8 files changed, 445 insertions, 97 deletions

diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 32f6cfcff212..17f51d63da56 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -4,60 +4,151 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 
-static int get_first_sibling(unsigned int cpu)
+static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
+				int cpus_per_vec)
 {
-	unsigned int ret;
+	const struct cpumask *siblmsk;
+	int cpu, sibl;
 
-	ret = cpumask_first(topology_sibling_cpumask(cpu));
-	if (ret < nr_cpu_ids)
-		return ret;
-	return cpu;
+	for ( ; cpus_per_vec > 0; ) {
+		cpu = cpumask_first(nmsk);
+
+		/* Should not happen, but I'm too lazy to think about it */
+		if (cpu >= nr_cpu_ids)
+			return;
+
+		cpumask_clear_cpu(cpu, nmsk);
+		cpumask_set_cpu(cpu, irqmsk);
+		cpus_per_vec--;
+
+		/* If the cpu has siblings, use them first */
+		siblmsk = topology_sibling_cpumask(cpu);
+		for (sibl = -1; cpus_per_vec > 0; ) {
+			sibl = cpumask_next(sibl, siblmsk);
+			if (sibl >= nr_cpu_ids)
+				break;
+			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
+				continue;
+			cpumask_set_cpu(sibl, irqmsk);
+			cpus_per_vec--;
+		}
+	}
+}
+
+static int get_nodes_in_cpumask(const struct cpumask *mask, nodemask_t *nodemsk)
+{
+	int n, nodes;
+
+	/* Calculate the number of nodes in the supplied affinity mask */
+	for (n = 0, nodes = 0; n < num_online_nodes(); n++) {
+		if (cpumask_intersects(mask, cpumask_of_node(n))) {
+			node_set(n, *nodemsk);
+			nodes++;
+		}
+	}
+	return nodes;
 }
 
-/*
- * Take a map of online CPUs and the number of available interrupt vectors
- * and generate an output cpumask suitable for spreading MSI/MSI-X vectors
- * so that they are distributed as good as possible around the CPUs.  If
- * more vectors than CPUs are available we'll map one to each CPU,
- * otherwise we map one to the first sibling of each socket.
+/**
+ * irq_create_affinity_masks - Create affinity masks for multiqueue spreading
+ * @affinity:		The affinity mask to spread. If NULL cpu_online_mask
+ *			is used
+ * @nvecs:		The number of vectors
  *
- * If there are more vectors than CPUs we will still only have one bit
- * set per CPU, but interrupt code will keep on assigning the vectors from
- * the start of the bitmap until we run out of vectors.
+ * Returns the masks pointer or NULL if allocation failed.
  */
-struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs)
+struct cpumask *irq_create_affinity_masks(const struct cpumask *affinity,
+					  int nvec)
 {
-	struct cpumask *affinity_mask;
-	unsigned int max_vecs = *nr_vecs;
+	int n, nodes, vecs_per_node, cpus_per_vec, extra_vecs, curvec = 0;
+	nodemask_t nodemsk = NODE_MASK_NONE;
+	struct cpumask *masks;
+	cpumask_var_t nmsk;
 
-	if (max_vecs == 1)
+	if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
 		return NULL;
 
-	affinity_mask = kzalloc(cpumask_size(), GFP_KERNEL);
-	if (!affinity_mask) {
-		*nr_vecs = 1;
-		return NULL;
-	}
+	masks = kzalloc(nvec * sizeof(*masks), GFP_KERNEL);
+	if (!masks)
+		goto out;
 
+	/* Stabilize the cpumasks */
 	get_online_cpus();
-	if (max_vecs >= num_online_cpus()) {
-		cpumask_copy(affinity_mask, cpu_online_mask);
-		*nr_vecs = num_online_cpus();
-	} else {
-		unsigned int vecs = 0, cpu;
-
-		for_each_online_cpu(cpu) {
-			if (cpu == get_first_sibling(cpu)) {
-				cpumask_set_cpu(cpu, affinity_mask);
-				vecs++;
-			}
+	/* If the supplied affinity mask is NULL, use cpu online mask */
+	if (!affinity)
+		affinity = cpu_online_mask;
+
+	nodes = get_nodes_in_cpumask(affinity, &nodemsk);
 
