mm: mlocking in try_to_unmap_one

There's contorted mlock/munlock handling in try_to_unmap_anon() and
try_to_unmap_file(), which we'd prefer not to repeat for KSM swapping.
Simplify it by moving it all down into try_to_unmap_one().

One thing is then lost, try_to_munlock()'s distinction between when no vma
holds the page mlocked, and when a vma does mlock it, but we could not get
mmap_sem to set the page flag.  But its only caller takes no interest in
that distinction (and is better testing SWAP_MLOCK anyway), so let's keep
the code simple and return SWAP_AGAIN for both cases.

try_to_unmap_file()'s TTU_MUNLOCK nonlinear handling was particularly
amusing: once unravelled, it turns out to have been choosing between two
different ways of doing the same nothing.  Ah, no, one way was actually
returning SWAP_FAIL when it meant to return SWAP_SUCCESS.

[kosaki.motohiro@jp.fujitsu.com: comment adding to mlocking in try_to_unmap_one]
[akpm@linux-foundation.org: remove test of MLOCK_PAGES]
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Izik Eidus <ieidus@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 32 insertions, 80 deletions

diff --git a/mm/mlock.c b/mm/mlock.c
index bd6f0e466f6c..48691fb08514 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -117,7 +117,7 @@ static void munlock_vma_page(struct page *page)
                         /*
                          * did try_to_unlock() succeed or punt?
                          */
-                        if (ret == SWAP_SUCCESS || ret == SWAP_AGAIN)
+                        if (ret != SWAP_MLOCK)
                                 count_vm_event(UNEVICTABLE_PGMUNLOCKED);
 
                         putback_lru_page(page);
diff --git a/mm/rmap.c b/mm/rmap.c
index f06cee48eca7..c3d6dc4223a4 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -788,6 +788,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                         ret = SWAP_MLOCK;
                         goto out_unmap;
                 }
+                if (MLOCK_PAGES && TTU_ACTION(flags) == TTU_MUNLOCK)
+                        goto out_unmap;
         }
         if (!(flags & TTU_IGNORE_ACCESS)) {
                 if (ptep_clear_flush_young_notify(vma, address, pte)) {
@@ -853,12 +855,22 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
         } else
                 dec_mm_counter(mm, file_rss);
 
-
         page_remove_rmap(page);
         page_cache_release(page);
 
 out_unmap:
         pte_unmap_unlock(pte, ptl);
+
+        if (MLOCK_PAGES && ret == SWAP_MLOCK) {
+                ret = SWAP_AGAIN;
+                if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
+                        if (vma->vm_flags & VM_LOCKED) {
+                                mlock_vma_page(page);
+                                ret = SWAP_MLOCK;
+                        }
+                        up_read(&vma->vm_mm->mmap_sem);
+                }
+        }
 out:
         return ret;
 }
@@ -980,23 +992,6 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
         return ret;
 }
 
-/*
- * common handling for pages mapped in VM_LOCKED vmas
- */
-static int try_to_mlock_page(struct page *page, struct vm_area_struct *vma)
-{
-        int mlocked = 0;
-
-        if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
-                if (vma->vm_flags & VM_LOCKED) {
-                        mlock_vma_page(page);
-                        mlocked++;      /* really mlocked the page */
-                }
-                up_read(&vma->vm_mm->mmap_sem);
-        }
-        return mlocked;
-}
-
 /**
  * try_to_unmap_anon - unmap or unlock anonymous page using the object-based
  * rmap method
@@ -1017,42 +1012,19 @@ static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
 {
         struct anon_vma *anon_vma;
         struct vm_area_struct *vma;
-        unsigned int mlocked = 0;
         int ret = SWAP_AGAIN;
-        int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
-
-        if (MLOCK_PAGES && unlikely(unlock))
-                ret = SWAP_SUCCESS;     /* default for try_to_munlock() */
 
         anon_vma = page_lock_anon_vma(page);
         if (!anon_vma)
                 return ret;
 
         list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
-                if (MLOCK_PAGES && unlikely(unlock)) {
-                        if (!((vma->vm_flags & VM_LOCKED) &&
-                              page_mapped_in_vma(page, vma)))
-                                continue;  /* must visit all unlocked vmas */
-                        ret = SWAP_MLOCK;  /* saw at least one mlocked vma */
-                } else {
-                        ret = try_to_unmap_one(page, vma, flags);
-                        if (ret == SWAP_FAIL || !page_mapped(page))
-                                break;
-                }
-                if (ret == SWAP_MLOCK) {
-                        mlocked = try_to_mlock_page(page, vma);
-                        if (mlocked)
-                                break;  /* stop if actually mlocked page */
-                }
+                ret = try_to_unmap_one(page, vma, flags);
+                if (ret != SWAP_AGAIN || !page_mapped(page))
+                        break;
         }
 
