diff options
Diffstat (limited to 'kernel/irq')
| -rw-r--r-- | kernel/irq/Kconfig | 85 | ||||
| -rw-r--r-- | kernel/irq/Makefile | 5 | ||||
| -rw-r--r-- | kernel/irq/autoprobe.c | 57 | ||||
| -rw-r--r-- | kernel/irq/chip.c | 886 | ||||
| -rw-r--r-- | kernel/irq/debug.h | 45 | ||||
| -rw-r--r-- | kernel/irq/devres.c | 47 | ||||
| -rw-r--r-- | kernel/irq/dummychip.c | 61 | ||||
| -rw-r--r-- | kernel/irq/generic-chip.c | 591 | ||||
| -rw-r--r-- | kernel/irq/handle.c | 578 | ||||
| -rw-r--r-- | kernel/irq/internals.h | 197 | ||||
| -rw-r--r-- | kernel/irq/irqdesc.c | 554 | ||||
| -rw-r--r-- | kernel/irq/irqdomain.c | 711 | ||||
| -rw-r--r-- | kernel/irq/manage.c | 1328 | ||||
| -rw-r--r-- | kernel/irq/migration.c | 46 | ||||
| -rw-r--r-- | kernel/irq/numa_migrate.c | 119 | ||||
| -rw-r--r-- | kernel/irq/pm.c | 77 | ||||
| -rw-r--r-- | kernel/irq/proc.c | 244 | ||||
| -rw-r--r-- | kernel/irq/resend.c | 34 | ||||
| -rw-r--r-- | kernel/irq/settings.h | 156 | ||||
| -rw-r--r-- | kernel/irq/spurious.c | 302 |
20 files changed, 4585 insertions, 1538 deletions
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig new file mode 100644 index 00000000000..d269cecdfbf --- /dev/null +++ b/kernel/irq/Kconfig @@ -0,0 +1,85 @@ +menu "IRQ subsystem" +# Options selectable by the architecture code + +# Make sparse irq Kconfig switch below available +config MAY_HAVE_SPARSE_IRQ + bool + +# Legacy support, required for itanic +config GENERIC_IRQ_LEGACY + bool + +# Enable the generic irq autoprobe mechanism +config GENERIC_IRQ_PROBE + bool + +# Use the generic /proc/interrupts implementation +config GENERIC_IRQ_SHOW + bool + +# Print level/edge extra information +config GENERIC_IRQ_SHOW_LEVEL + bool + +# Facility to allocate a hardware interrupt. This is legacy support +# and should not be used in new code. Use irq domains instead. +config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ + bool + +# Support for delayed migration from interrupt context +config GENERIC_PENDING_IRQ + bool + +# Alpha specific irq affinity mechanism +config AUTO_IRQ_AFFINITY + bool + +# Tasklet based software resend for pending interrupts on enable_irq() +config HARDIRQS_SW_RESEND + bool + +# Preflow handler support for fasteoi (sparc64) +config IRQ_PREFLOW_FASTEOI + bool + +# Edge style eoi based handler (cell) +config IRQ_EDGE_EOI_HANDLER + bool + +# Generic configurable interrupt chip implementation +config GENERIC_IRQ_CHIP + bool + select IRQ_DOMAIN + +# Generic irq_domain hw <--> linux irq number translation +config IRQ_DOMAIN + bool + +config IRQ_DOMAIN_DEBUG + bool "Expose hardware/virtual IRQ mapping via debugfs" + depends on IRQ_DOMAIN && DEBUG_FS + help + This option will show the mapping relationship between hardware irq + numbers and Linux irq numbers. The mapping is exposed via debugfs + in the file "irq_domain_mapping". + + If you don't know what this means you don't need it. + +# Support forced irq threading +config IRQ_FORCED_THREADING + bool + +config SPARSE_IRQ + bool "Support sparse irq numbering" if MAY_HAVE_SPARSE_IRQ + ---help--- + + Sparse irq numbering is useful for distro kernels that want + to define a high CONFIG_NR_CPUS value but still want to have + low kernel memory footprint on smaller machines. + + ( Sparse irqs can also be beneficial on NUMA boxes, as they spread + out the interrupt descriptors in a more NUMA-friendly way. ) + + If you don't know what to do here, say N. + +endmenu diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 7d047808419..fff17381f0a 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,7 +1,8 @@ -obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o +obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o obj-$(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_NUMA_IRQ_DESC) += numa_migrate.o obj-$(CONFIG_PM_SLEEP) += pm.o diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index 2295a31ef11..0119b9d467a 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -17,7 +17,7 @@ /* * Autodetection depends on the fact that any interrupt that * comes in on to an unassigned handler will get stuck with - * "IRQ_WAITING" cleared and the interrupt disabled. + * "IRQS_WAITING" cleared and the interrupt disabled. */ static DEFINE_MUTEX(probing_active); @@ -32,7 +32,6 @@ unsigned long probe_irq_on(void) { struct irq_desc *desc; unsigned long mask = 0; - unsigned int status; int i; /* @@ -46,20 +45,15 @@ unsigned long probe_irq_on(void) */ for_each_irq_desc_reverse(i, desc) { raw_spin_lock_irq(&desc->lock); - if (!desc->action && !(desc->status & IRQ_NOPROBE)) { - /* - * An old-style architecture might still have - * the handle_bad_irq handler there: - */ - compat_irq_chip_set_default_handler(desc); - + if (!desc->action && irq_settings_can_probe(desc)) { /* * Some chips need to know about probing in * progress: */ - if (desc->chip->set_type) - desc->chip->set_type(i, IRQ_TYPE_PROBE); - desc->chip->startup(i); + if (desc->irq_data.chip->irq_set_type) + desc->irq_data.chip->irq_set_type(&desc->irq_data, + IRQ_TYPE_PROBE); + irq_startup(desc, false); } raw_spin_unlock_irq(&desc->lock); } @@ -74,10 +68,10 @@ unsigned long probe_irq_on(void) */ for_each_irq_desc_reverse(i, desc) { raw_spin_lock_irq(&desc->lock); - if (!desc->action && !(desc->status & IRQ_NOPROBE)) { - desc->status |= IRQ_AUTODETECT | IRQ_WAITING; - if (desc->chip->startup(i)) - desc->status |= IRQ_PENDING; + if (!desc->action && irq_settings_can_probe(desc)) { + desc->istate |= IRQS_AUTODETECT | IRQS_WAITING; + if (irq_startup(desc, false)) + desc->istate |= IRQS_PENDING; } raw_spin_unlock_irq(&desc->lock); } @@ -92,13 +86,12 @@ unsigned long probe_irq_on(void) */ for_each_irq_desc(i, desc) { raw_spin_lock_irq(&desc->lock); - status = desc->status; - if (status & IRQ_AUTODETECT) { + if (desc->istate & IRQS_AUTODETECT) { /* It triggered already - consider it spurious. */ - if (!(status & IRQ_WAITING)) { - desc->status = status & ~IRQ_AUTODETECT; - desc->chip->shutdown(i); + if (!(desc->istate & IRQS_WAITING)) { + desc->istate &= ~IRQS_AUTODETECT; + irq_shutdown(desc); } else if (i < 32) mask |= 1 << i; @@ -124,20 +117,18 @@ EXPORT_SYMBOL(probe_irq_on); */ unsigned int probe_irq_mask(unsigned long val) { - unsigned int status, mask = 0; + unsigned int mask = 0; struct irq_desc *desc; int i; for_each_irq_desc(i, desc) { raw_spin_lock_irq(&desc->lock); - status = desc->status; - - if (status & IRQ_AUTODETECT) { - if (i < 16 && !(status & IRQ_WAITING)) + if (desc->istate & IRQS_AUTODETECT) { + if (i < 16 && !(desc->istate & IRQS_WAITING)) mask |= 1 << i; - desc->status = status & ~IRQ_AUTODETECT; - desc->chip->shutdown(i); + desc->istate &= ~IRQS_AUTODETECT; + irq_shutdown(desc); } raw_spin_unlock_irq(&desc->lock); } @@ -168,20 +159,18 @@ int probe_irq_off(unsigned long val) { int i, irq_found = 0, nr_of_irqs = 0; struct irq_desc *desc; - unsigned int status; for_each_irq_desc(i, desc) { raw_spin_lock_irq(&desc->lock); - status = desc->status; - if (status & IRQ_AUTODETECT) { - if (!(status & IRQ_WAITING)) { + if (desc->istate & IRQS_AUTODETECT) { + if (!(desc->istate & IRQS_WAITING)) { if (!nr_of_irqs) irq_found = i; nr_of_irqs++; } - desc->status = status & ~IRQ_AUTODETECT; - desc->chip->shutdown(i); + desc->istate &= ~IRQS_AUTODETECT; + irq_shutdown(desc); } raw_spin_unlock_irq(&desc->lock); } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 42ec11b2af8..a2b28a2fd7b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -16,348 +16,280 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> -#include "internals.h" - -static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data) -{ - struct irq_desc *desc; - unsigned long flags; - - desc = irq_to_desc(irq); - if (!desc) { - WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq); - return; - } - - /* Ensure we don't have left over values from a previous use of this irq */ - raw_spin_lock_irqsave(&desc->lock, flags); - desc->status = IRQ_DISABLED; - desc->chip = &no_irq_chip; - desc->handle_irq = handle_bad_irq; - desc->depth = 1; - desc->msi_desc = NULL; - desc->handler_data = NULL; - if (!keep_chip_data) - desc->chip_data = NULL; - desc->action = NULL; - desc->irq_count = 0; - desc->irqs_unhandled = 0; -#ifdef CONFIG_SMP - cpumask_setall(desc->affinity); -#ifdef CONFIG_GENERIC_PENDING_IRQ - cpumask_clear(desc->pending_mask); -#endif -#endif - raw_spin_unlock_irqrestore(&desc->lock, flags); -} - -/** - * dynamic_irq_init - initialize a dynamically allocated irq - * @irq: irq number to initialize - */ -void dynamic_irq_init(unsigned int irq) -{ - dynamic_irq_init_x(irq, false); -} - -/** - * dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq - * @irq: irq number to initialize - * - * does not set irq_to_desc(irq)->chip_data to NULL - */ -void dynamic_irq_init_keep_chip_data(unsigned int irq) -{ - dynamic_irq_init_x(irq, true); -} - -static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data) -{ - struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - - if (!desc) { - WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq); - return; - } - - raw_spin_lock_irqsave(&desc->lock, flags); - if (desc->action) { - raw_spin_unlock_irqrestore(&desc->lock, flags); - WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n", - irq); - return; - } - desc->msi_desc = NULL; - desc->handler_data = NULL; - if (!keep_chip_data) - desc->chip_data = NULL; - desc->handle_irq = handle_bad_irq; - desc->chip = &no_irq_chip; - desc->name = NULL; - clear_kstat_irqs(desc); - raw_spin_unlock_irqrestore(&desc->lock, flags); -} - -/** - * dynamic_irq_cleanup - cleanup a dynamically allocated irq - * @irq: irq number to initialize - */ -void dynamic_irq_cleanup(unsigned int irq) -{ - dynamic_irq_cleanup_x(irq, false); -} - -/** - * dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq - * @irq: irq number to initialize - * - * does not set irq_to_desc(irq)->chip_data to NULL - */ -void dynamic_irq_cleanup_keep_chip_data(unsigned int irq) -{ - dynamic_irq_cleanup_x(irq, true); -} +#include <trace/events/irq.h> +#include "internals.h" /** - * set_irq_chip - set the irq chip for an irq + * irq_set_chip - set the irq chip for an irq * @irq: irq number * @chip: pointer to irq chip description structure */ -int set_irq_chip(unsigned int irq, struct irq_chip *chip) +int irq_set_chip(unsigned int irq, struct irq_chip *chip) { - struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); - if (!desc) { - WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq); + if (!desc) return -EINVAL; - } if (!chip) chip = &no_irq_chip; - raw_spin_lock_irqsave(&desc->lock, flags); - irq_chip_set_defaults(chip); - desc->chip = chip; - raw_spin_unlock_irqrestore(&desc->lock, flags); - + desc->irq_data.chip = chip; + irq_put_desc_unlock(desc, flags); + /* + * For !CONFIG_SPARSE_IRQ make the irq show up in + * allocated_irqs. + */ + irq_mark_irq(irq); return 0; } -EXPORT_SYMBOL(set_irq_chip); +EXPORT_SYMBOL(irq_set_chip); /** - * set_irq_type - set the irq trigger type for an irq + * irq_set_type - set the irq trigger type for an irq * @irq: irq number * @type: IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h */ -int set_irq_type(unsigned int irq, unsigned int type) +int irq_set_irq_type(unsigned int irq, unsigned int type) { - struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; - int ret = -ENXIO; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + int ret = 0; - if (!desc) { - printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq); - return -ENODEV; - } + if (!desc) + return -EINVAL; type &= IRQ_TYPE_SENSE_MASK; - if (type == IRQ_TYPE_NONE) - return 0; - - raw_spin_lock_irqsave(&desc->lock, flags); ret = __irq_set_trigger(desc, irq, type); - raw_spin_unlock_irqrestore(&desc->lock, flags); + irq_put_desc_busunlock(desc, flags); return ret; } -EXPORT_SYMBOL(set_irq_type); +EXPORT_SYMBOL(irq_set_irq_type); /** - * set_irq_data - set irq type data for an irq + * irq_set_handler_data - set irq handler data for an irq * @irq: Interrupt number * @data: Pointer to interrupt specific data * * Set the hardware irq controller data for an irq */ -int set_irq_data(unsigned int irq, void *data) +int irq_set_handler_data(unsigned int irq, void *data) { - struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); - if (!desc) { - printk(KERN_ERR - "Trying to install controller data for IRQ%d\n", irq); + if (!desc) return -EINVAL; - } - - raw_spin_lock_irqsave(&desc->lock, flags); - desc->handler_data = data; - raw_spin_unlock_irqrestore(&desc->lock, flags); + desc->irq_data.handler_data = data; + irq_put_desc_unlock(desc, flags); return 0; } -EXPORT_SYMBOL(set_irq_data); +EXPORT_SYMBOL(irq_set_handler_data); /** - * set_irq_msi - set MSI descriptor data for an irq - * @irq: Interrupt number - * @entry: Pointer to MSI descriptor data + * irq_set_msi_desc_off - set MSI descriptor data for an irq at offset + * @irq_base: Interrupt number base + * @irq_offset: Interrupt number offset + * @entry: Pointer to MSI descriptor data * - * Set the MSI descriptor entry for an irq + * Set the MSI descriptor entry for an irq at offset */ -int set_irq_msi(unsigned int irq, struct msi_desc *entry) +int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset, + struct msi_desc *entry) { - struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq_base + irq_offset, &flags, IRQ_GET_DESC_CHECK_GLOBAL); - if (!desc) { - printk(KERN_ERR - "Trying to install msi data for IRQ%d\n", irq); + if (!desc) return -EINVAL; - } - - raw_spin_lock_irqsave(&desc->lock, flags); - desc->msi_desc = entry; - if (entry) - entry->irq = irq; - raw_spin_unlock_irqrestore(&desc->lock, flags); + desc->irq_data.msi_desc = entry; + if (entry && !irq_offset) + entry->irq = irq_base; + irq_put_desc_unlock(desc, flags); return 0; } /** - * set_irq_chip_data - set irq chip data for an irq + * irq_set_msi_desc - set MSI descriptor data for an irq + * @irq: Interrupt number + * @entry: Pointer to MSI descriptor data + * + * Set the MSI descriptor entry for an irq + */ +int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry) +{ + return irq_set_msi_desc_off(irq, 0, entry); +} + +/** + * irq_set_chip_data - set irq chip data for an irq * @irq: Interrupt number * @data: Pointer to chip specific data * * Set the hardware irq chip data for an irq */ -int set_irq_chip_data(unsigned int irq, void *data) +int irq_set_chip_data(unsigned int irq, void *data) { - struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); - if (!desc) { - printk(KERN_ERR - "Trying to install chip data for IRQ%d\n", irq); - return -EINVAL; - } - - if (!desc->chip) { - printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq); + if (!desc) return -EINVAL; - } - - raw_spin_lock_irqsave(&desc->lock, flags); - desc->chip_data = data; - raw_spin_unlock_irqrestore(&desc->lock, flags); - + desc->irq_data.chip_data = data; + irq_put_desc_unlock(desc, flags); return 0; } -EXPORT_SYMBOL(set_irq_chip_data); +EXPORT_SYMBOL(irq_set_chip_data); -/** - * set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq - * - * @irq: Interrupt number - * @nest: 0 to clear / 1 to set the IRQ_NESTED_THREAD flag - * - * The IRQ_NESTED_THREAD flag indicates that on - * request_threaded_irq() no separate interrupt thread should be - * created for the irq as the handler are called nested in the - * context of a demultiplexing interrupt handler thread. - */ -void set_irq_nested_thread(unsigned int irq, int nest) +struct irq_data *irq_get_irq_data(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - if (!desc) - return; + return desc ? &desc->irq_data : NULL; +} +EXPORT_SYMBOL_GPL(irq_get_irq_data); - raw_spin_lock_irqsave(&desc->lock, flags); - if (nest) - desc->status |= IRQ_NESTED_THREAD; - else - desc->status &= ~IRQ_NESTED_THREAD; - raw_spin_unlock_irqrestore(&desc->lock, flags); +static void irq_state_clr_disabled(struct irq_desc *desc) +{ + irqd_clear(&desc->irq_data, IRQD_IRQ_DISABLED); } -EXPORT_SYMBOL_GPL(set_irq_nested_thread); -/* - * default enable function - */ -static void default_enable(unsigned int irq) +static void irq_state_set_disabled(struct irq_desc *desc) { - struct irq_desc *desc = irq_to_desc(irq); + irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); +} - desc->chip->unmask(irq); - desc->status &= ~IRQ_MASKED; +static void irq_state_clr_masked(struct irq_desc *desc) +{ + irqd_clear(&desc->irq_data, IRQD_IRQ_MASKED); } -/* - * default disable function - */ -static void default_disable(unsigned int irq) +static void irq_state_set_masked(struct irq_desc *desc) { + irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); } -/* - * default startup function - */ -static unsigned int default_startup(unsigned int irq) +int irq_startup(struct irq_desc *desc, bool resend) { - struct irq_desc *desc = irq_to_desc(irq); + int ret = 0; - desc->chip->enable(irq); - return 0; + irq_state_clr_disabled(desc); + desc->depth = 0; + + if (desc->irq_data.chip->irq_startup) { + ret = desc->irq_data.chip->irq_startup(&desc->irq_data); + irq_state_clr_masked(desc); + } else { + irq_enable(desc); + } + if (resend) + check_irq_resend(desc, desc->irq_data.irq); + return ret; } -/* - * default shutdown function - */ -static void default_shutdown(unsigned int irq) +void irq_shutdown(struct irq_desc *desc) { - struct irq_desc *desc = irq_to_desc(irq); + irq_state_set_disabled(desc); + desc->depth = 1; + if (desc->irq_data.chip->irq_shutdown) + desc->irq_data.chip->irq_shutdown(&desc->irq_data); + else if (desc->irq_data.chip->irq_disable) + desc->irq_data.chip->irq_disable(&desc->irq_data); + else + desc->irq_data.chip->irq_mask(&desc->irq_data); + irq_state_set_masked(desc); +} - desc->chip->mask(irq); - desc->status |= IRQ_MASKED; +void irq_enable(struct irq_desc *desc) +{ + irq_state_clr_disabled(desc); + if (desc->irq_data.chip->irq_enable) + desc->irq_data.chip->irq_enable(&desc->irq_data); + else + desc->irq_data.chip->irq_unmask(&desc->irq_data); + irq_state_clr_masked(desc); } -/* - * Fixup enable/disable function pointers +/** + * irq_disable - Mark interrupt disabled + * @desc: irq descriptor which should be disabled + * + * If the chip does not implement the irq_disable callback, we + * use a lazy disable approach. That means we mark the interrupt + * disabled, but leave the hardware unmasked. That's an + * optimization because we avoid the hardware access for the + * common case where no interrupt happens after we marked it + * disabled. If an interrupt happens, then the interrupt flow + * handler masks the line at the hardware level and marks it + * pending. */ -void irq_chip_set_defaults(struct irq_chip *chip) -{ - if (!chip->enable) - chip->enable = default_enable; - if (!chip->disable) - chip->disable = default_disable; - if (!chip->startup) - chip->startup = default_startup; - /* - * We use chip->disable, when the user provided its own. When - * we have default_disable set for chip->disable, then we need - * to use default_shutdown, otherwise the irq line is not - * disabled on free_irq(): - */ - if (!chip->shutdown) - chip->shutdown = chip->disable != default_disable ? - chip->disable : default_shutdown; - if (!chip->name) - chip->name = chip->typename; - if (!chip->end) - chip->end = dummy_irq_chip.end; +void irq_disable(struct irq_desc *desc) +{ + irq_state_set_disabled(desc); + if (desc->irq_data.chip->irq_disable) { + desc->irq_data.chip->irq_disable(&desc->irq_data); + irq_state_set_masked(desc); + } +} + +void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu) +{ + if (desc->irq_data.chip->irq_enable) + desc->irq_data.chip->irq_enable(&desc->irq_data); + else + desc->irq_data.chip->irq_unmask(&desc->irq_data); + cpumask_set_cpu(cpu, desc->percpu_enabled); } -static inline void mask_ack_irq(struct irq_desc *desc, int irq) +void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu) { - if (desc->chip->mask_ack) - desc->chip->mask_ack(irq); + if (desc->irq_data.chip->irq_disable) + desc->irq_data.chip->irq_disable(&desc->irq_data); + else + desc->irq_data.chip->irq_mask(&desc->irq_data); + cpumask_clear_cpu(cpu, desc->percpu_enabled); +} + +static inline void mask_ack_irq(struct irq_desc *desc) +{ + if (desc->irq_data.chip->irq_mask_ack) + desc->irq_data.chip->irq_mask_ack(&desc->irq_data); else { - desc->chip->mask(irq); - if (desc->chip->ack) - desc->chip->ack(irq); + desc->irq_data.chip->irq_mask(&desc->irq_data); + if (desc->irq_data.chip->irq_ack) + desc->irq_data.chip->irq_ack(&desc->irq_data); + } + irq_state_set_masked(desc); +} + +void mask_irq(struct irq_desc *desc) +{ + if (desc->irq_data.chip->irq_mask) { + desc->irq_data.chip->irq_mask(&desc->irq_data); + irq_state_set_masked(desc); + } +} + +void unmask_irq(struct irq_desc *desc) +{ + if (desc->irq_data.chip->irq_unmask) { + desc->irq_data.chip->irq_unmask(&desc->irq_data); + irq_state_clr_masked(desc); + } +} + +void unmask_threaded_irq(struct irq_desc *desc) +{ + struct irq_chip *chip = desc->irq_data.chip; + + if (chip->flags & IRQCHIP_EOI_THREADED) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_unmask) { + chip->irq_unmask(&desc->irq_data); + irq_state_clr_masked(desc); } } @@ -379,13 +311,16 @@ void handle_nested_irq(unsigned int irq) raw_spin_lock_irq(&desc->lock); + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); kstat_incr_irqs_this_cpu(irq, desc); action = desc->action; - if (unlikely(!action || (desc->status & IRQ_DISABLED))) + if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; goto out_unlock; + } - desc->status |= IRQ_INPROGRESS; + irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); raw_spin_unlock_irq(&desc->lock); action_ret = action->thread_fn(action->irq, action->dev_id); @@ -393,13 +328,20 @@ void handle_nested_irq(unsigned int irq) note_interrupt(irq, desc, action_ret); raw_spin_lock_irq(&desc->lock); - desc->status &= ~IRQ_INPROGRESS; + irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); out_unlock: raw_spin_unlock_irq(&desc->lock); } EXPORT_SYMBOL_GPL(handle_nested_irq); +static bool irq_check_poll(struct irq_desc *desc) +{ + if (!(desc->istate & IRQS_POLL_INPROGRESS)) + return false; + return irq_wait_for_poll(desc); +} + /** * handle_simple_irq - Simple and software-decoded IRQs. * @irq: the interrupt number @@ -415,32 +357,44 @@ EXPORT_SYMBOL_GPL(handle_nested_irq); void handle_simple_irq(unsigned int irq, struct irq_desc *desc) { - struct irqaction *action; - irqreturn_t action_ret; - raw_spin_lock(&desc->lock); - if (unlikely(desc->status & IRQ_INPROGRESS)) - goto out_unlock; - desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); + if (unlikely(irqd_irq_inprogress(&desc->irq_data))) + if (!irq_check_poll(desc)) + goto out_unlock; + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); kstat_incr_irqs_this_cpu(irq, desc); - action = desc->action; - if (unlikely(!action || (desc->status & IRQ_DISABLED))) + if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; goto out_unlock; + } - desc->status |= IRQ_INPROGRESS; - raw_spin_unlock(&desc->lock); - - action_ret = handle_IRQ_event(irq, action); - if (!noirqdebug) - note_interrupt(irq, desc, action_ret); + handle_irq_event(desc); - raw_spin_lock(&desc->lock); - desc->status &= ~IRQ_INPROGRESS; out_unlock: raw_spin_unlock(&desc->lock); } +EXPORT_SYMBOL_GPL(handle_simple_irq); + +/* + * Called unconditionally from handle_level_irq() and only for oneshot + * interrupts from handle_fasteoi_irq() + */ +static void cond_unmask_irq(struct irq_desc *desc) +{ + /* + * We need to unmask in the following cases: + * - Standard level irq (IRQF_ONESHOT is not set) + * - Oneshot irq which did not wake the thread (caused by a + * spurious interrupt or a primary handler handling it + * completely). + */ + if (!irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) + unmask_irq(desc); +} /** * handle_level_irq - Level type irq handler @@ -455,44 +409,65 @@ out_unlock: void handle_level_irq(unsigned int irq, struct irq_desc *desc) { - struct irqaction *action; - irqreturn_t action_ret; - raw_spin_lock(&desc->lock); - mask_ack_irq(desc, irq); + mask_ack_irq(desc); - if (unlikely(desc->status & IRQ_INPROGRESS)) - goto out_unlock; - desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); + if (unlikely(irqd_irq_inprogress(&desc->irq_data))) + if (!irq_check_poll(desc)) + goto out_unlock; + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); kstat_incr_irqs_this_cpu(irq, desc); /* * If its disabled or no action available * keep it masked and get out of here */ - action = desc->action; - if (unlikely(!action || (desc->status & IRQ_DISABLED))) + if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; goto out_unlock; + } - desc->status |= IRQ_INPROGRESS; - raw_spin_unlock(&desc->lock); + handle_irq_event(desc); - action_ret = handle_IRQ_event(irq, action); - if (!noirqdebug) - note_interrupt(irq, desc, action_ret); - - raw_spin_lock(&desc->lock); - desc->status &= ~IRQ_INPROGRESS; + cond_unmask_irq(desc); - if (unlikely(desc->status & IRQ_ONESHOT)) - desc->status |= IRQ_MASKED; - else if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask) - desc->chip->unmask(irq); out_unlock: raw_spin_unlock(&desc->lock); } EXPORT_SYMBOL_GPL(handle_level_irq); +#ifdef CONFIG_IRQ_PREFLOW_FASTEOI +static inline void preflow_handler(struct irq_desc *desc) +{ + if (desc->preflow_handler) + desc->preflow_handler(&desc->irq_data); +} +#else +static inline void preflow_handler(struct irq_desc *desc) { } +#endif + +static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip) +{ + if (!