1 files changed, 355 insertions, 175 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 920d853a8e9e..ca2a2a894839 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -341,6 +341,12 @@ static inline bool should_fail_futex(bool fshared)
 }
 #endif /* CONFIG_FAIL_FUTEX */
 
+#ifdef CONFIG_COMPAT
+static void compat_exit_robust_list(struct task_struct *curr);
+#else
+static inline void compat_exit_robust_list(struct task_struct *curr) { }
+#endif
+
 static inline void futex_get_mm(union futex_key *key)
 {
 	mmgrab(key->private.mm);
@@ -713,7 +719,7 @@ again:
 
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
 		key->shared.i_seq = get_inode_sequence_number(inode);
-		key->shared.pgoff = basepage_index(tail);
+		key->shared.pgoff = page_to_pgoff(tail);
 		rcu_read_unlock();
 	}
 
@@ -833,6 +839,29 @@ static struct futex_pi_state *alloc_pi_state(void)
 	return pi_state;
 }
 
+static void pi_state_update_owner(struct futex_pi_state *pi_state,
+				  struct task_struct *new_owner)
+{
+	struct task_struct *old_owner = pi_state->owner;
+
+	lockdep_assert_held(&pi_state->pi_mutex.wait_lock);
+
+	if (old_owner) {
+		raw_spin_lock(&old_owner->pi_lock);
+		WARN_ON(list_empty(&pi_state->list));
+		list_del_init(&pi_state->list);
+		raw_spin_unlock(&old_owner->pi_lock);
+	}
+
+	if (new_owner) {
+		raw_spin_lock(&new_owner->pi_lock);
+		WARN_ON(!list_empty(&pi_state->list));
+		list_add(&pi_state->list, &new_owner->pi_state_list);
+		pi_state->owner = new_owner;
+		raw_spin_unlock(&new_owner->pi_lock);
+	}
+}
+
 static void get_pi_state(struct futex_pi_state *pi_state)
 {
 	WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount));
@@ -855,17 +884,12 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 	 * and has cleaned up the pi_state already
 	 */
 	if (pi_state->owner) {
-		struct task_struct *owner;
+		unsigned long flags;
 
-		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
-		owner = pi_state->owner;
-		if (owner) {
-			raw_spin_lock(&owner->pi_lock);
-			list_del_init(&pi_state->list);
-			raw_spin_unlock(&owner->pi_lock);
-		}
-		rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
-		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags);
+		pi_state_update_owner(pi_state, NULL);
+		rt_mutex_proxy_unlock(&pi_state->pi_mutex);
+		raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags);
 	}
 
 	if (current->pi_state_cache) {
@@ -889,7 +913,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
  * Kernel cleans up PI-state, but userspace is likely hosed.
  * (Robust-futex cleanup is separate and might save the day for userspace.)
  */
-void exit_pi_state_list(struct task_struct *curr)
+static void exit_pi_state_list(struct task_struct *curr)
 {
 	struct list_head *next, *head = &curr->pi_state_list;
 	struct futex_pi_state *pi_state;
@@ -959,7 +983,8 @@ void exit_pi_state_list(struct task_struct *curr)
 	}
 	raw_spin_unlock_irq(&curr->pi_lock);
 }
-
+#else
+static inline void exit_pi_state_list(struct task_struct *curr) { }
 #endif
 
 /*
@@ -1009,7 +1034,8 @@ void exit_pi_state_list(struct task_struct *curr)
  *	FUTEX_OWNER_DIED bit. See [4]
  *
  * [10] There is no transient state which leaves owner and user space
- *	TID out of sync.
+ *	TID out of sync. Except one error case where the kernel is denied
+ *	write access to the user address, see fixup_pi_state_owner().
  *
  *
  * Serialization and lifetime rules:
@@ -1168,16 +1194,47 @@ out_error:
 	return ret;
 }
 
