Merge tag 'irq-core-2021-04-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq updates from Thomas Gleixner:
 "The usual updates from the irq departement:

  Core changes:

   - Provide IRQF_NO_AUTOEN as a flag for request*_irq() so drivers can
     be cleaned up which either use a seperate mechanism to prevent
     auto-enable at request time or have a racy mechanism which disables
     the interrupt right after request.

   - Get rid of the last usage of irq_create_identity_mapping() and
     remove the interface.

   - An overhaul of tasklet_disable().

     Most usage sites of tasklet_disable() are in task context and
     usually in cleanup, teardown code pathes. tasklet_disable()
     spinwaits for a tasklet which is currently executed. That's not
     only a problem for PREEMPT_RT where this can lead to a live lock
     when the disabling task preempts the softirq thread. It's also
     problematic in context of virtualization when the vCPU which runs
     the tasklet is scheduled out and the disabling code has to spin
     wait until it's scheduled back in.

     There are a few code pathes which invoke tasklet_disable() from
     non-sleepable context. For these a new disable variant which still
     spinwaits is provided which allows to switch tasklet_disable() to a
     sleep wait mechanism. For the atomic use cases this does not solve
     the live lock issue on PREEMPT_RT. That is mitigated by blocking on
     the RT specific softirq lock.

   - The PREEMPT_RT specific implementation of softirq processing and
     local_bh_disable/enable().

     On RT enabled kernels soft interrupt processing happens always in
     task context and all interrupt handlers, which are not explicitly
     marked to be invoked in hard interrupt context are forced into task
     context as well. This allows to protect against softirq processing
     with a per CPU lock, which in turn allows to make BH disabled
     regions preemptible.

     Most of the softirq handling code is still shared. The RT/non-RT
     specific differences are addressed with a set of inline functions
     which provide the context specific functionality. The
     local_bh_disable() / local_bh_enable() mechanism are obviously
     seperate.

   - The usual set of small improvements and cleanups

  Driver changes:

   - New drivers for Nuvoton WPCM450 and DT 79rc3243x interrupt
     controllers

   - Extended functionality for MStar, STM32 and SC7280 irq chips

   - Enhanced robustness for ARM GICv3/4.1 drivers

   - The usual set of cleanups and improvements all over the place"

* tag 'irq-core-2021-04-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  irqchip/xilinx: Expose Kconfig option for Zynq/ZynqMP
  irqchip/gic-v3: Do not enable irqs when handling spurious interrups
  dt-bindings: interrupt-controller: Add IDT 79RC3243x Interrupt Controller
  irqchip: Add support for IDT 79rc3243x interrupt controller
  irqdomain: Drop references to recusive irqdomain setup
  irqdomain: Get rid of irq_create_strict_mappings()
  irqchip/jcore-aic: Kill use of irq_create_strict_mappings()
  ARM: PXA: Kill use of irq_create_strict_mappings()
  irqchip/gic-v4.1: Disable vSGI upon (GIC CPUIF < v4.1) detection
  irqchip/tb10x: Use 'fallthrough' to eliminate a warning
  genirq: Reduce irqdebug cacheline bouncing
  kernel: Initialize cpumask before parsing
  irqchip/wpcm450: Drop COMPILE_TEST
  irqchip/irq-mst: Support polarity configuration
  irqchip: Add driver for WPCM450 interrupt controller
  dt-bindings: interrupt-controller: Add nuvoton, wpcm450-aic
  dt-bindings: qcom,pdc: Add compatible for sc7280
  irqchip/stm32: Add usart instances exti direct event support
  irqchip/gic-v3: Fix OF_BAD_ADDR error handling
  irqchip/sifive-plic: Mark two global variables __ro_after_init
  ...

19 files changed, 360 insertions, 157 deletions

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 6d89e33fe3aa..8cc8e5713287 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -761,7 +761,7 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_nmi);
  *	handle_edge_irq - edge type IRQ handler
  *	@desc:	the interrupt description structure for this irq
  *
- *	Interrupt occures on the falling and/or rising edge of a hardware
+ *	Interrupt occurs on the falling and/or rising edge of a hardware
  *	signal. The occurrence is latched into the irq controller hardware
  *	and must be acked in order to be reenabled. After the ack another
  *	interrupt can happen on the same source even before the first one
@@ -808,7 +808,7 @@ void handle_edge_irq(struct irq_desc *desc)
 		/*
 		 * When another irq arrived while we were handling
 		 * one, we could have masked the irq.
-		 * Renable it, if it was not disabled in meantime.
+		 * Reenable it, if it was not disabled in meantime.
 		 */
 		if (unlikely(desc->istate & IRQS_PENDING)) {
 			if (!irqd_irq_disabled(&desc->irq_data) &&
@@ -1419,7 +1419,7 @@ EXPORT_SYMBOL_GPL(irq_chip_eoi_parent);
  * @dest:	The affinity mask to set
  * @force:	Flag to enforce setting (disable online checks)
  *
- * Conditinal, as the underlying parent chip might not implement it.
+ * Conditional, as the underlying parent chip might not implement it.
  */
 int irq_chip_set_affinity_parent(struct irq_data *data,
 				 const struct cpumask *dest, bool force)
@@ -1531,7 +1531,7 @@ EXPORT_SYMBOL_GPL(irq_chip_release_resources_parent);
 #endif
 
