mm: make swapoff more robust against soft dirty

Both s390 and powerpc have hit the issue of swapoff hanging, when
CONFIG_HAVE_ARCH_SOFT_DIRTY and CONFIG_MEM_SOFT_DIRTY ifdefs were not
quite as x86_64 had them.  I think it would be much clearer if
HAVE_ARCH_SOFT_DIRTY was just a Kconfig option set by architectures to
determine whether the MEM_SOFT_DIRTY option should be offered, and the
actual code depend upon CONFIG_MEM_SOFT_DIRTY alone.

But won't embark on that change myself: instead make swapoff more
robust, by using pte_swp_clear_soft_dirty() on each pte it encounters,
without an explicit #ifdef CONFIG_MEM_SOFT_DIRTY.  That being a no-op,
whether the bit in question is defined as 0 or the asm-generic fallback
is used, unless soft dirty is fully turned on.

Why "maybe" in maybe_same_pte()? Rename it pte_same_as_swp().

Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 31dc94fb0f6036d9eb40f54727e10c178f413ec8..2bb30aa3a4123a547bd29e1585a1234644a92152 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1111,19 +1111,9 @@ unsigned int count_swap_pages(int type, int free)
 }
 #endif /* CONFIG_HIBERNATION */
 
-static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
+static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte)
 {
-#ifdef CONFIG_MEM_SOFT_DIRTY
-       /*
-        * When pte keeps soft dirty bit the pte generated
-        * from swap entry does not has it, still it's same
-        * pte from logical point of view.
-        */
-       pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
-       return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
-#else
-       return pte_same(pte, swp_pte);
-#endif
+       return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte);
 }
 
 /*
@@ -1152,7 +1142,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
        }
 
        pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-       if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
+       if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) {
                mem_cgroup_cancel_charge(page, memcg, false);
                ret = 0;
                goto out;
@@ -1210,7 +1200,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                 * swapoff spends a _lot_ of time in this loop!
                 * Test inline before going to call unuse_pte.
                 */
-               if (unlikely(maybe_same_pte(*pte, swp_pte))) {
+               if (unlikely(pte_same_as_swp(*pte, swp_pte))) {
                        pte_unmap(pte);
                        ret = unuse_pte(vma, pmd, addr, entry, page);
                        if (ret)