_depth;
+static int primary_domain_index;
 static int n_mem_addr_cells, n_mem_size_cells;
-static int form1_affinity;
+
+#define FORM0_AFFINITY 0
+#define FORM1_AFFINITY 1
+#define FORM2_AFFINITY 2
+static int affinity_form;
 
 #define MAX_DISTANCE_REF_POINTS 4
 static int distance_ref_points_depth;
 static const __be32 *distance_ref_points;
 static int distance_lookup_table[MAX_NUMNODES][MAX_DISTANCE_REF_POINTS];
+static int numa_distance_table[MAX_NUMNODES][MAX_NUMNODES] = {
+	[0 ... MAX_NUMNODES - 1] = { [0 ... MAX_NUMNODES - 1] = -1 }
+};
+static int numa_id_index_table[MAX_NUMNODES] = { [0 ... MAX_NUMNODES - 1] = NUMA_NO_NODE };
 
 /*
  * Allocate node_to_cpumask_map based on number of available nodes
@@ -79,7 +83,7 @@ static void __init setup_node_to_cpumask_map(void)
 		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
 
 	/* cpumask_of_node() will now work */
-	dbg("Node to cpumask map for %u nodes\n", nr_node_ids);
+	pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
 }
 
 static int __init fake_numa_create_new_node(unsigned long end_pfn,
@@ -123,13 +127,13 @@ static int __init fake_numa_create_new_node(unsigned long end_pfn,
 		cmdline = p;
 		fake_nid++;
 		*nid = fake_nid;
-		dbg("created new fake_node with id %d\n", fake_nid);
+		pr_debug("created new fake_node with id %d\n", fake_nid);
 		return 1;
 	}
 	return 0;
 }
 
-static void reset_numa_cpu_lookup_table(void)
+static void __init reset_numa_cpu_lookup_table(void)
 {
 	unsigned int cpu;
 
@@ -137,33 +141,79 @@ static void reset_numa_cpu_lookup_table(void)
 		numa_cpu_lookup_table[cpu] = -1;
 }
 
-static void map_cpu_to_node(int cpu, int node)
+void map_cpu_to_node(int cpu, int node)
 {
 	update_numa_cpu_lookup_table(cpu, node);
 
-	dbg("adding cpu %d to node %d\n", cpu, node);
-
-	if (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node])))
+	if (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node]))) {
+		pr_debug("adding cpu %d to node %d\n", cpu, node);
 		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
+	}
 }
 
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR)
-static void unmap_cpu_from_node(unsigned long cpu)
+void unmap_cpu_from_node(unsigned long cpu)
 {
 	int node = numa_cpu_lookup_table[cpu];
 
-	dbg("removing cpu %lu from node %d\n", cpu, node);
-
 	if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) {
 		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
+		pr_debug("removing cpu %lu from node %d\n", cpu, node);
 	} else {
-		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
-		       cpu, node);
+		pr_warn("Warning: cpu %lu not found in node %d\n", cpu, node);
 	}
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
-int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+static int __associativity_to_nid(const __be32 *associativity,
+				  int max_array_sz)
+{
+	int nid;
+	/*
+	 * primary_domain_index is 1 based array index.
+	 */
+	int index = primary_domain_index  - 1;
+
+	if (!numa_enabled || index >= max_array_sz)
+		return NUMA_NO_NODE;
+
+	nid = of_read_number(&associativity[index], 1);
+
+	/* POWER4 LPAR uses 0xffff as invalid node */
+	if (nid == 0xffff || nid >= nr_node_ids)
+		nid = NUMA_NO_NODE;
+	return nid;
+}
+/*
+ * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
+ * info is found.
+ */
+static int associativity_to_nid(const __be32 *associativity)
+{
+	int array_sz = of_read_number(associativity, 1);
+
+	/* Skip the first element in the associativity array */
+	return __associativity_to_nid((associativity + 1), array_sz);
+}
+
+static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	int dist;
+	int node1, node2;
+
+	node1 = associativity_to_nid(cpu1_assoc);
+	node2 = associativity_to_nid(cpu2_assoc);
+
+	dist = numa_distance_table[node1][node2];
+	if (dist <= LOCAL_DISTANCE)
+		return 0;
+	else if (dist <= REMOTE_DISTANCE)
+		return 1;
+	else
+		return 2;
+}
+
+static int __cpu_form1_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	int dist = 0;
 