 /**
- * irq_chip_compose_msi_msg - Componse msi message for a irq chip
+ * irq_chip_compose_msi_msg - Compose msi message for a irq chip
  * @data:	Pointer to interrupt specific data
  * @msg:	Pointer to the MSI message
  *
diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c
index 0b0cdf206dc4..7fe6cffe7d0d 100644
--- a/kernel/irq/dummychip.c
+++ b/kernel/irq/dummychip.c
@@ -13,7 +13,7 @@
 
 /*
  * What should we do if we get a hw irq event on an illegal vector?
- * Each architecture has to answer this themself.
+ * Each architecture has to answer this themselves.
  */
 static void ack_bad(struct irq_data *data)
 {
diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c
index 43e3d1be622c..52f11c791bf8 100644
--- a/kernel/irq/ipi.c
+++ b/kernel/irq/ipi.c
@@ -107,7 +107,7 @@ free_descs:
  * @irq:	linux irq number to be destroyed
  * @dest:	cpumask of cpus which should have the IPI removed
  *
- * The IPIs allocated with irq_reserve_ipi() are retuerned to the system
+ * The IPIs allocated with irq_reserve_ipi() are returned to the system
  * destroying all virqs associated with them.
  *
  * Return 0 on success or error code on failure.
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index 40880c350b95..0cd02efa3a74 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -24,10 +24,6 @@ struct irq_sim_irq_ctx {
 	struct irq_sim_work_ctx	*work_ctx;
 };
 
-struct irq_sim_devres {
-	struct irq_domain	*domain;
-};
-
 static void irq_sim_irqmask(struct irq_data *data)
 {
 	struct irq_sim_irq_ctx *irq_ctx = irq_data_get_irq_chip_data(data);
@@ -216,11 +212,11 @@ void irq_domain_remove_sim(struct irq_domain *domain)
 }
 EXPORT_SYMBOL_GPL(irq_domain_remove_sim);
 
-static void devm_irq_domain_release_sim(struct device *dev, void *res)
+static void devm_irq_domain_remove_sim(void *data)
 {
-	struct irq_sim_devres *this = res;
+	struct irq_domain *domain = data;
 
-	irq_domain_remove_sim(this->domain);
+	irq_domain_remove_sim(domain);
 }
 
 /**
@@ -238,20 +234,17 @@ struct irq_domain *devm_irq_domain_create_sim(struct device *dev,
 					      struct fwnode_handle *fwnode,
 					      unsigned int num_irqs)
 {
-	struct irq_sim_devres *dr;
+	struct irq_domain *domain;
+	int ret;
 
-	dr = devres_alloc(devm_irq_domain_release_sim,
-			  sizeof(*dr), GFP_KERNEL);
-	if (!dr)
-		return ERR_PTR(-ENOMEM);
+	domain = irq_domain_create_sim(fwnode, num_irqs);
+	if (IS_ERR(domain))
+		return domain;
 
-	dr->domain = irq_domain_create_sim(fwnode, num_irqs);
-	if (IS_ERR(dr->domain)) {
-		devres_free(dr);
-		return dr->domain;
-	}
+	ret = devm_add_action_or_reset(dev, devm_irq_domain_remove_sim, domain);
+	if (ret)
+		return ERR_PTR(ret);
 
-	devres_add(dev, dr);
-	return dr->domain;
+	return domain;
 }
 EXPORT_SYMBOL_GPL(devm_irq_domain_create_sim);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index cc1a09406c6e..4a617d7312a4 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -31,7 +31,7 @@ static int __init irq_affinity_setup(char *str)
 	cpulist_parse(str, irq_default_affinity);
 	/*
 	 * Set at least the boot cpu. We don't want to end up with
-	 * bugreports caused by random comandline masks
+	 * bugreports caused by random commandline masks
 	 */
 	cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
 	return 1;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index d10ab1d689d5..f42ef868efd3 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -62,7 +62,7 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops);
  * @name:	Optional user provided domain name
  * @pa:		Optional user-provided physical address
  *
- * Allocate a struct irqchip_fwid, and return a poiner to the embedded
+ * Allocate a struct irqchip_fwid, and return a pointer to the embedded
  * fwnode_handle (or NULL on failure).
  *
  * Note: The types IRQCHIP_FWNODE_NAMED and IRQCHIP_FWNODE_NAMED_ID are
@@ -665,7 +665,7 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
 
 	pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
 
-	/* Look for default domain if nececssary */
+	/* Look for default domain if necessary */
 	if (domain == NULL)
 		domain = irq_default_domain;
 	if (domain == NULL) {
@@ -703,41 +703,6 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
 }
 EXPORT_SYMBOL_GPL(irq_create_mapping_affinity);
 