-			if (--max_vecs == 0)
+	/*
+	 * If the number of nodes in the mask is less than or equal the
+	 * number of vectors we just spread the vectors across the nodes.
+	 */
+	if (nvec <= nodes) {
+		for_each_node_mask(n, nodemsk) {
+			cpumask_copy(masks + curvec, cpumask_of_node(n));
+			if (++curvec == nvec)
 				break;
 		}
-		*nr_vecs = vecs;
+		goto outonl;
 	}
+
+	/* Spread the vectors per node */
+	vecs_per_node = nvec / nodes;
+	/* Account for rounding errors */
+	extra_vecs = nvec - (nodes * vecs_per_node);
+
+	for_each_node_mask(n, nodemsk) {
+		int ncpus, v, vecs_to_assign = vecs_per_node;
+
+		/* Get the cpus on this node which are in the mask */
+		cpumask_and(nmsk, affinity, cpumask_of_node(n));
+
+		/* Calculate the number of cpus per vector */
+		ncpus = cpumask_weight(nmsk);
+
+		for (v = 0; curvec < nvec && v < vecs_to_assign; curvec++, v++) {
+			cpus_per_vec = ncpus / vecs_to_assign;
+
+			/* Account for extra vectors to compensate rounding errors */
+			if (extra_vecs) {
+				cpus_per_vec++;
+				if (!--extra_vecs)
+					vecs_per_node++;
+			}
+			irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec);
+		}
+
+		if (curvec >= nvec)
+			break;
+	}
+
+outonl:
 	put_online_cpus();
+out:
+	free_cpumask_var(nmsk);
+	return masks;
+}
+
+/**
+ * irq_calc_affinity_vectors - Calculate to optimal number of vectors for a given affinity mask
+ * @affinity:		The affinity mask to spread. If NULL cpu_online_mask
+ *			is used
+ * @maxvec:		The maximum number of vectors available
+ */
+int irq_calc_affinity_vectors(const struct cpumask *affinity, int maxvec)
+{
+	int cpus, ret;
 
-	return affinity_mask;
+	/* Stabilize the cpumasks */
+	get_online_cpus();
+	/* If the supplied affinity mask is NULL, use cpu online mask */
+	if (!affinity)
+		affinity = cpu_online_mask;
+
+	cpus = cpumask_weight(affinity);
+	ret = (cpus < maxvec) ? cpus : maxvec;
+
+	put_online_cpus();
+	return ret;
 }
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 26ba5654d9d5..be3c34e4f2ac 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -76,7 +76,6 @@ int irq_set_irq_type(unsigned int irq, unsigned int type)
 	if (!desc)
 		return -EINVAL;
 
-	type &= IRQ_TYPE_SENSE_MASK;
 	ret = __irq_set_trigger(desc, type);
 	irq_put_desc_busunlock(desc, flags);
 	return ret;
@@ -756,7 +755,6 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct irqaction *action = desc->action;
-	void *dev_id = raw_cpu_ptr(action->percpu_dev_id);
 	unsigned int irq = irq_desc_get_irq(desc);
 	irqreturn_t res;
 
@@ -765,15 +763,26 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 	if (chip->irq_ack)
 		chip->irq_ack(&desc->irq_data);
 
-	trace_irq_handler_entry(irq, action);
-	res = action->handler(irq, dev_id);
-	trace_irq_handler_exit(irq, action, res);
+	if (likely(action)) {
+		trace_irq_handler_entry(irq, action);
+		res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
+		trace_irq_handler_exit(irq, action, res);
+	} else {
+		unsigned int cpu = smp_processor_id();
+		bool enabled = cpumask_test_cpu(cpu, desc->percpu_enabled);
+
+		if (enabled)
+			irq_percpu_disable(desc, cpu);
+
+		pr_err_once("Spurious%s percpu IRQ%u on CPU%u\n",
+			    enabled ? " and unmasked" : "", irq, cpu);
+	}
 
 	if (chip->irq_eoi)
 		chip->irq_eoi(&desc->irq_data);
 }
 
-void
+static void
 __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 		     int is_chained, const char *name)
 {
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index abd286afbd27..ee32870079c9 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -260,9 +260,9 @@ irq_gc_init_mask_cache(struct irq_chip_generic *gc, enum irq_gc_flags flags)
 }
 
