1 files changed, 358 insertions, 379 deletions

diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 1a7723604399..6acf268f005b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -12,10 +12,10 @@
 #include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
-#include <linux/radix-tree.h>
-#include <linux/bitmap.h>
+#include <linux/maple_tree.h>
 #include <linux/irqdomain.h>
 #include <linux/sysfs.h>
+#include <linux/string_choices.h>
 
 #include "internals.h"
 
@@ -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;
@@ -93,11 +93,23 @@ static void desc_smp_init(struct irq_desc *desc, int node,
 #endif
 }
 
+static void free_masks(struct irq_desc *desc)
+{
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	free_cpumask_var(desc->pending_mask);
+#endif
+	free_cpumask_var(desc->irq_common_data.affinity);
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	free_cpumask_var(desc->irq_common_data.effective_affinity);
+#endif
+}
+
 #else
 static inline int
 alloc_masks(struct irq_desc *desc, int node) { return 0; }
 static inline void
 desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { }
+static inline void free_masks(struct irq_desc *desc) { }
 #endif
 
 static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
@@ -123,15 +135,106 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
 	desc->name = NULL;
 	desc->owner = owner;
 	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(desc->kstat_irqs, cpu) = 0;
+		*per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { };
 	desc_smp_init(desc, node, affinity);
 }
 
-int nr_irqs = NR_IRQS;
-EXPORT_SYMBOL_GPL(nr_irqs);
+static unsigned int nr_irqs = NR_IRQS;
+
+/**
+ * irq_get_nr_irqs() - Number of interrupts supported by the system.
+ */
+unsigned int irq_get_nr_irqs(void)
+{
+	return nr_irqs;
+}
+EXPORT_SYMBOL_GPL(irq_get_nr_irqs);
+
+/**
+ * irq_set_nr_irqs() - Set the number of interrupts supported by the system.
+ * @nr: New number of interrupts.
+ *
+ * Return: @nr.
+ */
+unsigned int irq_set_nr_irqs(unsigned int nr)
+{
+	nr_irqs = nr;
+
+	return nr;
+}
+EXPORT_SYMBOL_GPL(irq_set_nr_irqs);
 
 static DEFINE_MUTEX(sparse_irq_lock);
-static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
+static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs,
+					MT_FLAGS_ALLOC_RANGE |
+					MT_FLAGS_LOCK_EXTERN |
+					MT_FLAGS_USE_RCU,
+					sparse_irq_lock);
+
+static int irq_find_free_area(unsigned int from, unsigned int cnt)
+{
+	MA_STATE(mas, &sparse_irqs, 0, 0);
+
+	if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt))
+		return -ENOSPC;
+	return mas.index;
+}
+
+static unsigned int irq_find_at_or_after(unsigned int offset)
+{
+	unsigned long index = offset;
+	struct irq_desc *desc;
+
+	guard(rcu)();
+	desc = mt_find(&sparse_irqs, &index, nr_irqs);
+
+	return desc ? irq_desc_get_irq(desc) : nr_irqs;
+}
+
+static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
+{
+	MA_STATE(mas, &sparse_irqs, irq, irq);
+	WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0);
+}
+
+static void delete_irq_desc(unsigned int irq)
+{
+	MA_STATE(mas, &sparse_irqs, irq, irq);
+	mas_erase(&mas);
+}
+
+#ifdef CONFIG_SPARSE_IRQ
+static const struct kobj_type irq_kobj_type;
+#endif
+
+static int init_desc(struct irq_desc *desc, int irq, int node,
+		     unsigned int flags,
+		     const struct cpumask *affinity,
+		     struct module *owner)
+{
+	desc->kstat_irqs = alloc_percpu(struct irqstat);
+	if (!desc->kstat_irqs)
+		return -ENOMEM;
+
+	if (alloc_masks(desc, node)) {
+		free_percpu(desc->kstat_irqs);
+		return -ENOMEM;
+	}
+
+	raw_spin_lock_init(&desc->lock);
+	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+	mutex_init(&desc->request_mutex);
+	init_waitqueue_head(&desc->wait_for_threads);
+	desc_set_defaults(irq, desc, node, affinity, owner);
+	irqd_set(&desc->irq_data, flags);
+	irq_resend_init(desc);
+#ifdef CONFIG_SPARSE_IRQ
+	kobject_init(&desc->kobj, &irq_kobj_type);
+	init_rcu_head(&desc->rcu);
+#endif
+
+	return 0;
+}
 
