Merge branch 'for-3.5' of ../cgroup into block/for-3.5/core-merged

cgroup/for-3.5 contains the following changes which blk-cgroup needs
to proceed with the on-going cleanup.

* Dynamic addition and removal of cftypes to make config/stat file
  handling modular for policies.

* cgroup removal update to not wait for css references to drain to fix
  blkcg removal hang caused by cfq caching cfqgs.

Pull in cgroup/for-3.5 into block/for-3.5/core.  This causes the
following conflicts in block/blk-cgroup.c.

* 761b3ef50e "cgroup: remove cgroup_subsys argument from callbacks"
  conflicts with blkiocg_pre_destroy() addition and blkiocg_attach()
  removal.  Resolved by removing @subsys from all subsys methods.

* 676f7c8f84 "cgroup: relocate cftype and cgroup_subsys definitions in
  controllers" conflicts with ->pre_destroy() and ->attach() updates
  and removal of modular config.  Resolved by dropping forward
  declarations of the methods and applying updates to the relocated
  blkio_subsys.

* 4baf6e3325 "cgroup: convert all non-memcg controllers to the new
  cftype interface" builds upon the previous item.  Resolved by adding
  ->base_cftypes to the relocated blkio_subsys.

Signed-off-by: Tejun Heo <tj@kernel.org>

8 files changed, 885 insertions, 200 deletions

diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 5a38bf4de641..cf1a4a68ce44 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -13,7 +13,7 @@ config GENERIC_HARDIRQS
 # Options selectable by the architecture code
 
 # Make sparse irq Kconfig switch below available
-config HAVE_SPARSE_IRQ
+config MAY_HAVE_SPARSE_IRQ
        bool
 
 # Enable the generic irq autoprobe mechanism
@@ -56,13 +56,22 @@ config GENERIC_IRQ_CHIP
 config IRQ_DOMAIN
 	bool
 
+config IRQ_DOMAIN_DEBUG
+	bool "Expose hardware/virtual IRQ mapping via debugfs"
+	depends on IRQ_DOMAIN && DEBUG_FS
+	help
+	  This option will show the mapping relationship between hardware irq
+	  numbers and Linux irq numbers. The mapping is exposed via debugfs
+	  in the file "virq_mapping".
+
+	  If you don't know what this means you don't need it.
+
 # Support forced irq threading
 config IRQ_FORCED_THREADING
        bool
 
 config SPARSE_IRQ
-	bool "Support sparse irq numbering"
-	depends on HAVE_SPARSE_IRQ
+	bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ
 	---help---
 
 	  Sparse irq numbering is useful for distro kernels that want
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 342d8f44e401..0119b9d467ae 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -53,7 +53,7 @@ unsigned long probe_irq_on(void)
 			if (desc->irq_data.chip->irq_set_type)
 				desc->irq_data.chip->irq_set_type(&desc->irq_data,
 							 IRQ_TYPE_PROBE);
-			irq_startup(desc);
+			irq_startup(desc, false);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -70,7 +70,7 @@ unsigned long probe_irq_on(void)
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && irq_settings_can_probe(desc)) {
 			desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
-			if (irq_startup(desc))
+			if (irq_startup(desc, false))
 				desc->istate |= IRQS_PENDING;
 		}
 		raw_spin_unlock_irq(&desc->lock);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f7c543a801d9..6080f6bc8c33 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -16,6 +16,8 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 
+#include <trace/events/irq.h>
+
 #include "internals.h"
 
 /**
@@ -61,8 +63,7 @@ int irq_set_irq_type(unsigned int irq, unsigned int type)
 		return -EINVAL;
 
 	type &= IRQ_TYPE_SENSE_MASK;
-	if (type != IRQ_TYPE_NONE)
-		ret = __irq_set_trigger(desc, irq, type);
+	ret = __irq_set_trigger(desc, irq, type);
 	irq_put_desc_busunlock(desc, flags);
 	return ret;
 }
@@ -157,19 +158,22 @@ static void irq_state_set_masked(struct irq_desc *desc)
 	irqd_set(&desc->irq_data, IRQD_IRQ_MASKED);
 }
 
-int irq_startup(struct irq_desc *desc)
+int irq_startup(struct irq_desc *desc, bool resend)
 {
+	int ret = 0;
+
 	irq_state_clr_disabled(desc);
 	desc->depth = 0;
 
 	if (desc->irq_data.chip->irq_startup) {
-		int ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
+		ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
 		irq_state_clr_masked(desc);
-		return ret;
+	} else {
+		irq_enable(desc);
 	}
-
-	irq_enable(desc);
-	return 0;
+	if (resend)
+		check_irq_resend(desc, desc->irq_data.irq);
+	return ret;
 }
 
 void irq_shutdown(struct irq_desc *desc)
@@ -330,6 +334,24 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(handle_simple_irq);
 
+/*
+ * Called unconditionally from handle_level_irq() and only for oneshot
+ * interrupts from handle_fasteoi_irq()
+ */
+static void cond_unmask_irq(struct irq_desc *desc)
+{
+	/*
+	 * We need to unmask in the following cases:
+	 * - Standard level irq (IRQF_ONESHOT is not set)
+	 * - Oneshot irq which did not wake the thread (caused by a
+	 *   spurious interrupt or a primary handler handling it
+	 *   completely).
+	 */
+	if (!irqd_irq_disabled(&desc->irq_data) &&
+	    irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot)
+		unmask_irq(desc);
+}
+
 /**
  *	handle_level_irq - Level type irq handler
  *	@irq:	the interrupt number
@@ -362,8 +384,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	handle_irq_event(desc);
 
