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>

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index acd2010328f3044b1cf6dd788e4ac09ab9262925..85e0c58bdfdfa1dcdfbc8d7ecc1a59aa52152f5c 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -69,7 +69,6 @@ int dequeue_hwpoisoned_huge_page(struct page *page);
 bool isolate_huge_page(struct page *page, struct list_head *list);
 void putback_active_hugepage(struct page *page);
 bool is_hugepage_active(struct page *page);
-void copy_huge_page(struct page *dst, struct page *src);
 
 #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
@@ -140,9 +139,6 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page)
 #define isolate_huge_page(p, l) false
 #define putback_active_hugepage(p)     do {} while (0)
 #define is_hugepage_active(x)  false
-static inline void copy_huge_page(struct page *dst, struct page *src)
-{
-}
 
 static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
                unsigned long address, unsigned long end, pgprot_t newprot)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7d57af21f49e920776979dfe11023780ebff6afb..2130365d387d33f7820041d338b5f8e86243170f 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -476,40 +476,6 @@ static int vma_has_reserves(struct vm_area_struct *vma, long chg)
        return 0;
 }
 
-static void copy_gigantic_page(struct page *dst, struct page *src)
-{
-       int i;
-       struct hstate *h = page_hstate(src);
-       struct page *dst_base = dst;
-       struct page *src_base = src;
-
-       for (i = 0; i < pages_per_huge_page(h); ) {
-               cond_resched();
-               copy_highpage(dst, src);
-
-               i++;
-               dst = mem_map_next(dst, dst_base, i);
-               src = mem_map_next(src, src_base, i);
-       }
-}
-
-void copy_huge_page(struct page *dst, struct page *src)
-{
-       int i;
-       struct hstate *h = page_hstate(src);
-
-       if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
-               copy_gigantic_page(dst, src);
-               return;
-       }
-
-       might_sleep();
-       for (i = 0; i < pages_per_huge_page(h); i++) {
-               cond_resched();
-               copy_highpage(dst + i, src + i);
-       }
-}
-
 static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
        int nid = page_to_nid(page);

diff --git a/mm/migrate.c b/mm/migrate.c
index 316e720a2023c260b0205cdd2cd6be7d257986ac..bb940045fe8595842ed58f2e32f87b83d40485e1 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -441,6 +441,54 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
        return MIGRATEPAGE_SUCCESS;
 }
 
+/*
+ * 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
  */