@@ -179,6 +229,15 @@ int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 	return dist;
 }
 
+int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
+{
+	/* We should not get called with FORM0 */
+	VM_WARN_ON(affinity_form == FORM0_AFFINITY);
+	if (affinity_form == FORM1_AFFINITY)
+		return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
+	return __cpu_form2_relative_distance(cpu1_assoc, cpu2_assoc);
+}
+
 /* must hold reference to node during call */
 static const __be32 *of_get_associativity(struct device_node *dev)
 {
@@ -190,7 +249,9 @@ int __node_distance(int a, int b)
 	int i;
 	int distance = LOCAL_DISTANCE;
 
-	if (!form1_affinity)
+	if (affinity_form == FORM2_AFFINITY)
+		return numa_distance_table[a][b];
+	else if (affinity_form == FORM0_AFFINITY)
 		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
 
 	for (i = 0; i < distance_ref_points_depth; i++) {
@@ -205,52 +266,6 @@ int __node_distance(int a, int b)
 }
 EXPORT_SYMBOL(__node_distance);
 
-static void initialize_distance_lookup_table(int nid,
-		const __be32 *associativity)
-{
-	int i;
-
-	if (!form1_affinity)
-		return;
-
-	for (i = 0; i < distance_ref_points_depth; i++) {
-		const __be32 *entry;
-
-		entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];
-		distance_lookup_table[nid][i] = of_read_number(entry, 1);
-	}
-}
-
-/*
- * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA
- * info is found.
- */
-static int associativity_to_nid(const __be32 *associativity)
-{
-	int nid = NUMA_NO_NODE;
-
-	if (!numa_enabled)
-		goto out;
-
-	if (of_read_number(associativity, 1) >= min_common_depth)
-		nid = of_read_number(&associativity[min_common_depth], 1);
-
-	/* POWER4 LPAR uses 0xffff as invalid node */
-	if (nid == 0xffff || nid >= nr_node_ids)
-		nid = NUMA_NO_NODE;
-
-	if (nid > 0 &&
-		of_read_number(associativity, 1) >= distance_ref_points_depth) {
-		/*
-		 * Skip the length field and send start of associativity array
-		 */
-		initialize_distance_lookup_table(nid, associativity + 1);
-	}
-
-out:
-	return nid;
-}
-
 /* Returns the nid associated with the given device tree node,
  * or -1 if not found.
  */
@@ -284,10 +299,155 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
-static int __init find_min_common_depth(void)
+static void __initialize_form1_numa_distance(const __be32 *associativity,
+					     int max_array_sz)
+{
+	int i, nid;
+
+	if (affinity_form != FORM1_AFFINITY)
+		return;
+
+	nid = __associativity_to_nid(associativity, max_array_sz);
+	if (nid != NUMA_NO_NODE) {
+		for (i = 0; i < distance_ref_points_depth; i++) {
+			const __be32 *entry;
+			int index = be32_to_cpu(distance_ref_points[i]) - 1;
+
+			/*
+			 * broken hierarchy, return with broken distance table
+			 */
+			if (WARN(index >= max_array_sz, "Broken ibm,associativity property"))
+				return;
+
+			entry = &associativity[index];
+			distance_lookup_table[nid][i] = of_read_number(entry, 1);
+		}
+	}
+}
+
+static void initialize_form1_numa_distance(const __be32 *associativity)
+{
+	int array_sz;
+
+	array_sz = of_read_number(associativity, 1);
+	/* Skip the first element in the associativity array */
+	__initialize_form1_numa_distance(associativity + 1, array_sz);
+}
+
+/*
+ * Used to update distance information w.r.t newly added node.
+ */
+void update_numa_distance(struct device_node *node)
+{
+	int nid;
+
+	if (affinity_form == FORM0_AFFINITY)
+		return;
+	else if (affinity_form == FORM1_AFFINITY) {
+		const __be32 *associativity;
+
+		associativity = of_get_associativity(node);
+		if (!associativity)
+			return;
+
+		initialize_form1_numa_distance(associativity);
+		return;
+	}
+
+	/* FORM2 affinity  */
+	nid = of_node_to_nid_single(node);
+	if (nid == NUMA_NO_NODE)
+		return;
+
+	/*
