Linux v4.14.170-rt75-rc1

index 071691963f7b..12702d48aaa3 100644
@@ -353,7 +353,7 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 
 	if (old_notify) {
 #ifdef CONFIG_PREEMPT_RT_BASE
-		kthread_cancel_work_sync(&notify->work);
+		kthread_cancel_work_sync(&old_notify->work);
 #else
 		cancel_work_sync(&old_notify->work);
 #endif

index fcff75934bdc..8d6badac9225 100644
@@ -1192,7 +1192,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(p->cpus_ptr, new_mask))
+	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);

index bcef01354d5c..581d40ee22a8 100644
@@ -243,7 +243,7 @@ struct futex_q {
 	struct plist_node list;
 
 	struct task_struct *task;
-	raw_spinlock_t *lock_ptr;
+	spinlock_t *lock_ptr;
 	union futex_key key;
 	struct futex_pi_state *pi_state;
 	struct rt_mutex_waiter *rt_waiter;

@@ -264,7 +264,7 @@ static const struct futex_q futex_q_init = {
  */
 struct futex_hash_bucket {
 	atomic_t waiters;
-	raw_spinlock_t lock;
+	spinlock_t lock;
 	struct plist_head chain;
 } ____cacheline_aligned_in_smp;
 

@@ -831,13 +831,13 @@ 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.
  */
-static struct futex_pi_state *__put_pi_state(struct futex_pi_state *pi_state)
+static void put_pi_state(struct futex_pi_state *pi_state)
 {
 	if (!pi_state)
-		return NULL;
+		return;
 
 	if (!atomic_dec_and_test(&pi_state->refcount))
-		return NULL;
+		return;
 
 	/*
 	 * If pi_state->owner is NULL, the owner is most probably dying

@@ -857,7 +857,9 @@ static struct futex_pi_state *__put_pi_state(struct futex_pi_state *pi_state)
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	}
 
-	if (!current->pi_state_cache) {
+	if (current->pi_state_cache) {
+		kfree(pi_state);
+	} else {
 		/*
 		 * pi_state->list is already empty.
 		 * clear pi_state->owner.

@@ -866,30 +868,6 @@ static struct futex_pi_state *__put_pi_state(struct futex_pi_state *pi_state)
 		pi_state->owner = NULL;
 		atomic_set(&pi_state->refcount, 1);
 		current->pi_state_cache = pi_state;
-		pi_state = NULL;
-	}
-	return pi_state;
-}
-
-static void put_pi_state(struct futex_pi_state *pi_state)
-{
-	kfree(__put_pi_state(pi_state));
-}
-
-static void put_pi_state_atomic(struct futex_pi_state *pi_state,
-				struct list_head *to_free)
-{
-	if (__put_pi_state(pi_state))
-		list_add(&pi_state->list, to_free);
-}
-
-static void free_pi_state_list(struct list_head *to_free)
-{
-	struct futex_pi_state *p, *next;
-
-	list_for_each_entry_safe(p, next, to_free, list) {
-		list_del(&p->list);
-		kfree(p);
 	}
 }
 

@@ -924,7 +902,6 @@ static void exit_pi_state_list(struct task_struct *curr)
 	struct futex_pi_state *pi_state;
 	struct futex_hash_bucket *hb;
 	union futex_key key = FUTEX_KEY_INIT;
-	LIST_HEAD(to_free);
 
 	if (!futex_cmpxchg_enabled)
 		return;

@@ -958,7 +935,7 @@ static void exit_pi_state_list(struct task_struct *curr)
 		}
 		raw_spin_unlock_irq(&curr->pi_lock);
 
-		raw_spin_lock(&hb->lock);
+		spin_lock(&hb->lock);
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 		raw_spin_lock(&curr->pi_lock);
 		/*

@@ -968,8 +945,10 @@ static void exit_pi_state_list(struct task_struct *curr)
 		if (head->next != next) {
 			/* retain curr->pi_lock for the loop invariant */
 			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
-			raw_spin_unlock(&hb->lock);
-			put_pi_state_atomic(pi_state, &to_free);
+			raw_spin_unlock_irq(&curr->pi_lock);
+			spin_unlock(&hb->lock);
+			raw_spin_lock_irq(&curr->pi_lock);
+			put_pi_state(pi_state);
 			continue;
 		}
 

@@ -980,7 +959,7 @@ static void exit_pi_state_list(struct task_struct *curr)
 
 		raw_spin_unlock(&curr->pi_lock);
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-		raw_spin_unlock(&hb->lock);
+		spin_unlock(&hb->lock);
 
 		rt_mutex_futex_unlock(&pi_state->pi_mutex);
 		put_pi_state(pi_state);

@@ -988,8 +967,6 @@ static void exit_pi_state_list(struct task_struct *curr)
 		raw_spin_lock_irq(&curr->pi_lock);
 	}
 	raw_spin_unlock_irq(&curr->pi_lock);
-
-	free_pi_state_list(&to_free);
 }
 #else
 static inline void exit_pi_state_list(struct task_struct *curr) { }

@@ -1530,7 +1507,7 @@ static void __unqueue_futex(struct futex_q *q)
 {
 	struct futex_hash_bucket *hb;
 
-	if (WARN_ON_SMP(!q->lock_ptr || !raw_spin_is_locked(q->lock_ptr))
+	if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr))
 	    || WARN_ON(plist_node_empty(&q->list)))
 		return;
 

@@ -1658,21 +1635,21 @@ static inline void
 double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
 {
 	if (hb1 <= hb2) {
-		raw_spin_lock(&hb1->lock);
+		spin_lock(&hb1->lock);
 		if (hb1 < hb2)
-			raw_spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING);
+			spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING);
 	} else { /* hb1 > hb2 */
-		raw_spin_lock(&hb2->lock);
-		raw_spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING);
+		spin_lock(&hb2->lock);
+		spin_lock_nested(&hb1->lock, SINGLE_DEPTH_NESTING);
 	}
 }
 
 static inline void
 double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
 {
-	raw_spin_unlock(&hb1->lock);
+	spin_unlock(&hb1->lock);
 	if (hb1 != hb2)
-		raw_spin_unlock(&hb2->lock);
+		spin_unlock(&hb2->lock);
 }
 
 /*

@@ -1700,7 +1677,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	if (!hb_waiters_pending(hb))
 		goto out_put_key;
 
-	raw_spin_lock(&hb->lock);
+	spin_lock(&hb->lock);
 
 	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex (&this->key, &key)) {

@@ -1719,7 +1696,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 		}
 	}
 
-	raw_spin_unlock(&hb->lock);
+	spin_unlock(&hb->lock);
 	wake_up_q(&wake_q);
 out_put_key:
 	put_futex_key(&key);

@@ -2032,7 +2009,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
 	DEFINE_WAKE_Q(wake_q);
-	LIST_HEAD(to_free);
 
 	if (nr_wake < 0 || nr_requeue < 0)
 		return -EINVAL;

@@ -2271,6 +2247,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 				requeue_pi_wake_futex(this, &key2, hb2);
 				drop_count++;
 				continue;
+			} else if (ret == -EAGAIN) {
+				/*
+				 * Waiter was woken by timeout or
+				 * signal and has set pi_blocked_on to
+				 * PI_WAKEUP_INPROGRESS before we
+				 * tried to enqueue it on the rtmutex.
+				 */
+				this->pi_state = NULL;
+				put_pi_state(pi_state);
+				continue;
 			} else if (ret) {
 				/*
 				 * rt_mutex_start_proxy_lock() detected a

@@ -2281,7 +2267,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 				 * object.
 				 */
 				this->pi_state = NULL;
-				put_pi_state_atomic(pi_state, &to_free);
+				put_pi_state(pi_state);
 				/*
 				 * We stop queueing more waiters and let user
 				 * space deal with the mess.

