diff options
Diffstat (limited to 'kernel/irq')
| -rw-r--r-- | kernel/irq/Kconfig | 4 | ||||
| -rw-r--r-- | kernel/irq/Makefile | 1 | ||||
| -rw-r--r-- | kernel/irq/chip.c | 28 | ||||
| -rw-r--r-- | kernel/irq/cpuhotplug.c | 82 | ||||
| -rw-r--r-- | kernel/irq/handle.c | 7 | ||||
| -rw-r--r-- | kernel/irq/internals.h | 4 | ||||
| -rw-r--r-- | kernel/irq/irqdomain.c | 177 | ||||
| -rw-r--r-- | kernel/irq/manage.c | 221 | ||||
| -rw-r--r-- | kernel/irq/msi.c | 8 | ||||
| -rw-r--r-- | kernel/irq/proc.c | 2 | ||||
| -rw-r--r-- | kernel/irq/settings.h | 12 |
11 files changed, 426 insertions, 120 deletions
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 9a76e3beda54..3b48dab80164 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -30,6 +30,10 @@ config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ config GENERIC_PENDING_IRQ bool +# Support for generic irq migrating off cpu before the cpu is offline. +config GENERIC_IRQ_MIGRATION + bool + # Alpha specific irq affinity mechanism config AUTO_IRQ_AFFINITY bool diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index d12123526e2b..2fc9cbdf35b6 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -5,5 +5,6 @@ obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o +obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o obj-$(CONFIG_PM_SLEEP) += pm.o obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index e28169dd1c36..15206453b12a 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -21,6 +21,20 @@ #include "internals.h" +static irqreturn_t bad_chained_irq(int irq, void *dev_id) +{ + WARN_ONCE(1, "Chained irq %d should not call an action\n", irq); + return IRQ_NONE; +} + +/* + * Chained handlers should never call action on their IRQ. This default + * action will emit warning if such thing happens. + */ +struct irqaction chained_action = { + .handler = bad_chained_irq, +}; + /** * irq_set_chip - set the irq chip for an irq * @irq: irq number @@ -227,6 +241,13 @@ void irq_enable(struct irq_desc *desc) * disabled. If an interrupt happens, then the interrupt flow * handler masks the line at the hardware level and marks it * pending. + * + * If the interrupt chip does not implement the irq_disable callback, + * a driver can disable the lazy approach for a particular irq line by + * calling 'irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY)'. This can + * be used for devices which cannot disable the interrupt at the + * device level under certain circumstances and have to use + * disable_irq[_nosync] instead. */ void irq_disable(struct irq_desc *desc) { @@ -234,6 +255,8 @@ void irq_disable(struct irq_desc *desc) if (desc->irq_data.chip->irq_disable) { desc->irq_data.chip->irq_disable(&desc->irq_data); irq_state_set_masked(desc); + } else if (irq_settings_disable_unlazy(desc)) { + mask_irq(desc); } } @@ -669,7 +692,7 @@ void handle_percpu_irq(struct irq_desc *desc) if (chip->irq_ack) chip->irq_ack(&desc->irq_data); - handle_irq_event_percpu(desc, desc->action); + handle_irq_event_percpu(desc); if (chip->irq_eoi) chip->irq_eoi(&desc->irq_data); @@ -746,6 +769,8 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, if (desc->irq_data.chip != &no_irq_chip) mask_ack_irq(desc); irq_state_set_disabled(desc); + if (is_chained) + desc->action = NULL; desc->depth = 1; } desc->handle_irq = handle; @@ -755,6 +780,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); + desc->action = &chained_action; irq_startup(desc, true); } } diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c new file mode 100644 index 000000000000..80f4f4e56fed --- /dev/null +++ b/kernel/irq/cpuhotplug.c @@ -0,0 +1,82 @@ +/* + * Generic cpu hotunplug interrupt migration code copied from the + * arch/arm implementation + * + * Copyright (C) Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/interrupt.h> +#include <linux/ratelimit.h> +#include <linux/irq.h> + +#include "internals.h" + +static bool migrate_one_irq(struct irq_desc *desc) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + const struct cpumask *affinity = d->common->affinity; + struct irq_chip *c; + bool ret = false; + + /* + * If this is a per-CPU interrupt, or the affinity does not + * include this CPU, then we have nothing to do. + */ + if (irqd_is_per_cpu(d) || + !cpumask_test_cpu(smp_processor_id(), affinity)) + return false; + + if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + affinity = cpu_online_mask; + ret = true; + } + + c = irq_data_get_irq_chip(d); + if (!c->irq_set_affinity) { + pr_warn_ratelimited("IRQ%u: unable to set affinity\n", d->irq); + } else { + int r = irq_do_set_affinity(d, affinity, false); + if (r) + pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n", + d->irq, r); + } + + return ret; +} + +/** + * irq_migrate_all_off_this_cpu - Migrate irqs away from offline cpu + * + * The current CPU has been marked offline. Migrate IRQs off this CPU. + * If the affinity settings do not allow other CPUs, force them onto any + * available CPU. + * + * Note: we must iterate over all IRQs, whether they have an attached + * action structure or not, as we need to get chained interrupts too. + */ +void irq_migrate_all_off_this_cpu(void) +{ + unsigned int irq; + struct irq_desc *desc; + unsigned long flags; + + local_irq_save(flags); + + for_each_active_irq(irq) { + bool affinity_broken; + + desc = irq_to_desc(irq); + raw_spin_lock(&desc->lock); + affinity_broken = migrate_one_irq(desc); + raw_spin_unlock(&desc->lock); + + if (affinity_broken) + pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n", + irq, smp_processor_id()); + } + + local_irq_restore(flags); +} diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index e25a83b67cce..a302cf9a2126 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -132,11 +132,11 @@ void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action) wake_up_process(action->thread); } -irqreturn_t -handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) +irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval = IRQ_NONE; unsigned int flags = 0, irq = desc->irq_data.irq; + struct irqaction *action = desc->action; do { irqreturn_t res; @@ -184,14 +184,13 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) irqreturn_t handle_irq_event(struct irq_desc *desc) { - struct irqaction *action = desc->action; irqreturn_t ret; desc->istate &= ~IRQS_PENDING; irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); raw_spin_unlock(&desc->lock); - ret = handle_irq_event_percpu(desc, action); + ret = handle_irq_event_percpu(desc); raw_spin_lock(&desc->lock); irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 5ef0c2dbe930..05c2188271b8 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -18,6 +18,8 @@ extern bool noirqdebug; +extern struct irqaction chained_action; + /* * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run @@ -81,7 +83,7 @@ extern void irq_mark_irq(unsigned int irq); extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); -irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action); +irqreturn_t handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index dc9d27c0c158..22aa9612ef7c 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -27,6 +27,57 @@ static int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, irq_hw_number_t hwirq, int node); static void irq_domain_check_hierarchy(struct irq_domain *domain); +struct irqchip_fwid { + struct fwnode_handle fwnode; + char *name; + void *data; +}; + +/** + * irq_domain_alloc_fwnode - Allocate a fwnode_handle suitable for + * identifying an irq domain + * @data: optional user-provided data + * + * Allocate a struct device_node, and return a poiner to the embedded + * fwnode_handle (or NULL on failure). + */ +struct fwnode_handle *irq_domain_alloc_fwnode(void *data) +{ + struct irqchip_fwid *fwid; + char *name; + + fwid = kzalloc(sizeof(*fwid), GFP_KERNEL); + name = kasprintf(GFP_KERNEL, "irqchip@%p", data); + + if (!fwid || !name) { + kfree(fwid); + kfree(name); + return NULL; + } + + fwid->name = name; + fwid->data = data; + fwid->fwnode.type = FWNODE_IRQCHIP; + return &fwid->fwnode; +} + +/** + * irq_domain_free_fwnode - Free a non-OF-backed fwnode_handle + * + * Free a fwnode_handle allocated with irq_domain_alloc_fwnode. + */ +void irq_domain_free_fwnode(struct fwnode_handle *fwnode) +{ + struct irqchip_fwid *fwid; + + if (WARN_ON(fwnode->type != FWNODE_IRQCHIP)) + return; + + fwid = container_of(fwnode, struct irqchip_fwid, fwnode); + kfree(fwid->name); + kfree(fwid); +} + /** * __irq_domain_add() - Allocate a new irq_domain data structure * @of_node: optional device-tree node of the interrupt controller @@ -40,23 +91,28 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain); * Allocates and initialize and irq_domain