1 files changed, 113 insertions, 15 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index 16dbe4c93895..76ed5921117a 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -670,13 +670,14 @@ again:
 		 * this reference was taken by ihold under the page lock
 		 * pinning the inode in place so i_lock was unnecessary. The
 		 * only way for this check to fail is if the inode was
-		 * truncated in parallel so warn for now if this happens.
+		 * truncated in parallel which is almost certainly an
+		 * application bug. In such a case, just retry.
 		 *
 		 * We are not calling into get_futex_key_refs() in file-backed
 		 * cases, therefore a successful atomic_inc return below will
 		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
 		 */
-		if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) {
+		if (!atomic_inc_not_zero(&inode->i_count)) {
 			rcu_read_unlock();
 			put_page(page);
 
@@ -820,8 +821,6 @@ static void get_pi_state(struct futex_pi_state *pi_state)
 /*
  * Drops a reference to the pi_state object and frees or caches it
  * when the last reference is gone.
- *
- * Must be called with the hb lock held.
  */
 static void put_pi_state(struct futex_pi_state *pi_state)
 {
@@ -836,16 +835,22 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 	 * and has cleaned up the pi_state already
 	 */
 	if (pi_state->owner) {
-		raw_spin_lock_irq(&pi_state->owner->pi_lock);
-		list_del_init(&pi_state->list);
-		raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+		struct task_struct *owner;
 
-		rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner);
+		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);
 	}
 
-	if (current->pi_state_cache)
+	if (current->pi_state_cache) {
 		kfree(pi_state);
-	else {
+	} else {
 		/*
 		 * pi_state->list is already empty.
 		 * clear pi_state->owner.
@@ -875,6 +880,8 @@ static struct task_struct *futex_find_get_task(pid_t pid)
 	return p;
 }
 
+#ifdef CONFIG_FUTEX_PI
+
 /*
  * This task is holding PI mutexes at exit time => bad.
  * Kernel cleans up PI-state, but userspace is likely hosed.
@@ -896,22 +903,41 @@ void exit_pi_state_list(struct task_struct *curr)
 	 */
 	raw_spin_lock_irq(&curr->pi_lock);
 	while (!list_empty(head)) {
-
 		next = head->next;
 		pi_state = list_entry(next, struct futex_pi_state, list);
 		key = pi_state->key;
 		hb = hash_futex(&key);
+
+		/*
+		 * We can race against put_pi_state() removing itself from the
+		 * list (a waiter going away). put_pi_state() will first
+		 * decrement the reference count and then modify the list, so
+		 * its possible to see the list entry but fail this reference
+		 * acquire.
+		 *
+		 * In that case; drop the locks to let put_pi_state() make
+		 * progress and retry the loop.
+		 */
+		if (!atomic_inc_not_zero(&pi_state->refcount)) {
+			raw_spin_unlock_irq(&curr->pi_lock);
+			cpu_relax();
+			raw_spin_lock_irq(&curr->pi_lock);
+			continue;
+		}
 		raw_spin_unlock_irq(&curr->pi_lock);
 
 		spin_lock(&hb->lock);
-
-		raw_spin_lock_irq(&curr->pi_lock);
+		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		raw_spin_lock(&curr->pi_lock);
 		/*
 		 * We dropped the pi-lock, so re-check whether this
 		 * task still owns the PI-state:
 		 */
 		if (head->next != next) {
+			/* retain curr->pi_lock for the loop invariant */
+			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 			spin_unlock(&hb->lock);
+			put_pi_state(pi_state);
 			continue;
 		}
 
@@ -919,9 +945,9 @@ void exit_pi_state_list(struct task_struct *curr)
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		pi_state->owner = NULL;
-		raw_spin_unlock_irq(&curr->pi_lock);
 
-		get_pi_state(pi_state);
+		raw_spin_unlock(&curr->pi_lock);
+		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 
 		rt_mutex_futex_unlock(&pi_state->pi_mutex);
@@ -932,6 +958,8 @@ void exit_pi_state_list(struct task_struct *curr)
 	raw_spin_unlock_irq(&curr->pi_lock);
 }
 
