hugetlb/cgroup: add hugetlb cgroup control files

Add the control files for hugetlb controller

[akpm@linux-foundation.org: s/CONFIG_CGROUP_HUGETLB_RES_CTLR/CONFIG_MEMCG_HUGETLB/g]
[akpm@linux-foundation.org: s/CONFIG_MEMCG_HUGETLB/CONFIG_CGROUP_HUGETLB/]
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hillf Danton <dhillf@gmail.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 137 insertions, 0 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 16a0f32c482..c57740bb203 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -30,6 +30,7 @@
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/node.h>
+#include <linux/hugetlb_cgroup.h>
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
@@ -1930,6 +1931,13 @@ void __init hugetlb_add_hstate(unsigned order)
 	h->next_nid_to_free = first_node(node_states[N_HIGH_MEMORY]);
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
+	/*
+	 * Add cgroup control files only if the huge page consists
+	 * of more than two normal pages. This is because we use
+	 * page[2].lru.next for storing cgoup details.
+	 */
+	if (order >= HUGETLB_CGROUP_MIN_ORDER)
+		hugetlb_cgroup_file_init(hugetlb_max_hstate - 1);
 
 	parsed_hstate = h;
 }
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index bc518bedea9..d1ca1196e62 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -26,6 +26,10 @@ struct hugetlb_cgroup {
 	struct res_counter hugepage[HUGE_MAX_HSTATE];
 };
 
+#define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
+#define MEMFILE_IDX(val)	(((val) >> 16) & 0xffff)
+#define MEMFILE_ATTR(val)	((val) & 0xffff)
+
 struct cgroup_subsys hugetlb_subsys __read_mostly;
 static struct hugetlb_cgroup *root_h_cgroup __read_mostly;
 
@@ -257,6 +261,131 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 	return;
 }
 
+static ssize_t hugetlb_cgroup_read(struct cgroup *cgroup, struct cftype *cft,
+				   struct file *file, char __user *buf,
+				   size_t nbytes, loff_t *ppos)
+{
+	u64 val;
+	char str[64];
+	int idx, name, len;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+	idx = MEMFILE_IDX(cft->private);
+	name = MEMFILE_ATTR(cft->private);
+
+	val = res_counter_read_u64(&h_cg->hugepage[idx], name);
+	len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val);
+	return simple_read_from_buffer(buf, nbytes, ppos, str, len);
+}
+
+static int hugetlb_cgroup_write(struct cgroup *cgroup, struct cftype *cft,
+				const char *buffer)
+{
+	int idx, name, ret;
+	unsigned long long val;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+	idx = MEMFILE_IDX(cft->private);
+	name = MEMFILE_ATTR(cft->private);
+
+	switch (name) {
+	case RES_LIMIT:
+		if (hugetlb_cgroup_is_root(h_cg)) {
+			/* Can't set limit on root */
+			ret = -EINVAL;
+			break;
+		}
+		/* This function does all necessary parse...reuse it */
+		ret = res_counter_memparse_write_strategy(buffer, &val);
+		if (ret)
+			break;
+		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static int hugetlb_cgroup_reset(struct cgroup *cgroup, unsigned int event)
+{
+	int idx, name, ret = 0;
+	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_cgroup(cgroup);
+
+	idx = MEMFILE_IDX(event);
+	name = MEMFILE_ATTR(event);
+
+	switch (name) {
+	case RES_MAX_USAGE:
+		res_counter_reset_max(&h_cg->hugepage[idx]);
+		break;
+	case RES_FAILCNT:
+		res_counter_reset_failcnt(&h_cg->hugepage[idx]);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static char *mem_fmt(char *buf, int size, unsigned long hsize)
+{
+	if (hsize >= (1UL << 30))
+		snprintf(buf, size, "%luGB", hsize >> 30);
+	else if (hsize >= (1UL << 20))
+		snprintf(buf, size, "%luMB", hsize >> 20);
+	else
+		snprintf(buf, size, "%luKB", hsize >> 10);
+	return buf;
+}
+
+int __init hugetlb_cgroup_file_init(int idx)
+{
+	char buf[32];
+	struct cftype *cft;
+	struct hstate *h = &hstates[idx];
+
+	/* format the size */
+	mem_fmt(buf, 32, huge_page_size(h));
+
+	/* Add the limit file */
+	cft = &h->cgroup_files[0];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf);
+	cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);
+	cft->read = hugetlb_cgroup_read;
+	cft->write_string = hugetlb_cgroup_write;
+
+	/* Add the usage file */
+	cft = &h->cgroup_files[1];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf);
+	cft->private = MEMFILE_PRIVATE(idx, RES_USAGE);
+	cft->read = hugetlb_cgroup_read;
+
+	/* Add the MAX usage file */
+	cft = &h->cgroup_files[2];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf);
+	cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE);
+	cft->trigger = hugetlb_cgroup_reset;
+	cft->read = hugetlb_cgroup_read;
+
+	/* Add the failcntfile */
+	cft = &h->cgroup_files[3];
+	snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf);
+	cft->private  = MEMFILE_PRIVATE(idx, RES_FAILCNT);
+	cft->trigger  = hugetlb_cgroup_reset;
+	cft->read = hugetlb_cgroup_read;
+
+	/* NULL terminate the last cft */
+	cft = &h->cgroup_files[4];
+	memset(cft, 0, sizeof(*cft));
+
+	WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files));
+
+	return 0;
+}
+
 struct cgroup_subsys hugetlb_subsys = {
 	.name = "hugetlb",
 	.create     = hugetlb_cgroup_create,