[PATCH 7/8] Use GFP_OTHER_NODE for transparent huge pages

From: Andi Kleen
Date: Mon Feb 21 2011 - 14:08:59 EST


From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

Pass GFP_OTHER_NODE for transparent hugepages NUMA allocations
done by the hugepages daemon. This way the low level accounting
for local versus remote pages works correctly.

Cc: aarcange@xxxxxxxxxx
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 18 ++++++++++--------
1 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5a05b35..877756e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -643,16 +643,17 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
return ret;
}

-static inline gfp_t alloc_hugepage_gfpmask(int defrag)
+static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
{
- return GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT);
+ return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp;
}

static inline struct page *alloc_hugepage_vma(int defrag,
struct vm_area_struct *vma,
- unsigned long haddr, int nd)
+ unsigned long haddr, int nd,
+ gfp_t extra_gfp)
{
- return alloc_pages_vma(alloc_hugepage_gfpmask(defrag),
+ return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp),
HPAGE_PMD_ORDER, vma, haddr, nd);
}

@@ -678,7 +679,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
if (unlikely(khugepaged_enter(vma)))
return VM_FAULT_OOM;
page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
- vma, haddr, numa_node_id());
+ vma, haddr, numa_node_id(), 0);
if (unlikely(!page))
goto out;
if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
@@ -799,7 +800,8 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
}

for (i = 0; i < HPAGE_PMD_NR; i++) {
- pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE,
+ pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE |
+ __GFP_OTHER_NODE,
vma, address, page_to_nid(page));
if (unlikely(!pages[i] ||
mem_cgroup_newpage_charge(pages[i], mm,
@@ -902,7 +904,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
if (transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow())
new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
- vma, haddr, numa_node_id());
+ vma, haddr, numa_node_id(), 0);
else
new_page = NULL;

@@ -1775,7 +1777,7 @@ static void collapse_huge_page(struct mm_struct *mm,
* scalability.
*/
new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
- node);
+ node, __GFP_OTHER_NODE);
if (unlikely(!new_page)) {
up_read(&mm->mmap_sem);
*hpage = ERR_PTR(-ENOMEM);
--
1.7.4

--
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/