1 files changed, 322 insertions, 164 deletions

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a9a9dbe49fe..3dc6a61bf06 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -7,6 +7,8 @@
  * This file contains driver APIs to the irq subsystem.
  */
 
+#define pr_fmt(fmt) "genirq: " fmt
+
 #include <linux/irq.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
@@ -14,6 +16,8 @@
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/sched/rt.h>
+#include <linux/task_work.h>
 
 #include "internals.h"
 
@@ -28,24 +32,10 @@ static int __init setup_forced_irqthreads(char *arg)
 early_param("threadirqs", setup_forced_irqthreads);
 #endif
 
-/**
- *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
- *	@irq: interrupt number to wait for
- *
- *	This function waits for any pending IRQ handlers for this interrupt
- *	to complete before returning. If you use this function while
- *	holding a resource the IRQ handler may need you will deadlock.
- *
- *	This function may be called - with care - from IRQ context.
- */
-void synchronize_irq(unsigned int irq)
+static void __synchronize_hardirq(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	bool inprogress;
 
-	if (!desc)
-		return;
-
 	do {
 		unsigned long flags;
 
@@ -63,12 +53,56 @@ void synchronize_irq(unsigned int irq)
 
 		/* Oops, that failed? */
 	} while (inprogress);
+}
 
-	/*
-	 * We made sure that no hardirq handler is running. Now verify
-	 * that no threaded handlers are active.
-	 */
-	wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active));
+/**
+ *	synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs)
+ *	@irq: interrupt number to wait for
+ *
+ *	This function waits for any pending hard IRQ handlers for this
+ *	interrupt to complete before returning. If you use this
+ *	function while holding a resource the IRQ handler may need you
+ *	will deadlock. It does not take associated threaded handlers
+ *	into account.
+ *
+ *	Do not use this for shutdown scenarios where you must be sure
+ *	that all parts (hardirq and threaded handler) have completed.
+ *
+ *	This function may be called - with care - from IRQ context.
+ */
+void synchronize_hardirq(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc)
+		__synchronize_hardirq(desc);
+}
+EXPORT_SYMBOL(synchronize_hardirq);
+
+/**
+ *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
+ *	@irq: interrupt number to wait for
+ *
+ *	This function waits for any pending IRQ handlers for this interrupt
+ *	to complete before returning. If you use this function while
+ *	holding a resource the IRQ handler may need you will deadlock.
+ *
+ *	This function may be called - with care - from IRQ context.
+ */
+void synchronize_irq(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc) {
+		__synchronize_hardirq(desc);
+		/*
+		 * We made sure that no hardirq handler is
+		 * running. Now verify that no threaded handlers are
+		 * active.
+		 */
+		wait_event(desc->wait_for_threads,
+			   !atomic_read(&desc->threads_active));
+	}
 }
 EXPORT_SYMBOL(synchronize_irq);
 
@@ -139,7 +173,27 @@ static inline void
 irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
 #endif
 
-int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
+int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			bool force)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+	int ret;
+
+	ret = chip->irq_set_affinity(data, mask, force);
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		cpumask_copy(data->affinity, mask);
+	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_set_thread_affinity(desc);
+		ret = 0;
+	}
+
+	return ret;
+}
+
+int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
+			    bool force)
 {
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	struct irq_desc *desc = irq_data_to_desc(data);
@@ -149,14 +203,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 		return -EINVAL;
 
 	if (irq_can_move_pcntxt(data)) {
-		ret = chip->irq_set_affinity(data, mask, false);
-		switch (ret) {
-		case IRQ_SET_MASK_OK:
-			cpumask_copy(data->affinity, mask);
-		case IRQ_SET_MASK_OK_NOCOPY:
-			irq_set_thread_affinity(desc);
-			ret = 0;
-		}
+		ret = irq_do_set_affinity(data, mask, force);
 	} else {
 		irqd_set_move_pending(data);
 		irq_copy_pending(desc, mask);
@@ -171,13 +218,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 	return ret;
 }
 
-/**
- *	irq_set_affinity - Set the irq affinity of a given irq
- *	@irq:		Interrupt to set affinity
- *	@mask:		cpumask
- *
- */
-int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
+int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -187,7 +228,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret =  __irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask);
+	ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return ret;
 }
@@ -280,9 +321,8 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
 static int
 setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
-	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct cpumask *set = irq_default_affinity;
-	int ret;
+	int node = desc->irq_data.node;
 
