[PATCH v6 0/6] Add support for FORM2 associativity

@@ -51,7 +51,7 @@ 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;
 

@@ -232,8 +232,8 @@ static int associativity_to_nid(const __be32 *associativity)
 	if (!numa_enabled)
 		goto out;
 
-	if (of_read_number(associativity, 1) >= min_common_depth)
-		nid = of_read_number(&associativity[min_common_depth], 1);
+	if (of_read_number(associativity, 1) >= primary_domain_index)
+		nid = of_read_number(&associativity[primary_domain_index], 1);
 
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= nr_node_ids)

@@ -284,9 +284,9 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
-static int __init find_min_common_depth(void)
+static int __init find_primary_domain_index(void)
 {
-	int depth;
+	int index;
 	struct device_node *root;
 
 	if (firmware_has_feature(FW_FEATURE_OPAL))

@@ -326,7 +326,7 @@ static int __init find_min_common_depth(void)
 	}
 
 	if (form1_affinity) {
-		depth = of_read_number(distance_ref_points, 1);
+		index = of_read_number(distance_ref_points, 1);
 	} else {
 		if (distance_ref_points_depth < 2) {
 			printk(KERN_WARNING "NUMA: "

@@ -334,7 +334,7 @@ static int __init find_min_common_depth(void)
 			goto err;
 		}
 
-		depth = of_read_number(&distance_ref_points[1], 1);
+		index = of_read_number(&distance_ref_points[1], 1);
 	}
 
 	/*

@@ -348,7 +348,7 @@ static int __init find_min_common_depth(void)
 	}
 
 	of_node_put(root);
-	return depth;
+	return index;
 
 err:
 	of_node_put(root);

@@ -437,16 +437,16 @@ 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;
+		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
 		nid = of_read_number(&aa.arrays[index], 1);
 
 		if (nid == 0xffff || nid >= nr_node_ids)

@@ -708,18 +708,18 @@ static int __init parse_numa_properties(void)
 		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);
+	dbg("NUMA associativity depth for CPU/Memory: %d\n", primary_domain_index);
 
 	/*
 	 * Even though we connect cpus to numa domains later in SMP

@@ -919,14 +919,14 @@ 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);
 	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:

@@ -1259,7 +1259,7 @@ 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:

@@ -64,6 +64,7 @@ static inline int early_cpu_to_node(int cpu)
 }
 
 int of_drconf_to_nid_single(struct drmem_lmb *lmb);
+void update_numa_distance(struct device_node *node);
 
 #else
 

@@ -93,6 +94,7 @@ static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	return first_online_node;
 }
 
+static inline void update_numa_distance(struct device_node *node) {}
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)

@@ -208,22 +208,6 @@ 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 (affinity_form != 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.

@@ -241,15 +225,6 @@ static int associativity_to_nid(const __be32 *associativity)
 	/* 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;
 }

@@ -287,6 +262,48 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
+static void __initialize_form1_numa_distance(const __be32 *associativity)
+{
+	int i, nid;
+
+	if (affinity_form != FORM1_AFFINITY)
+		return;
+
+	nid = associativity_to_nid(associativity);
+	if (nid != NUMA_NO_NODE) {
+		for (i = 0; i < distance_ref_points_depth; i++) {
+			const __be32 *entry;
+
+			entry = &associativity[be32_to_cpu(distance_ref_points[i])];
+			distance_lookup_table[nid][i] = of_read_number(entry, 1);
+		}
+	}
+}
+
+static void initialize_form1_numa_distance(struct device_node *node)
+{
+	const __be32 *associativity;
+
+	associativity = of_get_associativity(node);
+	if (!associativity)
+		return;
+
+	__initialize_form1_numa_distance(associativity);
+}
+
+/*
+ * Used to update distance information w.r.t newly added node.
+ */
+void update_numa_distance(struct device_node *node)
+{
+	if (affinity_form == FORM0_AFFINITY)
+		return;
+	else if (affinity_form == FORM1_AFFINITY) {
+		initialize_form1_numa_distance(node);
+		return;
+	}
+}
+
 static int __init find_primary_domain_index(void)
 {
 	int index;

