[PATCH 08/33] x86-64, NUMA: Use common {cpu|mem}_nodes_parsed

From: Tejun Heo
Date: Wed Feb 16 2011 - 07:21:35 EST


ACPI and amd are using separate nodes_parsed masks. Add
{cpu|mem}_nodes_parsed and use them in all NUMA init methods.
Initialization of the masks and building node_possible_map are now
handled commonly by initmem_init().

dummy_numa_init() is updated to set node 0 on both masks. While at
it, move the info messages from scan to init.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: Yinghai Lu <yinghai@xxxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Cyrill Gorcunov <gorcunov@xxxxxxxxx>
Cc: Shaohui Zheng <shaohui.zheng@xxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx>
---
arch/x86/include/asm/numa_64.h | 3 +++
arch/x86/mm/amdtopology_64.c | 10 ++++------
arch/x86/mm/numa_64.c | 25 ++++++++++++++++++-------
arch/x86/mm/srat_64.c | 17 ++++++-----------
4 files changed, 31 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 2819afa..de45936 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -27,6 +27,9 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
*/
#define NODE_MIN_SIZE (4*1024*1024)

+extern nodemask_t cpu_nodes_parsed __initdata;
+extern nodemask_t mem_nodes_parsed __initdata;
+
extern int __cpuinit numa_cpu_node(int cpu);

#ifdef CONFIG_NUMA_EMU
diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index 655ccff..4f822a2 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -28,7 +28,6 @@

static struct bootnode __initdata nodes[8];
static unsigned char __initdata nodeids[8];
-static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;

static __init int find_northbridge(void)
{
@@ -123,7 +122,7 @@ int __init amd_numa_init(void)
nodeid, (base >> 8) & 3, (limit >> 8) & 3);
return -EINVAL;
}
- if (node_isset(nodeid, nodes_parsed)) {
+ if (node_isset(nodeid, mem_nodes_parsed)) {
pr_info("Node %d already present, skipping\n",
nodeid);
continue;
@@ -173,7 +172,8 @@ int __init amd_numa_init(void)

prevbase = base;

- node_set(nodeid, nodes_parsed);
+ node_set(nodeid, mem_nodes_parsed);
+ node_set(nodeid, cpu_nodes_parsed);
}

if (!found)
@@ -190,7 +190,7 @@ void __init amd_get_nodes(struct bootnode *physnodes)
{
int i;

- for_each_node_mask(i, nodes_parsed) {
+ for_each_node_mask(i, mem_nodes_parsed) {
physnodes[i].start = nodes[i].start;
physnodes[i].end = nodes[i].end;
}
@@ -258,8 +258,6 @@ int __init amd_scan_nodes(void)
unsigned int apicid_base;
int i;

- BUG_ON(nodes_empty(nodes_parsed));
- node_possible_map = nodes_parsed;
memnode_shift = compute_hash_shift(nodes, 8, NULL);
if (memnode_shift < 0) {
pr_err("No NUMA node hash function found. Contact maintainer\n");
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index c984e34..4404e1d 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -25,6 +25,9 @@
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);

+nodemask_t cpu_nodes_parsed __initdata;
+nodemask_t mem_nodes_parsed __initdata;
+
struct memnode memnode;

static unsigned long __initdata nodemap_addr;
@@ -582,22 +585,23 @@ static int __init numa_emulation(unsigned long start_pfn,

static int dummy_numa_init(void)
{
- return 0;
-}
-
-static int dummy_scan_nodes(void)
-{
printk(KERN_INFO "%s\n",
numa_off ? "NUMA turned off" : "No NUMA configuration found");
printk(KERN_INFO "Faking a node at %016lx-%016lx\n",
0LU, max_pfn << PAGE_SHIFT);

+ node_set(0, cpu_nodes_parsed);
+ node_set(0, mem_nodes_parsed);
+
+ return 0;
+}
+
+static int dummy_scan_nodes(void)
+{
/* setup dummy node covering all memory */
memnode_shift = 63;
memnodemap = memnode.embedded_map;
memnodemap[0] = 0;
- node_set_online(0);
- node_set(0, node_possible_map);
memblock_x86_register_active_regions(0, 0, max_pfn);
init_memory_mapping_high();
setup_node_bootmem(0, 0, max_pfn << PAGE_SHIFT);
@@ -630,6 +634,8 @@ void __init initmem_init(void)
for (j = 0; j < MAX_LOCAL_APIC; j++)
set_apicid_to_node(j, NUMA_NO_NODE);

+ nodes_clear(cpu_nodes_parsed);
+ nodes_clear(mem_nodes_parsed);
nodes_clear(node_possible_map);
nodes_clear(node_online_map);

@@ -643,6 +649,11 @@ void __init initmem_init(void)
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
#endif
+ /* Account for nodes with cpus and no memory */
+ nodes_or(node_possible_map, mem_nodes_parsed, cpu_nodes_parsed);
+ if (WARN_ON(nodes_empty(node_possible_map)))
+ continue;
+
if (!scan_nodes[i]())
return;
}
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 597e011..33e72ec 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -28,8 +28,6 @@ int acpi_numa __initdata;

static struct acpi_table_slit *acpi_slit;

-static nodemask_t nodes_parsed __initdata;
-static nodemask_t cpu_nodes_parsed __initdata;
static struct bootnode nodes[MAX_NUMNODES] __initdata;
static struct bootnode nodes_add[MAX_NUMNODES];

@@ -293,7 +291,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)

if (!(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)) {
nd = &nodes[node];
- if (!node_test_and_set(node, nodes_parsed)) {
+ if (!node_test_and_set(node, mem_nodes_parsed)) {
nd->start = start;
nd->end = end;
} else {
@@ -319,7 +317,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
unsigned long pxmram, e820ram;

pxmram = 0;
- for_each_node_mask(i, nodes_parsed) {
+ for_each_node_mask(i, mem_nodes_parsed) {
unsigned long s = nodes[i].start >> PAGE_SHIFT;
unsigned long e = nodes[i].end >> PAGE_SHIFT;
pxmram += e - s;
@@ -348,7 +346,7 @@ void __init acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
{
int i;

- for_each_node_mask(i, nodes_parsed) {
+ for_each_node_mask(i, mem_nodes_parsed) {
cutoff_node(i, start, end);
physnodes[i].start = nodes[i].start;
physnodes[i].end = nodes[i].end;
@@ -449,9 +447,6 @@ int __init acpi_scan_nodes(void)

init_memory_mapping_high();

- /* Account for nodes with cpus and no memory */
- nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed);
-
/* Finally register nodes */
for_each_node_mask(i, node_possible_map)
setup_node_bootmem(i, nodes[i].start, nodes[i].end);
@@ -485,7 +480,7 @@ static int __init find_node_by_addr(unsigned long addr)
int ret = NUMA_NO_NODE;
int i;

- for_each_node_mask(i, nodes_parsed) {
+ for_each_node_mask(i, mem_nodes_parsed) {
/*
* Find the real node that this emulated node appears on. For
* the sake of simplicity, we only use a real node's starting
@@ -545,10 +540,10 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
__acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
memcpy(__apicid_to_node, fake_apicid_to_node, sizeof(__apicid_to_node));

- nodes_clear(nodes_parsed);
+ nodes_clear(mem_nodes_parsed);
for (i = 0; i < num_nodes; i++)
if (fake_nodes[i].start != fake_nodes[i].end)
- node_set(i, nodes_parsed);
+ node_set(i, mem_nodes_parsed);
}

static int null_slit_node_compare(int a, int b)
--
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/