From efdc64f0c792ea744bcc9203f35b908e66d42f41 Mon Sep 17 00:00:00 2001 From: Wang Chen Date: Mon, 29 Dec 2008 13:35:11 +0800 Subject: genirq: check chip->ack before calling Impact: fix theoretical NULL dereference The generic irq layer doesn't know whether irq_chip has ack routine on some architectures or not. Upon that, before calling chip->ack, we should check that it's not NULL. Signed-off-by: Wang Chen Signed-off-by: Ingo Molnar --- kernel/irq/chip.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6eb3c7952b64..0ad02d76a0c4 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -290,7 +290,8 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq) desc->chip->mask_ack(irq); else { desc->chip->mask(irq); - desc->chip->ack(irq); + if (desc->chip->ack) + desc->chip->ack(irq); } } @@ -475,7 +476,8 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc) kstat_incr_irqs_this_cpu(irq, desc); /* Start handling the irq */ - desc->chip->ack(irq); + if (desc->chip->ack) + desc->chip->ack(irq); desc = irq_remap_to_desc(irq, desc); /* Mark the IRQ currently in progress.*/ -- cgit v1.2.3 From d7e51e66899f95dabc89b4d4c6674a6e50fa37fc Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 7 Jan 2009 15:03:13 -0800 Subject: sparseirq: make some func to be used with genirq Impact: clean up sparseirq fallout on random.c Ingo suggested to change some ifdef from SPARSE_IRQ to GENERIC_HARDIRQS so we could some #ifdef later if all arch support genirq Signed-off-by: Yinghai Lu Acked-by: Matt Mackall Signed-off-by: Ingo Molnar --- drivers/char/random.c | 2 +- drivers/pci/intr_remapping.c | 2 +- include/linux/irq.h | 6 ++---- include/linux/kernel_stat.h | 6 +++--- kernel/irq/handle.c | 7 ++++--- 5 files changed, 11 insertions(+), 12 deletions(-) (limited to 'kernel/irq') diff --git a/drivers/char/random.c b/drivers/char/random.c index 7c13581ca9cd..a778918c8f42 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -558,7 +558,7 @@ struct timer_rand_state { unsigned dont_count_entropy:1; }; -#ifndef CONFIG_SPARSE_IRQ +#ifndef CONFIG_GENERIC_HARDIRQS static struct timer_rand_state *irq_timer_state[NR_IRQS]; diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c index f78371b22529..3d604132a04f 100644 --- a/drivers/pci/intr_remapping.c +++ b/drivers/pci/intr_remapping.c @@ -20,7 +20,7 @@ struct irq_2_iommu { u8 irte_mask; }; -#ifdef CONFIG_SPARSE_IRQ +#ifdef CONFIG_GENERIC_HARDIRQS static struct irq_2_iommu *get_one_free_irq_2_iommu(int cpu) { struct irq_2_iommu *iommu; diff --git a/include/linux/irq.h b/include/linux/irq.h index f899b502f186..e9a878978c85 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -160,12 +160,10 @@ struct irq_2_iommu; */ struct irq_desc { unsigned int irq; -#ifdef CONFIG_SPARSE_IRQ struct timer_rand_state *timer_rand_state; unsigned int *kstat_irqs; -# ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_INTR_REMAP struct irq_2_iommu *irq_2_iommu; -# endif #endif irq_flow_handler_t handle_irq; struct irq_chip *chip; @@ -202,13 +200,13 @@ extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc extern struct irq_desc irq_desc[NR_IRQS]; #else /* CONFIG_SPARSE_IRQ */ extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu); +#endif /* CONFIG_SPARSE_IRQ */ #define kstat_irqs_this_cpu(DESC) \ ((DESC)->kstat_irqs[smp_processor_id()]) #define kstat_incr_irqs_this_cpu(irqno, DESC) \ ((DESC)->kstat_irqs[smp_processor_id()]++) -#endif /* CONFIG_SPARSE_IRQ */ extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu); diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 570d20413119..a3431b164bea 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -28,7 +28,7 @@ struct cpu_usage_stat { struct kernel_stat { struct cpu_usage_stat cpustat; -#ifndef CONFIG_SPARSE_IRQ +#ifndef CONFIG_GENERIC_HARDIRQS unsigned int irqs[NR_IRQS]; #endif }; @@ -41,7 +41,7 @@ DECLARE_PER_CPU(struct kernel_stat, kstat); extern unsigned long long nr_context_switches(void); -#ifndef CONFIG_SPARSE_IRQ +#ifndef CONFIG_GENERIC_HARDIRQS #define kstat_irqs_this_cpu(irq) \ (kstat_this_cpu.irqs[irq]) @@ -55,7 +55,7 @@ static inline void kstat_incr_irqs_this_cpu(unsigned int irq, #endif -#ifndef CONFIG_SPARSE_IRQ +#ifndef CONFIG_GENERIC_HARDIRQS static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { return kstat_cpu(cpu).irqs[irq]; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index c20db0be9173..48299a8a22f8 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -213,6 +213,7 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { } }; +static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS]; int __init early_irq_init(void) { struct irq_desc *desc; @@ -222,8 +223,10 @@ int __init early_irq_init(void) desc = irq_desc; count = ARRAY_SIZE(irq_desc); - for (i = 0; i < count; i++) + for (i = 0; i < count; i++) { desc[i].irq = i; + desc[i].kstat_irqs = kstat_irqs_all[i]; + } return arch_early_irq_init(); } @@ -451,12 +454,10 @@ void early_init_irq_lock_class(void) } } -#ifdef CONFIG_SPARSE_IRQ 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; } -#endif EXPORT_SYMBOL(kstat_irqs_cpu); -- cgit v1.2.3 From 7f7ace0cda64c99599c23785f8979a072e118058 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sat, 10 Jan 2009 21:58:08 -0800 Subject: cpumask: update irq_desc to use cpumask_var_t Impact: reduce memory usage, use new cpumask API. Replace the affinity and pending_masks with cpumask_var_t's. This adds to the significant size reduction done with the SPARSE_IRQS changes. The added functions (init_alloc_desc_masks & init_copy_desc_masks) are in the include file so they can be inlined (and optimized out for the !CONFIG_CPUMASKS_OFFSTACK case.) [Naming chosen to be consistent with the other init*irq functions, as well as the backwards arg declaration of "from, to" instead of the more common "to, from" standard.] Includes a slight change to the declaration of struct irq_desc to embed the pending_mask within ifdef(CONFIG_SMP) to be consistent with other references, and some small changes to Xen. Tested: sparse/non-sparse/cpumask_offstack/non-cpumask_offstack/nonuma/nosmp on x86_64 Signed-off-by: Mike Travis Cc: Chris Wright Cc: Jeremy Fitzhardinge Cc: KOSAKI Motohiro Cc: Venkatesh Pallipadi Cc: virtualization@lists.osdl.org Cc: xen-devel@lists.xensource.com Cc: Yinghai Lu --- arch/x86/kernel/io_apic.c | 20 ++++++------ arch/x86/kernel/irq_32.c | 2 +- arch/x86/kernel/irq_64.c | 2 +- drivers/xen/events.c | 4 +-- include/linux/irq.h | 81 +++++++++++++++++++++++++++++++++++++++++++++-- kernel/irq/chip.c | 5 ++- kernel/irq/handle.c | 26 ++++++++------- kernel/irq/manage.c | 12 +++---- kernel/irq/migration.c | 12 +++---- kernel/irq/numa_migrate.c | 12 ++++++- kernel/irq/proc.c | 4 +-- 11 files changed, 135 insertions(+), 45 deletions(-) (limited to 'kernel/irq') diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index 1c4a1302536c..1337eab60ecc 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -356,7 +356,7 @@ set_extra_move_desc(struct irq_desc *desc, const struct cpumask *mask) if (!cfg->move_in_progress) { /* it means that domain is not changed */ - if (!cpumask_intersects(&desc->affinity, mask)) + if (!cpumask_intersects(desc->affinity, mask)) cfg->move_desc_pending = 1; } } @@ -579,9 +579,9 @@ set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask) if (assign_irq_vector(irq, cfg, mask)) return BAD_APICID; - cpumask_and(&desc->affinity, cfg->domain, mask); + cpumask_and(desc->affinity, cfg->domain, mask); set_extra_move_desc(desc, mask); - return cpu_mask_to_apicid_and(&desc->affinity, cpu_online_mask); + return cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask); } static void @@ -2383,7 +2383,7 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask) if (cfg->move_in_progress) send_cleanup_vector(cfg); - cpumask_copy(&desc->affinity, mask); + cpumask_copy(desc->affinity, mask); } static int migrate_irq_remapped_level_desc(struct irq_desc *desc) @@ -2405,11 +2405,11 @@ static int migrate_irq_remapped_level_desc(struct irq_desc *desc) } /* everthing is clear. we have right of way */ - migrate_ioapic_irq_desc(desc, &desc->pending_mask); + migrate_ioapic_irq_desc(desc, desc->pending_mask); ret = 0; desc->status &= ~IRQ_MOVE_PENDING; - cpumask_clear(&desc->pending_mask); + cpumask_clear(desc->pending_mask); unmask: unmask_IO_APIC_irq_desc(desc); @@ -2434,7 +2434,7 @@ static void ir_irq_migration(struct work_struct *work) continue; } - desc->chip->set_affinity(irq, &desc->pending_mask); + desc->chip->set_affinity(irq, desc->pending_mask); spin_unlock_irqrestore(&desc->lock, flags); } } @@ -2448,7 +2448,7 @@ static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc, { if (desc->status & IRQ_LEVEL) { desc->status |= IRQ_MOVE_PENDING; - cpumask_copy(&desc->pending_mask, mask); + cpumask_copy(desc->pending_mask, mask); migrate_irq_remapped_level_desc(desc); return; } @@ -2516,7 +2516,7 @@ static void irq_complete_move(struct irq_desc **descp) /* domain has not changed, but affinity did */ me = smp_processor_id(); - if (cpu_isset(me, desc->affinity)) { + if (cpumask_test_cpu(me, desc->affinity)) { *descp = desc = move_irq_desc(desc, me); /* get the new one */ cfg = desc->chip_data; @@ -4039,7 +4039,7 @@ void __init setup_ioapic_dest(void) */ if (desc->status & (IRQ_NO_BALANCING | IRQ_AFFINITY_SET)) - mask = &desc->affinity; + mask = desc->affinity; else mask = TARGET_CPUS; diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 74b9ff7341e9..e0f29be8ab0b 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -248,7 +248,7 @@ void fixup_irqs(void) if (irq == 2) continue; - affinity = &desc->affinity; + affinity = desc->affinity; if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { printk("Breaking affinity for irq %i\n", irq); affinity = cpu_all_mask; diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 