@@ -2298,7 +2284,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	 * in futex_proxy_trylock_atomic() or in lookup_pi_state(). We
 	 * need to drop it here again.
 	 */
-	put_pi_state_atomic(pi_state, &to_free);
+	put_pi_state(pi_state);
 
 out_unlock:
 	double_unlock_hb(hb1, hb2);

@@ -2319,7 +2305,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 out_put_key1:
 	put_futex_key(&key1);
 out:
-	free_pi_state_list(&to_free);
 	return ret ? ret : task_count;
 }
 

@@ -2343,8 +2328,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 
 	q->lock_ptr = &hb->lock;
 
-	raw_spin_lock(&hb->lock);
-
+	spin_lock(&hb->lock);
 	return hb;
 }
 

@@ -2352,7 +2336,7 @@ static inline void
 queue_unlock(struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
-	raw_spin_unlock(&hb->lock);
+	spin_unlock(&hb->lock);
 	hb_waiters_dec(hb);
 }
 

@@ -2391,7 +2375,7 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
 	__queue_me(q, hb);
-	raw_spin_unlock(&hb->lock);
+	spin_unlock(&hb->lock);
 }
 
 /**

@@ -2407,41 +2391,41 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
  */
 static int unqueue_me(struct futex_q *q)
 {
-	raw_spinlock_t *lock_ptr;
+	spinlock_t *lock_ptr;
 	int ret = 0;
 
 	/* In the common case we don't take the spinlock, which is nice. */
 retry:
 	/*
-	 * q->lock_ptr can change between this read and the following
-	 * raw_spin_lock. Use READ_ONCE to forbid the compiler from reloading
-	 * q->lock_ptr and optimizing lock_ptr out of the logic below.
+	 * q->lock_ptr can change between this read and the following spin_lock.
+	 * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and
+	 * optimizing lock_ptr out of the logic below.
 	 */
 	lock_ptr = READ_ONCE(q->lock_ptr);
 	if (lock_ptr != NULL) {
-		raw_spin_lock(lock_ptr);
+		spin_lock(lock_ptr);
 		/*
 		 * q->lock_ptr can change between reading it and
-		 * raw_spin_lock(), causing us to take the wrong lock.  This
+		 * spin_lock(), causing us to take the wrong lock.  This
 		 * corrects the race condition.
 		 *
 		 * Reasoning goes like this: if we have the wrong lock,
 		 * q->lock_ptr must have changed (maybe several times)
-		 * between reading it and the raw_spin_lock().  It can
-		 * change again after the raw_spin_lock() but only if it was
-		 * already changed before the raw_spin_lock().  It cannot,
+		 * between reading it and the spin_lock().  It can
+		 * change again after the spin_lock() but only if it was
+		 * already changed before the spin_lock().  It cannot,
 		 * however, change back to the original value.  Therefore
 		 * we can detect whether we acquired the correct lock.
 		 */
 		if (unlikely(lock_ptr != q->lock_ptr)) {
-			raw_spin_unlock(lock_ptr);
+			spin_unlock(lock_ptr);
 			goto retry;
 		}
 		__unqueue_futex(q);
 
 		BUG_ON(q->pi_state);
 
-		raw_spin_unlock(lock_ptr);
+		spin_unlock(lock_ptr);
 		ret = 1;
 	}
 

@@ -2457,16 +2441,13 @@ static int unqueue_me(struct futex_q *q)
 static void unqueue_me_pi(struct futex_q *q)
 	__releases(q->lock_ptr)
 {
-	struct futex_pi_state *ps;
-
 	__unqueue_futex(q);
 
 	BUG_ON(!q->pi_state);
-	ps = __put_pi_state(q->pi_state);
+	put_pi_state(q->pi_state);
 	q->pi_state = NULL;
 
-	raw_spin_unlock(q->lock_ptr);
-	kfree(ps);
+	spin_unlock(q->lock_ptr);
 }
 
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,

@@ -2599,7 +2580,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	 */
 handle_err:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-	raw_spin_unlock(q->lock_ptr);
+	spin_unlock(q->lock_ptr);
 
 	switch (err) {
 	case -EFAULT:

@@ -2617,7 +2598,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 		break;
 	}
 
-	raw_spin_lock(q->lock_ptr);
+	spin_lock(q->lock_ptr);
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	/*

@@ -2713,7 +2694,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
 	/*
 	 * The task state is guaranteed to be set before another task can
 	 * wake it. set_current_state() is implemented using smp_store_mb() and
-	 * queue_me() calls raw_spin_unlock() upon completion, both serializing
+	 * queue_me() calls spin_unlock() upon completion, both serializing
 	 * access to the hash list and forcing another memory barrier.
 	 */
 	set_current_state(TASK_INTERRUPTIBLE);

@@ -3013,7 +2994,15 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 	 * before __rt_mutex_start_proxy_lock() is done.
 	 */
 	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
-	raw_spin_unlock(q.lock_ptr);
+	/*
+	 * the migrate_disable() here disables migration in the in_atomic() fast
+	 * path which is enabled again in the following spin_unlock(). We have
+	 * one migrate_disable() pending in the slow-path which is reversed
+	 * after the raw_spin_unlock_irq() where we leave the atomic context.
+	 */
+	migrate_disable();
+
+	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

@@ -3021,6 +3010,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 	 */
 	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);
+	migrate_enable();
 
 	if (ret) {
 		if (ret == 1)

@@ -3034,7 +3024,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
 
 cleanup:
-	raw_spin_lock(q.lock_ptr);
+	spin_lock(q.lock_ptr);
 	/*
 	 * If we failed to acquire the lock (deadlock/signal/timeout), we must
 	 * first acquire the hb->lock before removing the lock from the

@@ -3135,7 +3125,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 		return ret;
 
 	hb = hash_futex(&key);
-	raw_spin_lock(&hb->lock);
+	spin_lock(&hb->lock);
 