-	if (!irqd_irq_disabled(&desc->irq_data) && !(desc->istate & IRQS_ONESHOT))
-		unmask_irq(desc);
+	cond_unmask_irq(desc);
+
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -417,6 +439,9 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	preflow_handler(desc);
 	handle_irq_event(desc);
 
+	if (desc->istate & IRQS_ONESHOT)
+		cond_unmask_irq(desc);
+
 out_eoi:
 	desc->irq_data.chip->irq_eoi(&desc->irq_data);
 out_unlock:
@@ -625,7 +650,7 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		irq_settings_set_noprobe(desc);
 		irq_settings_set_norequest(desc);
 		irq_settings_set_nothread(desc);
-		irq_startup(desc);
+		irq_startup(desc, true);
 	}
 out:
 	irq_put_desc_busunlock(desc, flags);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 470d08c82bbe..bdb180325551 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -54,14 +54,18 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action)
 static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
 {
 	/*
-	 * Wake up the handler thread for this action. In case the
-	 * thread crashed and was killed we just pretend that we
-	 * handled the interrupt. The hardirq handler has disabled the
-	 * device interrupt, so no irq storm is lurking. If the
+	 * In case the thread crashed and was killed we just pretend that
+	 * we handled the interrupt. The hardirq handler has disabled the
+	 * device interrupt, so no irq storm is lurking.
+	 */
+	if (action->thread->flags & PF_EXITING)
+		return;
+
+	/*
+	 * Wake up the handler thread for this action. If the
 	 * RUNTHREAD bit is already set, nothing to do.
 	 */
-	if (test_bit(IRQTF_DIED, &action->thread_flags) ||
-	    test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+	if (test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
 		return;
 
 	/*
@@ -110,6 +114,18 @@ static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
 	 * threads_oneshot untouched and runs the thread another time.
 	 */
 	desc->threads_oneshot |= action->thread_mask;
+
+	/*
+	 * We increment the threads_active counter in case we wake up
+	 * the irq thread. The irq thread decrements the counter when
+	 * it returns from the handler or in the exit path and wakes
+	 * up waiters which are stuck in synchronize_irq() when the
+	 * active count becomes zero. synchronize_irq() is serialized
+	 * against this code (hard irq handler) via IRQS_INPROGRESS
+	 * like the finalize_oneshot() code. See comment above.
+	 */
+	atomic_inc(&desc->threads_active);
+
 	wake_up_process(action->thread);
 }
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b7952316016a..8e5c56b3b7d9 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -20,14 +20,12 @@ extern bool noirqdebug;
 /*
  * Bits used by threaded handlers:
  * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
- * IRQTF_DIED      - handler thread died
  * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
  * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
  * IRQTF_FORCED_THREAD  - irq action is force threaded
  */
 enum {
 	IRQTF_RUNTHREAD,
-	IRQTF_DIED,
 	IRQTF_WARNED,
 	IRQTF_AFFINITY,
 	IRQTF_FORCED_THREAD,
@@ -67,7 +65,7 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
-extern int irq_startup(struct irq_desc *desc);
+extern int irq_startup(struct irq_desc *desc, bool resend);
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 1f9e26526b69..3601f3fbf67c 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -1,189 +1,793 @@
+#include <linux/debugfs.h>
+#include <linux/hardirq.h>
+#include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/irqdesc.h>
 #include <linux/irqdomain.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/fs.h>
+
+#define IRQ_DOMAIN_MAP_LEGACY 0 /* driver allocated fixed range of irqs.
+				 * ie. legacy 8259, gets irqs 1..15 */
+#define IRQ_DOMAIN_MAP_NOMAP 1 /* no fast reverse mapping */
+#define IRQ_DOMAIN_MAP_LINEAR 2 /* linear map of interrupts */
+#define IRQ_DOMAIN_MAP_TREE 3 /* radix tree */
 
 static LIST_HEAD(irq_domain_list);
 static DEFINE_MUTEX(irq_domain_mutex);
 
+static DEFINE_MUTEX(revmap_trees_mutex);
+static unsigned int irq_virq_count = NR_IRQS;
+static struct irq_domain *irq_default_domain;
+
 /**
- * irq_domain_add() - Register an irq_domain
- * @domain: ptr to initialized irq_domain structure
+ * irq_domain_alloc() - Allocate a new irq_domain data structure
+ * @of_node: optional device-tree node of the interrupt controller
+ * @revmap_type: type of reverse mapping to use
+ * @ops: map/unmap domain callbacks
+ * @host_data: Controller private data pointer
  *
- * Registers an irq_domain structure.  The irq_domain must at a minimum be
- * initialized with an ops structure pointer, and either a ->to_irq hook or
- * a valid irq_base value.  Everything else is optional.
+ * Allocates and initialize and irq_domain structure.  Caller is expected to
+ * register allocated irq_domain with irq_domain_register().  Returns pointer
+ * to IRQ domain, or NULL on failure.
  */
-void irq_domain_add(struct irq_domain *domain)
+static struct irq_domain *irq_domain_alloc(struct device_node *of_node,
+					   unsigned int revmap_type,
+					   const struct irq_domain_ops *ops,
+					   void *host_data)
 {
-	struct irq_data *d;
-	int hwirq, irq;
+	struct irq_domain *domain;
 
