[PATCH 11/33] x86-64, NUMA: Use common numa_nodes[]

From: Tejun Heo
Date: Wed Feb 16 2011 - 07:21:46 EST


ACPI and amd are using separate nodes[] array. Add numa_nodes[] and
use them in all NUMA init methods. cutoff_node() cleanup is moved
from srat_64.c to numa_64.c and applied in initmem_init() regardless
of init methods.

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 | 1 +
arch/x86/mm/amdtopology_64.c | 19 ++++++++---------
arch/x86/mm/numa_64.c | 24 ++++++++++++++++++++++
arch/x86/mm/srat_64.c | 43 ++++++++++-----------------------------
4 files changed, 45 insertions(+), 42 deletions(-)

diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index de45936..d3a4514 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -29,6 +29,7 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,

extern nodemask_t cpu_nodes_parsed __initdata;
extern nodemask_t mem_nodes_parsed __initdata;
+extern struct bootnode numa_nodes[MAX_NUMNODES] __initdata;

extern int __cpuinit numa_cpu_node(int cpu);

diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index b6029a6..f049fa6 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -26,7 +26,6 @@
#include <asm/apic.h>
#include <asm/amd_nb.h>

-static struct bootnode __initdata nodes[8];
static unsigned char __initdata nodeids[8];

static __init int find_northbridge(void)
@@ -166,8 +165,8 @@ int __init amd_numa_init(void)
pr_info("Node %d MemBase %016lx Limit %016lx\n",
nodeid, base, limit);

- nodes[nodeid].start = base;
- nodes[nodeid].end = limit;
+ numa_nodes[nodeid].start = base;
+ numa_nodes[nodeid].end = limit;

prevbase = base;

@@ -210,8 +209,8 @@ void __init amd_get_nodes(struct bootnode *physnodes)
int i;

for_each_node_mask(i, mem_nodes_parsed) {
- physnodes[i].start = nodes[i].start;
- physnodes[i].end = nodes[i].end;
+ physnodes[i].start = numa_nodes[i].start;
+ physnodes[i].end = numa_nodes[i].end;
}
}

@@ -221,7 +220,7 @@ static int __init find_node_by_addr(unsigned long addr)
int i;

for (i = 0; i < 8; i++)
- if (addr >= nodes[i].start && addr < nodes[i].end) {
+ if (addr >= numa_nodes[i].start && addr < numa_nodes[i].end) {
ret = i;
break;
}
@@ -274,7 +273,7 @@ int __init amd_scan_nodes(void)
{
int i;

- memnode_shift = compute_hash_shift(nodes, 8, NULL);
+ memnode_shift = compute_hash_shift(numa_nodes, 8, NULL);
if (memnode_shift < 0) {
pr_err("No NUMA node hash function found. Contact maintainer\n");
return -1;
@@ -284,11 +283,11 @@ int __init amd_scan_nodes(void)
/* use the coreid bits from early_identify_cpu */
for_each_node_mask(i, node_possible_map)
memblock_x86_register_active_regions(i,
- nodes[i].start >> PAGE_SHIFT,
- nodes[i].end >> PAGE_SHIFT);
+ numa_nodes[i].start >> PAGE_SHIFT,
+ numa_nodes[i].end >> PAGE_SHIFT);
init_memory_mapping_high();
for_each_node_mask(i, node_possible_map)
- setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+ setup_node_bootmem(i, numa_nodes[i].start, numa_nodes[i].end);

numa_init_array();
return 0;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 4404e1d..a6b899f 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -33,6 +33,8 @@ struct memnode memnode;
static unsigned long __initdata nodemap_addr;
static unsigned long __initdata nodemap_size;

+struct bootnode numa_nodes[MAX_NUMNODES] __initdata;
+
/*
* Given a shift value, try to populate memnodemap[]
* Returns :
@@ -182,6 +184,22 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
return NULL;
}

+static __init void cutoff_node(int i, unsigned long start, unsigned long end)
+{
+ struct bootnode *nd = &numa_nodes[i];
+
+ if (nd->start < start) {
+ nd->start = start;
+ if (nd->end < nd->start)
+ nd->start = nd->end;
+ }
+ if (nd->end > end) {
+ nd->end = end;
+ if (nd->start > nd->end)
+ nd->start = nd->end;
+ }
+}
+
/* Initialize bootmem allocator for a node */
void __init
setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
@@ -638,9 +656,15 @@ void __init initmem_init(void)
nodes_clear(mem_nodes_parsed);
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
+ memset(numa_nodes, 0, sizeof(numa_nodes));

if (numa_init[i]() < 0)
continue;
+
+ /* clean up the node list */
+ for (j = 0; j < MAX_NUMNODES; j++)
+ cutoff_node(j, 0, max_pfn << PAGE_SHIFT);
+
#ifdef CONFIG_NUMA_EMU
setup_physnodes(0, max_pfn << PAGE_SHIFT, i == 0, i == 1);
if (cmdline && !numa_emulation(0, max_pfn, i == 0, i == 1))
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 33e72ec..bfa4a6a 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -28,7 +28,6 @@ int acpi_numa __initdata;

static struct acpi_table_slit *acpi_slit;