63c88e6ec025..0b21cb1ea11f 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -100,7 +100,7 @@ void fixup_irqs(void) /* interrupt's are disabled at this point */ spin_lock(&desc->lock); - affinity = &desc->affinity; + affinity = desc->affinity; if (!irq_has_action(irq) || cpumask_equal(affinity, cpu_online_mask)) { spin_unlock(&desc->lock); diff --git a/drivers/xen/events.c b/drivers/xen/events.c index eb0dfdeaa949..e0767ff35d6c 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -125,7 +125,7 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) BUG_ON(irq == -1); #ifdef CONFIG_SMP - irq_to_desc(irq)->affinity = cpumask_of_cpu(cpu); + cpumask_copy(irq_to_desc(irq)->affinity, cpumask_of(cpu)); #endif __clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]); @@ -142,7 +142,7 @@ static void init_evtchn_cpu_bindings(void) /* By default all event channels notify CPU#0. */ for_each_irq_desc(i, desc) { - desc->affinity = cpumask_of_cpu(0); + cpumask_copy(desc->affinity, cpumask_of(0)); } #endif diff --git a/include/linux/irq.h b/include/linux/irq.h index f899b502f186..fa27210f1dfd 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -182,11 +182,11 @@ struct irq_desc { unsigned int irqs_unhandled; spinlock_t lock; #ifdef CONFIG_SMP - cpumask_t affinity; + cpumask_var_t affinity; unsigned int cpu; -#endif #ifdef CONFIG_GENERIC_PENDING_IRQ - cpumask_t pending_mask; + cpumask_var_t pending_mask; +#endif #endif #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; @@ -422,4 +422,79 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry); #endif /* !CONFIG_S390 */ +#ifdef CONFIG_SMP +/** + * init_alloc_desc_masks - allocate cpumasks for irq_desc + * @desc: pointer to irq_desc struct + * @boot: true if need bootmem + * + * Allocates affinity and pending_mask cpumask if required. + * Returns true if successful (or not required). + * Side effect: affinity has all bits set, pending_mask has all bits clear. + */ +static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node, + bool boot) +{ + if (boot) { + alloc_bootmem_cpumask_var(&desc->affinity); + cpumask_setall(desc->affinity); + +#ifdef CONFIG_GENERIC_PENDING_IRQ + alloc_bootmem_cpumask_var(&desc->pending_mask); + cpumask_clear(desc->pending_mask); +#endif + return true; + } + + if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node)) + return false; + cpumask_setall(desc->affinity); + +#ifdef CONFIG_GENERIC_PENDING_IRQ + if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) { + free_cpumask_var(desc->affinity); + return false; + } + cpumask_clear(desc->pending_mask); +#endif + return true; +} + +/** + * init_copy_desc_masks - copy cpumasks for irq_desc + * @old_desc: pointer to old irq_desc struct + * @new_desc: pointer to new irq_desc struct + * + * Insures affinity and pending_masks are copied to new irq_desc. + * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the + * irq_desc struct so the copy is redundant. + */ + +static inline void init_copy_desc_masks(struct irq_desc *old_desc, + struct irq_desc *new_desc) +{ +#ifdef CONFIG_CPUMASKS_OFFSTACK + cpumask_copy(new_desc->affinity, old_desc->affinity); + +#ifdef CONFIG_GENERIC_PENDING_IRQ + cpumask_copy(new_desc->pending_mask, old_desc->pending_mask); +#endif +#endif +} + +#else /* !CONFIG_SMP */ + +static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node, + bool boot) +{ + return true; +} + +static inline void init_copy_desc_masks(struct irq_desc *old_desc, + struct irq_desc *new_desc) +{ +} + +#endif /* CONFIG_SMP */ + #endif /* _LINUX_IRQ_H */ diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index f63c706d25e1..c248eba98b43 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -46,7 +46,10 @@ void dynamic_irq_init(unsigned int irq) desc->irq_count = 0; desc->irqs_unhandled = 0; #ifdef CONFIG_SMP - cpumask_setall(&desc->affinity); + cpumask_setall(desc->affinity); +#ifdef CONFIG_GENERIC_PENDING_IRQ + cpumask_clear(desc->pending_mask); +#endif #endif spin_unlock_irqrestore(&desc->lock, flags); } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index c20db0be9173..b8fa1354f01c 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -64,9 +64,6 @@ static struct irq_desc irq_desc_init = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif }; void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) @@ -88,6 +85,8 @@ void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) { + int node = cpu_to_node(cpu); + memcpy(desc, &irq_desc_init, sizeof(struct irq_desc)); spin_lock_init(&desc->lock); @@ -101,6 +100,10 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) printk(KERN_ERR "can not alloc kstat_irqs\n"); BUG_ON(1); } + if (!init_alloc_desc_masks(desc, node, false)) { + printk(KERN_ERR "can not alloc irq_desc cpumasks\n"); + BUG_ON(1); + } arch_init_chip_data(desc, cpu); } @@ -119,9 +122,6 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif } }; @@ -141,7 +141,7 @@ int __init early_irq_init(void) desc[i].irq = i; desc[i].kstat_irqs = kstat_irqs_legacy[i]; lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); - + init_alloc_desc_masks(&desc[i], 0, true); irq_desc_ptrs[i] = desc + i; } @@ -188,6 +188,10 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) printk(KERN_ERR "can not alloc irq_desc\n"); BUG_ON(1); } + if (!init_alloc_desc_masks(desc, node, false)) { + printk(KERN_ERR "can not alloc irq_desc cpumasks\n"); + BUG_ON(1); + } init_one_irq_desc(irq, desc, cpu); irq_desc_ptrs[irq] = desc; @@ -207,9 +211,6 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock), -#ifdef CONFIG_SMP - .affinity = CPU_MASK_ALL -#endif } }; @@ -222,9 +223,10 @@ int __init early_irq_init(void) desc = irq_desc; count = ARRAY_SIZE(irq_desc); - for (i = 0; i < count; i++) + for (i = 0; i < count; i++) { desc[i].irq = i; - + init_alloc_desc_masks(&desc[i], 0, true); + } return arch_early_irq_init(); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index cd0cd8dcb345..b98739af4558 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -98,14 +98,14 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) { - cpumask_copy(&desc->affinity, cpumask); + cpumask_copy(desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); } else { desc->status |= IRQ_MOVE_PENDING; - cpumask_copy(&desc->pending_mask, cpumask); + cpumask_copy(desc->pending_mask, cpumask); } #else - cpumask_copy(&desc->affinity, cpumask); + cpumask_copy(desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); #endif desc->status |= IRQ_AFFINITY_SET; @@ -127,16 +127,16 @@ int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc) * one of the targets is online. */ if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) { - if (cpumask_any_and(&desc->affinity, cpu_online_mask) + if (cpumask_any_and(desc->affinity, cpu_online_mask) < nr_cpu_ids) goto set_affinity; else desc->status &= ~IRQ_AFFINITY_SET; } - cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity); + cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity); set_affinity: - desc->chip->set_affinity(irq, &desc->affinity); + desc->chip->set_affinity(irq, desc->affinity); return 0; } diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index bd72329e630c..e05ad9be43b7 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -18,7 +18,7 @@ void move_masked_irq(int irq) desc->status &= ~IRQ_MOVE_PENDING; - if (unlikely(cpumask_empty(&desc->pending_mask))) + if (unlikely(cpumask_empty(desc->pending_mask))) return; if (!desc->chip->set_affinity) @@ -38,13 +38,13 @@ void move_masked_irq(int irq) * For correct operation this depends on the caller * masking the irqs. */ - if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask) + if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)) { - cpumask_and(&desc->affinity, - &desc->pending_mask, cpu_online_mask); - desc->chip->set_affinity(irq, &desc->affinity); + cpumask_and(desc->affinity, + desc->pending_mask, cpu_online_mask); + desc->chip->set_affinity(irq, desc->affinity); } - cpumask_clear(&desc->pending_mask); + cpumask_clear(desc->pending_mask); } void move_native_irq(int irq) diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index ecf765c6a77a..f001a4ea6414 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -46,6 +46,7 @@ static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, desc->cpu = cpu; lockdep_set_class(&desc->lock, &irq_desc_lock_class); init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids); + init_copy_desc_masks(old_desc, desc); arch_init_copy_chip_data(old_desc, desc, cpu); } @@ -76,11 +77,20 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, node = cpu_to_node(cpu); 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); + 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_alloc_desc_masks(desc, node, false)) { + printk(KERN_ERR "irq %d: can not get new irq_desc cpumask " + "for migration.