 #ifdef CONFIG_SPARSE_IRQ
 
@@ -143,124 +246,93 @@ 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)
+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 = "";
+	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		unsigned int c = kstat_irqs_cpu(irq, cpu);
+		unsigned int c = irq_desc_kstat_cpu(desc, cpu);
 
-		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c);
+		ret += sysfs_emit_at(buf, ret, "%s%u", p, c);
 		p = ",";
 	}
 
-	ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
+	ret += sysfs_emit_at(buf, 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)
+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;
+	guard(raw_spinlock_irq)(&desc->lock);
+	if (desc->irq_data.chip && desc->irq_data.chip->name)
+		return sysfs_emit(buf, "%s\n", desc->irq_data.chip->name);
+	return 0;
 }
 IRQ_ATTR_RO(chip_name);
 
-static ssize_t hwirq_show(struct kobject *kobj,
-			  struct kobj_attribute *attr, char *buf)
+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);
+	guard(raw_spinlock_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;
+		return sysfs_emit(buf, "%lu\n", desc->irq_data.hwirq);
+	return 0;
 }
 IRQ_ATTR_RO(hwirq);
 
-static ssize_t type_show(struct kobject *kobj,
-			 struct kobj_attribute *attr, char *buf)
+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;
+	guard(raw_spinlock_irq)(&desc->lock);
+	return sysfs_emit(buf, "%s\n", irqd_is_level_type(&desc->irq_data) ? "level" : "edge");
 
 }
 IRQ_ATTR_RO(type);
 
-static ssize_t wakeup_show(struct kobject *kobj,
-			   struct kobj_attribute *attr, char *buf)
+static ssize_t wakeup_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_wakeup_set(&desc->irq_data) ? "enabled" : "disabled");
-	raw_spin_unlock_irq(&desc->lock);
-
-	return ret;
 
+	guard(raw_spinlock_irq)(&desc->lock);
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(irqd_is_wakeup_set(&desc->irq_data)));
 }
 IRQ_ATTR_RO(wakeup);
 
-static ssize_t name_show(struct kobject *kobj,
-			 struct kobj_attribute *attr, char *buf)
+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);
+	guard(raw_spinlock_irq)(&desc->lock);
 	if (desc->name)
-		ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->name);
-	raw_spin_unlock_irq(&desc->lock);
-
-	return ret;
+		return sysfs_emit(buf, "%s\n", desc->name);
+	return 0;
 }
 IRQ_ATTR_RO(name);
 
-static ssize_t actions_show(struct kobject *kobj,
-			    struct kobj_attribute *attr, char *buf)
+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 = ",";
+	scoped_guard(raw_spinlock_irq, &desc->lock) {
+		for_each_action_of_desc(desc, action) {
+			ret += sysfs_emit_at(buf, ret, "%s%s", p, action->name);
+			p = ",";
+		}
 	}
-	raw_spin_unlock_irq(&desc->lock);
 
 	if (ret)
-		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
-
+		ret += sysfs_emit_at(buf, ret, "\n");
 	return ret;
 }
 IRQ_ATTR_RO(actions);
@@ -277,7 +349,7 @@ static struct attribute *irq_attrs[] = {
 };
 ATTRIBUTE_GROUPS(irq);
 
