Merge branch 'next/cleanup' into for-next

[karo-tx-linux.git] / mm / rmap.c

diff --git a/mm/rmap.c b/mm/rmap.c
index cdc2a885a4cde7d3f8312a4fbb97df4df0b2a2c4..79f3bf047f38497bdcdae741c2941370353a3ea7 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -23,21 +23,22 @@
  * inode->i_mutex      (while writing or truncating, not reading or faulting)
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
- *       mapping->i_mmap_rwsem
- *         anon_vma->rwsem
- *           mm->page_table_lock or pte_lock
- *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
- *             swap_lock (in swap_duplicate, swap_info_get)
- *               mmlist_lock (in mmput, drain_mmlist and others)
- *               mapping->private_lock (in __set_page_dirty_buffers)
- *                 mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
- *                   mapping->tree_lock (widely used)
- *               inode->i_lock (in set_page_dirty's __mark_inode_dirty)
- *               bdi.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 bdi.wb->list_lock in __sync_single_inode)
+ *       hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
+ *         mapping->i_mmap_rwsem
+ *           anon_vma->rwsem
+ *             mm->page_table_lock or pte_lock
+ *               zone->lru_lock (in mark_page_accessed, isolate_lru_page)
+ *               swap_lock (in swap_duplicate, swap_info_get)
+ *                 mmlist_lock (in mmput, drain_mmlist and others)
+ *                 mapping->private_lock (in __set_page_dirty_buffers)
+ *                   mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
+ *                     mapping->tree_lock (widely used)
+ *                 inode->i_lock (in set_page_dirty's __mark_inode_dirty)
+ *                 bdi.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 bdi.wb->list_lock in __sync_single_inode)
  *
  * anon_vma->rwsem,mapping->i_mutex      (memory_failure, collect_procs_anon)
  *   ->tasklist_lock
@@ -1411,6 +1412,11 @@ void page_remove_rmap(struct page *page, bool compound)
         */
 }
 
+struct rmap_private {
+       enum ttu_flags flags;
+       int lazyfreed;
+};
+
 /*
  * @arg: enum ttu_flags will be passed to this argument
  */
@@ -1422,7 +1428,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
        pte_t pteval;
        spinlock_t *ptl;
        int ret = SWAP_AGAIN;
-       enum ttu_flags flags = (enum ttu_flags)arg;
+       struct rmap_private *rp = arg;
+       enum ttu_flags flags = rp->flags;
 
        /* munlock has nothing to gain from examining un-locked vmas */
        if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
@@ -1514,6 +1521,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                 * See handle_pte_fault() ...
                 */
                VM_BUG_ON_PAGE(!PageSwapCache(page), page);
+
+               if (!PageDirty(page) && (flags & TTU_LZFREE)) {
+                       /* It's a freeable page by MADV_FREE */
+                       dec_mm_counter(mm, MM_ANONPAGES);
+                       rp->lazyfreed++;
+                       goto discard;
+               }
+
                if (swap_duplicate(entry) < 0) {
                        set_pte_at(mm, address, pte, pteval);
                        ret = SWAP_FAIL;
@@ -1534,6 +1549,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
        } else
                dec_mm_counter(mm, mm_counter_file(page));
 
+discard:
        page_remove_rmap(page, PageHuge(page));
        page_cache_release(page);
 
@@ -1586,9 +1602,14 @@ static int page_not_mapped(struct page *page)
 int try_to_unmap(struct page *page, enum ttu_flags flags)
 {
        int ret;
+       struct rmap_private rp = {
+               .flags = flags,
+               .lazyfreed = 0,
+       };
+
        struct rmap_walk_control rwc = {
                .rmap_one = try_to_unmap_one,
-               .arg = (void *)flags,
+               .arg = &rp,
                .done = page_not_mapped,
                .anon_lock = page_lock_anon_vma_read,
        };
@@ -1608,8 +1629,11 @@ int try_to_unmap(struct page *page, enum ttu_flags flags)
 
        ret = rmap_walk(page, &rwc);
 
-       if (ret != SWAP_MLOCK && !page_mapped(page))
+       if (ret != SWAP_MLOCK && !page_mapped(page)) {
                ret = SWAP_SUCCESS;
+               if (rp.lazyfreed && !PageDirty(page))
+                       ret = SWAP_LZFREE;
+       }
        return ret;
 }
 
@@ -1631,9 +1655,14 @@ int try_to_unmap(struct page *page, enum ttu_flags flags)
 int try_to_munlock(struct page *page)
 {
        int ret;
+       struct rmap_private rp = {
+               .flags = TTU_MUNLOCK,
+               .lazyfreed = 0,
+       };
+
        struct rmap_walk_control rwc = {
                .rmap_one = try_to_unmap_one,
-               .arg = (void *)TTU_MUNLOCK,
+               .arg = &rp,
                .done = page_not_mapped,
                .anon_lock = page_lock_anon_vma_read,