(desc->istate & IRQS_ONESHOT)) { + chip->irq_eoi(&desc->irq_data); + return; + } + /* + * We need to unmask in the following cases: + * - Oneshot irq which did not wake the thread (caused by a + * spurious interrupt or a primary handler handling it + * completely). + */ + if (!irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) { + chip->irq_eoi(&desc->irq_data); + unmask_irq(desc); + } else if (!(chip->flags & IRQCHIP_EOI_THREADED)) { + chip->irq_eoi(&desc->irq_data); + } +} + /** * handle_fasteoi_irq - irq handler for transparent controllers * @irq: the interrupt number @@ -506,43 +481,41 @@ EXPORT_SYMBOL_GPL(handle_level_irq); void handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) { - struct irqaction *action; - irqreturn_t action_ret; + struct irq_chip *chip = desc->irq_data.chip; raw_spin_lock(&desc->lock); - if (unlikely(desc->status & IRQ_INPROGRESS)) - goto out; + if (unlikely(irqd_irq_inprogress(&desc->irq_data))) + if (!irq_check_poll(desc)) + goto out; - desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); kstat_incr_irqs_this_cpu(irq, desc); /* * If its disabled or no action available * then mask it and get out of here: */ - action = desc->action; - if (unlikely(!action || (desc->status & IRQ_DISABLED))) { - desc->status |= IRQ_PENDING; - if (desc->chip->mask) - desc->chip->mask(irq); + if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) { + desc->istate |= IRQS_PENDING; + mask_irq(desc); goto out; } - desc->status |= IRQ_INPROGRESS; - desc->status &= ~IRQ_PENDING; - raw_spin_unlock(&desc->lock); + if (desc->istate & IRQS_ONESHOT) + mask_irq(desc); - action_ret = handle_IRQ_event(irq, action); - if (!noirqdebug) - note_interrupt(irq, desc, action_ret); + preflow_handler(desc); + handle_irq_event(desc); - raw_spin_lock(&desc->lock); - desc->status &= ~IRQ_INPROGRESS; -out: - desc->chip->eoi(irq); + cond_unmask_eoi_irq(desc, chip); raw_spin_unlock(&desc->lock); + return; +out: + if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED)) + chip->irq_eoi(&desc->irq_data); + raw_spin_unlock(&desc->lock); } /** @@ -551,7 +524,7 @@ out: * @desc: the interrupt description structure for this irq * * Interrupt occures on the falling and/or rising edge of a hardware - * signal. The occurence is latched into the irq controller hardware + * signal. The occurrence is latched into the irq controller hardware * and must be acked in order to be reenabled. After the ack another * interrupt can happen on the same source even before the first one * is handled by the associated event handler. If this happens it @@ -566,34 +539,28 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) { raw_spin_lock(&desc->lock); - desc->status &= ~(IRQ_REPLAY | IRQ_WAITING); - + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); /* * If we're currently running this IRQ, or its disabled, * we shouldn't process the IRQ. Mark it pending, handle * the necessary masking and go out */ - if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) || - !desc->action)) { - desc->status |= (IRQ_PENDING | IRQ_MASKED); - mask_ack_irq(desc, irq); - goto out_unlock; + if (unlikely(irqd_irq_disabled(&desc->irq_data) || + irqd_irq_inprogress(&desc->irq_data) || !desc->action)) { + if (!irq_check_poll(desc)) { + desc->istate |= IRQS_PENDING; + mask_ack_irq(desc); + goto out_unlock; + } } kstat_incr_irqs_this_cpu(irq, desc); /* Start handling the irq */ - if (desc->chip->ack) - desc->chip->ack(irq); - - /* Mark the IRQ currently in progress.*/ - desc->status |= IRQ_INPROGRESS; + desc->irq_data.chip->irq_ack(&desc->irq_data); do { - struct irqaction *action = desc->action; - irqreturn_t action_ret; - - if (unlikely(!action)) { - desc->chip->mask(irq); + if (unlikely(!desc->action)) { + mask_irq(desc); goto out_unlock; } @@ -602,26 +569,66 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) * one, we could have masked the irq. * Renable it, if it was not disabled in meantime. */ - if (unlikely((desc->status & - (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) == - (IRQ_PENDING | IRQ_MASKED))) { - desc->chip->unmask(irq); - desc->status &= ~IRQ_MASKED; + if (unlikely(desc->istate & IRQS_PENDING)) { + if (!irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data)) + unmask_irq(desc); } - desc->status &= ~IRQ_PENDING; - raw_spin_unlock(&desc->lock); - action_ret = handle_IRQ_event(irq, action); - if (!noirqdebug) - note_interrupt(irq, desc, action_ret); - raw_spin_lock(&desc->lock); + handle_irq_event(desc); - } while ((desc->status & (IRQ_PENDING | IRQ_DISABLED)) == IRQ_PENDING); + } while ((desc->istate & IRQS_PENDING) && + !irqd_irq_disabled(&desc->irq_data)); - desc->status &= ~IRQ_INPROGRESS; out_unlock: raw_spin_unlock(&desc->lock); } +EXPORT_SYMBOL(handle_edge_irq); + +#ifdef CONFIG_IRQ_EDGE_EOI_HANDLER +/** + * handle_edge_eoi_irq - edge eoi type IRQ handler + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Similar as the above handle_edge_irq, but using eoi and w/o the + * mask/unmask logic. + */ +void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + + raw_spin_lock(&desc->lock); + + desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING); + /* + * If we're currently running this IRQ, or its disabled, + * we shouldn't process the IRQ. Mark it pending, handle + * the necessary masking and go out + */ + if (unlikely(irqd_irq_disabled(&desc->irq_data) || + irqd_irq_inprogress(&desc->irq_data) || !desc->action)) { + if (!irq_check_poll(desc)) { + desc->istate |= IRQS_PENDING; + goto out_eoi; + } + } + kstat_incr_irqs_this_cpu(irq, desc); + + do { + if (unlikely(!desc->action)) + goto out_eoi; + + handle_irq_event(desc); + + } while ((desc->istate & IRQS_PENDING) && + !irqd_irq_disabled(&desc->irq_data)); + +out_eoi: + chip->irq_eoi(&desc->irq_data); + raw_spin_unlock(&desc->lock); +} +#endif /** * handle_percpu_irq - Per CPU local irq handler @@ -633,115 +640,180 @@ out_unlock: void handle_percpu_irq(unsigned int irq, struct irq_desc *desc) { - irqreturn_t action_ret; + struct irq_chip *chip = irq_desc_get_chip(desc); kstat_incr_irqs_this_cpu(irq, desc); - if (desc->chip->ack) - desc->chip->ack(irq); + if (chip->irq_ack) + chip->irq_ack(&desc->irq_data); - action_ret = handle_IRQ_event(irq, desc->action); - if (!noirqdebug) - note_interrupt(irq, desc, action_ret); + handle_irq_event_percpu(desc, desc->action); + + if (chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); +} + +/** + * handle_percpu_devid_irq - Per CPU local irq handler with per cpu dev ids + * @irq: the interrupt number + * @desc: the interrupt description structure for this irq + * + * Per CPU interrupts on SMP machines without locking requirements. Same as + * handle_percpu_irq() above but with the following extras: + * + * action->percpu_dev_id is a pointer to percpu variables which + * contain the real device id for the cpu on which this handler is + * called + */ +void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct irqaction *action = desc->action; + void *dev_id = __this_cpu_ptr(action->percpu_dev_id); + irqreturn_t res; + + kstat_incr_irqs_this_cpu(irq, desc); + + if (chip->irq_ack) + chip->irq_ack(&desc->irq_data); + + trace_irq_handler_entry(irq, action); + res = action->handler(irq, dev_id); + trace_irq_handler_exit(irq, action, res); - if (desc->chip->eoi) - desc->chip->eoi(irq); + if (chip->irq_eoi) + chip->irq_eoi(&desc->irq_data); } void -__set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, +__irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, const char *name) { - struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, 0); - if (!desc) { - printk(KERN_ERR - "Trying to install type control for IRQ%d\n", irq); + if (!desc) return; - } - if (!handle) + if (!handle) { handle = handle_bad_irq; - else if (desc->chip == &no_irq_chip) { - printk(KERN_WARNING "Trying to install %sinterrupt handler " - "for IRQ%d\n", is_chained ? "chained " : "", irq); - /* - * Some ARM implementations install a handler for really dumb - * interrupt hardware without setting an irq_chip. This worked - * with the ARM no_irq_chip but the check in setup_irq would - * prevent us to setup the interrupt at all. Switch it to - * dummy_irq_chip for easy transition. - */ - desc->chip = &dummy_irq_chip; + } else { + if (WARN_ON(desc->irq_data.chip == &no_irq_chip)) + goto out; } - chip_bus_lock(irq, desc); - raw_spin_lock_irqsave(&desc->lock, flags); - /* Uninstall? */ if (handle == handle_bad_irq) { - if (desc->chip != &no_irq_chip) - mask_ack_irq(desc, irq); - desc->status |= IRQ_DISABLED; + if (desc->irq_data.chip != &no_irq_chip) + mask_ack_irq(desc); + irq_state_set_disabled(desc); desc->depth = 1; } desc->handle_irq = handle; desc->name = name; if (handle != handle_bad_irq && is_chained) { - desc->status &= ~IRQ_DISABLED; - desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE; - desc->depth = 0; - desc->chip->startup(irq); + irq_settings_set_noprobe(desc); + irq_settings_set_norequest(desc); + irq_settings_set_nothread(desc); + irq_startup(desc, true); } - raw_spin_unlock_irqrestore(&desc->lock, flags); - chip_bus_sync_unlock(irq, desc); +out: + irq_put_desc_busunlock(desc, flags); } -EXPORT_SYMBOL_GPL(__set_irq_handler); +EXPORT_SYMBOL_GPL(__irq_set_handler); void -set_irq_chip_and_handler(unsigned int irq, struct irq_chip *chip, - irq_flow_handler_t handle) +irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, + irq_flow_handler_t handle, const char *name) { - set_irq_chip(irq, chip); - __set_irq_handler(irq, handle, 0, NULL); + irq_set_chip(irq, chip); + __irq_set_handler(irq, handle, 0, name); } +EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name); -void -set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, - irq_flow_handler_t handle, const char *name) +void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) { - set_irq_chip(irq, chip); - __set_irq_handler(irq, handle, 0, name); + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + + if (!desc) + return; + irq_settings_clr_and_set(desc, clr, set); + + irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | + IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT); + if (irq_settings_has_no_balance_set(desc)) + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + if (irq_settings_is_per_cpu(desc)) + irqd_set(&desc->irq_data, IRQD_PER_CPU); + if (irq_settings_can_move_pcntxt(desc)) + irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT); + if (irq_settings_is_level(desc)) + irqd_set(&desc->irq_data, IRQD_LEVEL); + + irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc)); + + irq_put_desc_unlock(desc, flags); } +EXPORT_SYMBOL_GPL(irq_modify_status); -void __init set_irq_noprobe(unsigned int irq) +/** + * irq_cpu_online - Invoke all irq_cpu_online functions. + * + * Iterate through all irqs and invoke the chip.irq_cpu_online() + * for each. + */ +void irq_cpu_online(void) { - struct irq_desc *desc = irq_to_desc(irq); + struct irq_desc *desc; + struct irq_chip *chip; unsigned long flags; + unsigned int irq; - if (!desc) { - printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq); - return; - } + for_each_active_irq(irq) { + desc = irq_to_desc(irq); + if (!desc) + continue; + + raw_spin_lock_irqsave(&desc->lock, flags); + + chip = irq_data_get_irq_chip(&desc->irq_data); + if (chip && chip->irq_cpu_online && + (!(chip->flags & IRQCHIP_ONOFFLINE_ENABLED) || + !irqd_irq_disabled(&desc->irq_data))) + chip->irq_cpu_online(&desc->irq_data); - raw_spin_lock_irqsave(&desc->lock, flags); - desc->status |= IRQ_NOPROBE; - raw_spin_unlock_irqrestore(&desc->lock, flags); + raw_spin_unlock_irqrestore(&desc->lock, flags); + } } -void __init set_irq_probe(unsigned int irq) +/** + * irq_cpu_offline - Invoke all irq_cpu_offline functions. + * + * Iterate through all irqs and invoke the chip.irq_cpu_offline() + * for each. + */ +void irq_cpu_offline(void) { - struct irq_desc *desc = irq_to_desc(irq); + struct irq_desc *desc; + struct irq_chip *chip; unsigned long flags; + unsigned int irq; - if (!desc) { - printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq); - return; - } + for_each_active_irq(irq) { + desc = irq_to_desc(irq); + if (!desc) + continue; - raw_spin_lock_irqsave(&desc->lock, flags); - desc->status &= ~IRQ_NOPROBE; - raw_spin_unlock_irqrestore(&desc->lock, flags); + raw_spin_lock_irqsave(&desc->lock, flags); + + chip = irq_data_get_irq_chip(&desc->irq_data); + if (chip && chip->irq_cpu_offline && + (!(chip->flags & IRQCHIP_ONOFFLINE_ENABLED) || + !irqd_irq_disabled(&desc->irq_data))) + chip->irq_cpu_offline(&desc->irq_data); + + raw_spin_unlock_irqrestore(&desc->lock, flags); + } } diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h new file mode 100644 index 00000000000..e75e29e4434 --- /dev/null +++ b/kernel/irq/debug.h @@ -0,0 +1,45 @@ +/* + * Debugging printout: + */ + +#include <linux/kallsyms.h> + +#define ___P(f) if (desc->status_use_accessors & f) printk("%14s set\n", #f) +#define ___PS(f) if (desc->istate & f) printk("%14s set\n", #f) +/* FIXME */ +#define ___PD(f) do { } while (0) + +static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc) +{ + printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n", + irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled); + printk("->handle_irq(): %p, ", desc->handle_irq); + print_symbol("%s\n", (unsigned long)desc->handle_irq); + printk("->irq_data.chip(): %p, ", desc->irq_data.chip); + print_symbol("%s\n", (unsigned long)desc->irq_data.chip); + printk("->action(): %p\n", desc->action); + if (desc->action) { + printk("->action->handler(): %p, ", desc->action->handler); + print_symbol("%s\n", (unsigned long)desc->action->handler); + } + + ___P(IRQ_LEVEL); + ___P(IRQ_PER_CPU); + ___P(IRQ_NOPROBE); + ___P(IRQ_NOREQUEST); + ___P(IRQ_NOTHREAD); + ___P(IRQ_NOAUTOEN); + + ___PS(IRQS_AUTODETECT); + ___PS(IRQS_REPLAY); + ___PS(IRQS_WAITING); + ___PS(IRQS_PENDING); + + ___PD(IRQS_INPROGRESS); + ___PD(IRQS_DISABLED); + ___PD(IRQS_MASKED); +} + +#undef ___P +#undef ___PS +#undef ___PD diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 1ef4ffcdfa5..1ef0606797c 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -73,6 +73,51 @@ int devm_request_threaded_irq(struct device *dev, unsigned int irq, EXPORT_SYMBOL(devm_request_threaded_irq); /** + * devm_request_any_context_irq - allocate an interrupt line for a managed device + * @dev: device to request interrupt for + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs + * @thread_fn: function to be called in a threaded interrupt context. NULL + * for devices which handle everything in @handler + * @irqflags: Interrupt type flags + * @devname: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * Except for the extra @dev argument, this function takes the + * same arguments and performs the same function as + * request_any_context_irq(). IRQs requested with this function will be + * automatically freed on driver detach. + * + * If an IRQ allocated with this function needs to be freed + * separately, devm_free_irq() must be used. + */ +int devm_request_any_context_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id) +{ + struct irq_devres *dr; + int rc; + + dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres), + GFP_KERNEL); + if (!dr) + return -ENOMEM; + + rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id); + if (rc) { + devres_free(dr); + return rc; + } + + dr->irq = irq; + dr->dev_id = dev_id; + devres_add(dev, dr); + + return 0; +} +EXPORT_SYMBOL(devm_request_any_context_irq); + +/** * devm_free_irq - free an interrupt * @dev: device to free interrupt for * @irq: Interrupt line to free @@ -87,8 +132,8 @@ void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id) { struct irq_devres match_data = { irq, dev_id }; - free_irq(irq, dev_id); WARN_ON(devres_destroy(dev, devm_irq_release, devm_irq_match, &match_data)); + free_irq(irq, dev_id); } EXPORT_SYMBOL(devm_free_irq); diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c new file mode 100644 index 00000000000..988dc58e884 --- /dev/null +++ b/kernel/irq/dummychip.c @@ -0,0 +1,61 @@ +/* + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner, Russell King + * + * This file contains the dummy interrupt chip implementation + */ +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/export.h> + +#include "internals.h" + +/* + * What should we do if we get a hw irq event on an illegal vector? + * Each architecture has to answer this themself. + */ +static void ack_bad(struct irq_data *data) +{ + struct irq_desc *desc = irq_data_to_desc(data); + + print_irq_desc(data->irq, desc); + ack_bad_irq(data->irq); +} + +/* + * NOP functions + */ +static void noop(struct irq_data *data) { } + +static unsigned int noop_ret(struct irq_data *data) +{ + return 0; +} + +/* + * Generic no controller implementation + */ +struct irq_chip no_irq_chip = { + .name = "none", + .irq_startup = noop_ret, + .irq_shutdown = noop, + .irq_enable = noop, + .irq_disable = noop, + .irq_ack = ack_bad, +}; + +/* + * Generic dummy implementation which can be used for + * real dumb interrupt sources + */ +struct irq_chip dummy_irq_chip = { + .name = "dummy", + .irq_startup = noop_ret, + .irq_shutdown = noop, + .irq_enable = noop, + .irq_disable = noop, + .irq_ack = noop, + .irq_mask = noop, + .irq_unmask = noop, +}; +EXPORT_SYMBOL_GPL(dummy_irq_chip); diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c new file mode 100644 index 00000000000..452d6f2ba21 --- /dev/null +++ b/kernel/irq/generic-chip.c @@ -0,0 +1,591 @@ +/* + * Library implementing the most common irq chip callback functions + * + * Copyright (C) 2011, Thomas Gleixner + */ +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/irqdomain.h> +#include <linux/interrupt.h> +#include <linux/kernel_stat.h> +#include <linux/syscore_ops.h> + +#include "internals.h" + +static LIST_HEAD(gc_list); +static DEFINE_RAW_SPINLOCK(gc_lock); + +/** + * irq_gc_noop - NOOP function + * @d: irq_data + */ +void irq_gc_noop(struct irq_data *d) +{ +} + +/** + * irq_gc_mask_disable_reg - Mask chip via disable register + * @d: irq_data + * + * Chip has separate enable/disable registers instead of a single mask + * register. + */ +void irq_gc_mask_disable_reg(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + ct->regs.disable); + *ct->mask_cache &= ~mask; + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_set_bit - Mask chip via setting bit in mask register + * @d: irq_data + * + * Chip has a single mask register. Values of this register are cached + * and protected by gc->lock + */ +void irq_gc_mask_set_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + *ct->mask_cache |= mask; + irq_reg_writel(*ct->mask_cache, gc->reg_base + ct->regs.mask); + irq_gc_unlock(gc); +} +EXPORT_SYMBOL_GPL(irq_gc_mask_set_bit); + +/** + * irq_gc_mask_clr_bit - Mask chip via clearing bit in mask register + * @d: irq_data + * + * Chip has a single mask register. Values of this register are cached + * and protected by gc->lock + */ +void irq_gc_mask_clr_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + *ct->mask_cache &= ~mask; + irq_reg_writel(*ct->mask_cache, gc->reg_base + ct->regs.mask); + irq_gc_unlock(gc); +} +EXPORT_SYMBOL_GPL(irq_gc_mask_clr_bit); + +/** + * irq_gc_unmask_enable_reg - Unmask chip via enable register + * @d: irq_data + * + * Chip has separate enable/disable registers instead of a single mask + * register. + */ +void irq_gc_unmask_enable_reg(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + ct->regs.enable); + *ct->mask_cache |= mask; + irq_gc_unlock(gc); +} + +/** + * irq_gc_ack_set_bit - Ack pending interrupt via setting bit + * @d: irq_data + */ +void irq_gc_ack_set_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + ct->regs.ack); + irq_gc_unlock(gc); +} +EXPORT_SYMBOL_GPL(irq_gc_ack_set_bit); + +/** + * irq_gc_ack_clr_bit - Ack pending interrupt via clearing bit + * @d: irq_data + */ +void irq_gc_ack_clr_bit(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = ~d->mask; + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + ct->regs.ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt + * @d: irq_data + */ +void irq_gc_mask_disable_reg_and_ack(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + ct->regs.mask); + irq_reg_writel(mask, gc->reg_base + ct->regs.ack); + irq_gc_unlock(gc); +} + +/** + * irq_gc_eoi - EOI interrupt + * @d: irq_data + */ +void irq_gc_eoi(struct irq_data *d) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = irq_data_get_chip_type(d); + u32 mask = d->mask; + + irq_gc_lock(gc); + irq_reg_writel(mask, gc->reg_base + ct->regs.eoi); + irq_gc_unlock(gc); +} + +/** + * irq_gc_set_wake - Set/clr wake bit for an interrupt + * @d: irq_data + * @on: Indicates whether the wake bit should be set or cleared + * + * For chips where the wake from suspend functionality is not + * configured in a separate register and the wakeup active state is + * just stored in a bitmask. + */ +int irq_gc_set_wake(struct irq_data *d, unsigned int on) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + u32 mask = d->mask; + + if (!