-	/*
-	 * This assumes that the irq_domain owner has already allocated
-	 * the irq_descs.  This block will be removed when support for dynamic
-	 * allocation of irq_descs is added to irq_domain.
-	 */
-	irq_domain_for_each_irq(domain, hwirq, irq) {
-		d = irq_get_irq_data(irq);
-		if (!d) {
-			WARN(1, "error: assigning domain to non existant irq_desc");
-			return;
-		}
-		if (d->domain) {
-			/* things are broken; just report, don't clean up */
-			WARN(1, "error: irq_desc already assigned to a domain");
-			return;
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (WARN_ON(!domain))
+		return NULL;
+
+	/* Fill structure */
+	domain->revmap_type = revmap_type;
+	domain->ops = ops;
+	domain->host_data = host_data;
+	domain->of_node = of_node_get(of_node);
+
+	return domain;
+}
+
+static void irq_domain_add(struct irq_domain *domain)
+{
+	mutex_lock(&irq_domain_mutex);
+	list_add(&domain->link, &irq_domain_list);
+	mutex_unlock(&irq_domain_mutex);
+	pr_debug("irq: Allocated domain of type %d @0x%p\n",
+		 domain->revmap_type, domain);
+}
+
+static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain,
+					     irq_hw_number_t hwirq)
+{
+	irq_hw_number_t first_hwirq = domain->revmap_data.legacy.first_hwirq;
+	int size = domain->revmap_data.legacy.size;
+
+	if (WARN_ON(hwirq < first_hwirq || hwirq >= first_hwirq + size))
+		return 0;
+	return hwirq - first_hwirq + domain->revmap_data.legacy.first_irq;
+}
+
+/**
+ * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain.
+ * @of_node: pointer to interrupt controller's device tree node.
+ * @size: total number of irqs in legacy mapping
+ * @first_irq: first number of irq block assigned to the domain
+ * @first_hwirq: first hwirq number to use for the translation. Should normally
+ *               be '0', but a positive integer can be used if the effective
+ *               hwirqs numbering does not begin at zero.
+ * @ops: map/unmap domain callbacks
+ * @host_data: Controller private data pointer
+ *
+ * Note: the map() callback will be called before this function returns
+ * for all legacy interrupts except 0 (which is always the invalid irq for
+ * a legacy controller).
+ */
+struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
+					 unsigned int size,
+					 unsigned int first_irq,
+					 irq_hw_number_t first_hwirq,
+					 const struct irq_domain_ops *ops,
+					 void *host_data)
+{
+	struct irq_domain *domain;
+	unsigned int i;
+
+	domain = irq_domain_alloc(of_node, IRQ_DOMAIN_MAP_LEGACY, ops, host_data);
+	if (!domain)
+		return NULL;
+
+	domain->revmap_data.legacy.first_irq = first_irq;
+	domain->revmap_data.legacy.first_hwirq = first_hwirq;
+	domain->revmap_data.legacy.size = size;
+
+	mutex_lock(&irq_domain_mutex);
+	/* Verify that all the irqs are available */
+	for (i = 0; i < size; i++) {
+		int irq = first_irq + i;
+		struct irq_data *irq_data = irq_get_irq_data(irq);
+
+		if (WARN_ON(!irq_data || irq_data->domain)) {
+			mutex_unlock(&irq_domain_mutex);
+			of_node_put(domain->of_node);
+			kfree(domain);
+			return NULL;
 		}
-		d->domain = domain;
-		d->hwirq = hwirq;
 	}
 
-	mutex_lock(&irq_domain_mutex);
-	list_add(&domain->list, &irq_domain_list);
+	/* Claim all of the irqs before registering a legacy domain */
+	for (i = 0; i < size; i++) {
+		struct irq_data *irq_data = irq_get_irq_data(first_irq + i);
+		irq_data->hwirq = first_hwirq + i;
+		irq_data->domain = domain;
+	}
 	mutex_unlock(&irq_domain_mutex);
+
+	for (i = 0; i < size; i++) {
+		int irq = first_irq + i;
+		int hwirq = first_hwirq + i;
+
+		/* IRQ0 gets ignored */
+		if (!irq)
+			continue;
+
+		/* Legacy flags are left to default at this point,
+		 * one can then use irq_create_mapping() to
+		 * explicitly change them
+		 */
+		ops->map(domain, irq, hwirq);
+
+		/* Clear norequest flags */
+		irq_clear_status_flags(irq, IRQ_NOREQUEST);
+	}
+
+	irq_domain_add(domain);
+	return domain;
+}
+
+/**
+ * irq_domain_add_linear() - Allocate and register a legacy revmap irq_domain.
+ * @of_node: pointer to interrupt controller's device tree node.
+ * @ops: map/unmap domain callbacks
+ * @host_data: Controller private data pointer
+ */
+struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
+					 unsigned int size,
+					 const struct irq_domain_ops *ops,
+					 void *host_data)
+{
+	struct irq_domain *domain;
+	unsigned int *revmap;
+
+	revmap = kzalloc(sizeof(*revmap) * size, GFP_KERNEL);
+	if (WARN_ON(!revmap))
+		return NULL;
+
+	domain = irq_domain_alloc(of_node, IRQ_DOMAIN_MAP_LINEAR, ops, host_data);
+	if (!domain) {
+		kfree(revmap);
+		return NULL;
+	}
+	domain->revmap_data.linear.size = size;
+	domain->revmap_data.linear.revmap = revmap;
+	irq_domain_add(domain);
+	return domain;
+}
+
+struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
+					 const struct irq_domain_ops *ops,
+					 void *host_data)
+{
+	struct irq_domain *domain = irq_domain_alloc(of_node,
+					IRQ_DOMAIN_MAP_NOMAP, ops, host_data);
+	if (domain)
+		irq_domain_add(domain);
+	return domain;
+}
+
+/**
+ * irq_domain_add_tree()
+ * @of_node: pointer to interrupt controller's device tree node.
+ * @ops: map/unmap domain callbacks
+ *
+ * Note: The radix tree will be allocated later during boot automatically
+ * (the reverse mapping will use the slow path until that happens).
+ */
+struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
+					 const struct irq_domain_ops *ops,
+					 void *host_data)
+{
+	struct irq_domain *domain = irq_domain_alloc(of_node,
+					IRQ_DOMAIN_MAP_TREE, ops, host_data);
+	if (domain) {
+		INIT_RADIX_TREE(&domain->revmap_data.tree, GFP_KERNEL);
+		irq_domain_add(domain);
+	}
+	return domain;
 }
 
