Partial revert "Basic kernel memory functionality for the Memory Controller"

This reverts commit e5671dfae59b165e2adfd4dfbdeab11ac8db5bda.

After a follow up discussion with Michal, it was agreed it would
be better to leave the kmem controller with just the tcp files,
deferring the behavior of the other general memory.kmem.* files
for a later time, when more caches are controlled. This is because
generic kmem files are not used by tcp accounting and it is
not clear how other slab caches would fit into the scheme.

We are reverting the original commit so we can track the reference.
Part of the patch is kept, because it was used by the later tcp
code. Conflicts are shown in the bottom. init/Kconfig is removed from
the revert entirely.

Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
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: David S. Miller <davem@davemloft.net>

Conflicts:

	Documentation/cgroups/memory.txt
	mm/memcontrol.c
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 6 insertions, 87 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7266202fa7cf..8cdc9156455c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -229,10 +229,6 @@ struct mem_cgroup {
 	 */
 	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.
 	 */
@@ -283,11 +279,6 @@ struct mem_cgroup {
 	 */
 	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;
@@ -359,14 +350,9 @@ enum charge_type {
 };
 
 /* for encoding cft->private value on file */
-
-enum mem_type {
-	_MEM = 0,
-	_MEMSWAP,
-	_OOM_TYPE,
-	_KMEM,
-};
-
+#define _MEM			(0)
+#define _MEMSWAP		(1)
+#define _OOM_TYPE		(2)
 #define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
 #define MEMFILE_TYPE(val)	(((val) >> 16) & 0xffff)
 #define MEMFILE_ATTR(val)	((val) & 0xffff)
@@ -3919,17 +3905,10 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 	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)
-			val += res_counter_read_u64(&memcg->res, RES_USAGE);
+			return res_counter_read_u64(&memcg->res, RES_USAGE);
 		else
-			val += res_counter_read_u64(&memcg->memsw, RES_USAGE);
-
-		return val;
+			return res_counter_read_u64(&memcg->memsw, RES_USAGE);
 	}
 
 	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
@@ -3962,11 +3941,6 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 		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;
@@ -4696,59 +4670,8 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
 #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));
-
 	/*
 	 * Part of this would be better living in a separate allocation
 	 * function, leaving us with just the cgroup tree population work.
@@ -4756,9 +4679,7 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
 	 * is only initialized after cgroup creation. I found the less
 	 * cumbersome way to deal with it to defer it all to populate time
 	 */
-	if (!ret)
-		ret = mem_cgroup_sockets_init(cont, ss);
-	return ret;
+	return mem_cgroup_sockets_init(cont, ss);
 };
 
 static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
@@ -5092,7 +5013,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	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.
@@ -5103,7 +5023,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	} 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;