-/**
- * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs
- * @domain: domain owning the interrupt range
- * @irq_base: beginning of linux IRQ range
- * @hwirq_base: beginning of hardware IRQ range
- * @count: Number of interrupts to map
- *
- * This routine is used for allocating and mapping a range of hardware
- * irqs to linux irqs where the linux irq numbers are at pre-defined
- * locations. For use by controllers that already have static mappings
- * to insert in to the domain.
- *
- * Non-linear users can use irq_create_identity_mapping() for IRQ-at-a-time
- * domain insertion.
- *
- * 0 is returned upon success, while any failure to establish a static
- * mapping is treated as an error.
- */
-int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base,
-			       irq_hw_number_t hwirq_base, int count)
-{
-	struct device_node *of_node;
-	int ret;
-
-	of_node = irq_domain_get_of_node(domain);
-	ret = irq_alloc_descs(irq_base, irq_base, count,
-			      of_node_to_nid(of_node));
-	if (unlikely(ret < 0))
-		return ret;
-
-	irq_domain_associate_many(domain, irq_base, hwirq_base, count);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(irq_create_strict_mappings);
-
 static int irq_domain_translate(struct irq_domain *d,
 				struct irq_fwspec *fwspec,
 				irq_hw_number_t *hwirq, unsigned int *type)
@@ -906,7 +871,7 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
 {
 	struct irq_data *data;
 
-	/* Look for default domain if nececssary */
+	/* Look for default domain if necessary */
 	if (domain == NULL)
 		domain = irq_default_domain;
 	if (domain == NULL)
@@ -1436,7 +1401,7 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
  * The whole process to setup an IRQ has been split into two steps.
  * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ
  * descriptor and required hardware resources. The second step,
- * irq_domain_activate_irq(), is to program hardwares with preallocated
+ * irq_domain_activate_irq(), is to program the hardware with preallocated
  * resources. In this way, it's easier to rollback when failing to
  * allocate resources.
  */
@@ -1694,12 +1659,10 @@ void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs)
 
 /**
  * irq_domain_alloc_irqs_parent - Allocate interrupts from parent domain
+ * @domain:	Domain below which interrupts must be allocated
  * @irq_base:	Base IRQ number
  * @nr_irqs:	Number of IRQs to allocate
  * @arg:	Allocation data (arch/domain specific)
- *
- * Check whether the domain has been setup recursive. If not allocate
- * through the parent domain.
  */
 int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
 				 unsigned int irq_base, unsigned int nr_irqs,
@@ -1715,11 +1678,9 @@ EXPORT_SYMBOL_GPL(irq_domain_alloc_irqs_parent);
 
 /**
  * irq_domain_free_irqs_parent - Free interrupts from parent domain
+ * @domain:	Domain below which interrupts must be freed
  * @irq_base:	Base IRQ number
  * @nr_irqs:	Number of IRQs to free
- *
- * Check whether the domain has been setup recursive. If not free
- * through the parent domain.
  */
 void irq_domain_free_irqs_parent(struct irq_domain *domain,
 				 unsigned int irq_base, unsigned int nr_irqs)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 21ea370fccda..4c14356543d9 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -179,7 +179,7 @@ bool irq_can_set_affinity_usr(unsigned int irq)
 
 /**
  *	irq_set_thread_affinity - Notify irq threads to adjust affinity
- *	@desc:		irq descriptor which has affitnity changed
+ *	@desc:		irq descriptor which has affinity changed
  *
  *	We just set IRQTF_AFFINITY and delegate the affinity setting
  *	to the interrupt thread itself. We can not call
@@ -326,7 +326,7 @@ static bool irq_set_affinity_deactivated(struct irq_data *data,
 	 * If the interrupt is not yet activated, just store the affinity
 	 * mask and do not call the chip driver at all. On activation the
 	 * driver has to make sure anyway that the interrupt is in a
-	 * useable state so startup works.
+	 * usable state so startup works.
 	 */
 	if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
 	    irqd_is_activated(data) || !irqd_affinity_on_activate(data))
@@ -1054,7 +1054,7 @@ again:
 	 * to IRQS_INPROGRESS and the irq line is masked forever.
 	 *
 	 * This also serializes the state of shared oneshot handlers
-	 * versus "desc->threads_onehsot |= action->thread_mask;" in
+	 * versus "desc->threads_oneshot |= action->thread_mask;" in
 	 * irq_wake_thread(). See the comment there which explains the
 	 * serialization.
 	 */
@@ -1157,7 +1157,7 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 
 /*
  * Interrupts explicitly requested as threaded interrupts want to be
- * preemtible - many of them need to sleep and wait for slow busses to
+ * preemptible - many of them need to sleep and wait for slow busses to
  * complete.
  */
 static irqreturn_t irq_thread_fn(struct irq_desc *desc,
@@ -1697,7 +1697,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 			irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
 		}
 
