Linux 3.14.34-rt32-rc1

index 424319061e09..0f057af22fb1 100644
@@ -59,7 +59,7 @@ struct gpio_bank {
 	u32 saved_datain;
 	u32 level_mask;
 	u32 toggle_mask;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct gpio_chip chip;
 	struct clk *dbck;
 	u32 mod_usage;

@@ -503,14 +503,14 @@ static int gpio_irq_type(struct irq_data *d, unsigned type)
 		(type & (IRQ_TYPE_LEVEL_LOW|IRQ_TYPE_LEVEL_HIGH)))
 		return -EINVAL;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	offset = GPIO_INDEX(bank, gpio);
 	retval = _set_gpio_triggering(bank, offset, type);
 	if (!LINE_USED(bank->mod_usage, offset)) {
 		_enable_gpio_module(bank, offset);
 		_set_gpio_direction(bank, offset, 1);
 	} else if (!gpio_is_input(bank, 1 << offset)) {
-		spin_unlock_irqrestore(&bank->lock, flags);
+		raw_spin_unlock_irqrestore(&bank->lock, flags);
 		return -EINVAL;
 	}
 

@@ -518,12 +518,12 @@ static int gpio_irq_type(struct irq_data *d, unsigned type)
 	if (retval) {
 		dev_err(bank->dev, "unable to lock offset %d for IRQ\n",
 			offset);
-		spin_unlock_irqrestore(&bank->lock, flags);
+		raw_spin_unlock_irqrestore(&bank->lock, flags);
 		return retval;
 	}
 
 	bank->irq_usage |= 1 << GPIO_INDEX(bank, gpio);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 		__irq_set_handler_locked(d->irq, handle_level_irq);

@@ -640,14 +640,14 @@ static int _set_gpio_wakeup(struct gpio_bank *bank, int gpio, int enable)
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	if (enable)
 		bank->context.wake_en |= gpio_bit;
 	else
 		bank->context.wake_en &= ~gpio_bit;
 
 	writel_relaxed(bank->context.wake_en, bank->base + bank->regs->wkup_en);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }

@@ -682,7 +682,7 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 	if (!BANK_USED(bank))
 		pm_runtime_get_sync(bank->dev);
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	/* Set trigger to none. You need to enable the desired trigger with
 	 * request_irq() or set_irq_type(). Only do this if the IRQ line has
 	 * not already been requested.

@@ -692,7 +692,7 @@ static int omap_gpio_request(struct gpio_chip *chip, unsigned offset)
 		_enable_gpio_module(bank, offset);
 	}
 	bank->mod_usage |= 1 << offset;
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }

@@ -702,11 +702,11 @@ static void omap_gpio_free(struct gpio_chip *chip, unsigned offset)
 	struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->mod_usage &= ~(1 << offset);
 	_disable_gpio_module(bank, offset);
 	_reset_gpio(bank, bank->chip.base + offset);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	/*
 	 * If this is the last gpio to be freed in the bank,

@@ -804,12 +804,12 @@ static void gpio_irq_shutdown(struct irq_data *d)
 	unsigned long flags;
 	unsigned offset = GPIO_INDEX(bank, gpio);
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	gpio_unlock_as_irq(&bank->chip, offset);
 	bank->irq_usage &= ~(1 << offset);
 	_disable_gpio_module(bank, offset);
 	_reset_gpio(bank, gpio);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	/*
 	 * If this is the last IRQ to be freed in the bank,

@@ -833,10 +833,10 @@ static void gpio_mask_irq(struct irq_data *d)
 	unsigned int gpio = irq_to_gpio(bank, d->hwirq);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_irqenable(bank, gpio, 0);
 	_set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), IRQ_TYPE_NONE);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_unmask_irq(struct irq_data *d)

@@ -847,7 +847,7 @@ static void gpio_unmask_irq(struct irq_data *d)
 	u32 trigger = irqd_get_trigger_type(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	if (trigger)
 		_set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), trigger);
 

@@ -859,7 +859,7 @@ static void gpio_unmask_irq(struct irq_data *d)
 	}
 
 	_set_gpio_irqenable(bank, gpio, 1);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static struct irq_chip gpio_irq_chip = {

@@ -882,9 +882,9 @@ static int omap_mpuio_suspend_noirq(struct device *dev)
 					OMAP_MPUIO_GPIO_MASKIT / bank->stride;
 	unsigned long		flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	writel_relaxed(0xffff & ~bank->context.wake_en, mask_reg);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }

@@ -897,9 +897,9 @@ static int omap_mpuio_resume_noirq(struct device *dev)
 					OMAP_MPUIO_GPIO_MASKIT / bank->stride;
 	unsigned long		flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	writel_relaxed(bank->context.wake_en, mask_reg);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }

@@ -942,9 +942,9 @@ static int gpio_input(struct gpio_chip *chip, unsigned offset)
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_direction(bank, offset, 1);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 	return 0;
 }
 

@@ -968,10 +968,10 @@ static int gpio_output(struct gpio_chip *chip, unsigned offset, int value)
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->set_dataout(bank, offset, value);
 	_set_gpio_direction(bank, offset, 0);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 	return 0;
 }
 

@@ -983,9 +983,9 @@ static int gpio_debounce(struct gpio_chip *chip, unsigned offset,
 
 	bank = container_of(chip, struct gpio_bank, chip);
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_debounce(bank, offset, debounce);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }

@@ -996,9 +996,9 @@ static void gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->set_dataout(bank, offset, value);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 /*---------------------------------------------------------------------*/

@@ -1210,7 +1210,7 @@ static int omap_gpio_probe(struct platform_device *pdev)
 	else
 		bank->set_dataout = _set_gpio_dataout_mask;
 
-	spin_lock_init(&bank->lock);
+	raw_spin_lock_init(&bank->lock);
 
 	/* Static mapping, never released */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);

@@ -1267,7 +1267,7 @@ static int omap_gpio_runtime_suspend(struct device *dev)
 	unsigned long flags;
 	u32 wake_low, wake_hi;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 
 	/*
 	 * Only edges can generate a wakeup event to the PRCM.

@@ -1320,7 +1320,7 @@ update_gpio_context_count:
 				bank->get_context_loss_count(bank->dev);
 
 	_gpio_dbck_disable(bank);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }

@@ -1335,7 +1335,7 @@ static int omap_gpio_runtime_resume(struct device *dev)
 	unsigned long flags;
 	int c;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 
 	/*
 	 * On the first resume during the probe, the context has not

@@ -1371,14 +1371,14 @@ static int omap_gpio_runtime_resume(struct device *dev)
 			if (c != bank->context_loss_count) {
 				omap_gpio_restore_context(bank);
 			} else {
-				spin_unlock_irqrestore(&bank->lock, flags);
+				raw_spin_unlock_irqrestore(&bank->lock, flags);
 				return 0;
 			}
 		}
 	}
 
 	if (!bank->workaround_enabled) {
-		spin_unlock_irqrestore(&bank->lock, flags);
+		raw_spin_unlock_irqrestore(&bank->lock, flags);
 		return 0;
 	}
 

@@ -1433,7 +1433,7 @@ static int omap_gpio_runtime_resume(struct device *dev)
 	}
 
 	bank->workaround_enabled = false;
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }

index 6c40660d1168..ccb3b8dbe6d4 100644
@@ -1465,23 +1465,32 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 /*
  * Slow path try-lock function:
  */
-static inline int
-rt_mutex_slowtrylock(struct rt_mutex *lock)
+static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
-	int ret = 0;
+	int ret;
 
+	/*
+	 * If the lock already has an owner we fail to get the lock.
+	 * This can be done without taking the @lock->wait_lock as
+	 * it is only being read, and this is a trylock anyway.
+	 */
+	if (rt_mutex_owner(lock))
+		return 0;
+
+	/*
+	 * The mutex has currently no owner. Lock the wait lock and
+	 * try to acquire the lock.
+	 */
 	if (!raw_spin_trylock(&lock->wait_lock))
-		return ret;
+		return 0;
 
-	if (likely(rt_mutex_owner(lock) != current)) {
+	ret = try_to_take_rt_mutex(lock, current, NULL);
 
-		ret = try_to_take_rt_mutex(lock, current, NULL);
-		/*
-		 * try_to_take_rt_mutex() sets the lock waiters
-		 * bit unconditionally. Clean this up.
-		 */
-		fixup_rt_mutex_waiters(lock);
-	}
+	/*
+	 * try_to_take_rt_mutex() sets the lock waiters bit
+	 * unconditionally. Clean this up.
+	 */
+	fixup_rt_mutex_waiters(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
 

index ccb3b8dbe6d4..e4cbd0cd5405 100644
@@ -575,78 +575,120 @@ static inline int lock_is_stealable(struct task_struct *task,
  *
  * Must be called with lock->wait_lock held.
  *
- * @lock:   the lock to be acquired.
- * @task:   the task which wants to acquire the lock
- * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
+ * @lock:   The lock to be acquired.
+ * @task:   The task which wants to acquire the lock
+ * @waiter: The waiter that is queued to the lock's wait list if the
+ *	    callsite called task_blocked_on_lock(), otherwise NULL
  */
 static int
 __try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 		       struct rt_mutex_waiter *waiter, int mode)
 {
+	unsigned long flags;
+
 	/*
-	 * We have to be careful here if the atomic speedups are
-	 * enabled, such that, when
-	 *  - no other waiter is on the lock
-	 *  - the lock has been released since we did the cmpxchg
-	 * the lock can be released or taken while we are doing the
-	 * checks and marking the lock with RT_MUTEX_HAS_WAITERS.
+	 * Before testing whether we can acquire @lock, we set the
+	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
+	 * other tasks which try to modify @lock into the slow path
+	 * and they serialize on @lock->wait_lock.
 	 *
-	 * The atomic acquire/release aware variant of
-	 * mark_rt_mutex_waiters uses a cmpxchg loop. After setting
-	 * the WAITERS bit, the atomic release / acquire can not
-	 * happen anymore and lock->wait_lock protects us from the
-	 * non-atomic case.
+	 * The RT_MUTEX_HAS_WAITERS bit can have a transitional state
+	 * as explained at the top of this file if and only if:
 	 *
-	 * Note, that this might set lock->owner =
-	 * RT_MUTEX_HAS_WAITERS in the case the lock is not contended
-	 * any more. This is fixed up when we take the ownership.
-	 * This is the transitional state explained at the top of this file.
+	 * - There is a lock owner. The caller must fixup the
+	 *   transient state if it does a trylock or leaves the lock
+	 *   function due to a signal or timeout.
+	 *
+	 * - @task acquires the lock and there are no other
+	 *   waiters. This is undone in rt_mutex_set_owner(@task) at
+	 *   the end of this function.
 	 */
 	mark_rt_mutex_waiters(lock);
 