+/**
+ * wait_for_owner_exiting - Block until the owner has exited
+ * @exiting:	Pointer to the exiting task
+ *
+ * Caller must hold a refcount on @exiting.
+ */
+static void wait_for_owner_exiting(int ret, struct task_struct *exiting)
+{
+	if (ret != -EBUSY) {
+		WARN_ON_ONCE(exiting);
+		return;
+	}
+
+	if (WARN_ON_ONCE(ret == -EBUSY && !exiting))
+		return;
+
+	mutex_lock(&exiting->futex_exit_mutex);
+	/*
+	 * No point in doing state checking here. If the waiter got here
+	 * while the task was in exec()->exec_futex_release() then it can
+	 * have any FUTEX_STATE_* value when the waiter has acquired the
+	 * mutex. OK, if running, EXITING or DEAD if it reached exit()
+	 * already. Highly unlikely and not a problem. Just one more round
+	 * through the futex maze.
+	 */
+	mutex_unlock(&exiting->futex_exit_mutex);
+
+	put_task_struct(exiting);
+}
+
 static int handle_exit_race(u32 __user *uaddr, u32 uval,
 			    struct task_struct *tsk)
 {
 	u32 uval2;
 
 	/*
-	 * If PF_EXITPIDONE is not yet set, then try again.
+	 * If the futex exit state is not yet FUTEX_STATE_DEAD, tell the
+	 * caller that the alleged owner is busy.
 	 */
-	if (tsk && !(tsk->flags & PF_EXITPIDONE))
-		return -EAGAIN;
+	if (tsk && tsk->futex_state != FUTEX_STATE_DEAD)
+		return -EBUSY;
 
 	/*
 	 * Reread the user space value to handle the following situation:
@@ -1195,8 +1252,9 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval,
 	 *    *uaddr = 0xC0000000;	     tsk = get_task(PID);
 	 *   }				     if (!tsk->flags & PF_EXITING) {
 	 *  ...				       attach();
-	 *  tsk->flags |= PF_EXITPIDONE;     } else {
-	 *				       if (!(tsk->flags & PF_EXITPIDONE))
+	 *  tsk->futex_state =               } else {
+	 *	FUTEX_STATE_DEAD;              if (tsk->futex_state !=
+	 *					  FUTEX_STATE_DEAD)
 	 *				         return -EAGAIN;
 	 *				       return -ESRCH; <--- FAIL
 	 *				     }
@@ -1227,7 +1285,8 @@ static int handle_exit_race(u32 __user *uaddr, u32 uval,
  * it after doing proper sanity checks.
  */
 static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
-			      struct futex_pi_state **ps)
+			      struct futex_pi_state **ps,
+			      struct task_struct **exiting)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
 	struct futex_pi_state *pi_state;
@@ -1252,22 +1311,33 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 	}
 
 	/*
-	 * We need to look at the task state flags to figure out,
-	 * whether the task is exiting. To protect against the do_exit
-	 * change of the task flags, we do this protected by
-	 * p->pi_lock:
+	 * We need to look at the task state to figure out, whether the
+	 * task is exiting. To protect against the change of the task state
+	 * in futex_exit_release(), we do this protected by p->pi_lock:
 	 */
 	raw_spin_lock_irq(&p->pi_lock);
-	if (unlikely(p->flags & PF_EXITING)) {
+	if (unlikely(p->futex_state != FUTEX_STATE_OK)) {
 		/*
-		 * The task is on the way out. When PF_EXITPIDONE is
-		 * set, we know that the task has finished the
-		 * cleanup:
+		 * The task is on the way out. When the futex state is
+		 * FUTEX_STATE_DEAD, we know that the task has finished
+		 * the cleanup:
 		 */
 		int ret = handle_exit_race(uaddr, uval, p);
 
 		raw_spin_unlock_irq(&p->pi_lock);
-		put_task_struct(p);
+		/*
+		 * If the owner task is between FUTEX_STATE_EXITING and
+		 * FUTEX_STATE_DEAD then store the task pointer and keep
+		 * the reference on the task struct. The calling code will
+		 * drop all locks, wait for the task to reach
+		 * FUTEX_STATE_DEAD and then drop the refcount. This is
+		 * required to prevent a live lock when the current task
+		 * preempted the exiting task between the two states.
+		 */
+		if (ret == -EBUSY)
+			*exiting = p;
+		else
+			put_task_struct(p);
 		return ret;
 	}
 