 /**
- * irq_domain_del() - Unregister an irq_domain
- * @domain: ptr to registered irq_domain.
+ * irq_find_host() - Locates a domain for a given device node
+ * @node: device-tree node of the interrupt controller
  */
-void irq_domain_del(struct irq_domain *domain)
+struct irq_domain *irq_find_host(struct device_node *node)
 {
-	struct irq_data *d;
-	int hwirq, irq;
+	struct irq_domain *h, *found = NULL;
+	int rc;
 
+	/* We might want to match the legacy controller last since
+	 * it might potentially be set to match all interrupts in
+	 * the absence of a device node. This isn't a problem so far
+	 * yet though...
+	 */
 	mutex_lock(&irq_domain_mutex);
-	list_del(&domain->list);
+	list_for_each_entry(h, &irq_domain_list, link) {
+		if (h->ops->match)
+			rc = h->ops->match(h, node);
+		else
+			rc = (h->of_node != NULL) && (h->of_node == node);
+
+		if (rc) {
+			found = h;
+			break;
+		}
+	}
 	mutex_unlock(&irq_domain_mutex);
+	return found;
+}
+EXPORT_SYMBOL_GPL(irq_find_host);
+
+/**
+ * irq_set_default_host() - Set a "default" irq domain
+ * @domain: default domain pointer
+ *
+ * For convenience, it's possible to set a "default" domain that will be used
+ * whenever NULL is passed to irq_create_mapping(). It makes life easier for
+ * platforms that want to manipulate a few hard coded interrupt numbers that
+ * aren't properly represented in the device-tree.
+ */
+void irq_set_default_host(struct irq_domain *domain)
+{
+	pr_debug("irq: Default domain set to @0x%p\n", domain);
+
+	irq_default_domain = domain;
+}
+
+/**
+ * irq_set_virq_count() - Set the maximum number of linux irqs
+ * @count: number of linux irqs, capped with NR_IRQS
+ *
+ * This is mainly for use by platforms like iSeries who want to program
+ * the virtual irq number in the controller to avoid the reverse mapping
+ */
+void irq_set_virq_count(unsigned int count)
+{
+	pr_debug("irq: Trying to set virq count to %d\n", count);
 
-	/* Clear the irq_domain assignments */
-	irq_domain_for_each_irq(domain, hwirq, irq) {
-		d = irq_get_irq_data(irq);
-		d->domain = NULL;
+	BUG_ON(count < NUM_ISA_INTERRUPTS);
+	if (count < NR_IRQS)
+		irq_virq_count = count;
+}
+
+static int irq_setup_virq(struct irq_domain *domain, unsigned int virq,
+			    irq_hw_number_t hwirq)
+{
+	struct irq_data *irq_data = irq_get_irq_data(virq);
+
+	irq_data->hwirq = hwirq;
+	irq_data->domain = domain;
+	if (domain->ops->map(domain, virq, hwirq)) {
+		pr_debug("irq: -> mapping failed, freeing\n");
+		irq_data->domain = NULL;
+		irq_data->hwirq = 0;
+		return -1;
 	}
+
+	irq_clear_status_flags(virq, IRQ_NOREQUEST);
+
+	return 0;
 }
 