 	/*
 	 * Check waiters first. We do not trust user space values at

@@ -3169,10 +3159,19 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 		 * rt_waiter. Also see the WARN in wake_futex_pi().
 		 */
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
-		raw_spin_unlock(&hb->lock);
+		/*
+		 * Magic trickery for now to make the RT migrate disable
+		 * logic happy. The following spin_unlock() happens with
+		 * interrupts disabled so the internal migrate_enable()
+		 * won't undo the migrate_disable() which was issued when
+		 * locking hb->lock.
+		 */
+		migrate_disable();
+		spin_unlock(&hb->lock);
 
 		/* drops pi_state->pi_mutex.wait_lock */
 		ret = wake_futex_pi(uaddr, uval, pi_state);
+		migrate_enable();
 
 		put_pi_state(pi_state);
 

@@ -3208,7 +3207,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 	 * owner.
 	 */
 	if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) {
-		raw_spin_unlock(&hb->lock);
+		spin_unlock(&hb->lock);
 		switch (ret) {
 		case -EFAULT:
 			goto pi_faulted;

@@ -3228,7 +3227,7 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 	ret = (curval == uval) ? 0 : -EAGAIN;
 
 out_unlock:
-	raw_spin_unlock(&hb->lock);
+	spin_unlock(&hb->lock);
 out_putkey:
 	put_futex_key(&key);
 	return ret;

@@ -3344,7 +3343,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct futex_hash_bucket *hb;
+	struct futex_hash_bucket *hb, *hb2;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
 	int res, ret;

@@ -3402,20 +3401,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
 	futex_wait_queue_me(hb, &q, to);
 
-	raw_spin_lock(&hb->lock);
-	ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
-	raw_spin_unlock(&hb->lock);
-	if (ret)
-		goto out_put_keys;
+	/*
+	 * On RT we must avoid races with requeue and trying to block
+	 * on two mutexes (hb->lock and uaddr2's rtmutex) by
+	 * serializing access to pi_blocked_on with pi_lock.
+	 */
+	raw_spin_lock_irq(&current->pi_lock);
+	if (current->pi_blocked_on) {
+		/*
+		 * We have been requeued or are in the process of
+		 * being requeued.
+		 */
+		raw_spin_unlock_irq(&current->pi_lock);
+	} else {
+		/*
+		 * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS
+		 * prevents a concurrent requeue from moving us to the
+		 * uaddr2 rtmutex. After that we can safely acquire
+		 * (and possibly block on) hb->lock.
+		 */
+		current->pi_blocked_on = PI_WAKEUP_INPROGRESS;
+		raw_spin_unlock_irq(&current->pi_lock);
+
+		spin_lock(&hb->lock);
+
+		/*
+		 * Clean up pi_blocked_on. We might leak it otherwise
+		 * when we succeeded with the hb->lock in the fast
+		 * path.
+		 */
+		raw_spin_lock_irq(&current->pi_lock);
+		current->pi_blocked_on = NULL;
+		raw_spin_unlock_irq(&current->pi_lock);
+
+		ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
+		spin_unlock(&hb->lock);
+		if (ret)
+			goto out_put_keys;
+	}
 
 	/*
-	 * In order for us to be here, we know our q.key == key2, and since
-	 * we took the hb->lock above, we also know that futex_requeue() has
-	 * completed and we no longer have to concern ourselves with a wakeup
-	 * race with the atomic proxy lock acquisition by the requeue code. The
-	 * futex_requeue dropped our key1 reference and incremented our key2
-	 * reference count.
+	 * In order to be here, we have either been requeued, are in
+	 * the process of being requeued, or requeue successfully
+	 * acquired uaddr2 on our behalf.  If pi_blocked_on was
+	 * non-null above, we may be racing with a requeue.  Do not
+	 * rely on q->lock_ptr to be hb2->lock until after blocking on
+	 * hb->lock or hb2->lock. The futex_requeue dropped our key1
+	 * reference and incremented our key2 reference count.
 	 */
+	hb2 = hash_futex(&key2);
 
 	/* Check if the requeue code acquired the second futex for us. */
 	if (!q.rt_waiter) {

@@ -3424,9 +3458,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 * did a lock-steal - fix up the PI-state in that case.
 		 */
 		if (q.pi_state && (q.pi_state->owner != current)) {
-			struct futex_pi_state *ps_free;
-
-			raw_spin_lock(q.lock_ptr);
+			spin_lock(&hb2->lock);
+			BUG_ON(&hb2->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;

@@ -3436,9 +3469,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
 			 */
-			ps_free = __put_pi_state(q.pi_state);
-			raw_spin_unlock(q.lock_ptr);
-			kfree(ps_free);
+			put_pi_state(q.pi_state);
+			spin_unlock(&hb2->lock);
 		}
 	} else {
 		struct rt_mutex *pi_mutex;

@@ -3452,7 +3484,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		pi_mutex = &q.pi_state->pi_mutex;
 		ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
 
-		raw_spin_lock(q.lock_ptr);
+		spin_lock(&hb2->lock);
+		BUG_ON(&hb2->lock != q.lock_ptr);
 		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
 			ret = 0;
 

@@ -4225,7 +4258,7 @@ static int __init futex_init(void)
 	for (i = 0; i < futex_hashsize; i++) {
 		atomic_set(&futex_queues[i].waiters, 0);
 		plist_head_init(&futex_queues[i].chain);
-		raw_spin_lock_init(&futex_queues[i].lock);
+		spin_lock_init(&futex_queues[i].lock);
 	}
 
 	return 0;

119 lines not on this page · raw message

index 2f6662d052d6..2a157c78e18c 100644
@@ -131,6 +131,9 @@ enum rtmutex_chainwalk {
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
+#define PI_WAKEUP_INPROGRESS	((struct rt_mutex_waiter *) 1)
+#define PI_REQUEUE_INPROGRESS	((struct rt_mutex_waiter *) 2)
+
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);

index 4708129e8df1..189e6f08575e 100644
@@ -6923,9 +6923,8 @@ migrate_disable_update_cpus_allowed(struct task_struct *p)
 	struct rq *rq;
 	struct rq_flags rf;
 
-	p->cpus_ptr = cpumask_of(smp_processor_id());
-
 	rq = task_rq_lock(p, &rf);
+	p->cpus_ptr = cpumask_of(smp_processor_id());
 	update_nr_migratory(p, -1);
 	p->nr_cpus_allowed = 1;
 	task_rq_unlock(rq, p, &rf);

@@ -6937,9 +6936,8 @@ migrate_enable_update_cpus_allowed(struct task_struct *p)
 	struct rq *rq;
 	struct rq_flags rf;
 
-	p->cpus_ptr = &p->cpus_mask;
-
 	rq = task_rq_lock(p, &rf);
+	p->cpus_ptr = &p->cpus_mask;
 	p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask);
 	update_nr_migratory(p, 1);
 	task_rq_unlock(rq, p, &rf);

index 1177f2815040..4bc01a2a9a88 100644
@@ -2328,6 +2328,26 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 	rt_mutex_set_owner(lock, NULL);
 }
 