structure. * Returns pointer to IRQ domain, or NULL on failure. */ -struct irq_domain *__irq_domain_add(struct device_node *of_node, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data) { 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)); if (WARN_ON(!domain)) return NULL; + of_node_get(of_node); + /* Fill structure */ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); domain->ops = ops; domain->host_data = host_data; - domain->of_node = of_node_get(of_node); + domain->fwnode = fwnode; domain->hwirq_max = hwirq_max; domain->revmap_size = size; domain->revmap_direct_max_irq = direct_max; @@ -102,7 +158,7 @@ void irq_domain_remove(struct irq_domain *domain) pr_debug("Removed domain %s\n", domain->name); - of_node_put(domain->of_node); + of_node_put(irq_domain_get_of_node(domain)); kfree(domain); } EXPORT_SYMBOL_GPL(irq_domain_remove); @@ -133,7 +189,7 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, { struct irq_domain *domain; - domain = __irq_domain_add(of_node, size, size, 0, ops, host_data); + domain = __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data); if (!domain) return NULL; @@ -177,7 +233,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, { struct irq_domain *domain; - domain = __irq_domain_add(of_node, first_hwirq + size, + domain = __irq_domain_add(of_node_to_fwnode(of_node), first_hwirq + size, first_hwirq + size, 0, ops, host_data); if (domain) irq_domain_associate_many(domain, first_irq, first_hwirq, size); @@ -187,12 +243,12 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, EXPORT_SYMBOL_GPL(irq_domain_add_legacy); /** - * irq_find_matching_host() - Locates a domain for a given device node - * @node: device-tree node of the interrupt controller + * irq_find_matching_fwnode() - Locates a domain for a given fwnode + * @fwnode: FW descriptor of the interrupt controller * @bus_token: domain-specific data */ -struct irq_domain *irq_find_matching_host(struct device_node *node, - enum irq_domain_bus_token bus_token) +struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode, + enum irq_domain_bus_token bus_token) { struct irq_domain *h, *found = NULL; int rc; @@ -209,9 +265,9 @@ struct irq_domain *irq_find_matching_host(struct device_node *node, mutex_lock(&irq_domain_mutex); list_for_each_entry(h, &irq_domain_list, link) { if (h->ops->match) - rc = h->ops->match(h, node, bus_token); + rc = h->ops->match(h, to_of_node(fwnode), bus_token); else - rc = ((h->of_node != NULL) && (h->of_node == node) && + rc = ((fwnode != NULL) && (h->fwnode == fwnode) && ((bus_token == DOMAIN_BUS_ANY) || (h->bus_token == bus_token))); @@ -223,7 +279,7 @@ struct irq_domain *irq_find_matching_host(struct device_node *node, mutex_unlock(&irq_domain_mutex); return found; } -EXPORT_SYMBOL_GPL(irq_find_matching_host); +EXPORT_SYMBOL_GPL(irq_find_matching_fwnode); /** * irq_set_default_host() - Set a "default" irq domain @@ -336,10 +392,12 @@ EXPORT_SYMBOL_GPL(irq_domain_associate); void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, irq_hw_number_t hwirq_base, int count) { + struct device_node *of_node; int i; + of_node = irq_domain_get_of_node(domain); pr_debug("%s(%s, irqbase=%i, hwbase=%i, count=%i)\n", __func__, - of_node_full_name(domain->of_node), irq_base, (int)hwirq_base, count); + of_node_full_name(of_node), irq_base, (int)hwirq_base, count); for (i = 0; i < count; i++) { irq_domain_associate(domain, irq_base + i, hwirq_base + i); @@ -359,12 +417,14 @@ EXPORT_SYMBOL_GPL(irq_domain_associate_many); */ unsigned int irq_create_direct_mapping(struct irq_domain *domain) { + struct device_node *of_node; unsigned int virq; if (domain == NULL) domain = irq_default_domain; - virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); + of_node = irq_domain_get_of_node(domain); + virq = irq_alloc_desc_from(1, of_node_to_nid(of_node)); if (!virq) { pr_debug("create_direct virq allocation failed\n"); return 0; @@ -399,6 +459,7 @@ EXPORT_SYMBOL_GPL(irq_create_direct_mapping); unsigned int irq_create_mapping(struct irq_domain *domain, irq_hw_number_t hwirq) { + struct device_node *of_node; int virq; pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); @@ -412,6 +473,8 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } pr_debug("-> using domain @%p\n", domain); + of_node = irq_domain_get_of_node(domain); + /* Check if mapping already exists */ virq = irq_find_mapping(domain, hwirq); if (virq) { @@ -420,8 +483,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } /* Allocate a virtual interrupt number */ - virq = irq_domain_alloc_descs(-1, 1, hwirq, - of_node_to_nid(domain->of_node)); + virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node)); if (virq <= 0) { pr_debug("-> virq allocation failed\n"); return 0; @@ -433,7 +495,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } pr_debug("irq %lu on domain %s mapped to virtual irq %u\n", - hwirq, of_node_full_name(domain->of_node), virq); + hwirq, of_node_full_name(of_node), virq); return virq; } @@ -460,10 +522,12 @@ EXPORT_SYMBOL_GPL(irq_create_mapping); 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(domain->of_node)); + of_node_to_nid(of_node)); if (unlikely(ret < 0)) return ret; @@ -472,28 +536,56 @@ int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base, } EXPORT_SYMBOL_GPL(irq_create_strict_mappings); -unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) +static int irq_domain_translate(struct irq_domain *d, + struct irq_fwspec *fwspec, + irq_hw_number_t *hwirq, unsigned int *type) +{ +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + if (d->ops->translate) + return d->ops->translate(d, fwspec, hwirq, type); +#endif + if (d->ops->xlate) + return d->ops->xlate(d, to_of_node(fwspec->fwnode), + fwspec->param, fwspec->param_count, + hwirq, type); + + /* If domain has no translation, then we assume interrupt line */ + *hwirq = fwspec->param[0]; + return 0; +} + +static void of_phandle_args_to_fwspec(struct of_phandle_args *irq_data, + struct irq_fwspec *fwspec) +{ + int i; + + fwspec->fwnode = irq_data->np ? &irq_data->np->fwnode : NULL; + fwspec->param_count = irq_data->args_count; + + for (i = 0; i < irq_data->args_count; i++) + fwspec->param[i] = irq_data->args[i]; +} + +unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) { struct irq_domain *domain; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; int virq; - domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain; + if (fwspec->fwnode) + domain = irq_find_matching_fwnode(fwspec->fwnode, DOMAIN_BUS_ANY); + else + domain = irq_default_domain; + if (!domain) { pr_warn("no irq domain found for %s !\n", - of_node_full_name(irq_data->np)); + of_node_full_name(to_of_node(fwspec->fwnode))); return 0; } - /* If domain has no translation, then we assume interrupt line */ - if (domain->ops->xlate == NULL) - hwirq = irq_data->args[0]; - else { - if (domain->ops->xlate(domain, irq_data->np, irq_data->args, - irq_data->args_count, &hwirq, &type)) - return 0; - } + if (irq_domain_translate(domain, fwspec, &hwirq, &type)) + return 0; if (irq_domain_is_hierarchy(domain)) { /* @@ -504,7 +596,7 @@ unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) if (virq) return virq; - virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, irq_data); + virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, fwspec); if (virq <= 0) return 0; } else { @@ -520,6 +612,15 @@ unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) irq_set_irq_type(virq, type); return virq; } +EXPORT_SYMBOL_GPL(irq_create_fwspec_mapping); + +unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) +{ + struct irq_fwspec fwspec; + + of_phandle_args_to_fwspec(irq_data, &fwspec); + return irq_create_fwspec_mapping(&fwspec); +} EXPORT_SYMBOL_GPL(irq_create_of_mapping); /** @@ -590,14 +691,16 @@ static int virq_debug_show(struct seq_file *m, void *private) "name", "mapped", "linear-max", "direct-max", "devtree-node"); mutex_lock(&irq_domain_mutex); list_for_each_entry(domain, &irq_domain_list, link) { + struct device_node *of_node; int count = 0; + of_node = irq_domain_get_of_node(domain); radix_tree_for_each_slot(slot, &domain->revmap_tree, &iter, 0) count++; seq_printf(m, "%c%-16s %6u %10u %10u %s\n", domain == irq_default_domain ? '*' : ' ', domain->name, domain->revmap_size + count, domain->revmap_size, domain->revmap_direct_max_irq, - domain->of_node ? of_node_full_name(domain->of_node) : ""); + of_node ? of_node_full_name(of_node) : ""); } mutex_unlock(&irq_domain_mutex); @@ -751,11 +854,11 @@ static int irq_domain_alloc_descs(int virq, unsigned int cnt, #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY /** - * irq_domain_add_hierarchy - Add a irqdomain into the hierarchy + * irq_domain_create_hierarchy - Add