 	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
@@ -301,13 +341,14 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 	}
 
 	cpumask_and(mask, cpu_online_mask, set);
-	ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
-	switch (ret) {
-	case IRQ_SET_MASK_OK:
-		cpumask_copy(desc->irq_data.affinity, mask);
-	case IRQ_SET_MASK_OK_NOCOPY:
-		irq_set_thread_affinity(desc);
+	if (node != NUMA_NO_NODE) {
+		const struct cpumask *nodemask = cpumask_of_node(node);
+
+		/* make sure at least one of the cpus in nodemask is online */
+		if (cpumask_intersects(mask, nodemask))
+			cpumask_and(mask, mask, nodemask);
 	}
+	irq_do_set_affinity(&desc->irq_data, mask, false);
 	return 0;
 }
 #else
@@ -539,9 +580,9 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
 		return 0;
 
 	if (irq_settings_can_request(desc)) {
-		if (desc->action)
-			if (irqflags & desc->action->flags & IRQF_SHARED)
-				canrequest =1;
+		if (!desc->action ||
+		    irqflags & desc->action->flags & IRQF_SHARED)
+			canrequest = 1;
 	}
 	irq_put_desc_unlock(desc, flags);
 	return canrequest;
@@ -559,7 +600,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		 * flow-types?
 		 */
 		pr_debug("No set_type function for IRQ %d (%s)\n", irq,
-				chip ? (chip->name ? : "unknown") : "unknown");
+			 chip ? (chip->name ? : "unknown") : "unknown");
 		return 0;
 	}
 
@@ -593,7 +634,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		ret = 0;
 		break;
 	default:
-		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+		pr_err("Setting trigger mode %lu for irq %u failed (%pF)\n",
 		       flags, irq, chip->irq_set_type);
 	}
 	if (unmask)
@@ -601,6 +642,22 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 	return ret;
 }
 
+#ifdef CONFIG_HARDIRQS_SW_RESEND
+int irq_set_parent(int irq, int parent_irq)
+{
+	unsigned long flags;
+	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
+
+	if (!desc)
+		return -EINVAL;
+
+	desc->parent_irq = parent_irq;
+
+	irq_put_desc_unlock(desc, flags);
+	return 0;
+}
+#endif
+
 /*
  * Default primary interrupt handler for threaded interrupts. Is
  * assigned as primary handler when request_threaded_irq is called
@@ -645,7 +702,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  * is marked MASKED.
  */
 static void irq_finalize_oneshot(struct irq_desc *desc,
-				 struct irqaction *action, bool force)
+				 struct irqaction *action)
 {
 	if (!(desc->istate & IRQS_ONESHOT))
 		return;
@@ -679,14 +736,14 @@ again:
 	 * we would clear the threads_oneshot bit of this thread which
 	 * was just set.
 	 */
-	if (!force && test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+	if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
 		goto out_unlock;
 
 	desc->threads_oneshot &= ~action->thread_mask;
 
 	if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) &&
 	    irqd_irq_masked(&desc->irq_data))
-		unmask_irq(desc);
+		unmask_threaded_irq(desc);
 
 out_unlock:
 	raw_spin_unlock_irq(&desc->lock);
@@ -695,12 +752,13 @@ out_unlock:
 
 #ifdef CONFIG_SMP
 /*
- * Check whether we need to chasnge the affinity of the interrupt thread.
+ * Check whether we need to change the affinity of the interrupt thread.
  */
 static void
 irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
 {
 	cpumask_var_t mask;
+	bool valid = true;
 
 	if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
 		return;
@@ -715,10 +773,18 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
 	}
 
 	raw_spin_lock_irq(&desc->lock);
-	cpumask_copy(mask, desc->irq_data.affinity);
+	/*
+	 * This code is triggered unconditionally. Check the affinity
+	 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
+	 */
+	if (desc->irq_data.affinity)
+		cpumask_copy(mask, desc->irq_data.affinity);
+	else
+		valid = false;
 	raw_spin_unlock_irq(&desc->lock);
 