-static struct kobj_type irq_kobj_type = {
+static const struct kobj_type irq_kobj_type = {
 	.release	= irq_kobj_release,
 	.sysfs_ops	= &kobj_sysfs_ops,
 	.default_groups = irq_groups,
@@ -288,22 +360,25 @@ 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.
+		 * crucial and failures in the late irq_sysfs_init()
+		 * cannot be rolled back.
 		 */
 		if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq))
 			pr_warn("Failed to add kobject for irq %d\n", irq);
+		else
+			desc->istate |= IRQS_SYSFS;
 	}
 }
 
 static void irq_sysfs_del(struct irq_desc *desc)
 {
 	/*
-	 * If irq_sysfs_init() has not yet been invoked (early boot), then
-	 * irq_kobj_base is NULL and the descriptor was never added.
-	 * kobject_del() complains about a object with no parent, so make
-	 * it conditional.
+	 * Only invoke kobject_del() when kobject_add() was successfully
+	 * invoked for the descriptor. This covers both early boot, where
+	 * sysfs is not initialized yet, and the case of a failed
+	 * kobject_add() invocation.
 	 */
-	if (irq_kobj_base)
+	if (desc->istate & IRQS_SYSFS)
 		kobject_del(&desc->kobj);
 }
 
@@ -313,26 +388,21 @@ static int __init irq_sysfs_init(void)
 	int irq;
 
 	/* Prevent concurrent irq alloc/free */
-	irq_lock_sparse();
-
+	guard(mutex)(&sparse_irq_lock);
 	irq_kobj_base = kobject_create_and_add("irq", kernel_kobj);
-	if (!irq_kobj_base) {
-		irq_unlock_sparse();
+	if (!irq_kobj_base)
 		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 = {
+static const struct kobj_type irq_kobj_type = {
 	.release	= irq_kobj_release,
 };
 
@@ -341,37 +411,12 @@ static void irq_sysfs_del(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)
-{
-	radix_tree_insert(&irq_desc_tree, irq, desc);
-}
-
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
-	return radix_tree_lookup(&irq_desc_tree, irq);
+	return mtree_load(&sparse_irqs, irq);
 }
-EXPORT_SYMBOL(irq_to_desc);
-
-static void delete_irq_desc(unsigned int irq)
-{
-	radix_tree_delete(&irq_desc_tree, irq);
-}
-
-#ifdef CONFIG_SMP
-static void free_masks(struct irq_desc *desc)
-{
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	free_cpumask_var(desc->pending_mask);
-#endif
-	free_cpumask_var(desc->irq_common_data.affinity);
-#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
-	free_cpumask_var(desc->irq_common_data.effective_affinity);
-#endif
-}
-#else
-static inline void free_masks(struct irq_desc *desc) { }
+#ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE
+EXPORT_SYMBOL_GPL(irq_to_desc);
 #endif
 
 void irq_lock_sparse(void)
@@ -389,34 +434,19 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
 				   struct module *owner)
 {
 	struct irq_desc *desc;
+	int ret;
 
 	desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node);
 	if (!desc)
 		return NULL;
-	/* allocate based on nr_cpu_ids */
-	desc->kstat_irqs = alloc_percpu(unsigned int);
-	if (!desc->kstat_irqs)
-		goto err_desc;
 
-	if (alloc_masks(desc, node))
-		goto err_kstat;
-
-	raw_spin_lock_init(&desc->lock);
-	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	mutex_init(&desc->request_mutex);
-	init_rcu_head(&desc->rcu);
-
-	desc_set_defaults(irq, desc, node, affinity, owner);
-	irqd_set(&desc->irq_data, flags);
-	kobject_init(&desc->kobj, &irq_kobj_type);
+	ret = init_desc(desc, irq, node, flags, affinity, owner);
+	if (unlikely(ret)) {
+		kfree(desc);
+		return NULL;
+	}
 
 	return desc;
-
-err_kstat:
-	free_percpu(desc->kstat_irqs);
-err_desc:
-	kfree(desc);
-	return NULL;
 }
 
