summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/numa.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/mm/numa.c')
-rw-r--r--arch/powerpc/mm/numa.c117
1 files changed, 45 insertions, 72 deletions
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 9d5f710d2c20..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>
@@ -34,6 +34,7 @@
#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;
@@ -42,11 +43,9 @@ static char *cmdline __initdata;
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 primary_domain_index;
static int n_mem_addr_cells, n_mem_size_cells;
@@ -367,6 +366,7 @@ void update_numa_distance(struct device_node *node)
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}
@@ -894,7 +894,7 @@ 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;
@@ -956,7 +956,9 @@ static int __init parse_numa_properties(void)
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);
@@ -1006,6 +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
@@ -1079,27 +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;
@@ -1107,7 +1103,7 @@ 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;
+ struct device_node *rtas, *root;
const __be32 *domains = NULL;
int prop_length, max_nodes;
u32 i;
@@ -1128,10 +1124,12 @@ static void __init find_possible_nodes(void)
* If the LPAR is migratable, new nodes might be activated after a LPM,
* so we should consider the max number in that case.
*/
- if (!of_get_property(of_root, "ibm,migratable-partition", NULL))
+ 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);
@@ -1159,6 +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
@@ -1203,9 +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) {
@@ -1287,23 +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;
+ int i = 0;
- memcell_buf = of_get_property(memory, "reg", &len);
- if (!memcell_buf || len <= 0)
- continue;
-
- /* 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);
@@ -1346,7 +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;
@@ -1421,43 +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)
generated by cgit (git 2.34.1) at 2025-12-25 08:01:51 +0000