-	set_cpus_allowed_ptr(current, mask);
+	if (valid)
+		set_cpus_allowed_ptr(current, mask);
 	free_cpumask_var(mask);
 }
 #else
@@ -739,13 +805,13 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 
 	local_bh_disable();
 	ret = action->thread_fn(action->irq, action->dev_id);
-	irq_finalize_oneshot(desc, action, false);
+	irq_finalize_oneshot(desc, action);
 	local_bh_enable();
 	return ret;
 }
 
 /*
- * Interrupts explicitely requested as threaded interupts want to be
+ * Interrupts explicitly requested as threaded interrupts want to be
  * preemtible - many of them need to sleep and wait for slow busses to
  * complete.
  */
@@ -755,105 +821,116 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc,
 	irqreturn_t ret;
 
 	ret = action->thread_fn(action->irq, action->dev_id);
-	irq_finalize_oneshot(desc, action, false);
+	irq_finalize_oneshot(desc, action);
 	return ret;
 }
 
+static void wake_threads_waitq(struct irq_desc *desc)
+{
+	if (atomic_dec_and_test(&desc->threads_active))
+		wake_up(&desc->wait_for_threads);
+}
+
+static void irq_thread_dtor(struct callback_head *unused)
+{
+	struct task_struct *tsk = current;
+	struct irq_desc *desc;
+	struct irqaction *action;
+
+	if (WARN_ON_ONCE(!(current->flags & PF_EXITING)))
+		return;
+
+	action = kthread_data(tsk);
+
+	pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
+	       tsk->comm, tsk->pid, action->irq);
+
+
+	desc = irq_to_desc(action->irq);
+	/*
+	 * If IRQTF_RUNTHREAD is set, we need to decrement
+	 * desc->threads_active and wake possible waiters.
+	 */
+	if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		wake_threads_waitq(desc);
+
+	/* Prevent a stale desc->threads_oneshot */
+	irq_finalize_oneshot(desc, action);
+}
+
 /*
  * Interrupt handler thread
  */
 static int irq_thread(void *data)
 {
-	static const struct sched_param param = {
-		.sched_priority = MAX_USER_RT_PRIO/2,
-	};
+	struct callback_head on_exit_work;
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
 	irqreturn_t (*handler_fn)(struct irq_desc *desc,
 			struct irqaction *action);
-	int wake;
 
-	if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
+	if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD,
 					&action->thread_flags))
 		handler_fn = irq_forced_thread_fn;
 	else
 		handler_fn = irq_thread_fn;
 
-	sched_setscheduler(current, SCHED_FIFO, &param);
-	current->irqaction = action;
+	init_task_work(&on_exit_work, irq_thread_dtor);
+	task_work_add(current, &on_exit_work, false);
+
+	irq_thread_check_affinity(desc, action);
 
 	while (!irq_wait_for_interrupt(action)) {
+		irqreturn_t action_ret;
 
 		irq_thread_check_affinity(desc, action);
 
-		atomic_inc(&desc->threads_active);
+		action_ret = handler_fn(desc, action);
+		if (action_ret == IRQ_HANDLED)
+			atomic_inc(&desc->threads_handled);
 
-		raw_spin_lock_irq(&desc->lock);
-		if (unlikely(irqd_irq_disabled(&desc->irq_data))) {
-			/*
-			 * CHECKME: We might need a dedicated
-			 * IRQ_THREAD_PENDING flag here, which
-			 * retriggers the thread in check_irq_resend()
-			 * but AFAICT IRQS_PENDING should be fine as it
-			 * retriggers the interrupt itself --- tglx
-			 */
-			desc->istate |= IRQS_PENDING;
-			raw_spin_unlock_irq(&desc->lock);
-		} else {
-			irqreturn_t action_ret;
-
-			raw_spin_unlock_irq(&desc->lock);
-			action_ret = handler_fn(desc, action);
-			if (!noirqdebug)
-				note_interrupt(action->irq, desc, action_ret);
-		}
-
-		wake = atomic_dec_and_test(&desc->threads_active);
-
-		if (wake && waitqueue_active(&desc->wait_for_threads))
-			wake_up(&desc->wait_for_threads);
+		wake_threads_waitq(desc);
 	}
 
