Merge commit 'v2.6.26-rc8' into core/softlockup

7 files changed, 164 insertions, 64 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 039baa4cd90..9fceb97e989 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1037,8 +1037,8 @@ int current_cpuset_is_being_rebound(void)
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
-	if ((int)val < 0)
-		val = -1;
+	if (val < -1 || val >= SD_LV_MAX)
+		return -EINVAL;
 
 	if (val != cs->relax_domain_level) {
 		cs->relax_domain_level = val;
@@ -1890,6 +1890,12 @@ static void common_cpu_mem_hotplug_unplug(void)
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 	scan_for_empty_cpusets(&top_cpuset);
 
+	/*
+	 * Scheduler destroys domains on hotplug events.
+	 * Rebuild them based on the current settings.
+	 */
+	rebuild_sched_domains();
+
 	cgroup_unlock();
 }
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 449def8074f..7d1136e97c1 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1096,21 +1096,64 @@ static void unqueue_me_pi(struct futex_q *q)
  * private futexes.
  */
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *newowner)
+				struct task_struct *newowner,
+				struct rw_semaphore *fshared)
 {
 	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
+	struct task_struct *oldowner = pi_state->owner;
 	u32 uval, curval, newval;
-	int ret;
+	int ret, attempt = 0;
 
 	/* Owner died? */
+	if (!pi_state->owner)
+		newtid |= FUTEX_OWNER_DIED;
+
+	/*
+	 * We are here either because we stole the rtmutex from the
+	 * pending owner or we are the pending owner which failed to
+	 * get the rtmutex. We have to replace the pending owner TID
+	 * in the user space variable. This must be atomic as we have
+	 * to preserve the owner died bit here.
+	 *
+	 * Note: We write the user space value _before_ changing the
+	 * pi_state because we can fault here. Imagine swapped out
+	 * pages or a fork, which was running right before we acquired
+	 * mmap_sem, that marked all the anonymous memory readonly for
+	 * cow.
+	 *
+	 * Modifying pi_state _before_ the user space value would
+	 * leave the pi_state in an inconsistent state when we fault
+	 * here, because we need to drop the hash bucket lock to
+	 * handle the fault. This might be observed in the PID check
+	 * in lookup_pi_state.
+	 */
+retry:
+	if (get_futex_value_locked(&uval, uaddr))
+		goto handle_fault;
+
+	while (1) {
+		newval = (uval & FUTEX_OWNER_DIED) | newtid;
+
+		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+
+		if (curval == -EFAULT)
+			goto handle_fault;
+		if (curval == uval)
+			break;
+		uval = curval;
+	}
+
+	/*
+	 * We fixed up user space. Now we need to fix the pi_state
+	 * itself.
+	 */
 	if (pi_state->owner != NULL) {
 		spin_lock_irq(&pi_state->owner->pi_lock);
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		spin_unlock_irq(&pi_state->owner->pi_lock);
-	} else
-		newtid |= FUTEX_OWNER_DIED;
+	}
 
 	pi_state->owner = newowner;
 
@@ -1118,26 +1161,35 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &newowner->pi_state_list);
 	spin_unlock_irq(&newowner->pi_lock);
+	return 0;
 
 	/*
-	 * We own it, so we have to replace the pending owner
-	 * TID. This must be atomic as we have preserve the
-	 * owner died bit here.
+	 * To handle the page fault we need to drop the hash bucket
+	 * lock here. That gives the other task (either the pending
+	 * owner itself or the task which stole the rtmutex) the
+	 * chance to try the fixup of the pi_state. So once we are
+	 * back from handling the fault we need to check the pi_state
+	 * after reacquiring the hash bucket lock and before trying to
+	 * do another fixup. When the fixup has been done already we
+	 * simply return.
 	 */
-	ret = get_futex_value_locked(&uval, uaddr);
+handle_fault:
+	spin_unlock(q->lock_ptr);
 
-	while (!ret) {
-		newval = (uval & FUTEX_OWNER_DIED) | newtid;
+	ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++);
 
-		curval = cmpxchg_futex_value_locked(uaddr, uval, newval);
+	spin_lock(q->lock_ptr);
 
-		if (curval == -EFAULT)
-			ret = -EFAULT;
-		if (curval == uval)
-			break;
-		uval = curval;
-	}
-	return ret;
+	/*
+	 * Check if someone else fixed it for us:
+	 */
+	if (pi_state->owner != oldowner)
+		return 0;
+
+	if (ret)
+		return ret;
+
+	goto retry;
 }
 
 /*
@@ -1507,7 +1559,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 		 * that case:
 		 */
 		if (q.pi_state->owner != curr)
-			ret = fixup_pi_state_owner(uaddr, &q, curr);
+			ret = fixup_pi_state_owner(uaddr, &q, curr, fshared);
 	} else {
 		/*
 		 * Catch the rare case, where the lock was released
@@ -1539,7 +1591,8 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 				int res;
 
 				owner = rt_mutex_owner(&q.pi_state->pi_mutex);
-				res = fixup_pi_state_owner(uaddr, &q, owner);
+				res = fixup_pi_state_owner(uaddr, &q, owner,
+							   fshared);
 