+	 * With FORM2 we expect NUMA distance of all possible NUMA
+	 * nodes to be provided during boot.
+	 */
+	WARN(numa_distance_table[nid][nid] == -1,
+	     "NUMA distance details for node %d not provided\n", nid);
+}
+EXPORT_SYMBOL_GPL(update_numa_distance);
+
+/*
+ * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN}
+ * ibm,numa-distance-table = { N, 1, 2, 4, 5, 1, 6, .... N elements}
+ */
+static void __init initialize_form2_numa_distance_lookup_table(void)
 {
-	int depth;
+	int i, j;
 	struct device_node *root;
+	const __u8 *form2_distances;
+	const __be32 *numa_lookup_index;
+	int form2_distances_length;
+	int max_numa_index, distance_index;
+
+	if (firmware_has_feature(FW_FEATURE_OPAL))
+		root = of_find_node_by_path("/ibm,opal");
+	else
+		root = of_find_node_by_path("/rtas");
+	if (!root)
+		root = of_find_node_by_path("/");
+
+	numa_lookup_index = of_get_property(root, "ibm,numa-lookup-index-table", NULL);
+	max_numa_index = of_read_number(&numa_lookup_index[0], 1);
+
+	/* first element of the array is the size and is encode-int */
+	form2_distances = of_get_property(root, "ibm,numa-distance-table", NULL);
+	form2_distances_length = of_read_number((const __be32 *)&form2_distances[0], 1);
+	/* Skip the size which is encoded int */
+	form2_distances += sizeof(__be32);
+
+	pr_debug("form2_distances_len = %d, numa_dist_indexes_len = %d\n",
+		 form2_distances_length, max_numa_index);
+
+	for (i = 0; i < max_numa_index; i++)
+		/* +1 skip the max_numa_index in the property */
+		numa_id_index_table[i] = of_read_number(&numa_lookup_index[i + 1], 1);
+
+
+	if (form2_distances_length != max_numa_index * max_numa_index) {
+		WARN(1, "Wrong NUMA distance information\n");
+		form2_distances = NULL; // don't use it
+	}
+	distance_index = 0;
+	for (i = 0;  i < max_numa_index; i++) {
+		for (j = 0; j < max_numa_index; j++) {
+			int nodeA = numa_id_index_table[i];
+			int nodeB = numa_id_index_table[j];
+			int dist;
+
+			if (form2_distances)
+				dist = form2_distances[distance_index++];
+			else if (nodeA == nodeB)
+				dist = LOCAL_DISTANCE;
+			else
+				dist = REMOTE_DISTANCE;
+			numa_distance_table[nodeA][nodeB] = dist;
+			pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, dist);
+		}
+	}
+
+	of_node_put(root);
+}
+
+static int __init find_primary_domain_index(void)
+{
+	int index;
+	struct device_node *root;
+
+	/*
+	 * Check for which form of affinity.
+	 */
+	if (firmware_has_feature(FW_FEATURE_OPAL)) {
+		affinity_form = FORM1_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM2_AFFINITY)) {
+		pr_debug("Using form 2 affinity\n");
+		affinity_form = FORM2_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) {
+		pr_debug("Using form 1 affinity\n");
+		affinity_form = FORM1_AFFINITY;
+	} else
+		affinity_form = FORM0_AFFINITY;
 
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		root = of_find_node_by_path("/ibm,opal");
@@ -313,42 +473,37 @@ static int __init find_min_common_depth(void)
 					&distance_ref_points_depth);
 
 	if (!distance_ref_points) {
-		dbg("NUMA: ibm,associativity-reference-points not found.\n");
+		pr_debug("ibm,associativity-reference-points not found.\n");
 		goto err;
 	}
 
 	distance_ref_points_depth /= sizeof(int);
-
-	if (firmware_has_feature(FW_FEATURE_OPAL) ||
-	    firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) {
-		dbg("Using form 1 affinity\n");
-		form1_affinity = 1;
-	}
-
-	if (form1_affinity) {
-		depth = of_read_number(distance_ref_points, 1);
-	} else {
+	if (affinity_form == FORM0_AFFINITY) {
 		if (distance_ref_points_depth < 2) {
-			printk(KERN_WARNING "NUMA: "
-				"short ibm,associativity-reference-points\n");
+			pr_warn("short ibm,associativity-reference-points\n");
 			goto err;
 		}
 
