[PATCH -V7 12/14] hugetlb: add charge/uncharge calls for HugeTLB alloc/free

[Aneesh Kumar K.V]

From: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxxxxxxx>

This adds necessary charge/uncharge calls in the HugeTLB code.  We do
hugetlb cgroup charge in page alloc and uncharge in compound page destructor.  We
also need to ignore HugeTLB pages in __mem_cgroup_uncharge_common because
that get called from delete_from_page_cache

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Acked-by: Hillf Danton <dhillf@xxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
---
 mm/hugetlb.c    |   16 +++++++++++++++-
 mm/memcontrol.c |    5 +++++
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6330de2..cad7a4d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -625,6 +625,8 @@ static void free_huge_page(struct page *page)
 	BUG_ON(page_count(page));
 	BUG_ON(page_mapcount(page));
 
+	hugetlb_cgroup_uncharge_page(hstate_index(h),
+				     pages_per_huge_page(h), page);
 	spin_lock(&hugetlb_lock);
 	if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
 		/* remove the page from active list */
@@ -1112,7 +1114,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	struct hstate *h = hstate_vma(vma);
 	struct page *page;
 	long chg;
+	int ret, idx;
+	struct hugetlb_cgroup *h_cg;
 
+	idx = hstate_index(h);
 	/*
 	 * Processes that did not create the mapping will have no
 	 * reserves and will not have accounted against subpool
@@ -1128,6 +1133,11 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 		if (hugepage_subpool_get_pages(spool, chg))
 			return ERR_PTR(-ENOSPC);
 
+	ret = hugetlb_cgroup_charge_page(idx, pages_per_huge_page(h), &h_cg);
+	if (ret) {
+		hugepage_subpool_put_pages(spool, chg);
+		return ERR_PTR(-ENOSPC);
+	}
 	spin_lock(&hugetlb_lock);
 	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
 	spin_unlock(&hugetlb_lock);
@@ -1135,6 +1145,9 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	if (!page) {
 		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
 		if (!page) {
+			hugetlb_cgroup_uncharge_cgroup(idx,
+						       pages_per_huge_page(h),
+						       h_cg);
 			hugepage_subpool_put_pages(spool, chg);
 			return ERR_PTR(-ENOSPC);
 		}
@@ -1143,7 +1156,8 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	set_page_private(page, (unsigned long)spool);
 
 	vma_commit_reservation(h, vma, addr);
-
+	/* update page cgroup details */
+	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
 	return page;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6df019b..a52780b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2931,6 +2931,11 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 
 	if (PageSwapCache(page))
 		return NULL;
+	/*
+	 * HugeTLB page uncharge happen in the HugeTLB compound page destructor
+	 */
+	if (PageHuge(page))
+		return NULL;
 
 	if (PageTransHuge(page)) {
 		nr_pages <<= compound_order(page);
-- 
1.7.10

--
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/