-	/* Prevent a stale desc->threads_oneshot */
-	irq_finalize_oneshot(desc, action, true);
-
 	/*
-	 * Clear irqaction. Otherwise exit_irq_thread() would make
-	 * fuzz about an active irq thread going into nirvana.
+	 * This is the regular exit path. __free_irq() is stopping the
+	 * thread via kthread_stop() after calling
+	 * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
+	 * oneshot mask bit can be set. We cannot verify that as we
+	 * cannot touch the oneshot mask at this point anymore as
+	 * __setup_irq() might have given out currents thread_mask
+	 * again.
 	 */
-	current->irqaction = NULL;
+	task_work_cancel(current, irq_thread_dtor);
 	return 0;
 }
 
-/*
- * Called from do_exit()
+/**
+ *	irq_wake_thread - wake the irq thread for the action identified by dev_id
+ *	@irq:		Interrupt line
+ *	@dev_id:	Device identity for which the thread should be woken
+ *
  */
-void exit_irq_thread(void)
+void irq_wake_thread(unsigned int irq, void *dev_id)
 {
-	struct task_struct *tsk = current;
-	struct irq_desc *desc;
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct irqaction *action;
+	unsigned long flags;
 
-	if (!tsk->irqaction)
+	if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
 		return;
 
-	printk(KERN_ERR
-	       "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
-	       tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
-
-	desc = irq_to_desc(tsk->irqaction->irq);
-
-	/*
-	 * Prevent a stale desc->threads_oneshot. Must be called
-	 * before setting the IRQTF_DIED flag.
-	 */
-	irq_finalize_oneshot(desc, tsk->irqaction, true);
-
-	/*
-	 * Set the THREAD DIED flag to prevent further wakeups of the
-	 * soon to be gone threaded handler.
-	 */
-	set_bit(IRQTF_DIED, &tsk->irqaction->flags);
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	for (action = desc->action; action; action = action->next) {
+		if (action->dev_id == dev_id) {
+			if (action->thread)
+				__irq_wake_thread(desc, action);
+			break;
+		}
+	}
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
+EXPORT_SYMBOL_GPL(irq_wake_thread);
 
 static void irq_setup_forced_threading(struct irqaction *new)
 {
@@ -871,6 +948,23 @@ static void irq_setup_forced_threading(struct irqaction *new)
 	}
 }
 
+static int irq_request_resources(struct irq_desc *desc)
+{
+	struct irq_data *d = &desc->irq_data;
+	struct irq_chip *c = d->chip;
+
+	return c->irq_request_resources ? c->irq_request_resources(d) : 0;
+}
+
+static void irq_release_resources(struct irq_desc *desc)
+{
+	struct irq_data *d = &desc->irq_data;
+	struct irq_chip *c = d->chip;
+
+	if (c->irq_release_resources)
+		c->irq_release_resources(d);
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -879,7 +973,6 @@ static int
 __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 {
 	struct irqaction *old, **old_ptr;
-	const char *old_name = NULL;
 	unsigned long flags, thread_mask = 0;
 	int ret, nested, shared = 0;
 	cpumask_var_t mask;
@@ -891,22 +984,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		return -ENOSYS;
 	if (!try_module_get(desc->owner))
 		return -ENODEV;
-	/*
-	 * Some drivers like serial.c use request_irq() heavily,
-	 * so we have to be careful not to interfere with a
-	 * running system.
-	 */
-	if (new->flags & IRQF_SAMPLE_RANDOM) {
-		/*
-		 * This function might sleep, we want to call it first,
-		 * outside of the atomic block.
-		 * Yes, this might clear the entropy pool if the wrong
-		 * driver is attempted to be loaded, without actually
-		 * installing a new handler, but is this really a problem,
-		 * only the sysadmin is able to do this.
-		 */
-		rand_initialize_irq(irq);
-	}
 
 	/*
 	 * Check whether the interrupt nests into another interrupt
@@ -936,6 +1013,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	 */
 	if (new->thread_fn && !nested) {
 		struct task_struct *t;
+		static const struct sched_param param = {
+			.sched_priority = MAX_USER_RT_PRIO/2,
+		};
 