-		depth = of_read_number(&distance_ref_points[1], 1);
+		index = of_read_number(&distance_ref_points[1], 1);
+	} else {
+		/*
+		 * Both FORM1 and FORM2 affinity find the primary domain details
+		 * at the same offset.
+		 */
+		index = of_read_number(distance_ref_points, 1);
 	}
-
 	/*
 	 * Warn and cap if the hardware supports more than
 	 * MAX_DISTANCE_REF_POINTS domains.
 	 */
 	if (distance_ref_points_depth > MAX_DISTANCE_REF_POINTS) {
-		printk(KERN_WARNING "NUMA: distance array capped at "
-			"%d entries\n", MAX_DISTANCE_REF_POINTS);
+		pr_warn("distance array capped at %d entries\n",
+			MAX_DISTANCE_REF_POINTS);
 		distance_ref_points_depth = MAX_DISTANCE_REF_POINTS;
 	}
 
 	of_node_put(root);
-	return depth;
+	return index;
 
 err:
 	of_node_put(root);
@@ -426,6 +581,38 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa)
 	return 0;
 }
 
+static int __init get_nid_and_numa_distance(struct drmem_lmb *lmb)
+{
+	struct assoc_arrays aa = { .arrays = NULL };
+	int default_nid = NUMA_NO_NODE;
+	int nid = default_nid;
+	int rc, index;
+
+	if ((primary_domain_index < 0) || !numa_enabled)
+		return default_nid;
+
+	rc = of_get_assoc_arrays(&aa);
+	if (rc)
+		return default_nid;
+
+	if (primary_domain_index <= aa.array_sz &&
+	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
+		const __be32 *associativity;
+
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
+		if (nid > 0 && affinity_form == FORM1_AFFINITY) {
+			/*
+			 * lookup array associativity entries have
+			 * no length of the array as the first element.
+			 */
+			__initialize_form1_numa_distance(associativity, aa.array_sz);
+		}
+	}
+	return nid;
+}
+
 /*
  * This is like of_node_to_nid_single() for memory represented in the
  * ibm,dynamic-reconfiguration-memory node.
@@ -437,35 +624,28 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	int nid = default_nid;
 	int rc, index;
 
-	if ((min_common_depth < 0) || !numa_enabled)
+	if ((primary_domain_index < 0) || !numa_enabled)
 		return default_nid;
 
 	rc = of_get_assoc_arrays(&aa);
 	if (rc)
 		return default_nid;
 
-	if (min_common_depth <= aa.array_sz &&
+	if (primary_domain_index <= aa.array_sz &&
 	    !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) {
-		index = lmb->aa_index * aa.array_sz + min_common_depth - 1;
-		nid = of_read_number(&aa.arrays[index], 1);
-
-		if (nid == 0xffff || nid >= nr_node_ids)
-			nid = default_nid;
+		const __be32 *associativity;
 
-		if (nid > 0) {
-			index = lmb->aa_index * aa.array_sz;
-			initialize_distance_lookup_table(nid,
-							&aa.arrays[index]);
-		}
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
 	}
-
 	return nid;
 }
 
 #ifdef CONFIG_PPC_SPLPAR
-static int vphn_get_nid(long lcpu)
+
+static int __vphn_get_associativity(long lcpu, __be32 *associativity)
 {
-	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	long rc, hwid;
 
 	/*
@@ -485,12 +665,30 @@ static int vphn_get_nid(long lcpu)
 
 		rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
 		if (rc == H_SUCCESS)
-			return associativity_to_nid(associativity);
+			return 0;
 	}
 
+	return -1;
+}
+
+static int vphn_get_nid(long lcpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+
+
+	if (!__vphn_get_associativity(lcpu, associativity))
+		return associativity_to_nid(associativity);
+
 	return NUMA_NO_NODE;
+
 }
 #else
+
+static int __vphn_get_associativity(long lcpu, __be32 *associativity)
+{
+	return -1;
+}
+
 static int vphn_get_nid(long unused)
 {
 	return NUMA_NO_NODE;
@@ -598,9 +796,6 @@ static int ppc_numa_cpu_prepare(unsigned int cpu)
 
 static int ppc_numa_cpu_dead(unsigned int cpu)
 {
-#ifdef CONFIG_HOTPLUG_CPU
-	unmap_cpu_from_node(cpu);
-#endif
 	return 0;
 }
 