@@ -433,6 +450,48 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa)
 	return 0;
 }
 
+static int 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) {
+		index = lmb->aa_index * aa.array_sz + primary_domain_index - 1;
+		nid = of_read_number(&aa.arrays[index], 1);
+
+		if (nid == 0xffff || nid >= nr_node_ids)
+			nid = default_nid;
+		if (nid > 0 && affinity_form == FORM1_AFFINITY) {
+			int i;
+			const __be32 *associativity;
+
+			index = lmb->aa_index * aa.array_sz;
+			associativity = &aa.arrays[index];
+			/*
+			 * lookup array associativity entries have different format
+			 * There is no length of the array as the first element.
+			 */
+			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);
+			}
+		}
+	}
+	return nid;
+}
+
 /*
  * This is like of_node_to_nid_single() for memory represented in the
  * ibm,dynamic-reconfiguration-memory node.

@@ -458,21 +517,14 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 
 		if (nid == 0xffff || nid >= nr_node_ids)
 			nid = default_nid;
-
-		if (nid > 0) {
-			index = lmb->aa_index * aa.array_sz;
-			initialize_distance_lookup_table(nid,
-							&aa.arrays[index]);
-		}
 	}
-
 	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;
 
 	/*

@@ -492,12 +544,30 @@ 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;

@@ -692,7 +762,7 @@ 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);

@@ -709,6 +779,7 @@ static int __init parse_numa_properties(void)
 	struct device_node *memory;
 	int default_nid = 0;
 	unsigned long i;
+	const __be32 *associativity;
 
 	if (numa_enabled == 0) {
 		printk(KERN_WARNING "NUMA disabled by user\n");

@@ -734,18 +805,30 @@ 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);
 		}
 

@@ -781,8 +864,11 @@ static int __init parse_numa_properties(void)
 		 * 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);

@@ -498,6 +498,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
 		return saved_rc;
 	}
 
+	update_numa_distance(dn);
+
 	rc = dlpar_online_cpu(dn);
 	if (rc) {
 		saved_rc = rc;

@@ -180,6 +180,8 @@ static int update_lmb_associativity_index(struct drmem_lmb *lmb)
 		return -ENODEV;
 	}
 
+	update_numa_distance(lmb_node);
+
 	dr_node = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
 	if (!dr_node) {
 		dlpar_free_cc_nodes(lmb_node);

@@ -171,19 +171,19 @@ static void unmap_cpu_from_node(unsigned long cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
-/*
- * 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)
+static int __associativity_to_nid(const __be32 *associativity,
+				  int max_array_sz)
 {
 	int nid = NUMA_NO_NODE;
+	/*
+	 * primary_domain_index is 1 based array index.
+	 */
+	int index = primary_domain_index  - 1;
 
-	if (!numa_enabled)
+	if (!numa_enabled || index >= max_array_sz)
 		goto out;
 
-	if (of_read_number(associativity, 1) >= primary_domain_index)
-		nid = of_read_number(&associativity[primary_domain_index], 1);
+	nid = of_read_number(&associativity[index], 1);
 
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= nr_node_ids)

@@ -191,6 +191,17 @@ static int associativity_to_nid(const __be32 *associativity)
 out:
 	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)
 {

@@ -295,24 +306,41 @@ int of_node_to_nid(struct device_node *device)
 }
 EXPORT_SYMBOL(of_node_to_nid);
 
-static void __initialize_form1_numa_distance(const __be32 *associativity)
+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);
+	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 (index >= max_array_sz)
+				return;
 
-			entry = &associativity[be32_to_cpu(distance_ref_points[i])];
+			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);
+}
+
 static void initialize_form1_numa_distance(struct device_node *node)
 {
 	const __be32 *associativity;