\n", irq); + /* still use old one */ + kfree(desc); + desc = old_desc; + goto out_unlock; + } init_copy_one_irq_desc(irq, old_desc, desc, cpu); irq_desc_ptrs[irq] = desc; diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index aae3f742bcec..692363dd591f 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -20,11 +20,11 @@ static struct proc_dir_entry *root_irq_dir; static int irq_affinity_proc_show(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->affinity; #ifdef CONFIG_GENERIC_PENDING_IRQ if (desc->status & IRQ_MOVE_PENDING) - mask = &desc->pending_mask; + mask = desc->pending_mask; #endif seq_cpumask(m, mask); seq_putc(m, '\n'); -- cgit v1.2.3 From 802bf931f2688ad125b73db597ce63cc842fb27a Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sat, 10 Jan 2009 21:58:09 -0800 Subject: cpumask: fix bug in use cpumask_var_t in irq_desc Impact: fix bug where new irq_desc uses old cpumask pointers which are freed. As Yinghai pointed out, init_copy_one_irq_desc() copies the old desc to the new desc overwriting the cpumask pointers. Since the old_desc and the cpumask pointers are freed, then memory corruption will occur if these old pointers are used. Move the allocation of these pointers to after the copy. Signed-off-by: Mike Travis Cc: Yinghai Lu --- include/linux/irq.h | 9 +++++++-- kernel/irq/handle.c | 8 +------- kernel/irq/numa_migrate.c | 13 ++++++++----- 3 files changed, 16 insertions(+), 14 deletions(-) (limited to 'kernel/irq') diff --git a/include/linux/irq.h b/include/linux/irq.h index fa27210f1dfd..27a67536511e 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -426,15 +426,18 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry); /** * init_alloc_desc_masks - allocate cpumasks for irq_desc * @desc: pointer to irq_desc struct + * @cpu: cpu which will be handling the cpumasks * @boot: true if need bootmem * * Allocates affinity and pending_mask cpumask if required. * Returns true if successful (or not required). * Side effect: affinity has all bits set, pending_mask has all bits clear. */ -static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node, +static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu, bool boot) { + int node; + if (boot) { alloc_bootmem_cpumask_var(&desc->affinity); cpumask_setall(desc->affinity); @@ -446,6 +449,8 @@ static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node, return true; } + node = cpu_to_node(cpu); + if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node)) return false; cpumask_setall(desc->affinity); @@ -484,7 +489,7 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc, #else /* !CONFIG_SMP */ -static inline bool init_alloc_desc_masks(struct irq_desc *desc, int node, +static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu, bool boot) { return true; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index b8fa1354f01c..f01c0a30cb42 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -85,8 +85,6 @@ void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) { - int node = cpu_to_node(cpu); - memcpy(desc, &irq_desc_init, sizeof(struct irq_desc)); spin_lock_init(&desc->lock); @@ -100,7 +98,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) printk(KERN_ERR "can not alloc kstat_irqs\n"); BUG_ON(1); } - if (!init_alloc_desc_masks(desc, node, false)) { + if (!init_alloc_desc_masks(desc, cpu, false)) { printk(KERN_ERR "can not alloc irq_desc cpumasks\n"); BUG_ON(1); } @@ -188,10 +186,6 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) printk(KERN_ERR "can not alloc irq_desc\n"); BUG_ON(1); } - if (!init_alloc_desc_masks(desc, node, false)) { - printk(KERN_ERR "can not alloc irq_desc cpumasks\n"); - BUG_ON(1); - } init_one_irq_desc(irq, desc, cpu); irq_desc_ptrs[irq] = desc; diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index f001a4ea6414..666260e4c065 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -38,16 +38,22 @@ static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc) old_desc->kstat_irqs = NULL; } -static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, +static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc, struct irq_desc *desc, int cpu) { memcpy(desc, old_desc, sizeof(struct irq_desc)); + if (!init_alloc_desc_masks(desc, cpu, false)) { + printk(KERN_ERR "irq %d: can not get new irq_desc cpumask " + "for migration.\n", irq); + return false; + } spin_lock_init(&desc->lock); desc->cpu = cpu; lockdep_set_class(&desc->lock, &irq_desc_lock_class); init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids); init_copy_desc_masks(old_desc, desc); arch_init_copy_chip_data(old_desc, desc, cpu); + return true; } static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc) @@ -83,15 +89,12 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc, desc = old_desc; goto out_unlock; } - if (!init_alloc_desc_masks(desc, node, false)) { - printk(KERN_ERR "irq %d: can not get new irq_desc cpumask " - "for migration.\n", irq); + if (!init_copy_one_irq_desc(irq, old_desc, desc, cpu)) { /* still use old one */ kfree(desc); desc = old_desc; goto out_unlock; } - init_copy_one_irq_desc(irq, old_desc, desc, cpu); irq_desc_ptrs[irq] = desc; -- cgit v1.2.3 From 9594949b060efe86ecaa1a66839232a3b9800bc9 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sat, 10 Jan 2009 22:24:06 -0800 Subject: irq: change references from NR_IRQS to nr_irqs Impact: preparation, cleanup, add KERN_INFO printk Modify references from NR_IRQS to nr_irqs as the later will become variable-sized based on nr_cpu_ids when CONFIG_SPARSE_IRQS=y. Signed-off-by: Mike Travis --- arch/x86/kernel/io_apic.c | 2 +- kernel/irq/handle.c | 14 +++++++++----- 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'kernel/irq') diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index 1337eab60ecc..ae80638012de 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -3183,7 +3183,7 @@ unsigned int create_irq_nr(unsigned int irq_want) irq = 0; spin_lock_irqsave(&vector_lock, flags); - for (new = irq_want; new < NR_IRQS; new++) { + for (new = irq_want; new < nr_irqs; new++) { if (platform_legacy_irq(new)) continue; diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index f01c0a30cb42..790c5fa7ea39 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -132,6 +132,8 @@ int __init early_irq_init(void) int legacy_count; int i; + 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); @@ -143,7 +145,7 @@ int __init early_irq_init(void) irq_desc_ptrs[i] = desc + i; } - for (i = legacy_count; i < NR_IRQS; i++) + for (i = legacy_count; i < nr_irqs; i++) irq_desc_ptrs[i] = NULL; return arch_early_irq_init(); @@ -151,7 +153,7 @@ int __init early_irq_init(void) struct irq_desc *irq_to_desc(unsigned int irq) { - return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL; + return (irq < nr_irqs) ? irq_desc_ptrs[irq] : NULL; } struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) @@ -160,9 +162,9 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) unsigned long flags; int node; - if (irq >= NR_IRQS) { - printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n", - irq, NR_IRQS); + if (irq >= nr_irqs) { + printk(KERN_WARNING "irq >= nr_irqs in irq_to_desc_alloc: %d %d\n", + irq, nr_irqs); WARN_ON(1); return NULL; } @@ -214,6 +216,8 @@ int __init early_irq_init(void) int count; int i; + printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS); + desc = irq_desc; count = ARRAY_SIZE(irq_desc); -- cgit v1.2.3 From e2f4d06545ec1f29b0e838ee34cbf3500ea5b9a4 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sat, 10 Jan 2009 22:24:06 -0800 Subject: irq: use WARN() instead of WARN_ON(). Impact: cleanup WARN msg. Ingo requested: > While at it, could you please also convert this to a WARN() construct > instead? (in a separate commit) ... and it shall be done. ;-) Signed-off-by: Mike Travis --- kernel/irq/handle.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 790c5fa7ea39..fd1ef16252f4 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -163,9 +163,8 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) int node; if (irq >= nr_irqs) { - printk(KERN_WARNING "irq >= nr_irqs in irq_to_desc_alloc: %d %d\n", - irq, nr_irqs); - WARN_ON(1); + WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n", + irq, nr_irqs); return NULL; } -- cgit v1.2.3 From 0fa0ebbf15addc1be8f73325d809c8547a9de304 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sat, 10 Jan 2009 22:24:06 -0800 Subject: irq: allocate irq_desc_ptrs array based on nr_irqs Impact: allocate irq_desc_ptrs in preparation for making it variable-sized. This addresses this memory usage bump when NR_CPUS bumped from 128 to 4096: 34816 +229376 264192 +658% irq_desc_ptrs(.data.read_mostly) The patch is split into two parts, the first simply allocates the irq_desc_ptrs array. Then next will deal with making it variable. This is only when CONFIG_SPARSE_IRQS=y. Signed-off-by: Mike Travis --- kernel/irq/handle.c | 11 +++++++++-- kernel/irq/internals.h | 7 +++++++ 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index fd1ef16252f4..d0b8f7e72790 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "internals.h" @@ -110,7 +111,7 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) */ DEFINE_SPINLOCK(sparse_irq_lock); -struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly; +struct irq_desc **irq_desc_ptrs __read_mostly; static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = { [0 ... NR_IRQS_LEGACY-1] = { @@ -137,6 +138,9 @@ int __init early_irq_init(void) desc = irq_desc_legacy; legacy_count = ARRAY_SIZE(irq_desc_legacy); + /* allocate irq_desc_ptrs array based on nr_irqs */ + irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *)); + for (i = 0; i < legacy_count; i++) { desc[i].irq = i; desc[i].kstat_irqs = kstat_irqs_legacy[i]; @@ -153,7 +157,10 @@ int __init early_irq_init(void) struct irq_desc *irq_to_desc(unsigned int irq) { - return (irq < nr_irqs) ? irq_desc_ptrs[irq] : NULL; + if (irq_desc_ptrs && irq < nr_irqs) + return irq_desc_ptrs[irq]; + + return NULL; } struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index e6d0a43cc125..40416a81a0f5 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -16,7 +16,14 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, extern struct lock_class_key irq_desc_lock_class; extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr); extern spinlock_t sparse_irq_lock; + +#ifdef CONFIG_SPARSE_IRQ +/* irq_desc_ptrs allocated at boot time */ +extern struct irq_desc **irq_desc_ptrs; +#else +/* irq_desc_ptrs is a fixed size array */ extern struct irq_desc *irq_desc_ptrs[NR_IRQS]; +#endif #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); -- cgit v1.2.3 From 9332fccdedf8e09448f3b69b624211ae879f6c45 