 				/* propagate -EFAULT, if the fixup failed */
 				if (res)
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 79e3c90113c..3ec23c3ec97 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -1499,7 +1499,8 @@ int kgdb_nmicallback(int cpu, void *regs)
 	return 1;
 }
 
-void kgdb_console_write(struct console *co, const char *s, unsigned count)
+static void kgdb_console_write(struct console *co, const char *s,
+   unsigned count)
 {
 	unsigned long flags;
 
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index e1cdf196a51..5e02b774070 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -217,8 +217,6 @@ long rcu_batches_completed(void)
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
-
 void __rcu_read_lock(void)
 {
 	int idx;
diff --git a/kernel/sched.c b/kernel/sched.c
index eaf6751e761..3aaa5c8cb42 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1127,6 +1127,7 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
+#ifdef CONFIG_SMP
 static void hotplug_hrtick_disable(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -1182,6 +1183,7 @@ static void init_hrtick(void)
 {
 	hotcpu_notifier(hotplug_hrtick, 0);
 }
+#endif /* CONFIG_SMP */
 
 static void init_rq_hrtick(struct rq *rq)
 {
@@ -4396,22 +4398,20 @@ do_wait_for_common(struct completion *x, long timeout, int state)
 			     signal_pending(current)) ||
 			    (state == TASK_KILLABLE &&
 			     fatal_signal_pending(current))) {
-				__remove_wait_queue(&x->wait, &wait);
-				return -ERESTARTSYS;
+				timeout = -ERESTARTSYS;
+				break;
 			}
 			__set_current_state(state);
 			spin_unlock_irq(&x->wait.lock);
 			timeout = schedule_timeout(timeout);
 			spin_lock_irq(&x->wait.lock);
-			if (!timeout) {
-				__remove_wait_queue(&x->wait, &wait);
-				return timeout;
-			}
-		} while (!x->done);
+		} while (!x->done && timeout);
 		__remove_wait_queue(&x->wait, &wait);
+		if (!x->done)
+			return timeout;
 	}
 	x->done--;
-	return timeout;
+	return timeout ?: 1;
 }
 
 static long __sched
@@ -6877,7 +6877,12 @@ static int default_relax_domain_level = -1;
 
 static int __init setup_relax_domain_level(char *str)
 {
-	default_relax_domain_level = simple_strtoul(str, NULL, 0);
+	unsigned long val;
+
+	val = simple_strtoul(str, NULL, 0);
+	if (val < SD_LV_MAX)
+		default_relax_domain_level = val;
+
 	return 1;
 }
 __setup("relax_domain_level=", setup_relax_domain_level);
@@ -7236,6 +7241,18 @@ void __attribute__((weak)) arch_update_cpu_topology(void)
 }
 
 /*
+ * Free current domain masks.
+ * Called after all cpus are attached to NULL domain.
+ */
+static void free_sched_domains(void)
+{
+	ndoms_cur = 0;
+	if (doms_cur != &fallback_doms)
+		kfree(doms_cur);
+	doms_cur = &fallback_doms;
+}
+
+/*
  * Set up scheduler domains and groups. Callers must hold the hotplug lock.
  * For now this just excludes isolated cpus, but could be used to
  * exclude other special cases in the future.
@@ -7382,6 +7399,7 @@ int arch_reinit_sched_domains(void)
 	get_online_cpus();
 	mutex_lock(&sched_domains_mutex);
 	detach_destroy_domains(&cpu_online_map);
+	free_sched_domains();
 	err = arch_init_sched_domains(&cpu_online_map);
 	mutex_unlock(&sched_domains_mutex);
 	put_online_cpus();
@@ -7467,6 +7485,7 @@ static int update_sched_domains(struct notifier_block *nfb,
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		detach_destroy_domains(&cpu_online_map);
+		free_sched_domains();
 		return NOTIFY_OK;
 
 	case CPU_UP_CANCELED:
@@ -7485,8 +7504,16 @@ static int update_sched_domains(struct notifier_block *nfb,
 		return NOTIFY_DONE;
 	}
 
+#ifndef CONFIG_CPUSETS
+	/*
+	 * Create default domain partitioning if cpusets are disabled.
+	 * Otherwise we let cpusets rebuild the domains based on the
+	 * current setup.
+	 */
+
 	/* The hotplug lock is already held by cpu_up/cpu_down */
 	arch_init_sched_domains(&cpu_online_map);
+#endif
 
 	return NOTIFY_OK;
 }
@@ -7626,7 +7653,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 	else
 		rt_se->rt_rq = parent->my_q;
 