+static void fixup_rt_mutex_blocked(struct rt_mutex *lock)
+{
+	struct task_struct *tsk = current;
+	/*
+	 * RT has a problem here when the wait got interrupted by a timeout
+	 * or a signal. task->pi_blocked_on is still set. The task must
+	 * acquire the hash bucket lock when returning from this function.
+	 *
+	 * If the hash bucket lock is contended then the
+	 * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in
+	 * task_blocks_on_rt_mutex() will trigger. This can be avoided by
+	 * clearing task->pi_blocked_on which removes the task from the
+	 * boosting chain of the rtmutex. That's correct because the task
+	 * is not longer blocked on it.
+	 */
+	raw_spin_lock(&tsk->pi_lock);
+	tsk->pi_blocked_on = NULL;
+	raw_spin_unlock(&tsk->pi_lock);
+}
+
 /**
  * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
  * @lock:		the rt_mutex to take

@@ -2400,6 +2420,9 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		ret = 0;
 	}
 
+	if (ret)
+		fixup_rt_mutex_blocked(lock);
+
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;

@@ -2480,7 +2503,6 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *to,
 			       struct rt_mutex_waiter *waiter)
 {
-	struct task_struct *tsk = current;
 	int ret;
 
 	raw_spin_lock_irq(&lock->wait_lock);

@@ -2492,23 +2514,8 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 	 * have to fix that up.
 	 */
 	fixup_rt_mutex_waiters(lock);
-	/*
-	 * RT has a problem here when the wait got interrupted by a timeout
-	 * or a signal. task->pi_blocked_on is still set. The task must
-	 * acquire the hash bucket lock when returning from this function.
-	 *
-	 * If the hash bucket lock is contended then the
-	 * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in
-	 * task_blocks_on_rt_mutex() will trigger. This can be avoided by
-	 * clearing task->pi_blocked_on which removes the task from the
-	 * boosting chain of the rtmutex. That's correct because the task
-	 * is not longer blocked on it.
-	 */
-	if (ret) {
-		raw_spin_lock(&tsk->pi_lock);
-		tsk->pi_blocked_on = NULL;
-		raw_spin_unlock(&tsk->pi_lock);
-	}
+	if (ret)
+		fixup_rt_mutex_blocked(lock);
 
 	raw_spin_unlock_irq(&lock->wait_lock);
 

index cf4e1452d4b4..d96714e1858c 100644
@@ -325,30 +325,6 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 }
 
 #ifdef CONFIG_MMU
-/*
- * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock.  If the lock is not
- * initialized by pgtable_page_ctor() then a coredump of the vector page will
- * fail.
- */
-static int __init vectors_user_mapping_init_page(void)
-{
-	struct page *page;
-	unsigned long addr = 0xffff0000;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-
-	pgd = pgd_offset_k(addr);
-	pud = pud_offset(pgd, addr);
-	pmd = pmd_offset(pud, addr);
-	page = pmd_page(*(pmd));
-
-	pgtable_page_ctor(page);
-
-	return 0;
-}
-late_initcall(vectors_user_mapping_init_page);
-
 #ifdef CONFIG_KUSER_HELPERS
 /*
  * The vectors page is always readable from user space for the

index e2b2196fd942..71886a8e8f71 100644
@@ -51,7 +51,7 @@ struct userfaultfd_ctx {
 	/* waitqueue head for events */
 	wait_queue_head_t event_wqh;
 	/* a refile sequence protected by fault_pending_wqh lock */
-	struct seqcount refile_seq;
+	seqlock_t refile_seq;
 	/* pseudo fd refcounting */
 	atomic_t refcount;
 	/* userfaultfd syscall flags */

@@ -1047,7 +1047,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 			 * waitqueue could become empty if this is the
 			 * only userfault.
 			 */
-			write_seqcount_begin(&ctx->refile_seq);
+			write_seqlock(&ctx->refile_seq);
 
 			/*
 			 * The fault_pending_wqh.lock prevents the uwq

@@ -1073,7 +1073,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 			list_del(&uwq->wq.entry);
 			__add_wait_queue(&ctx->fault_wqh, &uwq->wq);
 
-			write_seqcount_end(&ctx->refile_seq);
+			write_sequnlock(&ctx->refile_seq);
 
 			/* careful to always initialize msg if ret == 0 */
 			*msg = uwq->msg;

@@ -1246,11 +1246,11 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
 	 * sure we've userfaults to wake.
 	 */
 	do {
-		seq = read_seqcount_begin(&ctx->refile_seq);
+		seq = read_seqbegin(&ctx->refile_seq);
 		need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
 			waitqueue_active(&ctx->fault_wqh);
 		cond_resched();
-	} while (read_seqcount_retry(&ctx->refile_seq, seq));
+	} while (read_seqretry(&ctx->refile_seq, seq));
 	if (need_wakeup)
 		__wake_userfault(ctx, range);
 }

@@ -1915,7 +1915,7 @@ static void init_once_userfaultfd_ctx(void *mem)
 	init_waitqueue_head(&ctx->fault_wqh);
 	init_waitqueue_head(&ctx->event_wqh);
 	init_waitqueue_head(&ctx->fd_wqh);
-	seqcount_init(&ctx->refile_seq);
+	seqlock_init(&ctx->refile_seq);
 }
 
 /**

index 17718a11782b..d7925ee4b052 100644
@@ -26,7 +26,7 @@
  *
  * The following locks and mutexes are used by kmemleak:
  *
- * - kmemleak_lock (raw spinlock): protects the object_list modifications and
+ * - kmemleak_lock (raw_spinlock_t): protects the object_list modifications and
  *   accesses to the object_tree_root. The object_list is the main list
  *   holding the metadata (struct kmemleak_object) for the allocated memory
  *   blocks. The object_tree_root is a red black tree used to look-up

@@ -35,13 +35,13 @@
  *   object_tree_root in the create_object() function called from the
  *   kmemleak_alloc() callback and removed in delete_object() called from the
  *   kmemleak_free() callback
- * - kmemleak_object.lock (spinlock): protects a kmemleak_object. Accesses to
- *   the metadata (e.g. count) are protected by this lock. Note that some
- *   members of this structure may be protected by other means (atomic or
- *   kmemleak_lock). This lock is also held when scanning the corresponding
- *   memory block to avoid the kernel freeing it via the kmemleak_free()
- *   callback. This is less heavyweight than holding a global lock like
- *   kmemleak_lock during scanning
+ * - kmemleak_object.lock (raw_spinlock_t): protects a kmemleak_object.
+ *   Accesses to the metadata (e.g. count) are protected by this lock. Note
+ *   that some members of this structure may be protected by other means
+ *   (atomic or kmemleak_lock). This lock is also held when scanning the
+ *   corresponding memory block to avoid the kernel freeing it via the
+ *   kmemleak_free() callback. This is less heavyweight than holding a global
+ *   lock like kmemleak_lock during scanning.
  * - scan_mutex (mutex): ensures that only one thread may scan the memory for
  *   unreferenced objects at a time. The gray_list contains the objects which
  *   are already referenced or marked as false positives and need to be

