From 201d7f47f34bd7cb19161d0426f13b141e381f30 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 31 May 2017 11:58:32 +0200 Subject: genirq: Handle NOAUTOEN interrupt setup proper If an interrupt is marked NOAUTOEN then request_irq() installs the action, but does not enable the interrupt via startup_irq(). The interrupt is enabled via enable_irq() later from the driver. enable_irq() calls irq_enable(). That means that for interrupts which have a irq_startup() callback this callback is never invoked. Neither is irq_domain_activate_irq() invoked for such interrupts. If an interrupt depends on irq_startup() or irq_domain_activate_irq() then the enable via irq_enable() is not enough. Add a status flag IRQD_IRQ_STARTED_UP and use this to select the proper mechanism in enable_irq(). Use the flag also to avoid pointless calls into the low level functions. Signed-off-by: Thomas Gleixner Acked-by: Marc Zyngier Cc: dianders@chromium.org Cc: jeffy Cc: Brian Norris Cc: tfiga@chromium.org Link: http://lkml.kernel.org/r/20170531100212.130986205@linutronix.de --- kernel/irq/manage.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 070be980c37a..57056109f176 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -533,9 +533,15 @@ void __enable_irq(struct irq_desc *desc) goto err_out; /* Prevent probing on this irq: */ irq_settings_set_noprobe(desc); - irq_enable(desc); - check_irq_resend(desc); - /* fall-through */ + /* + * Call irq_startup() not irq_enable() here because the + * interrupt might be marked NOAUTOEN. So irq_startup() + * needs to be invoked when it gets enabled the first + * time. If it was already started up, then irq_startup() + * will invoke irq_enable() under the hood. + */ + irq_startup(desc, true); + break; } default: desc->depth--; -- cgit v1.2.3 From 04c848d398797a626608ff48804d809ae6687163 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 31 May 2017 11:58:33 +0200 Subject: genirq: Warn when IRQ_NOAUTOEN is used with shared interrupts Shared interrupts do not go well with disabling auto enable: 1) The sharing interrupt might request it while it's still disabled and then wait for interrupts forever. 2) The interrupt might have been requested by the driver sharing the line before IRQ_NOAUTOEN has been set. So the driver which expects that disabled state after calling request_irq() will not get what it wants. Even worse, when it calls enable_irq() later, it will trigger the unbalanced enable_irq() warning. Reported-by: Brian Norris Signed-off-by: Thomas Gleixner Cc: dianders@chromium.org Cc: jeffy Cc: Marc Zyngier Cc: tfiga@chromium.org Link: http://lkml.kernel.org/r/20170531100212.210682135@linutronix.de --- kernel/irq/chip.c | 7 +++++++ kernel/irq/manage.c | 12 ++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index e0051d58c909..bc1331f84fb5 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -935,6 +935,13 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) if (!desc) return; + + /* + * Warn when a driver sets the no autoenable flag on an already + * active interrupt. + */ + WARN_ON_ONCE(!desc->depth && (set & _IRQ_NOAUTOEN)); + irq_settings_clr_and_set(desc, clr, set); irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 57056109f176..49c37f1e71c0 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1334,11 +1334,19 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (new->flags & IRQF_ONESHOT) desc->istate |= IRQS_ONESHOT; - if (irq_settings_can_autoenable(desc)) + if (irq_settings_can_autoenable(desc)) { irq_startup(desc, true); - else + } else { + /* + * Shared interrupts do not go well with disabling + * auto enable. The sharing interrupt might request + * it while it's still disabled and then wait for + * interrupts forever. + */ + WARN_ON_ONCE(new->flags & IRQF_SHARED); /* Undo nested disables: */ desc->depth = 1; + } /* Exclude IRQ from balancing if requested */ if (new->flags & IRQF_NOBALANCING) { -- cgit v1.2.3 From 087cdfb662ae50e3826e7cd2e54b6519d07b60f0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jun 2017 01:37:17 +0200 Subject: genirq/debugfs: Add proper debugfs interface Debugging (hierarchical) interupt domains is tedious as there is no information about the hierarchy and no information about states of interrupts in the various domain levels. Add a debugfs directory 'irq' and subdirectories 'domains' and 'irqs'. The domains directory contains the domain files. The content is information about the domain. If the domain is part of a hierarchy then the parent domains are printed as well. # ls /sys/kernel/debug/irq/domains/ default INTEL-IR-2 INTEL-IR-MSI-2 IO-APIC-IR-2 PCI-MSI DMAR-MSI INTEL-IR-3 INTEL-IR-MSI-3 IO-APIC-IR-3 unknown-1 INTEL-IR-0 INTEL-IR-MSI-0 IO-APIC-IR-0 IO-APIC-IR-4 VECTOR INTEL-IR-1 INTEL-IR-MSI-1 IO-APIC-IR-1 PCI-HT # cat /sys/kernel/debug/irq/domains/VECTOR name: VECTOR size: 0 mapped: 216 flags: 0x00000041 # cat /sys/kernel/debug/irq/domains/IO-APIC-IR-0 name: IO-APIC-IR-0 size: 24 mapped: 19 flags: 0x00000041 parent: INTEL-IR-3 name: INTEL-IR-3 size: 65536 mapped: 167 flags: 0x00000041 parent: VECTOR name: VECTOR size: 0 mapped: 216 flags: 0x00000041 Unfortunately there is no per cpu information about the VECTOR domain (yet). The irqs directory contains detailed information about mapped interrupts. # cat /sys/kernel/debug/irq/irqs/3 