Merge tag 'linux-kselftest-4.1-rc1' of git://git.kernel.org/pub/scm/linux/kernel...

[sfrench/cifs-2.6.git] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index 411144f977b10eab492410728784efe37c4ea54a..97839f5c8c303df324a1cec1dfacadb1b0bfa04c 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3035,6 +3035,7 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
        int last_cpupid;
        int target_nid;
        bool migrated = false;
+       bool was_writable = pte_write(pte);
        int flags = 0;
 
        /* A PROT_NONE fault should not end up here */
@@ -3059,6 +3060,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
        /* Make it present again */
        pte = pte_modify(pte, vma->vm_page_prot);
        pte = pte_mkyoung(pte);
+       if (was_writable)
+               pte = pte_mkwrite(pte);
        set_pte_at(mm, addr, ptep, pte);
        update_mmu_cache(vma, addr, ptep);
 
@@ -3069,16 +3072,14 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
        }
 
        /*
-        * Avoid grouping on DSO/COW pages in specific and RO pages
-        * in general, RO pages shouldn't hurt as much anyway since
-        * they can be in shared cache state.
-        *
-        * FIXME! This checks "pmd_dirty()" as an approximation of
-        * "is this a read-only page", since checking "pmd_write()"
-        * is even more broken. We haven't actually turned this into
-        * a writable page, so pmd_write() will always be false.
+        * 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
+        * the case where a mapping is writable but the process never writes
+        * to it but pte_write gets cleared during protection updates and
+        * pte_dirty has unpredictable behaviour between PTE scan updates,
+        * background writeback, dirty balancing and application behaviour.
         */
-       if (!pte_dirty(pte))
+       if (!(vma->vm_flags & VM_WRITE))
                flags |= TNF_NO_GROUP;
 
        /*
@@ -3102,7 +3103,8 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
        if (migrated) {
                page_nid = target_nid;
                flags |= TNF_MIGRATED;
-       }
+       } else
+               flags |= TNF_MIGRATE_FAIL;
 
 out:
        if (page_nid != -1)