mm, numa: skip PTE-mapped THP on numa fault

We're going to have THP mapped with PTEs.  It will confuse
numabalancing.  Let's skip them for now.

Signed-off-by: Kirill A. Shutemov <[email protected]>
Tested-by: Sasha Levin <[email protected]>
Tested-by: Aneesh Kumar K.V <[email protected]>
Acked-by: Jerome Marchand <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Naoya Horiguchi <[email protected]>
Cc: Steve Capper <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Christoph Lameter <[email protected]>
Cc: David Rientjes <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

diff --git a/mm/memory.c b/mm/memory.c
index 9b0dbc2f0b9aa00abed8c390827ff2f481fb7c59..9d5b40892d4ddeca62cbdf222f00c3419b19ff36 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3193,6 +3193,12 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
                return 0;
        }
 
+       /* TODO: handle PTE-mapped THP */
+       if (PageCompound(page)) {
+               pte_unmap_unlock(ptep, ptl);
+               return 0;
+       }
+
        /*
         * Avoid grouping on RO pages in general. RO pages shouldn't hurt as
         * much anyway since they can be in shared cache state. This misses