handler: handle_edge_irq status: 0x00004000 istate: 0x00000000 ddepth: 1 wdepth: 0 dstate: 0x01018000 IRQD_IRQ_DISABLED IRQD_SINGLE_TARGET IRQD_MOVE_PCNTXT node: 0 affinity: 0-143 effectiv: 0 pending: domain: IO-APIC-IR-0 hwirq: 0x3 chip: IR-IO-APIC flags: 0x10 IRQCHIP_SKIP_SET_WAKE parent: domain: INTEL-IR-3 hwirq: 0x20000 chip: INTEL-IR flags: 0x0 parent: domain: VECTOR hwirq: 0x3 chip: APIC flags: 0x0 This was developed to simplify the debugging of the managed affinity changes. Signed-off-by: Thomas Gleixner Acked-by: Marc Zyngier Cc: Jens Axboe Cc: Michael Ellerman Cc: Keith Busch Cc: Peter Zijlstra Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20170619235444.537566163@linutronix.de Signed-off-by: Thomas Gleixner --- include/linux/irqdesc.h | 4 + include/linux/irqdomain.h | 4 + kernel/irq/Kconfig | 11 +++ kernel/irq/Makefile | 1 + kernel/irq/debugfs.c | 215 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/irq/internals.h | 22 +++++ kernel/irq/irqdesc.c | 1 + kernel/irq/irqdomain.c | 87 ++++++++++++++++++- kernel/irq/manage.c | 1 + 9 files changed, 345 insertions(+), 1 deletion(-) create mode 100644 kernel/irq/debugfs.c (limited to 'kernel/irq/manage.c') diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c9be57931b58..d425a3a09722 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -46,6 +46,7 @@ struct pt_regs; * @rcu: rcu head for delayed free * @kobj: kobject used to represent this struct in sysfs * @dir: /proc/irq/ procfs entry + * @debugfs_file: dentry for the debugfs file * @name: flow handler name for /proc/interrupts output */ struct irq_desc { @@ -88,6 +89,9 @@ struct irq_desc { #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; #endif +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + struct dentry *debugfs_file; +#endif #ifdef CONFIG_SPARSE_IRQ struct rcu_head rcu; struct kobject kobj; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 17ccd54d936d..914b0c31d233 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -139,6 +139,7 @@ struct irq_domain_chip_generic; * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains + * @debugfs_file: dentry for the domain debugfs file * * Revmap data, used internally by irq_domain * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that @@ -162,6 +163,9 @@ struct irq_domain { #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_domain *parent; #endif +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS + struct dentry *debugfs_file; +#endif /* reverse map data. The linear map gets appended to the irq_domain */ irq_hw_number_t hwirq_max; diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 3bbfd6a9c475..8d9498e51585 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -108,4 +108,15 @@ config SPARSE_IRQ If you don't know what to do here, say N. +config GENERIC_IRQ_DEBUGFS + bool "Expose irq internals in debugfs" + depends on DEBUG_FS + default n + ---help--- + + Exposes internal state information through debugfs. Mostly for + developers and debugging of hard to diagnose interrupt problems. + + If you don't know what to do here, say N. + endmenu diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 1d3ee3169202..c61fc9c2d1f7 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -10,3 +10,4 @@ obj-$(CONFIG_PM_SLEEP) += pm.o obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o obj-$(CONFIG_SMP) += affinity.o +obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c new file mode 100644 index 000000000000..50ee2f6593e8 --- /dev/null +++ b/kernel/irq/debugfs.c @@ -0,0 +1,215 @@ +/* + * Copyright 2017 Thomas Gleixner + * + * This file is licensed under the GPL V2. + */ +#include +#include +#include + +#include "internals.h" + +static struct dentry *irq_dir; + +struct irq_bit_descr { + unsigned int mask; + char *name; +}; +#define BIT_MASK_DESCR(m) { .mask = m, .name = #m } + +static void irq_debug_show_bits(struct seq_file *m, int ind, unsigned int state, + const struct irq_bit_descr *sd, int size) +{ + int i; + + for (i = 0; i < size; i++, sd++) { + if (state & sd->mask) + seq_printf(m, "%*s%s\n", ind + 12, "", sd->name); + } +} + +#ifdef CONFIG_SMP +static void irq_debug_show_masks(struct seq_file *m, struct irq_desc *desc) +{ + struct irq_data *data = irq_desc_get_irq_data(desc); + struct cpumask *msk; + + msk = irq_data_get_affinity_mask(data); + seq_printf(m, "affinity: %*pbl\n", cpumask_pr_args(msk)); +#ifdef CONFIG_GENERIC_PENDING_IRQ + msk = desc->pending_mask; + seq_printf(m, "pending: %*pbl\n", cpumask_pr_args(msk)); +#endif +} +#else +static void irq_debug_show_masks(struct seq_file *m, struct irq_desc *desc) { } +#endif + +static const struct irq_bit_descr irqchip_flags[] = { + BIT_MASK_DESCR(IRQCHIP_SET_TYPE_MASKED), + BIT_MASK_DESCR(IRQCHIP_EOI_IF_HANDLED), + BIT_MASK_DESCR(IRQCHIP_MASK_ON_SUSPEND), + BIT_MASK_DESCR(IRQCHIP_ONOFFLINE_ENABLED), + BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE), + BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE), + BIT_MASK_DESCR(IRQCHIP_EOI_THREADED), +}; + +static void +irq_debug_show_chip(struct seq_file *m, struct irq_data *data, int ind) +{ + struct irq_chip *chip = data->chip; + + if (!chip) { + seq_printf(m, "chip: None\n"); + return; + } + seq_printf(m, "%*schip: %s\n", ind, "", chip->name); + seq_printf(m, "%*sflags: 0x%lx\n", ind + 