@@ -685,7 +880,7 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
 			size = read_n_cells(n_mem_size_cells, usm);
 		}
 
-		nid = of_drconf_to_nid_single(lmb);
+		nid = get_nid_and_numa_distance(lmb);
 		fake_numa_create_new_node(((base + size) >> PAGE_SHIFT),
 					  &nid);
 		node_set_online(nid);
@@ -699,27 +894,34 @@ static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb,
 
 static int __init parse_numa_properties(void)
 {
-	struct device_node *memory;
+	struct device_node *memory, *pci;
 	int default_nid = 0;
 	unsigned long i;
+	const __be32 *associativity;
 
 	if (numa_enabled == 0) {
-		printk(KERN_WARNING "NUMA disabled by user\n");
+		pr_warn("disabled by user\n");
 		return -1;
 	}
 
-	min_common_depth = find_min_common_depth();
+	primary_domain_index = find_primary_domain_index();
 
-	if (min_common_depth < 0) {
+	if (primary_domain_index < 0) {
 		/*
-		 * if we fail to parse min_common_depth from device tree
+		 * if we fail to parse primary_domain_index from device tree
 		 * mark the numa disabled, boot with numa disabled.
 		 */
 		numa_enabled = false;
-		return min_common_depth;
+		return primary_domain_index;
 	}
 
-	dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth);
+	pr_debug("associativity depth for CPU/Memory: %d\n", primary_domain_index);
+
+	/*
+	 * If it is FORM2 initialize the distance table here.
+	 */
+	if (affinity_form == FORM2_AFFINITY)
+		initialize_form2_numa_distance_lookup_table();
 
 	/*
 	 * Even though we connect cpus to numa domains later in SMP
@@ -727,22 +929,36 @@ static int __init parse_numa_properties(void)
 	 * each node to be onlined must have NODE_DATA etc backing it.
 	 */
 	for_each_present_cpu(i) {
+		__be32 vphn_assoc[VPHN_ASSOC_BUFSIZE];
 		struct device_node *cpu;
-		int nid = vphn_get_nid(i);
+		int nid = NUMA_NO_NODE;
 
-		/*
-		 * Don't fall back to default_nid yet -- we will plug
-		 * cpus into nodes once the memory scan has discovered
-		 * the topology.
-		 */
-		if (nid == NUMA_NO_NODE) {
+		memset(vphn_assoc, 0, VPHN_ASSOC_BUFSIZE * sizeof(__be32));
+
+		if (__vphn_get_associativity(i, vphn_assoc) == 0) {
+			nid = associativity_to_nid(vphn_assoc);
+			initialize_form1_numa_distance(vphn_assoc);
+		} else {
+
+			/*
+			 * Don't fall back to default_nid yet -- we will plug
+			 * cpus into nodes once the memory scan has discovered
+			 * the topology.
+			 */
 			cpu = of_get_cpu_node(i, NULL);
 			BUG_ON(!cpu);
-			nid = of_node_to_nid_single(cpu);
+
+			associativity = of_get_associativity(cpu);
+			if (associativity) {
+				nid = associativity_to_nid(associativity);
+				initialize_form1_numa_distance(associativity);
+			}
 			of_node_put(cpu);
 		}
 
-		node_set_online(nid);
+		/* node_set_online() is an UB if 'nid' is negative */
+		if (likely(nid >= 0))
+			node_set_online(nid);
 	}
 
 	get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);
@@ -774,8 +990,11 @@ new_range:
 		 * have associativity properties.  If none, then
 		 * everything goes to default_nid.
 		 */
-		nid = of_node_to_nid_single(memory);
-		if (nid < 0)
+		associativity = of_get_associativity(memory);
+		if (associativity) {
+			nid = associativity_to_nid(associativity);
+			initialize_form1_numa_distance(associativity);
+		} else
 			nid = default_nid;
 
 		fake_numa_create_new_node(((start + size) >> PAGE_SHIFT), &nid);
@@ -789,6 +1008,18 @@ new_range:
 			goto new_range;
 	}
 
