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, 83 insertions, 0 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 2a9d98c..ae0f2c4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -557,6 +557,88 @@ void exit_fs(struct task_struct *tsk)
 
 EXPORT_SYMBOL_GPL(exit_fs);
 
+#ifdef CONFIG_MM_OWNER
+/*
+ * Task p is exiting and it owned mm, lets find a new owner for it
+ */
+static inline int
+mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
+{
+	/*
+	 * If there are other users of the mm and the owner (us) is exiting
+	 * we need to find a new owner to take on the responsibility.
+	 */
+	if (!mm)
+		return 0;
+	if (atomic_read(&mm->mm_users) <= 1)
+		return 0;
+	if (mm->owner != p)
+		return 0;
+	return 1;
+}
+
+void mm_update_next_owner(struct mm_struct *mm)
+{
+	struct task_struct *c, *g, *p = current;
+
+retry:
+	if (!mm_need_new_owner(mm, p))
+		return;
+
+	read_lock(&tasklist_lock);
+	/*
+	 * Search in the children
+	 */
+	list_for_each_entry(c, &p->children, sibling) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	}
+
+	/*
+	 * Search in the siblings
+	 */
+	list_for_each_entry(c, &p->parent->children, sibling) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	}
+
+	/*
+	 * Search through everything else. We should not get
+	 * here often
+	 */
+	do_each_thread(g, c) {
+		if (c->mm == mm)
+			goto assign_new_owner;
+	} while_each_thread(g, c);
+
+	read_unlock(&tasklist_lock);
+	return;
+
+assign_new_owner:
+	BUG_ON(c == p);
+	get_task_struct(c);
+	/*
+	 * The task_lock protects c->mm from changing.
+	 * We always want mm->owner->mm == mm
+	 */
+	task_lock(c);
+	/*
+	 * Delay read_unlock() till we have the task_lock()
+	 * to ensure that c does not slip away underneath us
+	 */
+	read_unlock(&tasklist_lock);
+	if (c->mm != mm) {
+		task_unlock(c);
+		put_task_struct(c);
+		goto retry;
+	}
+	cgroup_mm_owner_callbacks(mm->owner, c);
+	mm->owner = c;
+	task_unlock(c);
+	put_task_struct(c);
+}
+#endif /* CONFIG_MM_OWNER */
+
 /*
  * Turn us into a lazy TLB process if we
  * aren't already..
@@ -596,6 +678,7 @@ static void exit_mm(struct task_struct * tsk)
 	/* We don't want this task to be frozen prematurely */
 	clear_freeze_flag(tsk);
 	task_unlock(tsk);
+	mm_update_next_owner(mm);
 	mmput(mm);
 }