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>

4 files changed, 34 insertions, 15 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 095248082b7e..e155aa78d859 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -305,6 +305,12 @@ struct cgroup_subsys {
                         struct cgroup *cgrp);
         void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
         void (*bind)(struct cgroup_subsys *ss, struct cgroup *root);
+        /*
+         * This routine is called with the task_lock of mm->owner held
+         */
+        void (*mm_owner_changed)(struct cgroup_subsys *ss,
+                                        struct cgroup *old,
+                                        struct cgroup *new);
         int subsys_id;
         int active;
         int disabled;
@@ -390,4 +396,13 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 
 #endif /* !CONFIG_CGROUPS */
 
+#ifdef CONFIG_MM_OWNER
+extern void
+cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new);
+#else /* !CONFIG_MM_OWNER */
+static inline void
+cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
+{
+}
+#endif /* CONFIG_MM_OWNER */
 #endif /* _LINUX_CGROUP_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8b1c4295848b..e6608776bc96 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -27,9 +27,6 @@ struct mm_struct;
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
-extern void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p);
-extern void mm_free_cgroup(struct mm_struct *mm);
-
 #define page_reset_bad_cgroup(page)     ((page)->page_cgroup = 0)
 
 extern struct page_cgroup *page_get_page_cgroup(struct page *page);
@@ -48,8 +45,10 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
 
+extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
+
 #define mm_match_cgroup(mm, cgroup)     \
-        ((cgroup) == rcu_dereference((mm)->mem_cgroup))
+        ((cgroup) == mem_cgroup_from_task((mm)->owner))
 
 extern int mem_cgroup_prepare_migration(struct page *page);
 extern void mem_cgroup_end_migration(struct page *page);
@@ -73,15 +72,6 @@ extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
                                 struct zone *zone, int priority);
 
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
-static inline void mm_init_cgroup(struct mm_struct *mm,
-                                        struct task_struct *p)
-{
-}
-
-static inline void mm_free_cgroup(struct mm_struct *mm)
-{
-}
-
 static inline void page_reset_bad_cgroup(struct page *page)
 {
 }
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index e2bae8dde35a..bc97bd54f606 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -225,8 +225,9 @@ struct mm_struct {
         /* aio bits */
         rwlock_t                ioctx_list_lock;        /* aio lock */
         struct kioctx           *ioctx_list;
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-        struct mem_cgroup *mem_cgroup;
+#ifdef CONFIG_MM_OWNER
+        struct task_struct *owner;      /* The thread group leader that */
+                                        /* owns the mm_struct.          */
 #endif
 };
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 024d72b47a0c..1d02babdb2c7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2148,6 +2148,19 @@ static inline void migration_init(void)
 #define TASK_SIZE_OF(tsk)       TASK_SIZE
 #endif
 
+#ifdef CONFIG_MM_OWNER
+extern void mm_update_next_owner(struct mm_struct *mm);
+extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
+#else
+static inline void mm_update_next_owner(struct mm_struct *mm)
+{
+}
+
+static inline void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
+{
+}
+#endif /* CONFIG_MM_OWNER */
+
 #endif /* __KERNEL__ */
 
 #endif