diff options
Diffstat (limited to 'kernel/irq')
| -rw-r--r-- | kernel/irq/Kconfig | 2 | ||||
| -rw-r--r-- | kernel/irq/affinity.c | 7 | ||||
| -rw-r--r-- | kernel/irq/chip.c | 56 | ||||
| -rw-r--r-- | kernel/irq/cpuhotplug.c | 4 | ||||
| -rw-r--r-- | kernel/irq/debugfs.c | 11 | ||||
| -rw-r--r-- | kernel/irq/generic-chip.c | 4 | ||||
| -rw-r--r-- | kernel/irq/handle.c | 11 | ||||
| -rw-r--r-- | kernel/irq/internals.h | 4 | ||||
| -rw-r--r-- | kernel/irq/ipi.c | 16 | ||||
| -rw-r--r-- | kernel/irq/irq_sim.c | 2 | ||||
| -rw-r--r-- | kernel/irq/irqdesc.c | 54 | ||||
| -rw-r--r-- | kernel/irq/irqdomain.c | 23 | ||||
| -rw-r--r-- | kernel/irq/manage.c | 92 | ||||
| -rw-r--r-- | kernel/irq/matrix.c | 2 | ||||
| -rw-r--r-- | kernel/irq/msi.c | 807 | ||||
| -rw-r--r-- | kernel/irq/pm.c | 2 | ||||
| -rw-r--r-- | kernel/irq/proc.c | 8 |
17 files changed, 777 insertions, 328 deletions
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 10929eda9825..db3d174c53d4 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -24,6 +24,7 @@ config GENERIC_IRQ_SHOW_LEVEL # Supports effective affinity mask config GENERIC_IRQ_EFFECTIVE_AFF_MASK + depends on SMP bool # Support for delayed migration from interrupt context @@ -82,6 +83,7 @@ config IRQ_FASTEOI_HIERARCHY_HANDLERS # Generic IRQ IPI support config GENERIC_IRQ_IPI bool + depends on SMP select IRQ_DOMAIN_HIERARCHY # Generic MSI interrupt support diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f7ff8919dc9b..d9a5c1d65a79 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -258,7 +258,7 @@ static int __irq_build_affinity_masks(unsigned int startvec, nodemask_t nodemsk = NODE_MASK_NONE; struct node_vectors *node_vectors; - if (!cpumask_weight(cpu_mask)) + if (cpumask_empty(cpu_mask)) return 0; nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); @@ -269,8 +269,9 @@ static int __irq_build_affinity_masks(unsigned int startvec, */ if (numvecs <= nodes) { for_each_node_mask(n, nodemsk) { - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, - node_to_cpumask[n]); + /* Ensure that only CPUs which are in both masks are set */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); if (++curvec == last_affv) curvec = firstvec; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index f895265d7548..8ac37e8e738a 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -38,7 +38,7 @@ struct irqaction chained_action = { * @irq: irq number * @chip: pointer to irq chip description structure */ -int irq_set_chip(unsigned int irq, struct irq_chip *chip) +int irq_set_chip(unsigned int irq, const struct irq_chip *chip) { unsigned long flags; struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); @@ -46,10 +46,7 @@ int irq_set_chip(unsigned int irq, struct irq_chip *chip) if (!desc) return -EINVAL; - if (!chip) - chip = &no_irq_chip; - - desc->irq_data.chip = chip; + desc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip); irq_put_desc_unlock(desc, flags); /* * For !CONFIG_SPARSE_IRQ make the irq show up in @@ -191,7 +188,8 @@ enum { #ifdef CONFIG_SMP static int -__irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) +__irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff, + bool force) { struct irq_data *d = irq_desc_get_irq_data(desc); @@ -227,7 +225,8 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) } #else static __always_inline int -__irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) +__irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff, + bool force) { return IRQ_STARTUP_NORMAL; } @@ -255,7 +254,7 @@ static int __irq_startup(struct irq_desc *desc) int irq_startup(struct irq_desc *desc, bool resend, bool force) { struct irq_data *d = irq_desc_get_irq_data(desc); - struct cpumask *aff = irq_data_get_affinity_mask(d); + const struct cpumask *aff = irq_data_get_affinity_mask(d); int ret = 0; desc->depth = 0; @@ -575,8 +574,6 @@ EXPORT_SYMBOL_GPL(handle_simple_irq); */ void handle_untracked_irq(struct irq_desc *desc) { - unsigned int flags = 0; - raw_spin_lock(&desc->lock); if (!irq_may_run(desc)) @@ -593,7 +590,7 @@ void handle_untracked_irq(struct irq_desc *desc) irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); raw_spin_unlock(&desc->lock); - __handle_irq_event_percpu(desc, &flags); + __handle_irq_event_percpu(desc); raw_spin_lock(&desc->lock); irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); @@ -1011,8 +1008,10 @@ __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) + if (is_chained) { desc->action = NULL; + WARN_ON(irq_chip_pm_put(irq_desc_get_irq_data(desc))); + } desc->depth = 1; } desc->handle_irq = handle; @@ -1038,6 +1037,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); desc->action = &chained_action; + WARN_ON(irq_chip_pm_get(irq_desc_get_irq_data(desc))); irq_activate_and_startup(desc, IRQ_RESEND); } } @@ -1075,7 +1075,7 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, EXPORT_SYMBOL_GPL(irq_set_chained_handler_and_data); void -irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, +irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name) { irq_set_chip(irq, chip); @@ -1518,7 +1518,8 @@ int irq_chip_request_resources_parent(struct irq_data *data) if (data->chip->irq_request_resources) return data->chip->irq_request_resources(data); - return -ENOSYS; + /* no error on missing optional irq_chip::irq_request_resources */ + return 0; } EXPORT_SYMBOL_GPL(irq_chip_request_resources_parent); @@ -1560,6 +1561,14 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return 0; } +static struct device *irq_get_parent_device(struct irq_data *data) +{ + if (data->domain) + return data->domain->dev; + + return NULL; +} + /** * irq_chip_pm_get - Enable power for an IRQ chip * @data: Pointer to interrupt specific data @@ -1569,17 +1578,13 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) */ int irq_chip_pm_get(struct irq_data *data) { - int retval; + struct device *dev = irq_get_parent_device(data); + int retval = 0; - if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) { - retval = pm_runtime_get_sync(data->chip->parent_device); - if (retval < 0) { - pm_runtime_put_noidle(data->chip->parent_device); - return retval; - } - } + if (IS_ENABLED(CONFIG_PM) && dev) + retval = pm_runtime_resume_and_get(dev); - return 0; + return retval; } /** @@ -1592,10 +1597,11 @@ int irq_chip_pm_get(struct irq_data *data) */ int irq_chip_pm_put(struct irq_data *data) { + struct device *dev = irq_get_parent_device(data); int retval = 0; - if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) - retval = pm_runtime_put(data->chip->parent_device); + if (IS_ENABLED(CONFIG_PM) && dev) + retval = pm_runtime_put(dev); return (retval < 0) ? retval : 0; } diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 39a41c56ad4f..1ed2b1739363 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -176,10 +176,10 @@ static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) { const struct cpumask *hk_mask; - if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + if (!housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) return false; - hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) return false; diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index e4cff358b437..bbcaac64038e 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -30,7 +30,7 @@ static void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, static void irq_debug_show_masks(struct seq_file *m, struct irq_desc *desc) { struct irq_data *data = irq_desc_get_irq_data(desc); - struct cpumask *msk; + const struct cpumask *msk; msk = irq_data_get_affinity_mask(data); seq_printf(m, "affinity: %*pbl\n", cpumask_pr_args(msk)); @@ -58,6 +58,7 @@ static const struct irq_bit_descr irqchip_flags[] = { BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI), BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI), BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND), + BIT_MASK_DESCR(IRQCHIP_IMMUTABLE), }; static void @@ -69,8 +70,12 @@ irq_debug_show_chip(struct seq_file *m, struct irq_data *data, int ind) seq_printf(m, "chip: None\n"); return; } - seq_printf(m, "%*schip: %s\n", ind, "", chip->name); - seq_printf(m, "%*sflags: 0x%lx\n", ind + 1, "", chip->flags); + seq_printf(m, "%*schip: ", ind, ""); + if (chip->irq_print_chip) + chip->irq_print_chip(data, m); + else + seq_printf(m, "%s", chip->name); + seq_printf(m, "\n%*sflags: 0x%lx\n", ind + 1, "", chip->flags); irq_debug_show_bits(m, ind, chip->flags, irqchip_flags, ARRAY_SIZE(irqchip_flags)); } diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 6f29bf4c8515..c653cd31548d 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -431,7 +431,7 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, return 0; } -static void irq_unmap_generic_chip(struct irq_domain *d, unsigned int virq) +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; @@ -451,7 +451,7 @@ static void irq_unmap_generic_chip(struct irq_domain *d, unsigned int virq) } -struct irq_domain_ops irq_generic_chip_ops = { +const struct irq_domain_ops irq_generic_chip_ops = { .map = irq_map_generic_chip, .unmap = irq_unmap_generic_chip, .xlate = irq_domain_xlate_onetwocell, diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 27182003b879..9489f93b3db3 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -136,7 +136,7 @@ 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, unsigned int *flags) +irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval = IRQ_NONE; unsigned int irq = desc->irq_data.irq; @@ -174,10 +174,6 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags } __irq_wake_thread(desc, action); - - fallthrough; /* to add to randomness */ - case IRQ_HANDLED: - *flags |= action->flags; break; default: @@ -193,11 +189,10 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval; - unsigned int flags = 0; - retval = __handle_irq_event_percpu(desc, &flags); + retval = __handle_irq_event_percpu(desc); - add_interrupt_randomness(desc->irq_data.irq, flags); + add_interrupt_randomness(desc->irq_data.irq); if (!irq_settings_no_debug(desc)) note_interrupt(desc, retval); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 54363527feea..f09c60393e55 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -29,12 +29,14 @@ extern struct irqaction chained_action; * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed * IRQTF_AFFINITY - irq thread is requested to adjust affinity * IRQTF_FORCED_THREAD - irq action is force threaded + * IRQTF_READY - signals that irq thread is ready */ enum { IRQTF_RUNTHREAD, IRQTF_WARNED, IRQTF_AFFINITY, IRQTF_FORCED_THREAD, + IRQTF_READY, }; /* @@ -103,7 +105,7 @@ extern int __irq_get_irqchip_state(struct irq_data *data, extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); -irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags); +irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event(struct irq_desc *desc); diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c index 08ce7da3b57c..bbd945bacef0 100644 --- a/kernel/irq/ipi.c +++ b/kernel/irq/ipi.c @@ -115,11 +115,11 @@ free_descs: int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest) { struct irq_data *data = irq_get_irq_data(irq); - struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL; + const struct cpumask *ipimask; struct irq_domain *domain; unsigned int nr_irqs; - if (!irq || !data || !ipimask) + if (!irq || !data) return -EINVAL; domain = data->domain; @@ -131,7 +131,8 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest) return -EINVAL; } - if (WARN_ON(!cpumask_subset(dest, ipimask))) + ipimask = irq_data_get_affinity_mask(data); + if (!ipimask || WARN_ON(!cpumask_subset(dest, ipimask))) /* * Must be destroying a subset of CPUs to which this IPI * was set up to target @@ -162,12 +163,13 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest) irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu) { struct irq_data *data = irq_get_irq_data(irq); - struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL; + const struct cpumask *ipimask; - if (!data || !ipimask || cpu >= nr_cpu_ids) + if (!data || cpu >= nr_cpu_ids) return INVALID_HWIRQ; - if (!cpumask_test_cpu(cpu, ipimask)) + ipimask = irq_data_get_affinity_mask(data); + if (!ipimask || !cpumask_test_cpu(cpu, ipimask)) return INVALID_HWIRQ; /* @@ -186,7 +188,7 @@ EXPORT_SYMBOL_GPL(ipi_get_hwirq); static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data, const struct cpumask *dest, unsigned int cpu) { - struct cpumask *ipimask = irq_data_get_affinity_mask(data); + const struct cpumask *ipimask = irq_data_get_affinity_mask(data); if (!chip || !ipimask) return -EINVAL; diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c index 0cd02efa3a74..dd76323ea3fd 100644 --- a/kernel/irq/irq_sim.c +++ b/kernel/irq/irq_sim.c @@ -181,7 +181,7 @@ struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, goto err_free_bitmap; work_ctx->irq_count = num_irqs; - init_irq_work(&work_ctx->work, irq_sim_handle_irq); + work_ctx->work = IRQ_WORK_INIT_HARD(irq_sim_handle_irq); return work_ctx->domain; diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 2267e6527db3..a91f9001103c 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -251,7 +251,7 @@ static ssize_t actions_show(struct kobject *kobj, char *p = ""; raw_spin_lock_irq(&desc->lock); - for (action = desc->action; action != NULL; action = action->next) { + for_each_action_of_desc(desc, action) { ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s", p, action->name); p = ","; @@ -407,6 +407,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_rcu_head(&desc->rcu); + init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); @@ -575,6 +576,7 @@ int __init early_irq_init(void) raw_spin_lock_init(&desc[i].lock); lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); mutex_init(&desc[i].request_mutex); + init_waitqueue_head(&desc[i].wait_for_threads); desc_set_defaults(i, &desc[i], node, NULL, NULL); } return arch_early_irq_init(); @@ -640,7 +642,7 @@ int handle_irq_desc(struct irq_desc *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() && handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); @@ -662,6 +664,29 @@ int generic_handle_irq(unsigned int irq) } EXPORT_SYMBOL_GPL(generic_handle_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; + + 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 /** * generic_handle_domain_irq - Invoke the handler for a HW irq belonging @@ -676,11 +701,34 @@ EXPORT_SYMBOL_GPL(generic_handle_irq); */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { - WARN_ON_ONCE(!in_irq()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); + /** + * 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; + + local_irq_save(flags); + ret = handle_irq_desc(irq_resolve_mapping(domain, hwirq)); + local_irq_restore(flags); + return ret; +} +EXPORT_SYMBOL_GPL(generic_handle_domain_irq_safe); + /** * generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging * to a domain. diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index bf38c546aa25..8fe1da9614ee 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -147,7 +147,8 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int s static atomic_t unknown_domains; if (WARN_ON((size && direct_max) || - (!IS_ENABLED(CONFIG_IRQ_DOMAIN_NOMAP) && direct_max))) + (!IS_ENABLED(CONFIG_IRQ_DOMAIN_NOMAP) && direct_max) || + (direct_max && (direct_max != hwirq_max)))) return NULL; domain = kzalloc_node(struct_size(domain, revmap, size), @@ -219,7 +220,6 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int s domain->hwirq_max = hwirq_max; if (direct_max) { - size = direct_max; domain->flags |= IRQ_DOMAIN_FLAG_NO_MAP; } @@ -650,9 +650,9 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) pr_debug("create_direct virq allocation failed\n"); return 0; } - if (virq >= domain->revmap_size) { - pr_err("ERROR: no free irqs available below %i maximum\n", - domain->revmap_size); + if (virq >= domain->hwirq_max) { + pr_err("ERROR: no free irqs available below %lu maximum\n", + domain->hwirq_max); irq_free_desc(virq); return 0; } @@ -906,10 +906,12 @@ struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain, return desc; if (irq_domain_is_nomap(domain)) { - if (hwirq < domain->revmap_size) { + if (hwirq < domain->hwirq_max) { data = irq_domain_get_irq_data(domain, hwirq); if (data && data->hwirq == hwirq) desc = irq_data_to_desc(data); + if (irq && desc) + *irq = hwirq; } return desc; @@ -1319,7 +1321,8 @@ EXPORT_SYMBOL_GPL(irq_domain_get_irq_data); * @chip_data: The associated chip data */ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, + const struct irq_chip *chip, void *chip_data) { struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); @@ -1328,7 +1331,7 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, return -ENOENT; irq_data->hwirq = hwirq; - irq_data->chip = chip ? chip : &no_irq_chip; + irq_data->chip = (struct irq_chip *)(chip ? chip : &no_irq_chip); irq_data->chip_data = chip_data; return 0; @@ -1347,7 +1350,7 @@ EXPORT_SYMBOL_GPL(irq_domain_set_hwirq_and_chip); * @handler_name: The interrupt handler name */ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name) { @@ -1853,7 +1856,7 @@ EXPORT_SYMBOL_GPL(irq_domain_get_irq_data); * @handler_name: The interrupt handler name */ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name) { diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 7405e384e5ed..40fe7806cc8c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -205,16 +205,8 @@ static void irq_validate_effective_affinity(struct irq_data *data) pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", chip->name, data->irq); } - -static inline void irq_init_effective_affinity(struct irq_data *data, - const struct cpumask *mask) -{ - cpumask_copy(irq_data_get_effective_affinity_mask(data), mask); -} #else static inline void irq_validate_effective_affinity(struct irq_data *data) { } -static inline void irq_init_effective_affinity(struct irq_data *data, - const struct cpumask *mask) { } #endif int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, @@ -222,11 +214,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, { struct irq_desc *desc = irq_data_to_desc(data); struct irq_chip *chip = irq_data_get_irq_chip(data); + const struct cpumask *prog_mask; int ret; + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + if (!chip || !chip->irq_set_affinity) return -EINVAL; + raw_spin_lock(&tmp_mask_lock); /* * If this is a managed interrupt and housekeeping is enabled on * it check whether the requested affinity mask intersects with @@ -247,25 +244,35 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, * online. */ if (irqd_affinity_is_managed(data) && - housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { - const struct cpumask *hk_mask, *prog_mask; + housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) { + const struct cpumask *hk_mask; - static DEFINE_RAW_SPINLOCK(tmp_mask_lock); - static struct cpumask tmp_mask; + hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ); - hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); - - raw_spin_lock(&tmp_mask_lock); cpumask_and(&tmp_mask, mask, hk_mask); if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) prog_mask = mask; else prog_mask = &tmp_mask; - ret = chip->irq_set_affinity(data, prog_mask, force); - raw_spin_unlock(&tmp_mask_lock); } else { - ret = chip->irq_set_affinity(data, mask, force); + prog_mask = mask; } + + /* + * Make sure we only provide online CPUs to the irqchip, + * unless we are being asked to force the affinity (in which + * case we do as we are told). + */ + cpumask_and(&tmp_mask, prog_mask, cpu_online_mask); + if (!force && !cpumask_empty(&tmp_mask)) + ret = chip->irq_set_affinity(data, &tmp_mask, force); + else if (force) + ret = chip->irq_set_affinity(data, mask, force); + else + ret = -EINVAL; + + raw_spin_unlock(&tmp_mask_lock); + switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: @@ -332,7 +339,7 @@ static bool irq_set_affinity_deactivated(struct irq_data *data, return false; cpumask_copy(desc->irq_common_data.affinity, mask); - irq_init_effective_affinity(data, mask); + irq_data_update_effective_affinity(data, mask); irqd_set(data, IRQD_AFFINITY_SET); return true; } @@ -486,7 +493,8 @@ int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) } EXPORT_SYMBOL_GPL(irq_force_affinity); -int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) +int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, + bool setaffinity) { unsigned long flags; struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); @@ -495,12 +503,11 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) return -EINVAL; desc->affinity_hint = m; irq_put_desc_unlock(desc, flags); - /* set the initial affinity to prevent every interrupt being on CPU0 */ - if (m) + if (m && setaffinity) __irq_set_affinity(irq, m, false); return 0; } -EXPORT_SYMBOL_GPL(irq_set_affinity_hint); +EXPORT_SYMBOL_GPL(__irq_apply_affinity_hint); static void irq_affinity_notify(struct work_struct *work) { @@ -1249,6 +1256,31 @@ static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) } /* + * Internal function to notify that a interrupt thread is ready. + */ +static void irq_thread_set_ready(struct irq_desc *desc, + struct irqaction *action) +{ + set_bit(IRQTF_READY, &action->thread_flags); + wake_up(&desc->wait_for_threads); +} + +/* + * Internal function to wake up a interrupt thread and wait until it is + * ready. + */ +static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc, + struct irqaction *action) +{ + if (!action || !action->thread) + return; + + wake_up_process(action->thread); + wait_event(desc->wait_for_threads, + test_bit(IRQTF_READY, &action->thread_flags)); +} + +/* * Interrupt handler thread */ static int irq_thread(void *data) @@ -1259,6 +1291,8 @@ static int irq_thread(void *data) irqreturn_t (*handler_fn)(struct irq_desc *desc, struct irqaction *action); + irq_thread_set_ready(desc, action); + sched_set_fifo(current); if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD, @@ -1683,8 +1717,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!shared) { - init_waitqueue_head(&desc->wait_for_threads); - /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { ret = __irq_set_trigger(desc, @@ -1780,14 +1812,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irq_setup_timings(desc, new); - /* - * Strictly no need to wake it up, but hung_task complains - * when no hard interrupt wakes the thread up. - */ - if (new->thread) - wake_up_process(new->thread); - if (new->secondary) - wake_up_process(new->secondary->thread); + wake_up_and_wait_for_irq_thread_ready(desc, new); + wake_up_and_wait_for_irq_thread_ready(desc, new->secondary); register_irq_proc(irq, desc); new->dir = NULL; diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index bbfb26489aa1..1698e77645ac 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -286,7 +286,7 @@ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, unsigned int *mapped_cpu) { - unsigned int bit, cpu, end = m->alloc_end; + unsigned int bit, cpu, end; struct cpumap *cm; if (cpumask_empty(msk)) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 7f350ae59c5f..a9ee535293eb 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -14,12 +14,15 @@ #include <linux/irqdomain.h> #include <linux/msi.h> #include <linux/slab.h> +#include <linux/sysfs.h> #include <linux/pci.h> #include "internals.h" +static inline int msi_sysfs_create_group(struct device *dev); + /** - * alloc_msi_entry - Allocate an initialized msi_desc + * msi_alloc_desc - Allocate an initialized msi_desc * @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 @@ -29,34 +32,134 @@ * * Return: pointer to allocated &msi_desc on success or %NULL on failure */ -struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, - const struct irq_affinity_desc *affinity) +static struct msi_desc *msi_alloc_desc(struct device *dev, int nvec, + const struct irq_affinity_desc *affinity) { - struct msi_desc *desc; + struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL); - 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); + 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) +static void msi_free_desc(struct msi_desc *desc) +{ + kfree(desc->affinity); + kfree(desc); +} + +static int msi_insert_desc(struct msi_device_data *md, struct msi_desc *desc, unsigned int index) +{ + int ret; + + desc->msi_index = index; + ret = xa_insert(&md->__store, index, desc, GFP_KERNEL); + if (ret) + msi_free_desc(desc); + return ret; +} + +/** + * msi_add_msi_desc - Allocate and initialize a MSI descriptor + * @dev: Pointer to the device for which the descriptor is allocated + * @init_desc: Pointer to an MSI descriptor to initialize the new descriptor + * + * Return: 0 on success or an appropriate failure code. + */ +int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc) +{ + struct msi_desc *desc; + + lockdep_assert_held(&dev->msi.data->mutex); + + desc = msi_alloc_desc(dev, init_desc->nvec_used, init_desc->affinity); + if (!desc) + return -ENOMEM; + + /* Copy type specific data to the new descriptor. */ + desc->pci = init_desc->pci; + return msi_insert_desc(dev->msi.data, desc, init_desc->msi_index); +} + +/** + * msi_add_simple_msi_descs - Allocate and initialize MSI descriptors + * @dev: Pointer to the device for which the descriptors are allocated + * @index: Index for the first MSI descriptor + * @ndesc: Number of descriptors to allocate + * + * Return: 0 on success or an appropriate failure code. + */ +static int msi_add_simple_msi_descs(struct device *dev, unsigned int index, unsigned int ndesc) +{ + unsigned int idx, last = index + ndesc - 1; + struct msi_desc *desc; + int ret; + + lockdep_assert_held(&dev->msi.data->mutex); + + for (idx = index; idx <= last; idx++) { + desc = msi_alloc_desc(dev, 1, NULL); + if (!desc) + goto fail_mem; + ret = msi_insert_desc(dev->msi.data, desc, idx); + if (ret) + goto fail; + } + return 0; + +fail_mem: + ret = -ENOMEM; +fail: + msi_free_msi_descs_range(dev, MSI_DESC_NOTASSOCIATED, index, last); + return ret; +} + +static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter) +{ + switch (filter) { + case MSI_DESC_ALL: + return true; + case MSI_DESC_NOTASSOCIATED: + return !desc->irq; + case MSI_DESC_ASSOCIATED: + return !!desc->irq; + } + WARN_ON_ONCE(1); + return false; +} + +/** + * msi_free_msi_descs_range - Free MSI descriptors of a device + * @dev: Device to free the descriptors + * @filter: Descriptor state filter + * @first_index: Index to start freeing from + * @last_index: Last index to be freed + */ +void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, + unsigned int first_index, unsigned int last_index) { - kfree(entry->affinity); - kfree(entry); + struct xarray *xa = &dev->msi.data->__store; + struct msi_desc *desc; + unsigned long idx; + + lockdep_assert_held(&dev->msi.data->mutex); + + xa_for_each_range(xa, idx, desc, first_index, last_index) { + if (msi_desc_match(desc, filter)) { + xa_erase(xa, idx); + msi_free_desc(desc); + } + } } void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) @@ -72,139 +175,290 @@ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) } EXPORT_SYMBOL_GPL(get_cached_msi_msg); -static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, - char *buf) +static void msi_device_data_release(struct device *dev, void *res) { - struct msi_desc *entry; - bool is_msix = false; - unsigned long irq; - int retval; + struct msi_device_data *md = res; - retval = kstrtoul(attr->attr.name, 10, &irq); - if (retval) - return retval; + WARN_ON_ONCE(!xa_empty(&md->__store)); + xa_destroy(&md->__store); + dev->msi.data = NULL; +} - entry = irq_get_msi_desc(irq); - if (!entry) - return -ENODEV; +/** + * msi_setup_device_data - Setup MSI device data + * @dev: Device for which MSI device data should be set up + * + * Return: 0 on success, appropriate error code otherwise + * + * This can be called more than once for @dev. If the MSI device data is + * already allocated the call succeeds. The allocated memory is + * automatically released when the device is destroyed. + */ +int msi_setup_device_data(struct device *dev) +{ + struct msi_device_data *md; + int ret; - if (dev_is_pci(dev)) - is_msix = entry->msi_attrib.is_msix; + if (dev->msi.data) + return 0; - return sysfs_emit(buf, "%s\n", is_msix ? "msix" : "msi"); + md = devres_alloc(msi_device_data_release, sizeof(*md), GFP_KERNEL); + if (!md) + return -ENOMEM; + + ret = msi_sysfs_create_group(dev); + if (ret) { + devres_free(md); + return ret; + } + + xa_init(&md->__store); + mutex_init(&md->mutex); + dev->msi.data = md; + devres_add(dev, md); + return 0; } /** - * msi_populate_sysfs - Populate msi_irqs sysfs entries for devices - * @dev: The device(PCI, platform etc) who will get sysfs entries + * msi_lock_descs - Lock the MSI descriptor storage of a device + * @dev: Device to operate on + */ +void msi_lock_descs(struct device *dev) +{ + mutex_lock(&dev->msi.data->mutex); +} +EXPORT_SYMBOL_GPL(msi_lock_descs); + +/** + * msi_unlock_descs - Unlock the MSI descriptor storage of a device + * @dev: Device to operate on + */ +void msi_unlock_descs(struct device *dev) +{ + /* Invalidate the index wich was cached by the iterator */ + dev->msi.data->__iter_idx = MSI_MAX_INDEX; + mutex_unlock(&dev->msi.data->mutex); +} +EXPORT_SYMBOL_GPL(msi_unlock_descs); + +static struct msi_desc *msi_find_desc(struct msi_device_data *md, enum msi_desc_filter filter) +{ + struct msi_desc *desc; + + xa_for_each_start(&md->__store, md->__iter_idx, desc, md->__iter_idx) { + if (msi_desc_match(desc, filter)) + return desc; + } + md->__iter_idx = MSI_MAX_INDEX; + return NULL; +} + +/** + * msi_first_desc - Get the first MSI descriptor of a device + * @dev: Device to operate on + * @filter: Descriptor state filter * - * Return attribute_group ** so that specific bus MSI can save it to - * somewhere during initilizing msi irqs. If devices has no MSI irq, - * return NULL; if it fails to populate sysfs, return ERR_PTR + * Must be called with the MSI descriptor mutex held, i.e. msi_lock_descs() + * must be invoked before the call. + * + * Return: Pointer to the first MSI descriptor matching the search + * criteria, NULL if none found. */ -const struct attribute_group **msi_populate_sysfs(struct device *dev) -{ - const struct attribute_group **msi_irq_groups; - struct attribute **msi_attrs, *msi_attr; - struct device_attribute *msi_dev_attr; - struct attribute_group *msi_irq_group; - struct msi_desc *entry; - int ret = -ENOMEM; - int num_msi = 0; - int count = 0; - int i; +struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter) +{ + struct msi_device_data *md = dev->msi.data; - /* Determine how many msi entries we have */ - for_each_msi_entry(entry, dev) - num_msi += entry->nvec_used; - if (!num_msi) + if (WARN_ON_ONCE(!md)) return NULL; - /* Dynamically create the MSI attributes for the device */ - msi_attrs = kcalloc(num_msi + 1, sizeof(void *), GFP_KERNEL); - if (!msi_attrs) - return ERR_PTR(-ENOMEM); - - for_each_msi_entry(entry, dev) { - for (i = 0; i < entry->nvec_used; i++) { - msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL); - if (!msi_dev_attr) - goto error_attrs; - msi_attrs[count] = &msi_dev_attr->attr; - - sysfs_attr_init(&msi_dev_attr->attr); - msi_dev_attr->attr.name = kasprintf(GFP_KERNEL, "%d", - entry->irq + i); - if (!msi_dev_attr->attr.name) - goto error_attrs; - msi_dev_attr->attr.mode = 0444; - msi_dev_attr->show = msi_mode_show; - ++count; + lockdep_assert_held(&md->mutex); + + md->__iter_idx = 0; + return msi_find_desc(md, filter); +} +EXPORT_SYMBOL_GPL(msi_first_desc); + +/** + * msi_next_desc - Get the next MSI descriptor of a device + * @dev: Device to operate on + * + * The first invocation of msi_next_desc() has to be preceeded by a + * successful invocation of __msi_first_desc(). Consecutive invocations are + * only valid if the previous one was successful. All these operations have + * to be done within the same MSI mutex held region. + * + * Return: Pointer to the next MSI descriptor matching the search + * criteria, NULL if none found. + */ +struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter) +{ + struct msi_device_data *md = dev->msi.data; + + if (WARN_ON_ONCE(!md)) + return NULL; + + lockdep_assert_held(&md->mutex); + + if (md->__iter_idx >= (unsigned long)MSI_MAX_INDEX) + return NULL; + + md->__iter_idx++; + return msi_find_desc(md, filter); +} +EXPORT_SYMBOL_GPL(msi_next_desc); + +/** + * msi_get_virq - Return Linux interrupt number of a MSI interrupt + * @dev: Device to operate on + * @index: MSI interrupt index to look for (0-based) + * + * Return: The Linux interrupt number on success (> 0), 0 if not found + */ +unsigned int msi_get_virq(struct device *dev, unsigned int index) +{ + struct msi_desc *desc; + unsigned int ret = 0; + bool pcimsi; + + if (!dev->msi.data) + return 0; + + pcimsi = dev_is_pci(dev) ? to_pci_dev(dev)->msi_enabled : false; + + msi_lock_descs(dev); + desc = xa_load(&dev->msi.data->__store, pcimsi ? 0 : index); + if (desc && desc->irq) { + /* + * PCI-MSI has only one descriptor for multiple interrupts. + * PCI-MSIX and platform MSI use a descriptor per + * interrupt. + */ + if (pcimsi) { + if (index < desc->nvec_used) + ret = desc->irq + index; + } else { + ret = desc->irq; } } + msi_unlock_descs(dev); + return ret; +} +EXPORT_SYMBOL_GPL(msi_get_virq); - msi_irq_group = kzalloc(sizeof(*msi_irq_group), GFP_KERNEL); - if (!msi_irq_group) - goto error_attrs; - msi_irq_group->name = "msi_irqs"; - msi_irq_group->attrs = msi_attrs; +#ifdef CONFIG_SYSFS +static struct attribute *msi_dev_attrs[] = { + NULL +}; - msi_irq_groups = kcalloc(2, sizeof(void *), GFP_KERNEL); - if (!msi_irq_groups) - goto error_irq_group; - msi_irq_groups[0] = msi_irq_group; +static const struct attribute_group msi_irqs_group = { + .name = "msi_irqs", + .attrs = msi_dev_attrs, +}; - ret = sysfs_create_groups(&dev->kobj, msi_irq_groups); - if (ret) - goto error_irq_groups; - - return msi_irq_groups; - -error_irq_groups: - kfree(msi_irq_groups); -error_irq_group: - kfree(msi_irq_group); -error_attrs: - count = 0; - msi_attr = msi_attrs[count]; - while (msi_attr) { - msi_dev_attr = container_of(msi_attr, struct device_attribute, attr); - kfree(msi_attr->name); - kfree(msi_dev_attr); - ++count; - msi_attr = msi_attrs[count]; +static inline int msi_sysfs_create_group(struct device *dev) +{ + return devm_device_add_group(dev, &msi_irqs_group); +} + +static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + /* MSI vs. MSIX is per device not per interrupt */ + bool is_msix = dev_is_pci(dev) ? to_pci_dev(dev)->msix_enabled : false; + + return sysfs_emit(buf, "%s\n", is_msix ? "msix" : "msi"); +} + +static void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) +{ + struct device_attribute *attrs = desc->sysfs_attrs; + int i; + + if (!attrs) + return; + + desc->sysfs_attrs = NULL; + for (i = 0; i < desc->nvec_used; i++) { + if (attrs[i].show) + sysfs_remove_file_from_group(&dev->kobj, &attrs[i].attr, msi_irqs_group.name); + kfree(attrs[i].attr.name); + } + kfree(attrs); +} + +static int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) +{ + struct device_attribute *attrs; + int ret, i; + + attrs = kcalloc(desc->nvec_used, sizeof(*attrs), GFP_KERNEL); + if (!attrs) + return -ENOMEM; + + desc->sysfs_attrs = attrs; + for (i = 0; i < desc->nvec_used; i++) { + sysfs_attr_init(&attrs[i].attr); + attrs[i].attr.name = kasprintf(GFP_KERNEL, "%d", desc->irq + i); + if (!attrs[i].attr.name) { + ret = -ENOMEM; + goto fail; + } + + attrs[i].attr.mode = 0444; + attrs[i].show = msi_mode_show; + + ret = sysfs_add_file_to_group(&dev->kobj, &attrs[i].attr, msi_irqs_group.name); + if (ret) { + attrs[i].show = NULL; + goto fail; + } } - kfree(msi_attrs); - return ERR_PTR(ret); + return 0; + +fail: + msi_sysfs_remove_desc(dev, desc); + return ret; } +#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS /** - * msi_destroy_sysfs - Destroy msi_irqs sysfs entries for devices - * @dev: The device(PCI, platform etc) who will remove sysfs entries - * @msi_irq_groups: attribute_group for device msi_irqs entries + * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device + * @dev: The device (PCI, platform etc) which will get sysfs entries */ -void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_irq_groups) -{ - struct device_attribute *dev_attr; - struct attribute **msi_attrs; - int count = 0; - - if (msi_irq_groups) { - sysfs_remove_groups(&dev->kobj, msi_irq_groups); - msi_attrs = msi_irq_groups[0]->attrs; - while (msi_attrs[count]) { - dev_attr = container_of(msi_attrs[count], - struct device_attribute, attr); - kfree(dev_attr->attr.name); - kfree(dev_attr); - ++count; - } - kfree(msi_attrs); - kfree(msi_irq_groups[0]); - kfree(msi_irq_groups); +int msi_device_populate_sysfs(struct device *dev) +{ + struct msi_desc *desc; + int ret; + + msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) { + if (desc->sysfs_attrs) + continue; + ret = msi_sysfs_populate_desc(dev, desc); + if (ret) + return ret; } + return 0; } +/** + * msi_device_destroy_sysfs - Destroy msi_irqs sysfs entries for a device + * @dev: The device (PCI, platform etc) for which to remove + * sysfs entries + */ +void msi_device_destroy_sysfs(struct device *dev) +{ + struct msi_desc *desc; + + msi_for_each_desc(desc, dev, MSI_DESC_ALL) + msi_sysfs_remove_desc(dev, desc); +} +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */ +#else /* CONFIG_SYSFS */ +static inline int msi_sysfs_create_group(struct device *dev) { return 0; } +static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; } +static inline void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { } +#endif /* !CONFIG_SYSFS */ + #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN static inline void irq_chip_write_msi_msg(struct irq_data *data, struct msi_msg *msg) @@ -456,43 +710,38 @@ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, } int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, - int virq, int nvec, msi_alloc_info_t *arg) + int virq_base, int nvec, msi_alloc_info_t *arg) { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; struct msi_desc *desc; - int ret = 0; + int ret, virq; - for_each_msi_entry(desc, dev) { - /* Don't even try the multi-MSI brain damage. */ - if (WARN_ON(!desc->irq || desc->nvec_used != 1)) { - ret = -EINVAL; - break; - } + msi_lock_descs(dev); + ret = msi_add_simple_msi_descs(dev, virq_base, nvec); + if (ret) + goto unlock; - if (!(desc->irq >= virq && desc->irq < (virq + nvec))) - continue; + for (virq = virq_base; virq < virq_base + nvec; virq++) { + desc = xa_load(&dev->msi.data->__store, virq); + desc->irq = virq; ops->set_desc(arg, desc); - /* Assumes the domain mutex is held! */ - ret = irq_domain_alloc_irqs_hierarchy(domain, desc->irq, 1, - arg); + ret = irq_domain_alloc_irqs_hierarchy(domain, virq, 1, arg); if (ret) - break; + goto fail; - irq_set_msi_desc_off(desc->irq, 0, desc); - } - - if (ret) { - /* Mop up the damage */ - for_each_msi_entry(desc, dev) { - if (!(desc->irq >= virq && desc->irq < (virq + nvec))) - continue; - - irq_domain_free_irqs_common(domain, desc->irq, 1); - } + irq_set_msi_desc(virq, desc); } + msi_unlock_descs(dev); + return 0; +fail: + for (--virq; virq >= virq_base; virq--) + irq_domain_free_irqs_common(domain, virq, 1); + msi_free_msi_descs_range(dev, MSI_DESC_ALL, virq_base, virq_base + nvec - 1); +unlock: + msi_unlock_descs(dev); return ret; } @@ -531,8 +780,74 @@ static bool msi_check_reservation_mode(struct irq_domain *domain, * Checking the first MSI descriptor is sufficient. MSIX supports * masking and MSI does so when the can_mask attribute is set. */ - desc = first_msi_entry(dev); - return desc->msi_attrib.is_msix || desc->msi_attrib.can_mask; + desc = msi_first_desc(dev, MSI_DESC_ALL); + return desc->pci.msi_attrib.is_msix || desc->pci.msi_attrib.can_mask; +} + +static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc, + int allocated) +{ + switch(domain->bus_token) { + case DOMAIN_BUS_PCI_MSI: + case DOMAIN_BUS_VMD_MSI: + if (IS_ENABLED(CONFIG_PCI_MSI)) + break; + fallthrough; + default: + return -ENOSPC; + } + + /* Let a failed PCI multi MSI allocation retry */ + if (desc->nvec_used > 1) + return 1; + + /* If there was a successful allocation let the caller know */ + return allocated ? allocated : -ENOSPC; +} + +#define VIRQ_CAN_RESERVE 0x01 +#define VIRQ_ACTIVATE 0x02 +#define VIRQ_NOMASK_QUIRK 0x04 + +static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflags) +{ + struct irq_data *irqd = irq_domain_get_irq_data(domain, virq); + int ret; + + if (!(vflags & VIRQ_CAN_RESERVE)) { + irqd_clr_can_reserve(irqd); + if (vflags & VIRQ_NOMASK_QUIRK) + irqd_set_msi_nomask_quirk(irqd); + + /* + * If the interrupt is managed but no CPU is available to + * service it, shut it down until better times. Note that + * we only do this on the !RESERVE path as x86 (the only + * architecture using this flag) deals with this in a + * different way by using a catch-all vector. + */ + if ((vflags & VIRQ_ACTIVATE) && + irqd_affinity_is_managed(irqd) && + !cpumask_intersects(irq_data_get_affinity_mask(irqd), + cpu_online_mask)) { + irqd_set_managed_shutdown(irqd); + return 0; + } + } + + if (!(vflags & VIRQ_ACTIVATE)) + return 0; + + ret = irq_domain_activate_irq(irqd, vflags & VIRQ_CAN_RESERVE); + if (ret) + return ret; + /* + * If the interrupt uses reservation mode, clear the activated bit + * so request_irq() will assign the final vector. + */ + if (vflags & VIRQ_CAN_RESERVE) + irqd_clr_activated(irqd); + return 0; } int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, @@ -540,83 +855,103 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; - struct irq_data *irq_data; - struct msi_desc *desc; msi_alloc_info_t arg = { }; + unsigned int vflags = 0; + struct msi_desc *desc; + int allocated = 0; int i, ret, virq; - bool can_reserve; ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg); if (ret) return ret; - for_each_msi_entry(desc, dev) { + /* + * This flag is set by the PCI layer as we need to activate + * the MSI entries before the PCI layer enables MSI in the + * card. Otherwise the card latches a random msi message. + */ + if (info->flags & MSI_FLAG_ACTIVATE_EARLY) + vflags |= VIRQ_ACTIVATE; + + /* + * Interrupt can use a reserved vector and will not occupy + * a real device vector until the interrupt is requested. + */ + if (msi_check_reservation_mode(domain, info, dev)) { + vflags |= VIRQ_CAN_RESERVE; + /* + * MSI affinity setting requires a special quirk (X86) when + * reservation mode is active. + */ + if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) + vflags |= VIRQ_NOMASK_QUIRK; + } + + msi_for_each_desc(desc, dev, MSI_DESC_NOTASSOCIATED) { ops->set_desc(&arg, desc); virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used, dev_to_node(dev), &arg, false, desc->affinity); - if (virq < 0) { - ret = -ENOSPC; - if (ops->handle_error) - ret = ops->handle_error(domain, desc, ret); - if (ops->msi_finish) - ops->msi_finish(&arg, ret); - return ret; - } + if (virq < 0) + return msi_handle_pci_fail(domain, desc, allocated); for (i = 0; i < desc->nvec_used; i++) { irq_set_msi_desc_off(virq, i, desc); irq_debugfs_copy_devname(virq + i, dev); + ret = msi_init_virq(domain, virq + i, vflags); + if (ret) + return ret; } + if (info->flags & MSI_FLAG_DEV_SYSFS) { + ret = msi_sysfs_populate_desc(dev, desc); + if (ret) + return ret; + } + allocated++; } + return 0; +} - if (ops->msi_finish) - ops->msi_finish(&arg, 0); +static int msi_domain_add_simple_msi_descs(struct msi_domain_info *info, + struct device *dev, + unsigned int num_descs) +{ + if (!(info->flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS)) + return 0; - can_reserve = msi_check_reservation_mode(domain, info, dev); + return msi_add_simple_msi_descs(dev, 0, num_descs); +} - /* - * This flag is set by the PCI layer as we need to activate - * the MSI entries before the PCI layer enables MSI in the - * card. Otherwise the card latches a random msi message. - */ - if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY)) - goto skip_activate; - - for_each_msi_vector(desc, i, dev) { - if (desc->irq == i) { - virq = desc->irq; - dev_dbg(dev, "irq [%d-%d] for MSI\n", - virq, virq + desc->nvec_used - 1); - } +/** + * msi_domain_alloc_irqs_descs_locked - Allocate interrupts from a MSI interrupt domain + * @domain: The domain to allocate from + * @dev: Pointer to device struct of the device for which the interrupts + * are allocated + * @nvec: The number of interrupts to allocate + * + * Must be invoked from within a msi_lock_descs() / msi_unlock_descs() + * pair. Use this for MSI irqdomains which implement their own vector + * allocation/free. + * + * Return: %0 on success or an error code. + */ +int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev, + int nvec) +{ + struct msi_domain_info *info = domain->host_data; + struct msi_domain_ops *ops = info->ops; + int ret; - irq_data = irq_domain_get_irq_data(domain, i); - if (!can_reserve) { - irqd_clr_can_reserve(irq_data); - if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) - irqd_set_msi_nomask_quirk(irq_data); - } - ret = irq_domain_activate_irq(irq_data, can_reserve); - if (ret) - goto cleanup; - } + lockdep_assert_held(&dev->msi.data->mutex); -skip_activate: - /* - * If these interrupts use reservation mode, clear the activated bit - * so request_irq() will assign the final vector. - */ - if (can_reserve) { - for_each_msi_vector(desc, i, dev) { - irq_data = irq_domain_get_irq_data(domain, i); - irqd_clr_activated(irq_data); - } - } - return 0; + ret = msi_domain_add_simple_msi_descs(info, dev, nvec); + if (ret) + return ret; -cleanup: - msi_domain_free_irqs(domain, dev); + ret = ops->domain_alloc_irqs(domain, dev, nvec); + if (ret) + msi_domain_free_irqs_descs_locked(domain, dev); return ret; } @@ -629,52 +964,78 @@ cleanup: * * Return: %0 on success or an error code. */ -int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, - int nvec) +int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec) { - struct msi_domain_info *info = domain->host_data; - struct msi_domain_ops *ops = info->ops; + int ret; - return ops->domain_alloc_irqs(domain, dev, nvec); + msi_lock_descs(dev); + ret = msi_domain_alloc_irqs_descs_locked(domain, dev, nvec); + msi_unlock_descs(dev); + return ret; } void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) { - struct irq_data *irq_data; + struct msi_domain_info *info = domain->host_data; + struct irq_data *irqd; struct msi_desc *desc; int i; - for_each_msi_vector(desc, i, dev) { - irq_data = irq_domain_get_irq_data(domain, i); - if (irqd_is_activated(irq_data)) - irq_domain_deactivate_irq(irq_data); - } - - for_each_msi_entry(desc, dev) { - /* - * We might have failed to allocate an MSI early - * enough that there is no IRQ associated to this - * entry. If that's the case, don't do anything. - */ - if (desc->irq) { - irq_domain_free_irqs(desc->irq, desc->nvec_used); - desc->irq = 0; + /* Only handle MSI entries which have an interrupt associated */ + msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) { + /* Make sure all interrupts are deactivated */ + for (i = 0; i < desc->nvec_used; i++) { + irqd = irq_domain_get_irq_data(domain, desc->irq + i); + if (irqd && irqd_is_activated(irqd)) + irq_domain_deactivate_irq(irqd); } + + irq_domain_free_irqs(desc->irq, desc->nvec_used); + if (info->flags & MSI_FLAG_DEV_SYSFS) + msi_sysfs_remove_desc(dev, desc); + desc->irq = 0; } } +static void msi_domain_free_msi_descs(struct msi_domain_info *info, + struct device *dev) +{ + if (info->flags & MSI_FLAG_FREE_MSI_DESCS) + msi_free_msi_descs(dev); +} + /** - * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated to @dev + * msi_domain_free_irqs_descs_locked - Free interrupts from a MSI interrupt @domain associated to @dev * @domain: The domain to managing the interrupts * @dev: Pointer to device struct of the device for which the interrupts * are free + * + * Must be invoked from within a msi_lock_descs() / msi_unlock_descs() + * pair. Use this for MSI irqdomains which implement their own vector + * allocation. */ -void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev) { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; - return ops->domain_free_irqs(domain, dev); + lockdep_assert_held(&dev->msi.data->mutex); + + ops->domain_free_irqs(domain, dev); + msi_domain_free_msi_descs(info, dev); +} + +/** + * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated to @dev + * @domain: The domain to managing the interrupts + * @dev: Pointer to device struct of the device for which the interrupts + * are free + */ +void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +{ + msi_lock_descs(dev); + msi_domain_free_irqs_descs_locked(domain, dev); + msi_unlock_descs(dev); } /** diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index ca71123a6130..c556bc49d213 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -147,7 +147,6 @@ void suspend_device_irqs(void) synchronize_irq(irq); } } -EXPORT_SYMBOL_GPL(suspend_device_irqs); static void resume_irq(struct irq_desc *desc) { @@ -259,4 +258,3 @@ void resume_device_irqs(void) { resume_irqs(false); } -EXPORT_SYMBOL_GPL(resume_device_irqs); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index ee595ec09778..623b8136e9af 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -137,7 +137,7 @@ static inline int irq_select_affinity_usr(unsigned int irq) static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) { - unsigned int irq = (int)(long)PDE_DATA(file_inode(file)); + unsigned int irq = (int)(long)pde_data(file_inode(file)); cpumask_var_t new_value; int err; @@ -190,12 +190,12 @@ static ssize_t irq_affinity_list_proc_write(struct file *file, static int irq_affinity_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_proc_show, PDE_DATA(inode)); + return single_open(file, irq_affinity_proc_show, pde_data(inode)); } static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode)); + return single_open(file, irq_affinity_list_proc_show, pde_data(inode)); } static const struct proc_ops irq_affinity_proc_ops = { @@ -265,7 +265,7 @@ out: static int default_affinity_open(struct inode *inode, struct file *file) { - return single_open(file, default_affinity_show, PDE_DATA(inode)); + return single_open(file, default_affinity_show, pde_data(inode)); } static const struct proc_ops default_affinity_proc_ops = { |