mm, hugetlb: return a reserved page to a reserved pool if failed

If we fail with a reserved page, just calling put_page() is not
sufficient, because put_page() invoke free_huge_page() at last step and it
doesn't know whether a page comes from a reserved pool or not.  So it
doesn't do anything related to reserved count.  This makes reserve count
lower than how we need, because reserve count already decrease in
dequeue_huge_page_vma().  This patch fix this situation.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Hillf Danton <dhillf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5bf6468..0631556 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -572,6 +572,7 @@ retry_cpuset:
                                if (!vma_has_reserves(vma, chg))
                                        break;
 
+                               SetPagePrivate(page);
                                h->resv_huge_pages--;
                                break;
                        }
@@ -629,15 +630,20 @@ static void free_huge_page(struct page *page)
        int nid = page_to_nid(page);
        struct hugepage_subpool *spool =
                (struct hugepage_subpool *)page_private(page);
+       bool restore_reserve;
 
        set_page_private(page, 0);
        page->mapping = NULL;
        BUG_ON(page_count(page));
        BUG_ON(page_mapcount(page));
+       restore_reserve = PagePrivate(page);
 
        spin_lock(&hugetlb_lock);
        hugetlb_cgroup_uncharge_page(hstate_index(h),
                                     pages_per_huge_page(h), page);
+       if (restore_reserve)
+               h->resv_huge_pages++;
+
        if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
                /* remove the page from active list */
                list_del(&page->lru);
@@ -2636,6 +2642,8 @@ retry_avoidcopy:
        spin_lock(&mm->page_table_lock);
        ptep = huge_pte_offset(mm, address & huge_page_mask(h));
        if (likely(pte_same(huge_ptep_get(ptep), pte))) {
+               ClearPagePrivate(new_page);
+
                /* Break COW */
                huge_ptep_clear_flush(vma, address, ptep);
                set_huge_pte_at(mm, address, ptep,
@@ -2747,6 +2755,7 @@ retry:
                                        goto retry;
                                goto out;
                        }
+                       ClearPagePrivate(page);
 
                        spin_lock(&inode->i_lock);
                        inode->i_blocks += blocks_per_huge_page(h);
@@ -2793,8 +2802,10 @@ retry:
        if (!huge_pte_none(huge_ptep_get(ptep)))
                goto backout;
 
-       if (anon_rmap)
+       if (anon_rmap) {
+               ClearPagePrivate(page);
                hugepage_add_new_anon_rmap(page, vma, address);
+       }
        else
                page_dup_rmap(page);
        new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)