1 files changed, 159 insertions, 102 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index be3bff2315ff..6262f1534ac9 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -68,6 +68,7 @@
 #include <linux/freezer.h>
 #include <linux/memblock.h>
 #include <linux/fault-inject.h>
+#include <linux/refcount.h>
 
 #include <asm/futex.h>
 
@@ -212,7 +213,7 @@ struct futex_pi_state {
 	struct rt_mutex pi_mutex;
 
 	struct task_struct *owner;
-	atomic_t refcount;
+	refcount_t refcount;
 
 	union futex_key key;
 } __randomize_layout;
@@ -321,12 +322,8 @@ static int __init fail_futex_debugfs(void)
 	if (IS_ERR(dir))
 		return PTR_ERR(dir);
 
-	if (!debugfs_create_bool("ignore-private", mode, dir,
-				 &fail_futex.ignore_private)) {
-		debugfs_remove_recursive(dir);
-		return -ENOMEM;
-	}
-
+	debugfs_create_bool("ignore-private", mode, dir,
+			    &fail_futex.ignore_private);
 	return 0;
 }
 
@@ -803,7 +800,7 @@ static int refill_pi_state_cache(void)
 	INIT_LIST_HEAD(&pi_state->list);
 	/* pi_mutex gets initialized later */
 	pi_state->owner = NULL;
-	atomic_set(&pi_state->refcount, 1);
+	refcount_set(&pi_state->refcount, 1);
 	pi_state->key = FUTEX_KEY_INIT;
 
 	current->pi_state_cache = pi_state;
@@ -823,7 +820,7 @@ static struct futex_pi_state *alloc_pi_state(void)
 
 static void get_pi_state(struct futex_pi_state *pi_state)
 {
-	WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount));
+	WARN_ON_ONCE(!refcount_inc_not_zero(&pi_state->refcount));
 }
 
 /*
@@ -835,7 +832,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 	if (!pi_state)
 		return;
 
-	if (!atomic_dec_and_test(&pi_state->refcount))
+	if (!refcount_dec_and_test(&pi_state->refcount))
 		return;
 
 	/*
@@ -865,7 +862,7 @@ static void put_pi_state(struct futex_pi_state *pi_state)
 		 * refcount is at 0 - put it back to 1.
 		 */
 		pi_state->owner = NULL;
-		atomic_set(&pi_state->refcount, 1);
+		refcount_set(&pi_state->refcount, 1);
 		current->pi_state_cache = pi_state;
 	}
 }
@@ -908,7 +905,7 @@ void exit_pi_state_list(struct task_struct *curr)
 		 * 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)) {
+		if (!refcount_inc_not_zero(&pi_state->refcount)) {
 			raw_spin_unlock_irq(&curr->pi_lock);
 			cpu_relax();
 			raw_spin_lock_irq(&curr->pi_lock);
@@ -1064,7 +1061,7 @@ static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
 	 * and futex_wait_requeue_pi() as it cannot go to 0 and consequently
 	 * free pi_state before we can take a reference ourselves.
 	 */
-	WARN_ON(!atomic_read(&pi_state->refcount));
+	WARN_ON(!refcount_read(&pi_state->refcount));
 
 	/*
 	 * Now that we have a pi_state, we can acquire wait_lock
@@ -1314,13 +1311,15 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 {
+	int err;
 	u32 uninitialized_var(curval);
 
 	if (unlikely(should_fail_futex(true)))
 		return -EFAULT;
 
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
+	err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (unlikely(err))
+		return err;
 
 	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;
@@ -1452,11 +1451,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 	if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n"))
 		return;
 
-	/*
-	 * Queue the task for later wakeup for after we've released
-	 * the hb->lock. wake_q_add() grabs reference to p.
-	 */
-	wake_q_add(wake_q, p);
+	get_task_struct(p);
 	__unqueue_futex(q);
 	/*
 	 * The waiting task can free the futex_q as soon as q->lock_ptr = NULL
@@ -1466,6 +1461,12 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 	 * plist_del in __unqueue_futex().
 	 */
 	smp_store_release(&q->lock_ptr, NULL);
+
+	/*
+	 * Queue the task for later wakeup for after we've released
+	 * the hb->lock. wake_q_add() grabs reference to p.
+	 */
+	wake_q_add_safe(wake_q, p);
 }
 
 /*
@@ -1503,10 +1504,8 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 	if (unlikely(should_fail_futex(true)))
 		ret = -EFAULT;
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
-		ret = -EFAULT;
-
-	} else if (curval != uval) {
+	ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (!ret && (curval != uval)) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
 		 * try the TID->0 transition) raced with a waiter setting the
@@ -1701,32 +1700,32 @@ retry_private:
 	double_lock_hb(hb1, hb2);
 	op_ret = futex_atomic_op_inuser(op, uaddr2);
 	if (unlikely(op_ret < 0)) {
-
 		double_unlock_hb(hb1, hb2);
 