@@ -197,7 +197,7 @@ static LIST_HEAD(object_list);
 static LIST_HEAD(gray_list);
 /* search tree for object boundaries */
 static struct rb_root object_tree_root = RB_ROOT;
-/* rw_lock protecting the access to object_list and object_tree_root */
+/* protecting the access to object_list and object_tree_root */
 static DEFINE_RAW_SPINLOCK(kmemleak_lock);
 
 /* allocation caches for kmemleak internal data */

index 921eab83cd34..81c89d87723b 100644
@@ -3,6 +3,7 @@
 
 #include <linux/percpu.h>
 #include <linux/spinlock.h>
+#include <asm/current.h>
 
 #ifdef CONFIG_PREEMPT_RT_BASE
 

index 5801e516ba63..af05a63e4c06 100644
@@ -15,6 +15,7 @@
 #include <linux/llist.h>
 
 typedef void (*smp_call_func_t)(void *info);
+typedef bool (*smp_cond_func_t)(int cpu, void *info);
 struct __call_single_data {
 	struct llist_node llist;
 	smp_call_func_t func;

@@ -49,9 +50,8 @@ void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
  * cond_func returns a positive value. This may include the local
  * processor.
  */
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
-		smp_call_func_t func, void *info, bool wait,
-		gfp_t gfp_flags);
+void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
+		      void *info, bool wait, gfp_t gfp_flags);
 
 int smp_call_function_single_async(int cpu, call_single_data_t *csd);
 

index c94dd85c8d41..00fbb6aa948a 100644
@@ -667,9 +667,8 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * You must not call this function with disabled interrupts or
  * from a hardware interrupt handler or from a bottom half handler.
  */
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
-			smp_call_func_t func, void *info, bool wait,
-			gfp_t gfp_flags)
+void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
+		      void *info, bool wait, gfp_t gfp_flags)
 {
 	cpumask_var_t cpus;
 	int cpu, ret;

index 42c46bf3e0a5..a0276ba75270 100644
@@ -68,9 +68,8 @@ EXPORT_SYMBOL(on_each_cpu_mask);
  * Preemption is disabled here to make sure the cond_func is called under the
  * same condtions in UP and SMP.
  */
-void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
-		      smp_call_func_t func, void *info, bool wait,
-		      gfp_t gfp_flags)
+void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func,
+		      void *info, bool wait, gfp_t gfp_flags)
 {
 	unsigned long flags;
 

index 0503b31e2a87..a359a24ebd9f 100644
@@ -6102,10 +6102,10 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page),
 				     -nr_entries);
 	memcg_check_events(memcg, page);
+	local_unlock_irqrestore(event_lock, flags);
 
 	if (!mem_cgroup_is_root(memcg))
 		css_put_many(&memcg->css, nr_entries);
-	local_unlock_irqrestore(event_lock, flags);
 }
 
 /**

index 4bc01a2a9a88..848d9ed6f053 100644
@@ -1142,6 +1142,7 @@ void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
 void __lockfunc rt_spin_lock(spinlock_t *lock)
 {
 	sleeping_lock_inc();
+	rcu_read_lock();
 	migrate_disable();
 	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
 	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);

@@ -1157,6 +1158,7 @@ void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
 void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
 {
 	sleeping_lock_inc();
+	rcu_read_lock();
 	migrate_disable();
 	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
 	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);

@@ -1170,6 +1172,7 @@ void __lockfunc rt_spin_unlock(spinlock_t *lock)
 	spin_release(&lock->dep_map, 1, _RET_IP_);
 	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
 	migrate_enable();
+	rcu_read_unlock();
 	sleeping_lock_dec();
 }
 EXPORT_SYMBOL(rt_spin_unlock);

@@ -1201,6 +1204,7 @@ int __lockfunc rt_spin_trylock(spinlock_t *lock)
 	ret = __rt_mutex_trylock(&lock->lock);
 	if (ret) {
 		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
 	} else {
 		migrate_enable();
 		sleeping_lock_dec();

@@ -1217,6 +1221,7 @@ int __lockfunc rt_spin_trylock_bh(spinlock_t *lock)
 	ret = __rt_mutex_trylock(&lock->lock);
 	if (ret) {
 		sleeping_lock_inc();
+		rcu_read_lock();
 		migrate_disable();
 		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 	} else

@@ -1233,6 +1238,7 @@ int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags)
 	ret = __rt_mutex_trylock(&lock->lock);
 	if (ret) {
 		sleeping_lock_inc();
+		rcu_read_lock();
 		migrate_disable();
 		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 	}

index c3b91205161c..0ae8c62ea832 100644
@@ -310,6 +310,7 @@ int __lockfunc rt_read_trylock(rwlock_t *rwlock)
 	ret = do_read_rt_trylock(rwlock);
 	if (ret) {
 		rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
 	} else {
 		migrate_enable();
 		sleeping_lock_dec();

@@ -327,6 +328,7 @@ int __lockfunc rt_write_trylock(rwlock_t *rwlock)
 	ret = do_write_rt_trylock(rwlock);
 	if (ret) {
 		rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
 	} else {
 		migrate_enable();
 		sleeping_lock_dec();

@@ -338,6 +340,7 @@ EXPORT_SYMBOL(rt_write_trylock);
 void __lockfunc rt_read_lock(rwlock_t *rwlock)
 {
 	sleeping_lock_inc();
+	rcu_read_lock();
 	migrate_disable();
 	rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_);
 	do_read_rt_lock(rwlock);

@@ -347,6 +350,7 @@ EXPORT_SYMBOL(rt_read_lock);
 void __lockfunc rt_write_lock(rwlock_t *rwlock)
 {
 	sleeping_lock_inc();
+	rcu_read_lock();
 	migrate_disable();
 	rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
 	do_write_rt_lock(rwlock);

@@ -358,6 +362,7 @@ void __lockfunc rt_read_unlock(rwlock_t *rwlock)
 	rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
 	do_read_rt_unlock(rwlock);
 	migrate_enable();
+	rcu_read_unlock();
 	sleeping_lock_dec();
 }
 EXPORT_SYMBOL(rt_read_unlock);

@@ -367,6 +372,7 @@ void __lockfunc rt_write_unlock(rwlock_t *rwlock)
 	rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
 	do_write_rt_unlock(rwlock);
 	migrate_enable();
+	rcu_read_unlock();
 	sleeping_lock_dec();
 }
 EXPORT_SYMBOL(rt_write_unlock);

index 6728662a81e8..2e15fbc01eda 100644
@@ -241,8 +241,30 @@ static inline int __migrate_disabled(struct task_struct *p)
 }
 