-#if defined(CONFIG_OF_IRQ)
 /**
- * irq_create_of_mapping() - Map a linux irq number from a DT interrupt spec
+ * irq_create_direct_mapping() - Allocate an irq for direct mapping
+ * @domain: domain to allocate the irq for or NULL for default domain
  *
- * Used by the device tree interrupt mapping code to translate a device tree
- * interrupt specifier to a valid linux irq number.  Returns either a valid
- * linux IRQ number or 0.
+ * This routine is used for irq controllers which can choose the hardware
+ * interrupt numbers they generate. In such a case it's simplest to use
+ * the linux irq as the hardware interrupt number.
+ */
+unsigned int irq_create_direct_mapping(struct irq_domain *domain)
+{
+	unsigned int virq;
+
+	if (domain == NULL)
+		domain = irq_default_domain;
+
+	BUG_ON(domain == NULL);
+	WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP);
+
+	virq = irq_alloc_desc_from(1, 0);
+	if (!virq) {
+		pr_debug("irq: create_direct virq allocation failed\n");
+		return 0;
+	}
+	if (virq >= irq_virq_count) {
+		pr_err("ERROR: no free irqs available below %i maximum\n",
+			irq_virq_count);
+		irq_free_desc(virq);
+		return 0;
+	}
+
+	pr_debug("irq: create_direct obtained virq %d\n", virq);
+
+	if (irq_setup_virq(domain, virq, virq)) {
+		irq_free_desc(virq);
+		return 0;
+	}
+
+	return virq;
+}
+
+/**
+ * irq_create_mapping() - Map a hardware interrupt into linux irq space
+ * @domain: domain owning this hardware interrupt or NULL for default domain
+ * @hwirq: hardware irq number in that domain space
  *
- * When the caller no longer need the irq number returned by this function it
- * should arrange to call irq_dispose_mapping().
+ * Only one mapping per hardware interrupt is permitted. Returns a linux
+ * irq number.
+ * If the sense/trigger is to be specified, set_irq_type() should be called
+ * on the number returned from that call.
  */
+unsigned int irq_create_mapping(struct irq_domain *domain,
+				irq_hw_number_t hwirq)
+{
+	unsigned int virq, hint;
+
+	pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
+
+	/* Look for default domain if nececssary */
+	if (domain == NULL)
+		domain = irq_default_domain;
+	if (domain == NULL) {
+		printk(KERN_WARNING "irq_create_mapping called for"
+		       " NULL domain, hwirq=%lx\n", hwirq);
+		WARN_ON(1);
+		return 0;
+	}
+	pr_debug("irq: -> using domain @%p\n", domain);
+
+	/* Check if mapping already exists */
+	virq = irq_find_mapping(domain, hwirq);
+	if (virq) {
+		pr_debug("irq: -> existing mapping on virq %d\n", virq);
+		return virq;
+	}
+
+	/* Get a virtual interrupt number */
+	if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY)
+		return irq_domain_legacy_revmap(domain, hwirq);
+
+	/* Allocate a virtual interrupt number */
+	hint = hwirq % irq_virq_count;
+	if (hint == 0)
+		hint++;
+	virq = irq_alloc_desc_from(hint, 0);
+	if (!virq)
+		virq = irq_alloc_desc_from(1, 0);
+	if (!virq) {
+		pr_debug("irq: -> virq allocation failed\n");
+		return 0;
+	}
+
+	if (irq_setup_virq(domain, virq, hwirq)) {
+		if (domain->revmap_type != IRQ_DOMAIN_MAP_LEGACY)
+			irq_free_desc(virq);
+		return 0;
+	}
+
+	pr_debug("irq: irq %lu on domain %s mapped to virtual irq %u\n",
+		hwirq, domain->of_node ? domain->of_node->full_name : "null", virq);
+
+	return virq;
+}
+EXPORT_SYMBOL_GPL(irq_create_mapping);
+
 unsigned int irq_create_of_mapping(struct device_node *controller,
 				   const u32 *intspec, unsigned int intsize)
 {
 	struct irq_domain *domain;
-	unsigned long hwirq;
-	unsigned int irq, type;
-	int rc = -EINVAL;
+	irq_hw_number_t hwirq;
+	unsigned int type = IRQ_TYPE_NONE;
+	unsigned int virq;
 
-	/* Find a domain which can translate the irq spec */
-	mutex_lock(&irq_domain_mutex);
-	list_for_each_entry(domain, &irq_domain_list, list) {
-		if (!domain->ops->dt_translate)
-			continue;
-		rc = domain->ops->dt_translate(domain, controller,
-					intspec, intsize, &hwirq, &type);
-		if (rc == 0)
-			break;
+	domain = controller ? irq_find_host(controller) : irq_default_domain;
+	if (!domain) {
+#ifdef CONFIG_MIPS
+		/*
+		 * Workaround to avoid breaking interrupt controller drivers
+		 * that don't yet register an irq_domain.  This is temporary
+		 * code. ~~~gcl, Feb 24, 2012
+		 *
+		 * Scheduled for removal in Linux v3.6.  That should be enough
+		 * time.
+		 */
+		if (intsize > 0)
+			return intspec[0];
+#endif
+		printk(KERN_WARNING "irq: no irq domain found for %s !\n",
+		       controller->full_name);
+		return 0;
 	}
-	mutex_unlock(&irq_domain_mutex);
 
-	if (rc != 0)
-		return 0;
+	/* If domain has no translation, then we assume interrupt line */
+	if (domain->ops->xlate == NULL)
+		hwirq = intspec[0];
+	else {
+		if (domain->ops->xlate(domain, controller, intspec, intsize,
+				     &hwirq, &type))
+			return 0;
+	}
+
+	/* Create mapping */
+	virq = irq_create_mapping(domain, hwirq);
+	if (!virq)
+		return virq;
 
-	irq = irq_domain_to_irq(domain, hwirq);
-	if (type != IRQ_TYPE_NONE)
-		irq_set_irq_type(irq, type);
-	pr_debug("%s: mapped hwirq=%i to irq=%i, flags=%x\n",
-		 controller->full_name, (int)hwirq, irq, type);
-	return irq;
+	/* Set type if specified and different than the current one */
+	if (type != IRQ_TYPE_NONE &&
+	    type != (irqd_get_trigger_type(irq_get_irq_data(virq))))
+		irq_set_irq_type(virq, type);
+	return virq;
 }
 EXPORT_SYMBOL_GPL(irq_create_of_mapping);
 