+	/*
+	 * If @lock has an owner, give up.
+	 */
 	if (rt_mutex_owner(lock))
 		return 0;
 
 	/*
-	 * It will get the lock because of one of these conditions:
-	 * 1) there is no waiter
-	 * 2) higher priority than waiters
-	 * 3) it is top waiter
+	 * If @waiter != NULL, @task has already enqueued the waiter
+	 * into @lock waiter list. If @waiter == NULL then this is a
+	 * trylock attempt.
 	 */
-	if (rt_mutex_has_waiters(lock)) {
-		struct task_struct *pown = rt_mutex_top_waiter(lock)->task;
-
-		if (task != pown && !lock_is_stealable(task, pown, mode))
+	if (waiter) {
+		/*
+		 * If waiter is not the highest priority waiter of
+		 * @lock, give up.
+		 */
+		if (waiter != rt_mutex_top_waiter(lock))
 			return 0;
-	}
-
-	/* We got the lock. */
-
-	if (waiter || rt_mutex_has_waiters(lock)) {
-		unsigned long flags;
-		struct rt_mutex_waiter *top;
 
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
-
-		/* remove the queued waiter. */
-		if (waiter) {
-			rt_mutex_dequeue(lock, waiter);
-			task->pi_blocked_on = NULL;
-		}
+		/*
+		 * We can acquire the lock. Remove the waiter from the
+		 * lock waiters list.
+		 */
+		rt_mutex_dequeue(lock, waiter);
 
+	} else {
 		/*
-		 * We have to enqueue the top waiter(if it exists) into
-		 * task->pi_waiters list.
+		 * If the lock has waiters already we check whether @task is
+		 * eligible to take over the lock.
+		 *
+		 * If there are no other waiters, @task can acquire
+		 * the lock.  @task->pi_blocked_on is NULL, so it does
+		 * not need to be dequeued.
 		 */
 		if (rt_mutex_has_waiters(lock)) {
-			top = rt_mutex_top_waiter(lock);
-			rt_mutex_enqueue_pi(task, top);
+			/*
+			 * If @task->prio is greater than or equal to
+			 * the top waiter priority (kernel view),
+			 * @task lost.
+			 */
+			if (task->prio >= rt_mutex_top_waiter(lock)->prio)
+				return 0;
+
+			/*
+			 * The current top waiter stays enqueued. We
+			 * don't have to change anything in the lock
+			 * waiters order.
+			 */
+		} else {
+			/*
+			 * No waiters. Take the lock without the
+			 * pi_lock dance.@task->pi_blocked_on is NULL
+			 * and we have no waiters to enqueue in @task
+			 * pi waiters list.
+			 */
+			goto takeit;
 		}
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
 
+	/*
+	 * Clear @task->pi_blocked_on. Requires protection by
+	 * @task->pi_lock. Redundant operation for the @waiter == NULL
+	 * case, but conditionals are more expensive than a redundant
+	 * store.
+	 */
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	task->pi_blocked_on = NULL;
+	/*
+	 * Finish the lock acquisition. @task is the new owner. If
+	 * other waiters exist we have to insert the highest priority
+	 * waiter into @task->pi_waiters list.
+	 */
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+takeit:
+	/* We got the lock. */
 	debug_rt_mutex_lock(lock);
 
+	/*
+	 * This either preserves the RT_MUTEX_HAS_WAITERS bit if there
+	 * are still waiters or clears it.
+	 */
 	rt_mutex_set_owner(lock, task);
 
 	rt_mutex_deadlock_account_lock(lock, task);

index e4cbd0cd5405..901a29345451 100644
@@ -484,6 +484,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	/* Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	put_task_struct(task);
+
 	if (!rt_mutex_owner(lock)) {
 		struct rt_mutex_waiter *lock_top_waiter;
 

@@ -495,9 +497,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		if (top_waiter != lock_top_waiter)
 			rt_mutex_wake_waiter(lock_top_waiter);
 		raw_spin_unlock(&lock->wait_lock);
-		goto out_put_task;
+		return 0;
 	}
-	put_task_struct(task);
 
 	/* Grab the next task */
 	task = rt_mutex_owner(lock);

index 901a29345451..85f5369e27f3 100644
@@ -366,9 +366,10 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
-	struct rt_mutex *lock;
 	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
+	struct rt_mutex_waiter *prerequeue_top_waiter;
 	int detect_deadlock, ret = 0, depth = 0;
+	struct rt_mutex *lock;
 	unsigned long flags;
 
 	detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,

@@ -475,9 +476,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		goto out_unlock_pi;
 	}
 
-	top_waiter = rt_mutex_top_waiter(lock);
+	/*
+	 * Store the current top waiter before doing the requeue
+	 * operation on @lock. We need it for the boost/deboost
+	 * decision below.
+	 */
+	prerequeue_top_waiter = rt_mutex_top_waiter(lock);
 
-	/* Requeue the waiter */
+	/* Requeue the waiter in the lock waiter list. */
 	rt_mutex_dequeue(lock, waiter);
 	waiter->prio = task->prio;
 	rt_mutex_enqueue(lock, waiter);

@@ -486,6 +492,11 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	put_task_struct(task);
 
+	/*
+	 * We must abort the chain walk if there is no lock owner even
+	 * in the dead lock detection case, as we have nothing to
+	 * follow here. This is the end of the chain we are walking.
+	 */
 	if (!rt_mutex_owner(lock)) {
 		struct rt_mutex_waiter *lock_top_waiter;
 

@@ -494,29 +505,48 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		 * to wake the new top waiter up to try to get the lock.
 		 */
 		lock_top_waiter = rt_mutex_top_waiter(lock);
-		if (top_waiter != lock_top_waiter)
+		if (prerequeue_top_waiter != lock_top_waiter)
 			rt_mutex_wake_waiter(lock_top_waiter);
 		raw_spin_unlock(&lock->wait_lock);
 		return 0;
 	}
 
-	/* Grab the next task */
+	/* Grab the next task, i.e. the owner of @lock */
 	task = rt_mutex_owner(lock);
 	get_task_struct(task);
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		/* Boost the owner */
-		rt_mutex_dequeue_pi(task, top_waiter);
+		/*
+		 * The waiter became the new top (highest priority)
+		 * waiter on the lock. Replace the previous top waiter
+		 * in the owner tasks pi waiters list with this waiter
+		 * and adjust the priority of the owner.
+		 */
+		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
 		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 
-	} else if (top_waiter == waiter) {
-		/* Deboost the owner */
+	} else if (prerequeue_top_waiter == waiter) {
+		/*
+		 * The waiter was the top waiter on the lock, but is
+		 * no longer the top prority waiter. Replace waiter in
+		 * the owner tasks pi waiters list with the new top
+		 * (highest priority) waiter and adjust the priority
+		 * of the owner.
+		 * The new top waiter is stored in @waiter so that
+		 * @waiter == @top_waiter evaluates to true below and
+		 * we continue to deboost the rest of the chain.
+		 */
 		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
 		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
+	} else {
+		/*
+		 * Nothing changed. No need to do any priority
+		 * adjustment.
+		 */
 	}
 
 	/*

@@ -529,6 +559,10 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
+	/*
+	 * Store the top waiter of @lock for the end of chain walk
+	 * decision below.
+	 */
 	top_waiter = rt_mutex_top_waiter(lock);
 	raw_spin_unlock(&lock->wait_lock);
 

@@ -539,6 +573,11 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	if (!next_lock)
 		goto out_put_task;
 
+	/*
+	 * If the current waiter is not the top waiter on the lock,
+	 * then we can stop the chain walk here if we are not in full
+	 * deadlock detection mode.
+	 */
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 

index 85f5369e27f3..400026ec7f05 100644
@@ -358,6 +358,48 @@ static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
  * @top_task:	the current top waiter
  *
  * Returns 0 or -EDEADLK.
+ *
+ * Chain walk basics and protection scope
+ *
+ * [R] refcount on task
+ * [P] task->pi_lock held
+ * [L] rtmutex->wait_lock held
+ *
+ * Step	Description				Protected by
+ *	function arguments:
+ *	@task					[R]
+ *	@orig_lock if != NULL			@top_task is blocked on it
+ *	@next_lock				Unprotected. Cannot be
+ *						dereferenced. Only used for
+ *						comparison.
+ *	@orig_waiter if != NULL			@top_task is blocked on it
+ *	@top_task				current, or in case of proxy
+ *						locking protected by calling
+ *						code
+ *	again:
+ *	  loop_sanity_check();
+ *	retry:
+ * [1]	  lock(task->pi_lock);			[R] acquire [P]
+ * [2]	  waiter = task->pi_blocked_on;		[P]
+ * [3]	  check_exit_conditions_1();		[P]
+ * [4]	  lock = waiter->lock;			[P]
+ * [5]	  if (!try_lock(lock->wait_lock)) {	[P] try to acquire [L]
+ *	    unlock(task->pi_lock);		release [P]
+ *	    goto retry;
+ *	  }
+ * [6]	  check_exit_conditions_2();		[P] + [L]
+ * [7]	  requeue_lock_waiter(lock, waiter);	[P] + [L]
+ * [8]	  unlock(task->pi_lock);		release [P]
+ *	  put_task_struct(task);		release [R]
+ * [9]	  check_exit_conditions_3();		[L]
+ * [10]	  task = owner(lock);			[L]
+ *	  get_task_struct(task);		[L] acquire [R]
+ *	  lock(task->pi_lock);			[L] acquire [P]
+ * [11]	  requeue_pi_waiter(tsk, waiters(lock));[P] + [L]
+ * [12]	  check_exit_conditions_4();		[P] + [L]
+ * [13]	  unlock(task->pi_lock);		release [P]
+ *	  unlock(lock->wait_lock);		release [L]
+ *	  goto again;
  */
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 				      int deadlock_detect,