(mask & gc->wake_enabled)) + return -EINVAL; + + irq_gc_lock(gc); + if (on) + gc->wake_active |= mask; + else + gc->wake_active &= ~mask; + irq_gc_unlock(gc); + return 0; +} + +static void +irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, + int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler) +{ + raw_spin_lock_init(&gc->lock); + gc->num_ct = num_ct; + gc->irq_base = irq_base; + gc->reg_base = reg_base; + gc->chip_types->chip.name = name; + gc->chip_types->handler = handler; +} + +/** + * irq_alloc_generic_chip - Allocate a generic chip and initialize it + * @name: Name of the irq chip + * @num_ct: Number of irq_chip_type instances associated with this + * @irq_base: Interrupt base nr for this chip + * @reg_base: Register base address (virtual) + * @handler: Default flow handler associated with this chip + * + * Returns an initialized irq_chip_generic structure. The chip defaults + * to the primary (index 0) irq_chip_type and @handler + */ +struct irq_chip_generic * +irq_alloc_generic_chip(const char *name, int num_ct, unsigned int irq_base, + void __iomem *reg_base, irq_flow_handler_t handler) +{ + struct irq_chip_generic *gc; + unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); + + gc = kzalloc(sz, GFP_KERNEL); + if (gc) { + irq_init_generic_chip(gc, name, num_ct, irq_base, reg_base, + handler); + } + return gc; +} +EXPORT_SYMBOL_GPL(irq_alloc_generic_chip); + +static void +irq_gc_init_mask_cache(struct irq_chip_generic *gc, enum irq_gc_flags flags) +{ + struct irq_chip_type *ct = gc->chip_types; + u32 *mskptr = &gc->mask_cache, mskreg = ct->regs.mask; + int i; + + for (i = 0; i < gc->num_ct; i++) { + if (flags & IRQ_GC_MASK_CACHE_PER_TYPE) { + mskptr = &ct[i].mask_cache_priv; + mskreg = ct[i].regs.mask; + } + ct[i].mask_cache = mskptr; + if (flags & IRQ_GC_INIT_MASK_CACHE) + *mskptr = irq_reg_readl(gc->reg_base + mskreg); + } +} + +/** + * irq_alloc_domain_generic_chip - Allocate generic chips for an irq domain + * @d: irq domain for which to allocate chips + * @irqs_per_chip: Number of interrupts each chip handles + * @num_ct: Number of irq_chip_type instances associated with this + * @name: Name of the irq chip + * @handler: Default flow handler associated with these chips + * @clr: IRQ_* bits to clear in the mapping function + * @set: IRQ_* bits to set in the mapping function + * @gcflags: Generic chip specific setup flags + */ +int irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, + int num_ct, const char *name, + irq_flow_handler_t handler, + unsigned int clr, unsigned int set, + enum irq_gc_flags gcflags) +{ + struct irq_domain_chip_generic *dgc; + struct irq_chip_generic *gc; + int numchips, sz, i; + unsigned long flags; + void *tmp; + + if (d->gc) + return -EBUSY; + + numchips = DIV_ROUND_UP(d->revmap_size, irqs_per_chip); + if (!numchips) + return -EINVAL; + + /* Allocate a pointer, generic chip and chiptypes for each chip */ + sz = sizeof(*dgc) + numchips * sizeof(gc); + sz += numchips * (sizeof(*gc) + num_ct * sizeof(struct irq_chip_type)); + + tmp = dgc = kzalloc(sz, GFP_KERNEL); + if (!dgc) + return -ENOMEM; + dgc->irqs_per_chip = irqs_per_chip; + dgc->num_chips = numchips; + dgc->irq_flags_to_set = set; + dgc->irq_flags_to_clear = clr; + dgc->gc_flags = gcflags; + d->gc = dgc; + + /* Calc pointer to the first generic chip */ + tmp += sizeof(*dgc) + numchips * sizeof(gc); + for (i = 0; i < numchips; i++) { + /* Store the pointer to the generic chip */ + dgc->gc[i] = gc = tmp; + irq_init_generic_chip(gc, name, num_ct, i * irqs_per_chip, + NULL, handler); + gc->domain = d; + raw_spin_lock_irqsave(&gc_lock, flags); + list_add_tail(&gc->list, &gc_list); + raw_spin_unlock_irqrestore(&gc_lock, flags); + /* Calc pointer to the next generic chip */ + tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); + } + d->name = name; + return 0; +} +EXPORT_SYMBOL_GPL(irq_alloc_domain_generic_chips); + +/** + * irq_get_domain_generic_chip - Get a pointer to the generic chip of a hw_irq + * @d: irq domain pointer + * @hw_irq: Hardware interrupt number + */ +struct irq_chip_generic * +irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq) +{ + struct irq_domain_chip_generic *dgc = d->gc; + int idx; + + if (!dgc) + return NULL; + idx = hw_irq / dgc->irqs_per_chip; + if (idx >= dgc->num_chips) + return NULL; + return dgc->gc[idx]; +} +EXPORT_SYMBOL_GPL(irq_get_domain_generic_chip); + +/* + * Separate lockdep class for interrupt chip which can nest irq_desc + * lock. + */ +static struct lock_class_key irq_nested_lock_class; + +/* + * irq_map_generic_chip - Map a generic chip for an irq domain + */ +static int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, + irq_hw_number_t hw_irq) +{ + struct irq_data *data = irq_get_irq_data(virq); + struct irq_domain_chip_generic *dgc = d->gc; + struct irq_chip_generic *gc; + struct irq_chip_type *ct; + struct irq_chip *chip; + unsigned long flags; + int idx; + + if (!d->gc) + return -ENODEV; + + idx = hw_irq / dgc->irqs_per_chip; + if (idx >= dgc->num_chips) + return -EINVAL; + gc = dgc->gc[idx]; + + idx = hw_irq % dgc->irqs_per_chip; + + if (test_bit(idx, &gc->unused)) + return -ENOTSUPP; + + if (test_bit(idx, &gc->installed)) + return -EBUSY; + + ct = gc->chip_types; + chip = &ct->chip; + + /* We only init the cache for the first mapping of a generic chip */ + if (!gc->installed) { + raw_spin_lock_irqsave(&gc->lock, flags); + irq_gc_init_mask_cache(gc, dgc->gc_flags); + raw_spin_unlock_irqrestore(&gc->lock, flags); + } + + /* Mark the interrupt as installed */ + set_bit(idx, &gc->installed); + + if (dgc->gc_flags & IRQ_GC_INIT_NESTED_LOCK) + irq_set_lockdep_class(virq, &irq_nested_lock_class); + + if (chip->irq_calc_mask) + chip->irq_calc_mask(data); + else + data->mask = 1 << idx; + + irq_set_chip_and_handler(virq, chip, ct->handler); + irq_set_chip_data(virq, gc); + irq_modify_status(virq, dgc->irq_flags_to_clear, dgc->irq_flags_to_set); + return 0; +} + +struct irq_domain_ops irq_generic_chip_ops = { + .map = irq_map_generic_chip, + .xlate = irq_domain_xlate_onetwocell, +}; +EXPORT_SYMBOL_GPL(irq_generic_chip_ops); + +/** + * irq_setup_generic_chip - Setup a range of interrupts with a generic chip + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @flags: Flags for initialization + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Set up max. 32 interrupts starting from gc->irq_base. Note, this + * initializes all interrupts to the primary irq_chip_type and its + * associated handler. + */ +void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, + enum irq_gc_flags flags, unsigned int clr, + unsigned int set) +{ + struct irq_chip_type *ct = gc->chip_types; + struct irq_chip *chip = &ct->chip; + unsigned int i; + + raw_spin_lock(&gc_lock); + list_add_tail(&gc->list, &gc_list); + raw_spin_unlock(&gc_lock); + + irq_gc_init_mask_cache(gc, flags); + + for (i = gc->irq_base; msk; msk >>= 1, i++) { + if (!(msk & 0x01)) + continue; + + if (flags & IRQ_GC_INIT_NESTED_LOCK) + irq_set_lockdep_class(i, &irq_nested_lock_class); + + if (!(flags & IRQ_GC_NO_MASK)) { + struct irq_data *d = irq_get_irq_data(i); + + if (chip->irq_calc_mask) + chip->irq_calc_mask(d); + else + d->mask = 1 << (i - gc->irq_base); + } + irq_set_chip_and_handler(i, chip, ct->handler); + irq_set_chip_data(i, gc); + irq_modify_status(i, clr, set); + } + gc->irq_cnt = i - gc->irq_base; +} +EXPORT_SYMBOL_GPL(irq_setup_generic_chip); + +/** + * irq_setup_alt_chip - Switch to alternative chip + * @d: irq_data for this interrupt + * @type: Flow type to be initialized + * + * Only to be called from chip->irq_set_type() callbacks. + */ +int irq_setup_alt_chip(struct irq_data *d, unsigned int type) +{ + struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); + struct irq_chip_type *ct = gc->chip_types; + unsigned int i; + + for (i = 0; i < gc->num_ct; i++, ct++) { + if (ct->type & type) { + d->chip = &ct->chip; + irq_data_to_desc(d)->handle_irq = ct->handler; + return 0; + } + } + return -EINVAL; +} +EXPORT_SYMBOL_GPL(irq_setup_alt_chip); + +/** + * irq_remove_generic_chip - Remove a chip + * @gc: Generic irq chip holding all data + * @msk: Bitmask holding the irqs to initialize relative to gc->irq_base + * @clr: IRQ_* bits to clear + * @set: IRQ_* bits to set + * + * Remove up to 32 interrupts starting from gc->irq_base. + */ +void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, + unsigned int clr, unsigned int set) +{ + unsigned int i = gc->irq_base; + + raw_spin_lock(&gc_lock); + list_del(&gc->list); + raw_spin_unlock(&gc_lock); + + for (; msk; msk >>= 1, i++) { + if (!(msk & 0x01)) + continue; + + /* Remove handler first. That will mask the irq line */ + irq_set_handler(i, NULL); + irq_set_chip(i, &no_irq_chip); + irq_set_chip_data(i, NULL); + irq_modify_status(i, clr, set); + } +} +EXPORT_SYMBOL_GPL(irq_remove_generic_chip); + +static struct irq_data *irq_gc_get_irq_data(struct irq_chip_generic *gc) +{ + unsigned int virq; + + if (!gc->domain) + return irq_get_irq_data(gc->irq_base); + + /* + * We don't know which of the irqs has been actually + * installed. Use the first one. + */ + if (!gc->installed) + return NULL; + + virq = irq_find_mapping(gc->domain, gc->irq_base + __ffs(gc->installed)); + return virq ? irq_get_irq_data(virq) : NULL; +} + +#ifdef CONFIG_PM +static int irq_gc_suspend(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_suspend) { + struct irq_data *data = irq_gc_get_irq_data(gc); + + if (data) + ct->chip.irq_suspend(data); + } + } + return 0; +} + +static void irq_gc_resume(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_resume) { + struct irq_data *data = irq_gc_get_irq_data(gc); + + if (data) + ct->chip.irq_resume(data); + } + } +} +#else +#define irq_gc_suspend NULL +#define irq_gc_resume NULL +#endif + +static void irq_gc_shutdown(void) +{ + struct irq_chip_generic *gc; + + list_for_each_entry(gc, &gc_list, list) { + struct irq_chip_type *ct = gc->chip_types; + + if (ct->chip.irq_pm_shutdown) { + struct irq_data *data = irq_gc_get_irq_data(gc); + + if (data) + ct->chip.irq_pm_shutdown(data); + } + } +} + +static struct syscore_ops irq_gc_syscore_ops = { + .suspend = irq_gc_suspend, + .resume = irq_gc_resume, + .shutdown = irq_gc_shutdown, +}; + +static int __init irq_gc_init_ops(void) +{ + register_syscore_ops(&irq_gc_syscore_ops); + return 0; +} +device_initcall(irq_gc_init_ops); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 76d5a671bfe..63548027085 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -11,24 +11,15 @@ */ #include <linux/irq.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/module.h> #include <linux/random.h> +#include <linux/sched.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> -#include <linux/rculist.h> -#include <linux/hash.h> -#include <linux/radix-tree.h> + #include <trace/events/irq.h> #include "internals.h" -/* - * lockdep: we want to handle all irq_desc locks as a single lock-class: - */ -struct lock_class_key irq_desc_lock_class; - /** * handle_bad_irq - handle spurious and unhandled irqs * @irq: the interrupt number @@ -43,304 +34,6 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc) ack_bad_irq(irq); } -#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) -static void __init init_irq_default_affinity(void) -{ - alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); - cpumask_setall(irq_default_affinity); -} -#else -static void __init init_irq_default_affinity(void) -{ -} -#endif - -/* - * Linux has a controller-independent interrupt architecture. - * Every controller has a 'controller-template', that is used - * by the main code to do the right thing. Each driver-visible - * interrupt source is transparently wired to the appropriate - * controller. Thus drivers need not be aware of the - * interrupt-controller. - * - * The code is designed to be easily extended with new/different - * interrupt controllers, without having to do assembly magic or - * having to touch the generic code. - * - * Controller mappings for all interrupt sources: - */ -int nr_irqs = NR_IRQS; -EXPORT_SYMBOL_GPL(nr_irqs); - -#ifdef CONFIG_SPARSE_IRQ - -static struct irq_desc irq_desc_init = { - .irq = -1, - .status = IRQ_DISABLED, - .chip = &no_irq_chip, - .handle_irq = handle_bad_irq, - .depth = 1, - .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock), -}; - -void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr) -{ - void *ptr; - - ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), - GFP_ATOMIC, node); - - /* - * don't overwite if can not get new one - * init_copy_kstat_irqs() could still use old one - */ - if (ptr) { - printk(KERN_DEBUG " alloc kstat_irqs on node %d\n", node); - desc->kstat_irqs = ptr; - } -} - -static void init_one_irq_desc(int irq, struct irq_desc *desc, int node) -{ - memcpy(desc, &irq_desc_init, sizeof(struct irq_desc)); - - raw_spin_lock_init(&desc->lock); - desc->irq = irq; -#ifdef CONFIG_SMP - desc->node = node; -#endif - lockdep_set_class(&desc->lock, &irq_desc_lock_class); - init_kstat_irqs(desc, node, nr_cpu_ids); - if (!desc->kstat_irqs) { - printk(KERN_ERR "can not alloc kstat_irqs\n"); - BUG_ON(1); - } - if (!alloc_desc_masks(desc, node, false)) { - printk(KERN_ERR "can not alloc irq_desc cpumasks\n"); - BUG_ON(1); - } - init_desc_masks(desc); - arch_init_chip_data(desc, node); -} - -/* - * Protect the sparse_irqs: - */ -DEFINE_RAW_SPINLOCK(sparse_irq_lock); - -static RADIX_TREE(irq_desc_tree, GFP_ATOMIC); - -static void set_irq_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); -} - -void replace_irq_desc(unsigned int irq, struct irq_desc *desc) -{ - void **ptr; - - ptr = radix_tree_lookup_slot(&irq_desc_tree, irq); - if (ptr) - radix_tree_replace_slot(ptr, desc); -} - -static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = { - [0 ... NR_IRQS_LEGACY-1] = { - .irq = -1, - .status = IRQ_DISABLED, - .chip = &no_irq_chip, - .handle_irq = handle_bad_irq, - .depth = 1, - .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock), - } -}; - -static unsigned int *kstat_irqs_legacy; - -int __init early_irq_init(void) -{ - struct irq_desc *desc; - int legacy_count; - int node; - int i; - - init_irq_default_affinity(); - - /* initialize nr_irqs based on nr_cpu_ids */ - arch_probe_nr_irqs(); - printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs); - - desc = irq_desc_legacy; - legacy_count = ARRAY_SIZE(irq_desc_legacy); - node = first_online_node; - - /* allocate based on nr_cpu_ids */ - kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids * - sizeof(int), GFP_NOWAIT, node); - - for (i = 0; i < legacy_count; i++) { - desc[i].irq = i; -#ifdef CONFIG_SMP - desc[i].node = node; -#endif - desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids; - lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); - alloc_desc_masks(&desc[i], node, true); - init_desc_masks(&desc[i]); - set_irq_desc(i, &desc[i]); - } - - return arch_early_irq_init(); -} - -struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node) -{ - struct irq_desc *desc; - unsigned long flags; - - if (irq >= nr_irqs) { - WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n", - irq, nr_irqs); - return NULL; - } - - desc = irq_to_desc(irq); - if (desc) - return desc; - - raw_spin_lock_irqsave(&sparse_irq_lock, flags); - - /* We have to check it to avoid races with another CPU */ - desc = irq_to_desc(irq); - if (desc) - goto out_unlock; - - desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); - - printk(KERN_DEBUG " alloc irq_desc for %d on node %d\n", irq, node); - if (!desc) { - printk(KERN_ERR "can not alloc irq_desc\n"); - BUG_ON(1); - } - init_one_irq_desc(irq, desc, node); - - set_irq_desc(irq, desc); - -out_unlock: - raw_spin_unlock_irqrestore(&sparse_irq_lock, flags); - - return desc; -} - -#else /* !CONFIG_SPARSE_IRQ */ - -struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { - [0 ... NR_IRQS-1] = { - .status = IRQ_DISABLED, - .chip = &no_irq_chip, - .handle_irq = handle_bad_irq, - .depth = 1, - .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock), - } -}; - -static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS]; -int __init early_irq_init(void) -{ - struct irq_desc *desc; - int count; - int i; - - 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].irq = i; - alloc_desc_masks(&desc[i], 0, true); - init_desc_masks(&desc[i]); - desc[i].kstat_irqs = kstat_irqs_all[i]; - } - return arch_early_irq_init(); -} - -struct irq_desc *irq_to_desc(unsigned int irq) -{ - return (irq < NR_IRQS) ? irq_desc + irq : NULL; -} - -struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node) -{ - return irq_to_desc(irq); -} -#endif /* !CONFIG_SPARSE_IRQ */ - -void clear_kstat_irqs(struct irq_desc *desc) -{ - memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs))); -} - -/* - * What should we do if we get a hw irq event on an illegal vector? - * Each architecture has to answer this themself. - */ -static void ack_bad(unsigned int irq) -{ - struct irq_desc *desc = irq_to_desc(irq); - - print_irq_desc(irq, desc); - ack_bad_irq(irq); -} - -/* - * NOP functions - */ -static void noop(unsigned int irq) -{ -} - -static unsigned int noop_ret(unsigned int irq) -{ - return 0; -} - -/* - * Generic no controller implementation - */ -struct irq_chip no_irq_chip = { - .name = "none", - .startup = noop_ret, - .shutdown = noop, - .enable = noop, - .disable = noop, - .ack = ack_bad, - .end = noop, -}; - -/* - * Generic dummy implementation which can be used for - * real dumb interrupt sources - */ -struct irq_chip dummy_irq_chip = { - .name = "dummy", - .startup = noop_ret, - .shutdown = noop, - .enable = noop, - .disable = noop, - .ack = noop, - .mask = noop, - .unmask = noop, - .end = noop, -}; - /* * Special, empty irq handler: */ @@ -348,6 +41,7 @@ irqreturn_t no_action(int cpl, void *dev_id) { return IRQ_NONE; } +EXPORT_SYMBOL_GPL(no_action); static void warn_no_thread(unsigned int irq, struct irqaction *action) { @@ -358,34 +52,103 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action) "but no thread function available.", irq, action->name); } -/** - * handle_IRQ_event - irq action chain handler - * @irq: the interrupt number - * @action: the interrupt action chain for this irq - * - * Handles the action chain of an irq event - */ -irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) +void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action) { - irqreturn_t ret, retval = IRQ_NONE; - unsigned int status = 0; + /* + * In case the thread crashed and was killed we just pretend that + * we handled the interrupt. The hardirq handler has disabled the + * device interrupt, so no irq storm is lurking. + */ + if (action->thread->flags & PF_EXITING) + return; - if (!(action->flags & IRQF_DISABLED)) - local_irq_enable_in_hardirq(); + /* + * Wake up the handler thread for this action. If the + * RUNTHREAD bit is already set, nothing to do. + */ + if (test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + return; + + /* + * It's safe to OR the mask lockless here. We have only two + * places which write to threads_oneshot: This code and the + * irq thread. + * + * This code is the hard irq context and can never run on two + * cpus in parallel. If it ever does we have more serious + * problems than this bitmask. + * + * The irq threads of this irq which clear their "running" bit + * in threads_oneshot are serialized via desc->lock against + * each other and they are serialized against this code by + * IRQS_INPROGRESS. + * + * Hard irq handler: + * + * spin_lock(desc->lock); + * desc->state |= IRQS_INPROGRESS; + * spin_unlock(desc->lock); + * set_bit(IRQTF_RUNTHREAD, &action->thread_flags); + * desc->threads_oneshot |= mask; + * spin_lock(desc->lock); + * desc->state &= ~IRQS_INPROGRESS; + * spin_unlock(desc->lock); + * + * irq thread: + * + * again: + * spin_lock(desc->lock); + * if (desc->state & IRQS_INPROGRESS) { + * spin_unlock(desc->lock); + * while(desc->state & IRQS_INPROGRESS) + * cpu_relax(); + * goto again; + * } + * if (!test_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + * desc->threads_oneshot &= ~mask; + * spin_unlock(desc->lock); + * + * So either the thread waits for us to clear IRQS_INPROGRESS + * or we are waiting in the flow handler for desc->lock to be + * released before we reach this point. The thread also checks + * IRQTF_RUNTHREAD under desc->lock. If set it leaves + * threads_oneshot untouched and runs the thread another time. + */ + desc->threads_oneshot |= action->thread_mask; + + /* + * We increment the threads_active counter in case we wake up + * the irq thread. The irq thread decrements the counter when + * it returns from the handler or in the exit path and wakes + * up waiters which are stuck in synchronize_irq() when the + * active count becomes zero. synchronize_irq() is serialized + * against this code (hard irq handler) via IRQS_INPROGRESS + * like the finalize_oneshot() code. See comment above. + */ + atomic_inc(&desc->threads_active); + + wake_up_process(action->thread); +} + +irqreturn_t +handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) +{ + irqreturn_t retval = IRQ_NONE; + unsigned int flags = 0, irq = desc->irq_data.irq; do { + irqreturn_t res; + trace_irq_handler_entry(irq, action); - ret = action->handler(irq, action->dev_id); - trace_irq_handler_exit(irq, action, ret); + res = action->handler(irq, action->dev_id); + trace_irq_handler_exit(irq, action, res); - switch (ret) { - case IRQ_WAKE_THREAD: - /* - * Set result to handled so the spurious check - * does not trigger. - */ - ret = IRQ_HANDLED; + if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pF enabled interrupts\n", + irq, action->handler)) + local_irq_disable(); + switch (res) { + case IRQ_WAKE_THREAD: /* * Catch drivers which return WAKE_THREAD but * did not set up a thread function @@ -395,165 +158,40 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) break; } - /* - * Wake up the handler thread for this - * action. In case the thread crashed and was - * killed we just pretend that we handled the - * interrupt. The hardirq handler above has - * disabled the device interrupt, so no irq - * storm is lurking. - */ - if (likely(!test_bit(IRQTF_DIED, - &action->thread_flags))) { - set_bit(IRQTF_RUNTHREAD, &action->thread_flags); - wake_up_process(action->thread); - } + __irq_wake_thread(desc, action); /* Fall through to add to randomness */ case IRQ_HANDLED: - status |= action->flags; + flags |= action->flags; break; default: break; } - retval |= ret; + retval |= res; action = action->next; } while (action); - if (status & IRQF_SAMPLE_RANDOM) - add_interrupt_randomness(irq); - local_irq_disable(); + add_interrupt_randomness(irq, flags); + if (!noirqdebug) + note_interrupt(irq, desc, retval); return retval; } -#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ - -#ifdef CONFIG_ENABLE_WARN_DEPRECATED -# warning __do_IRQ is deprecated. Please convert to proper flow handlers -#endif - -/** - * __do_IRQ - original all in one highlevel IRQ handler - * @irq: the interrupt number - * - * __do_IRQ handles all normal device IRQ's (the special - * SMP cross-CPU interrupts have their own specific - * handlers). - * - * This is the original x86 implementation which is used for every - * interrupt type. - */ -unsigned int __do_IRQ(unsigned int irq) +irqreturn_t handle_irq_event(struct irq_desc *desc) { - struct irq_desc *desc = irq_to_desc(irq); - struct irqaction *action; - unsigned int status; - - kstat_incr_irqs_this_cpu(irq, desc); - - if (CHECK_IRQ_PER_CPU(desc->status)) { - irqreturn_t action_ret; - - /* - * No locking required for CPU-local interrupts: - */ - if (desc->chip->ack) - desc->chip->ack(irq); - if (likely(!(desc->status & IRQ_DISABLED))) { - action_ret = handle_IRQ_event(irq, desc->action); - if (!noirqdebug) - note_interrupt(irq, desc, action_ret); - } - desc->chip->end(irq); - return 1; - } - - raw_spin_lock(&desc->lock); - if (desc->chip->ack) - desc->chip->ack(irq); - /* - * REPLAY is when Linux resends an IRQ that was dropped earlier - * WAITING is used by probe to mark irqs that are being tested - */ - status = desc->status & ~(IRQ_REPLAY | IRQ_WAITING); - status |= IRQ_PENDING; /* we _want_ to handle it */ - - /* - * If the IRQ is disabled for whatever reason, we cannot - * use the action we have. - */ - action = NULL; - if (likely(!(status & (IRQ_DISABLED | IRQ_INPROGRESS)))) { - action = desc->action; - status &= ~IRQ_PENDING; /* we commit to handling */ - status |= IRQ_INPROGRESS; /* we are handling it */ - } - desc->status = status; - - /* - * If there is no IRQ handler or it was disabled, exit early. - * Since we set PENDING, if another processor is handling - * a different instance of this same irq, the other processor - * will take care of it. - */ - if (unlikely(!action)) - goto out; - - /* - * Edge triggered interrupts need to remember - * pending events. - * This applies to any hw interrupts that allow a second - * instance of the same irq to arrive while we are in do_IRQ - * or in the handler. But the code here only handles the _second_ - * instance of the irq, not the third or fourth. So it is mostly - * useful for irq hardware that does not mask cleanly in an - * SMP environment. - */ - for (;;) { - irqreturn_t action_ret; - - raw_spin_unlock(&desc->lock); - - action_ret = handle_IRQ_event(irq, action); - if (!noirqdebug) - note_interrupt(irq, desc, action_ret); - - raw_spin_lock(&desc->lock); - if (likely(!