diff options
author | Andy Whitcroft <apw@shadowen.org> | 2008-11-07 00:06:24 +0000 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@suse.de> | 2008-11-13 09:55:56 -0800 |
commit | 70e6b95d14d2f7f5202be36a808e7085a0f4ea96 (patch) | |
tree | b5dceb1d544d9403c597756ce7c6b4441d7f21a3 | |
parent | 75187a3094a68015582b344161c18b86ab60e665 (diff) | |
download | lwn-70e6b95d14d2f7f5202be36a808e7085a0f4ea96.tar.gz lwn-70e6b95d14d2f7f5202be36a808e7085a0f4ea96.zip |
hugetlbfs: handle pages higher order than MAX_ORDER
commit 69d177c2fc702d402b17fdca2190d5a7e3ca55c5 upstream
When working with hugepages, hugetlbfs assumes that those hugepages are
smaller than MAX_ORDER. Specifically it assumes that the mem_map is
contigious and uses that to optimise access to the elements of the mem_map
that represent the hugepage. Gigantic pages (such as 16GB pages on
powerpc) by definition are of greater order than MAX_ORDER (larger than
MAX_ORDER_NR_PAGES in size). This means that we can no longer make use of
the buddy alloctor guarentees for the contiguity of the mem_map, which
ensures that the mem_map is at least contigious for maximmally aligned
areas of MAX_ORDER_NR_PAGES pages.
This patch adds new mem_map accessors and iterator helpers which handle
any discontiguity at MAX_ORDER_NR_PAGES boundaries. It then uses these to
implement gigantic page versions of copy_huge_page and clear_huge_page,
and to allow follow_hugetlb_page handle gigantic pages.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Cc: Jon Tollefson <kniht@linux.vnet.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r-- | mm/hugetlb.c | 37 | ||||
-rw-r--r-- | mm/internal.h | 28 |
2 files changed, 64 insertions, 1 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9dbda3b5b86d..77427c8443a8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -353,11 +353,26 @@ static int vma_has_reserves(struct vm_area_struct *vma) return 0; } +static void clear_gigantic_page(struct page *page, + unsigned long addr, unsigned long sz) +{ + int i; + struct page *p = page; + + might_sleep(); + for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) { + cond_resched(); + clear_user_highpage(p, addr + i * PAGE_SIZE); + } +} static void clear_huge_page(struct page *page, unsigned long addr, unsigned long sz) { int i; + if (unlikely(sz > MAX_ORDER_NR_PAGES)) + return clear_gigantic_page(page, addr, sz); + might_sleep(); for (i = 0; i < sz/PAGE_SIZE; i++) { cond_resched(); @@ -365,12 +380,32 @@ static void clear_huge_page(struct page *page, } } +static void copy_gigantic_page(struct page *dst, struct page *src, + unsigned long addr, struct vm_area_struct *vma) +{ + int i; + struct hstate *h = hstate_vma(vma); + struct page *dst_base = dst; + struct page *src_base = src; + might_sleep(); + for (i = 0; i < pages_per_huge_page(h); ) { + cond_resched(); + copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} static void copy_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma) { int i; struct hstate *h = hstate_vma(vma); + if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) + return copy_gigantic_page(dst, src, addr, vma); + might_sleep(); for (i = 0; i < pages_per_huge_page(h); i++) { cond_resched(); @@ -2113,7 +2148,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, same_page: if (pages) { get_page(page); - pages[i] = page + pfn_offset; + pages[i] = mem_map_offset(page, pfn_offset); } if (vmas) diff --git a/mm/internal.h b/mm/internal.h index daff45047b14..92729ea9dc8c 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -54,6 +54,34 @@ static inline unsigned long page_order(struct page *page) } /* + * Return the mem_map entry representing the 'offset' subpage within + * the maximally aligned gigantic page 'base'. Handle any discontiguity + * in the mem_map at MAX_ORDER_NR_PAGES boundaries. + */ +static inline struct page *mem_map_offset(struct page *base, int offset) +{ + if (unlikely(offset >= MAX_ORDER_NR_PAGES)) + return pfn_to_page(page_to_pfn(base) + offset); + return base + offset; +} + +/* + * Iterator over all subpages withing the maximally aligned gigantic + * page 'base'. Handle any discontiguity in the mem_map. + */ +static inline struct page *mem_map_next(struct page *iter, + struct page *base, int offset) +{ + if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) { + unsigned long pfn = page_to_pfn(base) + offset; + if (!pfn_valid(pfn)) + return NULL; + return pfn_to_page(pfn); + } + return iter + 1; +} + +/* * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node, * so all functions starting at paging_init should be marked __init * in those cases. SPARSEMEM, however, allows for memory hotplug, |