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(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
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,
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;
{
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)
{
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;
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)
{
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++) {
}
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.
*/
}
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);
+}
+
+/*
+ * 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)
{
- int depth;
+ 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");
else
&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);
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) {
+ 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.
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);
+ const __be32 *associativity;
- 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]);
- }
+ 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;
/*
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;
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);
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");
+ 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
* 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);
}
* 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);
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);
static void __init find_possible_nodes(void)
{
struct device_node *rtas;
- const __be32 *domains;
+ const __be32 *domains = NULL;
int prop_length, max_nodes;
u32 i;
* 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);
+ if (!of_get_property(of_root, "ibm,migratable-partition", NULL))
+ domains = of_get_property(rtas,
+ "ibm,current-associativity-domains",
+ &prop_length);
if (!domains) {
domains = of_get_property(rtas, "ibm,max-associativity-domains",
&prop_length);
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:
if (strstr(p, "off"))
numa_enabled = 0;
- if (strstr(p, "debug"))
- numa_debug = 1;
-
p = strstr(p, "fake=");
if (p)
cmdline = p + strlen("fake=");
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:
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:
projects / linux-2.6-microblaze.git / blobdiff