-		if (irq_settings_can_autoenable(desc)) {
+		if (!(new->flags & IRQF_NO_AUTOEN) &&
+		    irq_settings_can_autoenable(desc)) {
 			irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
 		} else {
 			/*
@@ -1912,7 +1913,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	/* Last action releases resources */
 	if (!desc->action) {
 		/*
-		 * Reaquire bus lock as irq_release_resources() might
+		 * Reacquire bus lock as irq_release_resources() might
 		 * require it to deallocate resources over the slow bus.
 		 */
 		chip_bus_lock(desc);
@@ -2090,10 +2091,15 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	 * which interrupt is which (messes up the interrupt freeing
 	 * logic etc).
 	 *
+	 * Also shared interrupts do not go well with disabling auto enable.
+	 * The sharing interrupt might request it while it's still disabled
+	 * and then wait for interrupts forever.
+	 *
 	 * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
 	 * it cannot be set along with IRQF_NO_SUSPEND.
 	 */
 	if (((irqflags & IRQF_SHARED) && !dev_id) ||
+	    ((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) ||
 	    (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
 	    ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
 		return -EINVAL;
@@ -2249,7 +2255,8 @@ int request_nmi(unsigned int irq, irq_handler_t handler,
 
 	desc = irq_to_desc(irq);
 
-	if (!desc || irq_settings_can_autoenable(desc) ||
+	if (!desc || (irq_settings_can_autoenable(desc) &&
+	    !(irqflags & IRQF_NO_AUTOEN)) ||
 	    !irq_settings_can_request(desc) ||
 	    WARN_ON(irq_settings_is_per_cpu_devid(desc)) ||
 	    !irq_supports_nmi(desc))
@@ -2746,7 +2753,7 @@ int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which,
  *	irq_get_irqchip_state - returns the irqchip state of a interrupt.
  *	@irq: Interrupt line that is forwarded to a VM
  *	@which: One of IRQCHIP_STATE_* the caller wants to know about
- *	@state: a pointer to a boolean where the state is to be storeed
+ *	@state: a pointer to a boolean where the state is to be stored
  *
  *	This call snapshots the internal irqchip state of an
  *	interrupt, returning into @state the bit corresponding to
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 651a4ad6d711..578596e41cb6 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -337,15 +337,14 @@ void irq_matrix_assign(struct irq_matrix *m, unsigned int bit)
  * irq_matrix_reserve - Reserve interrupts
  * @m:		Matrix pointer
  *
- * This is merily a book keeping call. It increments the number of globally
+ * This is merely a book keeping call. It increments the number of globally
  * reserved interrupt bits w/o actually allocating them. This allows to
  * setup interrupt descriptors w/o assigning low level resources to it.
  * The actual allocation happens when the interrupt gets activated.
  */
 void irq_matrix_reserve(struct irq_matrix *m)
 {
-	if (m->global_reserved <= m->global_available &&
-	    m->global_reserved + 1 > m->global_available)
+	if (m->global_reserved == m->global_available)
 		pr_warn("Interrupt reservation exceeds available resources\n");
 
 	m->global_reserved++;
@@ -356,7 +355,7 @@ void irq_matrix_reserve(struct irq_matrix *m)
  * irq_matrix_remove_reserved - Remove interrupt reservation
  * @m:		Matrix pointer
  *
- * This is merily a book keeping call. It decrements the number of globally
+ * This is merely a book keeping call. It decrements the number of globally
  * reserved interrupt bits. This is used to undo irq_matrix_reserve() when the
  * interrupt was never in use and a real vector allocated, which undid the
  * reservation.
@@ -423,7 +422,9 @@ void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
 	if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
 		return;
 
-	clear_bit(bit, cm->alloc_map);
+	if (WARN_ON_ONCE(!test_and_clear_bit(bit, cm->alloc_map)))
+		return;
+
 	cm->allocated--;
 	if(managed)
 		cm->managed_allocated--;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index def48589ea48..61ca924ef4b4 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,7 +7,7 @@
 