@@ -1306,7 +1376,8 @@ static int attach_to_pi_owner(u32 __user *uaddr, u32 uval, union futex_key *key,
 
 static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 			   struct futex_hash_bucket *hb,
-			   union futex_key *key, struct futex_pi_state **ps)
+			   union futex_key *key, struct futex_pi_state **ps,
+			   struct task_struct **exiting)
 {
 	struct futex_q *top_waiter = futex_top_waiter(hb, key);
 
@@ -1321,13 +1392,13 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 	 * We are the first waiter - try to look up the owner based on
 	 * @uval and attach to it.
 	 */
-	return attach_to_pi_owner(uaddr, uval, key, ps);
+	return attach_to_pi_owner(uaddr, uval, key, ps, exiting);
 }
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 {
 	int err;
-	u32 uninitialized_var(curval);
+	u32 curval;
 
 	if (unlikely(should_fail_futex(true)))
 		return -EFAULT;
@@ -1349,6 +1420,8 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
  *			lookup
  * @task:		the task to perform the atomic lock work for.  This will
  *			be "current" except in the case of requeue pi.
+ * @exiting:		Pointer to store the task pointer of the owner task
+ *			which is in the middle of exiting
  * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
  *
  * Return:
@@ -1357,11 +1430,17 @@ static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
  *  - <0 - error
  *
  * The hb->lock and futex_key refs shall be held by the caller.
+ *
+ * @exiting is only set when the return value is -EBUSY. If so, this holds
+ * a refcount on the exiting task on return and the caller needs to drop it
+ * after waiting for the exit to complete.
  */
 static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				union futex_key *key,
 				struct futex_pi_state **ps,
-				struct task_struct *task, int set_waiters)
+				struct task_struct *task,
+				struct task_struct **exiting,
+				int set_waiters)
 {
 	u32 uval, newval, vpid = task_pid_vnr(task);
 	struct futex_q *top_waiter;
@@ -1431,7 +1510,7 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 	 * attach to the owner. If that fails, no harm done, we only
 	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	return attach_to_pi_owner(uaddr, newval, key, ps);
+	return attach_to_pi_owner(uaddr, newval, key, ps, exiting);
 }
 
 /**
@@ -1490,7 +1569,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
  */
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
 {
-	u32 uninitialized_var(curval), newval;
+	u32 curval, newval;
 	struct task_struct *new_owner;
 	bool postunlock = false;
 	DEFINE_WAKE_Q(wake_q);
@@ -1517,8 +1596,10 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 	 */
 	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
-	if (unlikely(should_fail_futex(true)))
+	if (unlikely(should_fail_futex(true))) {
 		ret = -EFAULT;
+		goto out_unlock;
+	}
 
 	ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
 	if (!ret && (curval != uval)) {
@@ -1534,26 +1615,15 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 			ret = -EINVAL;
 	}
 
-	if (ret)
-		goto out_unlock;
-
-	/*
-	 * This is a point of no return; once we modify the uval there is no
-	 * going back and subsequent operations must not fail.
-	 */
-
-	raw_spin_lock(&pi_state->owner->pi_lock);
-	WARN_ON(list_empty(&pi_state->list));
-	list_del_init(&pi_state->list);
-	raw_spin_unlock(&pi_state->owner->pi_lock);
-
-	raw_spin_lock(&new_owner->pi_lock);
-	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &new_owner->pi_state_list);
-	pi_state->owner = new_owner;
-	raw_spin_unlock(&new_owner->pi_lock);
-
-	postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+	if (!ret) {
+		/*
+		 * This is a point of no return; once we modified the uval
+		 * there is no going back and subsequent operations must
+		 * not fail.
+		 */
+		pi_state_update_owner(pi_state, new_owner);
+		postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+	}
 