 /**
- * irq_alloc_domain_generic_chip - Allocate generic chips for an irq domain
+ * __irq_alloc_domain_generic_chip - Allocate generic chips for an irq domain
  * @d:			irq domain for which to allocate chips
- * @irqs_per_chip:	Number of interrupts each chip handles
+ * @irqs_per_chip:	Number of interrupts each chip handles (max 32)
  * @num_ct:		Number of irq_chip_type instances associated with this
  * @name:		Name of the irq chip
  * @handler:		Default flow handler associated with these chips
@@ -270,11 +270,11 @@ irq_gc_init_mask_cache(struct irq_chip_generic *gc, enum irq_gc_flags flags)
  * @set:		IRQ_* bits to set in the mapping function
  * @gcflags:		Generic chip specific setup flags
  */
-int irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip,
-				   int num_ct, const char *name,
-				   irq_flow_handler_t handler,
-				   unsigned int clr, unsigned int set,
-				   enum irq_gc_flags gcflags)
+int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip,
+				     int num_ct, const char *name,
+				     irq_flow_handler_t handler,
+				     unsigned int clr, unsigned int set,
+				     enum irq_gc_flags gcflags)
 {
 	struct irq_domain_chip_generic *dgc;
 	struct irq_chip_generic *gc;
@@ -326,7 +326,21 @@ int irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip,
 	d->name = name;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(irq_alloc_domain_generic_chips);
+EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips);
+
+static struct irq_chip_generic *
+__irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq)
+{
+	struct irq_domain_chip_generic *dgc = d->gc;
+	int idx;
+
+	if (!dgc)
+		return ERR_PTR(-ENODEV);
+	idx = hw_irq / dgc->irqs_per_chip;
+	if (idx >= dgc->num_chips)
+		return ERR_PTR(-EINVAL);
+	return dgc->gc[idx];
+}
 
 /**
  * irq_get_domain_generic_chip - Get a pointer to the generic chip of a hw_irq
@@ -336,15 +350,9 @@ EXPORT_SYMBOL_GPL(irq_alloc_domain_generic_chips);
 struct irq_chip_generic *
 irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq)
 {
-	struct irq_domain_chip_generic *dgc = d->gc;
-	int idx;
+	struct irq_chip_generic *gc = __irq_get_domain_generic_chip(d, hw_irq);
 
-	if (!dgc)
-		return NULL;
-	idx = hw_irq / dgc->irqs_per_chip;
-	if (idx >= dgc->num_chips)
-		return NULL;
-	return dgc->gc[idx];
+	return !IS_ERR(gc) ? gc : NULL;
 }
 EXPORT_SYMBOL_GPL(irq_get_domain_generic_chip);
 
@@ -368,13 +376,9 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
 	unsigned long flags;
 	int idx;
 
-	if (!d->gc)
-		return -ENODEV;
-
-	idx = hw_irq / dgc->irqs_per_chip;
-	if (idx >= dgc->num_chips)
-		return -EINVAL;
-	gc = dgc->gc[idx];
+	gc = __irq_get_domain_generic_chip(d, hw_irq);
+	if (IS_ERR(gc))
+		return PTR_ERR(gc);
 
 	idx = hw_irq % dgc->irqs_per_chip;
 
@@ -409,10 +413,30 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq,
 	irq_modify_status(virq, dgc->irq_flags_to_clear, dgc->irq_flags_to_set);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(irq_map_generic_chip);
+
+static void irq_unmap_generic_chip(struct irq_domain *d, unsigned int virq)
+{
+	struct irq_data *data = irq_domain_get_irq_data(d, virq);
+	struct irq_domain_chip_generic *dgc = d->gc;
+	unsigned int hw_irq = data->hwirq;
+	struct irq_chip_generic *gc;
+	int irq_idx;
+
+	gc = irq_get_domain_generic_chip(d, hw_irq);
+	if (!gc)
+		return;
+
+	irq_idx = hw_irq % dgc->irqs_per_chip;
+
+	clear_bit(irq_idx, &gc->installed);
+	irq_domain_set_info(d, virq, hw_irq, &no_irq_chip, NULL, NULL, NULL,
+			    NULL);
+
+}
 
 struct irq_domain_ops irq_generic_chip_ops = {
 	.map	= irq_map_generic_chip,
+	.unmap  = irq_unmap_generic_chip,
 	.xlate	= irq_domain_xlate_onetwocell,
 };
 EXPORT_SYMBOL_GPL(irq_generic_chip_ops);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a623b44f2d4b..00bb0aeea1d0 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -15,6 +15,7 @@
 #include <linux/radix-tree.h>
 #include <linux/bitmap.h>
 #include <linux/irqdomain.h>
+#include <linux/sysfs.h>
 
 #include "internals.h"
 
@@ -123,6 +124,181 @@ static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
 
 #ifdef CONFIG_SPARSE_IRQ
 
+static void irq_kobj_release(struct kobject *kobj);
+
+#ifdef CONFIG_SYSFS
+static struct kobject *irq_kobj_base;
+
+#define IRQ_ATTR_RO(_name) \
+static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+
+static ssize_t per_cpu_count_show(struct kobject *kobj,
+				  struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	int cpu, irq = desc->irq_data.irq;
+	ssize_t ret = 0;
+	char *p = "";
+
+	for_each_possible_cpu(cpu) {
+		unsigned int c = kstat_irqs_cpu(irq, cpu);
+
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c);
+		p = ",";
+	}
+
+	ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
+	return ret;
+}
+IRQ_ATTR_RO(per_cpu_count);
+
+static ssize_t chip_name_show(struct kobject *kobj,
+			      struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	ssize_t ret = 0;
+
+	raw_spin_lock_irq(&desc->lock);
+	if (desc->irq_data.chip && desc->irq_data.chip->name) {
+		ret = scnprintf(buf, PAGE_SIZE, "%s\n",
+				desc->irq_data.chip->name);
+	}
+	raw_spin_unlock_irq(&desc->lock);
+
+	return ret;
+}
+IRQ_ATTR_RO(chip_name);
+
+static ssize_t hwirq_show(struct kobject *kobj,
+			  struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	ssize_t ret = 0;
+
+	raw_spin_lock_irq(&desc->lock);
+	if (desc->irq_data.domain)
+		ret = sprintf(buf, "%d\n", (int)desc->irq_data.hwirq);
+	raw_spin_unlock_irq(&desc->lock);
+
+	return ret;
+}
+IRQ_ATTR_RO(hwirq);
+
+static ssize_t type_show(struct kobject *kobj,
+			 struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	ssize_t ret = 0;
+
+	raw_spin_lock_irq(&desc->lock);
+	ret = sprintf(buf, "%s\n",
+		      irqd_is_level_type(&desc->irq_data) ? "level" : "edge");
+	raw_spin_unlock_irq(&desc->lock);
+
+	return ret;
+
+}
+IRQ_ATTR_RO(type);
+
+static ssize_t name_show(struct kobject *kobj,
+			 struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	ssize_t ret = 0;
+
+	raw_spin_lock_irq(&desc->lock);
+	if (desc->name)
+		ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->name);
+	raw_spin_unlock_irq(&desc->lock);
+
+	return ret;
+}
+IRQ_ATTR_RO(name);
+
+static ssize_t actions_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
+	struct irqaction *action;
+	ssize_t ret = 0;
+	char *p = "";
+
+	raw_spin_lock_irq(&desc->lock);
+	for (action = desc->action; action != NULL; action = action->next) {
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
+				 p, action->name);
+		p = ",";
+	}
+	raw_spin_unlock_irq(&desc->lock);
+
+	if (ret)
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
+
+	return ret;
+}
+IRQ_ATTR_RO(actions);
+
+static struct attribute *irq_attrs[] = {
+	&per_cpu_count_attr.attr,
+	&chip_name_attr.attr,
+	&hwirq_attr.attr,
+	&type_attr.attr,
+	&name_attr.attr,
+	&actions_attr.attr,
+	NULL
+};
+
+static struct kobj_type irq_kobj_type = {
+	.release	= irq_kobj_release,
+	.sysfs_ops	= &kobj_sysfs_ops,
+	.default_attrs	= irq_attrs,
+};
+
+static void irq_sysfs_add(int irq, struct irq_desc *desc)
+{
+	if (irq_kobj_base) {
+		/*
+		 * Continue even in case of failure as this is nothing
+		 * crucial.
+		 */
+		if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq))
+			pr_warn("Failed to add kobject for irq %d\n", irq);
+	}
+}
+
+static int __init irq_sysfs_init(void)
+{
+	struct irq_desc *desc;
+	int irq;
+
+	/* Prevent concurrent irq alloc/free */
+	irq_lock_sparse();
+
+	irq_kobj_base = kobject_create_and_add("irq", kernel_kobj);
+	if (!irq_kobj_base) {
+		irq_unlock_sparse();
+		return -ENOMEM;
+	}
+
+	/* Add the already allocated interrupts */
+	for_each_irq_desc(irq, desc)
+		irq_sysfs_add(irq, desc);
+	irq_unlock_sparse();
+
+	return 0;
+}
+postcore_initcall(irq_sysfs_init);
+
+#else /* !CONFIG_SYSFS */
+
+static struct kobj_type irq_kobj_type = {
+	.release	= irq_kobj_release,
+};
+
+static void irq_sysfs_add(int irq, struct irq_desc *desc) {}
+
+#endif /* CONFIG_SYSFS */
+
 static RADIX_TREE(irq_desc_tree, GFP_KERNEL);
 
 static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
@@ -187,6 +363,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
 
 	desc_set_defaults(irq, desc, node, affinity, owner);
 	irqd_set(&desc->irq_data, flags);
+	kobject_init(&desc->kobj, &irq_kobj_type);
 
 	return desc;
 
@@ -197,15 +374,22 @@ err_desc:
 	return NULL;
 }
 
-static void delayed_free_desc(struct rcu_head *rhp)
+static void irq_kobj_release(struct kobject *kobj)
 {
-	struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu);
+	struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj);
 
 	free_masks(desc);
 	free_percpu(desc->kstat_irqs);
 	kfree(desc);
 }
 
+static void delayed_free_desc(struct rcu_head *rhp)
+{
+	struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu);
+
+	kobject_put(&desc->kobj);
+}
+
 static void free_desc(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -217,8 +401,12 @@ static void free_desc(unsigned int irq)
 	 * kstat_irq_usr(). Once we deleted the descriptor from the
 	 * sparse tree we can free it. Access in proc will fail to
 	 * lookup the descriptor.
+	 *
+	 * The sysfs entry must be serialized against a concurrent
+	 * irq_sysfs_init() as well.
 	 */
 	mutex_lock(&sparse_irq_lock);
+	kobject_del(&desc->kobj);
 	delete_irq_desc(irq);
 	mutex_unlock(&sparse_irq_lock);
 
@@ -236,31 +424,31 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 	const struct cpumask *mask = NULL;
 	struct irq_desc *desc;
 	unsigned int flags;
-	int i, cpu = -1;
+	int i;
 
-	if (affinity && cpumask_empty(affinity))
-		return -EINVAL;
+	/* Validate affinity mask(s) */
+	if (affinity) {
+		for (i = 0, mask = affinity; i < cnt; i++, mask++) {
+			if (cpumask_empty(mask))
+				return -EINVAL;
+		}
+	}
 
 	flags = affinity ? IRQD_AFFINITY_MANAGED : 0;
+	mask = NULL;
 
 	for (i = 0; i < cnt; i++) {
 		if (affinity) {
-			cpu = cpumask_next(cpu, affinity);
-			if (cpu >= nr_cpu_ids)
-				cpu = cpumask_first(affinity);
-			node = cpu_to_node(cpu);
-
-			/*
-			 * For single allocations we use the caller provided
-			 * mask otherwise we use the mask of the target cpu
-			 */
-			mask = cnt == 1 ? affinity : cpumask_of(cpu);
+			node = cpu_to_node(cpumask_first(affinity));
+			mask = affinity;
+			affinity++;
 		}
 		desc = alloc_desc(start + i, node, flags, mask, owner);
 		if (!desc)
 			goto err;
 		mutex_lock(&sparse_irq_lock);
 		irq_insert_desc(start + i, desc);
+		irq_sysfs_add(start + i, desc);
 		mutex_unlock(&sparse_irq_lock);
 	}
 	return start;
@@ -481,9 +669,9 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
  * @cnt:	Number of consecutive irqs to allocate.
  * @node:	Preferred node on which the irq descriptor should be allocated
  * @owner:	Owning module (can be NULL)
- * @affinity:	Optional pointer to an affinity mask which hints where the
- *		irq descriptors should be allocated and which default
- *		affinities to use
+ * @affinity:	Optional pointer to an affinity mask array of size @cnt which
+ *		hints where the irq descriptors should be allocated and which
+ *		default affinities to use
  *
  * Returns the first irq number or error code
  */
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 4752b43662e0..8c0a0ae43521 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -80,7 +80,7 @@ EXPORT_SYMBOL_GPL(irq_domain_free_fwnode);
 
 /**
  * __irq_domain_add() - Allocate a new irq_domain data structure
- * @of_node: optional device-tree node of the interrupt controller
+ * @fwnode: firmware node for the interrupt controller
  * @size: Size of linear map; 0 for radix mapping only
  * @hwirq_max: Maximum number of interrupts supported by controller
  * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no
@@ -96,10 +96,8 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
 				    const struct irq_domain_ops *ops,
 				    void *host_data)
 {
+	struct device_node *of_node = to_of_node(fwnode);
 	struct irq_domain *domain;
-	struct device_node *of_node;
-
-	of_node = to_of_node(fwnode);
 
 	domain = kzalloc_node(sizeof(*domain) + (sizeof(unsigned int) * size),
 			      GFP_KERNEL, of_node_to_nid(of_node));
@@ -868,7 +866,10 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d,
 	if (WARN_ON(intsize < 1))
 		return -EINVAL;
 	*out_hwirq = intspec[0];
-	*out_type = (intsize > 1) ? intspec[1] : IRQ_TYPE_NONE;
+	if (intsize > 1)
+		*out_type = intspec[1] & IRQ_TYPE_SENSE_MASK;
+	else
+		*out_type = IRQ_TYPE_NONE;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(irq_domain_xlate_onetwocell);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 9530fcd27704..0c5f1a5db654 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -669,8 +669,6 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
 		return 0;
 	}
 
-	flags &= IRQ_TYPE_SENSE_MASK;
-
 	if (chip->flags & IRQCHIP_SET_TYPE_MASKED) {
 		if (!irqd_irq_masked(&desc->irq_data))
 			mask_irq(desc);
@@ -678,7 +676,8 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
 			unmask = 1;
 	}
 
-	/* caller masked out all except trigger mode flags */
+	/* Mask all flags except trigger mode */
+	flags &= IRQ_TYPE_SENSE_MASK;
 	ret = chip->irq_set_type(&desc->irq_data, flags);
 
 	switch (ret) {
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 19e9dfbe97fa..8a3e872798f3 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -18,20 +18,42 @@
 /* Temparory solution for building, will be removed later */
 #include <linux/pci.h>
 
-struct msi_desc *alloc_msi_entry(struct device *dev)
+/**
+ * alloc_msi_entry - Allocate an initialize msi_entry
+ * @dev:	Pointer to the device for which this is allocated
+ * @nvec:	The number of vectors used in this entry
+ * @affinity:	Optional pointer to an affinity mask array size of @nvec
+ *
+ * If @affinity is not NULL then a an affinity array[@nvec] is allocated
+ * and the affinity masks from @affinity are copied.
+ */
+struct msi_desc *
+alloc_msi_entry(struct device *dev, int nvec, const struct cpumask *affinity)
 {
-	struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	struct msi_desc *desc;
+
+	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 	if (!desc)
 		return NULL;
 
 	INIT_LIST_HEAD(&desc->list);
 	desc->dev = dev;
+	desc->nvec_used = nvec;
+	if (affinity) {
+		desc->affinity = kmemdup(affinity,
+			nvec * sizeof(*desc->affinity), GFP_KERNEL);
+		if (!desc->affinity) {
+			kfree(desc);
+			return NULL;
+		}
+	}
 
 	return desc;
 }
 
 void free_msi_entry(struct msi_desc *entry)
 {
+	kfree(entry->affinity);
 	kfree(entry);
 }
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 17caf4b63342..8ed90e3a88d6 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -78,6 +78,17 @@ static void wakeup_softirqd(void)
 }
 
 /*
+ * If ksoftirqd is scheduled, we do not want to process pending softirqs
+ * right now. Let ksoftirqd handle this at its own rate, to get fairness.
+ */
+static bool ksoftirqd_running(void)
+{
+	struct task_struct *tsk = __this_cpu_read(ksoftirqd);
+
+	return tsk && (tsk->state == TASK_RUNNING);
+}
+
+/*
  * preempt_count and SOFTIRQ_OFFSET usage:
  * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
  *   softirq processing.
@@ -313,7 +324,7 @@ asmlinkage __visible void do_softirq(void)
 
 	pending = local_softirq_pending();
 
-	if (pending)
+	if (pending && !ksoftirqd_running())
 		do_softirq_own_stack();
 
 	local_irq_restore(flags);
@@ -340,6 +351,9 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
+	if (ksoftirqd_running())
+		return;
+
 	if (!force_irqthreads) {
 #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
 		/*