@@ -586,27 +614,18 @@ static int get_nid_and_numa_distance(struct drmem_lmb *lmb)
 
 	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 + primary_domain_index - 1;
-		nid = of_read_number(&aa.arrays[index], 1);
+		const __be32 *associativity;
 
-		if (nid == 0xffff || nid >= nr_node_ids)
-			nid = default_nid;
+		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) {
-			int i;
-			const __be32 *associativity;
-
-			index = lmb->aa_index * aa.array_sz;
-			associativity = &aa.arrays[index];
 			/*
-			 * lookup array associativity entries have different format
-			 * There is no length of the array as the first element.
+			 * lookup array associativity entries have
+			 * no length of the array as the first element.
 			 */
-			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);
-			}
+			___initialize_form1_numa_distance(associativity,
+							  aa.array_sz);
 		}
 	}
 	return nid;

@@ -632,11 +651,11 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 
 	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 + primary_domain_index - 1;
-		nid = of_read_number(&aa.arrays[index], 1);
+		const __be32 *associativity;
 
-		if (nid == 0xffff || nid >= nr_node_ids)
-			nid = default_nid;
+		index = lmb->aa_index * aa.array_sz;
+		associativity = &aa.arrays[index];
+		nid = __associativity_to_nid(associativity, aa.array_sz);
 	}
 	return nid;
 }

@@ -44,7 +44,7 @@
 #define FW_FEATURE_OPAL		ASM_CONST(0x0000000010000000)
 #define FW_FEATURE_SET_MODE	ASM_CONST(0x0000000040000000)
 #define FW_FEATURE_BEST_ENERGY	ASM_CONST(0x0000000080000000)
-#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
+#define FW_FEATURE_FORM1_AFFINITY ASM_CONST(0x0000000100000000)
 #define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
 #define FW_FEATURE_DRMEM_V2	ASM_CONST(0x0000000400000000)
 #define FW_FEATURE_DRC_INFO	ASM_CONST(0x0000000800000000)

@@ -69,7 +69,7 @@ enum {
 		FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
 		FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
-		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN |
+		FW_FEATURE_FORM1_AFFINITY | FW_FEATURE_PRRN |
 		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
 		FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE |
 		FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR |

@@ -147,7 +147,7 @@ extern int of_read_drc_info_cell(struct property **prop,
 #define OV5_MSI			0x0201	/* PCIe/MSI support */
 #define OV5_CMO			0x0480	/* Cooperative Memory Overcommitment */
 #define OV5_XCMO		0x0440	/* Page Coalescing */
-#define OV5_TYPE1_AFFINITY	0x0580	/* Type 1 NUMA affinity */
+#define OV5_FORM1_AFFINITY	0x0580	/* FORM1 NUMA affinity */
 #define OV5_PRRN		0x0540	/* Platform Resource Reassignment */
 #define OV5_HP_EVT		0x0604	/* Hot Plug Event support */
 #define OV5_RESIZE_HPT		0x0601	/* Hash Page Table resizing */

@@ -1096,7 +1096,7 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 #else
 		0,
 #endif
-		.associativity = OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN),
+		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN),
 		.bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT),
 		.micro_checkpoint = 0,
 		.reserved0 = 0,

@@ -53,7 +53,10 @@ EXPORT_SYMBOL(node_data);
 
 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
+static int affinity_form;
 
 #define MAX_DISTANCE_REF_POINTS 4
 static int distance_ref_points_depth;

@@ -190,7 +193,7 @@ int __node_distance(int a, int b)
 	int i;
 	int distance = LOCAL_DISTANCE;
 
-	if (!form1_affinity)
+	if (affinity_form == FORM0_AFFINITY)
 		return ((a == b) ? LOCAL_DISTANCE : REMOTE_DISTANCE);
 
 	for (i = 0; i < distance_ref_points_depth; i++) {

@@ -210,7 +213,7 @@ static void initialize_distance_lookup_table(int nid,
 {
 	int i;
 
-	if (!form1_affinity)
+	if (affinity_form != FORM1_AFFINITY)
 		return;
 
 	for (i = 0; i < distance_ref_points_depth; i++) {

@@ -289,6 +292,17 @@ 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_FORM1_AFFINITY)) {
+		dbg("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");
 	else

@@ -318,23 +332,16 @@ static int __init find_primary_domain_index(void)
 	}
 
 	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) {
-		index = 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");
+			       "short ibm,associativity-reference-points\n");
 			goto err;
 		}
 
 		index = of_read_number(&distance_ref_points[1], 1);
+	} else {
+		index = of_read_number(distance_ref_points, 1);
 	}
 
 	/*

@@ -119,7 +119,7 @@ struct vec5_fw_feature {
 
 static __initdata struct vec5_fw_feature
 vec5_fw_features_table[] = {
-	{FW_FEATURE_TYPE1_AFFINITY,	OV5_TYPE1_AFFINITY},
+	{FW_FEATURE_FORM1_AFFINITY,	OV5_FORM1_AFFINITY},
 	{FW_FEATURE_PRRN,		OV5_PRRN},
 	{FW_FEATURE_DRMEM_V2,		OV5_DRMEM_V2},
 	{FW_FEATURE_DRC_INFO,		OV5_DRC_INFO},

@@ -0,0 +1,103 @@
+============================
+NUMA resource associativity
+=============================
+
+Associativity represents the groupings of the various platform resources into
+domains of substantially similar mean performance relative to resources outside
+of that domain. Resources subsets of a given domain that exhibit better
+performance relative to each other than relative to other resources subsets
+are represented as being members of a sub-grouping domain. This performance
+characteristic is presented in terms of NUMA node distance within the Linux kernel.
+From the platform view, these groups are also referred to as domains.
+
+PAPR interface currently supports different ways of communicating these resource
+grouping details to the OS. These are referred to as Form 0, Form 1 and Form2
+associativity grouping. Form 0 is the oldest format and is now considered deprecated.
+
+Hypervisor indicates the type/form of associativity used via "ibm,architecture-vec-5 property".
+Bit 0 of byte 5 in the "ibm,architecture-vec-5" property indicates usage of Form 0 or Form 1.
+A value of 1 indicates the usage of Form 1 associativity. For Form 2 associativity
+bit 2 of byte 5 in the "ibm,architecture-vec-5" property is used.
+
+Form 0
+-----
+Form 0 associativity supports only two NUMA distances (LOCAL and REMOTE).
+
+Form 1
+-----
+With Form 1 a combination of ibm,associativity-reference-points, and ibm,associativity
+device tree properties are used to determine the NUMA distance between resource groups/domains.
+
+The “ibm,associativity” property contains a list of one or more numbers (domainID)
+representing the resource’s platform grouping domains.
+
+The “ibm,associativity-reference-points” property contains a list of one or more numbers
+(domainID index) that represents the 1 based ordinal in the associativity lists.
+The list of domainID indexes represents an increasing hierarchy of resource grouping.
+
+ex:
+{ primary domainID index, secondary domainID index, tertiary domainID index.. }
+
+Linux kernel uses the domainID at the primary domainID index as the NUMA node id.
+Linux kernel computes NUMA distance between two domains by recursively comparing
+if they belong to the same higher-level domains. For mismatch at every higher
+level of the resource group, the kernel doubles the NUMA distance between the
+comparing domains.
+
+Form 2
+-------
+Form 2 associativity format adds separate device tree properties representing NUMA node distance
+thereby making the node distance computation flexible. Form 2 also allows flexible primary
+domain numbering. With numa distance computation now detached from the index value in
+"ibm,associativity-reference-points" property, Form 2 allows a large number of primary domain
+ids at the same domainID index representing resource groups of different performance/latency
+characteristics.
+
+Hypervisor indicates the usage of FORM2 associativity using bit 2 of byte 5 in the
+"ibm,architecture-vec-5" property.
+
+"ibm,numa-lookup-index-table" property contains a list of one or more numbers representing
+the domainIDs present in the system. The offset of the domainID in this property is
+used as an index while computing numa distance information via "ibm,numa-distance-table".
+
+prop-encoded-array: The number N of the domainIDs encoded as with encode-int, followed by
+N domainID encoded as with encode-int
+
+For ex:
+"ibm,numa-lookup-index-table" =  {4, 0, 8, 250, 252}. The offset of domainID 8 (2) is used when
+computing the distance of domain 8 from other domains present in the system. For the rest of
+this document, this offset will be referred to as domain distance offset.
+
+"ibm,numa-distance-table" property contains a list of one or more numbers representing the NUMA
+distance between resource groups/domains present in the system.
+
+prop-encoded-array: The number N of the distance values encoded as with encode-int, followed by
+N distance values encoded as with encode-bytes. The max distance value we could encode is 255.
+The number N must be equal to the square of m where m is the number of domainIDs in the
+numa-lookup-index-table.
+
+For ex:
+ibm,numa-lookup-index-table =  {3, 0, 8, 40}
+ibm,numa-distance-table     =  {9:u32, 10:u8, 20:u8, 80:u8, 20:u8, 10:u8, 160:u8, 80:u8, 160:u8, 10:u8}
+
+  | 0    8   40
+--|------------
+  |
+0 | 10   20  80
+  |
+8 | 20   10  160
+  |
+40| 80   160  10
+
+A possible "ibm,associativity" property for resources in node 0, 8 and 40
+
+{ 3, 6, 7, 0 }
+{ 3, 6, 9, 8 }
+{ 3, 6, 7, 40}
+
+With "ibm,associativity-reference-points"  { 0x3 }
+
+"ibm,lookup-index-table" helps in having a compact representation of distance matrix.
+Since domainID can be sparse, the matrix of distances can also be effectively sparse.
+With "ibm,lookup-index-table" we can achieve a compact representation of
+distance information.