 out_unlock:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
@@ -1850,6 +1920,8 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  * @key1:		the from futex key
  * @key2:		the to futex key
  * @ps:			address to store the pi_state pointer
+ * @exiting:		Pointer to store the task pointer of the owner task
+ *			which is in the middle of exiting
  * @set_waiters:	force setting the FUTEX_WAITERS bit (1) or not (0)
  *
  * Try and get the lock on behalf of the top waiter if we can do it atomically.
@@ -1857,16 +1929,20 @@ void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
  * then direct futex_lock_pi_atomic() to force setting the FUTEX_WAITERS bit.
  * hb1 and hb2 must be held by the caller.
  *
+ * @exiting is only set when the return value is -EBUSY. If so, this holds
+ * a refcount on the exiting task on return and the caller needs to drop it
+ * after waiting for the exit to complete.
+ *
  * Return:
  *  -  0 - failed to acquire the lock atomically;
  *  - >0 - acquired the lock, return value is vpid of the top_waiter
  *  - <0 - error
  */
-static int futex_proxy_trylock_atomic(u32 __user *pifutex,
-				 struct futex_hash_bucket *hb1,
-				 struct futex_hash_bucket *hb2,
-				 union futex_key *key1, union futex_key *key2,
-				 struct futex_pi_state **ps, int set_waiters)
+static int
+futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1,
+			   struct futex_hash_bucket *hb2, union futex_key *key1,
+			   union futex_key *key2, struct futex_pi_state **ps,
+			   struct task_struct **exiting, int set_waiters)
 {
 	struct futex_q *top_waiter = NULL;
 	u32 curval;
@@ -1903,7 +1979,7 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 	 */
 	vpid = task_pid_vnr(top_waiter->task);
 	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
-				   set_waiters);
+				   exiting, set_waiters);
 	if (ret == 1) {
 		requeue_pi_wake_futex(top_waiter, key2, hb2);
 		return vpid;
@@ -2032,6 +2108,8 @@ retry_private:
 	}
 
 	if (requeue_pi && (task_count - nr_wake < nr_requeue)) {
+		struct task_struct *exiting = NULL;
+
 		/*
 		 * Attempt to acquire uaddr2 and wake the top waiter. If we
 		 * intend to requeue waiters, force setting the FUTEX_WAITERS
@@ -2039,7 +2117,8 @@ retry_private:
 		 * faults rather in the requeue loop below.
 		 */
 		ret = futex_proxy_trylock_atomic(uaddr2, hb1, hb2, &key1,
-						 &key2, &pi_state, nr_requeue);
+						 &key2, &pi_state,
+						 &exiting, nr_requeue);
 
 		/*
 		 * At this point the top_waiter has either taken uaddr2 or is
@@ -2066,7 +2145,8 @@ retry_private:
 			 * If that call succeeds then we have pi_state and an
 			 * initial refcount on it.
 			 */
-			ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state);
+			ret = lookup_pi_state(uaddr2, ret, hb2, &key2,
+					      &pi_state, &exiting);
 		}
 
 		switch (ret) {
@@ -2084,17 +2164,24 @@ retry_private:
 			if (!ret)
 				goto retry;
 			goto out;
+		case -EBUSY:
 		case -EAGAIN:
 			/*
 			 * Two reasons for this:
-			 * - Owner is exiting and we just wait for the
+			 * - EBUSY: Owner is exiting and we just wait for the
 			 *   exit to complete.
-			 * - The user space value changed.
+			 * - EAGAIN: The user space value changed.
 			 */
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);
 			put_futex_key(&key1);
+			/*
+			 * Handle the case where the owner is in the middle of
+			 * exiting. Wait for the exit to complete otherwise
+			 * this task might loop forever, aka. live lock.
+			 */
+			wait_for_owner_exiting(ret, exiting);
 			cond_resched();
 			goto retry;
 		default:
@@ -2359,18 +2446,13 @@ static void unqueue_me_pi(struct futex_q *q)
 	spin_unlock(q->lock_ptr);
 }
 