 #else
-#define migrate_disable()		preempt_disable()
-#define migrate_enable()		preempt_enable()
+/**
+ * migrate_disable - Prevent migration of the current task
+ *
+ * Maps to preempt_disable() which also disables preemption. Use
+ * migrate_disable() to annotate that the intent is to prevent migration
+ * but not necessarily preemption.
+ *
+ * Can be invoked nested like preempt_disable() and needs the corresponding
+ * number of migrate_enable() invocations.
+ */
+#define migrate_disable()	preempt_disable()
+
+/**
+ * migrate_enable - Allow migration of the current task
+ *
+ * Counterpart to migrate_disable().
+ *
+ * As migrate_disable() can be invoked nested only the uttermost invocation
+ * reenables migration.
+ *
+ * Currently mapped to preempt_enable().
+ */
+#define migrate_enable()	preempt_enable()
+
 static inline int __migrate_disabled(struct task_struct *p)
 {
 	return 0;

index fa2c93cb42a2..92e12f5d0d64 100644
@@ -498,7 +498,7 @@ static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu)
 
 static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu)
 {
-	return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
+	return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu;
 }
 
 /*

index 189e6f08575e..46324d2099e3 100644
@@ -7008,6 +7008,7 @@ void migrate_enable(void)
 	if (p->migrate_disable_update) {
 		struct rq *rq;
 		struct rq_flags rf;
+		int cpu = task_cpu(p);
 
 		rq = task_rq_lock(p, &rf);
 		update_rq_clock(rq);

@@ -7017,21 +7018,15 @@ void migrate_enable(void)
 
 		p->migrate_disable_update = 0;
 
-		WARN_ON(smp_processor_id() != task_cpu(p));
-		if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
-			const struct cpumask *cpu_valid_mask = cpu_active_mask;
-			struct migration_arg arg;
-			unsigned int dest_cpu;
-
-			if (p->flags & PF_KTHREAD) {
-				/*
-				 * Kernel threads are allowed on online && !active CPUs
-				 */
-				cpu_valid_mask = cpu_online_mask;
-			}
-			dest_cpu = cpumask_any_and(cpu_valid_mask, &p->cpus_mask);
-			arg.task = p;
-			arg.dest_cpu = dest_cpu;
+		WARN_ON(smp_processor_id() != cpu);
+		if (!cpumask_test_cpu(cpu, &p->cpus_mask)) {
+			struct migration_arg arg = { p };
+			struct rq_flags rf;
+
+			rq = task_rq_lock(p, &rf);
+			update_rq_clock(rq);
+			arg.dest_cpu = select_fallback_rq(cpu, p);
+			task_rq_unlock(rq, p, &rf);
 
 			unpin_current_cpu();
 			preempt_lazy_enable();

index c18e23619f95..17718a11782b 100644
@@ -148,7 +148,7 @@ struct kmemleak_scan_area {
  * (use_count) and freed using the RCU mechanism.
  */
 struct kmemleak_object {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	unsigned int flags;		/* object status flags */
 	struct list_head object_list;
 	struct list_head gray_list;

@@ -562,7 +562,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
 	INIT_LIST_HEAD(&object->object_list);
 	INIT_LIST_HEAD(&object->gray_list);
 	INIT_HLIST_HEAD(&object->area_list);
-	spin_lock_init(&object->lock);
+	raw_spin_lock_init(&object->lock);
 	atomic_set(&object->use_count, 1);
 	object->flags = OBJECT_ALLOCATED;
 	object->pointer = ptr;

@@ -643,9 +643,9 @@ static void __delete_object(struct kmemleak_object *object)
 	 * Locking here also ensures that the corresponding memory block
 	 * cannot be freed when it is being scanned.
 	 */
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	object->flags &= ~OBJECT_ALLOCATED;
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	put_object(object);
 }
 

@@ -717,9 +717,9 @@ static void paint_it(struct kmemleak_object *object, int color)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	__paint_it(object, color);
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 }
 
 static void paint_ptr(unsigned long ptr, int color)

@@ -779,7 +779,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 		goto out;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	if (size == SIZE_MAX) {
 		size = object->pointer + object->size - ptr;
 	} else if (ptr + size > object->pointer + object->size) {

@@ -795,7 +795,7 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 
 	hlist_add_head(&area->node, &object->area_list);
 out_unlock:
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 out:
 	put_object(object);
 }

@@ -818,9 +818,9 @@ static void object_set_excess_ref(unsigned long ptr, unsigned long excess_ref)
 		return;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	object->excess_ref = excess_ref;
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	put_object(object);
 }
 

@@ -840,9 +840,9 @@ static void object_no_scan(unsigned long ptr)
 		return;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	object->flags |= OBJECT_NO_SCAN;
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	put_object(object);
 }
 

@@ -903,11 +903,11 @@ static void early_alloc(struct early_log *log)
 			       log->min_count, GFP_ATOMIC);
 	if (!object)
 		goto out;
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	for (i = 0; i < log->trace_len; i++)
 		object->trace[i] = log->trace[i];
 	object->trace_len = log->trace_len;
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 out:
 	rcu_read_unlock();
 }

@@ -1097,9 +1097,9 @@ void __ref kmemleak_update_trace(const void *ptr)
 		return;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	object->trace_len = __save_stack_trace(object->trace);
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 
 	put_object(object);
 }

@@ -1335,7 +1335,7 @@ static void scan_block(void *_start, void *_end,
 		 * previously acquired in scan_object(). These locks are
 		 * enclosed by scan_mutex.
 		 */
-		spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
+		raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
 		/* only pass surplus references (object already gray) */
 		if (color_gray(object)) {
 			excess_ref = object->excess_ref;

@@ -1344,7 +1344,7 @@ static void scan_block(void *_start, void *_end,
 			excess_ref = 0;
 			update_refs(object);
 		}
-		spin_unlock(&object->lock);
+		raw_spin_unlock(&object->lock);
 
 		if (excess_ref) {
 			object = lookup_object(excess_ref, 0);

@@ -1353,9 +1353,9 @@ static void scan_block(void *_start, void *_end,
 			if (object == scanned)
 				/* circular reference, ignore */
 				continue;
-			spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
+			raw_spin_lock_nested(&object->lock, SINGLE_DEPTH_NESTING);
 			update_refs(object);
-			spin_unlock(&object->lock);
+			raw_spin_unlock(&object->lock);
 		}
 	}
 	raw_spin_unlock_irqrestore(&kmemleak_lock, flags);

@@ -1391,7 +1391,7 @@ static void scan_object(struct kmemleak_object *object)
 	 * Once the object->lock is acquired, the corresponding memory block
 	 * cannot be freed (the same lock is acquired in delete_object).
 	 */
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	if (object->flags & OBJECT_NO_SCAN)
 		goto out;
 	if (!(object->flags & OBJECT_ALLOCATED))

@@ -1410,9 +1410,9 @@ static void scan_object(struct kmemleak_object *object)
 			if (start >= end)
 				break;
 
-			spin_unlock_irqrestore(&object->lock, flags);
+			raw_spin_unlock_irqrestore(&object->lock, flags);
 			cond_resched();
-			spin_lock_irqsave(&object->lock, flags);
+			raw_spin_lock_irqsave(&object->lock, flags);
 		} while (object->flags & OBJECT_ALLOCATED);
 	} else
 		hlist_for_each_entry(area, &object->area_list, node)

