mm: thp: give transparent hugepage code a separate copy_page

Right now, the migration code in migrate_page_copy() uses copy_huge_page()
for hugetlbfs and thp pages:

       if (PageHuge(page) || PageTransHuge(page))
                copy_huge_page(newpage, page);

So, yay for code reuse.  But:

  void copy_huge_page(struct page *dst, struct page *src)
  {
        struct hstate *h = page_hstate(src);

and a non-hugetlbfs page has no page_hstate().  This works 99% of the
time because page_hstate() determines the hstate from the page order
alone.  Since the page order of a THP page matches the default hugetlbfs
page order, it works.

But, if you change the default huge page size on the boot command-line
(say default_hugepagesz=1G), then we might not even *have* a 2MB hstate
so page_hstate() returns null and copy_huge_page() oopses pretty fast
since copy_huge_page() dereferences the hstate:

  void copy_huge_page(struct page *dst, struct page *src)
  {
        struct hstate *h = page_hstate(src);
        if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
  ...

Mel noticed that the migration code is really the only user of these
functions.  This moves all the copy code over to migrate.c and makes
copy_huge_page() work for THP by checking for it explicitly.

I believe the bug was introduced in commit b32967ff101a ("mm: numa: Add
THP migration for the NUMA working set scanning fault case")

[akpm@linux-foundation.org: fix coding-style and comment text, per Naoya Horiguchi]
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Tested-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 48 insertions, 0 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 316e720a2023..bb940045fe85 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -442,6 +442,54 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 }
 
 /*
+ * Gigantic pages are so large that we do not guarantee that page++ pointer
+ * arithmetic will work across the entire page.  We need something more
+ * specialized.
+ */
+static void __copy_gigantic_page(struct page *dst, struct page *src,
+				int nr_pages)
+{
+	int i;
+	struct page *dst_base = dst;
+	struct page *src_base = src;
+
+	for (i = 0; i < nr_pages; ) {
+		cond_resched();
+		copy_highpage(dst, src);
+
+		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)
+{
+	int i;
+	int nr_pages;
+
+	if (PageHuge(src)) {
+		/* hugetlbfs page */
+		struct hstate *h = page_hstate(src);
+		nr_pages = pages_per_huge_page(h);
+
+		if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
+			__copy_gigantic_page(dst, src, nr_pages);
+			return;
+		}
+	} else {
+		/* thp page */
+		BUG_ON(!PageTransHuge(src));
+		nr_pages = hpage_nr_pages(src);
+	}
+
+	for (i = 0; i < nr_pages; i++) {
+		cond_resched();
+		copy_highpage(dst + i, src + i);
+	}
+}
+
+/*
  * Copy the page to its new location
  */
 void migrate_page_copy(struct page *newpage, struct page *page)