[PATCH 5/9] mbind: add hugepage migration code to mbind()

[Naoya Horiguchi]

This patch extends 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.

ChangeLog v3:
 - revert introducing migrate_movable_pages
 - added alloc_huge_page_noerr free from ERR_VALUE

ChangeLog v2:
 - updated description and renamed patch title

Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Acked-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Reviewed-by: Wanpeng Li <liwanp@xxxxxxxxxxxxxxxxxx>
Acked-by: Hillf Danton <dhillf@xxxxxxxxx>
---
 include/linux/hugetlb.h |  3 +++
 mm/hugetlb.c            | 14 ++++++++++++++
 mm/mempolicy.c          |  4 +++-
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git v3.11-rc3.orig/include/linux/hugetlb.h v3.11-rc3/include/linux/hugetlb.h
index bc8d837..d1db007 100644
--- v3.11-rc3.orig/include/linux/hugetlb.h
+++ v3.11-rc3/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 v3.11-rc3.orig/mm/hugetlb.c v3.11-rc3/mm/hugetlb.c
index 649771c..ee764b0 100644
--- v3.11-rc3.orig/mm/hugetlb.c
+++ v3.11-rc3/mm/hugetlb.c
@@ -1195,6 +1195,20 @@ 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 v3.11-rc3.orig/mm/mempolicy.c v3.11-rc3/mm/mempolicy.c
index d96afc1..4a03c14 100644
--- v3.11-rc3.orig/mm/mempolicy.c
+++ v3.11-rc3/mm/mempolicy.c
@@ -1183,6 +1183,8 @@ 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
 	 */
@@ -1293,7 +1295,7 @@ 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))
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/