From: Peter Xu <peterx@redhat.com>
Subject: mm-check-against-orig_pte-for-finish_fault-fix

fix crash reported by Marek

Link: https://lkml.kernel.org/r/Ylb9rXJyPm8/ao8f@xz-m1.local
Signed-off-by: Peter Xu <peterx@redhat.com>
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/mm_types.h |    3 +++
 mm/memory.c              |   20 ++++++++++++--------
 2 files changed, 15 insertions(+), 8 deletions(-)

--- a/include/linux/mm_types.h~mm-check-against-orig_pte-for-finish_fault-fix
+++ a/include/linux/mm_types.h
@@ -815,6 +815,8 @@ typedef struct {
  * @FAULT_FLAG_UNSHARE: The fault is an unsharing request to unshare (and mark
  *                      exclusive) a possibly shared anonymous page that is
  *                      mapped R/O.
+ * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached.
+ *                        We should only access orig_pte if this flag set.
  *
  * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify
  * whether we would allow page faults to retry by specifying these two
@@ -851,6 +853,7 @@ enum fault_flag {
 	FAULT_FLAG_INSTRUCTION =	1 << 8,
 	FAULT_FLAG_INTERRUPTIBLE =	1 << 9,
 	FAULT_FLAG_UNSHARE =		1 << 10,
+	FAULT_FLAG_ORIG_PTE_VALID =	1 << 11,
 };
 
 #endif /* _LINUX_MM_TYPES_H */
--- a/mm/memory.c~mm-check-against-orig_pte-for-finish_fault-fix
+++ a/mm/memory.c
@@ -4179,6 +4179,15 @@ void do_set_pte(struct vm_fault *vmf, st
 	set_pte_at(vma->vm_mm, addr, vmf->pte, entry);
 }
 
+static bool vmf_pte_changed(struct vm_fault *vmf)
+{
+	if (vmf->flags & FAULT_FLAG_ORIG_PTE_VALID) {
+		return !pte_same(*vmf->pte, vmf->orig_pte);
+	}
+
+	return !pte_none(*vmf->pte);
+}
+
 /**
  * finish_fault - finish page fault once we have prepared the page to fault
  *
@@ -4237,7 +4246,7 @@ vm_fault_t finish_fault(struct vm_fault
 				      vmf->address, &vmf->ptl);
 	ret = 0;
 	/* Re-check under ptl */
-	if (likely(pte_same(*vmf->pte, vmf->orig_pte)))
+	if (likely(!vmf_pte_changed(vmf)))
 		do_set_pte(vmf, page, vmf->address);
 	else
 		ret = VM_FAULT_NOPAGE;
@@ -4705,13 +4714,7 @@ static vm_fault_t handle_pte_fault(struc
 		 * concurrent faults and from rmap lookups.
 		 */
 		vmf->pte = NULL;
-		/*
-		 * Always initialize orig_pte.  This matches with below
-		 * code to have orig_pte to be the none pte if pte==NULL.
-		 * This makes the rest code to be always safe to reference
-		 * it, e.g. in finish_fault() we'll detect pte changes.
-		 */
-		pte_clear(vmf->vma->vm_mm, vmf->address, &vmf->orig_pte);
+		vmf->flags &= ~FAULT_FLAG_ORIG_PTE_VALID;
 	} else {
 		/*
 		 * If a huge pmd materialized under us just retry later.  Use
@@ -4735,6 +4738,7 @@ static vm_fault_t handle_pte_fault(struc
 		 */
 		vmf->pte = pte_offset_map(vmf->pmd, vmf->address);
 		vmf->orig_pte = *vmf->pte;
+		vmf->flags |= FAULT_FLAG_ORIG_PTE_VALID;
 
 		/*
 		 * some architectures can have larger ptes than wordsize,
_