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sat, 10 Jan 2009 22:24:07 -0800 Subject: irq: initialize nr_irqs based on nr_cpu_ids Impact: Reduce memory usage. This is the second half of the changes to make the irq_desc_ptrs be variable sized based on nr_cpu_ids. This is done by adding a new "max_nr_irqs" macro to irq_vectors.h (and a dummy in irqnr.h) to return a max NR_IRQS value based on NR_CPUS or nr_cpu_ids. This necessitated moving the define of MAX_IO_APICS to a separate file (asm/apicnum.h) so it could be included without the baggage of the other asm/apicdef.h declarations. Signed-off-by: Mike Travis --- arch/x86/include/asm/apicdef.h | 8 ++------ arch/x86/include/asm/apicnum.h | 12 ++++++++++++ arch/x86/include/asm/irq_vectors.h | 16 +++++++++++----- include/linux/irqnr.h | 7 +++++++ kernel/irq/handle.c | 3 +++ 5 files changed, 35 insertions(+), 11 deletions(-) create mode 100644 arch/x86/include/asm/apicnum.h (limited to 'kernel/irq') diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 63134e31e8b9..1a6454ef7f6c 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -132,12 +132,8 @@ #define APIC_BASE_MSR 0x800 #define X2APIC_ENABLE (1UL << 10) -#ifdef CONFIG_X86_32 -# define MAX_IO_APICS 64 -#else -# define MAX_IO_APICS 128 -# define MAX_LOCAL_APIC 32768 -#endif +/* get MAX_IO_APICS */ +#include /* * All x86-64 systems are xAPIC compatible. diff --git a/arch/x86/include/asm/apicnum.h b/arch/x86/include/asm/apicnum.h new file mode 100644 index 000000000000..82f613c607ce --- /dev/null +++ b/arch/x86/include/asm/apicnum.h @@ -0,0 +1,12 @@ +#ifndef _ASM_X86_APICNUM_H +#define _ASM_X86_APICNUM_H + +/* define MAX_IO_APICS */ +#ifdef CONFIG_X86_32 +# define MAX_IO_APICS 64 +#else +# define MAX_IO_APICS 128 +# define MAX_LOCAL_APIC 32768 +#endif + +#endif /* _ASM_X86_APICNUM_H */ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index f7ff65032b9d..602361ad0e74 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -105,6 +105,8 @@ #if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER) +#include /* need MAX_IO_APICS */ + #ifndef CONFIG_SPARSE_IRQ # if NR_CPUS < MAX_IO_APICS # define NR_IRQS (NR_VECTORS + (32 * NR_CPUS)) @@ -112,11 +114,15 @@ # define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS)) # endif #else -# if (8 * NR_CPUS) > (32 * MAX_IO_APICS) -# define NR_IRQS (NR_VECTORS + (8 * NR_CPUS)) -# else -# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS)) -# endif + +/* defined as a macro so nr_irqs = max_nr_irqs(nr_cpu_ids) can be used */ +# define max_nr_irqs(nr_cpus) \ + ((8 * nr_cpus) > (32 * MAX_IO_APICS) ? \ + (NR_VECTORS + (8 * NR_CPUS)) : \ + (NR_VECTORS + (32 * MAX_IO_APICS))) \ + +# define NR_IRQS max_nr_irqs(NR_CPUS) + #endif #elif defined(CONFIG_X86_VOYAGER) diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h index 86af92e9e84c..de66e4e10406 100644 --- a/include/linux/irqnr.h +++ b/include/linux/irqnr.h @@ -20,11 +20,18 @@ # define for_each_irq_desc_reverse(irq, desc) \ for (irq = nr_irqs - 1; irq >= 0; irq--) + #else /* CONFIG_GENERIC_HARDIRQS */ +#include /* need possible max_nr_irqs() */ + extern int nr_irqs; extern struct irq_desc *irq_to_desc(unsigned int irq); +# ifndef max_nr_irqs +# define max_nr_irqs(nr_cpus) NR_IRQS +# endif + # define for_each_irq_desc(irq, desc) \ for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs; \ irq++, desc = irq_to_desc(irq)) \ diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index d0b8f7e72790..ebba7a116f14 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -133,6 +133,9 @@ int __init early_irq_init(void) int legacy_count; int i; + /* initialize nr_irqs based on nr_cpu_ids */ + nr_irqs = max_nr_irqs(nr_cpu_ids); + printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs); desc = irq_desc_legacy; -- cgit v1.2.3 From 542d865bbed4ce1f050f586e53cf1cfadda93766 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sat, 10 Jan 2009 22:24:07 -0800 Subject: kstat: modify kstat_irqs_legacy to be variable sized Impact: reduce memory usage. Allocate kstat_irqs_legacy based on nr_cpu_ids to deal with this memory usage bump when NR_CPUS bumped from 128 to 4096: 8192 +253952 262144 +3100% kstat_irqs_legacy(.bss) This is only when CONFIG_SPARSE_IRQS=y. Signed-off-by: Mike Travis --- kernel/irq/handle.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index ebba7a116f14..b39f32ac8f80 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -124,8 +124,7 @@ static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_sm } }; -/* FIXME: use bootmem alloc ...*/ -static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS]; +static unsigned int *kstat_irqs_legacy; int __init early_irq_init(void) { @@ -144,9 +143,14 @@ int __init early_irq_init(void) /* allocate irq_desc_ptrs array based on nr_irqs */ irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *)); + /* allocate based on nr_cpu_ids */ + /* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */ + kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids * + sizeof(int)); + for (i = 0; i < legacy_count; i++) { desc[i].irq = i; - desc[i].kstat_irqs = kstat_irqs_legacy[i]; + desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids; lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); init_alloc_desc_masks(&desc[i], 0, true); irq_desc_ptrs[i] = desc + i; -- cgit v1.2.3 From 92296c6d6e908c35fca287a21af27be814af9c75 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Sun, 11 Jan 2009 09:22:58 -0800 Subject: cpumask, irq: non-x86 build failures Ingo Molnar wrote: > All non-x86 architectures fail to build: > > In file included from /home/mingo/tip/include/linux/random.h:11, > from /home/mingo/tip/include/linux/stackprotector.h:6, > from /home/mingo/tip/init/main.c:17: > /home/mingo/tip/include/linux/irqnr.h:26:63: error: asm/irq_vectors.h: No such file or directory Do not include asm/irq_vectors.h in generic code - it's not available on all architectures. Signed-off-by: Ingo Molnar --- arch/x86/include/asm/apicdef.h | 8 ++++++-- include/linux/irqnr.h | 6 ------ kernel/irq/handle.c | 5 +++++ 3 files changed, 11 insertions(+), 8 deletions(-) (limited to 'kernel/irq') diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 1a6454ef7f6c..63134e31e8b9 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -132,8 +132,12 @@ #define APIC_BASE_MSR 0x800 #define X2APIC_ENABLE (1UL << 10) -/* get MAX_IO_APICS */ -#include +#ifdef CONFIG_X86_32 +# define MAX_IO_APICS 64 +#else +# define MAX_IO_APICS 128 +# define MAX_LOCAL_APIC 32768 +#endif /* * All x86-64 systems are xAPIC compatible. diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h index de66e4e10406..887477bc2ab0 100644 --- a/include/linux/irqnr.h +++ b/include/linux/irqnr.h @@ -23,15 +23,9 @@ #else /* CONFIG_GENERIC_HARDIRQS */ -#include /* need possible max_nr_irqs() */ - extern int nr_irqs; extern struct irq_desc *irq_to_desc(unsigned int irq); -# ifndef max_nr_irqs -# define max_nr_irqs(nr_cpus) NR_IRQS -# endif - # define for_each_irq_desc(irq, desc) \ for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs; \ irq++, desc = irq_to_desc(irq)) \ diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index b39f32ac8f80..04d3e46031e5 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -58,6 +58,11 @@ int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); #ifdef CONFIG_SPARSE_IRQ + +#ifndef max_nr_irqs +#define max_nr_irqs(nr_cpus) NR_IRQS +#endif + static struct irq_desc irq_desc_init = { .irq = -1, .status = IRQ_DISABLED, -- cgit v1.2.3 From 4a046d1754ee6ebb6f399696805ed61ea0444d4c Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 12 Jan 2009 17:39:24 -0800 Subject: x86: arch_probe_nr_irqs Impact: save RAM with large NR_CPUS, get smaller nr_irqs Signed-off-by: Yinghai Lu Signed-off-by: Mike Travis --- arch/x86/include/asm/irq_vectors.h | 7 ++----- arch/x86/kernel/io_apic.c | 16 ++++++++++++++++ include/linux/interrupt.h | 1 + kernel/irq/handle.c | 9 ++------- kernel/softirq.c | 5 +++++ 5 files changed, 26 insertions(+), 12 deletions(-) (limited to 'kernel/irq') diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 602361ad0e74..a16a2ab2b429 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -115,14 +115,11 @@ # endif #else -/* defined as a macro so nr_irqs = max_nr_irqs(nr_cpu_ids) can be used */ -# define max_nr_irqs(nr_cpus) \ - ((8 * nr_cpus) > (32 * MAX_IO_APICS) ? \ +# define NR_IRQS \ + ((8 * NR_CPUS) > (32 * MAX_IO_APICS) ? \ (NR_VECTORS + (8 * NR_CPUS)) : \ (NR_VECTORS + (32 * MAX_IO_APICS))) \ -# define NR_IRQS max_nr_irqs(NR_CPUS) - #endif #elif defined(CONFIG_X86_VOYAGER) diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c index ae80638012de..157986916cd1 100644 --- a/arch/x86/kernel/io_apic.c +++ b/arch/x86/kernel/io_apic.c @@ -3850,6 +3850,22 @@ void __init probe_nr_irqs_gsi(void) nr_irqs_gsi = nr; } +#ifdef CONFIG_SPARSE_IRQ +int __init arch_probe_nr_irqs(void) +{ + int nr; + + nr = ((8 * nr_cpu_ids) > (32 * nr_ioapics) ? + (NR_VECTORS + (8 * nr_cpu_ids)) : + (NR_VECTORS + (32 * nr_ioapics))); + + if (nr < nr_irqs && nr > nr_irqs_gsi) + nr_irqs = nr; + + return 0; +} +#endif + /* -------------------------------------------------------------------------- ACPI-based IOAPIC Configuration -------------------------------------------------------------------------- */ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9127f6b51a39..472f11765f60 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -467,6 +467,7 @@ int show_interrupts(struct seq_file *p, void *v); struct irq_desc; extern int early_irq_init(void); +extern int arch_probe_nr_irqs(void); extern int arch_early_irq_init(void); extern int arch_init_chip_data(struct irq_desc *desc, int cpu); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 04d3e46031e5..375d68cd5bf0 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -59,10 +59,6 @@ EXPORT_SYMBOL_GPL(nr_irqs); #ifdef CONFIG_SPARSE_IRQ -#ifndef max_nr_irqs -#define max_nr_irqs(nr_cpus) NR_IRQS -#endif - static struct irq_desc irq_desc_init = { .irq = -1, .status = IRQ_DISABLED, @@ -137,9 +133,8 @@ int __init early_irq_init(void) int legacy_count; int i; - /* initialize nr_irqs based on nr_cpu_ids */ - nr_irqs = max_nr_irqs(nr_cpu_ids); - + /* 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; diff --git a/kernel/softirq.c b/kernel/softirq.c index bdbe9de9cd8d..0365b4899a3d 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -795,6 +795,11 @@ int __init __weak early_irq_init(void) return 0; } +int __init __weak arch_probe_nr_irqs(void) +{ + return 0; +} + int __init __weak arch_early_irq_init(void) { return 0; -- cgit v1.2.3 From 74296a8ed6aa3c5bf672808ada690de7ba323ecc Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 16 Jan 2009 17:43:50 +0100 Subject: irq: provide debug_poll_all_shared_irqs() method under CONFIG_DEBUG_SHIRQ Provide a shared interrupt debug facility under CONFIG_DEBUG_SHIRQ: it uses the existing irqpoll facilities to iterate through all registered interrupt handlers and call those which can handle shared IRQ lines. This can be handy for suspend/resume debugging: if we call this function early during resume we can trigger crashes in those drivers which have incorrect assumptions about when exactly their ISRs will be called during suspend/resume. Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 6 ++++++ kernel/irq/spurious.c | 14 +++++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'kernel/irq') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 9127f6b51a39..468e3a25a4a1 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -462,6 +462,12 @@ static inline void init_irq_proc(void) } #endif +#if defined(CONFIG_GENERIC_HARDIRQS) && defined(CONFIG_DEBUG_SHIRQ) +extern void debug_poll_all_shared_irqs(void); +#else +static inline void debug_poll_all_shared_irqs(void) { } +#endif + int show_interrupts(struct seq_file *p, void *v); struct irq_desc; diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index dd364c11e56e..4d568294de3e 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -104,7 +104,7 @@ static int misrouted_irq(int irq) return ok; } -static void poll_spurious_irqs(unsigned long dummy) +static void poll_all_shared_irqs(void) { struct irq_desc *desc; int i; @@ -123,11 +123,23 @@ static void poll_spurious_irqs(unsigned long dummy) try_one_irq(i, desc); } +} + +static void poll_spurious_irqs(unsigned long dummy) +{ + poll_all_shared_irqs(); mod_timer(&poll_spurious_irq_timer, jiffies + POLL_SPURIOUS_IRQ_INTERVAL); } +#ifdef CONFIG_DEBUG_SHIRQ +void debug_poll_all_shared_irqs(void) +{ + poll_all_shared_irqs(); +} +#endif + /* * 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 -- cgit v1.2.3 From 0f3c2a89c1451cdf6328f99977bd9decd4f708e1 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 8 Feb 2009 16:18:03 -0800 Subject: irq: clear kstat_irqs Impact: get correct kstat_irqs [/proc/interrupts] for msi/msi-x etc need to call clear_kstat_irqs(), so when we reuse that irq_desc, we get correct kstat in /proc/interrupts. This makes /proc/interrupts not have entries. Don't need to worry about arch that doesn't support genirq, because they will not call dynamic_irq_cleanup(). v2: simplify and make clear_kstat_irqs more robust Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- kernel/irq/chip.c | 1 + kernel/irq/handle.c | 5 +++++ kernel/irq/internals.h | 1 + 3 files changed, 7 insertions(+) (limited to 'kernel/irq') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index f63c706d25e1..1310856cb22b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -78,6 +78,7 @@ void dynamic_irq_cleanup(unsigned int irq) desc->handle_irq = handle_bad_irq; desc->chip = &no_irq_chip; desc->name = NULL; + clear_kstat_irqs(desc); spin_unlock_irqrestore(&desc->lock, flags); } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 48299a8a22f8..1b473e7569aa 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -242,6 +242,11 @@ struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu) } #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. diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index e6d0a43cc125..b60950bf5a16 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -15,6 +15,7 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, extern struct lock_class_key irq_desc_lock_class; extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr); +extern void clear_kstat_irqs(struct irq_desc *desc); extern spinlock_t sparse_irq_lock; extern struct irq_desc *irq_desc_ptrs[NR_IRQS]; -- cgit v1.2.3 From 005bf0e6fa0e9543933fe2e36322af649df7cacb Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Sun, 8 Feb 2009 16:18:03 -0800 Subject: irq: optimize init_kstat_irqs/init_copy_kstat_irqs Simplify and make init_kstat_irqs etc more type proof, suggested by Andrew. Signed-off-by: Yinghai Lu Signed-off-by: Ingo Molnar --- kernel/irq/handle.c | 20 +++++++++++--------- kernel/irq/numa_migrate.c | 11 +++-------- 2 files changed, 14 insertions(+), 17 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 1b473e7569aa..49d642b62c64 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -71,19 +71,21 @@ static struct irq_desc irq_desc_init = { void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr) { - unsigned long bytes; - char *ptr; int node; - - /* Compute how many bytes we need per irq and allocate them */ - bytes = nr * sizeof(unsigned int); + void *ptr; node = cpu_to_node(cpu); - ptr = kzalloc_node(bytes, GFP_ATOMIC, node); - printk(KERN_DEBUG " alloc kstat_irqs on cpu %d node %d\n", cpu, node); + ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), GFP_ATOMIC, node); - if (ptr) - desc->kstat_irqs = (unsigned int *)ptr; + /* + * 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 cpu %d node %d\n", + cpu, node); + desc->kstat_irqs = ptr; + } } static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu) diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c index ecf765c6a77a..c500cfe422b6 100644 --- a/kernel/irq/numa_migrate.c +++ b/kernel/irq/numa_migrate.c @@ -17,16 +17,11 @@ static void init_copy_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc, int cpu, int nr) { - unsigned long bytes; - init_kstat_irqs(desc, cpu, nr); - if (desc->kstat_irqs != old_desc->kstat_irqs) { - /* Compute how many bytes we need per irq and allocate them */ - bytes = nr * sizeof(unsigned int); - - memcpy(desc->kstat_irqs, old_desc->kstat_irqs, bytes); - } + 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) -- cgit v1.2.3 From 548c8933801c9ee347b6f1bad2491e4286a4f3a2 Mon Sep 17 00:00:00 2001 From: Hannes Eder Date: Sun, 8 Feb 2009 20:24:47 +0100 Subject: kernel/irq: fix sparse warning: make symbol static While being at it make every occurrence of 'do_irq_select_affinity' have the same signature in terms of signedness of the first argument. Fix this sparse warning: kernel/irq/manage.c:112:5: warning: symbol 'do_irq_select_affinity' was not declared. Should it be static? Also rename do_irq_select_affinity() to setup_affinity() - shorter name and clearer naming. Signed-off-by: Hannes Eder Acked-by: Matthew Wilcox Signed-off-by: Ingo Molnar --- kernel/irq/manage.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 291f03664552..38008b80bd59 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -109,7 +109,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) /* * Generic version of the affinity autoselector. */ -int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc) +static int setup_affinity(unsigned int irq, struct irq_desc *desc) { if (!irq_can_set_affinity(irq)) return 0; @@ -133,7 +133,7 @@ set_affinity: return 0; } #else -static inline int do_irq_select_affinity(unsigned int irq, struct irq_desc *d) +static inline int setup_affinity(unsigned int irq, struct irq_desc *d) { return irq_select_affinity(irq); } @@ -149,14 +149,14 @@ int irq_select_affinity_usr(unsigned int irq) int ret; spin_lock_irqsave(&desc->lock, flags); - ret = do_irq_select_affinity(irq, desc); + ret = setup_affinity(irq, desc); spin_unlock_irqrestore(&desc->lock, flags); return ret; } #else -static inline int do_irq_select_affinity(int irq, struct irq_desc *desc) +static inline int setup_affinity(unsigned int irq, struct irq_desc *desc) { return 0; } @@ -488,7 +488,7 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) desc->status |= IRQ_NO_BALANCING; /* Set default affinity mask once everything is setup */ - do_irq_select_affinity(irq, desc); + setup_affinity(irq, desc); } else if ((new->flags & IRQF_TRIGGER_MASK) && (new->flags & IRQF_TRIGGER_MASK) -- cgit v1.2.3 From 0e43785c57fee50fbc00ea0378e941efb61fa0c2 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 13 Feb 2009 04:38:04 +0100 Subject: irq: use GFP_KERNEL for action allocation in request_irq() request_irq() calls into proc code via __setup_irq() which is not safe in an atomic context, so request_irq() can itself use the more reliable GFP_KERNEL allocation for the action descriptor. Signed-off-by: Johannes Weiner Signed-off-by: Ingo Molnar --- kernel/irq/manage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index cd0cd8dcb345..1c5055069170 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -717,7 +717,7 @@ int request_irq(unsigned int irq, irq_handler_t handler, if (!handler) return -EINVAL; - action = kmalloc(sizeof(struct irqaction), GFP_ATOMIC); + action = kmalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; -- cgit v1.2.3 From 327ec5699c29454322d0136375f717f509c145b6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 15 Feb 2009 11:21:37 +0100 Subject: irq: clean up manage.c - make printk message git-greppable - fix a few style details Signed-off-by: Ingo Molnar --- kernel/irq/manage.