@@ -1420,7 +1420,7 @@ static void scan_object(struct kmemleak_object *object)
 				   (void *)(area->start + area->size),
 				   object);
 out:
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 }
 
 /*

@@ -1473,7 +1473,7 @@ static void kmemleak_scan(void)
 	/* prepare the kmemleak_object's */
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
-		spin_lock_irqsave(&object->lock, flags);
+		raw_spin_lock_irqsave(&object->lock, flags);
 #ifdef DEBUG
 		/*
 		 * With a few exceptions there should be a maximum of

@@ -1490,7 +1490,7 @@ static void kmemleak_scan(void)
 		if (color_gray(object) && get_object(object))
 			list_add_tail(&object->gray_list, &gray_list);
 
-		spin_unlock_irqrestore(&object->lock, flags);
+		raw_spin_unlock_irqrestore(&object->lock, flags);
 	}
 	rcu_read_unlock();
 

@@ -1555,14 +1555,14 @@ static void kmemleak_scan(void)
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
-		spin_lock_irqsave(&object->lock, flags);
+		raw_spin_lock_irqsave(&object->lock, flags);
 		if (color_white(object) && (object->flags & OBJECT_ALLOCATED)
 		    && update_checksum(object) && get_object(object)) {
 			/* color it gray temporarily */
 			object->count = object->min_count;
 			list_add_tail(&object->gray_list, &gray_list);
 		}
-		spin_unlock_irqrestore(&object->lock, flags);
+		raw_spin_unlock_irqrestore(&object->lock, flags);
 	}
 	rcu_read_unlock();
 

@@ -1582,13 +1582,13 @@ static void kmemleak_scan(void)
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
-		spin_lock_irqsave(&object->lock, flags);
+		raw_spin_lock_irqsave(&object->lock, flags);
 		if (unreferenced_object(object) &&
 		    !(object->flags & OBJECT_REPORTED)) {
 			object->flags |= OBJECT_REPORTED;
 			new_leaks++;
 		}
-		spin_unlock_irqrestore(&object->lock, flags);
+		raw_spin_unlock_irqrestore(&object->lock, flags);
 	}
 	rcu_read_unlock();
 

@@ -1740,10 +1740,10 @@ static int kmemleak_seq_show(struct seq_file *seq, void *v)
 	struct kmemleak_object *object = v;
 	unsigned long flags;
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	if ((object->flags & OBJECT_REPORTED) && unreferenced_object(object))
 		print_unreferenced(seq, object);
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 	return 0;
 }
 

@@ -1773,9 +1773,9 @@ static int dump_str_object_info(const char *str)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&object->lock, flags);
+	raw_spin_lock_irqsave(&object->lock, flags);
 	dump_object_info(object);
-	spin_unlock_irqrestore(&object->lock, flags);
+	raw_spin_unlock_irqrestore(&object->lock, flags);
 
 	put_object(object);
 	return 0;

@@ -1794,11 +1794,11 @@ static void kmemleak_clear(void)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(object, &object_list, object_list) {
-		spin_lock_irqsave(&object->lock, flags);
+		raw_spin_lock_irqsave(&object->lock, flags);
 		if ((object->flags & OBJECT_REPORTED) &&
 		    unreferenced_object(object))
 			__paint_it(object, KMEMLEAK_GREY);
-		spin_unlock_irqrestore(&object->lock, flags);
+		raw_spin_unlock_irqrestore(&object->lock, flags);
 	}
 	rcu_read_unlock();
 

index c652b4a820cc..f94cfb3a41ed 100644
@@ -147,26 +147,21 @@ static bool location_is_valid(struct source_location *loc)
 {
 	return loc->file_name != NULL;
 }
-
-static DEFINE_SPINLOCK(report_lock);
-
-static void ubsan_prologue(struct source_location *location,
-			unsigned long *flags)
+static void ubsan_prologue(struct source_location *location)
 {
 	current->in_ubsan++;
-	spin_lock_irqsave(&report_lock, *flags);
 
 	pr_err("========================================"
 		"========================================\n");
 	print_source_location("UBSAN: Undefined behaviour in", location);
 }
 
-static void ubsan_epilogue(unsigned long *flags)
+static void ubsan_epilogue(void)
 {
 	dump_stack();
 	pr_err("========================================"
 		"========================================\n");
-	spin_unlock_irqrestore(&report_lock, *flags);
+
 	current->in_ubsan--;
 }
 

@@ -175,14 +170,13 @@ static void handle_overflow(struct overflow_data *data, void *lhs,
 {
 
 	struct type_descriptor *type = data->type;
-	unsigned long flags;
 	char lhs_val_str[VALUE_LENGTH];
 	char rhs_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(lhs_val_str, sizeof(lhs_val_str), type, lhs);
 	val_to_string(rhs_val_str, sizeof(rhs_val_str), type, rhs);

@@ -194,7 +188,7 @@ static void handle_overflow(struct overflow_data *data, void *lhs,
 		rhs_val_str,
 		type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 
 void __ubsan_handle_add_overflow(struct overflow_data *data,

@@ -222,20 +216,19 @@ EXPORT_SYMBOL(__ubsan_handle_mul_overflow);
 void __ubsan_handle_negate_overflow(struct overflow_data *data,
 				void *old_val)
 {
-	unsigned long flags;
 	char old_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(old_val_str, sizeof(old_val_str), data->type, old_val);
 
 	pr_err("negation of %s cannot be represented in type %s:\n",
 		old_val_str, data->type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_negate_overflow);
 

@@ -243,13 +236,12 @@ EXPORT_SYMBOL(__ubsan_handle_negate_overflow);
 void __ubsan_handle_divrem_overflow(struct overflow_data *data,
 				void *lhs, void *rhs)
 {
-	unsigned long flags;
 	char rhs_val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(rhs_val_str, sizeof(rhs_val_str), data->type, rhs);
 

@@ -259,58 +251,52 @@ void __ubsan_handle_divrem_overflow(struct overflow_data *data,
 	else
 		pr_err("division by zero\n");
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_divrem_overflow);
 
 static void handle_null_ptr_deref(struct type_mismatch_data_common *data)
 {
-	unsigned long flags;
-
 	if (suppress_report(data->location))
 		return;
 
-	ubsan_prologue(data->location, &flags);
+	ubsan_prologue(data->location);
 
 	pr_err("%s null pointer of type %s\n",
 		type_check_kinds[data->type_check_kind],
 		data->type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 
 static void handle_misaligned_access(struct type_mismatch_data_common *data,
 				unsigned long ptr)
 {
-	unsigned long flags;
-
 	if (suppress_report(data->location))
 		return;
 
