Merge branch 'next' into for-linus

1 files changed, 67 insertions, 72 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index f21f4a1d6a1c..8da044a1db0f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -31,11 +31,12 @@
  *             swap_lock (in swap_duplicate, swap_info_get)
  *               mmlist_lock (in mmput, drain_mmlist and others)
  *               mapping->private_lock (in __set_page_dirty_buffers)
- *               inode_lock (in set_page_dirty's __mark_inode_dirty)
+ *               inode->i_lock (in set_page_dirty's __mark_inode_dirty)
+ *               inode_wb_list_lock (in set_page_dirty's __mark_inode_dirty)
  *                 sb_lock (within inode_lock in fs/fs-writeback.c)
  *                 mapping->tree_lock (widely used, in set_page_dirty,
  *                           in arch-dependent flush_dcache_mmap_lock,
- *                           within inode_lock in __sync_single_inode)
+ *                           within inode_wb_list_lock in __sync_single_inode)
  *
  * (code doesn't rely on that order so it could be switched around)
  * ->tasklist_lock
@@ -67,11 +68,24 @@ static struct kmem_cache *anon_vma_chain_cachep;
 
 static inline struct anon_vma *anon_vma_alloc(void)
 {
-        return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+        struct anon_vma *anon_vma;
+
+        anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+        if (anon_vma) {
+                atomic_set(&anon_vma->refcount, 1);
+                /*
+                 * Initialise the anon_vma root to point to itself. If called
+                 * from fork, the root will be reset to the parents anon_vma.
+                 */
+                anon_vma->root = anon_vma;
+        }
+
+        return anon_vma;
 }
 
-void anon_vma_free(struct anon_vma *anon_vma)
+static inline void anon_vma_free(struct anon_vma *anon_vma)
 {
+        VM_BUG_ON(atomic_read(&anon_vma->refcount));
         kmem_cache_free(anon_vma_cachep, anon_vma);
 }
 
@@ -133,11 +147,6 @@ int anon_vma_prepare(struct vm_area_struct *vma)
                         if (unlikely(!anon_vma))
                                 goto out_enomem_free_avc;
                         allocated = anon_vma;
-                        /*
-                         * This VMA had no anon_vma yet.  This anon_vma is
-                         * the root of any anon_vma tree that might form.
-                         */
-                        anon_vma->root = anon_vma;
                 }
 
                 anon_vma_lock(anon_vma);
@@ -156,7 +165,7 @@ int anon_vma_prepare(struct vm_area_struct *vma)
                 anon_vma_unlock(anon_vma);
 
                 if (unlikely(allocated))
-                        anon_vma_free(allocated);
+                        put_anon_vma(allocated);
                 if (unlikely(avc))
                         anon_vma_chain_free(avc);
         }
@@ -241,9 +250,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
          */
         anon_vma->root = pvma->anon_vma->root;
         /*
-         * With KSM refcounts, an anon_vma can stay around longer than the
-         * process it belongs to.  The root anon_vma needs to be pinned
-         * until this anon_vma is freed, because the lock lives in the root.
+         * With refcounts, an anon_vma can stay around longer than the
+         * process it belongs to. The root anon_vma needs to be pinned until
+         * this anon_vma is freed, because the lock lives in the root.
          */
         get_anon_vma(anon_vma->root);
         /* Mark this anon_vma as the one where our new (COWed) pages go. */
@@ -253,7 +262,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma)
         return 0;
 
  out_error_free_anon_vma:
-        anon_vma_free(anon_vma);
+        put_anon_vma(anon_vma);
  out_error:
         unlink_anon_vmas(vma);
         return -ENOMEM;
@@ -272,15 +281,11 @@ static void anon_vma_unlink(struct anon_vma_chain *anon_vma_chain)
         list_del(&anon_vma_chain->same_anon_vma);
 
         /* We must garbage collect the anon_vma if it's empty */
-        empty = list_empty(&anon_vma->head) && !anonvma_external_refcount(anon_vma);
+        empty = list_empty(&anon_vma->head);
         anon_vma_unlock(anon_vma);
 
-        if (empty) {
-                /* We no longer need the root anon_vma */
-                if (anon_vma->root != anon_vma)
-                        drop_anon_vma(anon_vma->root);
-                anon_vma_free(anon_vma);
-        }
+        if (empty)
+                put_anon_vma(anon_vma);
 }
 
 void unlink_anon_vmas(struct vm_area_struct *vma)
@@ -303,7 +308,7 @@ static void anon_vma_ctor(void *data)
         struct anon_vma *anon_vma = data;
 
         spin_lock_init(&anon_vma->lock);
-        anonvma_external_refcount_init(anon_vma);
+        atomic_set(&anon_vma->refcount, 0);
         INIT_LIST_HEAD(&anon_vma->head);
 }
 