+	for_each_node_by_name(pci, "pci") {
+		int nid = NUMA_NO_NODE;
+
+		associativity = of_get_associativity(pci);
+		if (associativity) {
+			nid = associativity_to_nid(associativity);
+			initialize_form1_numa_distance(associativity);
+		}
+		if (likely(nid >= 0) && !node_online(nid))
+			node_set_online(nid);
+	}
+
 	/*
 	 * Now do the same thing for each MEMBLOCK listed in the
 	 * ibm,dynamic-memory property in the
@@ -811,10 +1042,8 @@ static void __init setup_nonnuma(void)
 	unsigned int nid = 0;
 	int i;
 
-	printk(KERN_DEBUG "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
-	       top_of_ram, total_ram);
-	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
-	       (top_of_ram - total_ram) >> 20);
+	pr_debug("Top of RAM: 0x%lx, Total RAM: 0x%lx\n", top_of_ram, total_ram);
+	pr_debug("Memory hole size: %ldMB\n", (top_of_ram - total_ram) >> 20);
 
 	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
 		fake_numa_create_new_node(end_pfn, &nid);
@@ -864,27 +1093,9 @@ void __init dump_numa_cpu_topology(void)
 static void __init 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);
-	u64 nd_pa;
-	void *nd;
-	int tnid;
-
-	nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
-	if (!nd_pa)
-		panic("Cannot allocate %zu bytes for node %d data\n",
-		      nd_size, nid);
-
-	nd = __va(nd_pa);
-
-	/* report and initialize */
-	pr_info("  NODE_DATA [mem %#010Lx-%#010Lx]\n",
-		nd_pa, nd_pa + nd_size - 1);
-	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
-	if (tnid != nid)
-		pr_info("    NODE_DATA(%d) on node %d\n", nid, tnid);
-
-	node_data[nid] = nd;
-	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
+
+	alloc_node_data(nid);
+
 	NODE_DATA(nid)->node_id = nid;
 	NODE_DATA(nid)->node_start_pfn = start_pfn;
 	NODE_DATA(nid)->node_spanned_pages = spanned_pages;
@@ -892,8 +1103,8 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 
 static void __init find_possible_nodes(void)
 {
-	struct device_node *rtas;
-	const __be32 *domains;
+	struct device_node *rtas, *root;
+	const __be32 *domains = NULL;
 	int prop_length, max_nodes;
 	u32 i;
 
@@ -909,9 +1120,16 @@ static void __init find_possible_nodes(void)
 	 * it doesn't exist, then fallback on ibm,max-associativity-domains.
 	 * Current denotes what the platform can support compared to max
 	 * which denotes what the Hypervisor can support.
+	 *
+	 * If the LPAR is migratable, new nodes might be activated after a LPM,
+	 * so we should consider the max number in that case.
 	 */
-	domains = of_get_property(rtas, "ibm,current-associativity-domains",
-					&prop_length);
+	root = of_find_node_by_path("/");
+	if (!of_get_property(root, "ibm,migratable-partition", NULL))
+		domains = of_get_property(rtas,
+					  "ibm,current-associativity-domains",
+					  &prop_length);
+	of_node_put(root);
 	if (!domains) {
 		domains = of_get_property(rtas, "ibm,max-associativity-domains",
 					&prop_length);
@@ -919,14 +1137,16 @@ static void __init find_possible_nodes(void)
 			goto out;
 	}
 
-	max_nodes = of_read_number(&domains[min_common_depth], 1);
+	max_nodes = of_read_number(&domains[primary_domain_index], 1);
+	pr_info("Partition configured for %d NUMA nodes.\n", max_nodes);
+
 	for (i = 0; i < max_nodes; i++) {
 		if (!node_possible(i))
 			node_set(i, node_possible_map);
 	}
 
 	prop_length /= sizeof(int);
-	if (prop_length > min_common_depth + 2)
+	if (prop_length > primary_domain_index + 2)
 		coregroup_enabled = 1;
 
 out:
@@ -937,6 +1157,9 @@ void __init mem_topology_setup(void)
 {
 	int cpu;
 
+	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
+	min_low_pfn = MEMORY_START >> PAGE_SHIFT;
+
 	/*
 	 * Linux/mm assumes node 0 to be online at boot. However this is not
 	 * true on PowerPC, where node 0 is similar to any other node, it
@@ -981,9 +1204,6 @@ void __init initmem_init(void)
 {
 	int nid;
 