a irqdomain into the hierarchy * @parent: Parent irq domain to associate with the new domain * @flags: Irq domain flags associated to the domain * @size: Size of the domain. See below - * @node: Optional device-tree node of the interrupt controller + * @fwnode: Optional fwnode of the interrupt controller * @ops: Pointer to the interrupt domain callbacks * @host_data: Controller private data pointer * @@ -765,19 +868,19 @@ static int irq_domain_alloc_descs(int virq, unsigned int cnt, * domain flags are set. * Returns pointer to IRQ domain, or NULL on failure. */ -struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, +struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, unsigned int flags, unsigned int size, - struct device_node *node, + struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data) { struct irq_domain *domain; if (size) - domain = irq_domain_add_linear(node, size, ops, host_data); + domain = irq_domain_create_linear(fwnode, size, ops, host_data); else - domain = irq_domain_add_tree(node, ops, host_data); + domain = irq_domain_create_tree(fwnode, ops, host_data); if (domain) { domain->parent = parent; domain->flags |= flags; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f9a59f6cabd2..a71175ff98d5 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -258,37 +258,6 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) } EXPORT_SYMBOL_GPL(irq_set_affinity_hint); -/** - * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt - * @irq: interrupt number to set affinity - * @vcpu_info: vCPU specific data - * - * This function uses the vCPU specific data to set the vCPU - * affinity for an irq. The vCPU specific data is passed from - * outside, such as KVM. One example code path is as below: - * KVM -> IOMMU -> irq_set_vcpu_affinity(). - */ -int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info) -{ - unsigned long flags; - struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); - struct irq_data *data; - struct irq_chip *chip; - int ret = -ENOSYS; - - if (!desc) - return -EINVAL; - - data = irq_desc_get_irq_data(desc); - chip = irq_data_get_irq_chip(data); - if (chip && chip->irq_set_vcpu_affinity) - ret = chip->irq_set_vcpu_affinity(data, vcpu_info); - irq_put_desc_unlock(desc, flags); - - return ret; -} -EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity); - static void irq_affinity_notify(struct work_struct *work) { struct irq_affinity_notify *notify = @@ -424,6 +393,37 @@ setup_affinity(struct irq_desc *desc, struct cpumask *mask) } #endif +/** + * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt + * @irq: interrupt number to set affinity + * @vcpu_info: vCPU specific data + * + * This function uses the vCPU specific data to set the vCPU + * affinity for an irq. The vCPU specific data is passed from + * outside, such as KVM. One example code path is as below: + * KVM -> IOMMU -> irq_set_vcpu_affinity(). + */ +int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + struct irq_data *data; + struct irq_chip *chip; + int ret = -ENOSYS; + + if (!desc) + return -EINVAL; + + data = irq_desc_get_irq_data(desc); + chip = irq_data_get_irq_chip(data); + if (chip && chip->irq_set_vcpu_affinity) + ret = chip->irq_set_vcpu_affinity(data, vcpu_info); + irq_put_desc_unlock(desc, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity); + void __disable_irq(struct irq_desc *desc) { if (!desc->depth++) @@ -730,6 +730,12 @@ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id) return IRQ_NONE; } +static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) +{ + WARN(1, "Secondary action handler called for irq %d\n", irq); + return IRQ_NONE; +} + static int irq_wait_for_interrupt(struct irqaction *action) { set_current_state(TASK_INTERRUPTIBLE); @@ -756,7 +762,8 @@ static int irq_wait_for_interrupt(struct irqaction *action) static void irq_finalize_oneshot(struct irq_desc *desc, struct irqaction *action) { - if (!(desc->istate & IRQS_ONESHOT)) + if (!(desc->istate & IRQS_ONESHOT) || + action->handler == irq_forced_secondary_handler) return; again: chip_bus_lock(desc); @@ -910,6 +917,18 @@ static void irq_thread_dtor(struct callback_head *unused) irq_finalize_oneshot(desc, action); } +static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) +{ + struct irqaction *secondary = action->secondary; + + if (WARN_ON_ONCE(!secondary)) + return; + + raw_spin_lock_irq(&desc->lock); + __irq_wake_thread(desc, secondary); + raw_spin_unlock_irq(&desc->lock); +} + /* * Interrupt handler thread */ @@ -940,6 +959,8 @@ static int irq_thread(void *data) action_ret = handler_fn(desc, action); if (action_ret == IRQ_HANDLED) atomic_inc(&desc->threads_handled); + if (action_ret == IRQ_WAKE_THREAD) + irq_wake_secondary(desc, action); wake_threads_waitq(desc); } @@ -984,20 +1005,36 @@ void irq_wake_thread(unsigned int irq, void *dev_id) } EXPORT_SYMBOL_GPL(irq_wake_thread); -static void irq_setup_forced_threading(struct irqaction *new) +static int irq_setup_forced_threading(struct irqaction *new) { if (!force_irqthreads) - return; + return 0; if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) - return; + return 0; new->flags |= IRQF_ONESHOT; - if (!new->thread_fn) { - set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); - new->thread_fn = new->handler; - new->handler = irq_default_primary_handler; + /* + * Handle the case where we have a real primary handler and a + * thread handler. We force thread them as well by creating a + * secondary action. + */ + if (new->handler != irq_default_primary_handler && new->thread_fn) { + /* Allocate the secondary action */ + new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL); + if (!new->secondary) + return -ENOMEM; + new->secondary->handler = irq_forced_secondary_handler; + new->secondary->thread_fn = new->thread_fn; + new->secondary->dev_id = new->dev_id; + new->secondary->irq = new->irq; + new->secondary->name = new->name; } + /* Deal with the primary handler */ + set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); + new->thread_fn = new->handler; + new->handler = irq_default_primary_handler; + return 0; } static int irq_request_resources(struct irq_desc *desc) @@ -1017,6 +1054,48 @@ static void irq_release_resources(struct irq_desc *desc) c->irq_release_resources(d); } +static int +setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) +{ + struct task_struct *t; + struct sched_param param = { + .sched_priority = MAX_USER_RT_PRIO/2, + }; + + if (!secondary) { + t = kthread_create(irq_thread, new, "irq/%d-%s", irq, + new->name); + } else { + t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq, + new->name); + param.sched_priority -= 1; + } + + if (IS_ERR(t)) + return PTR_ERR(t); + + sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m); + + /* + * We keep the reference to the task struct even if + * the thread dies to avoid that the interrupt code + * references an already freed task_struct. + */ + get_task_struct(t); + new->thread = t; + /* + * Tell the thread to set its affinity. This is + * important for shared interrupt handlers as we do + * not invoke setup_affinity() for the secondary + * handlers as everything is already set up. Even for + * interrupts marked with IRQF_NO_BALANCE this is + * correct as we want the thread to move to the cpu(s) + * on which the requesting code placed the interrupt. + */ + set_bit(IRQTF_AFFINITY, &new->thread_flags); + return 0; +} + /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. @@ -1037,6 +1116,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (!try_module_get(desc->owner)) return -ENODEV; + new->irq = irq; + /* * Check whether the interrupt nests into another interrupt * thread. @@ -1054,8 +1135,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ new->handler = irq_nested_primary_handler; } else { - if (irq_settings_can_thread(desc)) - irq_setup_forced_threading(new); + if (irq_settings_can_thread(desc)) { + ret = irq_setup_forced_threading(new); + if (ret) + goto out_mput; + } } /* @@ -1064,37 +1148,14 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * thread. */ if (new->thread_fn && !nested) { - struct task_struct *t; - static const struct sched_param param = { - .sched_priority = MAX_USER_RT_PRIO/2, - }; - - t = kthread_create(irq_thread, new, "irq/%d-%s", irq, - new->name); - if (IS_ERR(t)) { - ret = PTR_ERR(t); + ret = setup_irq_thread(new, irq, false); + if (ret) goto out_mput; + if (new->secondary) { + ret = setup_irq_thread(new->secondary, irq, true); + if (ret) + goto out_thread; } - - sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m); - - /* - * We keep the reference to the task struct even if - * the thread dies to avoid that the interrupt code - * references an already freed