-static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *argowner)
+static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
+				  struct task_struct *argowner)
 {
+	u32 uval, uninitialized_var(curval), newval, newtid;
 	struct futex_pi_state *pi_state = q->pi_state;
-	u32 uval, uninitialized_var(curval), newval;
 	struct task_struct *oldowner, *newowner;
-	u32 newtid;
-	int ret, err = 0;
-
-	lockdep_assert_held(q->lock_ptr);
-
-	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+	int err = 0;
 
 	oldowner = pi_state->owner;
 
@@ -2404,21 +2486,31 @@ retry:
 			 * We raced against a concurrent self; things are
 			 * already fixed up. Nothing to do.
 			 */
-			ret = 0;
-			goto out_unlock;
+			return 0;
 		}
 
 		if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) {
-			/* We got the lock after all, nothing to fix. */
-			ret = 0;
-			goto out_unlock;
+			/* We got the lock. pi_state is correct. Tell caller. */
+			return 1;
 		}
 
 		/*
-		 * Since we just failed the trylock; there must be an owner.
+		 * The trylock just failed, so either there is an owner or
+		 * there is a higher priority waiter than this one.
 		 */
 		newowner = rt_mutex_owner(&pi_state->pi_mutex);
-		BUG_ON(!newowner);
+		/*
+		 * If the higher priority waiter has not yet taken over the
+		 * rtmutex then newowner is NULL. We can't return here with
+		 * that state because it's inconsistent vs. the user space
+		 * state. So drop the locks and try again. It's a valid
+		 * situation and not any different from the other retry
+		 * conditions.
+		 */
+		if (unlikely(!newowner)) {
+			err = -EAGAIN;
+			goto handle_err;
+		}
 	} else {
 		WARN_ON_ONCE(argowner != current);
 		if (oldowner == current) {
@@ -2426,8 +2518,7 @@ retry:
 			 * We raced against a concurrent self; things are
 			 * already fixed up. Nothing to do.
 			 */
-			ret = 0;
-			goto out_unlock;
+			return 1;
 		}
 		newowner = argowner;
 	}
@@ -2457,22 +2548,9 @@ retry:
 	 * We fixed up user space. Now we need to fix the pi_state
 	 * itself.
 	 */
-	if (pi_state->owner != NULL) {
-		raw_spin_lock(&pi_state->owner->pi_lock);
-		WARN_ON(list_empty(&pi_state->list));
-		list_del_init(&pi_state->list);
-		raw_spin_unlock(&pi_state->owner->pi_lock);
-	}
+	pi_state_update_owner(pi_state, newowner);
 
-	pi_state->owner = newowner;
-
-	raw_spin_lock(&newowner->pi_lock);
-	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &newowner->pi_state_list);
-	raw_spin_unlock(&newowner->pi_lock);
-	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-
-	return 0;
+	return argowner == current;
 
 	/*
 	 * In order to reschedule or handle a page fault, we need to drop the
@@ -2493,17 +2571,16 @@ handle_err:
 
 	switch (err) {
 	case -EFAULT:
-		ret = fault_in_user_writeable(uaddr);
+		err = fault_in_user_writeable(uaddr);
 		break;
 
 	case -EAGAIN:
 		cond_resched();
-		ret = 0;
+		err = 0;
 		break;
 
 	default:
 		WARN_ON_ONCE(1);
-		ret = err;
 		break;
 	}
 
@@ -2513,17 +2590,44 @@ handle_err:
 	/*
 	 * Check if someone else fixed it for us:
 	 */
-	if (pi_state->owner != oldowner) {
-		ret = 0;
-		goto out_unlock;
-	}
+	if (pi_state->owner != oldowner)
+		return argowner == current;
 
-	if (ret)
-		goto out_unlock;
+	/* Retry if err was -EAGAIN or the fault in succeeded */
+	if (!err)
+		goto retry;
 
-	goto retry;
+	/*
+	 * fault_in_user_writeable() failed so user state is immutable. At
+	 * best we can make the kernel state consistent but user state will
+	 * be most likely hosed and any subsequent unlock operation will be
+	 * rejected due to PI futex rule [10].
+	 *
+	 * Ensure that the rtmutex owner is also the pi_state owner despite
+	 * the user space value claiming something different. There is no
+	 * point in unlocking the rtmutex if current is the owner as it
+	 * would need to wait until the next waiter has taken the rtmutex
+	 * to guarantee consistent state. Keep it simple. Userspace asked
+	 * for this wreckaged state.
+	 *
+	 * The rtmutex has an owner - either current or some other
+	 * task. See the EAGAIN loop above.
+	 */
+	pi_state_update_owner(pi_state, rt_mutex_owner(&pi_state->pi_mutex));
 
