On Wed, 28 Apr 2010 02:08:33 +0200 Andrea Arcangeli <aarcange@xxxxxxxxxx> wrote: > On Wed, Apr 28, 2010 at 09:03:02AM +0900, KAMEZAWA Hiroyuki wrote: > > I bet calling __get_user_pages_fast() before vma_adjust() is the way to go. > > When page_count(page) != page_mapcount(page) +1, migration skip it. > > My proposed fix avoids to walk the pagetables once more time and to > mangle over the page counts. Can you check it? It works but it needs > more review. Sure...but can we avoid temporal objrmap breakage(inconsistency) by it ? THanks, -Kame -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>