(desc->status & IRQ_PENDING))) - break; - desc->status &= ~IRQ_PENDING; - } - desc->status &= ~IRQ_INPROGRESS; + struct irqaction *action = desc->action; + irqreturn_t ret; -out: - /* - * The ->end() handler has to deal with interrupts which got - * disabled while the handler was running. - */ - desc->chip->end(irq); + desc->istate &= ~IRQS_PENDING; + irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); raw_spin_unlock(&desc->lock); - return 1; -} -#endif - -void early_init_irq_lock_class(void) -{ - struct irq_desc *desc; - int i; - - for_each_irq_desc(i, desc) { - lockdep_set_class(&desc->lock, &irq_desc_lock_class); - } -} + ret = handle_irq_event_percpu(desc, action); -unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) -{ - struct irq_desc *desc = irq_to_desc(irq); - return desc ? desc->kstat_irqs[cpu] : 0; + raw_spin_lock(&desc->lock); + irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); + return ret; } -EXPORT_SYMBOL(kstat_irqs_cpu); - diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index c63f3bc88f0..099ea2e0eb8 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -1,95 +1,196 @@ /* * IRQ subsystem internal functions and variables: + * + * Do not ever include this file from anything else than + * kernel/irq/. Do not even think about using any information outside + * of this file for your non core code. */ +#include <linux/irqdesc.h> +#include <linux/kernel_stat.h> -extern int noirqdebug; +#ifdef CONFIG_SPARSE_IRQ +# define IRQ_BITMAP_BITS (NR_IRQS + 8196) +#else +# define IRQ_BITMAP_BITS NR_IRQS +#endif -/* Set default functions for irq_chip structures: */ -extern void irq_chip_set_defaults(struct irq_chip *chip); +#define istate core_internal_state__do_not_mess_with_it -/* Set default handler: */ -extern void compat_irq_chip_set_default_handler(struct irq_desc *desc); +extern bool noirqdebug; + +/* + * Bits used by threaded handlers: + * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run + * 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 + */ +enum { + IRQTF_RUNTHREAD, + IRQTF_WARNED, + IRQTF_AFFINITY, + IRQTF_FORCED_THREAD, +}; + +/* + * Bit masks for desc->core_internal_state__do_not_mess_with_it + * + * IRQS_AUTODETECT - autodetection in progress + * IRQS_SPURIOUS_DISABLED - was disabled due to spurious interrupt + * detection + * IRQS_POLL_INPROGRESS - polling in progress + * IRQS_ONESHOT - irq is not unmasked in primary handler + * IRQS_REPLAY - irq is replayed + * IRQS_WAITING - irq is waiting + * IRQS_PENDING - irq is pending and replayed later + * IRQS_SUSPENDED - irq is suspended + */ +enum { + IRQS_AUTODETECT = 0x00000001, + IRQS_SPURIOUS_DISABLED = 0x00000002, + IRQS_POLL_INPROGRESS = 0x00000008, + IRQS_ONESHOT = 0x00000020, + IRQS_REPLAY = 0x00000040, + IRQS_WAITING = 0x00000080, + IRQS_PENDING = 0x00000200, + IRQS_SUSPENDED = 0x00000800, +}; + +#include "debug.h" +#include "settings.h" + +#define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data) extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, unsigned long flags); extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp); extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume); -extern struct lock_class_key irq_desc_lock_class; -extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); -extern void clear_kstat_irqs(struct irq_desc *desc); -extern raw_spinlock_t sparse_irq_lock; +extern int irq_startup(struct irq_desc *desc, bool resend); +extern void irq_shutdown(struct irq_desc *desc); +extern void irq_enable(struct irq_desc *desc); +extern void irq_disable(struct irq_desc *desc); +extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu); +extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); +extern void mask_irq(struct irq_desc *desc); +extern void unmask_irq(struct irq_desc *desc); +extern void unmask_threaded_irq(struct irq_desc *desc); #ifdef CONFIG_SPARSE_IRQ -void replace_irq_desc(unsigned int irq, struct irq_desc *desc); +static inline void irq_mark_irq(unsigned int irq) { } +#else +extern void irq_mark_irq(unsigned int irq); #endif +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(struct irq_desc *desc); + +/* Resending of interrupts :*/ +void check_irq_resend(struct irq_desc *desc, unsigned int irq); +bool irq_wait_for_poll(struct irq_desc *desc); +void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); + #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); +extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc); extern void register_handler_proc(unsigned int irq, struct irqaction *action); extern void unregister_handler_proc(unsigned int irq, struct irqaction *action); #else static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { } +static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { } static inline void register_handler_proc(unsigned int irq, struct irqaction *action) { } static inline void unregister_handler_proc(unsigned int irq, struct irqaction *action) { } #endif -extern int irq_select_affinity_usr(unsigned int irq); +extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask); extern void irq_set_thread_affinity(struct irq_desc *desc); +extern int irq_do_set_affinity(struct irq_data *data, + const struct cpumask *dest, bool force); + /* Inline functions for support of irq chips on slow busses */ -static inline void chip_bus_lock(unsigned int irq, struct irq_desc *desc) +static inline void chip_bus_lock(struct irq_desc *desc) +{ + if (unlikely(desc->irq_data.chip->irq_bus_lock)) + desc->irq_data.chip->irq_bus_lock(&desc->irq_data); +} + +static inline void chip_bus_sync_unlock(struct irq_desc *desc) +{ + if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock)) + desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data); +} + +#define _IRQ_DESC_CHECK (1 << 0) +#define _IRQ_DESC_PERCPU (1 << 1) + +#define IRQ_GET_DESC_CHECK_GLOBAL (_IRQ_DESC_CHECK) +#define IRQ_GET_DESC_CHECK_PERCPU (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU) + +struct irq_desc * +__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, + unsigned int check); +void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus); + +static inline struct irq_desc * +irq_get_desc_buslock(unsigned int irq, unsigned long *flags, unsigned int check) { - if (unlikely(desc->chip->bus_lock)) - desc->chip->bus_lock(irq); + return __irq_get_desc_lock(irq, flags, true, check); } -static inline void chip_bus_sync_unlock(unsigned int irq, struct irq_desc *desc) +static inline void +irq_put_desc_busunlock(struct irq_desc *desc, unsigned long flags) { - if (unlikely(desc->chip->bus_sync_unlock)) - desc->chip->bus_sync_unlock(irq); + __irq_put_desc_unlock(desc, flags, true); +} + +static inline struct irq_desc * +irq_get_desc_lock(unsigned int irq, unsigned long *flags, unsigned int check) +{ + return __irq_get_desc_lock(irq, flags, false, check); +} + +static inline void +irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) +{ + __irq_put_desc_unlock(desc, flags, false); } /* - * Debugging printout: + * Manipulation functions for irq_data.state */ +static inline void irqd_set_move_pending(struct irq_data *d) +{ + d->state_use_accessors |= IRQD_SETAFFINITY_PENDING; +} -#include <linux/kallsyms.h> +static inline void irqd_clr_move_pending(struct irq_data *d) +{ + d->state_use_accessors &= ~IRQD_SETAFFINITY_PENDING; +} -#define P(f) if (desc->status & f) printk("%14s set\n", #f) +static inline void irqd_clear(struct irq_data *d, unsigned int mask) +{ + d->state_use_accessors &= ~mask; +} -static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc) +static inline void irqd_set(struct irq_data *d, unsigned int mask) { - printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n", - irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled); - printk("->handle_irq(): %p, ", desc->handle_irq); - print_symbol("%s\n", (unsigned long)desc->handle_irq); - printk("->chip(): %p, ", desc->chip); - print_symbol("%s\n", (unsigned long)desc->chip); - printk("->action(): %p\n", desc->action); - if (desc->action) { - printk("->action->handler(): %p, ", desc->action->handler); - print_symbol("%s\n", (unsigned long)desc->action->handler); - } - - P(IRQ_INPROGRESS); - P(IRQ_DISABLED); - P(IRQ_PENDING); - P(IRQ_REPLAY); - P(IRQ_AUTODETECT); - P(IRQ_WAITING); - P(IRQ_LEVEL); - P(IRQ_MASKED); -#ifdef CONFIG_IRQ_PER_CPU - P(IRQ_PER_CPU); -#endif - P(IRQ_NOPROBE); - P(IRQ_NOREQUEST); - P(IRQ_NOAUTOEN); + d->state_use_accessors |= mask; } -#undef P +static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) +{ + return d->state_use_accessors & mask; +} +static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc) +{ + __this_cpu_inc(*desc->kstat_irqs); + __this_cpu_inc(kstat.irqs_sum); +} diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c new file mode 100644 index 00000000000..1487a123db5 --- /dev/null +++ b/kernel/irq/irqdesc.c @@ -0,0 +1,554 @@ +/* + * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar + * Copyright (C) 2005-2006, Thomas Gleixner, Russell King + * + * This file contains the interrupt descriptor management code + * + * Detailed information is available in Documentation/DocBook/genericirq + * + */ +#include <linux/irq.h> +#include <linux/slab.h> +#include <linux/export.h> +#include <linux/interrupt.h> +#include <linux/kernel_stat.h> +#include <linux/radix-tree.h> +#include <linux/bitmap.h> + +#include "internals.h" + +/* + * lockdep: we want to handle all irq_desc locks as a single lock-class: + */ +static struct lock_class_key irq_desc_lock_class; + +#if defined(CONFIG_SMP) +static void __init init_irq_default_affinity(void) +{ + alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); + cpumask_setall(irq_default_affinity); +} +#else +static void __init init_irq_default_affinity(void) +{ +} +#endif + +#ifdef CONFIG_SMP +static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) +{ + if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node)) + return -ENOMEM; + +#ifdef CONFIG_GENERIC_PENDING_IRQ + if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) { + free_cpumask_var(desc->irq_data.affinity); + return -ENOMEM; + } +#endif + return 0; +} + +static void desc_smp_init(struct irq_desc *desc, int node) +{ + desc->irq_data.node = node; + cpumask_copy(desc->irq_data.affinity, irq_default_affinity); +#ifdef CONFIG_GENERIC_PENDING_IRQ + cpumask_clear(desc->pending_mask); +#endif +} + +static inline int desc_node(struct irq_desc *desc) +{ + return desc->irq_data.node; +} + +#else +static inline int +alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; } +static inline void desc_smp_init(struct irq_desc *desc, int node) { } +static inline int desc_node(struct irq_desc *desc) { return 0; } +#endif + +static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, + struct module *owner) +{ + int cpu; + + desc->irq_data.irq = irq; + desc->irq_data.chip = &no_irq_chip; + desc->irq_data.chip_data = NULL; + desc->irq_data.handler_data = NULL; + desc->irq_data.msi_desc = NULL; + irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); + irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); + desc->handle_irq = handle_bad_irq; + desc->depth = 1; + desc->irq_count = 0; + desc->irqs_unhandled = 0; + desc->name = NULL; + desc->owner = owner; + for_each_possible_cpu(cpu) + *per_cpu_ptr(desc->kstat_irqs, cpu) = 0; + desc_smp_init(desc, node); +} + +int nr_irqs = NR_IRQS; +EXPORT_SYMBOL_GPL(nr_irqs); + +static DEFINE_MUTEX(sparse_irq_lock); +static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS); + +#ifdef CONFIG_SPARSE_IRQ + +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); +} +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_data.affinity); +} +#else +static inline void free_masks(struct irq_desc *desc) { } +#endif + +static struct irq_desc *alloc_desc(int irq, int node, struct module *owner) +{ + struct irq_desc *desc; + gfp_t gfp = GFP_KERNEL; + + desc = kzalloc_node(sizeof(*desc), gfp, 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, gfp, node)) + goto err_kstat; + + raw_spin_lock_init(&desc->lock); + lockdep_set_class(&desc->lock, &irq_desc_lock_class); + + desc_set_defaults(irq, desc, node, owner); + + return desc; + +err_kstat: + free_percpu(desc->kstat_irqs); +err_desc: + kfree(desc); + return NULL; +} + +static void free_desc(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + unregister_irq_proc(irq, desc); + + mutex_lock(&sparse_irq_lock); + delete_irq_desc(irq); + mutex_unlock(&sparse_irq_lock); + + free_masks(desc); + free_percpu(desc->kstat_irqs); + kfree(desc); +} + +static int alloc_descs(unsigned int start, unsigned int cnt, int node, + struct module *owner) +{ + struct irq_desc *desc; + int i; + + for (i = 0; i < cnt; i++) { + desc = alloc_desc(start + i, node, owner); + if (!desc) + goto err; + mutex_lock(&sparse_irq_lock); + irq_insert_desc(start + i, desc); + mutex_unlock(&sparse_irq_lock); + } + return start; + +err: + for (i--; i >= 0; i--) + free_desc(start + i); + + mutex_lock(&sparse_irq_lock); + bitmap_clear(allocated_irqs, start, cnt); + mutex_unlock(&sparse_irq_lock); + return -ENOMEM; +} + +static int irq_expand_nr_irqs(unsigned int nr) +{ + if (nr > IRQ_BITMAP_BITS) + return -ENOMEM; + nr_irqs = nr; + return 0; +} + +int __init early_irq_init(void) +{ + int i, initcnt, node = first_online_node; + struct irq_desc *desc; + + init_irq_default_affinity(); + + /* Let arch update nr_irqs and return the nr of preallocated irqs */ + initcnt = arch_probe_nr_irqs(); + printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt); + + if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS)) + nr_irqs = IRQ_BITMAP_BITS; + + if (WARN_ON(initcnt > IRQ_BITMAP_BITS)) + initcnt = IRQ_BITMAP_BITS; + + if (initcnt > nr_irqs) + nr_irqs = initcnt; + + for (i = 0; i < initcnt; i++) { + desc = alloc_desc(i, node, NULL); + set_bit(i, allocated_irqs); + irq_insert_desc(i, desc); + } + return arch_early_irq_init(); +} + +#else /* !CONFIG_SPARSE_IRQ */ + +struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { + [0 ... NR_IRQS-1] = { + .handle_irq = handle_bad_irq, + .depth = 1, + .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock), + } +}; + +int __init early_irq_init(void) +{ + int count, i, node = first_online_node; + struct irq_desc *desc; + + 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], GFP_KERNEL, node); + raw_spin_lock_init(&desc[i].lock); + lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); + desc_set_defaults(i, &desc[i], node, NULL); + } + return arch_early_irq_init(); +} + +struct irq_desc *irq_to_desc(unsigned int irq) +{ + return (irq < NR_IRQS) ? irq_desc + irq : NULL; +} +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, desc_node(desc), NULL); + raw_spin_unlock_irqrestore(&desc->lock, flags); +} + +static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, + struct module *owner) +{ + u32 i; + + for (i = 0; i < cnt; i++) { + struct irq_desc *desc = irq_to_desc(start + i); + + desc->owner = owner; + } + return start; +} + +static int irq_expand_nr_irqs(unsigned int nr) +{ + return -ENOMEM; +} + +void irq_mark_irq(unsigned int irq) +{ + mutex_lock(&sparse_irq_lock); + bitmap_set(allocated_irqs, irq, 1); + mutex_unlock(&sparse_irq_lock); +} + +#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) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc) + return -EINVAL; + generic_handle_irq_desc(irq, desc); + return 0; +} +EXPORT_SYMBOL_GPL(generic_handle_irq); + +/* Dynamic interrupt handling */ + +/** + * irq_free_descs - free irq descriptors + * @from: Start of descriptor range + * @cnt: Number of consecutive irqs to free + */ +void irq_free_descs(unsigned int from, unsigned int cnt) +{ + int i; + + if (from >= nr_irqs || (from + cnt) > nr_irqs) + return; + + for (i = 0; i < cnt; i++) + free_desc(from + i); + + mutex_lock(&sparse_irq_lock); + bitmap_clear(allocated_irqs, from, cnt); + mutex_unlock(&sparse_irq_lock); +} +EXPORT_SYMBOL_GPL(irq_free_descs); + +/** + * irq_alloc_descs - allocate and initialize a range of irq descriptors + * @irq: Allocate for specific irq number if irq >= 0 + * @from: Start the search from this irq number + * @cnt: Number of consecutive irqs to allocate. + * @node: Preferred node on which the irq descriptor should be allocated + * @owner: Owning module (can be NULL) + * + * 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) +{ + int start, ret; + + if (!cnt) + return -EINVAL; + + if (irq >= 0) { + if (from > irq) + return -EINVAL; + from = irq; + } else { + /* + * For interrupts which are freely allocated the + * architecture can force a lower bound to the @from + * argument. x86 uses this to exclude the GSI space. + */ + from = arch_dynirq_lower_bound(from); + } + + mutex_lock(&sparse_irq_lock); + + start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS, + from, cnt, 0); + ret = -EEXIST; + if (irq >=0 && start != irq) + goto err; + + if (start + cnt > nr_irqs) { + ret = irq_expand_nr_irqs(start + cnt); + if (ret) + goto err; + } + + bitmap_set(allocated_irqs, start, cnt); + mutex_unlock(&sparse_irq_lock); + return alloc_descs(start, cnt, node, owner); + +err: + mutex_unlock(&sparse_irq_lock); + return ret; +} +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); + + 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 + * + * Returns next irq number after offset or nr_irqs if none is found. + */ +unsigned int irq_get_next_irq(unsigned int offset) +{ + return find_next_bit(allocated_irqs, nr_irqs, offset); +} + +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); + + 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; + } + + if (bus) + chip_bus_lock(desc); + raw_spin_lock_irqsave(&desc->lock, *flags); + } + return desc; +} + +void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) +{ + raw_spin_unlock_irqrestore(&desc->lock, flags); + if (bus) + chip_bus_sync_unlock(desc); +} + +int irq_set_percpu_devid(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc) + return -EINVAL; + + if (desc->percpu_enabled) + return -EINVAL; + + desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL); + + if (!desc->percpu_enabled) + return -ENOMEM; + + irq_set_percpu_devid_flags(irq); + return 0; +} + +void kstat_incr_irq_this_cpu(unsigned int irq) +{ + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); +} + +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; +} + +unsigned int kstat_irqs(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + int cpu; + int sum = 0; + + if (!desc || !desc->kstat_irqs) + return 0; + for_each_possible_cpu(cpu) + sum += *per_cpu_ptr(desc->kstat_irqs, cpu); + return sum; +} diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c new file mode 100644 index 00000000000..eb5e10e32e0 --- /dev/null +++ b/kernel/irq/irqdomain.c @@ -0,0 +1,711 @@ +#define pr_fmt(fmt) "irq: " fmt + +#include <linux/debugfs.h> +#include <linux/hardirq.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdesc.h> +#include <linux/irqdomain.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/topology.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/smp.h> +#include <linux/fs.h> + +static LIST_HEAD(irq_domain_list); +static DEFINE_MUTEX(irq_domain_mutex); + +static DEFINE_MUTEX(revmap_trees_mutex); +static struct irq_domain *irq_default_domain; + +/** + * __irq_domain_add() - Allocate a new irq_domain data structure + * @of_node: optional device-tree node of the interrupt controller + * @size: Size of linear map; 0 for radix mapping only + * @hwirq_max: Maximum number of interrupts supported by controller + * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no + * direct mapping + * @ops: map/unmap domain callbacks + * @host_data: Controller private data pointer + * + * 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, + irq_hw_number_t hwirq_max, int direct_max, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + domain = kzalloc_node(sizeof(*domain) + (sizeof(unsigned int) * size), + GFP_KERNEL, of_node_to_nid(of_node)); + if (WARN_ON(!domain)) + return NULL; + + /* 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->hwirq_max = hwirq_max; + domain->revmap_size = size; + domain->revmap_direct_max_irq = direct_max; + + mutex_lock(&irq_domain_mutex); + list_add(&domain->link, &irq_domain_list); + mutex_unlock(&irq_domain_mutex); + + pr_debug("Added domain %s\n", domain->name); + return domain; +} +EXPORT_SYMBOL_GPL(__irq_domain_add); + +/** + * irq_domain_remove() - Remove an irq domain. + * @domain: domain to remove + * + * This routine is used to remove an irq domain. The caller must ensure + * that all mappings within the domain have been disposed of prior to + * use, depending on the revmap type. + */ +void irq_domain_remove(struct irq_domain *domain) +{ + mutex_lock(&irq_domain_mutex); + + /* + * radix_tree_delete() takes care of destroying the root + * node when all entries are removed. Shout if there are + * any mappings left. + */ + WARN_ON(domain->revmap_tree.height); + + list_del(&domain->link); + + /* + * If the going away domain is the default one, reset it. + */ + if (unlikely(irq_default_domain == domain)) + irq_set_default_host(NULL); + + mutex_unlock(&irq_domain_mutex); + + pr_debug("Removed domain %s\n", domain->name); + + of_node_put(domain->of_node); + kfree(domain); +} +EXPORT_SYMBOL_GPL(irq_domain_remove); + +/** + * irq_domain_add_simple() - Register an irq_domain and optionally map a range of irqs + * @of_node: pointer to interrupt controller's device tree node. + * @size: total number of irqs in mapping + * @first_irq: first number of irq block assigned to the domain, + * pass zero to assign irqs on-the-fly. If first_irq is non-zero, then + * pre-map all of the irqs in the domain to virqs starting at first_irq. + * @ops: map/unmap domain callbacks + * @host_data: Controller private data pointer + * + * Allocates an irq_domain, and optionally if first_irq is positive then also + * allocate irq_descs and map all of the hwirqs to virqs starting at first_irq. + * + * This is intended to implement the expected behaviour for most + * interrupt controllers. If device tree is used, then first_irq will be 0 and + * irqs get mapped dynamically on the fly. However, if the controller requires + * static virq assignments (non-DT boot) then it will set that up correctly. + */ +struct irq_domain *irq_domain_add_simple(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + domain = __irq_domain_add(of_node, size, size, 0, ops, host_data); + if (!domain) + return NULL; + + if (first_irq > 0) { + if (IS_ENABLED(CONFIG_SPARSE_IRQ)) { + /* attempt to allocated irq_descs */ + int rc = irq_alloc_descs(first_irq, first_irq, size, + of_node_to_nid(of_node)); + if (rc < 0) + pr_info("Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", + first_irq); + } + irq_domain_associate_many(domain, first_irq, 0, size); + } + + return domain; +} +EXPORT_SYMBOL_GPL(irq_domain_add_simple); + +/** + * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain. + * @of_node: pointer to interrupt controller's device tree node. + * @size: total number of irqs in legacy mapping + * @first_irq: first number of irq block assigned to the domain + * @first_hwirq: first hwirq number to use for the translation. Should normally + * be '0', but a positive integer can be used if the effective + * hwirqs numbering does not begin at zero. + * @ops: map/unmap domain callbacks + * @host_data: Controller private data pointer + * + * Note: the map() callback will be called before this function returns + * for all legacy interrupts except 0 (which is always the invalid irq for + * a legacy controller). + */ +struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + irq_hw_number_t first_hwirq, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + domain = __irq_domain_add(of_node, first_hwirq + size, + first_hwirq + size, 0, ops, host_data); + if (!domain) + return NULL; + + irq_domain_associate_many(domain, first_irq, first_hwirq, size); + + return domain; +} +EXPORT_SYMBOL_GPL(irq_domain_add_legacy); + +/** + * irq_find_host() - Locates a domain for a given device node + * @node: device-tree node of the interrupt controller + */ +struct irq_domain *irq_find_host(struct device_node *node) +{ + struct irq_domain *h, *found = NULL; + int rc; + + /* We might want to match the legacy controller last since + * it might potentially be set to match all interrupts in + * the absence of a device node. This isn't a problem so far + * yet though... + */ + mutex_lock(&irq_domain_mutex); + list_for_each_entry(h, &irq_domain_list, link) { + if (h->ops->match) + rc = h->ops->match(h, node); + else + rc = (h->of_node != NULL) && (h->of_node == node); + + if (rc) { + found = h; + break; + } + } + mutex_unlock(&irq_domain_mutex); + return found; +} +EXPORT_SYMBOL_GPL(irq_find_host); + +/** + * irq_set_default_host() - Set a "default" irq domain + * @domain: default domain pointer + * + * For convenience, it's possible to set a "default" domain that will be used + * whenever NULL is passed to irq_create_mapping(). It makes life easier for + * platforms that want to manipulate a few hard coded interrupt numbers that + * aren't properly represented in the device-tree. + */ +void irq_set_default_host(struct irq_domain *domain) +{ + pr_debug("Default domain set to @0x%p\n", domain); + + irq_default_domain = domain; +} +EXPORT_SYMBOL_GPL(irq_set_default_host); + +static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) +{ + struct irq_data *irq_data = irq_get_irq_data(irq); + irq_hw_number_t hwirq; + + if (WARN(!irq_data || irq_data->domain != domain, + "virq%i doesn't exist; cannot disassociate\n", irq)) + return; + + hwirq = irq_data->hwirq; + irq_set_status_flags(irq, IRQ_NOREQUEST); + + /* remove