-out_unlock:
+	return err;
+}
+
+static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
+				struct task_struct *argowner)
+{
+	struct futex_pi_state *pi_state = q->pi_state;
+	int ret;
+
+	lockdep_assert_held(q->lock_ptr);
+
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+	ret = __fixup_pi_state_owner(uaddr, q, argowner);
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	return ret;
 }
@@ -2547,8 +2651,6 @@ static long futex_wait_restart(struct restart_block *restart);
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-	int ret = 0;
-
 	if (locked) {
 		/*
 		 * Got the lock. We might not be the anticipated owner if we
@@ -2559,8 +2661,8 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 		 * stable state, anything else needs more attention.
 		 */
 		if (q->pi_state->owner != current)
-			ret = fixup_pi_state_owner(uaddr, q, current);
-		goto out;
+			return fixup_pi_state_owner(uaddr, q, current);
+		return 1;
 	}
 
 	/*
@@ -2571,24 +2673,17 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 	 * Another speculative read; pi_state->owner == current is unstable
 	 * but needs our attention.
 	 */
-	if (q->pi_state->owner == current) {
-		ret = fixup_pi_state_owner(uaddr, q, NULL);
-		goto out;
-	}
+	if (q->pi_state->owner == current)
+		return fixup_pi_state_owner(uaddr, q, NULL);
 
 	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
-	 * the owner of the rt_mutex.
+	 * the owner of the rt_mutex. Warn and establish consistent state.
 	 */
-	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
-		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
-				"pi-state %p\n", ret,
-				q->pi_state->pi_mutex.owner,
-				q->pi_state->owner);
-	}
+	if (WARN_ON_ONCE(rt_mutex_owner(&q->pi_state->pi_mutex) == current))
+		return fixup_pi_state_owner(uaddr, q, current);
 
-out:
-	return ret ? ret : locked;
+	return 0;
 }
 
 /**
@@ -2762,14 +2857,13 @@ retry:
 		goto out;
 
 	restart = &current->restart_block;
-	restart->fn = futex_wait_restart;
 	restart->futex.uaddr = uaddr;
 	restart->futex.val = val;
 	restart->futex.time = *abs_time;
 	restart->futex.bitset = bitset;
 	restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
 
-	ret = -ERESTART_RESTARTBLOCK;
+	ret = set_restart_fn(restart, futex_wait_restart);
 
 out:
 	if (to) {
@@ -2809,7 +2903,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 			 ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
-	struct futex_pi_state *pi_state = NULL;
+	struct task_struct *exiting = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	struct futex_q q = futex_q_init;
@@ -2837,7 +2931,8 @@ retry:
 retry_private:
 	hb = queue_lock(&q);
 
-	ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current, 0);
+	ret = futex_lock_pi_atomic(uaddr, hb, &q.key, &q.pi_state, current,
+				   &exiting, 0);
 	if (unlikely(ret)) {
 		/*
 		 * Atomic work succeeded and we got the lock,
@@ -2850,15 +2945,22 @@ retry_private:
 			goto out_unlock_put_key;
 		case -EFAULT:
 			goto uaddr_faulted;
+		case -EBUSY:
 		case -EAGAIN:
 			/*
 			 * Two reasons for this:
-			 * - Task is exiting and we just wait for the
+			 * - EBUSY: Task is exiting and we just wait for the
 			 *   exit to complete.
-			 * - The user space value changed.
+			 * - EAGAIN: The user space value changed.
 			 */
 			queue_unlock(hb);
 			put_futex_key(&q.key);
+			/*
+			 * Handle the case where the owner is in the middle of
+			 * exiting. Wait for the exit to complete otherwise
+			 * this task might loop forever, aka. live lock.
+			 */
+			wait_for_owner_exiting(ret, exiting);
 			cond_resched();
 			goto retry;
 		default:
@@ -2943,23 +3045,9 @@ no_block:
 	if (res)
 		ret = (res < 0) ? res : 0;
 