         page_unlock_anon_vma(anon_vma);
-
-        if (mlocked)
-                ret = SWAP_MLOCK;       /* actually mlocked the page */
-        else if (ret == SWAP_MLOCK)
-                ret = SWAP_AGAIN;       /* saw VM_LOCKED vma */
-
         return ret;
 }
 
@@ -1082,42 +1054,27 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
         unsigned long max_nl_cursor = 0;
         unsigned long max_nl_size = 0;
         unsigned int mapcount;
-        unsigned int mlocked = 0;
-        int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
-
-        if (MLOCK_PAGES && unlikely(unlock))
-                ret = SWAP_SUCCESS;     /* default for try_to_munlock() */
 
         spin_lock(&mapping->i_mmap_lock);
         vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
-                if (MLOCK_PAGES && unlikely(unlock)) {
-                        if (!((vma->vm_flags & VM_LOCKED) &&
-                                                page_mapped_in_vma(page, vma)))
-                                continue;       /* must visit all vmas */
-                        ret = SWAP_MLOCK;
-                } else {
-                        ret = try_to_unmap_one(page, vma, flags);
-                        if (ret == SWAP_FAIL || !page_mapped(page))
-                                goto out;
-                }
-                if (ret == SWAP_MLOCK) {
-                        mlocked = try_to_mlock_page(page, vma);
-                        if (mlocked)
-                                goto out;  /* stop if actually mlocked page */
-                }
+                ret = try_to_unmap_one(page, vma, flags);
+                if (ret != SWAP_AGAIN || !page_mapped(page))
+                        goto out;
         }
 
         if (list_empty(&mapping->i_mmap_nonlinear))
                 goto out;
 
+        /*
+         * We don't bother to try to find the munlocked page in nonlinears.
+         * It's costly. Instead, later, page reclaim logic may call
+         * try_to_unmap(TTU_MUNLOCK) and recover PG_mlocked lazily.
+         */
+        if (TTU_ACTION(flags) == TTU_MUNLOCK)
+                goto out;
+
         list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
                                                 shared.vm_set.list) {
-                if (MLOCK_PAGES && unlikely(unlock)) {
-                        if (!(vma->vm_flags & VM_LOCKED))
-                                continue;       /* must visit all vmas */
-                        ret = SWAP_MLOCK;       /* leave mlocked == 0 */
-                        goto out;               /* no need to look further */
-                }
                 if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
                         (vma->vm_flags & VM_LOCKED))
                         continue;
@@ -1159,10 +1116,9 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
                         cursor = (unsigned long) vma->vm_private_data;
                         while ( cursor < max_nl_cursor &&
                                 cursor < vma->vm_end - vma->vm_start) {
-                                ret = try_to_unmap_cluster(cursor, &mapcount,
-                                                                vma, page);
-                                if (ret == SWAP_MLOCK)
-                                        mlocked = 2;    /* to return below */
+                                if (try_to_unmap_cluster(cursor, &mapcount,
+                                                vma, page) == SWAP_MLOCK)
+                                        ret = SWAP_MLOCK;
                                 cursor += CLUSTER_SIZE;
                                 vma->vm_private_data = (void *) cursor;
                                 if ((int)mapcount <= 0)
@@ -1183,10 +1139,6 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
                 vma->vm_private_data = NULL;
 out:
         spin_unlock(&mapping->i_mmap_lock);
-        if (mlocked)
-                ret = SWAP_MLOCK;       /* actually mlocked the page */
-        else if (ret == SWAP_MLOCK)
-                ret = SWAP_AGAIN;       /* saw VM_LOCKED vma */
         return ret;
 }
 
@@ -1229,7 +1181,7 @@ int try_to_unmap(struct page *page, enum ttu_flags flags)
  *
  * Return values are:
  *
- * SWAP_SUCCESS - no vma's holding page mlocked.
+ * SWAP_AGAIN   - no vma is holding page mlocked, or,
  * SWAP_AGAIN   - page mapped in mlocked vma -- couldn't acquire mmap sem
  * SWAP_MLOCK   - page is now mlocked.
  */