[PATCH] hugepage: Small fixes to hugepage clear/copy path

Move the loops used in mm/hugetlb.c to clear and copy hugepages to their
own functions for clarity.  As we do so, we add some checks of need_resched
- we are, after all copying megabytes of memory here.  We also add
might_sleep() accordingly.  We generally dropped locks around the clear and
copy, already but not everyone has PREEMPT enabled, so we should still be
checking explicitly.

For this to work, we need to remove the clear_huge_page() from
alloc_huge_page(), which is called with the page_table_lock held in the COW
path.  We move the clear_huge_page() to just after the alloc_huge_page() in
the hugepage no-page path.  In the COW path, the new page is about to be
copied over, so clearing it was just a waste of time anyway.  So as a side
effect we also fix the fact that we held the page_table_lock for far too
long in this path by calling alloc_huge_page() under it.

It causes no regressions on the libhugetlbfs testsuite (ppc64, POWER5).

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 783098f..41b1038 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -27,6 +27,29 @@
 static unsigned int nr_huge_pages_node[MAX_NUMNODES];
 static unsigned int free_huge_pages_node[MAX_NUMNODES];
 
+static void clear_huge_page(struct page *page, unsigned long addr)
+{
+	int i;
+
+	might_sleep();
+	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) {
+		cond_resched();
+		clear_user_highpage(page + i, addr);
+	}
+}
+
+static void copy_huge_page(struct page *dst, struct page *src,
+			   unsigned long addr)
+{
+	int i;
+
+	might_sleep();
+	for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) {
+		cond_resched();
+		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE);
+	}
+}
+
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
  */
@@ -98,7 +121,6 @@
 struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr)
 {
 	struct page *page;
-	int i;
 
 	spin_lock(&hugetlb_lock);
 	page = dequeue_huge_page(vma, addr);
@@ -108,8 +130,6 @@
 	}
 	spin_unlock(&hugetlb_lock);
 	set_page_refcounted(page);
-	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); ++i)
-		clear_user_highpage(&page[i], addr);
 	return page;
 }
 
@@ -367,7 +387,7 @@
 			unsigned long address, pte_t *ptep, pte_t pte)
 {
 	struct page *old_page, *new_page;
-	int i, avoidcopy;
+	int avoidcopy;
 
 	old_page = pte_page(pte);
 
@@ -388,9 +408,7 @@
 	}
 
 	spin_unlock(&mm->page_table_lock);
-	for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++)
-		copy_user_highpage(new_page + i, old_page + i,
-				   address + i*PAGE_SIZE);
+	copy_huge_page(new_page, old_page, address);
 	spin_lock(&mm->page_table_lock);
 
 	ptep = huge_pte_offset(mm, address & HPAGE_MASK);
@@ -435,6 +453,7 @@
 			ret = VM_FAULT_OOM;
 			goto out;
 		}
+		clear_huge_page(page, address);
 
 		if (vma->vm_flags & VM_SHARED) {
 			int err;