diff options
author | Christoph Lameter <clameter@sgi.com> | 2006-12-06 20:31:45 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@woody.osdl.org> | 2006-12-07 08:39:20 -0800 |
commit | 89689ae7f95995723fbcd5c116c47933a3bb8b13 (patch) | |
tree | 4d73ff59b557fa1a84c6064406ff101c76ff8adc /mm | |
parent | c0a499c2c42992cff097b38be29d2ba60d2fd99a (diff) | |
download | lwn-89689ae7f95995723fbcd5c116c47933a3bb8b13.tar.gz lwn-89689ae7f95995723fbcd5c116c47933a3bb8b13.zip |
[PATCH] Get rid of zone_table[]
The zone table is mostly not needed. If we have a node in the page flags
then we can get to the zone via NODE_DATA() which is much more likely to be
already in the cpu cache.
In case of SMP and UP NODE_DATA() is a constant pointer which allows us to
access an exact replica of zonetable in the node_zones field. In all of
the above cases there will be no need at all for the zone table.
The only remaining case is if in a NUMA system the node numbers do not fit
into the page flags. In that case we make sparse generate a table that
maps sections to nodes and use that table to to figure out the node number.
This table is sized to fit in a single cache line for the known 32 bit
NUMA platform which makes it very likely that the information can be
obtained without a cache miss.
For sparsemem the zone table seems to be have been fairly large based on
the maximum possible number of sections and the number of zones per node.
There is some memory saving by removing zone_table. The main benefit is to
reduce the cache foootprint of the VM from the frequent lookups of zones.
Plus it simplifies the page allocator.
[akpm@osdl.org: build fix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'mm')
-rw-r--r-- | mm/memory_hotplug.c | 1 | ||||
-rw-r--r-- | mm/page_alloc.c | 22 | ||||
-rw-r--r-- | mm/sparse.c | 23 |
3 files changed, 23 insertions, 23 deletions
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fd678a662eae..0c055a090f4d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -72,7 +72,6 @@ static int __add_zone(struct zone *zone, unsigned long phys_start_pfn) return ret; } memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn); - zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages); return 0; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 08360aa111f9..23bc5bcbdcf9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -83,13 +83,6 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { EXPORT_SYMBOL(totalram_pages); -/* - * Used by page_zone() to look up the address of the struct zone whose - * id is encoded in the upper bits of page->flags - */ -struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly; -EXPORT_SYMBOL(zone_table); - static char *zone_names[MAX_NR_ZONES] = { "DMA", #ifdef CONFIG_ZONE_DMA32 @@ -1715,20 +1708,6 @@ void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone, } } -#define ZONETABLE_INDEX(x, zone_nr) ((x << ZONES_SHIFT) | zone_nr) -void zonetable_add(struct zone *zone, int nid, enum zone_type zid, - unsigned long pfn, unsigned long size) -{ - unsigned long snum = pfn_to_section_nr(pfn); - unsigned long end = pfn_to_section_nr(pfn + size); - - if (FLAGS_HAS_NODE) - zone_table[ZONETABLE_INDEX(nid, zid)] = zone; - else - for (; snum <= end; snum++) - zone_table[ZONETABLE_INDEX(snum, zid)] = zone; -} - #ifndef __HAVE_ARCH_MEMMAP_INIT #define memmap_init(size, nid, zone, start_pfn) \ memmap_init_zone((size), (nid), (zone), (start_pfn)) @@ -2421,7 +2400,6 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, if (!size) continue; - zonetable_add(zone, nid, j, zone_start_pfn, size); ret = init_currently_empty_zone(zone, zone_start_pfn, size); BUG_ON(ret); zone_start_pfn += size; diff --git a/mm/sparse.c b/mm/sparse.c index b3c82ba30012..158d6a2a5263 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -24,6 +24,25 @@ struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT] #endif EXPORT_SYMBOL(mem_section); +#ifdef NODE_NOT_IN_PAGE_FLAGS +/* + * If we did not store the node number in the page then we have to + * do a lookup in the section_to_node_table in order to find which + * node the page belongs to. + */ +#if MAX_NUMNODES <= 256 +static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned; +#else +static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned; +#endif + +unsigned long page_to_nid(struct page *page) +{ + return section_to_node_table[page_to_section(page)]; +} +EXPORT_SYMBOL(page_to_nid); +#endif + #ifdef CONFIG_SPARSEMEM_EXTREME static struct mem_section *sparse_index_alloc(int nid) { @@ -49,6 +68,10 @@ static int sparse_index_init(unsigned long section_nr, int nid) struct mem_section *section; int ret = 0; +#ifdef NODE_NOT_IN_PAGE_FLAGS + section_to_node_table[section_nr] = nid; +#endif + if (mem_section[root]) return -EEXIST; |