mm: thp: set the accessed flag for old pages on access fault

On x86 memory accesses to pages without the ACCESSED flag set result in
the ACCESSED flag being set automatically.  With the ARM architecture a
page access fault is raised instead (and it will continue to be raised
until the ACCESSED flag is set for the appropriate PTE/PMD).

For normal memory pages, handle_pte_fault will call pte_mkyoung
(effectively setting the ACCESSED flag).  For transparent huge pages,
pmd_mkyoung will only be called for a write fault.

This patch ensures that faults on transparent hugepages which do not
result in a CoW update the access flags for the faulting pmd.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Ni zhan Chen <nizhan.chen@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index b31cb7da03466b6550d9fa9fd0e4359c2540c957..1af47755245944e9f25d794a1f18717960f49d46 100644 (file)
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -8,6 +8,10 @@ extern int do_huge_pmd_anonymous_page(struct mm_struct *mm,
 extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                         pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
                         struct vm_area_struct *vma);
+extern void huge_pmd_set_accessed(struct mm_struct *mm,
+                                 struct vm_area_struct *vma,
+                                 unsigned long address, pmd_t *pmd,
+                                 pmd_t orig_pmd, int dirty);
 extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                               unsigned long address, pmd_t *pmd,
                               pmd_t orig_pmd);

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ea5fb93a53a9a0d33f9a2851ee2ab008fe6a8a9e..5f902e20e8c03eb70cd11d569e36a8697ed5d28a 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -784,6 +784,28 @@ out:
        return ret;
 }
 
+void huge_pmd_set_accessed(struct mm_struct *mm,
+                          struct vm_area_struct *vma,
+                          unsigned long address,
+                          pmd_t *pmd, pmd_t orig_pmd,
+                          int dirty)
+{
+       pmd_t entry;
+       unsigned long haddr;
+
+       spin_lock(&mm->page_table_lock);
+       if (unlikely(!pmd_same(*pmd, orig_pmd)))
+               goto unlock;
+
+       entry = pmd_mkyoung(orig_pmd);
+       haddr = address & HPAGE_PMD_MASK;
+       if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty))
+               update_mmu_cache_pmd(vma, address, pmd);
+
+unlock:
+       spin_unlock(&mm->page_table_lock);
+}
+
 static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
                                        struct vm_area_struct *vma,
                                        unsigned long address,

diff --git a/mm/memory.c b/mm/memory.c
index 221fc9ffcab1da33eb15947776975730b5058b67..765377385632086e872058cb46fe7958dadd472f 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3537,8 +3537,9 @@ retry:
 
                barrier();
                if (pmd_trans_huge(orig_pmd)) {
-                       if (flags & FAULT_FLAG_WRITE &&
-                           !pmd_write(orig_pmd) &&
+                       unsigned int dirty = flags & FAULT_FLAG_WRITE;
+
+                       if (dirty && !pmd_write(orig_pmd) &&
                            !pmd_trans_splitting(orig_pmd)) {
                                ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
                                                          orig_pmd);
@@ -3550,6 +3551,9 @@ retry:
                                if (unlikely(ret & VM_FAULT_OOM))
                                        goto retry;
                                return ret;
+                       } else {
+                               huge_pmd_set_accessed(mm, vma, address, pmd,
+                                                     orig_pmd, dirty);
                        }
                        return 0;
                }