 /**
  * irq_fixup_move_pending - Cleanup irq move pending from a dying CPU
- * @desc:		Interrupt descpriptor to clean up
+ * @desc:		Interrupt descriptor to clean up
  * @force_clear:	If set clear the move pending bit unconditionally.
  *			If not set, clear it only when the dying CPU is the
  *			last one in the pending mask.
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index b338d622f26e..c41965e348b5 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -5,7 +5,7 @@
  *
  * This file is licensed under GPLv2.
  *
- * This file contains common code to support Message Signalled Interrupt for
+ * This file contains common code to support Message Signaled Interrupts for
  * PCI compatible and non PCI compatible devices.
  */
 #include <linux/types.h>
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 98138788cb04..7c5cd42df3b9 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -144,7 +144,7 @@ static ssize_t write_irq_affinity(int type, struct file *file,
 	if (!irq_can_set_affinity_usr(irq) || no_irq_affinity)
 		return -EIO;
 
-	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
 		return -ENOMEM;
 
 	if (type)
@@ -238,7 +238,7 @@ static ssize_t default_affinity_write(struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
 		return -ENOMEM;
 
 	err = cpumask_parse_user(buffer, count, new_value);
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index bd1d85c610aa..0c46e9fe3a89 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -128,7 +128,7 @@ int check_irq_resend(struct irq_desc *desc, bool inject)
 	if (!try_retrigger(desc))
 		err = irq_sw_resend(desc);
 
-	/* If the retrigger was successfull, mark it with the REPLAY bit */
+	/* If the retrigger was successful, mark it with the REPLAY bit */
 	if (!err)
 		desc->istate |= IRQS_REPLAY;
 	return err;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index f865e5f4d382..c481d8458325 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -403,6 +403,10 @@ void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret)
 			desc->irqs_unhandled -= ok;
 	}
 
+	if (likely(!desc->irqs_unhandled))
+		return;
+
+	/* Now getting into unhandled irq detection */
 	desc->irq_count++;
 	if (likely(desc->irq_count < 100000))
 		return;
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index 773b6105c4ae..d309d6fbf5bd 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -84,7 +84,7 @@ void irq_timings_disable(void)
  * 2. Log interval
  *
  * We saw the irq timings allow to compute the interval of the
- * occurrences for a specific interrupt. We can reasonibly assume the
+ * occurrences for a specific interrupt. We can reasonably assume the
  * longer is the interval, the higher is the error for the next event
  * and we can consider storing those interval values into an array
  * where each slot in the array correspond to an interval at the power
@@ -416,7 +416,7 @@ static u64 __irq_timings_next_event(struct irqt_stat *irqs, int irq, u64 now)
 	 * Copy the content of the circular buffer into another buffer
 	 * in order to linearize the buffer instead of dealing with
 	 * wrapping indexes and shifted array which will be prone to
-	 * error and extremelly difficult to debug.
+	 * error and extremely difficult to debug.
 	 */
 	for (i = 0; i < count; i++) {
 		int index = (start + i) & IRQ_TIMINGS_MASK;
@@ -485,7 +485,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts)
 
 	/*
 	 * The interrupt triggered more than one second apart, that
-	 * ends the sequence as predictible for our purpose. In this
+	 * ends the sequence as predictable for our purpose. In this
 	 * case, assume we have the beginning of a sequence and the
 	 * timestamp is the first value. As it is impossible to
 	 * predict anything at this point, return.
@@ -514,7 +514,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts)
  *      If more than the array size interrupts happened during the
  *      last busy/idle cycle, the index wrapped up and we have to
  *      begin with the next element in the array which is the last one
- *      in the sequence, otherwise it is a the index 0.
+ *      in the sequence, otherwise it is at the index 0.
  *
  * - have an indication of the interrupts activity on this CPU
  *   (eg. irq/sec)
diff --git a/kernel/profile.c b/kernel/profile.c
index 6f69a4195d56..c2ebddb5e974 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -430,7 +430,7 @@ static ssize_t prof_cpu_mask_proc_write(struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
 		return -ENOMEM;
 
 	err = cpumask_parse_user(buffer, count, new_value);
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5f611658eeab..2c36a5fad589 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -60,7 +60,7 @@ void irqtime_account_irq(struct task_struct *curr, unsigned int offset)
 	cpu = smp_processor_id();
 	delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
 	irqtime->irq_start_time += delta;
-	pc = preempt_count() - offset;
+	pc = irq_count() - offset;
 
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
@@ -421,7 +421,7 @@ void vtime_task_switch(struct task_struct *prev)
 
 void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
 {
-	unsigned int pc = preempt_count() - offset;
+	unsigned int pc = irq_count() - offset;
 
 	if (pc & HARDIRQ_OFFSET) {
 		vtime_account_hardirq(tsk);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 9908ec4a9bfe..5a99696da86a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -13,6 +13,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
+#include <linux/local_lock.h>
 #include <linux/mm.h>
 #include <linux/notifier.h>
 #include <linux/percpu.h>
@@ -25,6 +26,7 @@
 #include <linux/smpboot.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
+#include <linux/wait_bit.h>
 
 #include <asm/softirq_stack.h>
 
@@ -102,20 +104,204 @@ EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
 #endif
 