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1c5055069170..8f4bc61f0df9 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -397,7 +397,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, * allocate special interrupts that are part of the architecture. */ static int -__setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new) +__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) { struct irqaction *old, **p; const char *old_name = NULL; @@ -687,11 +687,12 @@ int request_irq(unsigned int irq, irq_handler_t handler, * 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); + 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 /* -- cgit v1.2.3 From ae88a23b32fa7e0dc9fa7ce735966e68eb41b0bc Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 15 Feb 2009 11:29:50 +0100 Subject: irq: refactor and clean up the free_irq() code flow Impact: cleanup - separate out the loop from the actual freeing logic, this wins us two indentation levels allowing a number of followup prettifications - turn the WARN_ON() into a more informative WARN(). - clean up the comments and the code flow some more Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- kernel/irq/manage.c | 101 ++++++++++++++++++++++++++++------------------------ 1 file changed, 54 insertions(+), 47 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 8f4bc61f0df9..7a954b860c07 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -575,72 +575,79 @@ int setup_irq(unsigned int irq, struct irqaction *act) void free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); - struct irqaction **p; + struct irqaction *action, **p, **pp; unsigned long flags; - WARN_ON(in_interrupt()); + WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); if (!desc) return; spin_lock_irqsave(&desc->lock, flags); + + /* + * There can be multiple actions per IRQ descriptor, find the right + * one based on the dev_id: + */ p = &desc->action; for (;;) { - struct irqaction *action = *p; + action = *p; + pp = p; + + if (!action) { + WARN(1, "Trying to free already-free IRQ %d\n", irq); + spin_unlock_irqrestore(&desc->lock, flags); + + return; + } - if (action) { - struct irqaction **pp = p; + p = &action->next; + if (action->dev_id != dev_id) + continue; - p = &action->next; - if (action->dev_id != dev_id) - continue; + break; + } - /* Found it - now remove it from the list of entries */ - *pp = action->next; + /* Found it - now remove it from the list of entries: */ + *pp = action->next; - /* Currently used only by UML, might disappear one day.*/ + /* Currently used only by UML, might disappear one day: */ #ifdef CONFIG_IRQ_RELEASE_METHOD - if (desc->chip->release) - desc->chip->release(irq, dev_id); + if (desc->chip->release) + desc->chip->release(irq, dev_id); #endif - if (!desc->action) { - desc->status |= IRQ_DISABLED; - if (desc->chip->shutdown) - desc->chip->shutdown(irq); - else - desc->chip->disable(irq); - } - spin_unlock_irqrestore(&desc->lock, flags); - unregister_handler_proc(irq, action); + /* 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); + } + spin_unlock_irqrestore(&desc->lock, flags); + + unregister_handler_proc(irq, action); + + /* Make sure it's not being used on another CPU: */ + synchronize_irq(irq); - /* Make sure it's not being used on another CPU */ - synchronize_irq(irq); -#ifdef CONFIG_DEBUG_SHIRQ - /* - * It's a shared IRQ -- the driver ought to be - * prepared for it to happen even now it's - * being freed, so let's make sure.... We do - * this after actually deregistering it, to - * make sure that a 'real' IRQ doesn't run in - * parallel with our fake - */ - if (action->flags & IRQF_SHARED) { - local_irq_save(flags); - action->handler(irq, dev_id); - local_irq_restore(flags); - } -#endif - kfree(action); - return; - } - printk(KERN_ERR "Trying to free already-free IRQ %d\n", irq); #ifdef CONFIG_DEBUG_SHIRQ - dump_stack(); -#endif - spin_unlock_irqrestore(&desc->lock, flags); - return; + /* + * It's a shared IRQ -- the driver ought to be prepared for an IRQ + * event to happen even now it's being freed, so let's make sure that + * is so by doing an extra call to the handler .... + * + * ( We do this after actually deregistering it, to make sure that a + * 'real' IRQ doesn't run in * parallel with our fake. ) + */ + if (action->flags & IRQF_SHARED) { + local_irq_save(flags); + action->handler(irq, dev_id); + local_irq_restore(flags); } +#endif + kfree(action); } EXPORT_SYMBOL(free_irq); -- cgit v1.2.3 From 8316e38100c70cd1443ac90074eccdd033aa218d Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 17 Feb 2009 20:28:29 +0100 Subject: irq: further clean up the free_irq() code flow Linus noticed that the 'pp' variable can be eliminated altogether, and the loop can be cleaned up further. Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- kernel/irq/manage.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 7a954b860c07..de5a765e88ab 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -575,7 +575,7 @@ int setup_irq(unsigned int irq, struct irqaction *act) void free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); - struct irqaction *action, **p, **pp; + struct irqaction *action, **p; unsigned long flags; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); @@ -592,7 +592,6 @@ void free_irq(unsigned int irq, void *dev_id) p = &desc->action; for (;;) { action = *p; - pp = p; if (!action) { WARN(1, "Trying to free already-free IRQ %d\n", irq); @@ -601,15 +600,13 @@ void free_irq(unsigned int irq, void *dev_id) return; } + if (action->dev_id == dev_id) + break; p = &action->next; - if (action->dev_id != dev_id) - continue; - - break; } /* Found it - now remove it from the list of entries: */ - *pp = action->next; + *p = action->next; /* Currently used only by UML, might disappear one day: */ #ifdef CONFIG_IRQ_RELEASE_METHOD -- cgit v1.2.3 From f17c75453b2d195eba0a90d9f16a3ba88c85b3b4 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 17 Feb 2009 20:43:37 +0100 Subject: irq: name 'p' variables a bit better 'p' stands for pointer - make it clear in setup_irq() and free_irq() what kind of pointer it is. Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- kernel/irq/manage.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index de5a765e88ab..c589305210d7 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -399,7 +399,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, static int __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) { - struct irqaction *old, **p; + struct irqaction *old, **old_ptr; const char *old_name = NULL; unsigned long flags; int shared = 0; @@ -431,8 +431,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * The following block of code has to be executed atomically */ spin_lock_irqsave(&desc->lock, flags); - p = &desc->action; - old = *p; + old_ptr = &desc->action; + old = *old_ptr; if (old) { /* * Can't share interrupts unless both agree to and are @@ -455,8 +455,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) /* add new interrupt at end of irq queue */ do { - p = &old->next; - old = *p; + old_ptr = &old->next; + old = *old_ptr; } while (old); shared = 1; } @@ -507,7 +507,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) (int)(new->flags & IRQF_TRIGGER_MASK)); } - *p = new; + *old_ptr = new; /* Reset broken irq detection when installing new handler */ desc->irq_count = 0; @@ -575,7 +575,7 @@ int setup_irq(unsigned int irq, struct irqaction *act) void free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); - struct irqaction *action, **p; + struct irqaction *action, **action_ptr; unsigned long flags; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); @@ -589,9 +589,9 @@ void free_irq(unsigned int irq, void *dev_id) * There can be multiple actions per IRQ descriptor, find the right * one based on the dev_id: */ - p = &desc->action; + action_ptr = &desc->action; for (;;) { - action = *p; + action = *action_ptr; if (!action) { WARN(1, "Trying to free already-free IRQ %d\n", irq); @@ -602,11 +602,11 @@ void free_irq(unsigned int irq, void *dev_id) if (action->dev_id == dev_id) break; - p = &action->next; + action_ptr = &action->next; } /* Found it - now remove it from the list of entries: */ - *p = action->next; + *action_ptr = action->next; /* Currently used only by UML, might disappear one day: */ #ifdef CONFIG_IRQ_RELEASE_METHOD -- cgit v1.2.3 From af39241b90a345556b8884adff87096afe71b050 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 26 Feb 2009 10:11:05 -0500 Subject: tracing, genirq: add irq enter and exit trace events Impact: add new tracepoints Add them to the generic IRQ code, that way every architecture gets these new tracepoints, not just x86. Using Steve's new 'TRACE_FORMAT', I can get function graph trace as follows using the original two IRQ tracepoints: 3) | handle_IRQ_event() { 3) | /* (irq_handler_entry) irq=28 handler=eth0 */ 3) | e1000_intr_msi() { 3) 2.460 us | __napi_schedule(); 3) 9.416 us | } 3) | /* (irq_handler_exit) irq=28 handler=eth0 return=handled */ 3) + 22.935 us | } Signed-off-by: Jason Baron Signed-off-by: Steven Rostedt Acked-by: Peter Zijlstra Acked-by: Masami Hiramatsu Cc: KOSAKI Motohiro Cc: Mathieu Desnoyers Cc: "Frank Ch. Eigler" Cc: Arnaldo Carvalho de Melo Cc: Frederic Weisbecker Signed-off-by: Ingo Molnar --- include/trace/irq.h | 9 +++++++++ include/trace/irq_event_types.h | 17 +++++++++++++++++ kernel/irq/handle.c | 6 ++++++ kernel/trace/events.c | 2 ++ 4 files changed, 34 insertions(+) create mode 100644 include/trace/irq.h create mode 100644 include/trace/irq_event_types.h (limited to 'kernel/irq') diff --git a/include/trace/irq.h b/include/trace/irq.h new file mode 100644 index 000000000000..ff5d4495dc37 --- /dev/null +++ b/include/trace/irq.h @@ -0,0 +1,9 @@ +#ifndef _TRACE_IRQ_H +#define _TRACE_IRQ_H + +#include +#include + +#include + +#endif diff --git a/include/trace/irq_event_types.h b/include/trace/irq_event_types.h new file mode 100644 index 000000000000..5d0919fdd2d4 --- /dev/null +++ b/include/trace/irq_event_types.h @@ -0,0 +1,17 @@ + +/* use instead */ +#ifndef TRACE_FORMAT +# error Do not include this file directly. +# error Unless you know what you are doing. +#endif + +TRACE_FORMAT(irq_handler_entry, + TPPROTO(int irq, struct irqaction *action), + TPARGS(irq, action), + TPFMT("irq=%d handler=%s", irq, action->name)); + +TRACE_FORMAT(irq_handler_exit, + TPPROTO(int irq, struct irqaction *action, int ret), + TPARGS(irq, action, ret), + TPFMT("irq=%d handler=%s return=%s", + irq, action->name, ret ? "handled" : "unhandled")); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 3aba8d12f328..4709a7c870d7 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "internals.h" @@ -316,6 +317,9 @@ irqreturn_t no_action(int cpl, void *dev_id) return IRQ_NONE; } +DEFINE_TRACE(irq_handler_entry); +DEFINE_TRACE(irq_handler_exit); + /** * handle_IRQ_event - irq action chain handler * @irq: the interrupt number @@ -332,7 +336,9 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) local_irq_enable_in_hardirq(); do { + trace_irq_handler_entry(irq, action); ret = action->handler(irq, action->dev_id); + trace_irq_handler_exit(irq, action, ret); if (ret == IRQ_HANDLED) status |= action->flags; retval |= ret; diff --git a/kernel/trace/events.c b/kernel/trace/events.c index 38c89eef99ee..3c75623893cc 100644 --- a/kernel/trace/events.c +++ b/kernel/trace/events.c @@ -6,8 +6,10 @@ /* trace/.h here */ #include +#include #include "trace_events.h" /* trace/_event_types.h here */ #include +#include -- cgit v1.2.3 From 044d408409cc4e1bc75c886e27ca85c270db104c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 2 Mar 2009 16:13:32 +0100 Subject: genirq: assert that irq handlers are indeed running in hardirq context Make sure the genirq layer handlers are indeed running handlers in hardirq context. That is the genirq expectation and doing anything else is broken. Signed-off-by: Peter Zijlstra Cc: Andrew Morton LKML-Reference: <1236006812.5330.632.camel@laptop> Signed-off-by: Ingo Molnar --- kernel/irq/handle.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/irq') diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 3aba8d12f328..a2ee682bca2e 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -328,6 +328,8 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) irqreturn_t ret, retval = IRQ_NONE; unsigned int status = 0; + WARN_ONCE(!in_irq(), "BUG: IRQ handler called from non-hardirq context!"); + if (!(action->flags & IRQF_DISABLED)) local_irq_enable_in_hardirq(); -- cgit v1.2.3 From f21cfb258df6dd3ea0b3e56d75c7e994edb81b35 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Thu, 12 Mar 2009 21:05:42 +0900 Subject: irq: add remove_irq() for freeing of setup_irq() irqs Impact: add new API This patch adds a remove_irq() function for releasing interrupts requested with setup_irq(). Without this patch we have no way of releasing such interrupts since free_irq() today tries to kfree() the irqaction passed with setup_irq(). Signed-off-by: Magnus Damm LKML-Reference: <20090312120542.2926.56609.sendpatchset@rx1.opensource.se> Signed-off-by: Ingo Molnar --- include/linux/irq.h | 1 + kernel/irq/manage.c | 39 ++++++++++++++++++++++++++------------- 2 files changed, 27 insertions(+), 13 deletions(-) (limited to 'kernel/irq') diff --git a/include/linux/irq.h b/include/linux/irq.h index f899b502f186..56f9988362ec 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -236,6 +236,7 @@ typedef struct irq_desc irq_desc_t; #include extern int setup_irq(unsigned int irq, struct irqaction *new); +extern struct irqaction *remove_irq(unsigned int irq, void *dev_id); #ifdef CONFIG_GENERIC_HARDIRQS diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 52ee17135092..8b069a7046e9 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -551,20 +551,14 @@ int setup_irq(unsigned int irq, struct irqaction *act) } /** - * free_irq - free an interrupt + * remove_irq - free an interrupt * @irq: Interrupt line to free * @dev_id: Device identity to free * - * Remove an interrupt handler. The handler is removed and if the - * interrupt line is no longer in use by any driver it is disabled. - * On a shared IRQ the caller must ensure the interrupt is disabled - * on the card it drives 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. + * Used to remove interrupts statically setup by the early boot process. */ -void free_irq(unsigned int irq, void *dev_id) + +struct irqaction *remove_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action, **action_ptr; @@ -573,7 +567,7 @@ void free_irq(unsigned int irq, void *dev_id) WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); if (!desc) - return; + return NULL; spin_lock_irqsave(&desc->lock, flags); @@ -589,7 +583,7 @@ void free_irq(unsigned int irq, void *dev_id) WARN(1, "Trying to free already-free IRQ %d\n", irq); spin_unlock_irqrestore(&desc->lock, flags); - return; + return NULL; } if (action->dev_id == dev_id) @@ -636,7 +630,26 @@ void free_irq(unsigned int irq, void *dev_id) local_irq_restore(flags); } #endif - kfree(action); + return action; +} + +/** + * free_irq - free an interrupt allocated with request_irq + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Remove an interrupt handler. The handler is removed and if the + * interrupt line is no longer in use by any driver it is disabled. + * On a shared IRQ the caller must ensure the interrupt is disabled + * on the card it drives 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_irq(unsigned int irq, void *dev_id) +{ + kfree(remove_irq(irq, dev_id)); } EXPORT_SYMBOL(free_irq); -- cgit v1.2.3 From cbf94f06824780183e4bba165c7c29d5c7bd9a51 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Thu, 12 Mar 2009 21:05:51 +0900 Subject: irq: match remove_irq() args with setup_irq() Modify remove_irq() to match setup_irq(). Signed-off-by: Magnus Damm LKML-Reference: <20090312120551.2926.43942.sendpatchset@rx1.opensource.se> Signed-off-by: Ingo Molnar --- include/linux/irq.h | 2 +- kernel/irq/manage.c | 26 +++++++++++++++++--------- 2 files changed, 18 insertions(+), 10 deletions(-) (limited to 'kernel/irq') diff --git a/include/linux/irq.h b/include/linux/irq.h index 56f9988362ec..737eafbc1f3d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -236,7 +236,7 @@ typedef struct irq_desc irq_desc_t; #include extern int setup_irq(unsigned int irq, struct irqaction *new); -extern struct irqaction *remove_irq(unsigned int irq, void *dev_id); +extern void remove_irq(unsigned int irq, struct irqaction *act); #ifdef CONFIG_GENERIC_HARDIRQS diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 8b069a7046e9..fc16570c9b46 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -550,15 +550,11 @@ int setup_irq(unsigned int irq, struct irqaction *act) return __setup_irq(irq, desc, act); } -/** - * remove_irq - free an interrupt - * @irq: Interrupt line to free - * @dev_id: Device identity to free - * - * Used to remove interrupts statically setup by the early boot process. + /* + * Internal function to unregister an irqaction - used to free + * regular and special interrupts that are part of the architecture. */ - -struct irqaction *remove_irq(unsigned int irq, void *dev_id) +static struct irqaction *__free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action, **action_ptr; @@ -633,6 +629,18 @@ struct irqaction *remove_irq(unsigned int irq, void *dev_id) return action; } +/** + * remove_irq - free an interrupt + * @irq: Interrupt line to free + * @act: irqaction for the interrupt + * + * Used to remove interrupts statically setup by the early boot process. + */ +void remove_irq(unsigned int irq, struct irqaction *act) +{ + __free_irq(irq, act->dev_id); +} + /** * free_irq - free an interrupt allocated with request_irq * @irq: Interrupt line to free @@ -649,7 +657,7 @@ struct irqaction *remove_irq(unsigned int irq, void *dev_id) */ void free_irq(unsigned int irq, void *dev_id) { - kfree(remove_irq(irq, dev_id)); + kfree(__free_irq(irq, dev_id)); } EXPORT_SYMBOL(free_irq); -- cgit v1.2.3 From eb53b4e8fef10ccccb49a6dbb5e19ca84ba5a305 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Thu, 12 Mar 2009 21:05:59 +0900 Subject: irq: export remove_irq() and setup_irq() symbols Export the setup_irq() and remove_irq() symbols. I'd like to export these functions since I have timer code that needs to use setup_irq() early on (too early for request_irq()), and the same code can also be compiled as a module. Signed-off-by: Magnus Damm LKML-Reference: <20090312120559.2926.82371.sendpatchset@rx1.opensource.se> [ changed to _GPL as these are special APIs deep inside the irq layer. ] Signed-off-by: Ingo Molnar --- kernel/irq/manage.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index fc16570c9b46..e28db0f656ac 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -549,6 +549,7 @@ int setup_irq(unsigned int irq, struct irqaction *act) return __setup_irq(irq, desc, act); } +EXPORT_SYMBOL_GPL(setup_irq); /* * Internal function to unregister an irqaction - used to free @@ -640,6 +641,7 @@ void remove_irq(unsigned int irq, struct irqaction *act) { __free_irq(irq, act->dev_id); } +EXPORT_SYMBOL_GPL(remove_irq); /** * free_irq - free an interrupt allocated with request_irq -- cgit v1.2.3 From c8e2aeef0b8ac9fb8821b8b3734c031579d0b77a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 9 Mar 2009 20:26:23 +0100 Subject: genirq: remove redundant if condition Impact: cleanup The code is only compiled if CONFIG_GENERIC_HARDIRQS=y so another check for this define in the code is redundant. Remove it. Signed-off-by: Thomas Gleixner --- kernel/irq/manage.