@@ -497,41 +502,51 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
         struct mm_struct *mm = vma->vm_mm;
         int referenced = 0;
 
-        /*
-         * Don't want to elevate referenced for mlocked page that gets this far,
-         * in order that it progresses to try_to_unmap and is moved to the
-         * unevictable list.
-         */
-        if (vma->vm_flags & VM_LOCKED) {
-                *mapcount = 0;  /* break early from loop */
-                *vm_flags |= VM_LOCKED;
-                goto out;
-        }
-
-        /* Pretend the page is referenced if the task has the
-           swap token and is in the middle of a page fault. */
-        if (mm != current->mm && has_swap_token(mm) &&
-                        rwsem_is_locked(&mm->mmap_sem))
-                referenced++;
-
         if (unlikely(PageTransHuge(page))) {
                 pmd_t *pmd;
 
                 spin_lock(&mm->page_table_lock);
+                /*
+                 * rmap might return false positives; we must filter
+                 * these out using page_check_address_pmd().
+                 */
                 pmd = page_check_address_pmd(page, mm, address,
                                              PAGE_CHECK_ADDRESS_PMD_FLAG);
-                if (pmd && !pmd_trans_splitting(*pmd) &&
-                    pmdp_clear_flush_young_notify(vma, address, pmd))
+                if (!pmd) {
+                        spin_unlock(&mm->page_table_lock);
+                        goto out;
+                }
+
+                if (vma->vm_flags & VM_LOCKED) {
+                        spin_unlock(&mm->page_table_lock);
+                        *mapcount = 0;  /* break early from loop */
+                        *vm_flags |= VM_LOCKED;
+                        goto out;
+                }
+
+                /* go ahead even if the pmd is pmd_trans_splitting() */
+                if (pmdp_clear_flush_young_notify(vma, address, pmd))
                         referenced++;
                 spin_unlock(&mm->page_table_lock);
         } else {
                 pte_t *pte;
                 spinlock_t *ptl;
 
+                /*
+                 * rmap might return false positives; we must filter
+                 * these out using page_check_address().
+                 */
                 pte = page_check_address(page, mm, address, &ptl, 0);
                 if (!pte)
                         goto out;
 
+                if (vma->vm_flags & VM_LOCKED) {
+                        pte_unmap_unlock(pte, ptl);
+                        *mapcount = 0;  /* break early from loop */
+                        *vm_flags |= VM_LOCKED;
+                        goto out;
+                }
+
                 if (ptep_clear_flush_young_notify(vma, address, pte)) {
                         /*
                          * Don't treat a reference through a sequentially read
@@ -546,6 +561,12 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
                 pte_unmap_unlock(pte, ptl);
         }
 
+        /* Pretend the page is referenced if the task has the
+           swap token and is in the middle of a page fault. */
+        if (mm != current->mm && has_swap_token(mm) &&
+                        rwsem_is_locked(&mm->mmap_sem))
+                referenced++;
+
         (*mapcount)--;
 
         if (referenced)
@@ -1470,41 +1491,15 @@ int try_to_munlock(struct page *page)
                 return try_to_unmap_file(page, TTU_MUNLOCK);
 }
 
-#if defined(CONFIG_KSM) || defined(CONFIG_MIGRATION)
-/*
- * Drop an anon_vma refcount, freeing the anon_vma and anon_vma->root
- * if necessary.  Be careful to do all the tests under the lock.  Once
- * we know we are the last user, nobody else can get a reference and we
- * can do the freeing without the lock.
- */
-void drop_anon_vma(struct anon_vma *anon_vma)
+void __put_anon_vma(struct anon_vma *anon_vma)
 {
-        BUG_ON(atomic_read(&anon_vma->external_refcount) <= 0);
-        if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->root->lock)) {
-                struct anon_vma *root = anon_vma->root;
-                int empty = list_empty(&anon_vma->head);
-                int last_root_user = 0;
-                int root_empty = 0;
+        struct anon_vma *root = anon_vma->root;
 
-                /*
-                 * The refcount on a non-root anon_vma got dropped.  Drop
-                 * the refcount on the root and check if we need to free it.
-                 */
-                if (empty && anon_vma != root) {
-                        BUG_ON(atomic_read(&root->external_refcount) <= 0);
-                        last_root_user = atomic_dec_and_test(&root->external_refcount);
-                        root_empty = list_empty(&root->head);
-                }
-                anon_vma_unlock(anon_vma);
+        if (root != anon_vma && atomic_dec_and_test(&root->refcount))
+                anon_vma_free(root);
 
-                if (empty) {
-                        anon_vma_free(anon_vma);
-                        if (root_empty && last_root_user)
-                                anon_vma_free(root);
-                }
-        }
+        anon_vma_free(anon_vma);
 }
-#endif
 
 #ifdef CONFIG_MIGRATION
 /*