1 files changed, 30 insertions, 10 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 6ff5d729ded0..2e65df1831d9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3029,6 +3029,17 @@ static int __do_fault(struct vm_fault *vmf)
 	return ret;
 }
 
+/*
+ * The ordering of these checks is important for pmds with _PAGE_DEVMAP set.
+ * If we check pmd_trans_unstable() first we will trip the bad_pmd() check
+ * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly
+ * returning 1 but not before it spams dmesg with the pmd_clear_bad() output.
+ */
+static int pmd_devmap_trans_unstable(pmd_t *pmd)
+{
+	return pmd_devmap(*pmd) || pmd_trans_unstable(pmd);
+}
+
 static int pte_alloc_one_map(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
@@ -3052,18 +3063,27 @@ static int pte_alloc_one_map(struct vm_fault *vmf)
 map_pte:
 	/*
 	 * If a huge pmd materialized under us just retry later.  Use
-	 * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd
-	 * didn't become pmd_trans_huge under us and then back to pmd_none, as
-	 * a result of MADV_DONTNEED running immediately after a huge pmd fault
-	 * in a different thread of this mm, in turn leading to a misleading
-	 * pmd_trans_huge() retval.  All we have to ensure is that it is a
-	 * regular pmd that we can walk with pte_offset_map() and we can do that
-	 * through an atomic read in C, which is what pmd_trans_unstable()
-	 * provides.
+	 * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of
+	 * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge
+	 * under us and then back to pmd_none, as a result of MADV_DONTNEED
+	 * running immediately after a huge pmd fault in a different thread of
+	 * this mm, in turn leading to a misleading pmd_trans_huge() retval.
+	 * All we have to ensure is that it is a regular pmd that we can walk
+	 * with pte_offset_map() and we can do that through an atomic read in
+	 * C, which is what pmd_trans_unstable() provides.
 	 */
-	if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+	if (pmd_devmap_trans_unstable(vmf->pmd))
 		return VM_FAULT_NOPAGE;
 
+	/*
+	 * At this point we know that our vmf->pmd points to a page of ptes
+	 * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge()
+	 * for the duration of the fault.  If a racing MADV_DONTNEED runs and
+	 * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still
+	 * be valid and we will re-check to make sure the vmf->pte isn't
+	 * pte_none() under vmf->ptl protection when we return to
+	 * alloc_set_pte().
+	 */
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address,
 			&vmf->ptl);
 	return 0;
@@ -3690,7 +3710,7 @@ static int handle_pte_fault(struct vm_fault *vmf)
 		vmf->pte = NULL;
 	} else {
 		/* See comment in pte_alloc_one_map() */
-		if (pmd_trans_unstable(vmf->pmd) || pmd_devmap(*vmf->pmd))
+		if (pmd_devmap_trans_unstable(vmf->pmd))
 			return 0;
 		/*
 		 * A regular pmd is established and it can't morph into a huge