1, "", chip->flags); + irq_debug_show_bits(m, ind, chip->flags, irqchip_flags, + ARRAY_SIZE(irqchip_flags)); +} + +static void +irq_debug_show_data(struct seq_file *m, struct irq_data *data, int ind) +{ + seq_printf(m, "%*sdomain: %s\n", ind, "", + data->domain ? data->domain->name : ""); + seq_printf(m, "%*shwirq: 0x%lx\n", ind + 1, "", data->hwirq); + irq_debug_show_chip(m, data, ind + 1); +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + if (!data->parent_data) + return; + seq_printf(m, "%*sparent:\n", ind + 1, ""); + irq_debug_show_data(m, data->parent_data, ind + 4); +#endif +} + +static const struct irq_bit_descr irqdata_states[] = { + BIT_MASK_DESCR(IRQ_TYPE_EDGE_RISING), + BIT_MASK_DESCR(IRQ_TYPE_EDGE_FALLING), + BIT_MASK_DESCR(IRQ_TYPE_LEVEL_HIGH), + BIT_MASK_DESCR(IRQ_TYPE_LEVEL_LOW), + BIT_MASK_DESCR(IRQD_LEVEL), + + BIT_MASK_DESCR(IRQD_ACTIVATED), + BIT_MASK_DESCR(IRQD_IRQ_STARTED), + BIT_MASK_DESCR(IRQD_IRQ_DISABLED), + BIT_MASK_DESCR(IRQD_IRQ_MASKED), + BIT_MASK_DESCR(IRQD_IRQ_INPROGRESS), + + BIT_MASK_DESCR(IRQD_PER_CPU), + BIT_MASK_DESCR(IRQD_NO_BALANCING), + + BIT_MASK_DESCR(IRQD_MOVE_PCNTXT), + BIT_MASK_DESCR(IRQD_AFFINITY_SET), + BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING), + BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED), + BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN), + + BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU), + + BIT_MASK_DESCR(IRQD_WAKEUP_STATE), + BIT_MASK_DESCR(IRQD_WAKEUP_ARMED), +}; + +static const struct irq_bit_descr irqdesc_states[] = { + BIT_MASK_DESCR(_IRQ_NOPROBE), + BIT_MASK_DESCR(_IRQ_NOREQUEST), + BIT_MASK_DESCR(_IRQ_NOTHREAD), + BIT_MASK_DESCR(_IRQ_NOAUTOEN), + BIT_MASK_DESCR(_IRQ_NESTED_THREAD), + BIT_MASK_DESCR(_IRQ_PER_CPU_DEVID), + BIT_MASK_DESCR(_IRQ_IS_POLLED), + BIT_MASK_DESCR(_IRQ_DISABLE_UNLAZY), +}; + +static const struct irq_bit_descr irqdesc_istates[] = { + BIT_MASK_DESCR(IRQS_AUTODETECT), + BIT_MASK_DESCR(IRQS_SPURIOUS_DISABLED), + BIT_MASK_DESCR(IRQS_POLL_INPROGRESS), + BIT_MASK_DESCR(IRQS_ONESHOT), + BIT_MASK_DESCR(IRQS_REPLAY), + BIT_MASK_DESCR(IRQS_WAITING), + BIT_MASK_DESCR(IRQS_PENDING), + BIT_MASK_DESCR(IRQS_SUSPENDED), +}; + + +static int irq_debug_show(struct seq_file *m, void *p) +{ + struct irq_desc *desc = m->private; + struct irq_data *data; + + raw_spin_lock_irq(&desc->lock); + data = irq_desc_get_irq_data(desc); + seq_printf(m, "handler: %pf\n", desc->handle_irq); + seq_printf(m, "status: 0x%08x\n", desc->status_use_accessors); + irq_debug_show_bits(m, 0, desc->status_use_accessors, irqdesc_states, + ARRAY_SIZE(irqdesc_states)); + seq_printf(m, "istate: 0x%08x\n", desc->istate); + irq_debug_show_bits(m, 0, desc->istate, irqdesc_istates, + ARRAY_SIZE(irqdesc_istates)); + seq_printf(m, "ddepth: %u\n", desc->depth); + seq_printf(m, "wdepth: %u\n", desc->wake_depth); + seq_printf(m, "dstate: 0x%08x\n", irqd_get(data)); + irq_debug_show_bits(m, 0, irqd_get(data), irqdata_states, + ARRAY_SIZE(irqdata_states)); + seq_printf(m, "node: %d\n", irq_data_get_node(data)); + irq_debug_show_masks(m, desc); + irq_debug_show_data(m, data, 0); + raw_spin_unlock_irq(&desc->lock); + return 0; +} + +static int irq_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_debug_show, inode->i_private); +} + +static const struct file_operations dfs_irq_ops = { + .open = irq_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc) +{ + char name [10]; + + if (!irq_dir || !desc || desc->debugfs_file) + return; + + sprintf(name, "%d", irq); + desc->debugfs_file = debugfs_create_file(name, 0444, irq_dir, desc, + &dfs_irq_ops); +} + +void irq_remove_debugfs_entry(struct irq_desc *desc) +{ + if (desc->debugfs_file) + debugfs_remove(desc->debugfs_file); +} + +static int __init irq_debugfs_init(void) +{ + struct dentry *root_dir; + int irq; + + root_dir = debugfs_create_dir("irq", NULL); + if (!root_dir) + return -ENOMEM; + + irq_domain_debugfs_init(root_dir); + + irq_dir = debugfs_create_dir("irqs", root_dir); + + irq_lock_sparse(); + for_each_active_irq(irq) + irq_add_debugfs_entry(irq, irq_to_desc(irq)); + irq_unlock_sparse(); + + return 0; +} +__initcall(irq_debugfs_init); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 921a2419720c..094db5bfb83f 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -169,6 +169,11 @@ irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags) #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) +static inline unsigned int irqd_get(struct irq_data *d) +{ + return __irqd_to_state(d); +} + /* * Manipulation functions for irq_data.state */ @@ -237,3 +242,20 @@ 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) { } #endif /* CONFIG_GENERIC_IRQ_CHIP */ + +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); +void irq_remove_debugfs_entry(struct irq_desc *desc); +# ifdef CONFIG_IRQ_DOMAIN +void irq_domain_debugfs_init(struct dentry *root); +# else +static inline void irq_domain_debugfs_init(struct dentry *root); +# endif +#else /* CONFIG_GENERIC_IRQ_DEBUGFS */ +static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) +{ +} +static inline void irq_remove_debugfs_entry(struct irq_desc *d) +{ +} +#endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 09abce2ea8f0..feade536b6d1 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -394,6 +394,7 @@ static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); + irq_remove_debugfs_entry(desc); unregister_irq_proc(irq, desc); /* diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8d5805c655b6..75e1f0851c33 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -29,9 +29,17 @@ struct irqchip_fwid { struct fwnode_handle fwnode; unsigned int type; char *name; - void *data; + void *data; }; +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +static void debugfs_add_domain_dir(struct irq_domain *d); +static void debugfs_remove_domain_dir(struct irq_domain *d); +#else +static inline void debugfs_add_domain_dir(struct irq_domain *d) { } +static inline void debugfs_remove_domain_dir(struct irq_domain *d) { } +#endif + /** * irq_domain_alloc_fwnode - Allocate a fwnode_handle suitable for * identifying an irq domain @@ -194,6 +202,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_domain_check_hierarchy(domain); mutex_lock(&irq_domain_mutex); + debugfs_add_domain_dir(domain); list_add(&domain->link, &irq_domain_list); mutex_unlock(&irq_domain_mutex); @@ -213,6 +222,7 @@ EXPORT_SYMBOL_GPL(__irq_domain_add); void irq_domain_remove(struct irq_domain *domain) { mutex_lock(&irq_domain_mutex); + debugfs_remove_domain_dir(domain); WARN_ON(!radix_tree_empty(&domain->revmap_tree)); @@ -1599,3 +1609,78 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain) { } #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ + +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +static struct dentry *domain_dir; + +static void +irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind) +{ + seq_printf(m, "%*sname: %s\n", ind, "", d->name); + seq_printf(m, "%*ssize: %u\n", ind + 1, "", + d->revmap_size + d->revmap_direct_max_irq); + seq_printf(m, "%*smapped: %u\n", ind + 1, "", d->mapcount); + seq_printf(m, "%*sflags: 0x%08x\n", ind +1 , "", d->flags); +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + if (!d->parent) + return; + seq_printf(m, "%*sparent: %s\n", ind + 1, "", d->parent->name); + irq_domain_debug_show_one(m, d->parent, ind + 4); +#endif +} + +static int irq_domain_debug_show(struct seq_file *m, void *p) +{ + struct irq_domain *d = m->private; + + /* Default domain? Might be NULL */ + if (!d) { + if (!irq_default_domain) + return 0; + d = irq_default_domain; + } + irq_domain_debug_show_one(m, d, 0); + return 0; +} + +static int irq_domain_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, irq_domain_debug_show, inode->i_private); +} + +static const struct file_operations dfs_domain_ops = { + .open = irq_domain_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void debugfs_add_domain_dir(struct irq_domain *d) +{ + if (!d->name || !domain_dir || d->debugfs_file) + return; + d->debugfs_file = debugfs_create_file(d->name, 0444, domain_dir, d, + &dfs_domain_ops); +} + +static void debugfs_remove_domain_dir(struct irq_domain *d) +{ + if (d->debugfs_file) + debugfs_remove(d->debugfs_file); +} + +void __init irq_domain_debugfs_init(struct dentry *root) +{ + struct irq_domain *d; + + domain_dir = debugfs_create_dir("domains", root); + if (!domain_dir) + return; + + debugfs_create_file("default", 0444, domain_dir, NULL, &dfs_domain_ops); + mutex_lock(&irq_domain_mutex); + list_for_each_entry(d, &irq_domain_list, link) + debugfs_add_domain_dir(d); + mutex_unlock(&irq_domain_mutex); +} +#endif diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 4c34696ca575..284f4eb1ffbe 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1398,6 +1398,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) wake_up_process(new->secondary->thread); register_irq_proc(irq, desc); + irq_add_debugfs_entry(irq, desc); new->dir = NULL; register_handler_proc(irq, new); free_cpumask_var(mask); -- cgit v1.2.3 From cba4235e6031e9318d68186f6d765c531cbea4e1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jun 2017 01:37:21 +0200 Subject: genirq: Remove mask argument from setup_affinity() No point to have this alloc/free dance of cpumasks. Provide a static mask for setup_affinity() and protect it proper. Signed-off-by: Thomas Gleixner Cc: Jens Axboe Cc: Marc Zyngier Cc: Michael Ellerman Cc: Keith Busch Cc: Peter Zijlstra Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20170619235444.851571573@linutronix.de --- kernel/irq/internals.h | 2 +- kernel/irq/manage.c | 53 ++++++++++++++++++++++---------------------------- kernel/irq/proc.c | 8 +++++--- 3 files changed, 29 insertions(+), 34 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 094db5bfb83f..33ca83816b8c 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -109,7 +109,7 @@ static inline void unregister_handler_proc(unsigned int irq, extern bool irq_can_set_affinity_usr(unsigned int irq); -extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask); +extern int irq_select_affinity_usr(unsigned int irq); extern void irq_set_thread_affinity(struct irq_desc *desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 284f4eb1ffbe..e2f20d553d60 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -345,15 +345,18 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); /* * Generic version of the affinity autoselector. */ -static int setup_affinity(struct irq_desc *desc, struct cpumask *mask) +static int irq_setup_affinity(struct irq_desc *desc) { struct cpumask *set = irq_default_affinity; - int node = irq_desc_get_node(desc); + int ret, node = irq_desc_get_node(desc); + static DEFINE_RAW_SPINLOCK(mask_lock); + static struct cpumask mask; /* Excludes PER_CPU and NO_BALANCE interrupts */ if (!