+#endif
+
 /*
  * We need to check the following states:
  *
@@ -1203,6 +1231,10 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key,
 
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &p->pi_state_list);
+	/*
+	 * Assignment without holding pi_state->pi_mutex.wait_lock is safe
+	 * because there is no concurrency as the object is not published yet.
+	 */
 	pi_state->owner = p;
 	raw_spin_unlock_irq(&p->pi_lock);
 
@@ -1546,6 +1578,53 @@ out:
 	return ret;
 }
 
+static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
+{
+	unsigned int op =	  (encoded_op & 0x70000000) >> 28;
+	unsigned int cmp =	  (encoded_op & 0x0f000000) >> 24;
+	int oparg = sign_extend32((encoded_op & 0x00fff000) >> 12, 12);
+	int cmparg = sign_extend32(encoded_op & 0x00000fff, 12);
+	int oldval, ret;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
+		if (oparg < 0 || oparg > 31) {
+			char comm[sizeof(current->comm)];
+			/*
+			 * kill this print and return -EINVAL when userspace
+			 * is sane again
+			 */
+			pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n",
+					get_task_comm(comm, current), oparg);
+			oparg &= 31;
+		}
+		oparg = 1 << oparg;
+	}
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
+		return -EFAULT;
+
+	ret = arch_futex_atomic_op_inuser(op, oparg, &oldval, uaddr);
+	if (ret)
+		return ret;
+
+	switch (cmp) {
+	case FUTEX_OP_CMP_EQ:
+		return oldval == cmparg;
+	case FUTEX_OP_CMP_NE:
+		return oldval != cmparg;
+	case FUTEX_OP_CMP_LT:
+		return oldval < cmparg;
+	case FUTEX_OP_CMP_GE:
+		return oldval >= cmparg;
+	case FUTEX_OP_CMP_LE:
+		return oldval <= cmparg;
+	case FUTEX_OP_CMP_GT:
+		return oldval > cmparg;
+	default:
+		return -ENOSYS;
+	}
+}
+
 /*
  * Wake up all waiters hashed on the physical page that is mapped
  * to this virtual address:
@@ -1799,6 +1878,15 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_q *this, *next;
 	DEFINE_WAKE_Q(wake_q);
 
+	/*
+	 * When PI not supported: return -ENOSYS if requeue_pi is true,
+	 * consequently the compiler knows requeue_pi is always false past
+	 * this point which will optimize away all the conditional code
+	 * further down.
+	 */
+	if (!IS_ENABLED(CONFIG_FUTEX_PI) && requeue_pi)
+		return -ENOSYS;
+
 	if (requeue_pi) {
 		/*
 		 * Requeue PI only works on two distinct uaddrs. This
@@ -2594,6 +2682,9 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 	struct futex_q q = futex_q_init;
 	int res, ret;
 
+	if (!IS_ENABLED(CONFIG_FUTEX_PI))
+		return -ENOSYS;
+
 	if (refill_pi_state_cache())
 		return -ENOMEM;
 
@@ -2773,6 +2864,9 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 	struct futex_q *top_waiter;
 	int ret;
 
+	if (!IS_ENABLED(CONFIG_FUTEX_PI))
+		return -ENOSYS;
+
 retry:
 	if (get_user(uval, uaddr))
 		return -EFAULT;
@@ -2819,6 +2913,7 @@ retry:
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 
+		/* drops pi_state->pi_mutex.wait_lock */
 		ret = wake_futex_pi(uaddr, uval, pi_state);
 
 		put_pi_state(pi_state);
@@ -2983,6 +3078,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	struct futex_q q = futex_q_init;
 	int res, ret;
 
+	if (!IS_ENABLED(CONFIG_FUTEX_PI))
+		return -ENOSYS;
+
 	if (uaddr == uaddr2)
 		return -EINVAL;