@@ -382,6 +424,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * carefully whether things change under us.
 	 */
  again:
+	/*
+	 * We limit the lock chain length for each invocation.
+	 */
 	if (++depth > max_lock_depth) {
 		static int prev_max;
 

@@ -399,13 +444,28 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 		return -EDEADLK;
 	}
+
+	/*
+	 * We are fully preemptible here and only hold the refcount on
+	 * @task. So everything can have changed under us since the
+	 * caller or our own code below (goto retry/again) dropped all
+	 * locks.
+	 */
  retry:
 	/*
-	 * Task can not go away as we did a get_task() before !
+	 * [1] Task cannot go away as we did a get_task() before !
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
+	/*
+	 * [2] Get the waiter on which @task is blocked on.
+	 */
 	waiter = task->pi_blocked_on;
+
+	/*
+	 * [3] check_exit_conditions_1() protected by task->pi_lock.
+	 */
+
 	/*
 	 * Check whether the end of the boosting chain has been
 	 * reached or the state of the chain has changed while we

@@ -456,7 +516,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	if (!detect_deadlock && waiter->prio == task->prio)
 		goto out_unlock_pi;
 
+	/*
+	 * [4] Get the next lock
+	 */
 	lock = waiter->lock;
+	/*
+	 * [5] We need to trylock here as we are holding task->pi_lock,
+	 * which is the reverse lock order versus the other rtmutex
+	 * operations.
+	 */
 	if (!raw_spin_trylock(&lock->wait_lock)) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		cpu_relax();

@@ -464,6 +532,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	}
 
 	/*
+	 * [6] check_exit_conditions_2() protected by task->pi_lock and
+	 * lock->wait_lock.
+	 *
 	 * Deadlock detection. If the lock is the same as the original
 	 * lock which caused us to walk the lock chain or if the
 	 * current lock is owned by the task which initiated the chain

@@ -483,16 +554,18 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 */
 	prerequeue_top_waiter = rt_mutex_top_waiter(lock);
 
-	/* Requeue the waiter in the lock waiter list. */
+	/* [7] Requeue the waiter in the lock waiter list. */
 	rt_mutex_dequeue(lock, waiter);
 	waiter->prio = task->prio;
 	rt_mutex_enqueue(lock, waiter);
 
-	/* Release the task */
+	/* [8] Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	put_task_struct(task);
 
 	/*
+	 * [9] check_exit_conditions_3 protected by lock->wait_lock.
+	 *
 	 * We must abort the chain walk if there is no lock owner even
 	 * in the dead lock detection case, as we have nothing to
 	 * follow here. This is the end of the chain we are walking.

@@ -501,8 +574,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		struct rt_mutex_waiter *lock_top_waiter;
 
 		/*
-		 * If the requeue above changed the top waiter, then we need
-		 * to wake the new top waiter up to try to get the lock.
+		 * If the requeue [7] above changed the top waiter,
+		 * then we need to wake the new top waiter up to try
+		 * to get the lock.
 		 */
 		lock_top_waiter = rt_mutex_top_waiter(lock);
 		if (prerequeue_top_waiter != lock_top_waiter)

@@ -511,11 +585,12 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 		return 0;
 	}
 
-	/* Grab the next task, i.e. the owner of @lock */
+	/* [10] Grab the next task, i.e. the owner of @lock */
 	task = rt_mutex_owner(lock);
 	get_task_struct(task);
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
+	/* [11] requeue the pi waiters if necessary */
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		/*
 		 * The waiter became the new top (highest priority)

@@ -550,23 +625,30 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	}
 
 	/*
+	 * [12] check_exit_conditions_4() protected by task->pi_lock
+	 * and lock->wait_lock. The actual decisions are made after we
+	 * dropped the locks.
+	 *
 	 * Check whether the task which owns the current lock is pi
 	 * blocked itself. If yes we store a pointer to the lock for
 	 * the lock chain change detection above. After we dropped
 	 * task->pi_lock next_lock cannot be dereferenced anymore.
 	 */
 	next_lock = task_blocked_on_lock(task);
-
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
 	/*
 	 * Store the top waiter of @lock for the end of chain walk
 	 * decision below.
 	 */
 	top_waiter = rt_mutex_top_waiter(lock);
+
+	/* [13] Drop the locks */
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	raw_spin_unlock(&lock->wait_lock);
 
 	/*
+	 * Make the actual exit decisions [12], based on the stored
+	 * values.
+	 *
 	 * We reached the end of the lock chain. Stop right here. No
 	 * point to go back just to figure that out.
 	 */

index 400026ec7f05..6c74a0525dcb 100644
@@ -985,7 +985,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 static void remove_waiter(struct rt_mutex *lock,
 			  struct rt_mutex_waiter *waiter)
 {
-	int first = (waiter == rt_mutex_top_waiter(lock));
+	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex *next_lock = NULL;
 	unsigned long flags;

@@ -995,30 +995,32 @@ static void remove_waiter(struct rt_mutex *lock,
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-	if (!owner)
+	/*
+	 * Only update priority if the waiter was the highest priority
+	 * waiter of the lock and there is an owner to update.
+	 */
+	if (!owner || !is_top_waiter)
 		return;
 
-	if (first) {
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
+	rt_mutex_dequeue_pi(owner, waiter);
 
-		rt_mutex_dequeue_pi(owner, waiter);
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
 
-		if (rt_mutex_has_waiters(lock)) {
-			struct rt_mutex_waiter *next;
+	__rt_mutex_adjust_prio(owner);
 
-			next = rt_mutex_top_waiter(lock);
-			rt_mutex_enqueue_pi(owner, next);
-		}
-		__rt_mutex_adjust_prio(owner);

index edb77fd15803..d5a04ea47a13 100644
@@ -105,12 +105,10 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name);
 extern void rt_mutex_destroy(struct rt_mutex *lock);
 
 extern void rt_mutex_lock(struct rt_mutex *lock);
-extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
-						int detect_deadlock);
-extern int rt_mutex_lock_killable(struct rt_mutex *lock, int detect_deadlock);
+extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
+extern int rt_mutex_lock_killable(struct rt_mutex *lock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
-					struct hrtimer_sleeper *timeout,
-					int detect_deadlock);
+			       struct hrtimer_sleeper *timeout);
 
 extern int rt_mutex_trylock(struct rt_mutex *lock);
 

index 5ba3c0fc4d19..d2349337d1a0 100644
@@ -1708,7 +1708,7 @@ retry_private:
 			this->pi_state = pi_state;
 			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
 							this->rt_waiter,
-							this->task, 1);
+							this->task);
 			if (ret == 1) {
 				/* We got the lock. */
 				requeue_pi_wake_futex(this, &key2, hb2);

@@ -2337,9 +2337,9 @@ retry_private:
 	/*
 	 * Block on the PI mutex:
 	 */
-	if (!trylock)
-		ret = rt_mutex_timed_lock(&q.pi_state->pi_mutex, to, 1);
-	else {
+	if (!trylock) {
+		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
+	} else {
 		ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;

@@ -2703,7 +2703,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 */
 		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
-		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
 		debug_rt_mutex_free_waiter(&rt_waiter);
 
 		spin_lock(&hb2->lock);

index 90b8ba03e2a4..eac2ddea9c45 100644
@@ -98,7 +98,7 @@ int __lockfunc _mutex_lock_interruptible(struct mutex *lock)
 	int ret;
 
 	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	ret = rt_mutex_lock_interruptible(&lock->lock, 0);
+	ret = rt_mutex_lock_interruptible(&lock->lock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
 	return ret;

@@ -110,7 +110,7 @@ int __lockfunc _mutex_lock_killable(struct mutex *lock)
 	int ret;
 
 	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	ret = rt_mutex_lock_killable(&lock->lock, 0);
+	ret = rt_mutex_lock_killable(&lock->lock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
 	return ret;

@@ -137,7 +137,7 @@ int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass
 	int ret;
 
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
-	ret = rt_mutex_lock_interruptible(&lock->lock, 0);
+	ret = rt_mutex_lock_interruptible(&lock->lock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
 	return ret;

@@ -149,7 +149,7 @@ int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass)
 	int ret;
 
 	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-	ret = rt_mutex_lock_killable(&lock->lock, 0);
+	ret = rt_mutex_lock_killable(&lock->lock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
 	return ret;

index 1d96dd0d93c1..a6b605b51b97 100644
@@ -16,7 +16,7 @@
 #include <linux/freezer.h>
 #include <linux/stat.h>
 
-#include "rtmutex.h"
+#include "rtmutex_common.h"
 