 /*
- * preempt_count and SOFTIRQ_OFFSET usage:
- * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
- *   softirq processing.
- * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ * SOFTIRQ_OFFSET usage:
+ *
+ * On !RT kernels 'count' is the preempt counter, on RT kernels this applies
+ * to a per CPU counter and to task::softirqs_disabled_cnt.
+ *
+ * - count is changed by SOFTIRQ_OFFSET on entering or leaving softirq
+ *   processing.
+ *
+ * - count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
  *   on local_bh_disable or local_bh_enable.
+ *
  * This lets us distinguish between whether we are currently processing
  * softirq and whether we just have bh disabled.
  */
+#ifdef CONFIG_PREEMPT_RT
+
+/*
+ * RT accounts for BH disabled sections in task::softirqs_disabled_cnt and
+ * also in per CPU softirq_ctrl::cnt. This is necessary to allow tasks in a
+ * softirq disabled section to be preempted.
+ *
+ * The per task counter is used for softirq_count(), in_softirq() and
+ * in_serving_softirqs() because these counts are only valid when the task
+ * holding softirq_ctrl::lock is running.
+ *
+ * The per CPU counter prevents pointless wakeups of ksoftirqd in case that
+ * the task which is in a softirq disabled section is preempted or blocks.
+ */
+struct softirq_ctrl {
+	local_lock_t	lock;
+	int		cnt;
+};
+
+static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
+	.lock	= INIT_LOCAL_LOCK(softirq_ctrl.lock),
+};
+
+/**
+ * local_bh_blocked() - Check for idle whether BH processing is blocked
+ *
+ * Returns false if the per CPU softirq::cnt is 0 otherwise true.
+ *
+ * This is invoked from the idle task to guard against false positive
+ * softirq pending warnings, which would happen when the task which holds
+ * softirq_ctrl::lock was the only running task on the CPU and blocks on
+ * some other lock.
+ */
+bool local_bh_blocked(void)
+{
+	return __this_cpu_read(softirq_ctrl.cnt) != 0;
+}
+
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+	unsigned long flags;
+	int newcnt;
+
+	WARN_ON_ONCE(in_hardirq());
+
+	/* First entry of a task into a BH disabled section? */
+	if (!current->softirq_disable_cnt) {
+		if (preemptible()) {
+			local_lock(&softirq_ctrl.lock);
+			/* Required to meet the RCU bottomhalf requirements. */
+			rcu_read_lock();
+		} else {
+			DEBUG_LOCKS_WARN_ON(this_cpu_read(softirq_ctrl.cnt));
+		}
+	}
+
+	/*
+	 * Track the per CPU softirq disabled state. On RT this is per CPU
+	 * state to allow preemption of bottom half disabled sections.
+	 */
+	newcnt = __this_cpu_add_return(softirq_ctrl.cnt, cnt);
+	/*
+	 * Reflect the result in the task state to prevent recursion on the
+	 * local lock and to make softirq_count() & al work.
+	 */
+	current->softirq_disable_cnt = newcnt;
+
+	if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && newcnt == cnt) {
+		raw_local_irq_save(flags);
+		lockdep_softirqs_off(ip);
+		raw_local_irq_restore(flags);
+	}
+}
+EXPORT_SYMBOL(__local_bh_disable_ip);
+
+static void __local_bh_enable(unsigned int cnt, bool unlock)
+{
+	unsigned long flags;
+	int newcnt;
+
+	DEBUG_LOCKS_WARN_ON(current->softirq_disable_cnt !=
+			    this_cpu_read(softirq_ctrl.cnt));
+
+	if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && softirq_count() == cnt) {
+		raw_local_irq_save(flags);
+		lockdep_softirqs_on(_RET_IP_);
+		raw_local_irq_restore(flags);
+	}
+
+	newcnt = __this_cpu_sub_return(softirq_ctrl.cnt, cnt);
+	current->softirq_disable_cnt = newcnt;
+
+	if (!newcnt && unlock) {
+		rcu_read_unlock();
+		local_unlock(&softirq_ctrl.lock);
+	}
+}
+
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
+{
+	bool preempt_on = preemptible();
+	unsigned long flags;
+	u32 pending;
+	int curcnt;
+
+	WARN_ON_ONCE(in_irq());
+	lockdep_assert_irqs_enabled();
+
+	local_irq_save(flags);
+	curcnt = __this_cpu_read(softirq_ctrl.cnt);
+
+	/*
+	 * If this is not reenabling soft interrupts, no point in trying to
+	 * run pending ones.
+	 */
+	if (curcnt != cnt)
+		goto out;
+
+	pending = local_softirq_pending();
+	if (!pending || ksoftirqd_running(pending))
+		goto out;
+
+	/*
+	 * If this was called from non preemptible context, wake up the
+	 * softirq daemon.
+	 */
+	if (!preempt_on) {
+		wakeup_softirqd();
+		goto out;
+	}
+
+	/*
+	 * Adjust softirq count to SOFTIRQ_OFFSET which makes
+	 * in_serving_softirq() become true.
+	 */
+	cnt = SOFTIRQ_OFFSET;
+	__local_bh_enable(cnt, false);
+	__do_softirq();
+
+out:
+	__local_bh_enable(cnt, preempt_on);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__local_bh_enable_ip);
+
+/*
+ * Invoked from ksoftirqd_run() outside of the interrupt disabled section
+ * to acquire the per CPU local lock for reentrancy protection.
+ */
+static inline void ksoftirqd_run_begin(void)
+{
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+	local_irq_disable();
+}
+
+/* Counterpart to ksoftirqd_run_begin() */
+static inline void ksoftirqd_run_end(void)
+{
+	__local_bh_enable(SOFTIRQ_OFFSET, true);
+	WARN_ON_ONCE(in_interrupt());
+	local_irq_enable();
+}
+
+static inline void softirq_handle_begin(void) { }
+static inline void softirq_handle_end(void) { }
+
+static inline bool should_wake_ksoftirqd(void)
+{
+	return !this_cpu_read(softirq_ctrl.cnt);
+}
+
+static inline void invoke_softirq(void)
+{
+	if (should_wake_ksoftirqd())
+		wakeup_softirqd();
+}
+
+#else /* CONFIG_PREEMPT_RT */
 