-	/*
-	 * If fixup_owner() faulted and was unable to handle the fault, unlock
-	 * it and return the fault to userspace.
-	 */
-	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) {
-		pi_state = q.pi_state;
-		get_pi_state(pi_state);
-	}
-
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
 
-	if (pi_state) {
-		rt_mutex_futex_unlock(&pi_state->pi_mutex);
-		put_pi_state(pi_state);
-	}
-
 	goto out_put_key;
 
 out_unlock_put_key:
@@ -2995,7 +3083,7 @@ uaddr_faulted:
  */
 static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
-	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
+	u32 curval, uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb;
 	struct futex_q *top_waiter;
@@ -3225,7 +3313,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				 u32 __user *uaddr2)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
-	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	union futex_key key2 = FUTEX_KEY_INIT;
@@ -3310,16 +3397,17 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
-			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
-				pi_state = q.pi_state;
-				get_pi_state(pi_state);
-			}
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
 			 */
 			put_pi_state(q.pi_state);
 			spin_unlock(q.lock_ptr);
+			/*
+			 * Adjust the return value. It's either -EFAULT or
+			 * success (1) but the caller expects 0 for success.
+			 */
+			ret = ret < 0 ? ret : 0;
 		}
 	} else {
 		struct rt_mutex *pi_mutex;
@@ -3350,25 +3438,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
-		/*
-		 * If fixup_pi_state_owner() faulted and was unable to handle
-		 * the fault, unlock the rt_mutex and return the fault to
-		 * userspace.
-		 */
-		if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
-			pi_state = q.pi_state;
-			get_pi_state(pi_state);
-		}
-
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
-	if (pi_state) {
-		rt_mutex_futex_unlock(&pi_state->pi_mutex);
-		put_pi_state(pi_state);
-	}
-
 	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling
@@ -3485,7 +3558,7 @@ err_unlock:
 static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr,
 			      bool pi, bool pending_op)
 {
-	u32 uval, uninitialized_var(nval), mval;
+	u32 uval, nval, mval;
 	int err;
 
 	/* Futex address must be 32bit aligned */
@@ -3610,12 +3683,12 @@ static inline int fetch_robust_entry(struct robust_list __user **entry,
  *
  * We silently return on any sign of list-walking problem.
  */
-void exit_robust_list(struct task_struct *curr)
+static void exit_robust_list(struct task_struct *curr)
 {
 	struct robust_list_head __user *head = curr->robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
 	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
-	unsigned int uninitialized_var(next_pi);
+	unsigned int next_pi;
 	unsigned long futex_offset;
 	int rc;
 