 #define MAX_RT_TEST_THREADS	8
 #define MAX_RT_TEST_MUTEXES	8

@@ -107,7 +107,7 @@ static int handle_op(struct test_thread_data *td, int lockwakeup)
 
 		td->mutexes[id] = 1;
 		td->event = atomic_add_return(1, &rttest_event);
-		ret = rt_mutex_lock_interruptible(&mutexes[id], 0);
+		ret = rt_mutex_lock_interruptible(&mutexes[id]);
 		td->event = atomic_add_return(1, &rttest_event);
 		td->mutexes[id] = ret ? 0 : 4;
 		return ret ? -EINTR : 0;

150 lines not on this page · raw message

index ac636d37ec32..ec51460fa233 100644
@@ -115,12 +115,11 @@ extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
-				     struct task_struct *task,
-				     int detect_deadlock);
+				     struct task_struct *task);
 extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 				      struct hrtimer_sleeper *to,
-				      struct rt_mutex_waiter *waiter,
-				      int detect_deadlock);
+				      struct rt_mutex_waiter *waiter);
+extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"

index 49b2ed3dced8..62b6cee8ea7f 100644
@@ -66,12 +66,13 @@ void rt_mutex_debug_task_free(struct task_struct *task)
  * the deadlock. We print when we return. act_waiter can be NULL in
  * case of a remove waiter operation.
  */
-void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter,
+void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+			     struct rt_mutex_waiter *act_waiter,
 			     struct rt_mutex *lock)
 {
 	struct task_struct *task;
 
-	if (!debug_locks || detect || !act_waiter)
+	if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter)
 		return;
 
 	task = rt_mutex_owner(act_waiter->lock);

index ab29b6a22669..d0519c3432b6 100644
@@ -20,14 +20,15 @@ extern void debug_rt_mutex_unlock(struct rt_mutex *lock);
 extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock,
 				      struct task_struct *powner);
 extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock);
-extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter,
+extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+				    struct rt_mutex_waiter *waiter,
 				    struct rt_mutex *lock);
 extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter);
 # define debug_rt_mutex_reset_waiter(w)			\
 	do { (w)->deadlock_lock = NULL; } while (0)
 
-static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
-						 int detect)
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
+						  enum rtmutex_chainwalk walk)
 {
 	return (waiter != NULL);
 }

197 lines not on this page · raw message

index f6a1f3c133b1..c4060584c407 100644
@@ -22,10 +22,15 @@
 #define debug_rt_mutex_init(m, n)			do { } while (0)
 #define debug_rt_mutex_deadlock(d, a ,l)		do { } while (0)
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
-#define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
 
 static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
 {
 	WARN(1, "rtmutex deadlock detected\n");
 }
+
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w,
+						  enum rtmutex_chainwalk walk)
+{
+	return walk == RT_MUTEX_FULL_CHAINWALK;
+}

index ec51460fa233..c6dcda5e53af 100644
@@ -103,6 +103,21 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 }
 
 /*
+ * Constants for rt mutex functions which have a selectable deadlock
+ * detection.
+ *
+ * RT_MUTEX_MIN_CHAINWALK:	Stops the lock chain walk when there are
+ *				no further PI adjustments to be made.
+ *
+ * RT_MUTEX_FULL_CHAINWALK:	Invoke deadlock detection with a full
+ *				walk of the lock chain.
+ */
+enum rtmutex_chainwalk {
+	RT_MUTEX_MIN_CHAINWALK,
+	RT_MUTEX_FULL_CHAINWALK,
+};
+
+/*
  * PI-futex support (proxy locking functions, etc.):
  */
 #define PI_WAKEUP_INPROGRESS	((struct rt_mutex_waiter *) 1)

index 07fb4d717039..a0d9eadcfe02 100644
@@ -440,6 +440,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	struct rt_mutex *lock;
 	bool detect_deadlock;
 	unsigned long flags;
+	bool requeue = true;
 
 	detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
 

@@ -529,18 +530,31 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 			goto out_unlock_pi;
 		/*
 		 * If deadlock detection is off, we stop here if we
-		 * are not the top pi waiter of the task.
+		 * are not the top pi waiter of the task. If deadlock
+		 * detection is enabled we continue, but stop the
+		 * requeueing in the chain walk.
 		 */
-		if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
-			goto out_unlock_pi;
+		if (top_waiter != task_top_pi_waiter(task)) {
+			if (!detect_deadlock)
+				goto out_unlock_pi;
+			else
+				requeue = false;
+		}
 	}
 
 	/*
-	 * When deadlock detection is off then we check, if further
-	 * priority adjustment is necessary.
+	 * If the waiter priority is the same as the task priority
+	 * then there is no further priority adjustment necessary.  If
+	 * deadlock detection is off, we stop the chain walk. If its
+	 * enabled we continue, but stop the requeueing in the chain
+	 * walk.
 	 */
-	if (!detect_deadlock && waiter->prio == task->prio)
-		goto out_unlock_pi;
+	if (waiter->prio == task->prio) {
+		if (!detect_deadlock)
+			goto out_unlock_pi;
+		else
+			requeue = false;
+	}
 
 	/*
 	 * [4] Get the next lock

@@ -574,6 +588,55 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	}
 
 	/*
+	 * If we just follow the lock chain for deadlock detection, no
+	 * need to do all the requeue operations. To avoid a truckload
+	 * of conditionals around the various places below, just do the
+	 * minimum chain walk checks.
+	 */
+	if (!requeue) {
+		/*
+		 * No requeue[7] here. Just release @task [8]
+		 */
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		put_task_struct(task);
+
+		/*
+		 * [9] check_exit_conditions_3 protected by lock->wait_lock.
+		 * If there is no owner of the lock, end of chain.
+		 */
+		if (!rt_mutex_owner(lock)) {
+			raw_spin_unlock(&lock->wait_lock);
+			return 0;
+		}
+
+		/* [10] Grab the next task, i.e. owner of @lock */
+		task = rt_mutex_owner(lock);
+		get_task_struct(task);
+		raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+		/*
+		 * No requeue [11] here. We just do deadlock detection.
+		 *
+		 * [12] Store whether owner is blocked
+		 * itself. Decision is made after dropping the locks
+		 */
+		next_lock = task_blocked_on_lock(task);
+		/*
+		 * Get the top waiter for the next iteration
+		 */
+		top_waiter = rt_mutex_top_waiter(lock);
+
+		/* [13] Drop locks */
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		raw_spin_unlock(&lock->wait_lock);
+
+		/* If owner is not blocked, end of chain. */
+		if (!next_lock)
+			goto out_put_task;
+		goto again;
+	}
+
+	/*
 	 * Store the current top waiter before doing the requeue
 	 * operation on @lock. We need it for the boost/deboost
 	 * decision below.

index d2349337d1a0..a3ce98c65127 100644
@@ -1176,22 +1176,6 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	return 0;
 }
 
-static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
-{
-	u32 uninitialized_var(oldval);
-
-	/*
-	 * There is no waiter, so we unlock the futex. The owner died
-	 * bit has not to be preserved here. We are the owner:
-	 */
-	if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
-		return -EFAULT;
-	if (oldval != uval)
-		return -EAGAIN;
-
-	return 0;
-}
-
 /*
  * Express the locking dependencies for lockdep:
  */

@@ -2401,10 +2385,10 @@ uaddr_faulted:
  */
 static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
-	struct futex_hash_bucket *hb;
-	struct futex_q *this, *next;
+	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
-	u32 uval, vpid = task_pid_vnr(current);
+	struct futex_hash_bucket *hb;
+	struct futex_q *match;
 	int ret;
 
 retry:

@@ -2417,57 +2401,47 @@ retry:
 		return -EPERM;
 
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE);
-	if (unlikely(ret != 0))
-		goto out;
+	if (ret)
+		return ret;
 
 	hb = hash_futex(&key);
 	spin_lock(&hb->lock);
 
 	/*
-	 * To avoid races, try to do the TID -> 0 atomic transition
-	 * again. If it succeeds then we can return without waking
-	 * anyone else up. We only try this if neither the waiters nor
-	 * the owner died bit are set.
+	 * Check waiters first. We do not trust user space values at
+	 * all and we at least want to know if user space fiddled
+	 * with the futex value instead of blindly unlocking.
 	 */
-	if (!(uval & ~FUTEX_TID_MASK) &&
-	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
-		goto pi_faulted;
-	/*
-	 * Rare case: we managed to release the lock atomically,
-	 * no need to wake anyone else up:
-	 */
-	if (unlikely(uval == vpid))
-		goto out_unlock;
-
-	/*
-	 * Ok, other tasks may need to be woken up - check waiters
-	 * and do the wakeup if necessary:
-	 */
-	plist_for_each_entry_safe(this, next, &hb->chain, list) {
-		if (!match_futex (&this->key, &key))
-			continue;
-		ret = wake_futex_pi(uaddr, uval, this);
+	match = futex_top_waiter(hb, &key);
+	if (match) {
+		ret = wake_futex_pi(uaddr, uval, match);
 		/*
-		 * The atomic access to the futex value
-		 * generated a pagefault, so retry the
-		 * user-access and the wakeup:
+		 * The atomic access to the futex value generated a
+		 * pagefault, so retry the user-access and the wakeup:
 		 */
 		if (ret == -EFAULT)
 			goto pi_faulted;
 		goto out_unlock;
 	}
+
 	/*
-	 * No waiters - kernel unlocks the futex:
+	 * We have no kernel internal state, i.e. no waiters in the
+	 * kernel. Waiters which are about to queue themselves are stuck
+	 * on hb->lock. So we can safely ignore them. We do neither
+	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
+	 * owner.
 	 */
-	ret = unlock_futex_pi(uaddr, uval);
-	if (ret == -EFAULT)
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
 		goto pi_faulted;
 