 static void irq_kobj_release(struct kobject *kobj)
@@ -487,6 +517,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 				flags = IRQD_AFFINITY_MANAGED |
 					IRQD_MANAGED_SHUTDOWN;
 			}
+			flags |= IRQD_AFFINITY_SET;
 			mask = &affinity->mask;
 			node = cpu_to_node(cpumask_first(mask));
 			affinity++;
@@ -499,7 +530,6 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 		irq_sysfs_add(start + i, desc);
 		irq_add_debugfs_entry(start + i, desc);
 	}
-	bitmap_set(allocated_irqs, start, cnt);
 	return start;
 
 err:
@@ -508,12 +538,12 @@ err:
 	return -ENOMEM;
 }
 
-static int irq_expand_nr_irqs(unsigned int nr)
+static bool irq_expand_nr_irqs(unsigned int nr)
 {
-	if (nr > IRQ_BITMAP_BITS)
-		return -ENOMEM;
+	if (nr > MAX_SPARSE_IRQS)
+		return false;
 	nr_irqs = nr;
-	return 0;
+	return true;
 }
 
 int __init early_irq_init(void)
@@ -528,18 +558,17 @@ int __init early_irq_init(void)
 	printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n",
 	       NR_IRQS, nr_irqs, initcnt);
 
-	if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
-		nr_irqs = IRQ_BITMAP_BITS;
+	if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS))
+		nr_irqs = MAX_SPARSE_IRQS;
 
-	if (WARN_ON(initcnt > IRQ_BITMAP_BITS))
-		initcnt = IRQ_BITMAP_BITS;
+	if (WARN_ON(initcnt > MAX_SPARSE_IRQS))
+		initcnt = MAX_SPARSE_IRQS;
 
 	if (initcnt > nr_irqs)
 		nr_irqs = initcnt;
 
 	for (i = 0; i < initcnt; i++) {
 		desc = alloc_desc(i, node, 0, NULL, NULL);
-		set_bit(i, allocated_irqs);
 		irq_insert_desc(i, desc);
 	}
 	return arch_early_irq_init();
@@ -558,24 +587,29 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 int __init early_irq_init(void)
 {
 	int count, i, node = first_online_node;
-	struct irq_desc *desc;
+	int ret;
 
 	init_irq_default_affinity();
 
 	printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS);
 
-	desc = irq_desc;
 	count = ARRAY_SIZE(irq_desc);
 
 	for (i = 0; i < count; i++) {
-		desc[i].kstat_irqs = alloc_percpu(unsigned int);
-		alloc_masks(&desc[i], node);
-		raw_spin_lock_init(&desc[i].lock);
-		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		mutex_init(&desc[i].request_mutex);
-		desc_set_defaults(i, &desc[i], node, NULL, NULL);
+		ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL);
+		if (unlikely(ret))
+			goto __free_desc_res;
 	}
+
 	return arch_early_irq_init();
+
+__free_desc_res:
+	while (--i >= 0) {
+		free_masks(irq_desc + i);
+		free_percpu(irq_desc[i].kstat_irqs);
+	}
+
+	return ret;
 }
 
 struct irq_desc *irq_to_desc(unsigned int irq)
@@ -587,11 +621,10 @@ EXPORT_SYMBOL(irq_to_desc);
 static void free_desc(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	scoped_guard(raw_spinlock_irqsave, &desc->lock)
+		desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
+	delete_irq_desc(irq);
 }
 
 static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
@@ -604,132 +637,135 @@ static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
 		struct irq_desc *desc = irq_to_desc(start + i);
 
 		desc->owner = owner;
+		irq_insert_desc(start + i, desc);
 	}
-	bitmap_set(allocated_irqs, start, cnt);
 	return start;
 }
 
-static int irq_expand_nr_irqs(unsigned int nr)
+static inline bool irq_expand_nr_irqs(unsigned int nr)
 {
-	return -ENOMEM;
+	return false;
 }
 
 void irq_mark_irq(unsigned int irq)
 {
-	mutex_lock(&sparse_irq_lock);
-	bitmap_set(allocated_irqs, irq, 1);
-	mutex_unlock(&sparse_irq_lock);
+	guard(mutex)(&sparse_irq_lock);
+	irq_insert_desc(irq, irq_desc + irq);
 }
 
