memrlimit: cgroup mm owner callback changes to add task info

This patch adds an additional field to the mm_owner callbacks. This field
is required to get to the mm that changed. Hold mmap_sem in write mode
before calling the mm_owner_changed callback

[hugh@veritas.com: fix mmap_sem deadlock]
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Sudhir Kumar <skumar@linux.vnet.ibm.com>
Cc: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Cc: Paul Menage <menage@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Pavel Emelianov <xemul@openvz.org>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/cgroup.h

@@ -326,7 +326,8 @@ struct cgroup_subsys {
 	 */
 	void (*mm_owner_changed)(struct cgroup_subsys *ss,
 					struct cgroup *old,
-					struct cgroup *new);
+					struct cgroup *new,
+					struct task_struct *p);
 	int subsys_id;
 	int active;
 	int disabled;

kernel/cgroup.c

@@ -2735,6 +2735,8 @@ void cgroup_fork_callbacks(struct task_struct *child)
  * Called on every change to mm->owner. mm_init_owner() does not
  * invoke this routine, since it assigns the mm->owner the first time
  * and does not change it.
+ *
+ * The callbacks are invoked with mmap_sem held in read mode.
  */
 void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
 {
@@ -2750,7 +2752,7 @@ void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
 			if (oldcgrp == newcgrp)
 				continue;
 			if (ss->mm_owner_changed)
-				ss->mm_owner_changed(ss, oldcgrp, newcgrp);
+				ss->mm_owner_changed(ss, oldcgrp, newcgrp, new);
 		}
 	}
 }

kernel/exit.c

@@ -640,24 +640,23 @@ retry:
 assign_new_owner:
 	BUG_ON(c == p);
 	get_task_struct(c);
+	read_unlock(&tasklist_lock);
+	down_write(&mm->mmap_sem);
 	/*
 	 * 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);
+		up_write(&mm->mmap_sem);
 		put_task_struct(c);
 		goto retry;
 	}
 	cgroup_mm_owner_callbacks(mm->owner, c);
 	mm->owner = c;
 	task_unlock(c);
+	up_write(&mm->mmap_sem);
 	put_task_struct(c);
 }
 #endif /* CONFIG_MM_OWNER */