mm: mbind: add hugepage migration code to mbind()

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

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>
Acked-by: 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/include/linux/hugetlb.h b/include/linux/hugetlb.h
index bc8d8370cd0d0c8ff1885e01a31637b09b8aaaa5..d1db00790a84dc65182cfaca7eb4673bae1d33e2 100644 (file)
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -265,6 +265,8 @@ struct huge_bootmem_page {
 };
 
 struct page *alloc_huge_page_node(struct hstate *h, int nid);
+struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
+                               unsigned long addr, int avoid_reserve);
 
 /* arch callback */
 int __init alloc_bootmem_huge_page(struct hstate *h);
@@ -378,6 +380,7 @@ static inline pgoff_t basepage_index(struct page *page)
 #else  /* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
+#define alloc_huge_page_noerr(v, a, r) NULL
 #define alloc_bootmem_huge_page(h) NULL
 #define hstate_file(f) NULL
 #define hstate_sizelog(s) NULL

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e51723866fb1d361c49194ed79046c292d3f1852..d37b3b95c4392cb8d156ba915827dea820d3483a 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1207,6 +1207,20 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
        return page;
 }
 
+/*
+ * alloc_huge_page()'s wrapper which simply returns the page if allocation
+ * succeeds, otherwise NULL. This function is called from new_vma_page(),
+ * where no ERR_VALUE is expected to be returned.
+ */
+struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
+                               unsigned long addr, int avoid_reserve)
+{
+       struct page *page = alloc_huge_page(vma, addr, avoid_reserve);
+       if (IS_ERR(page))
+               page = NULL;
+       return page;
+}
+
 int __weak alloc_bootmem_huge_page(struct hstate *h)
 {
        struct huge_bootmem_page *m;

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4626be621e747b1df304d62b927a7ec0f0ccc020..c7c359213ae1ff2527e6167d15a91241068931d4 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1192,6 +1192,8 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int *
                vma = vma->vm_next;
        }
 
+       if (PageHuge(page))
+               return alloc_huge_page_noerr(vma, address, 1);
        /*
         * if !vma, alloc_page_vma() will use task or system default policy
         */
@@ -1302,7 +1304,7 @@ static long do_mbind(unsigned long start, unsigned long len,
                                        (unsigned long)vma,
                                        MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
                        if (nr_failed)
-                               putback_lru_pages(&pagelist);
+                               putback_movable_pages(&pagelist);
                }
 
                if (nr_failed && (flags & MPOL_MF_STRICT))