-#ifndef CONFIG_MMU
-		/*
-		 * we don't get EFAULT from MMU faults if we don't have an MMU,
-		 * but we might get them from range checking
-		 */
-		ret = op_ret;
-		goto out_put_keys;
-#endif
-
-		if (unlikely(op_ret != -EFAULT)) {
+		if (!IS_ENABLED(CONFIG_MMU) ||
+		    unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
+			/*
+			 * we don't get EFAULT from MMU faults if we don't have
+			 * an MMU, but we might get them from range checking
+			 */
 			ret = op_ret;
 			goto out_put_keys;
 		}
 
-		ret = fault_in_user_writeable(uaddr2);
-		if (ret)
-			goto out_put_keys;
+		if (op_ret == -EFAULT) {
+			ret = fault_in_user_writeable(uaddr2);
+			if (ret)
+				goto out_put_keys;
+		}
 
-		if (!(flags & FLAGS_SHARED))
+		if (!(flags & FLAGS_SHARED)) {
+			cond_resched();
 			goto retry_private;
+		}
 
 		put_futex_key(&key2);
 		put_futex_key(&key1);
+		cond_resched();
 		goto retry;
 	}
 
@@ -2218,11 +2217,11 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 	 * decrement the counter at queue_unlock() when some error has
 	 * occurred and we don't end up adding the task to the list.
 	 */
-	hb_waiters_inc(hb);
+	hb_waiters_inc(hb); /* implies smp_mb(); (A) */
 
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock); /* implies smp_mb(); (A) */
+	spin_lock(&hb->lock);
 	return hb;
 }
 
@@ -2351,7 +2350,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	u32 uval, uninitialized_var(curval), newval;
 	struct task_struct *oldowner, *newowner;
 	u32 newtid;
-	int ret;
+	int ret, err = 0;
 
 	lockdep_assert_held(q->lock_ptr);
 
@@ -2422,14 +2421,17 @@ retry:
 	if (!pi_state->owner)
 		newtid |= FUTEX_OWNER_DIED;
 
-	if (get_futex_value_locked(&uval, uaddr))
-		goto handle_fault;
+	err = get_futex_value_locked(&uval, uaddr);
+	if (err)
+		goto handle_err;
 
 	for (;;) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
-			goto handle_fault;
+		err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+		if (err)
+			goto handle_err;
+
 		if (curval == uval)
 			break;
 		uval = curval;
@@ -2457,23 +2459,37 @@ retry:
 	return 0;
 
 	/*
-	 * 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.
+	 * In order to reschedule or handle a page fault, we need to drop the
+	 * locks here. In the case of a fault, this 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:
+handle_err:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
-	ret = fault_in_user_writeable(uaddr);
+	switch (err) {
+	case -EFAULT:
+		ret = fault_in_user_writeable(uaddr);
+		break;
+
+	case -EAGAIN:
+		cond_resched();
+		ret = 0;
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		ret = err;
+		break;
+	}
 
 	spin_lock(q->lock_ptr);
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
@@ -2858,35 +2874,39 @@ retry_private:
 	 * and BUG when futex_unlock_pi() interleaves with this.
 	 *
 	 * Therefore acquire wait_lock while holding hb->lock, but drop the
-	 * latter before calling rt_mutex_start_proxy_lock(). This still fully
-	 * serializes against futex_unlock_pi() as that does the exact same
-	 * lock handoff sequence.
+	 * latter before calling __rt_mutex_start_proxy_lock(). This
+	 * interleaves with futex_unlock_pi() -- which does a similar lock
+	 * handoff -- such that the latter can observe the futex_q::pi_state
+	 * before __rt_mutex_start_proxy_lock() is done.
 	 */
 	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
 	spin_unlock(q.lock_ptr);
+	/*
+	 * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
+	 * such that futex_unlock_pi() is guaranteed to observe the waiter when
+	 * it sees the futex_q::pi_state.
+	 */
 	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
 	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
 
 	if (ret) {
 		if (ret == 1)
 			ret = 0;
-
-		spin_lock(q.lock_ptr);
-		goto no_block;
+		goto cleanup;
 	}
 