chip and handler */ + irq_set_chip_and_handler(irq, NULL, NULL); + + /* Make sure it's completed */ + synchronize_irq(irq); + + /* Tell the PIC about it */ + if (domain->ops->unmap) + domain->ops->unmap(domain, irq); + smp_mb(); + + irq_data->domain = NULL; + irq_data->hwirq = 0; + + /* Clear reverse map for this hwirq */ + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = 0; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_delete(&domain->revmap_tree, hwirq); + mutex_unlock(&revmap_trees_mutex); + } +} + +int irq_domain_associate(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + struct irq_data *irq_data = irq_get_irq_data(virq); + int ret; + + if (WARN(hwirq >= domain->hwirq_max, + "error: hwirq 0x%x is too large for %s\n", (int)hwirq, domain->name)) + return -EINVAL; + if (WARN(!irq_data, "error: virq%i is not allocated", virq)) + return -EINVAL; + if (WARN(irq_data->domain, "error: virq%i is already associated", virq)) + return -EINVAL; + + mutex_lock(&irq_domain_mutex); + irq_data->hwirq = hwirq; + irq_data->domain = domain; + if (domain->ops->map) { + ret = domain->ops->map(domain, virq, hwirq); + if (ret != 0) { + /* + * If map() returns -EPERM, this interrupt is protected + * by the firmware or some other service and shall not + * be mapped. Don't bother telling the user about it. + */ + if (ret != -EPERM) { + pr_info("%s didn't like hwirq-0x%lx to VIRQ%i mapping (rc=%d)\n", + domain->name, hwirq, virq, ret); + } + irq_data->domain = NULL; + irq_data->hwirq = 0; + mutex_unlock(&irq_domain_mutex); + return ret; + } + + /* If not already assigned, give the domain the chip's name */ + if (!domain->name && irq_data->chip) + domain->name = irq_data->chip->name; + } + + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = virq; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_insert(&domain->revmap_tree, hwirq, irq_data); + mutex_unlock(&revmap_trees_mutex); + } + mutex_unlock(&irq_domain_mutex); + + irq_clear_status_flags(virq, IRQ_NOREQUEST); + + return 0; +} +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) +{ + int i; + + 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); + + for (i = 0; i < count; i++) { + irq_domain_associate(domain, irq_base + i, hwirq_base + i); + } +} +EXPORT_SYMBOL_GPL(irq_domain_associate_many); + +/** + * irq_create_direct_mapping() - Allocate an irq for direct mapping + * @domain: domain to allocate the irq for or NULL for default domain + * + * This routine is used for irq controllers which can choose the hardware + * interrupt numbers they generate. In such a case it's simplest to use + * the linux irq as the hardware interrupt number. It still uses the linear + * or radix tree to store the mapping, but the irq controller can optimize + * the revmap path by using the hwirq directly. + */ +unsigned int irq_create_direct_mapping(struct irq_domain *domain) +{ + unsigned int virq; + + if (domain == NULL) + domain = irq_default_domain; + + virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); + if (!virq) { + pr_debug("create_direct virq allocation failed\n"); + return 0; + } + if (virq >= domain->revmap_direct_max_irq) { + pr_err("ERROR: no free irqs available below %i maximum\n", + domain->revmap_direct_max_irq); + irq_free_desc(virq); + return 0; + } + pr_debug("create_direct obtained virq %d\n", virq); + + if (irq_domain_associate(domain, virq, virq)) { + irq_free_desc(virq); + return 0; + } + + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_direct_mapping); + +/** + * irq_create_mapping() - Map a hardware interrupt into linux irq space + * @domain: domain owning this hardware interrupt or NULL for default domain + * @hwirq: hardware irq number in that domain space + * + * Only one mapping per hardware interrupt is permitted. Returns a linux + * irq number. + * If the sense/trigger is to be specified, set_irq_type() should be called + * on the number returned from that call. + */ +unsigned int irq_create_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + unsigned int hint; + int virq; + + pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); + + /* Look for default domain if nececssary */ + if (domain == NULL) + domain = irq_default_domain; + if (domain == NULL) { + WARN(1, "%s(, %lx) called with NULL domain\n", __func__, hwirq); + return 0; + } + pr_debug("-> using domain @%p\n", domain); + + /* Check if mapping already exists */ + virq = irq_find_mapping(domain, hwirq); + if (virq) { + pr_debug("-> existing mapping on virq %d\n", virq); + return virq; + } + + /* Allocate a virtual interrupt number */ + hint = hwirq % nr_irqs; + if (hint == 0) + hint++; + virq = irq_alloc_desc_from(hint, of_node_to_nid(domain->of_node)); + if (virq <= 0) + virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); + if (virq <= 0) { + pr_debug("-> virq allocation failed\n"); + return 0; + } + + if (irq_domain_associate(domain, virq, hwirq)) { + irq_free_desc(virq); + return 0; + } + + pr_debug("irq %lu on domain %s mapped to virtual irq %u\n", + hwirq, of_node_full_name(domain->of_node), virq); + + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_mapping); + +/** + * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs + * @domain: domain owning the interrupt range + * @irq_base: beginning of linux IRQ range + * @hwirq_base: beginning of hardware IRQ range + * @count: Number of interrupts to map + * + * This routine is used for allocating and mapping a range of hardware + * irqs to linux irqs where the linux irq numbers are at pre-defined + * locations. For use by controllers that already have static mappings + * to insert in to the domain. + * + * Non-linear users can use irq_create_identity_mapping() for IRQ-at-a-time + * domain insertion. + * + * 0 is returned upon success, while any failure to establish a static + * mapping is treated as an error. + */ +int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base, + irq_hw_number_t hwirq_base, int count) +{ + int ret; + + ret = irq_alloc_descs(irq_base, irq_base, count, + of_node_to_nid(domain->of_node)); + if (unlikely(ret < 0)) + return ret; + + irq_domain_associate_many(domain, irq_base, hwirq_base, count); + return 0; +} +EXPORT_SYMBOL_GPL(irq_create_strict_mappings); + +unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) +{ + struct irq_domain *domain; + irq_hw_number_t hwirq; + unsigned int type = IRQ_TYPE_NONE; + unsigned int virq; + + domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain; + if (!domain) { + pr_warn("no irq domain found for %s !\n", + of_node_full_name(irq_data->np)); + 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; + } + + /* Create mapping */ + virq = irq_create_mapping(domain, hwirq); + if (!virq) + return virq; + + /* Set type if specified and different than the current one */ + if (type != IRQ_TYPE_NONE && + type != irq_get_trigger_type(virq)) + irq_set_irq_type(virq, type); + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_of_mapping); + +/** + * irq_dispose_mapping() - Unmap an interrupt + * @virq: linux irq number of the interrupt to unmap + */ +void irq_dispose_mapping(unsigned int virq) +{ + struct irq_data *irq_data = irq_get_irq_data(virq); + struct irq_domain *domain; + + if (!virq || !irq_data) + return; + + domain = irq_data->domain; + if (WARN_ON(domain == NULL)) + return; + + irq_domain_disassociate(domain, virq); + irq_free_desc(virq); +} +EXPORT_SYMBOL_GPL(irq_dispose_mapping); + +/** + * irq_find_mapping() - Find a linux irq from an hw irq number. + * @domain: domain owning this hardware interrupt + * @hwirq: hardware irq number in that domain space + */ +unsigned int irq_find_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + struct irq_data *data; + + /* Look for default domain if nececssary */ + if (domain == NULL) + domain = irq_default_domain; + if (domain == NULL) + return 0; + + if (hwirq < domain->revmap_direct_max_irq) { + data = irq_get_irq_data(hwirq); + if (data && (data->domain == domain) && (data->hwirq == hwirq)) + return hwirq; + } + + /* Check if the hwirq is in the linear revmap. */ + if (hwirq < domain->revmap_size) + return domain->linear_revmap[hwirq]; + + rcu_read_lock(); + data = radix_tree_lookup(&domain->revmap_tree, hwirq); + rcu_read_unlock(); + return data ? data->irq : 0; +} +EXPORT_SYMBOL_GPL(irq_find_mapping); + +#ifdef CONFIG_IRQ_DOMAIN_DEBUG +static int virq_debug_show(struct seq_file *m, void *private) +{ + unsigned long flags; + struct irq_desc *desc; + struct irq_domain *domain; + struct radix_tree_iter iter; + void *data, **slot; + int i; + + seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", + "name", "mapped", "linear-max", "direct-max", "devtree-node"); + mutex_lock(&irq_domain_mutex); + list_for_each_entry(domain, &irq_domain_list, link) { + int count = 0; + 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) : ""); + } + mutex_unlock(&irq_domain_mutex); + + seq_printf(m, "%-5s %-7s %-15s %-*s %6s %-14s %s\n", "irq", "hwirq", + "chip name", (int)(2 * sizeof(void *) + 2), "chip data", + "active", "type", "domain"); + + for (i = 1; i < nr_irqs; i++) { + desc = irq_to_desc(i); + if (!desc) + continue; + + raw_spin_lock_irqsave(&desc->lock, flags); + domain = desc->irq_data.domain; + + if (domain) { + struct irq_chip *chip; + int hwirq = desc->irq_data.hwirq; + bool direct; + + seq_printf(m, "%5d ", i); + seq_printf(m, "0x%05x ", hwirq); + + chip = irq_desc_get_chip(desc); + seq_printf(m, "%-15s ", (chip && chip->name) ? chip->name : "none"); + + data = irq_desc_get_chip_data(desc); + seq_printf(m, data ? "0x%p " : " %p ", data); + + seq_printf(m, " %c ", (desc->action && desc->action->handler) ? '*' : ' '); + direct = (i == hwirq) && (i < domain->revmap_direct_max_irq); + seq_printf(m, "%6s%-8s ", + (hwirq < domain->revmap_size) ? "LINEAR" : "RADIX", + direct ? "(DIRECT)" : ""); + seq_printf(m, "%s\n", desc->irq_data.domain->name); + } + + raw_spin_unlock_irqrestore(&desc->lock, flags); + } + + return 0; +} + +static int virq_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, virq_debug_show, inode->i_private); +} + +static const struct file_operations virq_debug_fops = { + .open = virq_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init irq_debugfs_init(void) +{ + if (debugfs_create_file("irq_domain_mapping", S_IRUGO, NULL, + NULL, &virq_debug_fops) == NULL) + return -ENOMEM; + + return 0; +} +__initcall(irq_debugfs_init); +#endif /* CONFIG_IRQ_DOMAIN_DEBUG */ + +/** + * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings + * + * Device Tree IRQ specifier translation function which works with one cell + * bindings where the cell value maps directly to the hwirq number. + */ +int irq_domain_xlate_onecell(struct irq_domain *d, struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 1)) + return -EINVAL; + *out_hwirq = intspec[0]; + *out_type = IRQ_TYPE_NONE; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_xlate_onecell); + +/** + * irq_domain_xlate_twocell() - Generic xlate for direct two cell bindings + * + * Device Tree IRQ specifier translation function which works with two cell + * bindings where the cell values map directly to the hwirq number + * and linux irq flags. + */ +int irq_domain_xlate_twocell(struct irq_domain *d, struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 2)) + return -EINVAL; + *out_hwirq = intspec[0]; + *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_xlate_twocell); + +/** + * irq_domain_xlate_onetwocell() - Generic xlate for one or two cell bindings + * + * Device Tree IRQ specifier translation function which works with either one + * or two cell bindings where the cell values map directly to the hwirq number + * and linux irq flags. + * + * Note: don't use this function unless your interrupt controller explicitly + * supports both one and two cell bindings. For the majority of controllers + * the _onecell() or _twocell() variants above should be used. + */ +int irq_domain_xlate_onetwocell(struct irq_domain *d, + struct device_node *ctrlr, + const u32 *intspec, unsigned int intsize, + unsigned long *out_hwirq, unsigned int *out_type) +{ + if (WARN_ON(intsize < 1)) + return -EINVAL; + *out_hwirq = intspec[0]; + *out_type = (intsize > 1) ? intspec[1] : IRQ_TYPE_NONE; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_xlate_onetwocell); + +const struct irq_domain_ops irq_domain_simple_ops = { + .xlate = irq_domain_xlate_onetwocell, +}; +EXPORT_SYMBOL_GPL(irq_domain_simple_ops); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index eb6078ca60c..3dc6a61bf06 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -7,6 +7,8 @@ * This file contains driver APIs to the irq subsystem. */ +#define pr_fmt(fmt) "genirq: " fmt + #include <linux/irq.h> #include <linux/kthread.h> #include <linux/module.h> @@ -14,26 +16,25 @@ #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sched/rt.h> +#include <linux/task_work.h> #include "internals.h" -/** - * synchronize_irq - wait for pending IRQ handlers (on other CPUs) - * @irq: interrupt number to wait for - * - * This function waits for any pending IRQ handlers for this interrupt - * to complete before returning. If you use this function while - * holding a resource the IRQ handler may need you will deadlock. - * - * This function may be called - with care - from IRQ context. - */ -void synchronize_irq(unsigned int irq) +#ifdef CONFIG_IRQ_FORCED_THREADING +__read_mostly bool force_irqthreads; + +static int __init setup_forced_irqthreads(char *arg) { - struct irq_desc *desc = irq_to_desc(irq); - unsigned int status; + force_irqthreads = true; + return 0; +} +early_param("threadirqs", setup_forced_irqthreads); +#endif - if (!desc) - return; +static void __synchronize_hardirq(struct irq_desc *desc) +{ + bool inprogress; do { unsigned long flags; @@ -42,22 +43,66 @@ void synchronize_irq(unsigned int irq) * Wait until we're out of the critical section. This might * give the wrong answer due to the lack of memory barriers. */ - while (desc->status & IRQ_INPROGRESS) + while (irqd_irq_inprogress(&desc->irq_data)) cpu_relax(); /* Ok, that indicated we're done: double-check carefully. */ raw_spin_lock_irqsave(&desc->lock, flags); - status = desc->status; + inprogress = irqd_irq_inprogress(&desc->irq_data); raw_spin_unlock_irqrestore(&desc->lock, flags); /* Oops, that failed? */ - } while (status & IRQ_INPROGRESS); + } while (inprogress); +} - /* - * We made sure that no hardirq handler is running. Now verify - * that no threaded handlers are active. - */ - wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active)); +/** + * synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs) + * @irq: interrupt number to wait for + * + * This function waits for any pending hard IRQ handlers for this + * interrupt to complete before returning. If you use this + * function while holding a resource the IRQ handler may need you + * will deadlock. It does not take associated threaded handlers + * into account. + * + * Do not use this for shutdown scenarios where you must be sure + * that all parts (hardirq and threaded handler) have completed. + * + * This function may be called - with care - from IRQ context. + */ +void synchronize_hardirq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) + __synchronize_hardirq(desc); +} +EXPORT_SYMBOL(synchronize_hardirq); + +/** + * synchronize_irq - wait for pending IRQ handlers (on other CPUs) + * @irq: interrupt number to wait for + * + * This function waits for any pending IRQ handlers for this interrupt + * to complete before returning. If you use this function while + * holding a resource the IRQ handler may need you will deadlock. + * + * This function may be called - with care - from IRQ context. + */ +void synchronize_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) { + __synchronize_hardirq(desc); + /* + * We made sure that no hardirq handler is + * running. Now verify that no threaded handlers are + * active. + */ + wait_event(desc->wait_for_threads, + !atomic_read(&desc->threads_active)); + } } EXPORT_SYMBOL(synchronize_irq); @@ -73,8 +118,8 @@ int irq_can_set_affinity(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); - if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip || - !desc->chip->set_affinity) + if (!desc || !irqd_can_balance(&desc->irq_data) || + !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity) return 0; return 1; @@ -100,50 +145,186 @@ void irq_set_thread_affinity(struct irq_desc *desc) } } +#ifdef CONFIG_GENERIC_PENDING_IRQ +static inline bool irq_can_move_pcntxt(struct irq_data *data) +{ + return irqd_can_move_in_process_context(data); +} +static inline bool irq_move_pending(struct irq_data *data) +{ + return irqd_is_setaffinity_pending(data); +} +static inline void +irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) +{ + cpumask_copy(desc->pending_mask, mask); +} +static inline void +irq_get_pending(struct cpumask *mask, struct irq_desc *desc) +{ + cpumask_copy(mask, desc->pending_mask); +} +#else +static inline bool irq_can_move_pcntxt(struct irq_data *data) { return true; } +static inline bool irq_move_pending(struct irq_data *data) { return false; } +static inline void +irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { } +static inline void +irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { } +#endif + +int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + struct irq_desc *desc = irq_data_to_desc(data); + struct irq_chip *chip = irq_data_get_irq_chip(data); + int ret; + + ret = chip->irq_set_affinity(data, mask, force); + switch (ret) { + case IRQ_SET_MASK_OK: + cpumask_copy(data->affinity, mask); + case IRQ_SET_MASK_OK_NOCOPY: + irq_set_thread_affinity(desc); + ret = 0; + } + + return ret; +} + +int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + struct irq_chip *chip = irq_data_get_irq_chip(data); + struct irq_desc *desc = irq_data_to_desc(data); + int ret = 0; + + if (!chip || !chip->irq_set_affinity) + return -EINVAL; + + if (irq_can_move_pcntxt(data)) { + ret = irq_do_set_affinity(data, mask, force); + } else { + irqd_set_move_pending(data); + irq_copy_pending(desc, mask); + } + + if (desc->affinity_notify) { + kref_get(&desc->affinity_notify->kref); + schedule_work(&desc->affinity_notify->work); + } + irqd_set(data, IRQD_AFFINITY_SET); + + return ret; +} + +int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force) +{ + struct irq_desc *desc = irq_to_desc(irq); + unsigned long flags; + int ret; + + if (!desc) + return -EINVAL; + + raw_spin_lock_irqsave(&desc->lock, flags); + ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force); + raw_spin_unlock_irqrestore(&desc->lock, flags); + return ret; +} + +int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + + if (!desc) + return -EINVAL; + desc->affinity_hint = m; + irq_put_desc_unlock(desc, flags); + return 0; +} +EXPORT_SYMBOL_GPL(irq_set_affinity_hint); + +static void irq_affinity_notify(struct work_struct *work) +{ + struct irq_affinity_notify *notify = + container_of(work, struct irq_affinity_notify, work); + struct irq_desc *desc = irq_to_desc(notify->irq); + cpumask_var_t cpumask; + unsigned long flags; + + if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL)) + goto out; + + raw_spin_lock_irqsave(&desc->lock, flags); + if (irq_move_pending(&desc->irq_data)) + irq_get_pending(cpumask, desc); + else + cpumask_copy(cpumask, desc->irq_data.affinity); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + notify->notify(notify, cpumask); + + free_cpumask_var(cpumask); +out: + kref_put(¬ify->kref, notify->release); +} + /** - * irq_set_affinity - Set the irq affinity of a given irq - * @irq: Interrupt to set affinity - * @cpumask: cpumask + * irq_set_affinity_notifier - control notification of IRQ affinity changes + * @irq: Interrupt for which to enable/disable notification + * @notify: Context for notification, or %NULL to disable + * notification. Function pointers must be initialised; + * the other fields will be initialised by this function. * + * Must be called in process context. Notification may only be enabled + * after the IRQ is allocated and must be disabled before the IRQ is + * freed using free_irq(). */ -int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) +int +irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) { struct irq_desc *desc = irq_to_desc(irq); + struct irq_affinity_notify *old_notify; unsigned long flags; - if (!desc->chip->set_affinity) - return -EINVAL; + /* The release function is promised process context */ + might_sleep(); - raw_spin_lock_irqsave(&desc->lock, flags); + if (!desc) + return -EINVAL; -#ifdef CONFIG_GENERIC_PENDING_IRQ - if (desc->status & IRQ_MOVE_PCNTXT) { - if (!desc->chip->set_affinity(irq, cpumask)) { - cpumask_copy(desc->affinity, cpumask); - irq_set_thread_affinity(desc); - } - } - else { - desc->status |= IRQ_MOVE_PENDING; - cpumask_copy(desc->pending_mask, cpumask); - } -#else - if (!desc->chip->set_affinity(irq, cpumask)) { - cpumask_copy(desc->affinity, cpumask); - irq_set_thread_affinity(desc); + /* Complete initialisation of *notify */ + if (notify) { + notify->irq = irq; + kref_init(¬ify->kref); + INIT_WORK(¬ify->work, irq_affinity_notify); } -#endif - desc->status |= IRQ_AFFINITY_SET; + + raw_spin_lock_irqsave(&desc->lock, flags); + old_notify = desc->affinity_notify; + desc->affinity_notify = notify; raw_spin_unlock_irqrestore(&desc->lock, flags); + + if (old_notify) + kref_put(&old_notify->kref, old_notify->release); + return 0; } +EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); #ifndef CONFIG_AUTO_IRQ_AFFINITY /* * Generic version of the affinity autoselector. */ -static int setup_affinity(unsigned int irq, struct irq_desc *desc) +static int +setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask) { + struct cpumask *set = irq_default_affinity; + int node = desc->irq_data.node; + + /* Excludes PER_CPU and NO_BALANCE interrupts */ if (!irq_can_set_affinity(irq)) return 0; @@ -151,22 +332,28 @@ static int setup_affinity(unsigned int irq, struct irq_desc *desc) * Preserve an userspace affinity setup, but make sure that * one of the targets is online. */ - if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) { - if (cpumask_any_and(desc->affinity, cpu_online_mask) - < nr_cpu_ids) - goto set_affinity; + if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) { + if (cpumask_intersects(desc->irq_data.affinity, + cpu_online_mask)) + set = desc->irq_data.affinity; else - desc->status &= ~IRQ_AFFINITY_SET; + irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET); } - cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity); -set_affinity: - desc->chip->set_affinity(irq, desc->affinity); + cpumask_and(mask, cpu_online_mask, set); + if (node != NUMA_NO_NODE) { + const struct cpumask *nodemask = cpumask_of_node(node); + /* make sure at least one of the cpus in nodemask is online */ + if (cpumask_intersects(mask, nodemask)) + cpumask_and(mask, mask, nodemask); + } + irq_do_set_affinity(&desc->irq_data, mask, false); return 0; } #else -static inline int setup_affinity(unsigned int irq, struct irq_desc *d) +static inline int +setup_affinity(unsigned int irq, struct irq_desc *d, struct cpumask *mask) { return irq_select_affinity(irq); } @@ -175,23 +362,21 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *d) /* * Called when affinity is set via /proc/irq */ -int irq_select_affinity_usr(unsigned int irq) +int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; int ret; raw_spin_lock_irqsave(&desc->lock, flags); - ret = setup_affinity(irq, desc); - if (!ret) - irq_set_thread_affinity(desc); + ret = setup_affinity(irq, desc, mask); raw_spin_unlock_irqrestore(&desc->lock, flags); - return ret; } #else -static inline int setup_affinity(unsigned int irq, struct irq_desc *desc) +static inline int +setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask) { return 0; } @@ -200,15 +385,25 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *desc) void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend) { if (suspend) { - if (!desc->action || (desc->action->flags & IRQF_TIMER)) + if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND)) return; - desc->status |= IRQ_SUSPENDED; + desc->istate |= IRQS_SUSPENDED; } - if (!desc->depth++) { - desc->status |= IRQ_DISABLED; - desc->chip->disable(irq); - } + if (!desc->depth++) + irq_disable(desc); +} + +static int __disable_irq_nosync(unsigned int irq) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); + + if (!desc) + return -EINVAL; + __disable_irq(desc, irq, false); + irq_put_desc_busunlock(desc, flags); + return 0; } /** @@ -224,17 +419,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend) */ void disable_irq_nosync(unsigned int irq) { - struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - - if (!desc) - return; - - chip_bus_lock(irq, desc); - raw_spin_lock_irqsave(&desc->lock, flags); - __disable_irq(desc, irq, false); - raw_spin_unlock_irqrestore(&desc->lock, flags); - chip_bus_sync_unlock(irq, desc); + __disable_irq_nosync(irq); } EXPORT_SYMBOL(disable_irq_nosync); @@ -252,21 +437,24 @@ EXPORT_SYMBOL(disable_irq_nosync); */ void disable_irq(unsigned int irq) { - struct irq_desc *desc = irq_to_desc(irq); - - if (!desc) - return; - - disable_irq_nosync(irq); - if (desc->action) + if (!