[patch v2] mm, hugetlb_cgroup: round limit_in_bytes down to hugepage size

[David Rientjes <rientjes@xxxxxxxxxx>]

The page_counter rounds limits down to page size values.  This makes
sense, except in the case of hugetlb_cgroup where it's not possible to
charge partial hugepages.

Round the hugetlb_cgroup limit down to hugepage size.

Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
---
 mm/hugetlb_cgroup.c | 35 ++++++++++++++++++++++++++---------
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -67,26 +67,42 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
 	return false;
 }
 
+static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup,
+				struct hugetlb_cgroup *parent_h_cgroup)
+{
+	int idx;
+
+	for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) {
+		struct page_counter *counter = &h_cgroup->hugepage[idx];
+		struct page_counter *parent = NULL;
+		unsigned long limit;
+		int ret;
+
+		if (parent_h_cgroup)
+			parent = &parent_h_cgroup->hugepage[idx];
+		page_counter_init(counter, parent);
+
+		limit = round_down(PAGE_COUNTER_MAX,
+				   1 << huge_page_order(&hstates[idx]));
+		ret = page_counter_limit(counter, limit);
+		VM_BUG_ON(ret);
+	}
+}
+
 static struct cgroup_subsys_state *
 hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css);
 	struct hugetlb_cgroup *h_cgroup;
-	int idx;
 
 	h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL);
 	if (!h_cgroup)
 		return ERR_PTR(-ENOMEM);
 
-	if (parent_h_cgroup) {
-		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			page_counter_init(&h_cgroup->hugepage[idx],
-					  &parent_h_cgroup->hugepage[idx]);
-	} else {
+	if (!parent_h_cgroup)
 		root_h_cgroup = h_cgroup;
-		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			page_counter_init(&h_cgroup->hugepage[idx], NULL);
-	}
+
+	hugetlb_cgroup_init(h_cgroup, parent_h_cgroup);
 	return &h_cgroup->css;
 }
 
@@ -285,6 +301,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 		return ret;
 
 	idx = MEMFILE_IDX(of_cft(of)->private);
+	nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx]));
 
 	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>