 /**
- * irq_dispose_mapping() - Discard a mapping created by irq_create_of_mapping()
- * @irq: linux irq number to be discarded
+ * irq_dispose_mapping() - Unmap an interrupt
+ * @virq: linux irq number of the interrupt to unmap
+ */
+void irq_dispose_mapping(unsigned int virq)
+{
+	struct irq_data *irq_data = irq_get_irq_data(virq);
+	struct irq_domain *domain;
+	irq_hw_number_t hwirq;
+
+	if (!virq || !irq_data)
+		return;
+
+	domain = irq_data->domain;
+	if (WARN_ON(domain == NULL))
+		return;
+
+	/* Never unmap legacy interrupts */
+	if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY)
+		return;
+
+	irq_set_status_flags(virq, IRQ_NOREQUEST);
+
+	/* remove chip and handler */
+	irq_set_chip_and_handler(virq, NULL, NULL);
+
+	/* Make sure it's completed */
+	synchronize_irq(virq);
+
+	/* Tell the PIC about it */
+	if (domain->ops->unmap)
+		domain->ops->unmap(domain, virq);
+	smp_mb();
+
+	/* Clear reverse map */
+	hwirq = irq_data->hwirq;
+	switch(domain->revmap_type) {
+	case IRQ_DOMAIN_MAP_LINEAR:
+		if (hwirq < domain->revmap_data.linear.size)
+			domain->revmap_data.linear.revmap[hwirq] = 0;
+		break;
+	case IRQ_DOMAIN_MAP_TREE:
+		mutex_lock(&revmap_trees_mutex);
+		radix_tree_delete(&domain->revmap_data.tree, hwirq);
+		mutex_unlock(&revmap_trees_mutex);
+		break;
+	}
+
+	irq_free_desc(virq);
+}
+EXPORT_SYMBOL_GPL(irq_dispose_mapping);
+
+/**
+ * irq_find_mapping() - Find a linux irq from an hw irq number.
+ * @domain: domain owning this hardware interrupt
+ * @hwirq: hardware irq number in that domain space
+ *
+ * This is a slow path, for use by generic code. It's expected that an
+ * irq controller implementation directly calls the appropriate low level
+ * mapping function.
+ */
+unsigned int irq_find_mapping(struct irq_domain *domain,
+			      irq_hw_number_t hwirq)
+{
+	unsigned int i;
+	unsigned int hint = hwirq % irq_virq_count;
+
+	/* Look for default domain if nececssary */
+	if (domain == NULL)
+		domain = irq_default_domain;
+	if (domain == NULL)
+		return 0;
+
+	/* legacy -> bail early */
+	if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY)
+		return irq_domain_legacy_revmap(domain, hwirq);
+
+	/* Slow path does a linear search of the map */
+	if (hint == 0)
+		hint = 1;
+	i = hint;
+	do {
+		struct irq_data *data = irq_get_irq_data(i);
+		if (data && (data->domain == domain) && (data->hwirq == hwirq))
+			return i;
+		i++;
+		if (i >= irq_virq_count)
+			i = 1;
+	} while(i != hint);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_find_mapping);
+
+/**
+ * irq_radix_revmap_lookup() - Find a linux irq from a hw irq number.
+ * @domain: domain owning this hardware interrupt
+ * @hwirq: hardware irq number in that domain space
  *
- * Calling this function indicates the caller no longer needs a reference to
- * the linux irq number returned by a prior call to irq_create_of_mapping().
+ * This is a fast path, for use by irq controller code that uses radix tree
+ * revmaps
  */
-void irq_dispose_mapping(unsigned int irq)
+unsigned int irq_radix_revmap_lookup(struct irq_domain *domain,
+				     irq_hw_number_t hwirq)
 {
+	struct irq_data *irq_data;
+
+	if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_TREE))
+		return irq_find_mapping(domain, hwirq);
+
+	/*
+	 * Freeing an irq can delete nodes along the path to
+	 * do the lookup via call_rcu.
+	 */
+	rcu_read_lock();
+	irq_data = radix_tree_lookup(&domain->revmap_data.tree, hwirq);
+	rcu_read_unlock();
+
 	/*
-	 * nothing yet; will be filled when support for dynamic allocation of
-	 * irq_descs is added to irq_domain
+	 * If found in radix tree, then fine.
+	 * Else fallback to linear lookup - this should not happen in practice
+	 * as it means that we failed to insert the node in the radix tree.
 	 */
+	return irq_data ? irq_data->irq : irq_find_mapping(domain, hwirq);
 }
-EXPORT_SYMBOL_GPL(irq_dispose_mapping);
 
