2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Written by Pat Gaughen (gone@us.ibm.com) Mar 2002
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _ASM_MMZONE_H_
|
|
|
|
#define _ASM_MMZONE_H_
|
|
|
|
|
|
|
|
#include <asm/smp.h>
|
|
|
|
|
2005-07-08 08:56:39 +08:00
|
|
|
#ifdef CONFIG_NUMA
|
2005-06-23 15:07:57 +08:00
|
|
|
extern struct pglist_data *node_data[];
|
|
|
|
#define NODE_DATA(nid) (node_data[nid])
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-07-08 08:56:39 +08:00
|
|
|
#ifdef CONFIG_X86_NUMAQ
|
|
|
|
#include <asm/numaq.h>
|
|
|
|
#else /* summit or generic arch */
|
|
|
|
#include <asm/srat.h>
|
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-06-23 15:07:57 +08:00
|
|
|
extern int get_memcfg_numa_flat(void );
|
|
|
|
/*
|
|
|
|
* This allows any one NUMA architecture to be compiled
|
|
|
|
* for, and still fall back to the flat function if it
|
|
|
|
* fails.
|
|
|
|
*/
|
|
|
|
static inline void get_memcfg_numa(void)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_X86_NUMAQ
|
|
|
|
if (get_memcfg_numaq())
|
|
|
|
return;
|
2005-09-10 04:01:23 +08:00
|
|
|
#elif defined(CONFIG_ACPI_SRAT)
|
2005-06-23 15:07:57 +08:00
|
|
|
if (get_memcfg_from_srat())
|
|
|
|
return;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
get_memcfg_numa_flat();
|
|
|
|
}
|
|
|
|
|
2005-07-08 08:56:39 +08:00
|
|
|
extern int early_pfn_to_nid(unsigned long pfn);
|
|
|
|
|
2005-07-08 08:56:39 +08:00
|
|
|
#else /* !CONFIG_NUMA */
|
|
|
|
#define get_memcfg_numa get_memcfg_numa_flat
|
|
|
|
#define get_zholes_size(n) (0)
|
2005-06-23 15:07:57 +08:00
|
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
|
|
|
|
#ifdef CONFIG_DISCONTIGMEM
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* generic node memory support, the following assumptions apply:
|
|
|
|
*
|
|
|
|
* 1) memory comes in 256Mb contigious chunks which are either present or not
|
|
|
|
* 2) we will not have more than 64Gb in total
|
|
|
|
*
|
|
|
|
* for now assume that 64Gb is max amount of RAM for whole system
|
|
|
|
* 64Gb / 4096bytes/page = 16777216 pages
|
|
|
|
*/
|
|
|
|
#define MAX_NR_PAGES 16777216
|
|
|
|
#define MAX_ELEMENTS 256
|
|
|
|
#define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
|
|
|
|
|
|
|
|
extern s8 physnode_map[];
|
|
|
|
|
|
|
|
static inline int pfn_to_nid(unsigned long pfn)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
return((int) physnode_map[(pfn) / PAGES_PER_ELEMENT]);
|
|
|
|
#else
|
|
|
|
return 0;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
#define node_localnr(pfn, nid) ((pfn) - node_data[nid]->node_start_pfn)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Following are macros that each numa implmentation must define.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Given a kernel address, find the home node of the underlying memory.
|
|
|
|
*/
|
|
|
|
#define kvaddr_to_nid(kaddr) pfn_to_nid(__pa(kaddr) >> PAGE_SHIFT)
|
|
|
|
|
|
|
|
#define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn)
|
|
|
|
#define node_end_pfn(nid) \
|
|
|
|
({ \
|
|
|
|
pg_data_t *__pgdat = NODE_DATA(nid); \
|
|
|
|
__pgdat->node_start_pfn + __pgdat->node_spanned_pages; \
|
|
|
|
})
|
|
|
|
|
|
|
|
#define local_mapnr(kvaddr) \
|
|
|
|
({ \
|
|
|
|
unsigned long __pfn = __pa(kvaddr) >> PAGE_SHIFT; \
|
|
|
|
(__pfn - node_start_pfn(pfn_to_nid(__pfn))); \
|
|
|
|
})
|
|
|
|
|
|
|
|
/* XXX: FIXME -- wli */
|
|
|
|
#define kern_addr_valid(kaddr) (0)
|
|
|
|
|
|
|
|
#define pfn_to_page(pfn) \
|
|
|
|
({ \
|
|
|
|
unsigned long __pfn = pfn; \
|
|
|
|
int __node = pfn_to_nid(__pfn); \
|
[PATCH] remove non-DISCONTIG use of pgdat->node_mem_map
This patch effectively eliminates direct use of pgdat->node_mem_map outside
of the DISCONTIG code. On a flat memory system, these fields aren't
currently used, neither are they on a sparsemem system.
