[PATCH -v5 07/14] futex: Change locking rules

[Peter Zijlstra]

Currently futex-pi relies on hb->lock to serialize everything. Since
hb->lock is giving us problems (PI inversions among other things,
since on -rt hb lock itself is a rt_mutex), we want to break this up a
bit.

This patch reworks and documents the locking. Notably, it
consistently uses rt_mutex::wait_lock to serialize {uval, pi_state}.
This would allow us to do rt_mutex_unlock() (including deboost)
without holding hb->lock.

Nothing yet relies on the new locking rules.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 kernel/futex.c |  153 +++++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 123 insertions(+), 30 deletions(-)

--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -973,6 +973,39 @@ void exit_pi_state_list(struct task_stru
  *
  * [10] There is no transient state which leaves owner and user space
  *	TID out of sync.
+ *
+ *
+ * Serialization and lifetime rules:
+ *
+ * hb->lock:
+ *
+ *	hb -> futex_q, relation
+ *	futex_q -> pi_state, relation
+ *
+ *	(cannot be raw because hb can contain arbitrary amount
+ *	 of futex_q's)
+ *
+ * pi_mutex->wait_lock:
+ *
+ *	{uval, pi_state}
+ *
+ *	(and pi_mutex 'obviously')
+ *
+ * p->pi_lock:
+ *
+ *	p->pi_state_list -> pi_state->list, relation
+ *
+ * pi_state->refcount:
+ *
+ *	pi_state lifetime
+ *
+ *
+ * Lock order:
+ *
+ *   hb->lock
+ *     pi_mutex->wait_lock
+ *       p->pi_lock
+ *
  */
 
 /*
@@ -980,10 +1013,12 @@ void exit_pi_state_list(struct task_stru
  * the pi_state against the user space value. If correct, attach to
  * it.
  */
-static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
+			      struct futex_pi_state *pi_state,
 			      struct futex_pi_state **ps)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
+	int ret, uval2;
 
 	/*
 	 * Userspace might have messed up non-PI and PI futexes [3]
@@ -991,9 +1026,34 @@ static int attach_to_pi_state(u32 uval,
 	if (unlikely(!pi_state))
 		return -EINVAL;
 
+	/*
+	 * We get here with hb->lock held, and having found a
+	 * futex_top_waiter(). This means that futex_lock_pi() of said futex_q
+	 * has dropped the hb->lock in between queue_me() and unqueue_me_pi(),
+	 * which in turn means that futex_lock_pi() still has a reference on
+	 * our pi_state.
+	 */
 	WARN_ON(!atomic_read(&pi_state->refcount));
 
 	/*
+	 * Now that we have a pi_state, we can acquire wait_lock
+	 * and do the state validation.
+	 */
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+	/*
+	 * Since {uval, pi_state} is serialized by wait_lock, and our current
+	 * uval was read without holding it, it can have changed. Verify it
+	 * still is what we expect it to be, otherwise retry the entire
+	 * operation.
+	 */
+	if (get_futex_value_locked(&uval2, uaddr))
+		goto out_efault;
+
+	if (uval != uval2)
+		goto out_eagain;
+
+	/*
 	 * Handle the owner died case:
 	 */
 	if (uval & FUTEX_OWNER_DIED) {
@@ -1008,11 +1068,11 @@ static int attach_to_pi_state(u32 uval,
 			 * is not 0. Inconsistent state. [5]
 			 */
 			if (pid)
-				return -EINVAL;
+				goto out_einval;
 			/*
 			 * Take a ref on the state and return success. [4]
 			 */
-			goto out_state;
+			goto out_attach;
 		}
 
 		/*
@@ -1024,14 +1084,14 @@ static int attach_to_pi_state(u32 uval,
 		 * Take a ref on the state and return success. [6]
 		 */
 		if (!pid)
-			goto out_state;
+			goto out_attach;
 	} else {
 		/*
 		 * If the owner died bit is not set, then the pi_state
 		 * must have an owner. [7]
 		 */
 		if (!pi_state->owner)
-			return -EINVAL;
+			goto out_einval;
 	}
 
 	/*
@@ -1040,11 +1100,29 @@ static int attach_to_pi_state(u32 uval,
 	 * user space TID. [9/10]
 	 */
 	if (pid != task_pid_vnr(pi_state->owner))
-		return -EINVAL;
-out_state:
+		goto out_einval;
+
+out_attach:
 	atomic_inc(&pi_state->refcount);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	*ps = pi_state;
 	return 0;
+
+out_einval:
+	ret = -EINVAL;
+	goto out_error;
+
+out_eagain:
+	ret = -EAGAIN;
+	goto out_error;
+
+out_efault:
+	ret = -EFAULT;
+	goto out_error;
+
+out_error:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	return ret;
 }
 