task_struct. - */ - get_task_struct(t); - new->thread = t; - /* - * Tell the thread to set its affinity. This is - * important for shared interrupt handlers as we do - * not invoke setup_affinity() for the secondary - * handlers as everything is already set up. Even for - * interrupts marked with IRQF_NO_BALANCE this is - * correct as we want the thread to move to the cpu(s) - * on which the requesting code placed the interrupt. - */ - set_bit(IRQTF_AFFINITY, &new->thread_flags); } if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { @@ -1267,7 +1328,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irq, nmsk, omsk); } - new->irq = irq; *old_ptr = new; irq_pm_install_action(desc, new); @@ -1293,6 +1353,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ if (new->thread) wake_up_process(new->thread); + if (new->secondary) + wake_up_process(new->secondary->thread); register_irq_proc(irq, desc); new->dir = NULL; @@ -1323,6 +1385,13 @@ out_thread: kthread_stop(t); put_task_struct(t); } + if (new->secondary && new->secondary->thread) { + struct task_struct *t = new->secondary->thread; + + new->secondary->thread = NULL; + kthread_stop(t); + put_task_struct(t); + } out_mput: module_put(desc->owner); return ret; @@ -1394,6 +1463,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) /* If this was the last handler, shut down the IRQ line: */ if (!desc->action) { + irq_settings_clr_disable_unlazy(desc); irq_shutdown(desc); irq_release_resources(desc); } @@ -1430,9 +1500,14 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) if (action->thread) { kthread_stop(action->thread); put_task_struct(action->thread); + if (action->secondary && action->secondary->thread) { + kthread_stop(action->secondary->thread); + put_task_struct(action->secondary->thread); + } } module_put(desc->owner); + kfree(action->secondary); return action; } @@ -1576,8 +1651,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, retval = __setup_irq(irq, desc, action); chip_bus_sync_unlock(desc); - if (retval) + if (retval) { + kfree(action->secondary); kfree(action); + } #ifdef CONFIG_DEBUG_SHIRQ_FIXME if (!retval && (irqflags & IRQF_SHARED)) { diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index be9149f62eb8..6b0c0b74a2a1 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -235,11 +235,11 @@ static void msi_domain_update_chip_ops(struct msi_domain_info *info) /** * msi_create_irq_domain - Create a MSI interrupt domain - * @of_node: Optional device-tree node of the interrupt controller + * @fwnode: Optional fwnode of the interrupt controller * @info: MSI domain info * @parent: Parent irq domain */ -struct irq_domain *msi_create_irq_domain(struct device_node *node, +struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent) { @@ -248,8 +248,8 @@ struct irq_domain *msi_create_irq_domain(struct device_node *node, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) msi_domain_update_chip_ops(info); - return irq_domain_add_hierarchy(parent, 0, 0, node, &msi_domain_ops, - info); + return irq_domain_create_hierarchy(parent, 0, 0, fwnode, + &msi_domain_ops, info); } /** diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index a50ddc9417ff..a916cf144b65 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -475,7 +475,7 @@ int show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(j) any_count |= kstat_irqs_cpu(i, j); action = desc->action; - if (!action && !any_count) + if ((!action || action == &chained_action) && !any_count) goto out; seq_printf(p, "%*d: ", prec, i); diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 3320b84cc60f..320579d89091 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -15,6 +15,7 @@ enum { _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, _IRQ_IS_POLLED = IRQ_IS_POLLED, + _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; @@ -28,6 +29,7 @@ enum { #define IRQ_NESTED_THREAD GOT_YOU_MORON #define IRQ_PER_CPU_DEVID GOT_YOU_MORON #define IRQ_IS_POLLED GOT_YOU_MORON +#define IRQ_DISABLE_UNLAZY GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON @@ -154,3 +156,13 @@ static inline bool irq_settings_is_polled(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_IS_POLLED; } + +static inline bool irq_settings_disable_unlazy(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_DISABLE_UNLAZY; +} + +static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY; +} |