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

[~andy/linux] / mm / huge_memory.c

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 243f4cc757775533f369a1d8acaee7d12c607e53..610e3df2768a6a5b2ec1e293da4c96dafbbe2d30 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -211,24 +211,29 @@ static void put_huge_zero_page(void)
        BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
 }
 
-static int shrink_huge_zero_page(struct shrinker *shrink,
-               struct shrink_control *sc)
+static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
+                                       struct shrink_control *sc)
 {
-       if (!sc->nr_to_scan)
-               /* we can free zero page only if last reference remains */
-               return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+       /* we can free zero page only if last reference remains */
+       return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+}
 
+static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
+                                      struct shrink_control *sc)
+{
        if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
                struct page *zero_page = xchg(&huge_zero_page, NULL);
                BUG_ON(zero_page == NULL);
                __free_page(zero_page);
+               return HPAGE_PMD_NR;
        }
 
        return 0;
 }
 
 static struct shrinker huge_zero_page_shrinker = {
-       .shrink = shrink_huge_zero_page,
+       .count_objects = shrink_huge_zero_page_count,
+       .scan_objects = shrink_huge_zero_page_scan,
        .seeks = DEFAULT_SEEKS,
 };
 
@@ -820,17 +825,19 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                count_vm_event(THP_FAULT_FALLBACK);
                return VM_FAULT_FALLBACK;
        }
-       count_vm_event(THP_FAULT_ALLOC);
        if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
                put_page(page);
+               count_vm_event(THP_FAULT_FALLBACK);
                return VM_FAULT_FALLBACK;
        }
        if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page))) {
                mem_cgroup_uncharge_page(page);
                put_page(page);
+               count_vm_event(THP_FAULT_FALLBACK);
                return VM_FAULT_FALLBACK;
        }
 
+       count_vm_event(THP_FAULT_ALLOC);
        return 0;
 }
 
@@ -1143,7 +1150,6 @@ alloc:
                new_page = NULL;
 
        if (unlikely(!new_page)) {
-               count_vm_event(THP_FAULT_FALLBACK);
                if (is_huge_zero_pmd(orig_pmd)) {
                        ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
                                        address, pmd, orig_pmd, haddr);
@@ -1154,9 +1160,9 @@ alloc:
                                split_huge_page(page);
                        put_page(page);
                }
+               count_vm_event(THP_FAULT_FALLBACK);
                goto out;
        }
-       count_vm_event(THP_FAULT_ALLOC);
 
        if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
                put_page(new_page);
@@ -1164,10 +1170,13 @@ alloc:
                        split_huge_page(page);
                        put_page(page);
                }
+               count_vm_event(THP_FAULT_FALLBACK);
                ret |= VM_FAULT_OOM;
                goto out;
        }
 
+       count_vm_event(THP_FAULT_ALLOC);
+
        if (is_huge_zero_pmd(orig_pmd))
                clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
        else
@@ -2688,6 +2697,7 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 
        mmun_start = haddr;
        mmun_end   = haddr + HPAGE_PMD_SIZE;
+again:
        mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
        spin_lock(&mm->page_table_lock);
        if (unlikely(!pmd_trans_huge(*pmd))) {
@@ -2710,7 +2720,14 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
        split_huge_page(page);
 
        put_page(page);
-       BUG_ON(pmd_trans_huge(*pmd));
+
+       /*
+        * We don't always have down_write of mmap_sem here: a racing
+        * do_huge_pmd_wp_page() might have copied-on-write to another
+        * huge page before our split_huge_page() got the anon_vma lock.
+        */
+       if (unlikely(pmd_trans_huge(*pmd)))
+               goto again;
 }
 
 void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,