-#ifdef CONFIG_GENERIC_IRQ_LEGACY
-void irq_init_desc(unsigned int irq)
-{
-	free_desc(irq);
-}
-#endif
-
 #endif /* !CONFIG_SPARSE_IRQ */
 
-/**
- * generic_handle_irq - Invoke the handler for a particular irq
- * @irq:	The irq number to handle
- *
- */
-int generic_handle_irq(unsigned int irq)
+int handle_irq_desc(struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_data *data;
 
 	if (!desc)
 		return -EINVAL;
 
 	data = irq_desc_get_irq_data(desc);
-	if (WARN_ON_ONCE(!in_irq() && handle_enforce_irqctx(data)))
+	if (WARN_ON_ONCE(!in_hardirq() && irqd_is_handle_enforce_irqctx(data)))
 		return -EPERM;
 
 	generic_handle_irq_desc(desc);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(generic_handle_irq);
 
-#ifdef CONFIG_HANDLE_DOMAIN_IRQ
 /**
- * __handle_domain_irq - Invoke the handler for a HW irq belonging to a domain
- * @domain:	The domain where to perform the lookup
- * @hwirq:	The HW irq number to convert to a logical one
- * @lookup:	Whether to perform the domain lookup or not
- * @regs:	Register file coming from the low-level handling code
+ * generic_handle_irq - Invoke the handler for a particular irq
+ * @irq:	The irq number to handle
  *
  * Returns:	0 on success, or -EINVAL if conversion has failed
- */
-int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq,
-			bool lookup, struct pt_regs *regs)
+ *
+ * 		This function must be called from an IRQ context with irq regs
+ * 		initialized.
+  */
+int generic_handle_irq(unsigned int irq)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
-	unsigned int irq = hwirq;
-	int ret = 0;
-
-	irq_enter();
-
-#ifdef CONFIG_IRQ_DOMAIN
-	if (lookup)
-		irq = irq_find_mapping(domain, hwirq);
-#endif
+	return handle_irq_desc(irq_to_desc(irq));
+}
+EXPORT_SYMBOL_GPL(generic_handle_irq);
 
-	/*
-	 * Some hardware gives randomly wrong interrupts.  Rather
-	 * than crashing, do something sensible.
-	 */
-	if (unlikely(!irq || irq >= nr_irqs)) {
-		ack_bad_irq(irq);
-		ret = -EINVAL;
-	} else {
-		generic_handle_irq(irq);
-	}
+/**
+ * generic_handle_irq_safe - Invoke the handler for a particular irq from any
+ *			     context.
+ * @irq:	The irq number to handle
+ *
+ * Returns:	0 on success, a negative value on error.
+ *
+ * This function can be called from any context (IRQ or process context). It
+ * will report an error if not invoked from IRQ context and the irq has been
+ * marked to enforce IRQ-context only.
+ */
+int generic_handle_irq_safe(unsigned int irq)
+{
+	unsigned long flags;
+	int ret;
 
-	irq_exit();
-	set_irq_regs(old_regs);
+	local_irq_save(flags);
+	ret = handle_irq_desc(irq_to_desc(irq));
+	local_irq_restore(flags);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(generic_handle_irq_safe);
 