-int irq_domain_simple_dt_translate(struct irq_domain *d,
-			    struct device_node *controller,
-			    const u32 *intspec, unsigned int intsize,
-			    unsigned long *out_hwirq, unsigned int *out_type)
+/**
+ * irq_radix_revmap_insert() - Insert a hw irq to linux irq number mapping.
+ * @domain: domain owning this hardware interrupt
+ * @virq: linux irq number
+ * @hwirq: hardware irq number in that domain space
+ *
+ * This is for use by irq controllers that use a radix tree reverse
+ * mapping for fast lookup.
+ */
+void irq_radix_revmap_insert(struct irq_domain *domain, unsigned int virq,
+			     irq_hw_number_t hwirq)
 {
-	if (d->of_node != controller)
-		return -EINVAL;
-	if (intsize < 1)
-		return -EINVAL;
-	if (d->nr_irq && ((intspec[0] < d->hwirq_base) ||
-	    (intspec[0] >= d->hwirq_base + d->nr_irq)))
-		return -EINVAL;
+	struct irq_data *irq_data = irq_get_irq_data(virq);
+
+	if (WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_TREE))
+		return;
+
+	if (virq) {
+		mutex_lock(&revmap_trees_mutex);
+		radix_tree_insert(&domain->revmap_data.tree, hwirq, irq_data);
+		mutex_unlock(&revmap_trees_mutex);
+	}
+}
+
+/**
+ * irq_linear_revmap() - Find a linux irq from a hw irq number.
+ * @domain: domain owning this hardware interrupt
+ * @hwirq: hardware irq number in that domain space
+ *
+ * This is a fast path, for use by irq controller code that uses linear
+ * revmaps. It does fallback to the slow path if the revmap doesn't exist
+ * yet and will create the revmap entry with appropriate locking
+ */
+unsigned int irq_linear_revmap(struct irq_domain *domain,
+			       irq_hw_number_t hwirq)
+{
+	unsigned int *revmap;
+
+	if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_LINEAR))
+		return irq_find_mapping(domain, hwirq);
+
+	/* Check revmap bounds */
+	if (unlikely(hwirq >= domain->revmap_data.linear.size))
+		return irq_find_mapping(domain, hwirq);
+
+	/* Check if revmap was allocated */
+	revmap = domain->revmap_data.linear.revmap;
+	if (unlikely(revmap == NULL))
+		return irq_find_mapping(domain, hwirq);
+
+	/* Fill up revmap with slow path if no mapping found */
+	if (unlikely(!revmap[hwirq]))
+		revmap[hwirq] = irq_find_mapping(domain, hwirq);
+
+	return revmap[hwirq];
+}
+
+#ifdef CONFIG_IRQ_DOMAIN_DEBUG
+static int virq_debug_show(struct seq_file *m, void *private)
+{
+	unsigned long flags;
+	struct irq_desc *desc;
+	const char *p;
+	static const char none[] = "none";
+	void *data;
+	int i;
+
+	seq_printf(m, "%-5s  %-7s  %-15s  %-18s  %s\n", "virq", "hwirq",
+		      "chip name", "chip data", "domain name");
+
+	for (i = 1; i < nr_irqs; i++) {
+		desc = irq_to_desc(i);
+		if (!desc)
+			continue;
+
+		raw_spin_lock_irqsave(&desc->lock, flags);
+
+		if (desc->action && desc->action->handler) {
+			struct irq_chip *chip;
+
+			seq_printf(m, "%5d  ", i);
+			seq_printf(m, "0x%05lx  ", desc->irq_data.hwirq);
+
+			chip = irq_desc_get_chip(desc);
+			if (chip && chip->name)
+				p = chip->name;
+			else
+				p = none;
+			seq_printf(m, "%-15s  ", p);
+
+			data = irq_desc_get_chip_data(desc);
+			seq_printf(m, "0x%16p  ", data);
+
+			if (desc->irq_data.domain && desc->irq_data.domain->of_node)
+				p = desc->irq_data.domain->of_node->full_name;
+			else
+				p = none;
+			seq_printf(m, "%s\n", p);
+		}
+
+		raw_spin_unlock_irqrestore(&desc->lock, flags);
+	}
+
+	return 0;
+}
 
+static int virq_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, virq_debug_show, inode->i_private);
+}
+
+static const struct file_operations virq_debug_fops = {
+	.open = virq_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init irq_debugfs_init(void)
+{
+	if (debugfs_create_file("irq_domain_mapping", S_IRUGO, NULL,
+				 NULL, &virq_debug_fops) == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+__initcall(irq_debugfs_init);
+#endif /* CONFIG_IRQ_DOMAIN_DEBUG */
+
+int irq_domain_simple_map(struct irq_domain *d, unsigned int irq,
+			  irq_hw_number_t hwirq)
+{
+	return 0;
+}
+
+/**
+ * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings
+ *
+ * Device Tree IRQ specifier translation function which works with one cell
+ * bindings where the cell value maps directly to the hwirq number.
+ */
+int irq_domain_xlate_onecell(struct irq_domain *d, struct device_node *ctrlr,
+			     const u32 *intspec, unsigned int intsize,
+			     unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (WARN_ON(intsize < 1))
+		return -EINVAL;
 	*out_hwirq = intspec[0];
 	*out_type = IRQ_TYPE_NONE;
-	if (intsize > 1)
-		*out_type = intspec[1] & IRQ_TYPE_SENSE_MASK;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(irq_domain_xlate_onecell);
 
 /**
- * irq_domain_create_simple() - Set up a 'simple' translation range
+ * irq_domain_xlate_twocell() - Generic xlate for direct two cell bindings
+ *
+ * Device Tree IRQ specifier translation function which works with two cell
+ * bindings where the cell values map directly to the hwirq number
+ * and linux irq flags.
  */
-void irq_domain_add_simple(struct device_node *controller, int irq_base)
+int irq_domain_xlate_twocell(struct irq_domain *d, struct device_node *ctrlr,
+			const u32 *intspec, unsigned int intsize,
+			irq_hw_number_t *out_hwirq, unsigned int *out_type)
 {
-	struct irq_domain *domain;
-
-	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
-	if (!domain) {
-		WARN_ON(1);
-		return;
-	}
+	if (WARN_ON(intsize < 2))
+		return -EINVAL;
+	*out_hwirq = intspec[0];
+	*out_type = intspec[1] & IRQ_TYPE_SENSE_MASK;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_domain_xlate_twocell);
 
-	domain->irq_base = irq_base;
-	domain->of_node = of_node_get(controller);
-	domain->ops = &irq_domain_simple_ops;
-	irq_domain_add(domain);
+/**
+ * irq_domain_xlate_onetwocell() - Generic xlate for one or two cell bindings
+ *
+ * Device Tree IRQ specifier translation function which works with either one
+ * or two cell bindings where the cell values map directly to the hwirq number
+ * and linux irq flags.
+ *
+ * Note: don't use this function unless your interrupt controller explicitly
+ * supports both one and two cell bindings.  For the majority of controllers
+ * the _onecell() or _twocell() variants above should be used.
+ */
+int irq_domain_xlate_onetwocell(struct irq_domain *d,
+				struct device_node *ctrlr,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq, unsigned int *out_type)
+{
+	if (WARN_ON(intsize < 1))
+		return -EINVAL;
+	*out_hwirq = intspec[0];
+	*out_type = (intsize > 1) ? intspec[1] : IRQ_TYPE_NONE;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(irq_domain_add_simple);
+EXPORT_SYMBOL_GPL(irq_domain_xlate_onetwocell);
 
