mm: migrate: add hugepage migration code to move_pages()

Extend move_pages() to handle vma with VM_HUGETLB set.  We will be able to
migrate hugepage with move_pages(2) after applying the enablement patch
which comes later in this series.

We avoid getting refcount on tail pages of hugepage, because unlike thp,
hugepage is not split and we need not care about races with splitting.

And migration of larger (1GB for x86_64) hugepage are not enabled.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memory.c b/mm/memory.c
index c1c6d59..2b73dbd 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1481,7 +1481,8 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
        if (pud_none(*pud))
                goto no_page_table;
        if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
-               BUG_ON(flags & FOLL_GET);
+               if (flags & FOLL_GET)
+                       goto out;
                page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
                goto out;
        }
@@ -1492,8 +1493,20 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
        if (pmd_none(*pmd))
                goto no_page_table;
        if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
-               BUG_ON(flags & FOLL_GET);
                page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
+               if (flags & FOLL_GET) {
+                       /*
+                        * Refcount on tail pages are not well-defined and
+                        * shouldn't be taken. The caller should handle a NULL
+                        * return when trying to follow tail pages.
+                        */
+                       if (PageHead(page))
+                               get_page(page);
+                       else {
+                               page = NULL;
+                               goto out;
+                       }
+               }
                goto out;
        }
        if ((flags & FOLL_NUMA) && pmd_numa(*pmd))

diff --git a/mm/migrate.c b/mm/migrate.c
index 3ec47d3..d313737 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1092,7 +1092,11 @@ static struct page *new_page_node(struct page *p, unsigned long private,
 
        *result = &pm->status;
 
-       return alloc_pages_exact_node(pm->node,
+       if (PageHuge(p))
+               return alloc_huge_page_node(page_hstate(compound_head(p)),
+                                       pm->node);
+       else
+               return alloc_pages_exact_node(pm->node,
                                GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
 }
 
@@ -1152,6 +1156,11 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
                                !migrate_all)
                        goto put_and_set;
 
+               if (PageHuge(page)) {
+                       isolate_huge_page(page, &pagelist);
+                       goto put_and_set;
+               }
+
                err = isolate_lru_page(page);
                if (!err) {
                        list_add_tail(&page->lru, &pagelist);
@@ -1174,7 +1183,7 @@ set_status:
                err = migrate_pages(&pagelist, new_page_node,
                                (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
                if (err)
-                       putback_lru_pages(&pagelist);
+                       putback_movable_pages(&pagelist);
        }
 
        up_read(&mm->mmap_sem);