[086/123] sched: Fix fork vs hotplug vs cpuset namespaces

[Greg KH <gregkh@suse.de>]

[-- Attachment #1: sched-fix-fork-vs-hotplug-vs-cpuset-namespaces.patch --]
[-- Type: text/plain, Size: 5589 bytes --]

From: Peter Zijlstra <a.p.zijlstra@chello.nl>

commit fabf318e5e4bda0aca2b0d617b191884fda62703 upstream

There are a number of issues:

1) TASK_WAKING vs cgroup_clone (cpusets)

copy_process():

  sched_fork()
    child->state = TASK_WAKING; /* waiting for wake_up_new_task() */
  if (current->nsproxy != p->nsproxy)
     ns_cgroup_clone()
       cgroup_clone()
         mutex_lock(inode->i_mutex)
         mutex_lock(cgroup_mutex)
         cgroup_attach_task()
	   ss->can_attach()
           ss->attach() [ -> cpuset_attach() ]
             cpuset_attach_task()
               set_cpus_allowed_ptr();
                 while (child->state == TASK_WAKING)
                   cpu_relax();
will deadlock the system.

2) cgroup_clone (cpusets) vs copy_process

So even if the above would work we still have:

copy_process():

  if (current->nsproxy != p->nsproxy)
     ns_cgroup_clone()
       cgroup_clone()
         mutex_lock(inode->i_mutex)
         mutex_lock(cgroup_mutex)
         cgroup_attach_task()
	   ss->can_attach()
           ss->attach() [ -> cpuset_attach() ]
             cpuset_attach_task()
               set_cpus_allowed_ptr();
  ...

  p->cpus_allowed = current->cpus_allowed

over-writing the modified cpus_allowed.

3) fork() vs hotplug

  if we unplug the child's cpu after the sanity check when the child
  gets attached to the task_list but before wake_up_new_task() shit
  will meet with fan.

Solve all these issues by moving fork cpu selection into
wake_up_new_task().

Reported-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Serge E. Hallyn <serue@us.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1264106190.4283.1314.camel@laptop>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 kernel/fork.c  |   15 ---------------
 kernel/sched.c |   39 +++++++++++++++++++++++++++------------
 2 files changed, 27 insertions(+), 27 deletions(-)

--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1233,21 +1233,6 @@ static struct task_struct *copy_process(
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
-	/*
-	 * The task hasn't been attached yet, so its cpus_allowed mask will
-	 * not be changed, nor will its assigned CPU.
-	 *
-	 * The cpus_allowed mask of the parent may have changed after it was
-	 * copied first time - so re-copy it here, then check the child's CPU
-	 * to ensure it is on a valid CPU (and if not, just force it back to
-	 * parent's CPU). This avoids alot of nasty races.
-	 */
-	p->cpus_allowed = current->cpus_allowed;
-	p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed;
-	if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
-			!cpu_online(task_cpu(p))))
-		set_task_cpu(p, smp_processor_id());
-
 	/* CLONE_PARENT re-uses the old parent */
 	if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
 		p->real_parent = current->real_parent;
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2351,14 +2351,12 @@ static int select_fallback_rq(int cpu, s
 }
 
 /*
- * Called from:
+ * Gets called from 3 sites (exec, fork, wakeup), since it is called without
+ * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
+ * by:
  *
- *  - fork, @p is stable because it isn't on the tasklist yet
- *
- *  - exec, @p is unstable, retry loop
- *
- *  - wake-up, we serialize ->cpus_allowed against TASK_WAKING so
- *             we should be good.
+ *  exec:           is unstable, retry loop
+ *  fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
  */
 static inline
 int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
@@ -2652,9 +2650,6 @@ void sched_fork(struct task_struct *p, i
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 
-#ifdef CONFIG_SMP
-	cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
-#endif
 	set_task_cpu(p, cpu);
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
@@ -2684,6 +2679,21 @@ void wake_up_new_task(struct task_struct
 {
 	unsigned long flags;
 	struct rq *rq;
+	int cpu = get_cpu();
+
+#ifdef CONFIG_SMP
+	/*
+	 * Fork balancing, do it here and not earlier because:
+	 *  - cpus_allowed can change in the fork path
+	 *  - any previously selected cpu might disappear through hotplug
+	 *
+	 * We still have TASK_WAKING but PF_STARTING is gone now, meaning
+	 * ->cpus_allowed is stable, we have preemption disabled, meaning
+	 * cpu_online_mask is stable.
+	 */
+	cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
+	set_task_cpu(p, cpu);
+#endif
 
 	rq = task_rq_lock(p, &flags);
 	BUG_ON(p->state != TASK_WAKING);
@@ -2697,6 +2707,7 @@ void wake_up_new_task(struct task_struct
 		p->sched_class->task_woken(rq, p);
 #endif
 	task_rq_unlock(rq, &flags);
+	put_cpu();
 }
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -7198,14 +7209,18 @@ int set_cpus_allowed_ptr(struct task_str
 	 * the ->cpus_allowed mask from under waking tasks, which would be
 	 * possible when we change rq->lock in ttwu(), so synchronize against
 	 * TASK_WAKING to avoid that.
+	 *
+	 * Make an exception for freshly cloned tasks, since cpuset namespaces
+	 * might move the task about, we have to validate the target in
+	 * wake_up_new_task() anyway since the cpu might have gone away.
 	 */
 again:
-	while (p->state == TASK_WAKING)
+	while (p->state == TASK_WAKING && !(p->flags & PF_STARTING))
 		cpu_relax();
 
 	rq = task_rq_lock(p, &flags);
 
-	if (p->state == TASK_WAKING) {
+	if (p->state == TASK_WAKING && !(p->flags & PF_STARTING)) {
 		task_rq_unlock(rq, &flags);
 		goto again;
 	}