-	max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
-	max_pfn = max_low_pfn;
-
 	memblock_dump_all();
 
 	for_each_online_node(nid) {
@@ -1014,9 +1234,6 @@ static int __init early_numa(char *p)
 	if (strstr(p, "off"))
 		numa_enabled = 0;
 
-	if (strstr(p, "debug"))
-		numa_debug = 1;
-
 	p = strstr(p, "fake=");
 	if (p)
 		cmdline = p + strlen("fake=");
@@ -1068,23 +1285,15 @@ static int hot_add_node_scn_to_nid(unsigned long scn_addr)
 	int nid = NUMA_NO_NODE;
 
 	for_each_node_by_type(memory, "memory") {
-		unsigned long start, size;
-		int ranges;
-		const __be32 *memcell_buf;
-		unsigned int len;
-
-		memcell_buf = of_get_property(memory, "reg", &len);
-		if (!memcell_buf || len <= 0)
-			continue;
+		int i = 0;
 
-		/* ranges in cell */
-		ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells);
+		while (1) {
+			struct resource res;
 
-		while (ranges--) {
-			start = read_n_cells(n_mem_addr_cells, &memcell_buf);
-			size = read_n_cells(n_mem_size_cells, &memcell_buf);
+			if (of_address_to_resource(memory, i++, &res))
+				break;
 
-			if ((scn_addr < start) || (scn_addr >= (start + size)))
+			if ((scn_addr < res.start) || (scn_addr > res.end))
 				continue;
 
 			nid = of_node_to_nid_single(memory);
@@ -1127,7 +1336,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 	return nid;
 }
 
-static u64 hot_add_drconf_memory_max(void)
+u64 hot_add_drconf_memory_max(void)
 {
 	struct device_node *memory = NULL;
 	struct device_node *dn = NULL;
@@ -1179,7 +1388,7 @@ static long vphn_get_associativity(unsigned long cpu,
 
 	switch (rc) {
 	case H_SUCCESS:
-		dbg("VPHN hcall succeeded. Reset polling...\n");
+		pr_debug("VPHN hcall succeeded. Reset polling...\n");
 		goto out;
 
 	case H_FUNCTION:
@@ -1202,43 +1411,26 @@ out:
 	return rc;
 }
 
-int find_and_online_cpu_nid(int cpu)
+void find_and_update_cpu_nid(int cpu)
 {
 	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	int new_nid;
 
 	/* Use associativity from first thread for all siblings */
 	if (vphn_get_associativity(cpu, associativity))
-		return cpu_to_node(cpu);
+		return;
 
+	/* Do not have previous associativity, so find it now. */
 	new_nid = associativity_to_nid(associativity);
-	if (new_nid < 0 || !node_possible(new_nid))
-		new_nid = first_online_node;
 
-	if (NODE_DATA(new_nid) == NULL) {
-#ifdef CONFIG_MEMORY_HOTPLUG
-		/*
-		 * Need to ensure that NODE_DATA is initialized for a node from
-		 * available memory (see memblock_alloc_try_nid). If unable to
-		 * init the node, then default to nearest node that has memory
-		 * installed. Skip onlining a node if the subsystems are not
-		 * yet initialized.
-		 */
-		if (!topology_inited || try_online_node(new_nid))
-			new_nid = first_online_node;
-#else
-		/*
-		 * Default to using the nearest node that has memory installed.
-		 * Otherwise, it would be necessary to patch the kernel MM code
-		 * to deal with more memoryless-node error conditions.
-		 */
+	if (new_nid < 0 || !node_possible(new_nid))
 		new_nid = first_online_node;
-#endif
-	}
+	else
+		// Associate node <-> cpu, so cpu_up() calls
+		// try_online_node() on the right node.
+		set_cpu_numa_node(cpu, new_nid);
 
-	pr_debug("%s:%d cpu %d nid %d\n", __FUNCTION__, __LINE__,
-		cpu, new_nid);
-	return new_nid;
+	pr_debug("%s:%d cpu %d nid %d\n", __func__, __LINE__, cpu, new_nid);
 }
 
 int cpu_to_coregroup_id(int cpu)
@@ -1259,7 +1451,7 @@ int cpu_to_coregroup_id(int cpu)
 		goto out;
 
 	index = of_read_number(associativity, 1);
-	if (index > min_common_depth + 1)
+	if (index > primary_domain_index + 1)
 		return of_read_number(&associativity[index - 1], 1);
 
 out: