powerpc/pseries: Add support for FORM2 associativity

PAPR interface currently supports two different ways of communicating resource
grouping details to the OS. These are referred to as Form 0 and Form 1
associativity grouping. Form 0 is the older format and is now considered
deprecated. This patch adds another resource grouping named FORM2.

Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210812132223.225214-6-aneesh.kumar@linux.ibm.com

1 files changed, 152 insertions, 35 deletions

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index fe3a9a38eddf..fe9c6ced40b2 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -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 +171,54 @@ static void unmap_cpu_from_node(unsigned long cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
+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;
@@ -186,8 +239,9 @@ 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 +255,9 @@ 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++) {
@@ -216,37 +272,6 @@ int __node_distance(int a, int b)
 }
 EXPORT_SYMBOL(__node_distance);
 
-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);
-}
-
 /* Returns the nid associated with the given device tree node,
  * or -1 if not found.
  */
@@ -320,6 +345,8 @@ static void initialize_form1_numa_distance(const __be32 *associativity)
  */
 void update_numa_distance(struct device_node *node)
 {
+	int nid;
+
 	if (affinity_form == FORM0_AFFINITY)
 		return;
 	else if (affinity_form == FORM1_AFFINITY) {
@@ -332,6 +359,84 @@ void update_numa_distance(struct device_node *node)
 		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);
+}
+
+/*
+ * 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)
@@ -344,6 +449,9 @@ static int __init find_primary_domain_index(void)
 	 */
 	if (firmware_has_feature(FW_FEATURE_OPAL)) {
 		affinity_form = FORM1_AFFINITY;
+	} else if (firmware_has_feature(FW_FEATURE_FORM2_AFFINITY)) {
+		dbg("Using form 2 affinity\n");
+		affinity_form = FORM2_AFFINITY;
 	} else if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY)) {
 		dbg("Using form 1 affinity\n");
 		affinity_form = FORM1_AFFINITY;
@@ -388,9 +496,12 @@ static int __init find_primary_domain_index(void)
 
 		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.
@@ -820,6 +931,12 @@ static int __init parse_numa_properties(void)
 	dbg("NUMA 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
 	 * init, we need to know the node ids now. This is because
 	 * each node to be onlined must have NODE_DATA etc backing it.