x86, mm: Fix node_possible_map logic

Recently there were some changes to the meaning of node_possible_map,
and it is quite strange:

- the node without memory would be set in node_possible_map
- but some node with less NODE_MIN_SIZE will be kicked out of node_possible_map.

fix it by adding strict_setup_node_bootmem().

Also, remove unparse_node().

so result will be:

1. cpu_to_node() will return online node only (nearest one)
2. apicid_to_node() still returns the node that could be not online but is set
   in node_possible_map.
3. node_possible_map will include nodes that mem on it are less NODE_MIN_SIZE

v2: after move_cpus_to_node change.

[ Impact: get node_possible_map right ]

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Tested-by: Jack Steiner <steiner@sgi.com>
LKML-Reference: <4A0C49BE.6080800@kernel.org>
[ v3: various small cleanups and comment clarifications ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Yinghai Lu 2009-05-15 13:59:37 -07:00 committed by Ingo Molnar
parent 888a589f6b
commit 7c43769a97
3 changed files with 19 additions and 30 deletions

View File

@ -24,6 +24,13 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
unsigned long end);
#ifdef CONFIG_NUMA
/*
* Too small node sizes may confuse the VM badly. Usually they
* result from BIOS bugs. So dont recognize nodes as standalone
* NUMA entities that have less than this amount of RAM listed:
*/
#define NODE_MIN_SIZE (4*1024*1024)
extern void __init init_cpu_to_node(void);
extern void __cpuinit numa_set_node(int cpu, int node);
extern void __cpuinit numa_clear_node(int cpu);

View File

@ -179,18 +179,25 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
}
/* Initialize bootmem allocator for a node */
void __init setup_node_bootmem(int nodeid, unsigned long start,
unsigned long end)
void __init
setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
{
unsigned long start_pfn, last_pfn, bootmap_pages, bootmap_size;
const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
unsigned long bootmap_start, nodedata_phys;
void *bootmap;
const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
int nid;
if (!end)
return;
/*
* Don't confuse VM with a node that doesn't have the
* minimum amount of memory:
*/
if (end && (end - start) < NODE_MIN_SIZE)
return;
start = roundup(start, ZONE_ALIGN);
printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,

View File

@ -36,10 +36,6 @@ static int num_node_memblks __initdata;
static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata;
static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata;
/* Too small nodes confuse the VM badly. Usually they result
from BIOS bugs. */
#define NODE_MIN_SIZE (4*1024*1024)
static __init int setup_node(int pxm)
{
return acpi_map_pxm_to_node(pxm);
@ -338,17 +334,6 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
return 1;
}
static void __init unparse_node(int node)
{
int i;
node_clear(node, nodes_parsed);
node_clear(node, cpu_nodes_parsed);
for (i = 0; i < MAX_LOCAL_APIC; i++) {
if (apicid_to_node[i] == node)
apicid_to_node[i] = NUMA_NO_NODE;
}
}
void __init acpi_numa_arch_fixup(void) {}
/* Use the information discovered above to actually set up the nodes. */
@ -360,18 +345,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
return -1;
/* First clean up the node list */
for (i = 0; i < MAX_NUMNODES; i++) {
for (i = 0; i < MAX_NUMNODES; i++)
cutoff_node(i, start, end);
/*
* don't confuse VM with a node that doesn't have the
* minimum memory.
*/
if (nodes[i].end &&
(nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) {
unparse_node(i);
node_set_offline(i);
}
}
if (!nodes_cover_memory(nodes)) {
bad_srat();
@ -404,7 +379,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
if (node == NUMA_NO_NODE)
continue;
if (!node_isset(node, node_possible_map))
if (!node_online(node))
numa_clear_node(i);
}
numa_init_array();