-	rt_se->rt_rq = &rq->rt;
 	rt_se->my_q = rt_rq;
 	rt_se->parent = parent;
 	INIT_LIST_HEAD(&rt_se->run_list);
@@ -8348,7 +8374,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_CGROUP_SCHED
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 {
-	struct task_group *tgi, *parent = tg->parent;
+	struct task_group *tgi, *parent = tg ? tg->parent : NULL;
 	unsigned long total = 0;
 
 	if (!parent) {
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 3432d573205..0f3c19197fa 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -250,7 +250,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 			if (rt_rq->rt_time || rt_rq->rt_nr_running)
 				idle = 0;
 			spin_unlock(&rt_rq->rt_runtime_lock);
-		}
+		} else if (rt_rq->rt_nr_running)
+			idle = 0;
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
@@ -449,13 +450,19 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 #endif
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
 	struct rt_rq *group_rq = group_rt_rq(rt_se);
 
-	if (group_rq && rt_rq_throttled(group_rq))
+	/*
+	 * Don't enqueue the group if its throttled, or when empty.
+	 * The latter is a consequence of the former when a child group
+	 * get throttled and the current group doesn't have any other
+	 * active members.
+	 */
+	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
 	list_add_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se));
@@ -464,7 +471,7 @@ static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	inc_rt_tasks(rt_se, rt_rq);
 }
 
-static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
+static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
@@ -480,11 +487,10 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
  * Because the prio of an upper entry depends on the lower
  * entries, we must remove entries top - down.
  */
-static void dequeue_rt_stack(struct task_struct *p)
+static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 {
-	struct sched_rt_entity *rt_se, *back = NULL;
+	struct sched_rt_entity *back = NULL;
 
-	rt_se = &p->rt;
 	for_each_sched_rt_entity(rt_se) {
 		rt_se->back = back;
 		back = rt_se;
@@ -492,7 +498,26 @@ static void dequeue_rt_stack(struct task_struct *p)
 
 	for (rt_se = back; rt_se; rt_se = rt_se->back) {
 		if (on_rt_rq(rt_se))
-			dequeue_rt_entity(rt_se);
+			__dequeue_rt_entity(rt_se);
+	}
+}
+
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
+{
+	dequeue_rt_stack(rt_se);
+	for_each_sched_rt_entity(rt_se)
+		__enqueue_rt_entity(rt_se);
+}
+
+static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
+{
+	dequeue_rt_stack(rt_se);
+
+	for_each_sched_rt_entity(rt_se) {
+		struct rt_rq *rt_rq = group_rt_rq(rt_se);
+
+		if (rt_rq && rt_rq->rt_nr_running)
+			__enqueue_rt_entity(rt_se);
 	}
 }
 
@@ -506,32 +531,15 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 	if (wakeup)
 		rt_se->timeout = 0;
 
-	dequeue_rt_stack(p);
-
-	/*
-	 * enqueue everybody, bottom - up.
-	 */
-	for_each_sched_rt_entity(rt_se)
-		enqueue_rt_entity(rt_se);
+	enqueue_rt_entity(rt_se);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
-	struct rt_rq *rt_rq;
 
 	update_curr_rt(rq);
-
-	dequeue_rt_stack(p);
-
-	/*
-	 * re-enqueue all non-empty rt_rq entities.
-	 */
-	for_each_sched_rt_entity(rt_se) {
-		rt_rq = group_rt_rq(rt_se);
-		if (rt_rq && rt_rq->rt_nr_running)
-			enqueue_rt_entity(rt_se);
-	}
+	dequeue_rt_entity(rt_se);
 }
 
 /*
@@ -542,8 +550,10 @@ static
 void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
 {
 	struct rt_prio_array *array = &rt_rq->active;
+	struct list_head *queue = array->queue + rt_se_prio(rt_se);
 
-	list_move_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se));
+	if (on_rt_rq(rt_se))
+		list_move_tail(&rt_se->run_list, queue);
 }
 
 static void requeue_task_rt(struct rq *rq, struct task_struct *p)
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index a38878e0e49..80179ef7450 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -198,6 +198,9 @@ static inline void sched_info_queued(struct task_struct *t)
 /*
  * Called when a process ceases being the active-running process, either
  * voluntarily or involuntarily.  Now we can calculate how long we ran.
+ * Also, if the process is still in the TASK_RUNNING state, call
+ * sched_info_queued() to mark that it has now again started waiting on
+ * the runqueue.
  */
 static inline void sched_info_depart(struct task_struct *t)
 {
@@ -206,6 +209,9 @@ static inline void sched_info_depart(struct task_struct *t)
 
 	t->sched_info.cpu_time += delta;
 	rq_sched_info_depart(task_rq(t), delta);
+
+	if (t->state == TASK_RUNNING)
+		sched_info_queued(t);
 }
 
 /*