 /*
@@ -1095,6 +1173,9 @@ static int attach_to_pi_owner(u32 uval,
 
 	/*
 	 * No existing pi state. First waiter. [2]
+	 *
+	 * This creates pi_state, we have hb->lock held, this means nothing can
+	 * observe this state, wait_lock is irrelevant.
 	 */
 	pi_state = alloc_pi_state();
 
@@ -1119,7 +1200,8 @@ static int attach_to_pi_owner(u32 uval,
 	return 0;
 }
 
-static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+static int lookup_pi_state(u32 __user *uaddr, u32 uval,
+			   struct futex_hash_bucket *hb,
 			   union futex_key *key, struct futex_pi_state **ps)
 {
 	struct futex_q *top_waiter = futex_top_waiter(hb, key);
@@ -1129,7 +1211,7 @@ static int lookup_pi_state(u32 uval, str
 	 * attach to the pi_state when the validation succeeds.
 	 */
 	if (top_waiter)
-		return attach_to_pi_state(uval, top_waiter->pi_state, ps);
+		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
 
 	/*
 	 * We are the first waiter - try to look up the owner based on
@@ -1148,7 +1230,7 @@ static int lock_pi_update_atomic(u32 __u
 	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
 		return -EFAULT;
 
-	/*If user space value changed, let the caller retry */
+	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;
 }
 
@@ -1204,7 +1286,7 @@ static int futex_lock_pi_atomic(u32 __us
 	 */
 	top_waiter = futex_top_waiter(hb, key);
 	if (top_waiter)
-		return attach_to_pi_state(uval, top_waiter->pi_state, ps);
+		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
 
 	/*
 	 * No waiter and user TID is 0. We are here because the
@@ -1336,6 +1418,7 @@ static int wake_futex_pi(u32 __user *uad
 
 	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
 		ret = -EFAULT;
+
 	} else if (curval != uval) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
@@ -1348,6 +1431,7 @@ static int wake_futex_pi(u32 __user *uad
 		else
 			ret = -EINVAL;
 	}
+
 	if (ret) {
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		return ret;
@@ -1823,7 +1907,7 @@ static int futex_requeue(u32 __user *uad
 			 * If that call succeeds then we have pi_state and an
 			 * initial refcount on it.
 			 */
-			ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
+			ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state);
 		}
 
 		switch (ret) {
@@ -2122,10 +2206,13 @@ static int fixup_pi_state_owner(u32 __us
 {
 	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, uninitialized_var(curval), newval;
+	struct task_struct *oldowner;
 	int ret;
 
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+	oldowner = pi_state->owner;
 	/* Owner died? */
 	if (!pi_state->owner)
 		newtid |= FUTEX_OWNER_DIED;
@@ -2141,11 +2228,10 @@ static int fixup_pi_state_owner(u32 __us
 	 * because we can fault here. Imagine swapped out pages or a fork
 	 * 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.
+	 * 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 locks to handle the fault. This might be observed
+	 * in the PID check in lookup_pi_state.
 	 */
 retry:
 	if (get_futex_value_locked(&uval, uaddr))
@@ -2166,36 +2252,43 @@ static int fixup_pi_state_owner(u32 __us
 	 * itself.
 	 */
 	if (pi_state->owner != NULL) {
-		raw_spin_lock_irq(&pi_state->owner->pi_lock);
+		raw_spin_lock(&pi_state->owner->pi_lock);
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
-		raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+		raw_spin_unlock(&pi_state->owner->pi_lock);
 	}
 
 	pi_state->owner = newowner;
 
-	raw_spin_lock_irq(&newowner->pi_lock);
+	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_irq(&newowner->pi_lock);
+	raw_spin_unlock(&newowner->pi_lock);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+
 	return 0;
 
 	/*
-	 * To handle the page fault we need to drop the hash bucket
-	 * lock here. That gives the other task (either the highest priority
-	 * waiter 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.
+	 * To handle the page fault we need to drop the locks here. That gives
+	 * the other task (either the highest priority waiter 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 locks and before trying to
+	 * do another fixup. When the fixup has been done already we simply
+	 * return.
+	 *
+	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
+	 * drop hb->lock since the caller owns the hb -> futex_q relation.
+	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
 	 */
 handle_fault:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
 	ret = fault_in_user_writeable(uaddr);
 
 	spin_lock(q->lock_ptr);
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	/*
 	 * Check if someone else fixed it for us: