Merge commit 'v3.0.58' into android-3.0

Change-Id: I05959ed26f71cf9197df59291e8e13f254b2115c

9 files changed, 74 insertions, 40 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 739553e..3948f0a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2665,9 +2665,7 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
 		dentry->d_fsdata = cgrp;
 		inc_nlink(parent->d_inode);
 		rcu_assign_pointer(cgrp->dentry, dentry);
-		dget(dentry);
 	}
-	dput(dentry);
 
 	return error;
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index e45efe7..61e554e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -716,7 +716,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				struct futex_pi_state **ps,
 				struct task_struct *task, int set_waiters)
 {
-	int lock_taken, ret, ownerdied = 0;
+	int lock_taken, ret, force_take = 0;
 	u32 uval, newval, curval, vpid = task_pid_vnr(task);
 
 retry:
@@ -755,17 +755,15 @@ retry:
 	newval = curval | FUTEX_WAITERS;
 
 	/*
-	 * There are two cases, where a futex might have no owner (the
-	 * owner TID is 0): OWNER_DIED. We take over the futex in this
-	 * case. We also do an unconditional take over, when the owner
-	 * of the futex died.
-	 *
-	 * This is safe as we are protected by the hash bucket lock !
+	 * Should we force take the futex? See below.
 	 */
-	if (unlikely(ownerdied || !(curval & FUTEX_TID_MASK))) {
-		/* Keep the OWNER_DIED bit */
+	if (unlikely(force_take)) {
+		/*
+		 * Keep the OWNER_DIED and the WAITERS bit and set the
+		 * new TID value.
+		 */
 		newval = (curval & ~FUTEX_TID_MASK) | vpid;
-		ownerdied = 0;
+		force_take = 0;
 		lock_taken = 1;
 	}
 
@@ -775,7 +773,7 @@ retry:
 		goto retry;
 
 	/*
-	 * We took the lock due to owner died take over.
+	 * We took the lock due to forced take over.
 	 */
 	if (unlikely(lock_taken))
 		return 1;
@@ -790,20 +788,25 @@ retry:
 		switch (ret) {
 		case -ESRCH:
 			/*
-			 * No owner found for this futex. Check if the
-			 * OWNER_DIED bit is set to figure out whether
-			 * this is a robust futex or not.
+			 * We failed to find an owner for this
+			 * futex. So we have no pi_state to block
+			 * on. This can happen in two cases:
+			 *
+			 * 1) The owner died
+			 * 2) A stale FUTEX_WAITERS bit
+			 *
+			 * Re-read the futex value.
 			 */
 			if (get_futex_value_locked(&curval, uaddr))
 				return -EFAULT;
 
 			/*
-			 * We simply start over in case of a robust
-			 * futex. The code above will take the futex
-			 * and return happy.
+			 * If the owner died or we have a stale
+			 * WAITERS bit the owner TID in the user space
+			 * futex is 0.
 			 */
-			if (curval & FUTEX_OWNER_DIED) {
-				ownerdied = 1;
+			if (!(curval & FUTEX_TID_MASK)) {
+				force_take = 1;
 				goto retry;
 			}
 		default:
@@ -840,6 +843,9 @@ static void wake_futex(struct futex_q *q)
 {
 	struct task_struct *p = q->task;
 
+	if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
+		return;
+
 	/*
 	 * We set q->lock_ptr = NULL _before_ we wake up the task. If
 	 * a non-futex wake up happens on another CPU then the task
@@ -1075,6 +1081,10 @@ retry_private:
 
 	plist_for_each_entry_safe(this, next, head, list) {
 		if (match_futex (&this->key, &key1)) {
+			if (this->pi_state || this->rt_waiter) {
+				ret = -EINVAL;
+				goto out_unlock;
+			}
 			wake_futex(this);
 			if (++ret >= nr_wake)
 				break;
@@ -1087,6 +1097,10 @@ retry_private:
 		op_ret = 0;
 		plist_for_each_entry_safe(this, next, head, list) {
 			if (match_futex (&this->key, &key2)) {
+				if (this->pi_state || this->rt_waiter) {
+					ret = -EINVAL;
+					goto out_unlock;
+				}
 				wake_futex(this);
 				if (++op_ret >= nr_wake2)
 					break;
@@ -1095,6 +1109,7 @@ retry_private:
 		ret += op_ret;
 	}
 
