ksm: enable KSM page migration

Migration of KSM pages is now safe: remove the PageKsm restrictions from
mempolicy.c and migrate.c.

But keep PageKsm out of __unmap_and_move()'s anon_vma contortions, which
are irrelevant to KSM: it looks as if that code was preventing hotremove
migration of KSM pages, unless they happened to be in swapcache.

There is some question as to whether enforcing a NUMA mempolicy migration
ought to migrate KSM pages, mapped into entirely unrelated processes; but
moving page_mapcount > 1 is only permitted with MPOL_MF_MOVE_ALL anyway,
and it seems reasonable to assume that you wouldn't set MADV_MERGEABLE on
any area where this is a worry.

Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Petr Holasek <pholasek@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Izik Eidus <izik.eidus@ravellosystems.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2ae78e255e080fa02492a2cc06a677174ee339ca..d344c36db63f3463001427983494ece1e90845b7 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -496,9 +496,8 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                /*
                 * vm_normal_page() filters out zero pages, but there might
                 * still be PageReserved pages to skip, perhaps in a VDSO.
-                * And we cannot move PageKsm pages sensibly or safely yet.
                 */
-               if (PageReserved(page) || PageKsm(page))
+               if (PageReserved(page))
                        continue;
                nid = page_to_nid(page);
                if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))

diff --git a/mm/migrate.c b/mm/migrate.c
index e545ce7ddc177503c007d9493f83bb219f1d766c..20a03eb0667f1b0a04e7ae79c7064bffe239f682 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -731,20 +731,6 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
                lock_page(page);
        }
 
-       /*
-        * Only memory hotplug's offline_pages() caller has locked out KSM,
-        * and can safely migrate a KSM page.  The other cases have skipped
-        * PageKsm along with PageReserved - but it is only now when we have
-        * the page lock that we can be certain it will not go KSM beneath us
-        * (KSM will not upgrade a page from PageAnon to PageKsm when it sees
-        * its pagecount raised, but only here do we take the page lock which
-        * serializes that).
-        */
-       if (PageKsm(page) && !offlining) {
-               rc = -EBUSY;
-               goto unlock;
-       }
-
        /* charge against new page */
        mem_cgroup_prepare_migration(page, newpage, &mem);
 
@@ -771,7 +757,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
         * File Caches may use write_page() or lock_page() in migration, then,
         * just care Anon page here.
         */
-       if (PageAnon(page)) {
+       if (PageAnon(page) && !PageKsm(page)) {
                /*
                 * Only page_lock_anon_vma_read() understands the subtleties of
                 * getting a hold on an anon_vma from outside one of its mms.
@@ -851,7 +837,6 @@ uncharge:
        mem_cgroup_end_migration(mem, page, newpage,
                                 (rc == MIGRATEPAGE_SUCCESS ||
                                  rc == MIGRATEPAGE_BALLOON_SUCCESS));
-unlock:
        unlock_page(page);
 out:
        return rc;
@@ -1155,7 +1140,7 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
                        goto set_status;
 
                /* Use PageReserved to check for zero page */
-               if (PageReserved(page) || PageKsm(page))
+               if (PageReserved(page))
                        goto put_and_set;
 
                pp->page = page;
@@ -1317,7 +1302,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 
                err = -ENOENT;
                /* Use PageReserved to check for zero page */
-               if (!page || PageReserved(page) || PageKsm(page))
+               if (!page || PageReserved(page))
                        goto set_status;
 
                err = page_to_nid(page);