+	/*
+	 * If uval has changed, let user space handle it.
+	 */
+	ret = (curval == uval) ? 0 : -EAGAIN;
+
 out_unlock:
 	spin_unlock(&hb->lock);
 	put_futex_key(&key);
-
-out:
 	return ret;
 
 pi_faulted:

index a3ce98c65127..8bb158215e2c 100644
@@ -786,87 +786,85 @@ static int
 lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 		union futex_key *key, struct futex_pi_state **ps)
 {
+	struct futex_q *match = futex_top_waiter(hb, key);
 	struct futex_pi_state *pi_state = NULL;
-	struct futex_q *this, *next;
 	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	plist_for_each_entry_safe(this, next, &hb->chain, list) {
-		if (match_futex(&this->key, key)) {
-			/*
-			 * Sanity check the waiter before increasing
-			 * the refcount and attaching to it.
-			 */
-			pi_state = this->pi_state;
-			/*
-			 * Userspace might have messed up non-PI and
-			 * PI futexes [3]
-			 */
-			if (unlikely(!pi_state))
-				return -EINVAL;
+	if (match) {
+		/*
+		 * Sanity check the waiter before increasing the
+		 * refcount and attaching to it.
+		 */
+		pi_state = match->pi_state;
+		/*
+		 * Userspace might have messed up non-PI and PI
+		 * futexes [3]
+		 */
+		if (unlikely(!pi_state))
+			return -EINVAL;
 
-			WARN_ON(!atomic_read(&pi_state->refcount));
+		WARN_ON(!atomic_read(&pi_state->refcount));
 
+		/*
+		 * Handle the owner died case:
+		 */
+		if (uval & FUTEX_OWNER_DIED) {
 			/*
-			 * Handle the owner died case:
+			 * exit_pi_state_list sets owner to NULL and
+			 * wakes the topmost waiter. The task which
+			 * acquires the pi_state->rt_mutex will fixup
+			 * owner.
 			 */
-			if (uval & FUTEX_OWNER_DIED) {
+			if (!pi_state->owner) {
 				/*
-				 * exit_pi_state_list sets owner to NULL and
-				 * wakes the topmost waiter. The task which
-				 * acquires the pi_state->rt_mutex will fixup
-				 * owner.
+				 * No pi state owner, but the user
+				 * space TID is not 0. Inconsistent
+				 * state. [5]
 				 */
-				if (!pi_state->owner) {
-					/*
-					 * No pi state owner, but the user
-					 * space TID is not 0. Inconsistent
-					 * state. [5]
-					 */
-					if (pid)
-						return -EINVAL;
-					/*
-					 * Take a ref on the state and
-					 * return. [4]
-					 */
-					goto out_state;
-				}
-
-				/*
-				 * If TID is 0, then either the dying owner
-				 * has not yet executed exit_pi_state_list()
-				 * or some waiter acquired the rtmutex in the
-				 * pi state, but did not yet fixup the TID in
-				 * user space.
-				 *
-				 * Take a ref on the state and return. [6]
-				 */
-				if (!pid)
-					goto out_state;
-			} else {
+				if (pid)
+					return -EINVAL;
 				/*
-				 * If the owner died bit is not set,
-				 * then the pi_state must have an
-				 * owner. [7]
+				 * Take a ref on the state and
+				 * return. [4]
 				 */
-				if (!pi_state->owner)
-					return -EINVAL;
+				goto out_state;
 			}
 
 			/*
-			 * Bail out if user space manipulated the
-			 * futex value. If pi state exists then the
-			 * owner TID must be the same as the user
-			 * space TID. [9/10]
+			 * If TID is 0, then either the dying owner
+			 * has not yet executed exit_pi_state_list()
+			 * or some waiter acquired the rtmutex in the
+			 * pi state, but did not yet fixup the TID in
+			 * user space.
+			 *
+			 * Take a ref on the state and return. [6]
+			 */
+			if (!pid)
+				goto out_state;
+		} else {
+			/*
+			 * If the owner died bit is not set,
+			 * then the pi_state must have an
+			 * owner. [7]
 			 */
-			if (pid != task_pid_vnr(pi_state->owner))
+			if (!pi_state->owner)
 				return -EINVAL;
-
-		out_state:
-			atomic_inc(&pi_state->refcount);
-			*ps = pi_state;
-			return 0;
 		}
+
+		/*
+		 * Bail out if user space manipulated the
+		 * futex value. If pi state exists then the
+		 * owner TID must be the same as the user
+		 * space TID. [9/10]
+		 */
+		if (pid != task_pid_vnr(pi_state->owner))
+			return -EINVAL;
+
+	out_state:
+		atomic_inc(&pi_state->refcount);
+		*ps = pi_state;
+		return 0;
 	}
 
 	/*

index 8bb158215e2c..8377eec3f650 100644
@@ -782,92 +782,96 @@ void exit_pi_state_list(struct task_struct *curr)
  * [10] There is no transient state which leaves owner and user space
  *	TID out of sync.
  */
-static int
-lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
-		union futex_key *key, struct futex_pi_state **ps)
+
+/*
+ * Validate that the existing waiter has a pi_state and sanity check
+ * the pi_state against the user space value. If correct, attach to
+ * it.
+ */
+static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+			      struct futex_pi_state **ps)
 {
-	struct futex_q *match = futex_top_waiter(hb, key);
-	struct futex_pi_state *pi_state = NULL;
-	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	if (match) {
-		/*
-		 * Sanity check the waiter before increasing the
-		 * refcount and attaching to it.
-		 */
-		pi_state = match->pi_state;
-		/*
-		 * Userspace might have messed up non-PI and PI
-		 * futexes [3]
-		 */
-		if (unlikely(!pi_state))
-			return -EINVAL;
+	/*
+	 * Userspace might have messed up non-PI and PI futexes [3]
+	 */
+	if (unlikely(!pi_state))
+		return -EINVAL;
 
-		WARN_ON(!atomic_read(&pi_state->refcount));
+	WARN_ON(!atomic_read(&pi_state->refcount));
 
+	/*
+	 * Handle the owner died case:
+	 */
+	if (uval & FUTEX_OWNER_DIED) {
 		/*
-		 * Handle the owner died case:
+		 * exit_pi_state_list sets owner to NULL and wakes the
+		 * topmost waiter. The task which acquires the
+		 * pi_state->rt_mutex will fixup owner.
 		 */
-		if (uval & FUTEX_OWNER_DIED) {
-			/*
-			 * exit_pi_state_list sets owner to NULL and
-			 * wakes the topmost waiter. The task which
-			 * acquires the pi_state->rt_mutex will fixup
-			 * owner.
-			 */
-			if (!pi_state->owner) {
-				/*
-				 * No pi state owner, but the user
-				 * space TID is not 0. Inconsistent
-				 * state. [5]
-				 */
-				if (pid)
-					return -EINVAL;
-				/*
-				 * Take a ref on the state and
-				 * return. [4]
-				 */
-				goto out_state;
-			}
-
+		if (!pi_state->owner) {
 			/*
-			 * If TID is 0, then either the dying owner
-			 * has not yet executed exit_pi_state_list()
-			 * or some waiter acquired the rtmutex in the
-			 * pi state, but did not yet fixup the TID in
-			 * user space.
-			 *
-			 * Take a ref on the state and return. [6]
+			 * No pi state owner, but the user space TID
+			 * is not 0. Inconsistent state. [5]
 			 */
-			if (!pid)
-				goto out_state;
-		} else {
+			if (pid)
+				return -EINVAL;
 			/*
-			 * If the owner died bit is not set,
-			 * then the pi_state must have an
-			 * owner. [7]
+			 * Take a ref on the state and return success. [4]
 			 */
-			if (!pi_state->owner)
-				return -EINVAL;
+			goto out_state;
 		}
 
 		/*
-		 * Bail out if user space manipulated the
-		 * futex value. If pi state exists then the
-		 * owner TID must be the same as the user
-		 * space TID. [9/10]
+		 * If TID is 0, then either the dying owner has not
+		 * yet executed exit_pi_state_list() or some waiter
+		 * acquired the rtmutex in the pi state, but did not
+		 * yet fixup the TID in user space.
+		 *
+		 * Take a ref on the state and return success. [6]
+		 */
+		if (!pid)
+			goto out_state;
+	} else {
+		/*
+		 * If the owner died bit is not set, then the pi_state
+		 * must have an owner. [7]
 		 */
-		if (pid != task_pid_vnr(pi_state->owner))
+		if (!pi_state->owner)
 			return -EINVAL;
-
-	out_state:
-		atomic_inc(&pi_state->refcount);
-		*ps = pi_state;
-		return 0;
 	}
 
 	/*
+	 * Bail out if user space manipulated the futex value. If pi
+	 * state exists then the owner TID must be the same as the
+	 * user space TID. [9/10]
+	 */
+	if (pid != task_pid_vnr(pi_state->owner))
+		return -EINVAL;
+out_state:
+	atomic_inc(&pi_state->refcount);
+	*ps = pi_state;
+	return 0;
+}
+
+static int
+lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+		union futex_key *key, struct futex_pi_state **ps)
+{
+	struct futex_q *match = futex_top_waiter(hb, key);
+	struct futex_pi_state *pi_state = NULL;
+	struct task_struct *p;
+	pid_t pid = uval & FUTEX_TID_MASK;
+
+	/*
+	 * If there is a waiter on that futex, validate it and
+	 * attach to the pi_state when the validation succeeds.
+	 */
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
+
+	/*
 	 * We are the first waiter - try to look up the real owner and attach
 	 * the new pi_state to it, but bail out when TID = 0 [1]
 	 */

index 8377eec3f650..e0802beff9ad 100644
@@ -855,21 +855,16 @@ out_state:
 	return 0;
 }
 