-#ifdef CONFIG_TRACE_IRQFLAGS
 /*
- * This is for softirq.c-internal use, where hardirqs are disabled
+ * This one is for softirq.c-internal use, where hardirqs are disabled
  * legitimately:
  */
+#ifdef CONFIG_TRACE_IRQFLAGS
 void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 {
 	unsigned long flags;
@@ -206,6 +392,32 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
 }
 EXPORT_SYMBOL(__local_bh_enable_ip);
 
+static inline void softirq_handle_begin(void)
+{
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+}
+
+static inline void softirq_handle_end(void)
+{
+	__local_bh_enable(SOFTIRQ_OFFSET);
+	WARN_ON_ONCE(in_interrupt());
+}
+
+static inline void ksoftirqd_run_begin(void)
+{
+	local_irq_disable();
+}
+
+static inline void ksoftirqd_run_end(void)
+{
+	local_irq_enable();
+}
+
+static inline bool should_wake_ksoftirqd(void)
+{
+	return true;
+}
+
 static inline void invoke_softirq(void)
 {
 	if (ksoftirqd_running(local_softirq_pending()))
@@ -250,6 +462,8 @@ asmlinkage __visible void do_softirq(void)
 	local_irq_restore(flags);
 }
 
+#endif /* !CONFIG_PREEMPT_RT */
+
 /*
  * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
  * but break the loop if need_resched() is set or after 2 ms.
@@ -318,7 +532,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 
 	pending = local_softirq_pending();
 
-	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+	softirq_handle_begin();
 	in_hardirq = lockdep_softirq_start();
 	account_softirq_enter(current);
 
@@ -354,8 +568,10 @@ restart:
 		pending >>= softirq_bit;
 	}
 
-	if (__this_cpu_read(ksoftirqd) == current)
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
+	    __this_cpu_read(ksoftirqd) == current)
 		rcu_softirq_qs();
+
 	local_irq_disable();
 
 	pending = local_softirq_pending();
@@ -369,8 +585,7 @@ restart:
 
 	account_softirq_exit(current);
 	lockdep_softirq_end(in_hardirq);
-	__local_bh_enable(SOFTIRQ_OFFSET);
-	WARN_ON_ONCE(in_interrupt());
+	softirq_handle_end();
 	current_restore_flags(old_flags, PF_MEMALLOC);
 }
 
@@ -465,7 +680,7 @@ inline void raise_softirq_irqoff(unsigned int nr)
 	 * Otherwise we wake up ksoftirqd to make sure we
 	 * schedule the softirq soon.
 	 */
-	if (!in_interrupt())
+	if (!in_interrupt() && should_wake_ksoftirqd())
 		wakeup_softirqd();
 }
 
@@ -531,6 +746,20 @@ void __tasklet_hi_schedule(struct tasklet_struct *t)
 }
 EXPORT_SYMBOL(__tasklet_hi_schedule);
 