__disable_irq_nosync(irq)) synchronize_irq(irq); } EXPORT_SYMBOL(disable_irq); void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume) { - if (resume) - desc->status &= ~IRQ_SUSPENDED; + if (resume) { + if (!(desc->istate & IRQS_SUSPENDED)) { + if (!desc->action) + return; + if (!(desc->action->flags & IRQF_FORCE_RESUME)) + return; + /* Pretend that it got disabled ! */ + desc->depth++; + } + desc->istate &= ~IRQS_SUSPENDED; + } switch (desc->depth) { case 0: @@ -274,12 +462,11 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume) WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq); break; case 1: { - unsigned int status = desc->status & ~IRQ_DISABLED; - - if (desc->status & IRQ_SUSPENDED) + if (desc->istate & IRQS_SUSPENDED) goto err_out; /* Prevent probing on this irq: */ - desc->status = status | IRQ_NOPROBE; + irq_settings_set_noprobe(desc); + irq_enable(desc); check_irq_resend(desc, irq); /* fall-through */ } @@ -297,21 +484,22 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume) * IRQ line is re-enabled. * * This function may be called from IRQ context only when - * desc->chip->bus_lock and desc->chip->bus_sync_unlock are NULL ! + * desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL ! */ void enable_irq(unsigned int irq) { - struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); if (!desc) return; + if (WARN(!desc->irq_data.chip, + KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq)) + goto out; - chip_bus_lock(irq, desc); - raw_spin_lock_irqsave(&desc->lock, flags); __enable_irq(desc, irq, false); - raw_spin_unlock_irqrestore(&desc->lock, flags); - chip_bus_sync_unlock(irq, desc); +out: + irq_put_desc_busunlock(desc, flags); } EXPORT_SYMBOL(enable_irq); @@ -320,14 +508,17 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on) struct irq_desc *desc = irq_to_desc(irq); int ret = -ENXIO; - if (desc->chip->set_wake) - ret = desc->chip->set_wake(irq, on); + if (irq_desc_get_chip(desc)->flags & IRQCHIP_SKIP_SET_WAKE) + return 0; + + if (desc->irq_data.chip->irq_set_wake) + ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on); return ret; } /** - * set_irq_wake - control irq power management wakeup + * irq_set_irq_wake - control irq power management wakeup * @irq: interrupt to control * @on: enable/disable power management wakeup * @@ -338,23 +529,25 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on) * Wakeup mode lets this IRQ wake the system from sleep * states like "suspend to RAM". */ -int set_irq_wake(unsigned int irq, unsigned int on) +int irq_set_irq_wake(unsigned int irq, unsigned int on) { - struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; + struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); int ret = 0; + if (!desc) + return -EINVAL; + /* wakeup-capable irqs can be shared between drivers that * don't need to have the same sleep mode behaviors. */ - raw_spin_lock_irqsave(&desc->lock, flags); if (on) { if (desc->wake_depth++ == 0) { ret = set_irq_wake_real(irq, on); if (ret) desc->wake_depth = 0; else - desc->status |= IRQ_WAKEUP; + irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE); } } else { if (desc->wake_depth == 0) { @@ -364,14 +557,13 @@ int set_irq_wake(unsigned int irq, unsigned int on) if (ret) desc->wake_depth = 1; else - desc->status &= ~IRQ_WAKEUP; + irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE); } } - - raw_spin_unlock_irqrestore(&desc->lock, flags); + irq_put_desc_busunlock(desc, flags); return ret; } -EXPORT_SYMBOL(set_irq_wake); +EXPORT_SYMBOL(irq_set_irq_wake); /* * Internal function that tells the architecture code whether a @@ -380,67 +572,92 @@ EXPORT_SYMBOL(set_irq_wake); */ int can_request_irq(unsigned int irq, unsigned long irqflags) { - struct irq_desc *desc = irq_to_desc(irq); - struct irqaction *action; + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + int canrequest = 0; if (!desc) return 0; - if (desc->status & IRQ_NOREQUEST) - return 0; - - action = desc->action; - if (action) - if (irqflags & action->flags & IRQF_SHARED) - action = NULL; - - return !action; -} - -void compat_irq_chip_set_default_handler(struct irq_desc *desc) -{ - /* - * If the architecture still has not overriden - * the flow handler then zap the default. This - * should catch incorrect flow-type setting. - */ - if (desc->handle_irq == &handle_bad_irq) - desc->handle_irq = NULL; + if (irq_settings_can_request(desc)) { + if (!desc->action || + irqflags & desc->action->flags & IRQF_SHARED) + canrequest = 1; + } + irq_put_desc_unlock(desc, flags); + return canrequest; } int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, - unsigned long flags) + unsigned long flags) { - int ret; - struct irq_chip *chip = desc->chip; + struct irq_chip *chip = desc->irq_data.chip; + int ret, unmask = 0; - if (!chip || !chip->set_type) { + if (!chip || !chip->irq_set_type) { /* * IRQF_TRIGGER_* but the PIC does not support multiple * flow-types? */ pr_debug("No set_type function for IRQ %d (%s)\n", irq, - chip ? (chip->name ? : "unknown") : "unknown"); + chip ? (chip->name ? : "unknown") : "unknown"); return 0; } - /* caller masked out all except trigger mode flags */ - ret = chip->set_type(irq, flags); - - if (ret) - pr_err("setting trigger mode %d for irq %u failed (%pF)\n", - (int)flags, irq, chip->set_type); - else { - if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH)) - flags |= IRQ_LEVEL; - /* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */ - desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK); - desc->status |= flags; + flags &= IRQ_TYPE_SENSE_MASK; + + if (chip->flags & IRQCHIP_SET_TYPE_MASKED) { + if (!irqd_irq_masked(&desc->irq_data)) + mask_irq(desc); + if (!irqd_irq_disabled(&desc->irq_data)) + unmask = 1; } + /* caller masked out all except trigger mode flags */ + ret = chip->irq_set_type(&desc->irq_data, flags); + + switch (ret) { + case IRQ_SET_MASK_OK: + irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK); + irqd_set(&desc->irq_data, flags); + + case IRQ_SET_MASK_OK_NOCOPY: + flags = irqd_get_trigger_type(&desc->irq_data); + irq_settings_set_trigger_mask(desc, flags); + irqd_clear(&desc->irq_data, IRQD_LEVEL); + irq_settings_clr_level(desc); + if (flags & IRQ_TYPE_LEVEL_MASK) { + irq_settings_set_level(desc); + irqd_set(&desc->irq_data, IRQD_LEVEL); + } + + ret = 0; + break; + default: + pr_err("Setting trigger mode %lu for irq %u failed (%pF)\n", + flags, irq, chip->irq_set_type); + } + if (unmask) + unmask_irq(desc); return ret; } +#ifdef CONFIG_HARDIRQS_SW_RESEND +int irq_set_parent(int irq, int parent_irq) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + + if (!desc) + return -EINVAL; + + desc->parent_irq = parent_irq; + + irq_put_desc_unlock(desc, flags); + return 0; +} +#endif + /* * Default primary interrupt handler for threaded interrupts. Is * assigned as primary handler when request_threaded_irq is called @@ -463,8 +680,9 @@ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id) static int irq_wait_for_interrupt(struct irqaction *action) { + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) { @@ -472,7 +690,9 @@ static int irq_wait_for_interrupt(struct irqaction *action) return 0; } schedule(); + set_current_state(TASK_INTERRUPTIBLE); } + __set_current_state(TASK_RUNNING); return -1; } @@ -481,16 +701,53 @@ static int irq_wait_for_interrupt(struct irqaction *action) * handler finished. unmask if the interrupt has not been disabled and * is marked MASKED. */ -static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc) +static void irq_finalize_oneshot(struct irq_desc *desc, + struct irqaction *action) { - chip_bus_lock(irq, desc); + if (!(desc->istate & IRQS_ONESHOT)) + return; +again: + chip_bus_lock(desc); raw_spin_lock_irq(&desc->lock); - if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) { - desc->status &= ~IRQ_MASKED; - desc->chip->unmask(irq); + + /* + * Implausible though it may be we need to protect us against + * the following scenario: + * + * The thread is faster done than the hard interrupt handler + * on the other CPU. If we unmask the irq line then the + * interrupt can come in again and masks the line, leaves due + * to IRQS_INPROGRESS and the irq line is masked forever. + * + * This also serializes the state of shared oneshot handlers + * versus "desc->threads_onehsot |= action->thread_mask;" in + * irq_wake_thread(). See the comment there which explains the + * serialization. + */ + if (unlikely(irqd_irq_inprogress(&desc->irq_data))) { + raw_spin_unlock_irq(&desc->lock); + chip_bus_sync_unlock(desc); + cpu_relax(); + goto again; } + + /* + * Now check again, whether the thread should run. Otherwise + * we would clear the threads_oneshot bit of this thread which + * was just set. + */ + if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + goto out_unlock; + + desc->threads_oneshot &= ~action->thread_mask; + + if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data)) + unmask_threaded_irq(desc); + +out_unlock: raw_spin_unlock_irq(&desc->lock); - chip_bus_sync_unlock(irq, desc); + chip_bus_sync_unlock(desc); } #ifdef CONFIG_SMP @@ -501,6 +758,7 @@ static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { cpumask_var_t mask; + bool valid = true; if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags)) return; @@ -515,10 +773,18 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) } raw_spin_lock_irq(&desc->lock); - cpumask_copy(mask, desc->affinity); + /* + * This code is triggered unconditionally. Check the affinity + * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out. + */ + if (desc->irq_data.affinity) + cpumask_copy(mask, desc->irq_data.affinity); + else + valid = false; raw_spin_unlock_irq(&desc->lock); - set_cpus_allowed_ptr(current, mask); + if (valid) + set_cpus_allowed_ptr(current, mask); free_cpumask_var(mask); } #else @@ -527,77 +793,176 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { } #endif /* + * Interrupts which are not explicitely requested as threaded + * interrupts rely on the implicit bh/preempt disable of the hard irq + * context. So we need to disable bh here to avoid deadlocks and other + * side effects. + */ +static irqreturn_t +irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) +{ + irqreturn_t ret; + + local_bh_disable(); + ret = action->thread_fn(action->irq, action->dev_id); + irq_finalize_oneshot(desc, action); + local_bh_enable(); + return ret; +} + +/* + * Interrupts explicitly requested as threaded interrupts want to be + * preemtible - many of them need to sleep and wait for slow busses to + * complete. + */ +static irqreturn_t irq_thread_fn(struct irq_desc *desc, + struct irqaction *action) +{ + irqreturn_t ret; + + ret = action->thread_fn(action->irq, action->dev_id); + irq_finalize_oneshot(desc, action); + return ret; +} + +static void wake_threads_waitq(struct irq_desc *desc) +{ + if (atomic_dec_and_test(&desc->threads_active)) + wake_up(&desc->wait_for_threads); +} + +static void irq_thread_dtor(struct callback_head *unused) +{ + struct task_struct *tsk = current; + struct irq_desc *desc; + struct irqaction *action; + + if (WARN_ON_ONCE(!(current->flags & PF_EXITING))) + return; + + action = kthread_data(tsk); + + pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", + tsk->comm, tsk->pid, action->irq); + + + desc = irq_to_desc(action->irq); + /* + * If IRQTF_RUNTHREAD is set, we need to decrement + * desc->threads_active and wake possible waiters. + */ + if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags)) + wake_threads_waitq(desc); + + /* Prevent a stale desc->threads_oneshot */ + irq_finalize_oneshot(desc, action); +} + +/* * Interrupt handler thread */ static int irq_thread(void *data) { - struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, }; + struct callback_head on_exit_work; struct irqaction *action = data; struct irq_desc *desc = irq_to_desc(action->irq); - int wake, oneshot = desc->status & IRQ_ONESHOT; + irqreturn_t (*handler_fn)(struct irq_desc *desc, + struct irqaction *action); - sched_setscheduler(current, SCHED_FIFO, ¶m); - current->irqaction = action; + if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD, + &action->thread_flags)) + handler_fn = irq_forced_thread_fn; + else + handler_fn = irq_thread_fn; - while (!irq_wait_for_interrupt(action)) { - - irq_thread_check_affinity(desc, action); + init_task_work(&on_exit_work, irq_thread_dtor); + task_work_add(current, &on_exit_work, false); - atomic_inc(&desc->threads_active); + irq_thread_check_affinity(desc, action); - raw_spin_lock_irq(&desc->lock); - if (unlikely(desc->status & IRQ_DISABLED)) { - /* - * CHECKME: We might need a dedicated - * IRQ_THREAD_PENDING flag here, which - * retriggers the thread in check_irq_resend() - * but AFAICT IRQ_PENDING should be fine as it - * retriggers the interrupt itself --- tglx - */ - desc->status |= IRQ_PENDING; - raw_spin_unlock_irq(&desc->lock); - } else { - raw_spin_unlock_irq(&desc->lock); - - action->thread_fn(action->irq, action->dev_id); + while (!irq_wait_for_interrupt(action)) { + irqreturn_t action_ret; - if (oneshot) - irq_finalize_oneshot(action->irq, desc); - } + irq_thread_check_affinity(desc, action); - wake = atomic_dec_and_test(&desc->threads_active); + action_ret = handler_fn(desc, action); + if (action_ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); - if (wake && waitqueue_active(&desc->wait_for_threads)) - wake_up(&desc->wait_for_threads); + wake_threads_waitq(desc); } /* - * Clear irqaction. Otherwise exit_irq_thread() would make - * fuzz about an active irq thread going into nirvana. + * This is the regular exit path. __free_irq() is stopping the + * thread via kthread_stop() after calling + * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the + * oneshot mask bit can be set. We cannot verify that as we + * cannot touch the oneshot mask at this point anymore as + * __setup_irq() might have given out currents thread_mask + * again. */ - current->irqaction = NULL; + task_work_cancel(current, irq_thread_dtor); return 0; } -/* - * Called from do_exit() +/** + * irq_wake_thread - wake the irq thread for the action identified by dev_id + * @irq: Interrupt line + * @dev_id: Device identity for which the thread should be woken + * */ -void exit_irq_thread(void) +void irq_wake_thread(unsigned int irq, void *dev_id) { - struct task_struct *tsk = current; + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action; + unsigned long flags; - if (!tsk->irqaction) + if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return; - printk(KERN_ERR - "exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n", - tsk->comm ? tsk->comm : "", tsk->pid, tsk->irqaction->irq); + raw_spin_lock_irqsave(&desc->lock, flags); + for (action = desc->action; action; action = action->next) { + if (action->dev_id == dev_id) { + if (action->thread) + __irq_wake_thread(desc, action); + break; + } + } + raw_spin_unlock_irqrestore(&desc->lock, flags); +} +EXPORT_SYMBOL_GPL(irq_wake_thread); - /* - * Set the THREAD DIED flag to prevent further wakeups of the - * soon to be gone threaded handler. - */ - set_bit(IRQTF_DIED, &tsk->irqaction->flags); +static void irq_setup_forced_threading(struct irqaction *new) +{ + if (!force_irqthreads) + return; + if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) + return; + + 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; + } +} + +static int irq_request_resources(struct irq_desc *desc) +{ + struct irq_data *d = &desc->irq_data; + struct irq_chip *c = d->chip; + + return c->irq_request_resources ? c->irq_request_resources(d) : 0; +} + +static void irq_release_resources(struct irq_desc *desc) +{ + struct irq_data *d = &desc->irq_data; + struct irq_chip *c = d->chip; + + if (c->irq_release_resources) + c->irq_release_resources(d); } /* @@ -608,51 +973,37 @@ static int __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) { struct irqaction *old, **old_ptr; - const char *old_name = NULL; - unsigned long flags; - int nested, shared = 0; - int ret; + unsigned long flags, thread_mask = 0; + int ret, nested, shared = 0; + cpumask_var_t mask; if (!desc) return -EINVAL; - if (desc->chip == &no_irq_chip) + if (desc->irq_data.chip == &no_irq_chip) return -ENOSYS; - /* - * Some drivers like serial.c use request_irq() heavily, - * so we have to be careful not to interfere with a - * running system. - */ - if (new->flags & IRQF_SAMPLE_RANDOM) { - /* - * This function might sleep, we want to call it first, - * outside of the atomic block. - * Yes, this might clear the entropy pool if the wrong - * driver is attempted to be loaded, without actually - * installing a new handler, but is this really a problem, - * only the sysadmin is able to do this. - */ - rand_initialize_irq(irq); - } - - /* Oneshot interrupts are not allowed with shared */ - if ((new->flags & IRQF_ONESHOT) && (new->flags & IRQF_SHARED)) - return -EINVAL; + if (!try_module_get(desc->owner)) + return -ENODEV; /* * Check whether the interrupt nests into another interrupt * thread. */ - nested = desc->status & IRQ_NESTED_THREAD; + nested = irq_settings_is_nested_thread(desc); if (nested) { - if (!new->thread_fn) - return -EINVAL; + if (!new->thread_fn) { + ret = -EINVAL; + goto out_mput; + } /* * Replace the primary handler which was provided from * the driver for non nested interrupt handling by the * dummy function which warns when called. */ new->handler = irq_nested_primary_handler; + } else { + if (irq_settings_can_thread(desc)) + irq_setup_forced_threading(new); } /* @@ -662,11 +1013,19 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ 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)) - return PTR_ERR(t); + if (IS_ERR(t)) { + ret = PTR_ERR(t); + goto out_mput; + } + + 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 @@ -674,9 +1033,36 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ 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)) { + ret = -ENOMEM; + goto out_thread; } /* + * Drivers are often written to work w/o knowledge about the + * underlying irq chip implementation, so a request for a + * threaded irq without a primary hard irq context handler + * requires the ONESHOT flag to be set. Some irq chips like + * MSI based interrupts are per se one shot safe. Check the + * chip flags, so we can avoid the unmask dance at the end of + * the threaded handler for those. + */ + if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE) + new->flags &= ~IRQF_ONESHOT; + + /* * The following block of code has to be executed atomically */ raw_spin_lock_irqsave(&desc->lock, flags); @@ -687,31 +1073,99 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * Can't share interrupts unless both agree to and are * the same type (level, edge, polarity). So both flag * fields must have IRQF_SHARED set and the bits which - * set the trigger type must match. + * set the trigger type must match. Also all must + * agree on ONESHOT. */ if (!((old->flags & new->flags) & IRQF_SHARED) || - ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK)) { - old_name = old->name; + ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) || + ((old->flags ^ new->flags) & IRQF_ONESHOT)) goto mismatch; - } -#if defined(CONFIG_IRQ_PER_CPU) /* All handlers must agree on per-cpuness */ if ((old->flags & IRQF_PERCPU) != (new->flags & IRQF_PERCPU)) goto mismatch; -#endif /* add new interrupt at end of irq queue */ do { + /* + * Or all existing action->thread_mask bits, + * so we can find the next zero bit for this + * new action. + */ + thread_mask |= old->thread_mask; old_ptr = &old->next; old = *old_ptr; } while (old); shared = 1; } + /* + * Setup the thread mask for this irqaction for ONESHOT. For + * !ONESHOT irqs the thread mask is 0 so we can avoid a + * conditional in irq_wake_thread(). + */ + if (new->flags & IRQF_ONESHOT) { + /* + * Unlikely to have 32 resp 64 irqs sharing one line, + * but who knows. + */ + if (thread_mask == ~0UL) { + ret = -EBUSY; + goto out_mask; + } + /* + * The thread_mask for the action is or'ed to + * desc->thread_active to indicate that the + * IRQF_ONESHOT thread handler has been woken, but not + * yet finished. The bit is cleared when a thread + * completes. When all threads of a shared interrupt + * line have completed desc->threads_active becomes + * zero and the interrupt line is unmasked. See + * handle.c:irq_wake_thread() for further information. + * + * If no thread is woken by primary (hard irq context) + * interrupt handlers, then desc->threads_active is + * also checked for zero to unmask the irq line in the + * affected hard irq flow handlers + * (handle_[fasteoi|level]_irq). + * + * The new action gets the first zero bit of + * thread_mask assigned. See the loop above which or's + * all existing action->thread_mask bits. + */ + new->thread_mask = 1 << ffz(thread_mask); + + } else if (new->handler == irq_default_primary_handler && + !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) { + /* + * The interrupt was requested with handler = NULL, so + * we use the default primary handler for it. But it + * does not have the oneshot flag set. In combination + * with level interrupts this is deadly, because the + * default primary handler just wakes the thread, then + * the irq lines is reenabled, but the device still + * has the level irq asserted. Rinse and repeat.... + * + * While this works for edge type interrupts, we play + * it safe and reject unconditionally because we can't + * say for sure which type this interrupt really + * has. The type flags are unreliable as the + * underlying chip implementation can override them. + */ + pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n", + irq); + ret = -EINVAL; + goto out_mask; + } + if (!shared) { - irq_chip_set_defaults(desc->chip); + ret = irq_request_resources(desc); + if (ret) { + pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", + new->name, irq, desc->irq_data.chip->name); + goto out_mask; + } init_waitqueue_head(&desc->wait_for_threads); @@ -721,42 +1175,44 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) new->flags & IRQF_TRIGGER_MASK); if (ret) - goto out_thread; - } else - compat_irq_chip_set_default_handler(desc); -#if defined(CONFIG_IRQ_PER_CPU) - if (new->flags & IRQF_PERCPU) - desc->status |= IRQ_PER_CPU; -#endif + goto out_mask; + } - desc->status &= ~(IRQ_AUTODETECT | IRQ_WAITING | IRQ_ONESHOT | - IRQ_INPROGRESS | IRQ_SPURIOUS_DISABLED); + desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ + IRQS_ONESHOT | IRQS_WAITING); + irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); + + if (new->flags & IRQF_PERCPU) { + irqd_set(&desc->irq_data, IRQD_PER_CPU); + irq_settings_set_per_cpu(desc); + } if (new->flags & IRQF_ONESHOT) - desc->status |= IRQ_ONESHOT; + desc->istate |= IRQS_ONESHOT; - if (!(desc->status & IRQ_NOAUTOEN)) { - desc->depth = 0; - desc->status &= ~IRQ_DISABLED; - desc->chip->startup(irq); - } else + if (irq_settings_can_autoenable(desc)) + irq_startup(desc, true); + else /* Undo nested disables: */ desc->depth = 1; /* Exclude IRQ from balancing if requested */ - if (new->flags & IRQF_NOBALANCING) - desc->status |= IRQ_NO_BALANCING; + if (new->flags & IRQF_NOBALANCING) { + irq_settings_set_no_balancing(desc); + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + } /* Set default affinity mask once everything is setup */ - setup_affinity(irq, desc); - - } else if ((new->flags & IRQF_TRIGGER_MASK) - && (new->flags & IRQF_TRIGGER_MASK) - != (desc->status & IRQ_TYPE_SENSE_MASK)) { - /* hope the handler works with the actual trigger mode... */ - pr_warning("IRQ %d uses trigger mode %d; requested %d\n", - irq, (int)(desc->status & IRQ_TYPE_SENSE_MASK), - (int)(new->flags & IRQF_TRIGGER_MASK)); + setup_affinity(irq, desc, mask); + + } else if (new->flags & IRQF_TRIGGER_MASK) { + unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK; + unsigned int omsk = irq_settings_get_trigger_mask(desc); + + if (nmsk != omsk) + /* hope the handler works with current trigger mode */ + pr_warning("irq %d uses trigger mode %u; requested %u\n", + irq, nmsk, omsk); } new->irq = irq; @@ -770,8 +1226,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * Check whether we disabled the irq via the spurious handler * before. Reenable it and give it another chance. */ - if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) { - desc->status &= ~IRQ_SPURIOUS_DISABLED; + if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) { + desc->istate &= ~IRQS_SPURIOUS_DISABLED; __enable_irq(desc, irq, false); } @@ -787,30 +1243,34 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) register_irq_proc(irq, desc); new->dir = NULL; register_handler_proc(irq, new); + free_cpumask_var(mask); return 0; mismatch: -#ifdef CONFIG_DEBUG_SHIRQ if (!(new->flags & IRQF_PROBE_SHARED)) { - printk(KERN_ERR "IRQ handler type mismatch for IRQ %d\n", irq); - if (old_name) - printk(KERN_ERR "current handler: %s\n", old_name); + pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n", + irq, new->flags, new->name, old->flags, old->name); +#ifdef CONFIG_DEBUG_SHIRQ dump_stack(); - } #endif + } ret = -EBUSY; -out_thread: +out_mask: raw_spin_unlock_irqrestore(&desc->lock, flags); + free_cpumask_var(mask); + +out_thread: if (new->thread) { struct task_struct *t = new->thread; new->thread = NULL; - if (likely(!test_bit(IRQTF_DIED, &new->thread_flags))) - kthread_stop(t); + kthread_stop(t); put_task_struct(t); } +out_mput: + module_put(desc->owner); return ret; } @@ -823,13 +1283,20 @@ out_thread: */ int setup_irq(unsigned int irq, struct irqaction *act) { + int retval; struct irq_desc *desc = irq_to_desc(irq); - return __setup_irq(irq, desc, act); + if (WARN_ON(irq_settings_is_per_cpu_devid(desc))) + return -EINVAL; + chip_bus_lock(desc); + retval = __setup_irq(irq, desc, act); + chip_bus_sync_unlock(desc); + + return retval; } EXPORT_SYMBOL_GPL(setup_irq); - /* +/* * Internal function to unregister an irqaction - used to free * regular and special interrupts that are part of the architecture. */ @@ -869,21 +1336,18 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) /* Found it - now remove it from the list of entries: */ *action_ptr = action->next; - /* Currently used only by UML, might disappear one day: */ -#ifdef CONFIG_IRQ_RELEASE_METHOD - if (desc->chip->release) - desc->chip->release(irq, dev_id); -#endif - /* If this was the last handler, shut down the IRQ line: */ if (!desc->action) { - desc->status |= IRQ_DISABLED; - if (desc->chip->shutdown) - desc->chip->shutdown(irq); - else - desc->chip->disable(irq); + irq_shutdown(desc); + irq_release_resources(desc); } +#ifdef CONFIG_SMP + /* make sure affinity_hint is cleaned up */ + if (WARN_ON_ONCE(desc->affinity_hint)) + desc->affinity_hint = NULL; +#endif + raw_spin_unlock_irqrestore(&desc->lock, flags); unregister_handler_proc(irq, action); @@ -908,11 +1372,11 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) #endif if (action->thread) { - if (!test_bit(IRQTF_DIED, &action->thread_flags)) - kthread_stop(action->thread); + kthread_stop(action->thread); put_task_struct(action->thread); } + module_put(desc->owner); return action; } @@ -925,7 +1389,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) */ void remove_irq(unsigned int irq, struct irqaction *act) { - __free_irq(irq, act->dev_id); + struct irq_desc *desc = irq_to_desc(irq); + + if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc))) + __free_irq(irq, act->dev_id); } EXPORT_SYMBOL_GPL(remove_irq); @@ -947,12 +1414,17 @@ void free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); - if (!desc) + if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) return; - chip_bus_lock(irq, desc); +#ifdef CONFIG_SMP + if (WARN_ON(desc->affinity_notify)) + desc->affinity_notify = NULL; +#endif + + chip_bus_lock(desc); kfree(__free_irq(irq, dev_id)); - chip_bus_sync_unlock(irq, desc); + chip_bus_sync_unlock(desc); } EXPORT_SYMBOL(free_irq); @@ -977,7 +1449,7 @@ EXPORT_SYMBOL(free_irq); * and to set up the interrupt handler in the right order. * * If you want to set up a threaded irq handler for your device - * then you need to supply @handler and @thread_fn. @handler ist + * then you need to supply @handler and @thread_fn. @handler is * still called in hard interrupt context and has to check * whether the interrupt originates from the device. If yes it * needs to disable the interrupt on the device and return @@ -995,8 +1467,6 @@ EXPORT_SYMBOL(free_irq); * Flags: * * IRQF_SHARED Interrupt is shared - * IRQF_DISABLED Disable local interrupts while processing - * IRQF_SAMPLE_RANDOM The interrupt can be used for entropy * IRQF_TRIGGER_* Specify active edge(s) or level * */ @@ -1009,25 +1479,6 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, int retval; /* - * handle_IRQ_event() always ignores IRQF_DISABLED except for - * the _first_ irqaction (sigh). That can cause oopsing, but - * the behavior is classified as "will not fix" so we need to - * start nudging drivers away from using that idiom. - */ - if ((irqflags & (IRQF_SHARED|IRQF_DISABLED)) == - (IRQF_SHARED|IRQF_DISABLED)) { - pr_warning( - "IRQ %d/%s: IRQF_DISABLED is not guaranteed on shared IRQs\n", - irq, devname); - } - -#ifdef CONFIG_LOCKDEP - /* - * Lockdep wants atomic interrupt handlers: - */ - irqflags |= IRQF_DISABLED; -#endif - /* * Sanity-check: shared interrupts must pass in a real dev-ID, * otherwise we'll have trouble later trying to figure out * which interrupt is which (messes up the interrupt freeing @@ -1040,7 +1491,8 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, if (!desc) return -EINVAL; - if (desc->status & IRQ_NOREQUEST) + if (!irq_settings_can_request(desc) || + WARN_ON(irq_settings_is_per_cpu_devid(desc))) return -EINVAL; if (!handler) { @@ -1059,14 +1511,14 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, action->name = devname; action->dev_id = dev_id; - chip_bus_lock(irq, desc); + chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); - chip_bus_sync_unlock(irq, desc); + chip_bus_sync_unlock(desc); if (retval) kfree(action); -#ifdef CONFIG_DEBUG_SHIRQ +#ifdef CONFIG_DEBUG_SHIRQ_FIXME if (!retval && (irqflags & IRQF_SHARED)) { /* * It's a shared IRQ -- the driver ought to be prepared for it @@ -1088,3 +1540,233 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, return retval; } EXPORT_SYMBOL(request_threaded_irq); + +/** + * request_any_context_irq - allocate an interrupt line + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * Threaded handler for threaded interrupts. + * @flags: Interrupt type flags + * @name: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * This call allocates interrupt resources and enables the + * interrupt line and IRQ handling. It selects either a + * hardirq or threaded handling method depending on the + * context. + * + * On failure, it returns a negative value. On success, + * it returns either IRQC_IS_HARDIRQ or IRQC_IS_NESTED. + */ +int request_any_context_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, const char *name, void *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + int ret; + + if (!desc) + return -EINVAL; + + if (irq_settings_is_nested_thread(desc)) { + ret = request_threaded_irq(irq, NULL, handler, + flags, name, dev_id); + return !ret ? IRQC_IS_NESTED : ret; + } + + ret = request_irq(irq, handler, flags, name, dev_id); + return !ret ? IRQC_IS_HARDIRQ : ret; +} +EXPORT_SYMBOL_GPL(request_any_context_irq); + +void enable_percpu_irq(unsigned int irq, unsigned int type) +{ + unsigned int cpu = smp_processor_id(); + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU); + + if (!desc) + return; + + type &= IRQ_TYPE_SENSE_MASK; + if (type != IRQ_TYPE_NONE) { + int ret; + + ret = __irq_set_trigger(desc, irq, type); + + if (ret) { + WARN(1, "failed to set type for IRQ%d\n", irq); + goto out; + } + } + + irq_percpu_enable(desc, cpu); +out: + irq_put_desc_unlock(desc, flags); +} +EXPORT_SYMBOL_GPL(enable_percpu_irq); + +void disable_percpu_irq(unsigned int irq) +{ + unsigned int cpu = smp_processor_id(); + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU); + + if (!desc) + return; + + irq_percpu_disable(desc, cpu); + irq_put_desc_unlock(desc, flags); +} +EXPORT_SYMBOL_GPL(disable_percpu_irq); + +/* + * Internal function to unregister a percpu irqaction. + */ +static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action; + unsigned long flags; + + WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); + + if (!desc) + return NULL; + + raw_spin_lock_irqsave(&desc->lock, flags); + + action = desc->action; + if (!action || action->percpu_dev_id != dev_id) { + WARN(1, "Trying to free already-free IRQ %d\n", irq); + goto bad; + } + + if (!cpumask_empty(desc->percpu_enabled)) { + WARN(1, "percpu IRQ %d still enabled on CPU%d!\n", + irq, cpumask_first(desc->percpu_enabled)); + goto bad; + } + + /* Found it - now remove it from the list of entries: */ + desc->action = NULL; + + raw_spin_unlock_irqrestore(&desc->lock, flags); + + unregister_handler_proc(irq, action); + + module_put(desc->owner); + return action; + +bad: + raw_spin_unlock_irqrestore(&desc->lock, flags); + return NULL; +} + +/** + * remove_percpu_irq - free a per-cpu interrupt + * @irq: Interrupt line to free + * @act: irqaction for the interrupt + * + * Used to remove interrupts statically setup by the early boot process. + */ +void remove_percpu_irq(unsigned int irq, struct irqaction *act) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc && irq_settings_is_per_cpu_devid(desc)) + __free_percpu_irq(irq, act->percpu_dev_id); +} + +/** + * free_percpu_irq - free an interrupt allocated with request_percpu_irq + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Remove a percpu interrupt handler. The handler is removed, but + * the interrupt line is not disabled. This must be done on each + * CPU before calling this function. The function does not return + * until any executing interrupts for this IRQ have completed. + * + * This function must not be called from interrupt context. + */ +void free_percpu_irq(unsigned int irq, void __percpu *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (!desc || !irq_settings_is_per_cpu_devid(desc)) + return; + + chip_bus_lock(desc); + kfree(__free_percpu_irq(irq, dev_id)); + chip_bus_sync_unlock(desc); +} + +/** + * setup_percpu_irq - setup a per-cpu interrupt + * @irq: Interrupt line to setup + * @act: irqaction for the interrupt + * + * Used to statically setup per-cpu interrupts in the early boot process. + */ +int setup_percpu_irq(unsigned int irq, struct irqaction *act) +{ + struct irq_desc *desc = irq_to_desc(irq); + int retval; + + if (!desc || !irq_settings_is_per_cpu_devid(desc)) + return -EINVAL; + chip_bus_lock(desc); + retval = __setup_irq(irq, desc, act); + chip_bus_sync_unlock(desc); + + return retval; +} + +/** + * request_percpu_irq - allocate a percpu interrupt line + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs. + * @devname: An ascii name for the claiming device + * @dev_id: A percpu cookie passed back to the handler function + * + * This call allocates interrupt resources, but doesn't + * automatically enable the interrupt. It has to be done on each + * CPU using enable_percpu_irq(). + * + * Dev_id must be globally unique. It is a per-cpu variable, and + * the handler gets called with the interrupted CPU's instance of + * that variable. + */ +int request_percpu_irq(unsigned int irq, irq_handler_t handler, + const char *devname, void __percpu *dev_id) +{ + struct irqaction *action; + struct irq_desc *desc; + int retval; + + if (!dev_id) + return -EINVAL; + + desc = irq_to_desc(irq); + if (!desc || !irq_settings_can_request(desc) || + !irq_settings_is_per_cpu_devid(desc)) + return -EINVAL; + + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); + if (!action) + return -ENOMEM; + + action->handler = handler; + action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND; + action->name = devname; + action->percpu_dev_id = dev_id; + + chip_bus_lock(desc); + retval = __setup_irq(irq, desc, action); + chip_bus_sync_unlock(desc); + + if (retval) + kfree(action); + + return retval; +} diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 24196228083..ca3f4aaff70 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -4,27 +4,28 @@ #include "internals.h" -void move_masked_irq(int irq) +void irq_move_masked_irq(struct irq_data *idata) { - struct irq_desc *desc = irq_to_desc(irq); + struct irq_desc *desc = irq_data_to_desc(idata); + struct irq_chip *chip = idata->chip; - if (likely(!(desc->status & IRQ_MOVE_PENDING))) + if (likely(!irqd_is_setaffinity_pending(&desc->irq_data))) return; /* * Paranoia: cpu-local interrupts shouldn't be calling in here anyway. */ - if (CHECK_IRQ_PER_CPU(desc->status)) { + if (!irqd_can_balance(&desc->irq_data)) { WARN_ON(1); return; } - desc->status &= ~IRQ_MOVE_PENDING; + irqd_clr_move_pending(&desc->irq_data); if (unlikely(cpumask_empty(desc->pending_mask))) return; - if (!desc->chip->set_affinity) + if (!chip->irq_set_affinity) return; assert_raw_spin_locked(&desc->lock); @@ -34,35 +35,38 @@ void move_masked_irq(int irq) * do the disable, re-program, enable sequence. * This is *not* particularly important for level triggered * but in a edge trigger case, we might be setting rte - * when an active trigger is comming in. This could + * when an active trigger is coming in. This could * cause some ioapics to mal-function. * Being paranoid i guess! * * For correct operation this depends on the caller * masking the irqs. */ - if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask) - < nr_cpu_ids)) - if (!desc->chip->set_affinity(irq, desc->pending_mask)) { - cpumask_copy(desc->affinity, desc->pending_mask); - irq_set_thread_affinity(desc); - } + if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids) + irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false); cpumask_clear(desc->pending_mask); } -void move_native_irq(int irq) +void irq_move_irq(struct irq_data *idata) { - struct irq_desc *desc = irq_to_desc(irq); + bool masked; - if (likely(!(desc->status & IRQ_MOVE_PENDING))) + if (likely(!irqd_is_setaffinity_pending(idata))) return; - if (unlikely(desc->status & IRQ_DISABLED)) + if (unlikely(irqd_irq_disabled(idata))) return; - desc->chip->mask(irq); - move_masked_irq(irq); - desc->chip->unmask(irq); + /* + * Be careful vs. already masked interrupts. If this is a + * threaded interrupt with ONESHOT set, we can end up with an + * interrupt storm. + */ + masked = irqd_irq_masked(idata); + if (!masked) + idata->chip->irq_mask(idata); + irq_move_masked_irq(idata); + if (!masked) + idata->chip->irq_unmask(idata); } - diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c deleted file mode 100644 index 963559dbd85..00000000000 --- a/kernel/irq/numa_migrate.c +++ /dev/null @@ -1,119 +0,0 @@ -/* - * NUMA irq-desc migration code - * - * Migrate IRQ data structures (irq_desc, chip_data, etc.) over to - * the new "home node" of the IRQ. - */ - -#include <linux/irq.h> -#include <linux/module.h> -#include <linux/random.h> -#include <linux/interrupt.h> -#include <linux/kernel_stat.h> - -#include "internals.h" - -static void init_copy_kstat_irqs(struct irq_desc *old_desc, - struct irq_desc *desc, - int node, int nr) -{ - init_kstat_irqs(desc, node, nr); - - if (desc->kstat_irqs != old_desc->kstat_irqs) - memcpy(desc->kstat_irqs, old_desc->kstat_irqs, - nr * sizeof(*desc->kstat_irqs)); -} - -static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc) -{ - if (old_desc->kstat_irqs == desc->kstat_irqs) - return; - - kfree(old_desc->kstat_irqs); - old_desc->kstat_irqs = NULL; -} - -static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, - struct irq_desc *desc, int node) -{ - memcpy(desc, old_desc, sizeof(struct irq_desc)); - if (!alloc_desc_masks(desc, node, false)) { - printk(KERN_ERR "irq %d: can not get new irq_desc cpumask " - "for migration.\n", irq); - return false; - } - raw_spin_lock_init(&desc->lock); - desc->node = node; - lockdep_set_class(&desc->lock, &irq_desc_lock_class); - init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids); - init_copy_desc_masks(old_desc, desc); - arch_init_copy_chip_data(old_desc, desc, node); - return true; -} - -static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc) -{ - free_kstat_irqs(old_desc, desc); - free_desc_masks(old_desc, desc); - arch_free_chip_data(old_desc, desc); -} - -static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, - int node) -{ - struct irq_desc *desc; - unsigned int irq; - unsigned long flags; - - irq = old_desc->irq; - - raw_spin_lock_irqsave(&sparse_irq_lock, flags); - - /* We have to check it to avoid races with another CPU */ - desc = irq_to_desc(irq); - - if (desc && old_desc != desc) - goto out_unlock; - - desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node); - if (!desc) { - printk(KERN_ERR "irq %d: can not get new irq_desc " - "for migration.\n", irq); - /* still use old one */ - desc = old_desc; - goto out_unlock; - } - if (!init_copy_one_irq_desc(irq, old_desc, desc, node)) { - /* still use old one */ - kfree(desc); - desc = old_desc; - goto out_unlock; - } - - replace_irq_desc(irq, desc); - raw_spin_unlock_irqrestore(&sparse_irq_lock, flags); - - /* free the old one */ - free_one_irq_desc(old_desc, desc); - kfree(old_desc); - - return desc; - -out_unlock: - raw_spin_unlock_irqrestore(&sparse_irq_lock, flags); - - return desc; -} - -struct irq_desc *move_irq_desc(struct irq_desc *desc, int node) -{ - /* those static or target node is -1, do not move them */ - if (desc->irq < NR_IRQS_LEGACY || node == -1) - return desc; - - if (desc->node != node) - desc = __real_move_irq_desc(desc, node); - - return desc; -} - diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index 0d4005d85b0..abcd6ca86cb 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -9,6 +9,7 @@ #include <linux/irq.h> #include <linux/module.h> #include <linux/interrupt.h> +#include <linux/syscore_ops.h> #include "internals.h" @@ -18,7 +19,7 @@ * During system-wide suspend or hibernation device drivers need to be prevented * from receiving interrupts and this function is provided for this purpose. * It marks all interrupt lines in use, except for the timer ones, as disabled - * and sets the IRQ_SUSPENDED flag for each of them. + * and sets the IRQS_SUSPENDED flag for each of them. */ void suspend_device_irqs(void) { @@ -34,26 +35,22 @@ void suspend_device_irqs(void) } for_each_irq_desc(irq, desc) - if (desc->status & IRQ_SUSPENDED) + if (desc->istate & IRQS_SUSPENDED) synchronize_irq(irq); } EXPORT_SYMBOL_GPL(suspend_device_irqs); -/** - * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs() - * - * Enable all interrupt lines previously disabled by suspend_device_irqs() that - * have the IRQ_SUSPENDED flag set. - */ -void resume_device_irqs(void) +static void resume_irqs(bool want_early) { struct irq_desc *desc; int irq; for_each_irq_desc(irq, desc) { unsigned long flags; + bool is_early = desc->action && + desc->action->flags & IRQF_EARLY_RESUME; - if (!(desc->status & IRQ_SUSPENDED)) + if (!is_early && want_early) continue; raw_spin_lock_irqsave(&desc->lock, flags); @@ -61,6 +58,40 @@ void resume_device_irqs(void) raw_spin_unlock_irqrestore(&desc->lock, flags); } } + +/** + * irq_pm_syscore_ops - enable interrupt lines early + * + * Enable all interrupt lines with %IRQF_EARLY_RESUME set. + */ +static void irq_pm_syscore_resume(void) +{ + resume_irqs(true); +} + +static struct syscore_ops irq_pm_syscore_ops = { + .resume = irq_pm_syscore_resume, +}; + +static int __init irq_pm_init_ops(void) +{ + register_syscore_ops(&irq_pm_syscore_ops); + return 0; +} + +device_initcall(irq_pm_init_ops); + +/** + * resume_device_irqs - enable interrupt lines disabled by suspend_device_irqs() + * + * Enable all non-%IRQF_EARLY_RESUME interrupt lines previously + * disabled by suspend_device_irqs() that have the IRQS_SUSPENDED flag + * set as well as those with %IRQF_FORCE_RESUME. + */ +void resume_device_irqs(void) +{ + resume_irqs(false); +} EXPORT_SYMBOL_GPL(resume_device_irqs); /** @@ -71,9 +102,29 @@ int check_wakeup_irqs(void) struct irq_desc *desc; int irq; - for_each_irq_desc(irq, desc) - if ((desc->status & IRQ_WAKEUP) && (desc->status & IRQ_PENDING)) - return -EBUSY; + for_each_irq_desc(irq, desc) { + /* + * Only interrupts which are marked as wakeup source + * and have not been disabled before the suspend check + * can abort suspend. + */ + if (irqd_is_wakeup_set(&desc->irq_data)) { + if (desc->depth == 1 && desc->istate & IRQS_PENDING) + return -EBUSY; + continue; + } + /* + * Check the non wakeup interrupts whether they need + * to be masked before finally going into suspend + * state. That's for hardware which has no wakeup + * source configuration facility. The chip + * implementation indicates that with + * IRQCHIP_MASK_ON_SUSPEND. + */ + if (desc->istate & IRQS_SUSPENDED && + irq_desc_get_chip(desc)->flags & IRQCHIP_MASK_ON_SUSPEND) + mask_irq(desc); + } return 0; } diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 6f50eccc79c..ac1ba2f1103 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -7,9 +7,11 @@ */ #include <linux/irq.h> +#include <linux/gfp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/interrupt.h> +#include <linux/kernel_stat.h> #include "internals.h" @@ -17,17 +19,41 @@ static struct proc_dir_entry *root_irq_dir; #ifdef CONFIG_SMP -static int irq_affinity_proc_show(struct seq_file *m, void *v) +static int show_irq_affinity(int type, struct seq_file *m, void *v) { struct irq_desc *desc = irq_to_desc((long)m->private); - const struct cpumask *mask = desc->affinity; + const struct cpumask *mask = desc->irq_data.affinity; #ifdef CONFIG_GENERIC_PENDING_IRQ - if (desc->status & IRQ_MOVE_PENDING) + if (irqd_is_setaffinity_pending(&desc->irq_data)) mask = desc->pending_mask; #endif + if (type) + seq_cpumask_list(m, mask); + else + seq_cpumask(m, mask); + seq_putc(m, '\n'); + return 0; +} + +static int irq_affinity_hint_proc_show(struct seq_file *m, void *v) +{ + struct irq_desc *desc = irq_to_desc((long)m->private); + unsigned long flags; + cpumask_var_t mask; + + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + raw_spin_lock_irqsave(&desc->lock, flags); + if (desc->affinity_hint) + cpumask_copy(mask, desc->affinity_hint); + raw_spin_unlock_irqrestore(&desc->lock, flags); + seq_cpumask(m, mask); seq_putc(m, '\n'); + free_cpumask_var(mask); + return 0; } @@ -36,21 +62,34 @@ static int irq_affinity_proc_show(struct seq_file *m, void *v) #endif int no_irq_affinity; -static ssize_t irq_affinity_proc_write(struct file *file, +static int irq_affinity_proc_show(struct seq_file *m, void *v) +{ + return show_irq_affinity(0, m, v); +} + +static int irq_affinity_list_proc_show(struct seq_file *m, void *v) +{ + return show_irq_affinity(1, m, v); +} + + +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(file->f_path.dentry->d_inode)->data; + unsigned int irq = (int)(long)PDE_DATA(file_inode(file)); cpumask_var_t new_value; int err; - if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity || - irq_balancing_disabled(irq)) + if (!irq_can_set_affinity(irq) || no_irq_affinity) return -EIO; if (!alloc_cpumask_var(&new_value, GFP_KERNEL)) return -ENOMEM; - err = cpumask_parse_user(buffer, count, new_value); + if (type) + err = cpumask_parselist_user(buffer, count, new_value); + else + err = cpumask_parse_user(buffer, count, new_value); if (err) goto free_cpumask; @@ -67,7 +106,7 @@ static ssize_t irq_affinity_proc_write(struct file *file, if (!cpumask_intersects(new_value, cpu_online_mask)) { /* Special case for empty set - allow the architecture code to set default SMP affinity. */ - err = irq_select_affinity_usr(irq) ? -EINVAL : count; + err = irq_select_affinity_usr(irq, new_value) ? -EINVAL : count; } else { irq_set_affinity(irq, new_value); err = count; @@ -78,9 +117,31 @@ free_cpumask: return err; } +static ssize_t irq_affinity_proc_write(struct file *file, + const char __user *buffer, size_t count, loff_t *pos) +{ + return write_irq_affinity(0, file, buffer, count, pos); +} + +static ssize_t irq_affinity_list_proc_write(struct file *file, + const char __user *buffer, size_t count, loff_t *pos) +{ + return write_irq_affinity(1, file, buffer, count, pos); +} + static int irq_affinity_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_proc_show, PDE(inode)->data); + 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)); +} + +static int irq_affinity_hint_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_affinity_hint_proc_show, PDE_DATA(inode)); } static const struct file_operations irq_affinity_proc_fops = { @@ -91,6 +152,21 @@ static const struct file_operations irq_affinity_proc_fops = { .write = irq_affinity_proc_write, }; +static const struct file_operations irq_affinity_hint_proc_fops = { + .open = irq_affinity_hint_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations irq_affinity_list_proc_fops = { + .open = irq_affinity_list_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = irq_affinity_list_proc_write, +}; + static int default_affinity_show(struct seq_file *m, void *v) { seq_cpumask(m, irq_default_affinity); @@ -136,7 +212,7 @@ out: static int default_affinity_open(struct inode *inode, struct file *file) { - return single_open(file, default_affinity_show, PDE(inode)->data); + return single_open(file, default_affinity_show, PDE_DATA(inode)); } static const struct file_operations default_affinity_proc_fops = { @@ -146,6 +222,26 @@ static const struct file_operations default_affinity_proc_fops = { .release = single_release, .write = default_affinity_write, }; + +static int irq_node_proc_show(struct seq_file *m, void *v) +{ + struct irq_desc *desc = irq_to_desc((long) m->private); + + seq_printf(m, "%d\n", desc->irq_data.node); + return 0; +} + +static int irq_node_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_node_proc_show, PDE_DATA(inode)); +} + +static const struct file_operations irq_node_proc_fops = { + .open = irq_node_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif static int irq_spurious_proc_show(struct seq_file *m, void *v) @@ -160,7 +256,7 @@ static int irq_spurious_proc_show(struct seq_file *m, void *v) static int irq_spurious_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_spurious_proc_show, NULL); + return single_open(file, irq_spurious_proc_show, PDE_DATA(inode)); } static const struct file_operations irq_spurious_proc_fops = { @@ -215,7 +311,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) { char name [MAX_NAMELEN]; - if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir) + if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir) return; memset(name, 0, MAX_NAMELEN); @@ -228,29 +324,55 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) #ifdef CONFIG_SMP /* create /proc/irq/<irq>/smp_affinity */ - proc_create_data("smp_affinity", 0600, desc->dir, + proc_create_data("smp_affinity", 0644, desc->dir, &irq_affinity_proc_fops, (void *)(long)irq); + + /* create /proc/irq/<irq>/affinity_hint */ + proc_create_data("affinity_hint", 0444, desc->dir, + &irq_affinity_hint_proc_fops, (void *)(long)irq); + + /* create /proc/irq/<irq>/smp_affinity_list */ + proc_create_data("smp_affinity_list", 0644, desc->dir, + &irq_affinity_list_proc_fops, (void *)(long)irq); + + proc_create_data("node", 0444, desc->dir, + &irq_node_proc_fops, (void *)(long)irq); #endif proc_create_data("spurious", 0444, desc->dir, &irq_spurious_proc_fops, (void *)(long)irq); } +void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) +{ + char name [MAX_NAMELEN]; + + if (!root_irq_dir || !desc->dir) + return; +#ifdef CONFIG_SMP + remove_proc_entry("smp_affinity", desc->dir); + remove_proc_entry("affinity_hint", desc->dir); + remove_proc_entry("smp_affinity_list", desc->dir); + remove_proc_entry("node", desc->dir); +#endif + remove_proc_entry("spurious", desc->dir); + + memset(name, 0, MAX_NAMELEN); + sprintf(name, "%u", irq); + remove_proc_entry(name, root_irq_dir); +} + #undef MAX_NAMELEN void unregister_handler_proc(unsigned int irq, struct irqaction *action) { - if (action->dir) { - struct irq_desc *desc = irq_to_desc(irq); - - remove_proc_entry(action->dir->name, desc->dir); - } + proc_remove(action->dir); } static void register_default_affinity_proc(void) { #ifdef CONFIG_SMP - proc_create("irq/default_smp_affinity", 0600, NULL, + proc_create("irq/default_smp_affinity", 0644, NULL, &default_affinity_proc_fops); #endif } @@ -278,3 +400,85 @@ void init_irq_proc(void) } } +#ifdef CONFIG_GENERIC_IRQ_SHOW + +int __weak arch_show_interrupts(struct seq_file *p, int prec) +{ + return 0; +} + +#ifndef ACTUAL_NR_IRQS +# define ACTUAL_NR_IRQS nr_irqs +#endif + +int show_interrupts(struct seq_file *p, void *v) +{ + static int prec; + + unsigned long flags, any_count = 0; + int i = *(loff_t *) v, j; + struct irqaction *action; + struct irq_desc *desc; + + if (i > ACTUAL_NR_IRQS) + return 0; + + if (i == ACTUAL_NR_IRQS) + return arch_show_interrupts(p, prec); + + /* print header and calculate the width of the first column */ + if (i == 0) { + for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec) + j *= 10; + + seq_printf(p, "%*s", prec + 8, ""); + for_each_online_cpu(j) + seq_printf(p, "CPU%-8d", j); + seq_putc(p, '\n'); + } + + desc = irq_to_desc(i); + if (!desc) + return 0; + + raw_spin_lock_irqsave(&desc->lock, flags); + for_each_online_cpu(j) + any_count |= kstat_irqs_cpu(i, j); + action = desc->action; + if (!action && !any_count) + goto out; + + seq_printf(p, "%*d: ", prec, i); + for_each_online_cpu(j) + seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); + + if (desc->irq_data.chip) { + if (desc->irq_data.chip->irq_print_chip) + desc->irq_data.chip->irq_print_chip(&desc->irq_data, p); + else if (desc->irq_data.chip->name) + seq_printf(p, " %8s", desc->irq_data.chip->name); + else + seq_printf(p, " %8s", "-"); + } else { + seq_printf(p, " %8s", "None"); + } + if (desc->irq_data.domain) + seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq); +#ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL + seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge"); +#endif + if (desc->name) + seq_printf(p, "-%-8s", desc->name); + + if (action) { + seq_printf(p, " %s", action->name); + while ((action = action->next) != NULL) + seq_printf(p, ", %s", action->name); + } + + seq_putc(p, '\n'); +out: + raw_spin_unlock_irqrestore(&desc->lock, flags); + return 0; +} +#endif diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index 090c3763f3a..9065107f083 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -23,7 +23,7 @@ #ifdef CONFIG_HARDIRQS_SW_RESEND /* Bitmap to handle software resend of interrupts: */ -static DECLARE_BITMAP(irqs_resend, NR_IRQS); +static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS); /* * Run software resends of IRQ's @@ -55,23 +55,33 @@ static DECLARE_TASKLET(resend_tasklet, resend_irqs, 0); */ void check_irq_resend(struct irq_desc *desc, unsigned int irq) { - unsigned int status = desc->status; - - /* - * Make sure the interrupt is enabled, before resending it: - */ - desc->chip->enable(irq); - /* * We do not resend level type interrupts. Level type * interrupts are resent by hardware when they are still - * active. + * active. Clear the pending bit so suspend/resume does not + * get confused. */ - if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) { - desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY; + if (irq_settings_is_level(desc)) { + desc->istate &= ~IRQS_PENDING; + return; + } + if (desc->istate & IRQS_REPLAY) + return; + if (desc->istate & IRQS_PENDING) { + desc->istate &= ~IRQS_PENDING; + desc->istate |= IRQS_REPLAY; - if (!desc->chip->retrigger || !desc->chip->retrigger(irq)) { + if (!desc->irq_data.chip->irq_retrigger || + !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) { #ifdef CONFIG_HARDIRQS_SW_RESEND + /* + * If the interrupt has a parent irq and runs + * in the thread context of the parent irq, + * retrigger the parent. + */ + if (desc->parent_irq && + irq_settings_is_nested_thread(desc)) + irq = desc->parent_irq; /* Set it pending and activate the softirq: */ set_bit(irq, irqs_resend); tasklet_schedule(&resend_tasklet); diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h new file mode 100644 index 00000000000..3320b84cc60 --- /dev/null +++ b/kernel/irq/settings.h @@ -0,0 +1,156 @@ +/* + * Internal header to deal with irq_desc->status which will be renamed + * to irq_desc->settings. + */ +enum { + _IRQ_DEFAULT_INIT_FLAGS = IRQ_DEFAULT_INIT_FLAGS, + _IRQ_PER_CPU = IRQ_PER_CPU, + _IRQ_LEVEL = IRQ_LEVEL, + _IRQ_NOPROBE = IRQ_NOPROBE, + _IRQ_NOREQUEST = IRQ_NOREQUEST, + _IRQ_NOTHREAD = IRQ_NOTHREAD, + _IRQ_NOAUTOEN = IRQ_NOAUTOEN, + _IRQ_MOVE_PCNTXT = IRQ_MOVE_PCNTXT, + _IRQ_NO_BALANCING = IRQ_NO_BALANCING, + _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, + _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_IS_POLLED = IRQ_IS_POLLED, + _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, +}; + +#define IRQ_PER_CPU GOT_YOU_MORON +#define IRQ_NO_BALANCING GOT_YOU_MORON +#define IRQ_LEVEL GOT_YOU_MORON +#define IRQ_NOPROBE GOT_YOU_MORON +#define IRQ_NOREQUEST GOT_YOU_MORON +#define IRQ_NOTHREAD GOT_YOU_MORON +#define IRQ_NOAUTOEN GOT_YOU_MORON +#define IRQ_NESTED_THREAD GOT_YOU_MORON +#define IRQ_PER_CPU_DEVID GOT_YOU_MORON +#define IRQ_IS_POLLED GOT_YOU_MORON +#undef IRQF_MODIFY_MASK +#define IRQF_MODIFY_MASK GOT_YOU_MORON + +static inline void +irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) +{ + desc->status_use_accessors &= ~(clr & _IRQF_MODIFY_MASK); + desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); +} + +static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_PER_CPU; +} + +static inline bool irq_settings_is_per_cpu_devid(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_PER_CPU_DEVID; +} + +static inline void irq_settings_set_per_cpu(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_PER_CPU; +} + +static inline void irq_settings_set_no_balancing(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NO_BALANCING; +} + +static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NO_BALANCING; +} + +static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc) +{ + return desc->status_use_accessors & IRQ_TYPE_SENSE_MASK; +} + +static inline void +irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask) +{ + desc->status_use_accessors &= ~IRQ_TYPE_SENSE_MASK; + desc->status_use_accessors |= mask & IRQ_TYPE_SENSE_MASK; +} + +static inline bool irq_settings_is_level(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_LEVEL; +} + +static inline void irq_settings_clr_level(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_LEVEL; +} + +static inline void irq_settings_set_level(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_LEVEL; +} + +static inline bool irq_settings_can_request(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOREQUEST); +} + +static inline void irq_settings_clr_norequest(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_NOREQUEST; +} + +static inline void irq_settings_set_norequest(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NOREQUEST; +} + +static inline bool irq_settings_can_thread(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOTHREAD); +} + +static inline void irq_settings_clr_nothread(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_NOTHREAD; +} + +static inline void irq_settings_set_nothread(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NOTHREAD; +} + +static inline bool irq_settings_can_probe(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOPROBE); +} + +static inline void irq_settings_clr_noprobe(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_NOPROBE; +} + +static inline void irq_settings_set_noprobe(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NOPROBE; +} + +static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_MOVE_PCNTXT; +} + +static inline bool irq_settings_can_autoenable(struct irq_desc *desc) +{ + return !(desc->status_use_accessors & _IRQ_NOAUTOEN); +} + +static inline bool irq_settings_is_nested_thread(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NESTED_THREAD; +} + +static inline bool irq_settings_is_polled(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_IS_POLLED; +} diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 89fb90ae534..e2514b0e439 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -14,75 +14,106 @@ #include <linux/moduleparam.h> #include <linux/timer.h> +#include "internals.h" + static int irqfixup __read_mostly; #define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10) static void poll_spurious_irqs(unsigned long dummy); static DEFINE_TIMER(poll_spurious_irq_timer, poll_spurious_irqs, 0, 0); +static int irq_poll_cpu; +static atomic_t irq_poll_active; + +/* + * We wait here for a poller to finish. + * + * If the poll runs on this CPU, then we yell loudly and return + * false. That will leave the interrupt line disabled in the worst + * case, but it should never happen. + * + * We wait until the poller is done and then recheck disabled and + * action (about to be disabled). Only if it's still active, we return + * true and let the handler run. + */ +bool irq_wait_for_poll(struct irq_desc *desc) +{ + if (WARN_ONCE(irq_poll_cpu == smp_processor_id(), + "irq poll in progress on cpu %d for irq %d\n", + smp_processor_id(), desc->irq_data.irq)) + return false; + +#ifdef CONFIG_SMP + do { + raw_spin_unlock(&desc->lock); + while (irqd_irq_inprogress(&desc->irq_data)) + cpu_relax(); + raw_spin_lock(&desc->lock); + } while (irqd_irq_inprogress(&desc->irq_data)); + /* Might have been disabled in meantime */ + return !irqd_irq_disabled(&desc->irq_data) && desc->action; +#else + return false; +#endif +} + /* * Recovery handler for misrouted interrupts. */ -static int try_one_irq(int irq, struct irq_desc *desc) +static int try_one_irq(int irq, struct irq_desc *desc, bool force) { + irqreturn_t ret = IRQ_NONE; struct irqaction *action; - int ok = 0, work = 0; raw_spin_lock(&desc->lock); - /* Already running on another processor */ - if (desc->status & IRQ_INPROGRESS) { - /* - * Already running: If it is shared get the other - * CPU to go looking for our mystery interrupt too - */ - if (desc->action && (desc->action->flags & IRQF_SHARED)) - desc->status |= IRQ_PENDING; - raw_spin_unlock(&desc->lock); - return ok; - } - /* Honour the normal IRQ locking */ - desc->status |= IRQ_INPROGRESS; - action = desc->action; - raw_spin_unlock(&desc->lock); - while (action) { - /* Only shared IRQ handlers are safe to call */ - if (action->flags & IRQF_SHARED) { - if (action->handler(irq, action->dev_id) == - IRQ_HANDLED) - ok = 1; - } - action = action->next; - } - local_irq_disable(); - /* Now clean up the flags */ - raw_spin_lock(&desc->lock); - action = desc->action; + /* + * PER_CPU, nested thread interrupts and interrupts explicitely + * marked polled are excluded from polling. + */ + if (irq_settings_is_per_cpu(desc) || + irq_settings_is_nested_thread(desc) || + irq_settings_is_polled(desc)) + goto out; + + /* + * Do not poll disabled interrupts unless the spurious + * disabled poller asks explicitely. + */ + if (irqd_irq_disabled(&desc->irq_data) && !force) + goto out; /* - * While we were looking for a fixup someone queued a real - * IRQ clashing with our walk: + * All handlers must agree on IRQF_SHARED, so we test just the + * first. */ - while ((desc->status & IRQ_PENDING) && action) { + action = desc->action; + if (!action || !(action->flags & IRQF_SHARED) || + (action->flags & __IRQF_TIMER)) + goto out; + + /* Already running on another processor */ + if (irqd_irq_inprogress(&desc->irq_data)) { /* - * Perform real IRQ processing for the IRQ we deferred + * Already running: If it is shared get the other + * CPU to go looking for our mystery interrupt too */ - work = 1; - raw_spin_unlock(&desc->lock); - handle_IRQ_event(irq, action); - raw_spin_lock(&desc->lock); - desc->status &= ~IRQ_PENDING; + desc->istate |= IRQS_PENDING; + goto out; } - desc->status &= ~IRQ_INPROGRESS; - /* - * If we did actual work for the real IRQ line we must let the - * IRQ controller clean up too - */ - if (work && desc->chip && desc->chip->end) - desc->chip->end(irq); - raw_spin_unlock(&desc->lock); - return ok; + /* Mark it poll in progress */ + desc->istate |= IRQS_POLL_INPROGRESS; + do { + if (handle_irq_event(desc) == IRQ_HANDLED) + ret = IRQ_HANDLED; + /* Make sure that there is still a valid action */ + action = desc->action; + } while ((desc->istate & IRQS_PENDING) && action); + desc->istate &= ~IRQS_POLL_INPROGRESS; +out: + raw_spin_unlock(&desc->lock); + return ret == IRQ_HANDLED; } static int misrouted_irq(int irq) @@ -90,6 +121,11 @@ static int misrouted_irq(int irq) struct irq_desc *desc; int i, ok = 0; + if (atomic_inc_return(&irq_poll_active) != 1) + goto out; + + irq_poll_cpu = smp_processor_id(); + for_each_irq_desc(i, desc) { if (!i) continue; @@ -97,9 +133,11 @@ static int misrouted_irq(int irq) if (i == irq) /* Already tried */ continue; - if (try_one_irq(i, desc)) + if (try_one_irq(i, desc, false)) ok = 1; } +out: + atomic_dec(&irq_poll_active); /* So the caller can adjust the irq error counts */ return ok; } @@ -109,27 +147,39 @@ static void poll_spurious_irqs(unsigned long dummy) struct irq_desc *desc; int i; + if (atomic_inc_return(&irq_poll_active) != 1) + goto out; + irq_poll_cpu = smp_processor_id(); + for_each_irq_desc(i, desc) { - unsigned int status; + unsigned int state; if (!i) continue; /* Racy but it doesn't matter */ - status = desc->status; + state = desc->istate; barrier(); - if (!(status & IRQ_SPURIOUS_DISABLED)) + if (!(state & IRQS_SPURIOUS_DISABLED)) continue; local_irq_disable(); - try_one_irq(i, desc); + try_one_irq(i, desc, true); local_irq_enable(); } - +out: + atomic_dec(&irq_poll_active); mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); } +static inline int bad_action_ret(irqreturn_t action_ret) +{ + if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD))) + return 0; + return 1; +} + /* * If 99,900 of the previous 100,000 interrupts have not been handled * then assume that the IRQ is stuck in some manner. Drop a diagnostic @@ -137,17 +187,15 @@ static void poll_spurious_irqs(unsigned long dummy) * * (The other 100-of-100,000 interrupts may have been a correctly * functioning device sharing an IRQ with the failing one) - * - * Called under desc->lock */ - static void __report_bad_irq(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret) { struct irqaction *action; + unsigned long flags; - if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) { + if (bad_action_ret(action_ret)) { printk(KERN_ERR "irq event %d: bogus return value %x\n", irq, action_ret); } else { @@ -157,14 +205,23 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc, dump_stack(); printk(KERN_ERR "handlers:\n"); + /* + * We need to take desc->lock here. note_interrupt() is called + * w/o desc->lock held, but IRQ_PROGRESS set. We might race + * with something else removing an action. It's ok to take + * desc->lock here. See synchronize_irq(). + */ + raw_spin_lock_irqsave(&desc->lock, flags); action = desc->action; while (action) { - printk(KERN_ERR "[<%p>]", action->handler); - print_symbol(" (%s)", - (unsigned long)action->handler); - printk("\n"); + printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler); + if (action->thread_fn) + printk(KERN_CONT " threaded [<%p>] %pf", + action->thread_fn, action->thread_fn); + printk(KERN_CONT "\n"); action = action->next; } + raw_spin_unlock_irqrestore(&desc->lock, flags); } static void @@ -213,10 +270,121 @@ try_misrouted_irq(unsigned int irq, struct irq_desc *desc, return action && (action->flags & IRQF_IRQPOLL); } +#define SPURIOUS_DEFERRED 0x80000000 + void note_interrupt(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret) { - if (unlikely(action_ret != IRQ_HANDLED)) { + if (desc->istate & IRQS_POLL_INPROGRESS || + irq_settings_is_polled(desc)) + return; + + if (bad_action_ret(action_ret)) { + report_bad_irq(irq, desc, action_ret); + return; + } + + /* + * We cannot call note_interrupt from the threaded handler + * because we need to look at the compound of all handlers + * (primary and threaded). Aside of that in the threaded + * shared case we have no serialization against an incoming + * hardware interrupt while we are dealing with a threaded + * result. + * + * So in case a thread is woken, we just note the fact and + * defer the analysis to the next hardware interrupt. + * + * The threaded handlers store whether they sucessfully + * handled an interrupt and we check whether that number + * changed versus the last invocation. + * + * We could handle all interrupts with the delayed by one + * mechanism, but for the non forced threaded case we'd just + * add pointless overhead to the straight hardirq interrupts + * for the sake of a few lines less code. + */ + if (action_ret & IRQ_WAKE_THREAD) { + /* + * There is a thread woken. Check whether one of the + * shared primary handlers returned IRQ_HANDLED. If + * not we defer the spurious detection to the next + * interrupt. + */ + if (action_ret == IRQ_WAKE_THREAD) { + int handled; + /* + * We use bit 31 of thread_handled_last to + * denote the deferred spurious detection + * active. No locking necessary as + * thread_handled_last is only accessed here + * and we have the guarantee that hard + * interrupts are not reentrant. + */ + if (!(desc->threads_handled_last & SPURIOUS_DEFERRED)) { + desc->threads_handled_last |= SPURIOUS_DEFERRED; + return; + } + /* + * Check whether one of the threaded handlers + * returned IRQ_HANDLED since the last + * interrupt happened. + * + * For simplicity we just set bit 31, as it is + * set in threads_handled_last as well. So we + * avoid extra masking. And we really do not + * care about the high bits of the handled + * count. We just care about the count being + * different than the one we saw before. + */ + handled = atomic_read(&desc->threads_handled); + handled |= SPURIOUS_DEFERRED; + if (handled != desc->threads_handled_last) { + action_ret = IRQ_HANDLED; + /* + * Note: We keep the SPURIOUS_DEFERRED + * bit set. We are handling the + * previous invocation right now. + * Keep it for the current one, so the + * next hardware interrupt will + * account for it. + */ + desc->threads_handled_last = handled; + } else { + /* + * None of the threaded handlers felt + * responsible for the last interrupt + * + * We keep the SPURIOUS_DEFERRED bit + * set in threads_handled_last as we + * need to account for the current + * interrupt as well. + */ + action_ret = IRQ_NONE; + } + } else { + /* + * One of the primary handlers returned + * IRQ_HANDLED. So we don't care about the + * threaded handlers on the same line. Clear + * the deferred detection bit. + * + * In theory we could/should check whether the + * deferred bit is set and take the result of + * the previous run into account here as + * well. But it's really not worth the + * trouble. If every other interrupt is + * handled we never trigger the spurious + * detector. And if this is just the one out + * of 100k unhandled ones which is handled + * then we merily delay the spurious detection + * by one hard interrupt. Not a real problem. + */ + desc->threads_handled_last &= ~SPURIOUS_DEFERRED; + } + } + + if (unlikely(action_ret == IRQ_NONE)) { /* * If we are seeing only the odd spurious IRQ caused by * bus asynchronicity then don't eventually trigger an error, @@ -228,8 +396,6 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, else desc->irqs_unhandled++; desc->last_unhandled = jiffies; - if (unlikely(action_ret != IRQ_NONE)) - report_bad_irq(irq, desc, action_ret); } if (unlikely(try_misrouted_irq(irq, desc, action_ret))) { @@ -252,9 +418,9 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, * Now kill the IRQ */ printk(KERN_EMERG "Disabling IRQ #%d\n", irq); - desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED; + desc->istate |= IRQS_SPURIOUS_DISABLED; desc->depth++; - desc->chip->disable(irq); + irq_disable(desc); mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); @@ -262,7 +428,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc, desc->irqs_unhandled = 0; } -int noirqdebug __read_mostly; +bool noirqdebug __read_mostly; int noirqdebug_setup(char *str) { |