-static int
-lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
-		union futex_key *key, struct futex_pi_state **ps)
+/*
+ * Lookup the task for the TID provided from user space and attach to
+ * it after doing proper sanity checks.
+ */
+static int attach_to_pi_owner(u32 uval, union futex_key *key,
+			      struct futex_pi_state **ps)
 {
-	struct futex_q *match = futex_top_waiter(hb, key);
-	struct futex_pi_state *pi_state = NULL;
-	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
-
-	/*
-	 * If there is a waiter on that futex, validate it and
-	 * attach to the pi_state when the validation succeeds.
-	 */
-	if (match)
-		return attach_to_pi_state(uval, match->pi_state, ps);
+	struct futex_pi_state *pi_state;
+	struct task_struct *p;
 
 	/*
 	 * We are the first waiter - try to look up the real owner and attach

@@ -912,7 +907,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	pi_state = alloc_pi_state();
 
 	/*
-	 * Initialize the pi_mutex in locked state and make 'p'
+	 * Initialize the pi_mutex in locked state and make @p
 	 * the owner of it:
 	 */
 	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);

@@ -932,6 +927,25 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	return 0;
 }
 
+static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+			   union futex_key *key, struct futex_pi_state **ps)
+{
+	struct futex_q *match = futex_top_waiter(hb, key);
+
+	/*
+	 * If there is a waiter on that futex, validate it and
+	 * attach to the pi_state when the validation succeeds.
+	 */
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
+
+	/*
+	 * We are the first waiter - try to look up the owner based on
+	 * @uval and attach to it.
+	 */
+	return attach_to_pi_owner(uval, key, ps);
+}
+
 /**
  * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
  * @uaddr:		the pi futex user address

index e0802beff9ad..e7f392e56be4 100644
@@ -946,6 +946,17 @@ static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 	return attach_to_pi_owner(uval, key, ps);
 }
 
+static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
+{
+	u32 uninitialized_var(curval);
+
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
+		return -EFAULT;
+
+	/*If user space value changed, let the caller retry */
+	return curval != uval ? -EAGAIN : 0;
+}
+
 /**
  * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
  * @uaddr:		the pi futex user address

@@ -969,113 +980,69 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
 				struct futex_pi_state **ps,
 				struct task_struct *task, int set_waiters)
 {
-	int lock_taken, ret, force_take = 0;
-	u32 uval, newval, curval, vpid = task_pid_vnr(task);
-
-retry:
-	ret = lock_taken = 0;
+	u32 uval, newval, vpid = task_pid_vnr(task);
+	struct futex_q *match;
+	int ret;
 
 	/*
-	 * To avoid races, we attempt to take the lock here again
-	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
-	 * the locks. It will most likely not succeed.
+	 * Read the user space value first so we can validate a few
+	 * things before proceeding further.
 	 */
-	newval = vpid;
-	if (set_waiters)
-		newval |= FUTEX_WAITERS;
-
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
+	if (get_futex_value_locked(&uval, uaddr))
 		return -EFAULT;
 
 	/*
 	 * Detect deadlocks.
 	 */
-	if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
+	if ((unlikely((uval & FUTEX_TID_MASK) == vpid)))
 		return -EDEADLK;
 
 	/*
-	 * Surprise - we got the lock, but we do not trust user space at all.
+	 * Lookup existing state first. If it exists, try to attach to
+	 * its pi_state.
 	 */
-	if (unlikely(!curval)) {
-		/*
-		 * We verify whether there is kernel state for this
-		 * futex. If not, we can safely assume, that the 0 ->
-		 * TID transition is correct. If state exists, we do
-		 * not bother to fixup the user space state as it was
-		 * corrupted already.
-		 */
-		return futex_top_waiter(hb, key) ? -EINVAL : 1;
-	}
-
-	uval = curval;
-
-	/*
-	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
-	 * to wake at the next unlock.
-	 */
-	newval = curval | FUTEX_WAITERS;
+	match = futex_top_waiter(hb, key);
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
 
 	/*
-	 * Should we force take the futex? See below.
+	 * No waiter and user TID is 0. We are here because the
+	 * waiters or the owner died bit is set or called from
+	 * requeue_cmp_pi or for whatever reason something took the
+	 * syscall.
 	 */
-	if (unlikely(force_take)) {
+	if (!(uval & FUTEX_TID_MASK)) {
 		/*
-		 * Keep the OWNER_DIED and the WAITERS bit and set the
-		 * new TID value.
+		 * We take over the futex. No other waiters and the user space
+		 * TID is 0. We preserve the owner died bit.
 		 */
-		newval = (curval & ~FUTEX_TID_MASK) | vpid;
-		force_take = 0;
-		lock_taken = 1;
-	}
+		newval = uval & FUTEX_OWNER_DIED;
+		newval |= vpid;
 
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
-	if (unlikely(curval != uval))
-		goto retry;
+		/* The futex requeue_pi code can enforce the waiters bit */
+		if (set_waiters)
+			newval |= FUTEX_WAITERS;
+
+		ret = lock_pi_update_atomic(uaddr, uval, newval);
+		/* If the take over worked, return 1 */
+		return ret < 0 ? ret : 1;
+	}
 
 	/*
-	 * We took the lock due to forced take over.
+	 * First waiter. Set the waiters bit before attaching ourself to
+	 * the owner. If owner tries to unlock, it will be forced into
+	 * the kernel and blocked on hb->lock.
 	 */
-	if (unlikely(lock_taken))
-		return 1;
-
+	newval = uval | FUTEX_WAITERS;
+	ret = lock_pi_update_atomic(uaddr, uval, newval);
+	if (ret)
+		return ret;
 	/*
-	 * We dont have the lock. Look up the PI state (or create it if
-	 * we are the first waiter):
+	 * If the update of the user space value succeeded, we try to
+	 * attach to the owner. If that fails, no harm done, we only
+	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	ret = lookup_pi_state(uval, hb, key, ps);
-
-	if (unlikely(ret)) {
-		switch (ret) {
-		case -ESRCH:
-			/*
-			 * We failed to find an owner for this
-			 * futex. So we have no pi_state to block
-			 * on. This can happen in two cases:
-			 *
-			 * 1) The owner died
-			 * 2) A stale FUTEX_WAITERS bit
-			 *
-			 * Re-read the futex value.
-			 */
-			if (get_futex_value_locked(&curval, uaddr))
-				return -EFAULT;
-
-			/*
-			 * If the owner died or we have a stale
-			 * WAITERS bit the owner TID in the user space
-			 * futex is 0.
-			 */
-			if (!(curval & FUTEX_TID_MASK)) {
-				force_take = 1;
-				goto retry;
-			}
-		default:
-			break;
-		}
-	}
-
-	return ret;
+	return attach_to_pi_owner(uval, key, ps);
 }
 
 /**

@@ -1649,7 +1616,12 @@ retry_private:
 				goto retry;
 			goto out;
 		case -EAGAIN:
-			/* The owner was exiting, try again. */
+			/*
+			 * Two reasons for this:
+			 * - Owner is exiting and we just wait for the
+			 *   exit to complete.
+			 * - The user space value changed.
+			 */
 			double_unlock_hb(hb1, hb2);
 			hb_waiters_dec(hb2);
 			put_futex_key(&key2);

@@ -2316,8 +2288,10 @@ retry_private:
 			goto uaddr_faulted;
 		case -EAGAIN:
 			/*
-			 * Task is exiting and we just wait for the
-			 * exit to complete.
+			 * Two reasons for this:
+			 * - Task is exiting and we just wait for the
+			 *   exit to complete.
+			 * - The user space value changed.
 			 */
 			queue_unlock(hb);
 			put_futex_key(&q.key);

index a0d9eadcfe02..ec72272ab73a 100644
@@ -1697,7 +1697,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(ret)) {
-		remove_waiter(lock, &waiter);
+		if (rt_mutex_has_waiters(lock))
+			remove_waiter(lock, &waiter);
 		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
 	} else if (ww_ctx) {
 		ww_mutex_account_lock(lock, ww_ctx);

index ec72272ab73a..74a824523d3a 100644
@@ -361,7 +361,8 @@ int max_lock_depth = 1024;
 
 static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
 {
-	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+	return rt_mutex_real_waiter(p->pi_blocked_on) ?
+		p->pi_blocked_on->lock : NULL;
 }
 
 /*

index 74a824523d3a..1794fae96a2a 100644
@@ -2238,7 +2238,7 @@ __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_c
 
 	might_sleep();
 
-	mutex_acquire(&lock->base.dep_map, 0, 0, _RET_IP_);
+	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
 	ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx);
 	if (ret)
 		mutex_release(&lock->base.dep_map, 1, _RET_IP_);

@@ -2256,8 +2256,7 @@ __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
 
 	might_sleep();
 
-	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map,
-			_RET_IP_);
+	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
 	ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx);
 	if (ret)
 		mutex_release(&lock->base.dep_map, 1, _RET_IP_);

index 1794fae96a2a..27a1993111f9 100644
@@ -2239,7 +2239,8 @@ __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_c
 	might_sleep();
 
 	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
-	ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx);
+	ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL,
+				RT_MUTEX_FULL_CHAINWALK, ww_ctx);
 	if (ret)
 		mutex_release(&lock->base.dep_map, 1, _RET_IP_);
 	else if (!ret && ww_ctx->acquired > 1)

@@ -2257,7 +2258,8 @@ __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
 	might_sleep();
 
 	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
-	ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx);
+	ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL,
+				RT_MUTEX_FULL_CHAINWALK, ww_ctx);
 	if (ret)
 		mutex_release(&lock->base.dep_map, 1, _RET_IP_);
 	else if (!ret && ww_ctx->acquired > 1)

index 0b46ef261c77..c2c8a7828f04 100644
@@ -611,9 +611,9 @@ struct bau_control {
 	cycles_t		send_message;
 	cycles_t		period_end;
 	cycles_t		period_time;
-	spinlock_t		uvhub_lock;
-	spinlock_t		queue_lock;
-	spinlock_t		disable_lock;
+	raw_spinlock_t		uvhub_lock;
+	raw_spinlock_t		queue_lock;
+	raw_spinlock_t		disable_lock;
 	/* tunables */
 	int			max_concurr;
 	int			max_concurr_const;

