diff options
| author | Bob Picco <bob.picco@hp.com> | 2006-06-28 12:54:55 -0400 |
|---|---|---|
| committer | Tony Luck <tony.luck@intel.com> | 2006-08-03 10:12:30 -0700 |
| commit | 921eea1cdf6ce7f0db88e4579474a04b1fb0fe6d (patch) | |
| tree | 51a9099562dffa2276100f1bff429cc5dc2e4118 /arch/ia64/mm/discontig.c | |
| parent | 0a69ca91be2b36f99a48daacd1f12d9d49ecaf87 (diff) | |
| download | blackbird-op-linux-921eea1cdf6ce7f0db88e4579474a04b1fb0fe6d.tar.gz blackbird-op-linux-921eea1cdf6ce7f0db88e4579474a04b1fb0fe6d.zip | |
[IA64] align high endpoint of VIRTUAL_MEM_MAP
Assure that vmem_map's high endpoint is MAX_ORDER aligned. Not doing so violates
the buddy allocator algorithm. Also anyone using mem=XXX on boot line and
not aligned to MAX_ORDER requires this patch in order to satisfy buddy
allocator. vmem_map always starts at pfn 0. The potentially large MAX_ORDER
on ia64 (due to hugetlbfs) requires that the end of vmem_map be aligned
to MAX_ORDER_NR_PAGES.
This was boot tested for: FLATMEM, FLATMEM+VIRTUAL_MEM_MAP,
DISCONTIGMEM+VIRTUAL_MEM_MAP and SPARSEMEM.
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Diffstat (limited to 'arch/ia64/mm/discontig.c')
| -rw-r--r-- | arch/ia64/mm/discontig.c | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 99bd9e30db96..8eeb669917fa 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -751,7 +751,8 @@ void __init paging_init(void) efi_memmap_walk(filter_rsvd_memory, count_node_pages); #ifdef CONFIG_VIRTUAL_MEM_MAP - vmalloc_end -= PAGE_ALIGN(max_low_pfn * sizeof(struct page)); + vmalloc_end -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) * + sizeof(struct page)); vmem_map = (struct page *) vmalloc_end; efi_memmap_walk(create_mem_map_page_table, NULL); printk("Virtual mem_map starts at 0x%p\n", vmem_map); |
