1 files changed, 21 insertions, 7 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7acd12503f7..5f34bd8dda3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -800,7 +800,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 
 	if (page && arch_prepare_hugepage(page)) {
 		__free_pages(page, huge_page_order(h));
-		return NULL;
+		page = NULL;
 	}
 
 	spin_lock(&hugetlb_lock);
@@ -2315,8 +2315,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * from page cache lookup which is in HPAGE_SIZE units.
 	 */
 	address = address & huge_page_mask(h);
-	pgoff = ((address - vma->vm_start) >> PAGE_SHIFT)
-		+ (vma->vm_pgoff >> PAGE_SHIFT);
+	pgoff = vma_hugecache_offset(h, vma, address);
 	mapping = (struct address_space *)page_private(page);
 
 	/*
@@ -2349,6 +2348,9 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 
 /*
  * Hugetlb_cow() should be called with page lock of the original hugepage held.
+ * Called with hugetlb_instantiation_mutex held and pte_page locked so we
+ * cannot race with other handlers or page migration.
+ * Keep the pte_same checks anyway to make transition from the mutex easier.
  */
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte,
@@ -2408,7 +2410,14 @@ retry_avoidcopy:
 				BUG_ON(page_count(old_page) != 1);
 				BUG_ON(huge_pte_none(pte));
 				spin_lock(&mm->page_table_lock);
-				goto retry_avoidcopy;
+				ptep = huge_pte_offset(mm, address & huge_page_mask(h));
+				if (likely(pte_same(huge_ptep_get(ptep), pte)))
+					goto retry_avoidcopy;
+				/*
+				 * race occurs while re-acquiring page_table_lock, and
+				 * our job is done.
+				 */
+				return 0;
 			}
 			WARN_ON_ONCE(1);
 		}
@@ -2499,6 +2508,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	struct hstate *h = hstate_vma(vma);
 	int ret = VM_FAULT_SIGBUS;
+	int anon_rmap = 0;
 	pgoff_t idx;
 	unsigned long size;
 	struct page *page;
@@ -2553,14 +2563,13 @@ retry:
 			spin_lock(&inode->i_lock);
 			inode->i_blocks += blocks_per_huge_page(h);
 			spin_unlock(&inode->i_lock);
-			page_dup_rmap(page);
 		} else {
 			lock_page(page);
 			if (unlikely(anon_vma_prepare(vma))) {
 				ret = VM_FAULT_OOM;
 				goto backout_unlocked;
 			}
-			hugepage_add_new_anon_rmap(page, vma, address);
+			anon_rmap = 1;
 		}
 	} else {
 		/*
@@ -2573,7 +2582,6 @@ retry:
 			      VM_FAULT_SET_HINDEX(h - hstates);
 			goto backout_unlocked;
 		}
-		page_dup_rmap(page);
 	}
 
 	/*
@@ -2597,6 +2605,10 @@ retry:
 	if (!huge_pte_none(huge_ptep_get(ptep)))
 		goto backout;
 
+	if (anon_rmap)
+		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)
 				&& (vma->vm_flags & VM_SHARED)));
 	set_huge_pte_at(mm, address, ptep, new_pte);
@@ -2630,6 +2642,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
 	struct hstate *h = hstate_vma(vma);
 
+	address &= huge_page_mask(h);
+
 	ptep = huge_pte_offset(mm, address);
 	if (ptep) {
 		entry = huge_ptep_get(ptep);