@@ -773,15 +773,15 @@ static inline int atom_asr(short i, struct atomic_short *v)
  * to be lowered below the current 'v'.  atomic_add_unless can only stop
  * on equal.
  */
-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u)
 {
-	spin_lock(lock);
+	raw_spin_lock(lock);
 	if (atomic_read(v) >= u) {
-		spin_unlock(lock);
+		raw_spin_unlock(lock);
 		return 0;
 	}
 	atomic_inc(v);
-	spin_unlock(lock);
+	raw_spin_unlock(lock);
 	return 1;
 }
 

index a30836c8ac4d..f559a092d8fa 100644
@@ -502,7 +502,7 @@ struct uv_blade_info {
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
 	short		memory_nid;
-	spinlock_t	nmi_lock;	/* obsolete, see uv_hub_nmi */
+	raw_spinlock_t	nmi_lock;	/* obsolete, see uv_hub_nmi */
 	unsigned long	nmi_count;	/* obsolete, see uv_hub_nmi */
 };
 extern struct uv_blade_info *uv_blade_info;

index d263b1307de1..1ef690e5459f 100644
@@ -911,7 +911,7 @@ void __init uv_system_init(void)
 			uv_blade_info[blade].pnode = pnode;
 			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
-			spin_lock_init(&uv_blade_info[blade].nmi_lock);
+			raw_spin_lock_init(&uv_blade_info[blade].nmi_lock);
 			min_pnode = min(pnode, min_pnode);
 			max_pnode = max(pnode, max_pnode);
 			blade++;

index dfe605ac1bcd..999fd5be9aa1 100644
@@ -719,9 +719,9 @@ static void destination_plugged(struct bau_desc *bau_desc,
 
 		quiesce_local_uvhub(hmaster);
 
-		spin_lock(&hmaster->queue_lock);
+		raw_spin_lock(&hmaster->queue_lock);
 		reset_with_ipi(&bau_desc->distribution, bcp);
-		spin_unlock(&hmaster->queue_lock);
+		raw_spin_unlock(&hmaster->queue_lock);
 
 		end_uvhub_quiesce(hmaster);
 

@@ -741,9 +741,9 @@ static void destination_timeout(struct bau_desc *bau_desc,
 
 		quiesce_local_uvhub(hmaster);
 
-		spin_lock(&hmaster->queue_lock);
+		raw_spin_lock(&hmaster->queue_lock);
 		reset_with_ipi(&bau_desc->distribution, bcp);
-		spin_unlock(&hmaster->queue_lock);
+		raw_spin_unlock(&hmaster->queue_lock);
 
 		end_uvhub_quiesce(hmaster);
 

@@ -764,7 +764,7 @@ static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
 	cycles_t tm1;
 
 	hmaster = bcp->uvhub_master;
-	spin_lock(&hmaster->disable_lock);
+	raw_spin_lock(&hmaster->disable_lock);
 	if (!bcp->baudisabled) {
 		stat->s_bau_disabled++;
 		tm1 = get_cycles();

@@ -777,7 +777,7 @@ static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
 			}
 		}
 	}
-	spin_unlock(&hmaster->disable_lock);
+	raw_spin_unlock(&hmaster->disable_lock);
 }
 
 static void count_max_concurr(int stat, struct bau_control *bcp,

@@ -840,7 +840,7 @@ static void record_send_stats(cycles_t time1, cycles_t time2,
  */
 static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat)
 {
-	spinlock_t *lock = &hmaster->uvhub_lock;
+	raw_spinlock_t *lock = &hmaster->uvhub_lock;
 	atomic_t *v;
 
 	v = &hmaster->active_descriptor_count;

@@ -972,7 +972,7 @@ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
 	struct bau_control *hmaster;
 
 	hmaster = bcp->uvhub_master;
-	spin_lock(&hmaster->disable_lock);
+	raw_spin_lock(&hmaster->disable_lock);
 	if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) {
 		stat->s_bau_reenabled++;
 		for_each_present_cpu(tcpu) {

@@ -984,10 +984,10 @@ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
 				tbcp->period_giveups = 0;
 			}
 		}
-		spin_unlock(&hmaster->disable_lock);
+		raw_spin_unlock(&hmaster->disable_lock);
 		return 0;
 	}
-	spin_unlock(&hmaster->disable_lock);
+	raw_spin_unlock(&hmaster->disable_lock);
 	return -1;
 }
 

@@ -1895,9 +1895,9 @@ static void __init init_per_cpu_tunables(void)
 		bcp->cong_reps			= congested_reps;
 		bcp->disabled_period =		sec_2_cycles(disabled_period);
 		bcp->giveup_limit =		giveup_limit;
-		spin_lock_init(&bcp->queue_lock);
-		spin_lock_init(&bcp->uvhub_lock);
-		spin_lock_init(&bcp->disable_lock);
+		raw_spin_lock_init(&bcp->queue_lock);
+		raw_spin_lock_init(&bcp->uvhub_lock);
+		raw_spin_lock_init(&bcp->disable_lock);
 	}
 }
 

index 5c86786bbfd2..c039afa26aa2 100644
@@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
 
 /* There is one of these allocated per node */
 struct uv_rtc_timer_head {
-	spinlock_t	lock;
+	raw_spinlock_t	lock;
 	/* next cpu waiting for timer, local node relative: */
 	int		next_cpu;
 	/* number of cpus on this node: */

@@ -178,7 +178,7 @@ static __init int uv_rtc_allocate_timers(void)
 				uv_rtc_deallocate_timers();
 				return -ENOMEM;
 			}
-			spin_lock_init(&head->lock);
+			raw_spin_lock_init(&head->lock);
 			head->ncpus = uv_blade_nr_possible_cpus(bid);
 			head->next_cpu = -1;
 			blade_info[bid] = head;

@@ -232,7 +232,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
 	unsigned long flags;
 	int next_cpu;
 
-	spin_lock_irqsave(&head->lock, flags);
+	raw_spin_lock_irqsave(&head->lock, flags);
 
 	next_cpu = head->next_cpu;
 	*t = expires;

@@ -244,12 +244,12 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
 		if (uv_setup_intr(cpu, expires)) {
 			*t = ULLONG_MAX;
 			uv_rtc_find_next_timer(head, pnode);
-			spin_unlock_irqrestore(&head->lock, flags);
+			raw_spin_unlock_irqrestore(&head->lock, flags);
 			return -ETIME;
 		}
 	}
 
-	spin_unlock_irqrestore(&head->lock, flags);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
 	return 0;
 }
 

@@ -268,7 +268,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
 	unsigned long flags;
 	int rc = 0;
 
-	spin_lock_irqsave(&head->lock, flags);
+	raw_spin_lock_irqsave(&head->lock, flags);
 
 	if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force)
 		rc = 1;

@@ -280,7 +280,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
 			uv_rtc_find_next_timer(head, pnode);
 	}
 
-	spin_unlock_irqrestore(&head->lock, flags);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
 
 	return rc;
 }

@@ -300,13 +300,18 @@ static int uv_rtc_unset_timer(int cpu, int force)
 static cycle_t uv_read_rtc(struct clocksource *cs)
 {
 	unsigned long offset;
+	cycle_t cycles;
 
+	preempt_disable();
 	if (uv_get_min_hub_revision_id() == 1)
 		offset = 0;
 	else
 		offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
 
-	return (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
+	cycles = (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
+	preempt_enable();
+
+	return cycles;
 }
 
 /*

index 2aff798fbef4..54d26a98ff84 100644
@@ -90,6 +90,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	preempt_disable_rt();
+
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"

@@ -101,6 +103,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "cc", "memory");
 
 	*uval = val;
+
+	preempt_enable_rt();
 	return ret;
 }
 

index df2fbba7efc8..30b1a4010b89 100644
@@ -127,6 +127,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 
 #else	/* min ARCH >= ARMv6 */
 
+#define __HAVE_ARCH_CMPXCHG 1
+
 extern void __bad_cmpxchg(volatile void *ptr, int size);
 
 /*

index 6b59617760c1..740219e35d6c 100644
@@ -124,7 +124,7 @@ void *kmap_coherent(struct page *page, unsigned long addr)
 
 	BUG_ON(Page_dcache_dirty(page));
 
-	pagefault_disable();
+	raw_pagefault_disable();
 	idx = (addr >> PAGE_SHIFT) & (FIX_N_COLOURS - 1);
 #ifdef CONFIG_MIPS_MT_SMTC
 	idx += FIX_N_COLOURS * smp_processor_id() +

@@ -191,7 +191,7 @@ void kunmap_coherent(void)
 	write_c0_entryhi(old_ctx);
 	EXIT_CRITICAL(flags);
 #endif
-	pagefault_enable();
+	raw_pagefault_enable();
 }
 
 void copy_user_highpage(struct page *to, struct page *from,

index d2895836f9fa..c85e07ab51e4 100644
@@ -191,7 +191,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 	/* TODO: audit callers to ensure they are ready for qc_issue to
 	 * unconditionally re-enable interrupts
 	 */
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	spin_unlock(ap->lock);
 