__irq_can_set_affinity(desc)) return 0; + raw_spin_lock(&mask_lock); /* * Preserve the managed affinity setting and a userspace affinity * setup, but make sure that one of the targets is online. @@ -367,43 +370,42 @@ static int setup_affinity(struct irq_desc *desc, struct cpumask *mask) irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET); } - cpumask_and(mask, cpu_online_mask, set); + 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); + if (cpumask_intersects(&mask, nodemask)) + cpumask_and(&mask, &mask, nodemask); } - irq_do_set_affinity(&desc->irq_data, mask, false); - return 0; + ret = irq_do_set_affinity(&desc->irq_data, &mask, false); + raw_spin_unlock(&mask_lock); + return ret; } #else /* Wrapper for ALPHA specific affinity selector magic */ -static inline int setup_affinity(struct irq_desc *d, struct cpumask *mask) +int irq_setup_affinity(struct irq_desc *desc) { - return irq_select_affinity(irq_desc_get_irq(d)); + return irq_select_affinity(irq_desc_get_irq(desc)); } #endif /* - * Called when affinity is set via /proc/irq + * Called when a bogus affinity is set via /proc/irq */ -int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask) +int irq_select_affinity_usr(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; int ret; raw_spin_lock_irqsave(&desc->lock, flags); - ret = setup_affinity(desc, mask); + ret = irq_setup_affinity(desc); raw_spin_unlock_irqrestore(&desc->lock, flags); return ret; } - #else -static inline int -setup_affinity(struct irq_desc *desc, struct cpumask *mask) +static inline int setup_affinity(struct irq_desc *desc) { return 0; } @@ -1128,7 +1130,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) struct irqaction *old, **old_ptr; unsigned long flags, thread_mask = 0; int ret, nested, shared = 0; - cpumask_var_t mask; if (!desc) return -EINVAL; @@ -1187,11 +1188,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } } - 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 @@ -1256,7 +1252,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ if (thread_mask == ~0UL) { ret = -EBUSY; - goto out_mask; + goto out_unlock; } /* * The thread_mask for the action is or'ed to @@ -1300,7 +1296,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n", irq); ret = -EINVAL; - goto out_mask; + goto out_unlock; } if (!shared) { @@ -1308,7 +1304,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) 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; + goto out_unlock; } init_waitqueue_head(&desc->wait_for_threads); @@ -1320,7 +1316,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (ret) { irq_release_resources(desc); - goto out_mask; + goto out_unlock; } } @@ -1357,7 +1353,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } /* Set default affinity mask once everything is setup */ - setup_affinity(desc, mask); + irq_setup_affinity(desc); } else if (new->flags & IRQF_TRIGGER_MASK) { unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK; @@ -1401,8 +1397,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irq_add_debugfs_entry(irq, desc); new->dir = NULL; register_handler_proc(irq, new); - free_cpumask_var(mask); - return 0; mismatch: @@ -1415,9 +1409,8 @@ mismatch: } ret = -EBUSY; -out_mask: +out_unlock: raw_spin_unlock_irqrestore(&desc->lock, flags); - free_cpumask_var(mask); out_thread: if (new->thread) { diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index c53edad7b459..d35bb8d4c317 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -120,9 +120,11 @@ static ssize_t write_irq_affinity(int type, struct file *file, * one online CPU still has to be targeted. */ 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, new_value) ? -EINVAL : count; + /* + * Special case for empty set - allow the architecture code + * to set default SMP affinity. + */ + err = irq_select_affinity_usr(irq) ? -EINVAL : count; } else { irq_set_affinity(irq, new_value); err = count; -- cgit v1.2.3 From 43564bd97d0e6182bbd43b51b33254c728832551 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jun 2017 01:37:22 +0200 Subject: genirq: Rename setup_affinity() to irq_setup_affinity() Rename it with a proper irq_ prefix and make it available for other files in the core code. Preparatory patch for moving the irq affinity setup around. Signed-off-by: Thomas Gleixner Cc: Jens Axboe Cc: Marc Zyngier Cc: Michael Ellerman Cc: Keith Busch Cc: Peter Zijlstra Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20170619235444.928501004@linutronix.de --- kernel/irq/internals.h | 6 ++++++ kernel/irq/manage.c | 7 +------ 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 33ca83816b8c..2d7927d9fb57 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -116,6 +116,12 @@ 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); +#ifdef CONFIG_SMP +extern int irq_setup_affinity(struct irq_desc *desc); +#else +static inline int irq_setup_affinity(struct irq_desc *desc) { return 0; } +#endif + /* Inline functions for support of irq chips on slow busses */ static inline void chip_bus_lock(struct irq_desc *desc) { diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e2f20d553d60..907fb791ff63 