Merge branch 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel...

[karo-tx-linux.git] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index 635451abc8f7c9b84663535678a26a9b0848c89d..8132787ae4d509d475ed6a77705076ddfee30630 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3404,8 +3404,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        if (unlikely(pmd_none(*pmd)) &&
            unlikely(__pte_alloc(mm, vma, pmd, address)))
                return VM_FAULT_OOM;
-       /* if an huge pmd materialized from under us just retry later */
-       if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+       /*
+        * 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.
+        */
+       if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd)))
                return 0;
        /*
         * A regular pmd is established and it can't morph into a huge pmd