cgroups: add an owner to the mm_struct

Remove the mem_cgroup member from mm_struct and instead adds an owner.

This approach was suggested by Paul Menage.  The advantage of this approach
is that, once the mm->owner is known, using the subsystem id, the cgroup
can be determined.  It also allows several control groups that are
virtually grouped by mm_struct, to exist independent of the memory
controller i.e., without adding mem_cgroup's for each controller, to
mm_struct.

A new config option CONFIG_MM_OWNER is added and the memory resource
controller selects this config option.

This patch also adds cgroup callbacks to notify subsystems when mm->owner
changes.  The mm_cgroup_changed callback is called with the task_lock() of
the new task held and is called just prior to changing the mm->owner.

I am indebted to Paul Menage for the several reviews of this patchset and
helping me make it lighter and simpler.

This patch was tested on a powerpc box, it was compiled with both the
MM_OWNER config turned on and off.

After the thread group leader exits, it's moved to init_css_state by
cgroup_exit(), thus all future charges from runnings threads would be
redirected to the init_css_set's subsystem.

Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Hirokazu Takahashi <taka@valinux.co.jp>
Cc: David Rientjes <rientjes@google.com>,
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Reviewed-by: Paul Menage <menage@google.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 5 insertions, 23 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d12795cc7622..49d80814798b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -236,26 +236,12 @@ static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 				css);
 }
 
-static struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
+struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 {
 	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
 				struct mem_cgroup, css);
 }
 
-void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p)
-{
-	struct mem_cgroup *mem;
-
-	mem = mem_cgroup_from_task(p);
-	css_get(&mem->css);
-	mm->mem_cgroup = mem;
-}
-
-void mm_free_cgroup(struct mm_struct *mm)
-{
-	css_put(&mm->mem_cgroup->css);
-}
-
 static inline int page_cgroup_locked(struct page *page)
 {
 	return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
@@ -476,6 +462,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	int zid = zone_idx(z);
 	struct mem_cgroup_per_zone *mz;
 
+	BUG_ON(!mem_cont);
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
 	if (active)
 		src = &mz->active_list;
@@ -574,7 +561,7 @@ retry:
 		mm = &init_mm;
 
 	rcu_read_lock();
-	mem = rcu_dereference(mm->mem_cgroup);
+	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	/*
 	 * For every charge from the cgroup, increment reference count
 	 */
@@ -985,10 +972,9 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	struct mem_cgroup *mem;
 	int node;
 
-	if (unlikely((cont->parent) == NULL)) {
+	if (unlikely((cont->parent) == NULL))
 		mem = &init_mem_cgroup;
-		init_mm.mem_cgroup = mem;
-	} else
+	else
 		mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
 
 	if (mem == NULL)
@@ -1067,10 +1053,6 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 	if (!thread_group_leader(p))
 		goto out;
 
-	css_get(&mem->css);
-	rcu_assign_pointer(mm->mem_cgroup, mem);
-	css_put(&old_mem->css);
-
 out:
 	mmput(mm);
 }