-static struct bootnode nodes[MAX_NUMNODES] __initdata;
static struct bootnode nodes_add[MAX_NUMNODES];

static int num_node_memblks __initdata;
@@ -55,29 +54,13 @@ static __init int conflicting_memblks(unsigned long start, unsigned long end)
return -1;
}

-static __init void cutoff_node(int i, unsigned long start, unsigned long end)
-{
- struct bootnode *nd = &nodes[i];
-
- if (nd->start < start) {
- nd->start = start;
- if (nd->end < nd->start)
- nd->start = nd->end;
- }
- if (nd->end > end) {
- nd->end = end;
- if (nd->start > nd->end)
- nd->start = nd->end;
- }
-}
-
static __init void bad_srat(void)
{
int i;
printk(KERN_ERR "SRAT: SRAT not used.\n");
acpi_numa = -1;
for (i = 0; i < MAX_NUMNODES; i++) {
- nodes[i].start = nodes[i].end = 0;
+ numa_nodes[i].start = numa_nodes[i].end = 0;
nodes_add[i].start = nodes_add[i].end = 0;
}
remove_all_active_ranges();
@@ -276,12 +259,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
if (i == node) {
printk(KERN_WARNING
"SRAT: Warning: PXM %d (%lx-%lx) overlaps with itself (%Lx-%Lx)\n",
- pxm, start, end, nodes[i].start, nodes[i].end);
+ pxm, start, end, numa_nodes[i].start, numa_nodes[i].end);
} else if (i >= 0) {
printk(KERN_ERR
"SRAT: PXM %d (%lx-%lx) overlaps with PXM %d (%Lx-%Lx)\n",
pxm, start, end, node_to_pxm(i),
- nodes[i].start, nodes[i].end);
+ numa_nodes[i].start, numa_nodes[i].end);
bad_srat();
return;
}
@@ -290,7 +273,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
start, end);

if (!(ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)) {
- nd = &nodes[node];
+ nd = &numa_nodes[node];
if (!node_test_and_set(node, mem_nodes_parsed)) {
nd->start = start;
nd->end = end;
@@ -347,9 +330,8 @@ void __init acpi_get_nodes(struct bootnode *physnodes, unsigned long start,
int i;

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;
+ physnodes[i].start = numa_nodes[i].start;
+ physnodes[i].end = numa_nodes[i].end;
}
}
#endif /* CONFIG_NUMA_EMU */
@@ -372,10 +354,6 @@ int __init acpi_scan_nodes(void)
if (acpi_numa <= 0)
return -1;

- /* First clean up the node list */
- for (i = 0; i < MAX_NUMNODES; i++)
- cutoff_node(i, 0, max_pfn << PAGE_SHIFT);
-
/*
* Join together blocks on the same node, holes between
* which don't overlap with memory on other nodes.
@@ -440,7 +418,7 @@ int __init acpi_scan_nodes(void)

/* for out of order entries in SRAT */
sort_node_map();
- if (!nodes_cover_memory(nodes)) {
+ if (!nodes_cover_memory(numa_nodes)) {
bad_srat();
return -1;
}
@@ -449,12 +427,13 @@ int __init acpi_scan_nodes(void)

/* Finally register nodes */
for_each_node_mask(i, node_possible_map)
- setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+ setup_node_bootmem(i, numa_nodes[i].start, numa_nodes[i].end);
/* Try again in case setup_node_bootmem missed one due
to missing bootmem */
for_each_node_mask(i, node_possible_map)
if (!node_online(i))
- setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+ setup_node_bootmem(i, numa_nodes[i].start,
+ numa_nodes[i].end);

for (i = 0; i < nr_cpu_ids; i++) {
int node = early_cpu_to_node(i);
@@ -486,7 +465,7 @@ static int __init find_node_by_addr(unsigned long addr)
* the sake of simplicity, we only use a real node's starting
* address to determine which emulated node it appears on.
*/
- if (addr >= nodes[i].start && addr < nodes[i].end) {
+ if (addr >= numa_nodes[i].start && addr < numa_nodes[i].end) {
ret = i;
break;
}
--
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/