 #ifdef CONFIG_IRQ_DOMAIN
 /**
- * handle_domain_nmi - Invoke the handler for a HW irq belonging to a domain
+ * generic_handle_domain_irq - Invoke the handler for a HW irq belonging
+ *                             to a domain.
  * @domain:	The domain where to perform the lookup
  * @hwirq:	The HW irq number to convert to a logical one
- * @regs:	Register file coming from the low-level handling code
- *
- *		This function must be called from an NMI context.
  *
  * Returns:	0 on success, or -EINVAL if conversion has failed
+ *
+ * 		This function must be called from an IRQ context with irq regs
+ * 		initialized.
  */
-int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq,
-		      struct pt_regs *regs)
+int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq)
 {
-	struct pt_regs *old_regs = set_irq_regs(regs);
-	unsigned int irq;
-	int ret = 0;
-
-	/*
-	 * NMI context needs to be setup earlier in order to deal with tracing.
-	 */
-	WARN_ON(!in_nmi());
-
-	irq = irq_find_mapping(domain, hwirq);
+	return handle_irq_desc(irq_resolve_mapping(domain, hwirq));
+}
+EXPORT_SYMBOL_GPL(generic_handle_domain_irq);
 
-	/*
-	 * ack_bad_irq is not NMI-safe, just report
-	 * an invalid interrupt.
-	 */
-	if (likely(irq))
-		generic_handle_irq(irq);
-	else
-		ret = -EINVAL;
+ /**
+ * generic_handle_irq_safe - Invoke the handler for a HW irq belonging
+ *			     to a domain from any context.
+ * @domain:	The domain where to perform the lookup
+ * @hwirq:	The HW irq number to convert to a logical one
+ *
+ * Returns:	0 on success, a negative value on error.
+ *
+ * This function can be called from any context (IRQ or process
+ * context). If the interrupt is marked as 'enforce IRQ-context only' then
+ * the function must be invoked from hard interrupt context.
+ */
+int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq)
+{
+	unsigned long flags;
+	int ret;
 
-	set_irq_regs(old_regs);
+	local_irq_save(flags);
+	ret = handle_irq_desc(irq_resolve_mapping(domain, hwirq));
+	local_irq_restore(flags);
 	return ret;
 }
-#endif
+EXPORT_SYMBOL_GPL(generic_handle_domain_irq_safe);
+
+/**
+ * generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging
+ *                             to a domain.
+ * @domain:	The domain where to perform the lookup
+ * @hwirq:	The HW irq number to convert to a logical one
+ *
+ * Returns:	0 on success, or -EINVAL if conversion has failed
+ *
+ * 		This function must be called from an NMI context with irq regs
+ * 		initialized.
+ **/
+int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq)
+{
+	WARN_ON_ONCE(!in_nmi());
+	return handle_irq_desc(irq_resolve_mapping(domain, hwirq));
+}
 #endif
 
 /* Dynamic interrupt handling */
@@ -746,12 +782,9 @@ void irq_free_descs(unsigned int from, unsigned int cnt)
 	if (from >= nr_irqs || (from + cnt) > nr_irqs)
 		return;
 
-	mutex_lock(&sparse_irq_lock);
+	guard(mutex)(&sparse_irq_lock);
 	for (i = 0; i < cnt; i++)
 		free_desc(from + i);
-
-	bitmap_clear(allocated_irqs, from, cnt);
-	mutex_unlock(&sparse_irq_lock);
 }
 EXPORT_SYMBOL_GPL(irq_free_descs);
 
@@ -768,11 +801,10 @@ EXPORT_SYMBOL_GPL(irq_free_descs);
  *
  * Returns the first irq number or error code
  */
-int __ref
-__irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
-		  struct module *owner, const struct irq_affinity_desc *affinity)
+int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
+			    struct module *owner, const struct irq_affinity_desc *affinity)
 {
-	int start, ret;
+	int start;
 
 	if (!cnt)
 		return -EINVAL;
@@ -790,77 +822,20 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 		from = arch_dynirq_lower_bound(from);
 	}
 
-	mutex_lock(&sparse_irq_lock);
+	guard(mutex)(&sparse_irq_lock);
 