-
 	if (unlikely(to))
 		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
 
 	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
 
+cleanup:
 	spin_lock(q.lock_ptr);
 	/*
-	 * If we failed to acquire the lock (signal/timeout), we must
+	 * If we failed to acquire the lock (deadlock/signal/timeout), we must
 	 * first acquire the hb->lock before removing the lock from the
-	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
-	 * wait lists consistent.
+	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait
+	 * lists consistent.
 	 *
 	 * In particular; it is important that futex_unlock_pi() can not
 	 * observe this inconsistency.
@@ -3010,6 +3030,10 @@ retry:
 		 * there is no point where we hold neither; and therefore
 		 * wake_futex_pi() must observe a state consistent with what we
 		 * observed.
+		 *
+		 * In particular; this forces __rt_mutex_start_proxy() to
+		 * complete such that we're guaranteed to observe the
+		 * rt_waiter. Also see the WARN in wake_futex_pi().
 		 */
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
@@ -3034,10 +3058,8 @@ retry:
 		 * A unconditional UNLOCK_PI op raced against a waiter
 		 * setting the FUTEX_WAITERS bit. Try again.
 		 */
-		if (ret == -EAGAIN) {
-			put_futex_key(&key);
-			goto retry;
-		}
+		if (ret == -EAGAIN)
+			goto pi_retry;
 		/*
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
@@ -3052,9 +3074,19 @@ retry:
 	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
 	 * owner.
 	 */
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+	if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) {
 		spin_unlock(&hb->lock);
-		goto pi_faulted;
+		switch (ret) {
+		case -EFAULT:
+			goto pi_faulted;
+
+		case -EAGAIN:
+			goto pi_retry;
+
+		default:
+			WARN_ON_ONCE(1);
+			goto out_putkey;
+		}
 	}
 
 	/*
@@ -3068,6 +3100,11 @@ out_putkey:
 	put_futex_key(&key);
 	return ret;
 
+pi_retry:
+	put_futex_key(&key);
+	cond_resched();
+	goto retry;
+
 pi_faulted:
 	put_futex_key(&key);
 
@@ -3428,47 +3465,67 @@ err_unlock:
 static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
 {
 	u32 uval, uninitialized_var(nval), mval;
+	int err;
+
+	/* Futex address must be 32bit aligned */
+	if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
+		return -1;
 
 retry:
 	if (get_user(uval, uaddr))
 		return -1;
 
-	if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) {
-		/*
-		 * Ok, this dying thread is truly holding a futex
-		 * of interest. Set the OWNER_DIED bit atomically
-		 * via cmpxchg, and if the value had FUTEX_WAITERS
-		 * set, wake up a waiter (if any). (We have to do a
-		 * futex_wake() even if OWNER_DIED is already set -
-		 * to handle the rare but possible case of recursive
-		 * thread-death.) The rest of the cleanup is done in
-		 * userspace.
-		 */
-		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-		/*
-		 * We are not holding a lock here, but we want to have
-		 * the pagefault_disable/enable() protection because
-		 * we want to handle the fault gracefully. If the
-		 * access fails we try to fault in the futex with R/W
-		 * verification via get_user_pages. get_user() above
-		 * does not guarantee R/W access. If that fails we
-		 * give up and leave the futex locked.
-		 */
-		if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
+		return 0;
+
+	/*
+	 * Ok, this dying thread is truly holding a futex
+	 * of interest. Set the OWNER_DIED bit atomically
+	 * via cmpxchg, and if the value had FUTEX_WAITERS
+	 * set, wake up a waiter (if any). (We have to do a
+	 * futex_wake() even if OWNER_DIED is already set -
+	 * to handle the rare but possible case of recursive
+	 * thread-death.) The rest of the cleanup is done in
+	 * userspace.
+	 */
+	mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
+
+	/*
+	 * We are not holding a lock here, but we want to have
+	 * the pagefault_disable/enable() protection because
+	 * we want to handle the fault gracefully. If the
+	 * access fails we try to fault in the futex with R/W
+	 * verification via get_user_pages. get_user() above
+	 * does not guarantee R/W access. If that fails we
+	 * give up and leave the futex locked.
+	 */
+	if ((err = cmpxchg_futex_value_locked(&nval, uaddr, uval, mval))) {
+		switch (err) {
+		case -EFAULT:
 			if (fault_in_user_writeable(uaddr))
 				return -1;
 			goto retry;
-		}
-		if (nval != uval)
+
+		case -EAGAIN:
+			cond_resched();
 			goto retry;
 
-		/*
-		 * Wake robust non-PI futexes here. The wakeup of
-		 * PI futexes happens in exit_pi_state():
-		 */
-		if (!pi && (uval & FUTEX_WAITERS))
-			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		default:
+			WARN_ON_ONCE(1);
+			return err;
+		}
 	}
+
+	if (nval != uval)
+		goto retry;
+
+	/*
+	 * Wake robust non-PI futexes here. The wakeup of
+	 * PI futexes happens in exit_pi_state():
+	 */
+	if (!pi && (uval & FUTEX_WAITERS))
+		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+
 	return 0;
 }
 
@@ -3812,7 +3869,7 @@ err_unlock:
 #endif /* CONFIG_COMPAT */
 
 #ifdef CONFIG_COMPAT_32BIT_TIME
-COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
+SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val,
 		struct old_timespec32 __user *, utime, u32 __user *, uaddr2,
 		u32, val3)
 {