@@ -53,6 +53,7 @@
 #define FW_FEATURE_ULTRAVISOR	ASM_CONST(0x0000004000000000)
 #define FW_FEATURE_STUFF_TCE	ASM_CONST(0x0000008000000000)
 #define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000)
+#define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000)
 
 #ifndef __ASSEMBLY__
 

@@ -73,7 +74,7 @@ enum {
 		FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 |
 		FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE |
 		FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR |
-		FW_FEATURE_RPT_INVALIDATE,
+		FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR,
 	FW_FEATURE_POWERNV_ALWAYS = 0,

@@ -149,6 +149,7 @@ extern int of_read_drc_info_cell(struct property **prop,
 #define OV5_XCMO		0x0440	/* Page Coalescing */
 #define OV5_FORM1_AFFINITY	0x0580	/* FORM1 NUMA affinity */
 #define OV5_PRRN		0x0540	/* Platform Resource Reassignment */
+#define OV5_FORM2_AFFINITY	0x0520	/* Form2 NUMA affinity */
 #define OV5_HP_EVT		0x0604	/* Hot Plug Event support */
 #define OV5_RESIZE_HPT		0x0601	/* Hash Page Table resizing */
 #define OV5_PFO_HW_RNG		0x1180	/* PFO Random Number Generator */

@@ -1096,7 +1096,8 @@ static const struct ibm_arch_vec ibm_architecture_vec_template __initconst = {
 #else
 		0,
 #endif
-		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN),
+		.associativity = OV5_FEAT(OV5_FORM1_AFFINITY) | OV5_FEAT(OV5_PRRN) |
+		OV5_FEAT(OV5_FORM2_AFFINITY),
 		.bin_opts = OV5_FEAT(OV5_RESIZE_HPT) | OV5_FEAT(OV5_HP_EVT),
 		.micro_checkpoint = 0,
 		.reserved0 = 0,

