rmap: add exclusively owned pages to the newest anon_vma

The recent anon_vma fixes cause many anonymous pages to end up
in the parent process anon_vma, even when the page is exclusively
owned by the current process.

Adding exclusively owned anonymous pages to the top anon_vma
reduces rmap scanning overhead, especially in workloads with
forking servers.

This patch adds a parameter to __page_set_anon_rmap that can
be used to indicate whether or not the added page is exclusively
owned by the current process.

Pages added through page_add_new_anon_rmap are exclusively
owned by the current process, and can be added to the top
anon_vma.

Pages added through page_add_anon_rmap can be either shared
or exclusively owned, so we do the conservative thing and
add it to the oldest anon_vma.

A next step would be to add the exclusive parameter to
page_add_anon_rmap, to be used from functions where we do
know for sure whether a page is exclusively owned.

Signed-off-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Johannes Weiner <hannes@cmpxchg.org>
Lightly-tested-by: Borislav Petkov <bp@alien8.de>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
[ Edited to look nicer  - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/rmap.c b/mm/rmap.c
index 4bad3267537a8c7826d313afa661a03f51b2df26..526704e8215d0f3124769083bc0f14e2817cab3a 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -730,23 +730,28 @@ void page_move_anon_rmap(struct page *page,
  * @page:      the page to add the mapping to
  * @vma:       the vm area in which the mapping is added
  * @address:   the user virtual address mapped
+ * @exclusive: the page is exclusively owned by the current process
  */
 static void __page_set_anon_rmap(struct page *page,
-       struct vm_area_struct *vma, unsigned long address)
+       struct vm_area_struct *vma, unsigned long address, int exclusive)
 {
-       struct anon_vma_chain *avc;
-       struct anon_vma *anon_vma;
+       struct anon_vma *anon_vma = vma->anon_vma;
 
-       BUG_ON(!vma->anon_vma);
+       BUG_ON(!anon_vma);
 
        /*
-        * We must use the _oldest_ possible anon_vma for the page mapping!
+        * If the page isn't exclusively mapped into this vma,
+        * we must use the _oldest_ possible anon_vma for the
+        * page mapping!
         *
-        * So take the last AVC chain entry in the vma, which is the deepest
-        * ancestor, and use the anon_vma from that.
+        * So take the last AVC chain entry in the vma, which is
+        * the deepest ancestor, and use the anon_vma from that.
         */
-       avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma);
-       anon_vma = avc->anon_vma;
+       if (!exclusive) {
+               struct anon_vma_chain *avc;
+               avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma);
+               anon_vma = avc->anon_vma;
+       }
 
        anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
        page->mapping = (struct address_space *) anon_vma;
@@ -802,7 +807,7 @@ void page_add_anon_rmap(struct page *page,
        VM_BUG_ON(!PageLocked(page));
        VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
        if (first)
-               __page_set_anon_rmap(page, vma, address);
+               __page_set_anon_rmap(page, vma, address, 0);
        else
                __page_check_anon_rmap(page, vma, address);
 }
@@ -824,7 +829,7 @@ void page_add_new_anon_rmap(struct page *page,
        SetPageSwapBacked(page);
        atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
        __inc_zone_page_state(page, NR_ANON_PAGES);
-       __page_set_anon_rmap(page, vma, address);
+       __page_set_anon_rmap(page, vma, address, 1);
        if (page_evictable(page, vma))
                lru_cache_add_lru(page, LRU_ACTIVE_ANON);
        else