+out_unlock:
 	double_unlock_hb(hb1, hb2);
 out_put_keys:
 	put_futex_key(&key2);
@@ -1384,9 +1399,13 @@ retry_private:
 		/*
 		 * FUTEX_WAIT_REQEUE_PI and FUTEX_CMP_REQUEUE_PI should always
 		 * be paired with each other and no other futex ops.
+		 *
+		 * We should never be requeueing a futex_q with a pi_state,
+		 * which is awaiting a futex_unlock_pi().
 		 */
 		if ((requeue_pi && !this->rt_waiter) ||
-		    (!requeue_pi && this->rt_waiter)) {
+		    (!requeue_pi && this->rt_waiter) ||
+		    this->pi_state) {
 			ret = -EINVAL;
 			break;
 		}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index fa4a70e..3e1bdf9 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -698,6 +698,7 @@ static void
 irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
 {
 	cpumask_var_t mask;
+	bool valid = true;
 
 	if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
 		return;
@@ -712,10 +713,18 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
 	}
 
 	raw_spin_lock_irq(&desc->lock);
-	cpumask_copy(mask, desc->irq_data.affinity);
+	/*
+	 * This code is triggered unconditionally. Check the affinity
+	 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
+	 */
+	if (desc->irq_data.affinity)
+		cpumask_copy(mask, desc->irq_data.affinity);
+	else
+		valid = false;
 	raw_spin_unlock_irq(&desc->lock);
 
-	set_cpus_allowed_ptr(current, mask);
+	if (valid)
+		set_cpus_allowed_ptr(current, mask);
 	free_cpumask_var(mask);
 }
 #else
@@ -925,6 +934,16 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 */
 		get_task_struct(t);
 		new->thread = t;
+		/*
+		 * Tell the thread to set its affinity. This is
+		 * important for shared interrupt handlers as we do
+		 * not invoke setup_affinity() for the secondary
+		 * handlers as everything is already set up. Even for
+		 * interrupts marked with IRQF_NO_BALANCE this is
+		 * correct as we want the thread to move to the cpu(s)
+		 * on which the requesting code placed the interrupt.
+		 */
+		set_bit(IRQTF_AFFINITY, &new->thread_flags);
 	}
 
 	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
diff --git a/kernel/resource.c b/kernel/resource.c
index 3ff4017..b29b83d 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -419,6 +419,9 @@ static int __find_resource(struct resource *root, struct resource *old,
 		else
 			tmp.end = root->end;
 
+		if (tmp.end < tmp.start)
+			goto next;
+
 		resource_clip(&tmp, constraint->min, constraint->max);
 		arch_remove_reservations(&tmp);
 
@@ -436,8 +439,10 @@ static int __find_resource(struct resource *root, struct resource *old,
 				return 0;
 			}
 		}
-		if (!this)
+
+next:		if (!this || this->end == root->end)
 			break;
+
 		if (this != old)
 			tmp.start = this->end + 1;
 		this = this->sibling;
diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c
index 429242f..f280df1 100644
--- a/kernel/sched_autogroup.c
+++ b/kernel/sched_autogroup.c
@@ -160,15 +160,11 @@ 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);
 }
diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h
index 0557705..7b859ff 100644
--- a/kernel/sched_autogroup.h
+++ b/kernel/sched_autogroup.h
@@ -1,11 +1,6 @@
 #ifdef CONFIG_SCHED_AUTOGROUP
 
 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;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 9f8e2e1..f88ea18 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2058,7 +2058,7 @@ static void reset_iter_read(struct ftrace_iterator *iter)
 {
 	iter->pos = 0;
 	iter->func_pos = 0;
-	iter->flags &= ~(FTRACE_ITER_PRINTALL & FTRACE_ITER_HASH);
+	iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_HASH);
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 3d0c56a..53e4432 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -113,7 +113,7 @@ static unsigned long get_timestamp(int this_cpu)
 	return cpu_clock(this_cpu) >> 30LL;  /* 2^30 ~= 10^9 */
 }
 
-static unsigned long get_sample_period(void)
+static u64 get_sample_period(void)
 {
 	/*
 	 * convert watchdog_thresh from seconds to ns
@@ -121,7 +121,7 @@ static unsigned long get_sample_period(void)
 	 * increment before the hardlockup detector generates
 	 * a warning
 	 */
-	return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
+	return get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5);
 }
 
 /* Commands for resetting the watchdog */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index aef9452..dc8438d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1145,8 +1145,8 @@ int queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
 	if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) {
 		unsigned int lcpu;
 
-		BUG_ON(timer_pending(timer));
-		BUG_ON(!list_empty(&work->entry));
+		WARN_ON_ONCE(timer_pending(timer));
+		WARN_ON_ONCE(!list_empty(&work->entry));
 
 		timer_stats_timer_set_start_info(&dwork->timer);
 
@@ -2044,8 +2044,10 @@ static int rescuer_thread(void *__wq)
 repeat:
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	if (kthread_should_stop())
+	if (kthread_should_stop()) {
+		__set_current_state(TASK_RUNNING);
 		return 0;
+	}
 
 	/*
 	 * See whether any cpu is asking for help.  Unbounded