@@ -3675,6 +3748,114 @@ void exit_robust_list(struct task_struct *curr)
 	}
 }
 
+static void futex_cleanup(struct task_struct *tsk)
+{
+	if (unlikely(tsk->robust_list)) {
+		exit_robust_list(tsk);
+		tsk->robust_list = NULL;
+	}
+
+#ifdef CONFIG_COMPAT
+	if (unlikely(tsk->compat_robust_list)) {
+		compat_exit_robust_list(tsk);
+		tsk->compat_robust_list = NULL;
+	}
+#endif
+
+	if (unlikely(!list_empty(&tsk->pi_state_list)))
+		exit_pi_state_list(tsk);
+}
+
+/**
+ * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD
+ * @tsk:	task to set the state on
+ *
+ * Set the futex exit state of the task lockless. The futex waiter code
+ * observes that state when a task is exiting and loops until the task has
+ * actually finished the futex cleanup. The worst case for this is that the
+ * waiter runs through the wait loop until the state becomes visible.
+ *
+ * This is called from the recursive fault handling path in do_exit().
+ *
+ * This is best effort. Either the futex exit code has run already or
+ * not. If the OWNER_DIED bit has been set on the futex then the waiter can
+ * take it over. If not, the problem is pushed back to user space. If the
+ * futex exit code did not run yet, then an already queued waiter might
+ * block forever, but there is nothing which can be done about that.
+ */
+void futex_exit_recursive(struct task_struct *tsk)
+{
+	/* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */
+	if (tsk->futex_state == FUTEX_STATE_EXITING)
+		mutex_unlock(&tsk->futex_exit_mutex);
+	tsk->futex_state = FUTEX_STATE_DEAD;
+}
+
+static void futex_cleanup_begin(struct task_struct *tsk)
+{
+	/*
+	 * Prevent various race issues against a concurrent incoming waiter
+	 * including live locks by forcing the waiter to block on
+	 * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in
+	 * attach_to_pi_owner().
+	 */
+	mutex_lock(&tsk->futex_exit_mutex);
+
+	/*
+	 * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock.
+	 *
+	 * This ensures that all subsequent checks of tsk->futex_state in
+	 * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with
+	 * tsk->pi_lock held.
+	 *
+	 * It guarantees also that a pi_state which was queued right before
+	 * the state change under tsk->pi_lock by a concurrent waiter must
+	 * be observed in exit_pi_state_list().
+	 */
+	raw_spin_lock_irq(&tsk->pi_lock);
+	tsk->futex_state = FUTEX_STATE_EXITING;
+	raw_spin_unlock_irq(&tsk->pi_lock);
+}
+
+static void futex_cleanup_end(struct task_struct *tsk, int state)
+{
+	/*
+	 * Lockless store. The only side effect is that an observer might
+	 * take another loop until it becomes visible.
+	 */
+	tsk->futex_state = state;
+	/*
+	 * Drop the exit protection. This unblocks waiters which observed
+	 * FUTEX_STATE_EXITING to reevaluate the state.
+	 */
+	mutex_unlock(&tsk->futex_exit_mutex);
+}
+
+void futex_exec_release(struct task_struct *tsk)
+{
+	/*
+	 * The state handling is done for consistency, but in the case of
+	 * exec() there is no way to prevent futher damage as the PID stays
+	 * the same. But for the unlikely and arguably buggy case that a
+	 * futex is held on exec(), this provides at least as much state
+	 * consistency protection which is possible.
+	 */
+	futex_cleanup_begin(tsk);
+	futex_cleanup(tsk);
+	/*
+	 * Reset the state to FUTEX_STATE_OK. The task is alive and about
+	 * exec a new binary.
+	 */
+	futex_cleanup_end(tsk, FUTEX_STATE_OK);
+}
+
+void futex_exit_release(struct task_struct *tsk)
+{
+	futex_cleanup_begin(tsk);
+	futex_cleanup(tsk);
+	futex_cleanup_end(tsk, FUTEX_STATE_DEAD);
+}
+
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		u32 __user *uaddr2, u32 val2, u32 val3)
 {
@@ -3686,8 +3867,7 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 
 	if (op & FUTEX_CLOCK_REALTIME) {
 		flags |= FLAGS_CLOCKRT;
-		if (cmd != FUTEX_WAIT && cmd != FUTEX_WAIT_BITSET && \
-		    cmd != FUTEX_WAIT_REQUEUE_PI)
+		if (cmd != FUTEX_WAIT_BITSET &&	cmd != FUTEX_WAIT_REQUEUE_PI)
 			return -ENOSYS;
 	}
 
@@ -3802,12 +3982,12 @@ static void __user *futex_uaddr(struct robust_list __user *entry,
  *
  * We silently return on any sign of list-walking problem.
  */
-void compat_exit_robust_list(struct task_struct *curr)
+static void compat_exit_robust_list(struct task_struct *curr)
 {
 	struct compat_robust_list_head __user *head = curr->compat_robust_list;
 	struct robust_list __user *entry, *next_entry, *pending;
 	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
-	unsigned int uninitialized_var(next_pi);
+	unsigned int next_pi;
 	compat_uptr_t uentry, next_uentry, upending;
 	compat_long_t futex_offset;
 	int rc;