 	/* If the device fell off, no sense in issuing commands */

@@ -261,7 +261,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 
  out:
 	spin_lock(ap->lock);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 	return ret;
 }
 

index fa54408b66b2..be24d2d186fa 100644
@@ -2512,14 +2512,17 @@ static void __init memcg_stock_init(void)
  */
 static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-	struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
+	struct memcg_stock_pcp *stock;
+	int cpu = get_cpu_light();
+
+	stock = &per_cpu(memcg_stock, cpu);
 
 	if (stock->cached != memcg) { /* reset if necessary */
 		drain_stock(stock);
 		stock->cached = memcg;
 	}
 	stock->nr_pages += nr_pages;
-	put_cpu_var(memcg_stock);
+	put_cpu_light();
 }
 
 /*

new file mode 100644
index 000000000000..f175fa9a6016
@@ -0,0 +1,24 @@
+#ifndef _LINUX_SWORK_H
+#define _LINUX_SWORK_H
+
+#include <linux/list.h>
+
+struct swork_event {
+	struct list_head item;
+	unsigned long flags;
+	void (*func)(struct swork_event *);
+};
+
+static inline void INIT_SWORK(struct swork_event *event,
+			      void (*func)(struct swork_event *))
+{
+	event->flags = 0;
+	event->func = func;
+}
+
+bool swork_queue(struct swork_event *sev);
+
+int swork_get(void);
+void swork_put(void);
+
+#endif /* _LINUX_SWORK_H */

172 lines not on this page · raw message

index a4acaf2bcf18..22ca25818120 100644
@@ -349,9 +349,9 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 	if (!svc_xprt_has_something_to_do(xprt))
 		return;
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	put_cpu();
+	put_cpu_light();
 
 	spin_lock_bh(&pool->sp_lock);
 

index 0065b08fbb7a..924c2d274ab5 100644
@@ -20,6 +20,7 @@
 
 struct rw_semaphore {
 	struct rt_mutex		lock;
+	int			read_depth;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif

index eac2ddea9c45..9a972e996185 100644
@@ -322,7 +322,8 @@ EXPORT_SYMBOL(rt_up_write);
 void  rt_up_read(struct rw_semaphore *rwsem)
 {
 	rwsem_release(&rwsem->dep_map, 1, _RET_IP_);
-	rt_mutex_unlock(&rwsem->lock);
+	if (--rwsem->read_depth == 0)
+		rt_mutex_unlock(&rwsem->lock);
 }
 EXPORT_SYMBOL(rt_up_read);
 

@@ -333,6 +334,7 @@ EXPORT_SYMBOL(rt_up_read);
 void  rt_downgrade_write(struct rw_semaphore *rwsem)
 {
 	BUG_ON(rt_mutex_owner(&rwsem->lock) != current);
+	rwsem->read_depth = 1;
 }
 EXPORT_SYMBOL(rt_downgrade_write);
 

@@ -370,12 +372,23 @@ EXPORT_SYMBOL(rt_down_write_nested_lock);
 
 int  rt_down_read_trylock(struct rw_semaphore *rwsem)
 {
-	int ret;
+	struct rt_mutex *lock = &rwsem->lock;
+	int ret = 1;
 
-	ret = rt_mutex_trylock(&rwsem->lock);
-	if (ret)
-		rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
+	/*
+	 * recursive read locks succeed when current owns the rwsem,
+	 * but not when read_depth == 0 which means that the rwsem is
+	 * write locked.
+	 */
+	if (rt_mutex_owner(lock) != current)
+		ret = rt_mutex_trylock(&rwsem->lock);
+	else if (!rwsem->read_depth)
+		ret = 0;
 
+	if (ret) {
+		rwsem->read_depth++;
+		rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(rt_down_read_trylock);

@@ -383,7 +396,10 @@ EXPORT_SYMBOL(rt_down_read_trylock);
 static void __rt_down_read(struct rw_semaphore *rwsem, int subclass)
 {
 	rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_);
-	rt_mutex_lock(&rwsem->lock);
+
+	if (rt_mutex_owner(&rwsem->lock) != current)
+		rt_mutex_lock(&rwsem->lock);
+	rwsem->read_depth++;
 }
 
 void  rt_down_read(struct rw_semaphore *rwsem)

@@ -408,6 +424,7 @@ void  __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name,
 	debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem));
 	lockdep_init_map(&rwsem->dep_map, name, key, 0);
 #endif
+	rwsem->read_depth = 0;
 	rwsem->lock.save_state = 0;
 }
 EXPORT_SYMBOL(__rt_rwsem_init);

index 27a1993111f9..ee4e7e747e06 100644
@@ -1694,13 +1694,20 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 
 	if (likely(!ret))
 		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter, ww_ctx);
+	else if (ww_ctx) {
+		/* ww_mutex received EDEADLK, let it become EALREADY */
+		ret = __mutex_lock_check_stamp(lock, ww_ctx);
+		BUG_ON(!ret);
+	}
 
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(ret)) {
 		if (rt_mutex_has_waiters(lock))
 			remove_waiter(lock, &waiter);
-		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
+		/* ww_mutex want to report EDEADLK/EALREADY, let them */
+		if (!ww_ctx)
+			rt_mutex_handle_deadlock(ret, chwalk, &waiter);
 	} else if (ww_ctx) {
 		ww_mutex_account_lock(lock, ww_ctx);
 	}

@@ -2239,8 +2246,7 @@ __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_c
 	might_sleep();
 
 	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
-	ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL,
-				RT_MUTEX_FULL_CHAINWALK, ww_ctx);
+	ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx);
 	if (ret)
 		mutex_release(&lock->base.dep_map, 1, _RET_IP_);
 	else if (!ret && ww_ctx->acquired > 1)

@@ -2258,8 +2264,7 @@ __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
 	might_sleep();
 
 	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
-	ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL,
-				RT_MUTEX_FULL_CHAINWALK, ww_ctx);
+	ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx);
 	if (ret)
 		mutex_release(&lock->base.dep_map, 1, _RET_IP_);
 	else if (!ret && ww_ctx->acquired > 1)

@@ -2271,11 +2276,13 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock);
 
 void __sched ww_mutex_unlock(struct ww_mutex *lock)
 {
+	int nest = !!lock->ctx;
+
 	/*
 	 * The unlocking fastpath is the 0->1 transition from 'locked'
 	 * into 'unlocked' state:
 	 */
-	if (lock->ctx) {
+	if (nest) {
 #ifdef CONFIG_DEBUG_MUTEXES
 		DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
 #endif

@@ -2284,7 +2291,7 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock)
 		lock->ctx = NULL;
 	}
 
-	mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+	mutex_release(&lock->base.dep_map, nest, _RET_IP_);
 	rt_mutex_unlock(&lock->base.lock);
 }
 EXPORT_SYMBOL(ww_mutex_unlock);

index 081fd7e6a9f0..f297ddd3365c 100644
@@ -29,6 +29,7 @@
 #include <linux/pm.h>
 #include <linux/thermal.h>
 #include <linux/debugfs.h>
+#include <linux/work-simple.h>
 #include <asm/cpu_device_id.h>
 #include <asm/mce.h>
 

@@ -352,7 +353,7 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
 	}
 }
 
-static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
+static void platform_thermal_notify_work(struct swork_event *event)
 {
 	unsigned long flags;
 	int cpu = smp_processor_id();

@@ -369,7 +370,7 @@ static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
 			pkg_work_scheduled[phy_id]) {
 		disable_pkg_thres_interrupt();
 		spin_unlock_irqrestore(&pkg_work_lock, flags);
-		return -EINVAL;
+		return;
 	}
 	pkg_work_scheduled[phy_id] = 1;
 	spin_unlock_irqrestore(&pkg_work_lock, flags);

@@ -378,9 +379,48 @@ static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
 	schedule_delayed_work_on(cpu,
 				&per_cpu(pkg_temp_thermal_threshold_work, cpu),
 				msecs_to_jiffies(notify_delay_ms));
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+static struct swork_event notify_work;
+
+static int thermal_notify_work_init(void)
+{
+	int err;
+
+	err = swork_get();
+	if (err)
+		return err;
+
+	INIT_SWORK(&notify_work, platform_thermal_notify_work);
 	return 0;
 }
 
+static void thermal_notify_work_cleanup(void)
+{
+	swork_put();
+}
+
+static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
+{
+	swork_queue(&notify_work);
+	return 0;
+}
+
+#else  /* !CONFIG_PREEMPT_RT_FULL */
+
+static int thermal_notify_work_init(void) { return 0; }
+
+static int thermal_notify_work_cleanup(void) {  }
+
+static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
+{
+	platform_thermal_notify_work(NULL);
+
+	return 0;
+}
+#endif /* CONFIG_PREEMPT_RT_FULL */
+
 static int find_siblings_cpu(int cpu)
 {
 	int i;

@@ -584,6 +624,9 @@ static int __init pkg_temp_thermal_init(void)
 	if (!x86_match_cpu(pkg_temp_thermal_ids))
 		return -ENODEV;
 
+	if (!thermal_notify_work_init())
+		return -ENODEV;
+
 	spin_lock_init(&pkg_work_lock);
 	platform_thermal_package_notify =
 			pkg_temp_thermal_platform_thermal_notify;

@@ -608,7 +651,7 @@ err_ret:
 	kfree(pkg_work_scheduled);
 	platform_thermal_package_notify = NULL;
 	platform_thermal_package_rate_control = NULL;

index 19ae2366a7a9..b93a6103fa4d 100644
@@ -590,6 +590,8 @@ GENERATE_TESTCASE(init_held_rsem)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock)
 

@@ -605,9 +607,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Enabling hardirqs with a softirq-safe lock held:
  */

@@ -640,6 +645,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)
 #undef E1
 #undef E2
 
+#endif
+
 /*
  * Enabling irqs with an irq-safe lock held:
  */

@@ -663,6 +670,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A_rlock)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock)
 

@@ -678,6 +687,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 

@@ -709,6 +720,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock)
 

@@ -724,6 +737,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_rlock)
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 #undef E3