Basic kernel memory functionality for the Memory Controller
This patch lays down the foundation for the kernel memory component
of the Memory Controller.
As of today, I am only laying down the following files:
* memory.independent_kmem_limit
* memory.kmem.limit_in_bytes (currently ignored)
* memory.kmem.usage_in_bytes (always zero)
Signed-off-by: Glauber Costa <glommer@parallels.com>
CC: Kirill A. Shutemov <kirill@shutemov.name>
CC: Paul Menage <paul@paulmenage.org>
CC: Greg Thelen <gthelen@google.com>
CC: Johannes Weiner <jweiner@redhat.com>
CC: Michal Hocko <mhocko@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6aff93c..9fbcff7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -227,6 +227,10 @@
*/
struct res_counter memsw;
/*
+ * the counter to account for kmem usage.
+ */
+ struct res_counter kmem;
+ /*
* Per cgroup active and inactive list, similar to the
* per zone LRU lists.
*/
@@ -277,6 +281,11 @@
*/
unsigned long move_charge_at_immigrate;
/*
+ * Should kernel memory limits be stabilished independently
+ * from user memory ?
+ */
+ int kmem_independent_accounting;
+ /*
* percpu counter.
*/
struct mem_cgroup_stat_cpu *stat;
@@ -344,9 +353,14 @@
};
/* for encoding cft->private value on file */
-#define _MEM (0)
-#define _MEMSWAP (1)
-#define _OOM_TYPE (2)
+
+enum mem_type {
+ _MEM = 0,
+ _MEMSWAP,
+ _OOM_TYPE,
+ _KMEM,
+};
+
#define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val))
#define MEMFILE_TYPE(val) (((val) >> 16) & 0xffff)
#define MEMFILE_ATTR(val) ((val) & 0xffff)
@@ -3848,10 +3862,17 @@
u64 val;
if (!mem_cgroup_is_root(memcg)) {
+ val = 0;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ if (!memcg->kmem_independent_accounting)
+ val = res_counter_read_u64(&memcg->kmem, RES_USAGE);
+#endif
if (!swap)
- return res_counter_read_u64(&memcg->res, RES_USAGE);
+ val += res_counter_read_u64(&memcg->res, RES_USAGE);
else
- return res_counter_read_u64(&memcg->memsw, RES_USAGE);
+ val += res_counter_read_u64(&memcg->memsw, RES_USAGE);
+
+ return val;
}
val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
@@ -3884,6 +3905,11 @@
else
val = res_counter_read_u64(&memcg->memsw, name);
break;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+ case _KMEM:
+ val = res_counter_read_u64(&memcg->kmem, name);
+ break;
+#endif
default:
BUG();
break;
@@ -4612,6 +4638,69 @@
}
#endif /* CONFIG_NUMA */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+static u64 kmem_limit_independent_read(struct cgroup *cgroup, struct cftype *cft)
+{
+ return mem_cgroup_from_cont(cgroup)->kmem_independent_accounting;
+}
+
+static int kmem_limit_independent_write(struct cgroup *cgroup, struct cftype *cft,
+ u64 val)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
+ struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+
+ val = !!val;
+
+ /*
+ * This follows the same hierarchy restrictions than
+ * mem_cgroup_hierarchy_write()
+ */
+ if (!parent || !parent->use_hierarchy) {
+ if (list_empty(&cgroup->children))
+ memcg->kmem_independent_accounting = val;
+ else
+ return -EBUSY;
+ }
+ else
+ return -EINVAL;
+
+ return 0;
+}
+static struct cftype kmem_cgroup_files[] = {
+ {
+ .name = "independent_kmem_limit",
+ .read_u64 = kmem_limit_independent_read,
+ .write_u64 = kmem_limit_independent_write,
+ },
+ {
+ .name = "kmem.usage_in_bytes",
+ .private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
+ .read_u64 = mem_cgroup_read,
+ },
+ {
+ .name = "kmem.limit_in_bytes",
+ .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
+ .read_u64 = mem_cgroup_read,
+ },
+};
+
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+ int ret = 0;
+
+ ret = cgroup_add_files(cont, ss, kmem_cgroup_files,
+ ARRAY_SIZE(kmem_cgroup_files));
+ return ret;
+};
+
+#else
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+ return 0;
+}
+#endif
+
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
@@ -4925,6 +5014,7 @@
if (parent && parent->use_hierarchy) {
res_counter_init(&memcg->res, &parent->res);
res_counter_init(&memcg->memsw, &parent->memsw);
+ res_counter_init(&memcg->kmem, &parent->kmem);
/*
* We increment refcnt of the parent to ensure that we can
* safely access it on res_counter_charge/uncharge.
@@ -4935,6 +5025,7 @@
} else {
res_counter_init(&memcg->res, NULL);
res_counter_init(&memcg->memsw, NULL);
+ res_counter_init(&memcg->kmem, NULL);
}
memcg->last_scanned_child = 0;
memcg->last_scanned_node = MAX_NUMNODES;
@@ -4978,6 +5069,10 @@
if (!ret)
ret = register_memsw_files(cont, ss);
+
+ if (!ret)
+ ret = register_kmem_files(cont, ss);
+
return ret;
}