@@ -56,12 +56,17 @@ static int n_mem_addr_cells, n_mem_size_cells;
 
 #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

@@ -166,6 +171,44 @@ static void unmap_cpu_from_node(unsigned long cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
+/*
+ * 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) >= primary_domain_index)
+		nid = of_read_number(&associativity[primary_domain_index], 1);
+
+	/* POWER4 LPAR uses 0xffff as invalid node */
+	if (nid == 0xffff || nid >= nr_node_ids)
+		nid = NUMA_NO_NODE;
+out:
+	return nid;
+}
+
+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;

@@ -186,8 +229,9 @@ int cpu_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
 {
 	/* We should not get called with FORM0 */
 	VM_WARN_ON(affinity_form == FORM0_AFFINITY);
-
-	return __cpu_form1_relative_distance(cpu1_assoc, cpu2_assoc);
+	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 */

@@ -201,7 +245,9 @@ int __node_distance(int a, int b)
 	int i;
 	int distance = LOCAL_DISTANCE;
 
-	if (affinity_form == FORM0_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++) {

@@ -216,27 +262,6 @@ int __node_distance(int a, int b)
 }
 EXPORT_SYMBOL(__node_distance);
 
-/*
- * 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) >= primary_domain_index)
-		nid = of_read_number(&associativity[primary_domain_index], 1);
-
-	/* POWER4 LPAR uses 0xffff as invalid node */
-	if (nid == 0xffff || nid >= nr_node_ids)
-		nid = NUMA_NO_NODE;
-out:
-	return nid;
-}
-
 /* Returns the nid associated with the given device tree node,
  * or -1 if not found.
  */

@@ -304,12 +329,93 @@ static void initialize_form1_numa_distance(struct device_node *node)
  */
 void update_numa_distance(struct device_node *node)
 {
+	int nid;
+
 	if (affinity_form == FORM0_AFFINITY)
 		return;
 	else if (affinity_form == FORM1_AFFINITY) {
 		initialize_form1_numa_distance(node);
 		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);
+}
+
+/*
+ * ibm,numa-lookup-index-table= {N, domainid1, domainid2, ..... domainidN}
+ * ibm,numa-distance-table = { N, 1, 2, 4, 5, 1, 6, .... N elements}
+ */
+static void initialize_form2_numa_distance_lookup_table(void)
+{
+	int i, j;
+	struct device_node *root;
+	const __u8 *numa_dist_table;
+	const __be32 *numa_lookup_index;
+	int numa_dist_table_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 */
+	numa_dist_table = of_get_property(root, "ibm,numa-distance-table", NULL);
+	numa_dist_table_length = of_read_number((const __be32 *)&numa_dist_table[0], 1);
+	/* Skip the size which is encoded int */
+	numa_dist_table += sizeof(__be32);
+
+	pr_debug("numa_dist_table_len = %d, numa_dist_indexes_len = %d\n",
+		 numa_dist_table_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 (numa_dist_table_length != max_numa_index * max_numa_index) {
+
+		WARN(1, "Wrong NUMA distance information\n");
+		/* consider everybody else just remote. */
+		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];
+
+				if (nodeA == nodeB)
+					numa_distance_table[nodeA][nodeB] = LOCAL_DISTANCE;
+				else
+					numa_distance_table[nodeA][nodeB] = REMOTE_DISTANCE;
+			}
+		}
+	}
+
+	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];
+
+			numa_distance_table[nodeA][nodeB] = numa_dist_table[distance_index++];
+			pr_debug("dist[%d][%d]=%d ", nodeA, nodeB, numa_distance_table[nodeA][nodeB]);
+		}
+	}
+	of_node_put(root);
 }
 
 static int __init find_primary_domain_index(void)