sched/autogroup: Fix crash on reboot when autogroup is disabled

Due to these two commits:

  8323f26ce342 sched: Fix race in task_group()
  800d4d30c8f2 sched, autogroup: Stop going ahead if autogroup is disabled

... autogroup scheduling's dynamic knobs are wrecked.

With both patches applied, all you have to do to crash a box is
disable autogroup during boot up, then reboot.. boom, NULL pointer
dereference due to 800d4d30 not allowing autogroup to move things,
and 8323f26ce making that the only way to switch runqueues.

Remove most of the (dysfunctional) knobs and turn the remaining
sched_autogroup_enabled knob readonly.

If the user fiddles with cgroups hereafter, once tasks
are moved, autogroup won't mess with them again unless
they call setsid().

No knobs, no glitz, nada, just a cute little thing folks can
turn on if they don't want to muck about with cgroups and/or
systemd.

Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Xiaotian Feng <xtfeng@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Xiaotian Feng <dannyfeng@tencent.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: <stable@vger.kernel.org> # v3.6
Link: http://lkml.kernel.org/r/1351451963.4999.8.camel@maggy.simpson.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 12 insertions, 65 deletions

diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 0984a21076a3..0f1bacb005a4 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -110,6 +110,9 @@ out_fail:
 
 bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 {
+	if (!sysctl_sched_autogroup_enabled)
+		return false;
+
 	if (tg != &root_task_group)
 		return false;
 
@@ -143,15 +146,11 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 
 	p->signal->autogroup = autogroup_kref_get(ag);
 
-	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
-		goto out;
-
 	t = p;
 	do {
 		sched_move_task(t);
 	} while_each_thread(p, t);
 
-out:
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
 }
@@ -159,8 +158,11 @@ out:
 /* Allocates GFP_KERNEL, cannot be called under any spinlock */
 void sched_autogroup_create_attach(struct task_struct *p)
 {
-	struct autogroup *ag = autogroup_create();
+	struct autogroup *ag;
 
+	if (!sysctl_sched_autogroup_enabled)
+		return;
+	ag = autogroup_create();
 	autogroup_move_group(p, ag);
 	/* drop extra reference added by autogroup_create() */
 	autogroup_kref_put(ag);
@@ -176,11 +178,15 @@ EXPORT_SYMBOL(sched_autogroup_detach);
 
 void sched_autogroup_fork(struct signal_struct *sig)
 {
+	if (!sysctl_sched_autogroup_enabled)
+		return;
 	sig->autogroup = autogroup_task_get(current);
 }
 
 void sched_autogroup_exit(struct signal_struct *sig)
 {
+	if (!sysctl_sched_autogroup_enabled)
+		return;
 	autogroup_kref_put(sig->autogroup);
 }
 
@@ -193,58 +199,6 @@ static int __init setup_autogroup(char *str)
 
 __setup("noautogroup", setup_autogroup);
 
-#ifdef CONFIG_PROC_FS
-
-int proc_sched_autogroup_set_nice(struct task_struct *p, int nice)
-{
-	static unsigned long next = INITIAL_JIFFIES;
-	struct autogroup *ag;
-	int err;
-
-	if (nice < -20 || nice > 19)
-		return -EINVAL;
-
-	err = security_task_setnice(current, nice);
-	if (err)
-		return err;
-
-	if (nice < 0 && !can_nice(current, nice))
-		return -EPERM;
-
-	/* this is a heavy operation taking global locks.. */
-	if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next))
-		return -EAGAIN;
-
-	next = HZ / 10 + jiffies;
-	ag = autogroup_task_get(p);
-
-	down_write(&ag->lock);
-	err = sched_group_set_shares(ag->tg, prio_to_weight[nice + 20]);
-	if (!err)
-		ag->nice = nice;
-	up_write(&ag->lock);
-
-	autogroup_kref_put(ag);
-
-	return err;
-}
-
-void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
-{
-	struct autogroup *ag = autogroup_task_get(p);
-
-	if (!task_group_is_autogroup(ag->tg))
-		goto out;
-
-	down_read(&ag->lock);
-	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
-	up_read(&ag->lock);
-
-out:
-	autogroup_kref_put(ag);
-}
-#endif /* CONFIG_PROC_FS */
-
 #ifdef CONFIG_SCHED_DEBUG
 int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
diff --git a/kernel/sched/auto_group.h b/kernel/sched/auto_group.h
index 8bd047142816..4552c6bf79d2 100644
--- a/kernel/sched/auto_group.h
+++ b/kernel/sched/auto_group.h
@@ -4,11 +4,6 @@
 #include <linux/rwsem.h>
 
 struct autogroup {
-	/*
-	 * reference doesn't mean how many thread attach to this
-	 * autogroup now. It just stands for the number of task
-	 * could use this autogroup.
-	 */
 	struct kref		kref;
 	struct task_group	*tg;
 	struct rw_semaphore	lock;
@@ -29,9 +24,7 @@ extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg);
 static inline struct task_group *
 autogroup_task_group(struct task_struct *p, struct task_group *tg)
 {
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
-	if (enabled && task_wants_autogroup(p, tg))
+	if (task_wants_autogroup(p, tg))
 		return p->signal->autogroup->tg;
 
 	return tg;