hugetlbfs: handle pages higher order than MAX_ORDER

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>
Cc: <stable@kernel.org>		[2.6.27.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/hugetlb.c

@@ -354,11 +354,26 @@ 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();
@@ -366,12 +381,32 @@ 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();
@@ -2130,7 +2165,7 @@ same_page:
 			if (zeropage_ok)
 				pages[i] = ZERO_PAGE(0);
 			else
-				pages[i] = page + pfn_offset;
+				pages[i] = mem_map_offset(page, pfn_offset);
 			get_page(pages[i]);
 		}
 

mm/internal.h

@@ -175,6 +175,34 @@ static inline void free_page_mlock(struct page *page) { }
 
 #endif /* CONFIG_UNEVICTABLE_LRU */
 
+/*
+ * 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