-	ubsan_prologue(data->location, &flags);
+	ubsan_prologue(data->location);
 
 	pr_err("%s misaligned address %p for type %s\n",
 		type_check_kinds[data->type_check_kind],
 		(void *)ptr, data->type->type_name);
 	pr_err("which requires %ld byte alignment\n", data->alignment);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 
 static void handle_object_size_mismatch(struct type_mismatch_data_common *data,
 					unsigned long ptr)
 {
-	unsigned long flags;
-
 	if (suppress_report(data->location))
 		return;
 
-	ubsan_prologue(data->location, &flags);
+	ubsan_prologue(data->location);
 	pr_err("%s address %p with insufficient space\n",
 		type_check_kinds[data->type_check_kind],
 		(void *) ptr);
 	pr_err("for an object of type %s\n", data->type->type_name);
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 
 static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data,

@@ -356,12 +342,10 @@ EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1);
 
 void __ubsan_handle_nonnull_return(struct nonnull_return_data *data)
 {
-	unsigned long flags;
-
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	pr_err("null pointer returned from function declared to never return null\n");
 

@@ -369,49 +353,46 @@ void __ubsan_handle_nonnull_return(struct nonnull_return_data *data)
 		print_source_location("returns_nonnull attribute specified in",
 				&data->attr_location);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_nonnull_return);
 
 void __ubsan_handle_vla_bound_not_positive(struct vla_bound_data *data,
 					void *bound)
 {
-	unsigned long flags;
 	char bound_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(bound_str, sizeof(bound_str), data->type, bound);
 	pr_err("variable length array bound value %s <= 0\n", bound_str);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_vla_bound_not_positive);
 
 void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index)
 {
-	unsigned long flags;
 	char index_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(index_str, sizeof(index_str), data->index_type, index);
 	pr_err("index %s is out of range for type %s\n", index_str,
 		data->array_type->type_name);
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_out_of_bounds);
 
 void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
 					void *lhs, void *rhs)
 {
-	unsigned long flags;
 	struct type_descriptor *rhs_type = data->rhs_type;
 	struct type_descriptor *lhs_type = data->lhs_type;
 	char rhs_str[VALUE_LENGTH];

@@ -420,7 +401,7 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(rhs_str, sizeof(rhs_str), rhs_type, rhs);
 	val_to_string(lhs_str, sizeof(lhs_str), lhs_type, lhs);

@@ -443,18 +424,16 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
 			lhs_str, rhs_str,
 			lhs_type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds);
 
 
 void __ubsan_handle_builtin_unreachable(struct unreachable_data *data)
 {
-	unsigned long flags;
-
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 	pr_err("calling __builtin_unreachable()\n");
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 	panic("can't return from __builtin_unreachable()");
 }
 EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);

@@ -462,19 +441,18 @@ EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);
 void __ubsan_handle_load_invalid_value(struct invalid_value_data *data,
 				void *val)
 {
-	unsigned long flags;
 	char val_str[VALUE_LENGTH];
 
 	if (suppress_report(&data->location))
 		return;
 
-	ubsan_prologue(&data->location, &flags);
+	ubsan_prologue(&data->location);
 
 	val_to_string(val_str, sizeof(val_str), data->type, val);
 
 	pr_err("load of value %s is not a valid value for type %s\n",
 		val_str, data->type->type_name);
 
-	ubsan_epilogue(&flags);
+	ubsan_epilogue();
 }
 EXPORT_SYMBOL(__ubsan_handle_load_invalid_value);

index 05b93cfa6fd9..9be794896d87 100644
@@ -314,7 +314,9 @@ void pin_current_cpu(void)
 	preempt_lazy_enable();
 	preempt_enable();
 
+	sleeping_lock_inc();
 	__read_rt_lock(cpuhp_pin);
+	sleeping_lock_dec();
 
 	preempt_disable();
 	preempt_lazy_disable();

index fde47216af94..fcff75934bdc 100644
@@ -7045,7 +7045,10 @@ void migrate_enable(void)
 			unpin_current_cpu();
 			preempt_lazy_enable();
 			preempt_enable();
+
+			sleeping_lock_inc();
 			stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
+			sleeping_lock_dec();
 			tlb_migrate_finish(p->mm);
 
 			return;

index 6f4a4ae881c8..9f3c8bb62e57 100644
@@ -23,7 +23,7 @@ notrace static unsigned int check_preemption_disabled(const char *what1,
 	 * Kernel threads bound to a single CPU can safely use
 	 * smp_processor_id():
 	 */
-	if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu)))
+	if (current->nr_cpus_allowed == 1)
 		goto out;
 
 	/*

index 3855e0b11877..ec490eaac6f7 100644
@@ -758,9 +758,7 @@ static int exynos5_i2c_probe(struct platform_device *pdev)
 	}
 
 	ret = devm_request_irq(&pdev->dev, i2c->irq, exynos5_i2c_irq,
-				IRQF_NO_SUSPEND | IRQF_ONESHOT,
-				dev_name(&pdev->dev), i2c);
-
+			       IRQF_NO_SUSPEND, dev_name(&pdev->dev), i2c);
 	if (ret != 0) {
 		dev_err(&pdev->dev, "cannot request HS-I2C IRQ %d\n", i2c->irq);
 		goto err_clk;

index 8d6badac9225..4708129e8df1 100644
@@ -1217,13 +1217,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p))
 		goto out;
 
-#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
-	if (__migrate_disabled(p)) {
-		p->migrate_disable_update = 1;
-		goto out;
-	}
-#endif
-
 	if (task_running(rq, p) || p->state == TASK_WAKING) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */

index f66708779274..afa0e42ccdd1 100644
@@ -96,6 +96,8 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 	if (____preempt_count_dec_and_test())
 		return true;
 #ifdef CONFIG_PREEMPT_LAZY
+	if (preempt_count())
+		return false;
 	if (current_thread_info()->preempt_lazy_count)
 		return false;
 	return test_thread_flag(TIF_NEED_RESCHED_LAZY);

index bb68957d3da5..76c1a207ccc1 100644
@@ -464,8 +464,7 @@ static int hix5hd2_i2c_probe(struct platform_device *pdev)
 	hix5hd2_i2c_init(priv);
 
 	ret = devm_request_irq(&pdev->dev, irq, hix5hd2_i2c_irq,
-			       IRQF_NO_SUSPEND | IRQF_ONESHOT,
-			       dev_name(&pdev->dev), priv);
+			       IRQF_NO_SUSPEND, dev_name(&pdev->dev), priv);
 	if (ret != 0) {
 		dev_err(&pdev->dev, "cannot request HS-I2C IRQ %d\n", irq);
 		goto err_clk;

index eb68f7fb8a36..7b04e54bea01 100644
@@ -252,7 +252,7 @@ static void task_non_contending(struct task_struct *p)
 
 	dl_se->dl_non_contending = 1;
 	get_task_struct(p);
-	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL);
+	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
 }
 
 static void task_contending(struct sched_dl_entity *dl_se, int flags)

@@ -1234,7 +1234,7 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->inactive_timer;
 
-	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	timer->function = inactive_task_timer;
 }