 		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
 				   new->name);
@@ -943,6 +1023,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			ret = PTR_ERR(t);
 			goto out_mput;
 		}
+
+		sched_setscheduler_nocheck(t, SCHED_FIFO, &param);
+
 		/*
 		 * We keep the reference to the task struct even if
 		 * the thread dies to avoid that the interrupt code
@@ -950,6 +1033,16 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 */
 		get_task_struct(t);
 		new->thread = t;
+		/*
+		 * Tell the thread to set its affinity. This is
+		 * important for shared interrupt handlers as we do
+		 * not invoke setup_affinity() for the secondary
+		 * handlers as everything is already set up. Even for
+		 * interrupts marked with IRQF_NO_BALANCE this is
+		 * correct as we want the thread to move to the cpu(s)
+		 * on which the requesting code placed the interrupt.
+		 */
+		set_bit(IRQTF_AFFINITY, &new->thread_flags);
 	}
 
 	if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
@@ -958,6 +1051,18 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	}
 
 	/*
+	 * Drivers are often written to work w/o knowledge about the
+	 * underlying irq chip implementation, so a request for a
+	 * threaded irq without a primary hard irq context handler
+	 * requires the ONESHOT flag to be set. Some irq chips like
+	 * MSI based interrupts are per se one shot safe. Check the
+	 * chip flags, so we can avoid the unmask dance at the end of
+	 * the threaded handler for those.
+	 */
+	if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)
+		new->flags &= ~IRQF_ONESHOT;
+
+	/*
 	 * The following block of code has to be executed atomically
 	 */
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -973,10 +1078,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 */
 		if (!((old->flags & new->flags) & IRQF_SHARED) ||
 		    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
-		    ((old->flags ^ new->flags) & IRQF_ONESHOT)) {
-			old_name = old->name;
+		    ((old->flags ^ new->flags) & IRQF_ONESHOT))
 			goto mismatch;
-		}
 
 		/* All handlers must agree on per-cpuness */
 		if ((old->flags & IRQF_PERCPU) !=
@@ -985,6 +1088,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 		/* add new interrupt at end of irq queue */
 		do {
+			/*
+			 * Or all existing action->thread_mask bits,
+			 * so we can find the next zero bit for this
+			 * new action.
+			 */
 			thread_mask |= old->thread_mask;
 			old_ptr = &old->next;
 			old = *old_ptr;
@@ -993,16 +1101,72 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	}
 
 	/*
-	 * Setup the thread mask for this irqaction. Unlikely to have
-	 * 32 resp 64 irqs sharing one line, but who knows.
+	 * Setup the thread mask for this irqaction for ONESHOT. For
+	 * !ONESHOT irqs the thread mask is 0 so we can avoid a
+	 * conditional in irq_wake_thread().
 	 */
-	if (new->flags & IRQF_ONESHOT && thread_mask == ~0UL) {
-		ret = -EBUSY;
+	if (new->flags & IRQF_ONESHOT) {
+		/*
+		 * Unlikely to have 32 resp 64 irqs sharing one line,
+		 * but who knows.
+		 */
+		if (thread_mask == ~0UL) {
+			ret = -EBUSY;
+			goto out_mask;
+		}
+		/*
+		 * The thread_mask for the action is or'ed to
+		 * desc->thread_active to indicate that the
+		 * IRQF_ONESHOT thread handler has been woken, but not
+		 * yet finished. The bit is cleared when a thread
+		 * completes. When all threads of a shared interrupt
+		 * line have completed desc->threads_active becomes
+		 * zero and the interrupt line is unmasked. See
+		 * handle.c:irq_wake_thread() for further information.
+		 *
+		 * If no thread is woken by primary (hard irq context)
+		 * interrupt handlers, then desc->threads_active is
+		 * also checked for zero to unmask the irq line in the
+		 * affected hard irq flow handlers
+		 * (handle_[fasteoi|level]_irq).
+		 *
+		 * The new action gets the first zero bit of
+		 * thread_mask assigned. See the loop above which or's
+		 * all existing action->thread_mask bits.
+		 */
+		new->thread_mask = 1 << ffz(thread_mask);
+
+	} else if (new->handler == irq_default_primary_handler &&
+		   !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) {
+		/*
+		 * The interrupt was requested with handler = NULL, so
+		 * we use the default primary handler for it. But it
+		 * does not have the oneshot flag set. In combination
+		 * with level interrupts this is deadly, because the
+		 * default primary handler just wakes the thread, then
+		 * the irq lines is reenabled, but the device still
+		 * has the level irq asserted. Rinse and repeat....
+		 *
+		 * While this works for edge type interrupts, we play
+		 * it safe and reject unconditionally because we can't
+		 * say for sure which type this interrupt really
+		 * has. The type flags are unreliable as the
+		 * underlying chip implementation can override them.
+		 */
+		pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
+		       irq);
+		ret = -EINVAL;
 		goto out_mask;
 	}
-	new->thread_mask = 1 << ffz(thread_mask);
 