+static bool tasklet_clear_sched(struct tasklet_struct *t)
+{
+	if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) {
+		wake_up_var(&t->state);
+		return true;
+	}
+
+	WARN_ONCE(1, "tasklet SCHED state not set: %s %pS\n",
+		  t->use_callback ? "callback" : "func",
+		  t->use_callback ? (void *)t->callback : (void *)t->func);
+
+	return false;
+}
+
 static void tasklet_action_common(struct softirq_action *a,
 				  struct tasklet_head *tl_head,
 				  unsigned int softirq_nr)
@@ -550,13 +779,12 @@ static void tasklet_action_common(struct softirq_action *a,
 
 		if (tasklet_trylock(t)) {
 			if (!atomic_read(&t->count)) {
-				if (!test_and_clear_bit(TASKLET_STATE_SCHED,
-							&t->state))
-					BUG();
-				if (t->use_callback)
-					t->callback(t);
-				else
-					t->func(t->data);
+				if (tasklet_clear_sched(t)) {
+					if (t->use_callback)
+						t->callback(t);
+					else
+						t->func(t->data);
+				}
 				tasklet_unlock(t);
 				continue;
 			}
@@ -606,21 +834,62 @@ void tasklet_init(struct tasklet_struct *t,
 }
 EXPORT_SYMBOL(tasklet_init);
 
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+/*
+ * Do not use in new code. Waiting for tasklets from atomic contexts is
+ * error prone and should be avoided.
+ */
+void tasklet_unlock_spin_wait(struct tasklet_struct *t)
+{
+	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
+		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			/*
+			 * Prevent a live lock when current preempted soft
+			 * interrupt processing or prevents ksoftirqd from
+			 * running. If the tasklet runs on a different CPU
+			 * then this has no effect other than doing the BH
+			 * disable/enable dance for nothing.
+			 */
+			local_bh_disable();
+			local_bh_enable();
+		} else {
+			cpu_relax();
+		}
+	}
+}
+EXPORT_SYMBOL(tasklet_unlock_spin_wait);
+#endif
+
 void tasklet_kill(struct tasklet_struct *t)
 {
 	if (in_interrupt())
 		pr_notice("Attempt to kill tasklet from interrupt\n");
 
-	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
-		do {
-			yield();
-		} while (test_bit(TASKLET_STATE_SCHED, &t->state));
-	}
+	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
+		wait_var_event(&t->state, !test_bit(TASKLET_STATE_SCHED, &t->state));
+
 	tasklet_unlock_wait(t);
-	clear_bit(TASKLET_STATE_SCHED, &t->state);
+	tasklet_clear_sched(t);
 }
 EXPORT_SYMBOL(tasklet_kill);
 
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+void tasklet_unlock(struct tasklet_struct *t)
+{
+	smp_mb__before_atomic();
+	clear_bit(TASKLET_STATE_RUN, &t->state);
+	smp_mb__after_atomic();
+	wake_up_var(&t->state);
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock);
+
+void tasklet_unlock_wait(struct tasklet_struct *t)
+{
+	wait_var_event(&t->state, !test_bit(TASKLET_STATE_RUN, &t->state));
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock_wait);
+#endif
+
 void __init softirq_init(void)
 {
 	int cpu;
@@ -643,53 +912,21 @@ static int ksoftirqd_should_run(unsigned int cpu)
 
 static void run_ksoftirqd(unsigned int cpu)
 {
-	local_irq_disable();
+	ksoftirqd_run_begin();
 	if (local_softirq_pending()) {
 		/*
 		 * We can safely run softirq on inline stack, as we are not deep
 		 * in the task stack here.
 		 */
 		__do_softirq();
-		local_irq_enable();
+		ksoftirqd_run_end();
 		cond_resched();
 		return;
 	}
-	local_irq_enable();
+	ksoftirqd_run_end();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-/*
- * tasklet_kill_immediate is called to remove a tasklet which can already be
- * scheduled for execution on @cpu.
- *
- * Unlike tasklet_kill, this function removes the tasklet
- * _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
- *
- * When this function is called, @cpu must be in the CPU_DEAD state.
- */
-void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
-{
-	struct tasklet_struct **i;
-
-	BUG_ON(cpu_online(cpu));
-	BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));
-
-	if (!test_bit(TASKLET_STATE_SCHED, &t->state))
-		return;
-
-	/* CPU is dead, so no lock needed. */
-	for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) {
-		if (*i == t) {
-			*i = t->next;
-			/* If this was the tail element, move the tail ptr */
-			if (*i == NULL)
-				per_cpu(tasklet_vec, cpu).tail = i;
-			return;
-		}
-	}
-	BUG();
-}
-
 static int takeover_tasklets(unsigned int cpu)
 {
 	/* CPU is dead, so no lock needed. */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e10a4af88737..0cc55791b2b6 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -973,7 +973,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	if (unlikely(local_softirq_pending())) {
 		static int ratelimit;
 
-		if (ratelimit < 10 &&
+		if (ratelimit < 10 && !local_bh_blocked() &&
 		    (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
 			pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n",
 				(unsigned int) local_softirq_pending());
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c0c9aa5cd8e2..915fe8790f04 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4832,7 +4832,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	cpumask_var_t tracing_cpumask_new;
 	int err;
 
-	if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
+	if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
 		return -ENOMEM;
 
 	err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);