1 files changed, 128 insertions, 138 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index a5876694a60e..e68db7745039 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -39,6 +39,7 @@
 #include <linux/freezer.h>
 #include <linux/memblock.h>
 #include <linux/fault-inject.h>
+#include <linux/time_namespace.h>
 
 #include <asm/futex.h>
 
@@ -309,8 +310,6 @@ static inline bool should_fail_futex(bool fshared)
 
 #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
 
 /*
@@ -764,6 +763,29 @@ 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(!refcount_inc_not_zero(&pi_state->refcount));
@@ -786,17 +808,12 @@ 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) {
@@ -916,7 +933,7 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }
  * [10] Found  | Found    | task      | !=taskTID | 0/1    | Invalid
  *
  * [1]	Indicates that the kernel can acquire the futex atomically. We
- *	came came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
+ *	came here due to a stale FUTEX_WAITERS/FUTEX_OWNER_DIED bit.
  *
  * [2]	Valid, if TID does not belong to a kernel thread. If no matching
  *      thread is found then it indicates that the owner TID has died.
@@ -941,7 +958,8 @@ static inline 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:
@@ -1502,8 +1520,10 @@ 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)) {
@@ -1519,26 +1539,15 @@ 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);
@@ -2321,18 +2330,13 @@ 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)
 {
 	struct futex_pi_state *pi_state = q->pi_state;
-	u32 uval, 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);
+	u32 uval, curval, newval, newtid;
+	int err = 0;
 
 	oldowner = pi_state->owner;
 
@@ -2366,21 +2370,31 @@ 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) {
@@ -2388,8 +2402,7 @@ retry:
 			 * We raced against a concurrent self; things are
 			 * already fixed up. Nothing to do.
 			 */
-			ret = 0;
-			goto out_unlock;
+			return 1;
 		}
 		newowner = argowner;
 	}
@@ -2419,22 +2432,9 @@ 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->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);
+	pi_state_update_owner(pi_state, newowner);
 
-	return 0;
+	return argowner == current;
 
 	/*
 	 * In order to reschedule or handle a page fault, we need to drop the
@@ -2455,17 +2455,16 @@ 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;
 	}
 
@@ -2475,17 +2474,44 @@ 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;
 }
@@ -2509,8 +2535,6 @@ 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
@@ -2521,8 +2545,8 @@ 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);
-		return ret ? ret : locked;
+			return fixup_pi_state_owner(uaddr, q, current);
+		return 1;
 	}
 
 	/*
@@ -2533,23 +2557,17 @@ 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);
-		return ret;
-	}
+	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);
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -2757,7 +2775,6 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 			 ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to;
-	struct futex_pi_state *pi_state = NULL;
 	struct task_struct *exiting = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
@@ -2893,23 +2910,8 @@ 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;
 
 out_unlock_put_key:
@@ -3010,7 +3012,7 @@ retry:
 		 * Success, we're done! No tricky corner cases.
 		 */
 		if (!ret)
-			goto out_putkey;
+			return ret;
 		/*
 		 * The atomic access to the futex value generated a
 		 * pagefault, so retry the user-access and the wakeup:
@@ -3027,7 +3029,7 @@ retry:
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
 		 */
-		goto out_putkey;
+		return ret;
 	}
 
 	/*
@@ -3048,7 +3050,7 @@ retry:
 
 		default:
 			WARN_ON_ONCE(1);
-			goto out_putkey;
+			return ret;
 		}
 	}
 
@@ -3059,7 +3061,6 @@ retry:
 
 out_unlock:
 	spin_unlock(&hb->lock);
-out_putkey:
 	return ret;
 
 pi_retry:
@@ -3169,7 +3170,6 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				 u32 __user *uaddr2)
 {
 	struct hrtimer_sleeper timeout, *to;
-	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;
@@ -3247,16 +3247,17 @@ 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;
@@ -3287,25 +3288,10 @@ 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
@@ -3776,8 +3762,8 @@ long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 
 
 SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
-		struct __kernel_timespec __user *, utime, u32 __user *, uaddr2,
-		u32, val3)
+		const struct __kernel_timespec __user *, utime,
+		u32 __user *, uaddr2, u32, val3)
 {
 	struct timespec64 ts;
 	ktime_t t, *tp = NULL;
@@ -3797,6 +3783,8 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 		t = timespec64_to_ktime(ts);
 		if (cmd == FUTEX_WAIT)
 			t = ktime_add_safe(ktime_get(), t);
+		else if (!(op & FUTEX_CLOCK_REALTIME))
+			t = timens_ktime_to_host(CLOCK_MONOTONIC, t);
 		tp = &t;
 	}
 	/*
@@ -3970,7 +3958,7 @@ err_unlock:
 
 #ifdef CONFIG_COMPAT_32BIT_TIME
 SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
-		struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
+		const struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
 		u32, val3)
 {
 	struct timespec64 ts;
@@ -3989,6 +3977,8 @@ SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
 		t = timespec64_to_ktime(ts);
 		if (cmd == FUTEX_WAIT)
 			t = ktime_add_safe(ktime_get(), t);
+		else if (!(op & FUTEX_CLOCK_REALTIME))
+			t = timens_ktime_to_host(CLOCK_MONOTONIC, t);
 		tp = &t;
 	}
 	if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||