 	if (!shared) {
+		ret = irq_request_resources(desc);
+		if (ret) {
+			pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n",
+			       new->name, irq, desc->irq_data.chip->name);
+			goto out_mask;
+		}
+
 		init_waitqueue_head(&desc->wait_for_threads);
 
 		/* Setup the type (level, edge polarity) if configured: */
@@ -1027,7 +1191,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			desc->istate |= IRQS_ONESHOT;
 
 		if (irq_settings_can_autoenable(desc))
-			irq_startup(desc);
+			irq_startup(desc, true);
 		else
 			/* Undo nested disables: */
 			desc->depth = 1;
@@ -1047,7 +1211,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 		if (nmsk != omsk)
 			/* hope the handler works with current  trigger mode */
-			pr_warning("IRQ %d uses trigger mode %u; requested %u\n",
+			pr_warning("irq %d uses trigger mode %u; requested %u\n",
 				   irq, nmsk, omsk);
 	}
 
@@ -1084,14 +1248,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	return 0;
 
 mismatch:
-#ifdef CONFIG_DEBUG_SHIRQ
 	if (!(new->flags & IRQF_PROBE_SHARED)) {
-		printk(KERN_ERR "IRQ handler type mismatch for IRQ %d\n", irq);
-		if (old_name)
-			printk(KERN_ERR "current handler: %s\n", old_name);
+		pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n",
+		       irq, new->flags, new->name, old->flags, old->name);
+#ifdef CONFIG_DEBUG_SHIRQ
 		dump_stack();
-	}
 #endif
+	}
 	ret = -EBUSY;
 
 out_mask:
@@ -1103,8 +1266,7 @@ out_thread:
 		struct task_struct *t = new->thread;
 
 		new->thread = NULL;
-		if (likely(!test_bit(IRQTF_DIED, &new->thread_flags)))
-			kthread_stop(t);
+		kthread_stop(t);
 		put_task_struct(t);
 	}
 out_mput:
@@ -1174,15 +1336,11 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 	/* Found it - now remove it from the list of entries: */
 	*action_ptr = action->next;
 
-	/* Currently used only by UML, might disappear one day: */
-#ifdef CONFIG_IRQ_RELEASE_METHOD
-	if (desc->irq_data.chip->release)
-		desc->irq_data.chip->release(irq, dev_id);
-#endif
-
 	/* If this was the last handler, shut down the IRQ line: */
-	if (!desc->action)
+	if (!desc->action) {
 		irq_shutdown(desc);
+		irq_release_resources(desc);
+	}
 
 #ifdef CONFIG_SMP
 	/* make sure affinity_hint is cleaned up */
@@ -1214,8 +1372,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 #endif
 
 	if (action->thread) {
-		if (!test_bit(IRQTF_DIED, &action->thread_flags))
-			kthread_stop(action->thread);
+		kthread_stop(action->thread);
 		put_task_struct(action->thread);
 	}
 
@@ -1310,7 +1467,6 @@ EXPORT_SYMBOL(free_irq);
  *	Flags:
  *
  *	IRQF_SHARED		Interrupt is shared
- *	IRQF_SAMPLE_RANDOM	The interrupt can be used for entropy
  *	IRQF_TRIGGER_*		Specify active edge(s) or level
  *
  */
@@ -1447,6 +1603,7 @@ void enable_percpu_irq(unsigned int irq, unsigned int type)
 out:
 	irq_put_desc_unlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(enable_percpu_irq);
 
 void disable_percpu_irq(unsigned int irq)
 {
@@ -1460,6 +1617,7 @@ void disable_percpu_irq(unsigned int irq)
 	irq_percpu_disable(desc, cpu);
 	irq_put_desc_unlock(desc, flags);
 }
+EXPORT_SYMBOL_GPL(disable_percpu_irq);
 
 /*
  * Internal function to unregister a percpu irqaction.