-	start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
-					   from, cnt, 0);
-	ret = -EEXIST;
+	start = irq_find_free_area(from, cnt);
 	if (irq >=0 && start != irq)
-		goto unlock;
+		return -EEXIST;
 
 	if (start + cnt > nr_irqs) {
-		ret = irq_expand_nr_irqs(start + cnt);
-		if (ret)
-			goto unlock;
+		if (!irq_expand_nr_irqs(start + cnt))
+			return -ENOMEM;
 	}
-	ret = alloc_descs(start, cnt, node, affinity, owner);
-unlock:
-	mutex_unlock(&sparse_irq_lock);
-	return ret;
+	return alloc_descs(start, cnt, node, affinity, owner);
 }
 EXPORT_SYMBOL_GPL(__irq_alloc_descs);
 
-#ifdef CONFIG_GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
-/**
- * irq_alloc_hwirqs - Allocate an irq descriptor and initialize the hardware
- * @cnt:	number of interrupts to allocate
- * @node:	node on which to allocate
- *
- * Returns an interrupt number > 0 or 0, if the allocation fails.
- */
-unsigned int irq_alloc_hwirqs(int cnt, int node)
-{
-	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL, NULL);
-
-	if (irq < 0)
-		return 0;
-
-	for (i = irq; cnt > 0; i++, cnt--) {
-		if (arch_setup_hwirq(i, node))
-			goto err;
-		irq_clear_status_flags(i, _IRQ_NOREQUEST);
-	}
-	return irq;
-
-err:
-	for (i--; i >= irq; i--) {
-		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
-		arch_teardown_hwirq(i);
-	}
-	irq_free_descs(irq, cnt);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(irq_alloc_hwirqs);
-
-/**
- * irq_free_hwirqs - Free irq descriptor and cleanup the hardware
- * @from:	Free from irq number
- * @cnt:	number of interrupts to free
- *
- */
-void irq_free_hwirqs(unsigned int from, int cnt)
-{
-	int i, j;
-
-	for (i = from, j = cnt; j > 0; i++, j--) {
-		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
-		arch_teardown_hwirq(i);
-	}
-	irq_free_descs(from, cnt);
-}
-EXPORT_SYMBOL_GPL(irq_free_hwirqs);
-#endif
-
 /**
  * irq_get_next_irq - get next allocated irq number
  * @offset:	where to start the search
@@ -869,30 +844,30 @@ EXPORT_SYMBOL_GPL(irq_free_hwirqs);
  */
 unsigned int irq_get_next_irq(unsigned int offset)
 {
-	return find_next_bit(allocated_irqs, nr_irqs, offset);
+	return irq_find_at_or_after(offset);
 }
 
-struct irq_desc *
-__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
-		    unsigned int check)
+struct irq_desc *__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
+				     unsigned int check)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc;
 
-	if (desc) {
-		if (check & _IRQ_DESC_CHECK) {
-			if ((check & _IRQ_DESC_PERCPU) &&
-			    !irq_settings_is_per_cpu_devid(desc))
-				return NULL;
-
-			if (!(check & _IRQ_DESC_PERCPU) &&
-			    irq_settings_is_per_cpu_devid(desc))
-				return NULL;
-		}
+	desc = irq_to_desc(irq);
+	if (!desc)
+		return NULL;
 
-		if (bus)
-			chip_bus_lock(desc);
-		raw_spin_lock_irqsave(&desc->lock, *flags);
+	if (check & _IRQ_DESC_CHECK) {
+		if ((check & _IRQ_DESC_PERCPU) && !irq_settings_is_per_cpu_devid(desc))
+			return NULL;
+
+		if (!(check & _IRQ_DESC_PERCPU) && irq_settings_is_per_cpu_devid(desc))
+			return NULL;
 	}
+
+	if (bus)
+		chip_bus_lock(desc);
+	raw_spin_lock_irqsave(&desc->lock, *flags);
+
 	return desc;
 }
 
@@ -904,15 +879,11 @@ void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
 		chip_bus_sync_unlock(desc);
 }
 