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -345,7 +345,7 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); /* * Generic version of the affinity autoselector. */ -static int irq_setup_affinity(struct irq_desc *desc) +int irq_setup_affinity(struct irq_desc *desc) { struct cpumask *set = irq_default_affinity; int ret, node = irq_desc_get_node(desc); @@ -404,11 +404,6 @@ int irq_select_affinity_usr(unsigned int irq) raw_spin_unlock_irqrestore(&desc->lock, flags); return ret; } -#else -static inline int setup_affinity(struct irq_desc *desc) -{ - return 0; -} #endif /** -- cgit v1.2.3 From 2e051552df69af6d134c2592d0d6f1ac80f01190 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jun 2017 01:37:23 +0200 Subject: genirq: Move initial affinity setup to irq_startup() The startup vs. setaffinity ordering of interrupts depends on the IRQF_NOAUTOEN flag. Chained interrupts are not getting any affinity assignment at all. A regular interrupt is started up and then the affinity is set. A IRQF_NOAUTOEN marked interrupt is not started up, but the affinity is set nevertheless. Move the affinity setup to startup_irq() so the ordering is always the same and chained interrupts get the proper default affinity assigned as well. Signed-off-by: Thomas Gleixner Cc: Jens Axboe Cc: Marc Zyngier Cc: Michael Ellerman Cc: Keith Busch Cc: Peter Zijlstra Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20170619235445.020534783@linutronix.de --- kernel/irq/chip.c | 2 ++ kernel/irq/manage.c | 15 ++++++--------- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index bc1331f84fb5..e290d73b88e2 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -213,6 +213,8 @@ int irq_startup(struct irq_desc *desc, bool resend) irq_enable(desc); } irq_state_set_started(desc); + /* Set default affinity mask once everything is setup */ + irq_setup_affinity(desc); } if (resend) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 907fb791ff63..1e283073cecc 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1327,6 +1327,12 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (new->flags & IRQF_ONESHOT) desc->istate |= IRQS_ONESHOT; + /* Exclude IRQ from balancing if requested */ + if (new->flags & IRQF_NOBALANCING) { + irq_settings_set_no_balancing(desc); + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + } + if (irq_settings_can_autoenable(desc)) { irq_startup(desc, true); } else { @@ -1341,15 +1347,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) desc->depth = 1; } - /* Exclude IRQ from balancing if requested */ - 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 */ - irq_setup_affinity(desc); - } else if (new->flags & IRQF_TRIGGER_MASK) { unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK; unsigned int omsk = irqd_get_trigger_type(&desc->irq_data); -- cgit v1.2.3 From 137221df69c6f8a7002f82dc3d95052d34f5667e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 20 Jun 2017 01:37:24 +0200 Subject: genirq: Move pending helpers to internal.h So that the affinity code can reuse them. Signed-off-by: Christoph Hellwig Signed-off-by: Thomas Gleixner Cc: Jens Axboe Cc: Marc Zyngier Cc: Michael Ellerman Cc: Keith Busch Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20170619235445.109426284@linutronix.de --- kernel/irq/internals.h | 38 ++++++++++++++++++++++++++++++++++++++ kernel/irq/manage.c | 28 ---------------------------- 2 files changed, 38 insertions(+), 28 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 2d7927d9fb57..20b197f0a7b5 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -249,6 +249,44 @@ irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, void __iomem *reg_base, irq_flow_handler_t handler) { } #endif /* CONFIG_GENERIC_IRQ_CHIP */ +#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 /* CONFIG_GENERIC_PENDING_IRQ */ +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 /* CONFIG_GENERIC_PENDING_IRQ */ + #ifdef CONFIG_GENERIC_IRQ_DEBUGFS void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); void irq_remove_debugfs_entry(struct irq_desc *desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1e283073cecc..7dcf19397c39 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -168,34 +168,6 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } -#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) { -- cgit v1.2.3 From 4cde9c6b826834b861a2b58653ab33150f562064 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 20 Jun 2017 01:37:49 +0200 Subject: genirq: Add force argument to irq_startup() In order to handle managed interrupts gracefully on irq_startup() so they won't lose their assigned affinity, it's necessary to allow startups which keep the interrupts in managed shutdown state, if none of the assigend CPUs is online. This allows drivers to request interrupts w/o the CPUs being online, which avoid online/offline churn in drivers. Add a force argument which can override that decision and let only request_irq() and enable_irq() allow the managed shutdown handling. enable_irq() is required, because the interrupt might be requested with IRQF_NOAUTOEN and enable_irq() invokes irq_startup() which would then wreckage the assignment again. All other callers force startup and potentially break the assigned affinity. No functional change as this only adds the function argument. Signed-off-by: Thomas Gleixner Cc: Jens Axboe Cc: Marc Zyngier Cc: Michael Ellerman Cc: Keith Busch Cc: Peter Zijlstra Cc: Christoph Hellwig Link: http://lkml.kernel.org/r/20170619235447.112094565@linutronix.de --- kernel/irq/autoprobe.c | 4 ++-- kernel/irq/chip.c | 4 ++-- kernel/irq/internals.h | 9 ++++++++- kernel/irq/manage.c | 4 ++-- 4 files changed, 14 insertions(+), 7 deletions(-) (limited to 'kernel/irq/manage.c') diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index 0119b9d467ae..d30a0dd5cc02 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -53,7 +53,7 @@ unsigned long probe_irq_on(void) 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); + irq_startup(desc, IRQ_NORESEND, IRQ_START_FORCE); } raw_spin_unlock_irq(&desc->lock); } @@ -70,7 +70,7 @@ unsigned long probe_irq_on(void) raw_spin_lock_irq(&desc->lock); if (!desc->action && irq_settings_can_probe(desc)) { desc->istate |= IRQS_AUTODETECT | IRQS_WAITING; - if (irq_startup(desc, false)) + if (irq_startup(desc, IRQ_NORESEND, IRQ_START_FORCE)) desc->istate |= IRQS_PENDING; } raw_spin_unlock_irq(&desc->lock); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 1163089aa245..b7599e952d3b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -212,7 +212,7 @@ static int __irq_startup(struct irq_desc *desc) return ret; } -int irq_startup(struct irq_desc *desc, bool resend) +int irq_startup(struct irq_desc *desc, bool resend, bool force) { int ret = 0; @@ -892,7 +892,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); desc->action = &chained_action; - irq_startup(desc, true); + irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE); } } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index ca4666b4cd39..5fd105e252c3 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -66,7 +66,14 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned long flags); extern void __disable_irq(struct irq_desc *desc); extern void __enable_irq(struct irq_desc *desc); -extern int irq_startup(struct irq_desc *desc, bool resend); +#define IRQ_RESEND true +#define IRQ_NORESEND false + +#define IRQ_START_FORCE true +#define IRQ_START_COND false + +extern int irq_startup(struct irq_desc *desc, bool resend, bool force); + extern void irq_shutdown(struct irq_desc *desc); extern void irq_enable(struct irq_desc *desc); extern void irq_disable(struct irq_desc *desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 7dcf19397c39..3577c091ac7b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -509,7 +509,7 @@ void __enable_irq(struct irq_desc *desc) * time. If it was already started up, then irq_startup() * will invoke irq_enable() under the hood. */ - irq_startup(desc, true); + irq_startup(desc, IRQ_RESEND, IRQ_START_COND); break; } default: @@ -1306,7 +1306,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (irq_settings_can_autoenable(desc)) { - irq_startup(desc, true); + irq_startup(desc, IRQ_RESEND, IRQ_START_COND); } else { /* * Shared interrupts do not go well with disabling -- cgit v1.2.3 From b2d3d61adb7b73cfe5f82404f7a130a76fc64232 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 23 Jun 2017 16:11:07 +0200 Subject: genirq/timings: Add infrastructure to track the interrupt timings The interrupt framework gives a lot of information about each interrupt. It does not keep track of when those interrupts occur though, which is a prerequisite for estimating the next interrupt arrival for power management purposes. Add a mechanism to record the timestamp for each interrupt occurrences in a per-CPU circular buffer to help with the prediction of the next occurrence using a statistical model. Each CPU can store up to IRQ_TIMINGS_SIZE events , the current value of IRQ_TIMINGS_SIZE is 32. Each event is encoded into a single u64, where the high 48 bits are used for the timestamp and the low 16 bits are for the irq number. A static key is introduced so when the irq prediction is switched off at runtime, the overhead is near to zero. It results in most of the code in internals.h for inline reasons and a very few in the new file timings.c. The latter will contain more in the next patch which will provide the statistical model for the next event prediction. Signed-off-by: Daniel Lezcano Signed-off-by: Thomas Gleixner Acked-by: Nicolas Pitre Cc: Jens Axboe Cc: Hannes Reinecke Cc: Vincent Guittot Cc: "Rafael J . Wysocki" Cc: Peter Zijlstra Cc: Bjorn Helgaas Link: http://lkml.kernel.org/r/1498227072-5980-1-git-send-email-daniel.lezcano@linaro.org --- include/linux/interrupt.h | 5 +++ kernel/irq/Kconfig | 3 ++ kernel/irq/Makefile | 1 + kernel/irq/handle.c | 2 ++ kernel/irq/internals.h | 90 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/irq/manage.c | 3 ++ kernel/irq/timings.c | 30 ++++++++++++++++ 7 files changed, 134 insertions(+) create mode 100644 kernel/irq/timings.c (limited to 'kernel/irq/manage.c') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a6fba4804672..9f617238a2f7 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -703,6 +703,11 @@ static inline void init_irq_proc(void) } #endif +#ifdef CONFIG_IRQ_TIMINGS +void irq_timings_enable(void); +void irq_timings_disable(void); +#endif + struct seq_file; int show_interrupts(struct seq_file *p, void *v); int arch_show_interrupts(struct seq_file *p, int prec); diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index