+const struct irq_domain_ops irq_domain_simple_ops = {
+	.map = irq_domain_simple_map,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
+
+#ifdef CONFIG_OF_IRQ
 void irq_domain_generate_simple(const struct of_device_id *match,
 				u64 phys_base, unsigned int irq_start)
 {
 	struct device_node *node;
-	pr_info("looking for phys_base=%llx, irq_start=%i\n",
+	pr_debug("looking for phys_base=%llx, irq_start=%i\n",
 		(unsigned long long) phys_base, (int) irq_start);
 	node = of_find_matching_node_by_address(NULL, match, phys_base);
 	if (node)
-		irq_domain_add_simple(node, irq_start);
-	else
-		pr_info("no node found\n");
+		irq_domain_add_legacy(node, 32, irq_start, 0,
+				      &irq_domain_simple_ops, NULL);
 }
 EXPORT_SYMBOL_GPL(irq_domain_generate_simple);
-#endif /* CONFIG_OF_IRQ */
-
-struct irq_domain_ops irq_domain_simple_ops = {
-#ifdef CONFIG_OF_IRQ
-	.dt_translate = irq_domain_simple_dt_translate,
-#endif /* CONFIG_OF_IRQ */
-};
-EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
+#endif
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a9a9dbe49fea..89a3ea82569b 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -282,7 +282,7 @@ 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 ret, node = desc->irq_data.node;
 
 	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
@@ -301,6 +301,13 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 	}
 
 	cpumask_and(mask, cpu_online_mask, set);
+	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);
+	}
 	ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
@@ -645,7 +652,7 @@ 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;
@@ -679,7 +686,7 @@ 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;
@@ -739,7 +746,7 @@ 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;
 }
@@ -755,10 +762,17 @@ 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) &&
+	    waitqueue_active(&desc->wait_for_threads))
+		wake_up(&desc->wait_for_threads);
+}
+
 /*
  * Interrupt handler thread
  */
@@ -771,57 +785,41 @@ static int irq_thread(void *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;
+	current->irq_thread = 1;
 
 	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 (!noirqdebug)
+			note_interrupt(action->irq, desc, action_ret);
 
-		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
+	 * 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.
+	 *
+	 * Clear irq_thread. Otherwise exit_irq_thread() would make
 	 * fuzz about an active irq thread going into nirvana.
 	 */
-	current->irqaction = NULL;
+	current->irq_thread = 0;
 	return 0;
 }
 
@@ -832,27 +830,28 @@ void exit_irq_thread(void)
 {
 	struct task_struct *tsk = current;
 	struct irq_desc *desc;
+	struct irqaction *action;
 
-	if (!tsk->irqaction)
+	if (!tsk->irq_thread)
 		return;
 
+	action = kthread_data(tsk);
+
 	printk(KERN_ERR
 	       "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
-	       tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq);
+	       tsk->comm ? tsk->comm : "", tsk->pid, action->irq);
 
-	desc = irq_to_desc(tsk->irqaction->irq);
+	desc = irq_to_desc(action->irq);
 
 	/*
-	 * Prevent a stale desc->threads_oneshot. Must be called
-	 * before setting the IRQTF_DIED flag.
+	 * If IRQTF_RUNTHREAD is set, we need to decrement
+	 * desc->threads_active and wake possible waiters.
 	 */
-	irq_finalize_oneshot(desc, tsk->irqaction, true);
+	if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags))
+		wake_threads_waitq(desc);
 
-	/*
-	 * Set the THREAD DIED flag to prevent further wakeups of the
-	 * soon to be gone threaded handler.
-	 */
-	set_bit(IRQTF_DIED, &tsk->irqaction->flags);
+	/* Prevent a stale desc->threads_oneshot */
+	irq_finalize_oneshot(desc, action);
 }
 
 static void irq_setup_forced_threading(struct irqaction *new)
@@ -985,6 +984,11 @@ __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;
@@ -993,14 +997,41 @@ __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;
-		goto out_mask;
+	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);
 	}
-	new->thread_mask = 1 << ffz(thread_mask);
 
 	if (!shared) {
 		init_waitqueue_head(&desc->wait_for_threads);
@@ -1027,7 +1058,7 @@ __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;
@@ -1103,8 +1134,7 @@ 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:
@@ -1214,8 +1244,7 @@ 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);
 	}
 
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 47420908fba0..c3c89751b327 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -43,12 +43,16 @@ void irq_move_masked_irq(struct irq_data *idata)
 	 * masking the irqs.
 	 */
 	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
-		   < nr_cpu_ids))
-		if (!chip->irq_set_affinity(&desc->irq_data,
-					    desc->pending_mask, false)) {
+		   < nr_cpu_ids)) {
+		int ret = chip->irq_set_affinity(&desc->irq_data,
+						 desc->pending_mask, false);
+		switch (ret) {
+		case IRQ_SET_MASK_OK:
 			cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
+		case IRQ_SET_MASK_OK_NOCOPY:
 			irq_set_thread_affinity(desc);
 		}
+	}
 
 	cpumask_clear(desc->pending_mask);
 }