There was also a node_mem_map(nid) macro on many architectures. Its use
along with the use of ->node_mem_map itself was not consistent. It has
been removed in favor of two new, more explicit, arch-independent macros:
pgdat_page_nr(pgdat, pagenr)
nid_page_nr(nid, pagenr)
I called them "pgdat" and "nid" because we overload the term "node" to mean
"NUMA node", "DISCONTIG node" or "pg_data_t" in very confusing ways. I
believe the newer names are much clearer.
These macros can be overridden in the sparsemem case with a theoretically
slower operation using node_start_pfn and pfn_to_page(), instead. We could
make this the only behavior if people want, but I don't want to change too
much at once. One thing at a time.
This patch removes more code than it adds.
Compile tested on alpha, alpha discontig, arm, arm-discontig, i386, i386
generic, NUMAQ, Summit, ppc64, ppc64 discontig, and x86_64. Full list
here: http://sr71.net/patches/2.6.12/2.6.12-rc1-mhp2/configs/
Boot tested on NUMAQ, x86 SMP and ppc64 power4/5 LPARs.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin J. Bligh <mbligh@aracnet.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:07:37 +08:00
|
|
|
&NODE_DATA(__node)->node_mem_map[node_localnr(__pfn,__node)]; \
|
2005-04-17 06:20:36 +08:00
|
|
|
})
|
|
|
|
|
|
|
|
#define page_to_pfn(pg) \
|
|
|
|
({ \
|
|
|
|
struct page *__page = pg; \
|
|
|
|
struct zone *__zone = page_zone(__page); \
|
|
|
|
(unsigned long)(__page - __zone->zone_mem_map) \
|
|
|
|
+ __zone->zone_start_pfn; \
|
|
|
|
})
|
|
|
|
|
|
|
|
#ifdef CONFIG_X86_NUMAQ /* we have contiguous memory on NUMA-Q */
|
|
|
|
#define pfn_valid(pfn) ((pfn) < num_physpages)
|
|
|
|
#else
|
|
|
|
static inline int pfn_valid(int pfn)
|
|
|
|
{
|
|
|
|
int nid = pfn_to_nid(pfn);
|
|
|
|
|
|
|
|
if (nid >= 0)
|
|
|
|
return (pfn < node_end_pfn(nid));
|
|
|
|
return 0;
|
|
|
|
}
|
2005-06-23 15:07:57 +08:00
|
|
|
#endif /* CONFIG_X86_NUMAQ */
|
|
|
|
|
|
|
|
#endif /* CONFIG_DISCONTIGMEM */
|
|
|
|
|
|
|
|
#ifdef CONFIG_NEED_MULTIPLE_NODES
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
2005-06-23 15:07:57 +08:00
|
|
|
* Following are macros that are specific to this numa platform.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2005-06-23 15:07:57 +08:00
|
|
|
#define reserve_bootmem(addr, size) \
|
|
|
|
reserve_bootmem_node(NODE_DATA(0), (addr), (size))
|
|
|
|
#define alloc_bootmem(x) \
|
|
|
|
__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
|
|
|
|
#define alloc_bootmem_low(x) \
|
|
|
|
__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
|
|
|
|
#define alloc_bootmem_pages(x) \
|
|
|
|
__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
|
|
|
|
#define alloc_bootmem_low_pages(x) \
|
|
|
|
__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
|
|
|
|
#define alloc_bootmem_node(ignore, x) \
|
|
|
|
__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
|
|
|
|
#define alloc_bootmem_pages_node(ignore, x) \
|
|
|
|
__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
|
|
|
|
#define alloc_bootmem_low_pages_node(ignore, x) \
|
|
|
|
__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-06-23 15:07:57 +08:00
|
|
|
#endif /* CONFIG_NEED_MULTIPLE_NODES */
|
2005-06-23 15:07:52 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* _ASM_MMZONE_H_ */
|