fcbb1d6d51cb..27c4e774071c 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -85,6 +85,9 @@ config GENERIC_MSI_IRQ_DOMAIN config HANDLE_DOMAIN_IRQ bool +config IRQ_TIMINGS + bool + config IRQ_DOMAIN_DEBUG bool "Expose hardware/virtual IRQ mapping via debugfs" depends on IRQ_DOMAIN && DEBUG_FS diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index c61fc9c2d1f7..e4aef7351f2b 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,5 +1,6 @@ obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o +obj-$(CONFIG_IRQ_TIMINGS) += timings.o obj-$(CONFIG_GENERIC_IRQ_CHIP) += generic-chip.o obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index d3f24905852c..eb4d3e8945b8 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -138,6 +138,8 @@ irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags unsigned int irq = desc->irq_data.irq; struct irqaction *action; + record_irq_time(desc); + for_each_action_of_desc(desc, action) { irqreturn_t res; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index a573e0771baf..b95b74920433 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -8,6 +8,7 @@ #include #include #include +#include #ifdef CONFIG_SPARSE_IRQ # define IRQ_BITMAP_BITS (NR_IRQS + 8196) @@ -57,6 +58,7 @@ enum { IRQS_WAITING = 0x00000080, IRQS_PENDING = 0x00000200, IRQS_SUSPENDED = 0x00000800, + IRQS_TIMINGS = 0x00001000, }; #include "debug.h" @@ -255,6 +257,94 @@ static inline void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { } #endif +#ifdef CONFIG_IRQ_TIMINGS + +#define IRQ_TIMINGS_SHIFT 5 +#define IRQ_TIMINGS_SIZE (1 << IRQ_TIMINGS_SHIFT) +#define IRQ_TIMINGS_MASK (IRQ_TIMINGS_SIZE - 1) + +/** + * struct irq_timings - irq timings storing structure + * @values: a circular buffer of u64 encoded values + * @count: the number of elements in the array + */ +struct irq_timings { + u64 values[IRQ_TIMINGS_SIZE]; + int count; +}; + +DECLARE_PER_CPU(struct irq_timings, irq_timings); + +static inline void irq_remove_timings(struct irq_desc *desc) +{ + desc->istate &= ~IRQS_TIMINGS; +} + +static inline void irq_setup_timings(struct irq_desc *desc, struct irqaction *act) +{ + /* + * We don't need the measurement because the idle code already + * knows the next expiry event. + */ + if (act->flags & __IRQF_TIMER) + return; + + desc->istate |= IRQS_TIMINGS; +} + +extern void irq_timings_enable(void); +extern void irq_timings_disable(void); + +DECLARE_STATIC_KEY_FALSE(irq_timing_enabled); + +/* + * The interrupt number and the timestamp are encoded into a single + * u64 variable to optimize the size. + * 48 bit time stamp and 16 bit IRQ number is way sufficient. + * Who cares an IRQ after 78 hours of idle time? + */ +static inline u64 irq_timing_encode(u64 timestamp, int irq) +{ + return (timestamp << 16) | irq; +} + +static inline int irq_timing_decode(u64 value, u64 *timestamp) +{ + *timestamp = value >> 16; + return value & U16_MAX; +} + +/* + * The function record_irq_time is only called in one place in the + * interrupts handler. We want this function always inline so the code + * inside is embedded in the function and the static key branching + * code can act at the higher level. Without the explicit + * __always_inline we can end up with a function call and a small + * overhead in the hotpath for nothing. + */ +static __always_inline void record_irq_time(struct irq_desc *desc) +{ + if (!static_branch_likely(&irq_timing_enabled)) + return; + + if (desc->istate & IRQS_TIMINGS) { + struct irq_timings *timings = this_cpu_ptr(&irq_timings); + + timings->values[timings->count & IRQ_TIMINGS_MASK] = + irq_timing_encode(local_clock(), + irq_desc_get_irq(desc)); + + timings->count++; + } +} +#else +static inline void irq_remove_timings(struct irq_desc *desc) {} +static inline void irq_setup_timings(struct irq_desc *desc, + struct irqaction *act) {}; +static inline void record_irq_time(struct irq_desc *desc) {} +#endif /* CONFIG_IRQ_TIMINGS */ + + #ifdef CONFIG_GENERIC_IRQ_CHIP void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name, int num_ct, unsigned int irq_base, diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3577c091ac7b..5c11c1730ba5 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1348,6 +1348,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) raw_spin_unlock_irqrestore(&desc->lock, flags); + irq_setup_timings(desc, new); + /* * Strictly no need to wake it up, but hung_task complains * when no hard interrupt wakes the thread up. @@ -1474,6 +1476,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) irq_settings_clr_disable_unlazy(desc); irq_shutdown(desc); irq_release_resources(desc); + irq_remove_timings(desc); } #ifdef CONFIG_SMP diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c new file mode 100644 index 000000000000..56cf6870fa26 --- /dev/null +++ b/kernel/irq/timings.c @@ -0,0 +1,30 @@ +/* + * linux/kernel/irq/timings.c + * + * Copyright (C) 2016, Linaro Ltd - Daniel Lezcano + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#include +#include +#include +#include + +#include "internals.h" + +DEFINE_STATIC_KEY_FALSE(irq_timing_enabled); + +DEFINE_PER_CPU(struct irq_timings, irq_timings); + +void irq_timings_enable(void) +{ + static_branch_enable(&irq_timing_enabled); +} + +void irq_timings_disable(void) +{ + static_branch_disable(&irq_timing_enabled); +} -- cgit v1.2.3