-int irq_set_percpu_devid_partition(unsigned int irq,
-				   const struct cpumask *affinity)
+int irq_set_percpu_devid(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (!desc)
-		return -EINVAL;
-
-	if (desc->percpu_enabled)
+	if (!desc || desc->percpu_enabled)
 		return -EINVAL;
 
 	desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL);
@@ -920,34 +891,10 @@ int irq_set_percpu_devid_partition(unsigned int irq,
 	if (!desc->percpu_enabled)
 		return -ENOMEM;
 
-	if (affinity)
-		desc->percpu_affinity = affinity;
-	else
-		desc->percpu_affinity = cpu_possible_mask;
-
 	irq_set_percpu_devid_flags(irq);
 	return 0;
 }
 
-int irq_set_percpu_devid(unsigned int irq)
-{
-	return irq_set_percpu_devid_partition(irq, NULL);
-}
-
-int irq_get_percpu_devid_partition(unsigned int irq, struct cpumask *affinity)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	if (!desc || !desc->percpu_enabled)
-		return -EINVAL;
-
-	if (affinity)
-		cpumask_copy(affinity, desc->percpu_affinity);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(irq_get_percpu_devid_partition);
-
 void kstat_incr_irq_this_cpu(unsigned int irq)
 {
 	kstat_incr_irqs_this_cpu(irq_to_desc(irq));
@@ -966,49 +913,67 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	return desc && desc->kstat_irqs ?
-			*per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
-}
-
-static bool irq_is_nmi(struct irq_desc *desc)
-{
-	return desc->istate & IRQS_NMI;
+	return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0;
 }
 
-/**
- * kstat_irqs - Get the statistics for an interrupt
- * @irq:	The interrupt number
- *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. The caller must ensure that the interrupt is not removed
- * concurrently.
- */
-unsigned int kstat_irqs(unsigned int irq)
+static unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned int sum = 0;
 	int cpu;
 
-	if (!desc || !desc->kstat_irqs)
-		return 0;
 	if (!irq_settings_is_per_cpu_devid(desc) &&
 	    !irq_settings_is_per_cpu(desc) &&
 	    !irq_is_nmi(desc))
-	    return desc->tot_count;
+		return data_race(desc->tot_count);
 
-	for_each_possible_cpu(cpu)
-		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
+	for_each_cpu(cpu, cpumask)
+		sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu));
 	return sum;
 }
 
+static unsigned int kstat_irqs(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc || !desc->kstat_irqs)
+		return 0;
+	return kstat_irqs_desc(desc, cpu_possible_mask);
+}
+
+#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT
+
+void kstat_snapshot_irqs(void)
+{
+	struct irq_desc *desc;
+	unsigned int irq;
+
+	for_each_irq_desc(irq, desc) {
+		if (!desc->kstat_irqs)
+			continue;
+		this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt));
+	}
+}
+
+unsigned int kstat_get_irq_since_snapshot(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc || !desc->kstat_irqs)
+		return 0;
+	return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref);
+}
+
+#endif
+
 /**
- * kstat_irqs_usr - Get the statistics for an interrupt
+ * kstat_irqs_usr - Get the statistics for an interrupt from thread context
  * @irq:	The interrupt number
  *
  * Returns the sum of interrupt counts on all cpus since boot for @irq.
- * Contrary to kstat_irqs() this can be called from any context.
- * It uses rcu since a concurrent removal of an interrupt descriptor is
- * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
+ *
+ * It uses rcu to protect the access since a concurrent removal of an
+ * interrupt descriptor is observing an rcu grace period before
+ * delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
@@ -1019,3 +984,17 @@ unsigned int kstat_irqs_usr(unsigned int irq)
 	rcu_read_unlock();
 	return sum;
 }
+
+#ifdef CONFIG_LOCKDEP
+void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class,
+			     struct lock_class_key *request_class)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc) {
+		lockdep_set_class(&desc->lock, lock_class);
+		lockdep_set_class(&desc->request_mutex, request_class);
+	}
+}
+EXPORT_SYMBOL_GPL(__irq_set_lockdep_class);
+#endif