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e28db0f656ac..4600f877c292 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -15,7 +15,7 @@ #include "internals.h" -#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) +#ifdef CONFIG_SMP cpumask_var_t irq_default_affinity; /** -- cgit v1.2.3 From 4553573277906901f62f73c0432b332c53de5e2c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 22 Feb 2009 23:00:32 +0100 Subject: genirq: use kzalloc instead of explicit zero initialization Impact: simplification Signed-off-by: Thomas Gleixner Reviewed-by: Peter Zijlstra --- kernel/irq/manage.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel/irq') diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 4600f877c292..8a22039a90ba 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -737,15 +737,13 @@ int request_irq(unsigned int irq, irq_handler_t handler, if (!handler) return -EINVAL; - action = kmalloc(sizeof(struct irqaction), GFP_KERNEL); + action = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!action) return -ENOMEM; action->handler = handler; action->flags = irqflags; - cpus_clear(action->mask); action->name = devname; - action->next = NULL; action->dev_id = dev_id; retval = __setup_irq(irq, desc, action); -- cgit v1.2.3 From 0e57aa11abb15b70db53d1f95ae70b3c980ac885 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 13 Mar 2009 14:34:05 +0100 Subject: genirq: deprecate __do_IRQ Two years migration time is enough. Remove the compability cruft. Add the deprecated warning in kernel/irq/handle.c because marking __do_IRQ itself is way too noisy. Signed-off-by: Thomas Gleixner --- Documentation/feature-removal-schedule.txt | 8 ++++++++ kernel/irq/handle.c | 5 +++++ 2 files changed, 13 insertions(+) (limited to 'kernel/irq') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 20d3b94703a4..63b4550411be 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -344,3 +344,11 @@ Why: See commits 129f8ae9b1b5be94517da76009ea956e89104ce8 and Removal is subject to fixing any remaining bugs in ACPI which may cause the thermal throttling not to happen at the right time. Who: Dave Jones , Matthew Garrett + +----------------------------- + +What: __do_IRQ all in one fits nothing interrupt handler +When: 2.6.32 +Why: __do_IRQ was kept for easy migration to the type flow handlers. + More than two years of migration time is enough. +Who: Thomas Gleixner diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a2ee682bca2e..6661704140c7 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -349,6 +349,11 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) } #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 -- cgit v1.2.3 From 3aa551c9b4c40018f0e261a178e3d25478dc04a9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 23 Mar 2009 18:28:15 +0100 Subject: genirq: add threaded interrupt handler support Add support for threaded interrupt handlers: A device driver can request that its main interrupt handler runs in a thread. To achive this the device driver requests the interrupt with request_threaded_irq() and provides additionally to the handler a thread function. The handler function is called in hard interrupt context and needs to check whether the interrupt originated from the device. If the interrupt originated from the device then the handler can either return IRQ_HANDLED or IRQ_WAKE_THREAD. IRQ_HANDLED is returned when no further action is required. IRQ_WAKE_THREAD causes the genirq code to invoke the threaded (main) handler. When IRQ_WAKE_THREAD is returned handler must have disabled the interrupt on the device level. This is mandatory for shared interrupt handlers, but we need to do it as well for obscure x86 hardware where disabling an interrupt on the IO_APIC level redirects the interrupt to the legacy PIC interrupt lines. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar --- include/linux/hardirq.h | 2 +- include/linux/interrupt.h | 37 ++++++++- include/linux/irq.h | 5 ++ include/linux/irqreturn.h | 2 + include/linux/sched.h | 5 ++ kernel/exit.c | 2 + kernel/irq/handle.c | 31 +++++++- kernel/irq/manage.c | 192 ++++++++++++++++++++++++++++++++++++++++++---- 8 files changed, 259 insertions(+), 17 deletions(-) (limited to 'kernel/irq') diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index f83288347dda..2dfaadbdb2ac 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -105,7 +105,7 @@ # define IRQ_EXIT_OFFSET HARDIRQ_OFFSET #endif -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS) extern void synchronize_irq(unsigned int irq); #else # define synchronize_irq(irq) barrier() diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 0c9cb63e6895..6fc2b720c231 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -59,6 +59,16 @@ #define IRQF_NOBALANCING 0x00000800 #define IRQF_IRQPOLL 0x00001000 +/* + * Bits used by threaded handlers: + * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run + * IRQTF_DIED - handler thread died + */ +enum { + IRQTF_RUNTHREAD, + IRQTF_DIED, +}; + typedef irqreturn_t (*irq_handler_t)(int, void *); /** @@ -71,6 +81,9 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * @next: pointer to the next irqaction for shared interrupts * @irq: interrupt number * @dir: pointer to the proc/irq/NN/name entry + * @thread_fn: interupt handler function for threaded interrupts + * @thread: thread pointer for threaded interrupts + * @thread_flags: flags related to @thread */ struct irqaction { irq_handler_t handler; @@ -81,11 +94,31 @@ struct irqaction { struct irqaction *next; int irq; struct proc_dir_entry *dir; + irq_handler_t thread_fn; + struct task_struct *thread; + unsigned long thread_flags; }; extern irqreturn_t no_action(int cpl, void *dev_id); -extern int __must_check request_irq(unsigned int, irq_handler_t handler, - unsigned long, const char *, void *); + +extern int __must_check +request_threaded_irq(unsigned int irq, irq_handler_t handler, + irq_handler_t thread_fn, + unsigned long flags, const char *name, void *dev); + +static inline int __must_check +request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, + const char *name, void *dev) +{ + return request_threaded_irq(irq, handler, NULL, flags, name, dev); +} + +#ifdef CONFIG_GENERIC_HARDIRQS +extern void exit_irq_thread(void); +#else +static inline void exit_irq_thread(void) { } +#endif + extern void free_irq(unsigned int, void *); struct device; diff --git a/include/linux/irq.h b/include/linux/irq.h index 873e4ac11b81..8b1cf0630210 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -155,6 +156,8 @@ struct irq_2_iommu; * @affinity: IRQ affinity on SMP * @cpu: cpu index useful for balancing * @pending_mask: pending rebalanced interrupts + * @threads_active: number of irqaction threads currently running + * @wait_for_threads: wait queue for sync_irq to wait for threaded handlers * @dir: /proc/irq/ procfs entry * @name: flow handler name for /proc/interrupts output */ @@ -186,6 +189,8 @@ struct irq_desc { cpumask_var_t pending_mask; #endif #endif + atomic_t threads_active; + wait_queue_head_t wait_for_threads; #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; #endif diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h index c5584ca5b8c9..819acaaac3f5 100644 --- a/include/linux/irqreturn.h +++ b/include/linux/irqreturn.h @@ -5,10 +5,12 @@ * enum irqreturn * @IRQ_NONE interrupt was not from this device * @IRQ_HANDLED interrupt was handled by this device + * @IRQ_WAKE_THREAD handler requests to wake the handler thread */ enum irqreturn { IRQ_NONE, IRQ_HANDLED, + IRQ_WAKE_THREAD, }; typedef enum irqreturn irqreturn_t; diff --git a/include/linux/sched.h b/include/linux/sched.h index 46d680643f89..38b77b0f56e5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1292,6 +1292,11 @@ struct task_struct { /* Protection of (de-)allocation: mm, files, fs, tty, keyrings */ spinlock_t alloc_lock; +#ifdef CONFIG_GENERIC_HARDIRQS + /* IRQ handler threads */ + struct irqaction *irqaction; +#endif + /* Protection of the PI data structures: */ spinlock_t pi_lock; diff --git a/kernel/exit.c b/kernel/exit.c index 167e1e3ad7c6..ca0b3488c4a9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1037,6 +1037,8 @@ NORET_TYPE void do_exit(long code) schedule(); } + exit_irq_thread(); + exit_signals(tsk); /* sets PF_EXITING */ /* * tsk->flags are checked in the futex code to protect against diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 9ebf77968871..fe8f45374e86 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -357,8 +357,37 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) do { ret = action->handler(irq, action->dev_id); - if (ret == IRQ_HANDLED) + + switch (ret) { + case IRQ_WAKE_THREAD: + /* + * 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); + } + + /* + * Set it to handled so the spurious check + * does not trigger. + */ + ret = IRQ_HANDLED; + /* Fall through to add to randomness */ + case IRQ_HANDLED: status |= action->flags; + break; + + default: + break; + } + retval |= ret; action = action->next; } while (action); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 6458e99984c0..a4c1ab86cd25 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -8,16 +8,15 @@ */ #include +#include #include #include #include #include +#include #include "internals.h" -#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) -cpumask_var_t irq_default_affinity; - /** * synchronize_irq - wait for pending IRQ handlers (on other CPUs) * @irq: interrupt number to wait for @@ -53,9 +52,18 @@ void synchronize_irq(unsigned int irq) /* Oops, that failed? */ } while (status & IRQ_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)); } EXPORT_SYMBOL(synchronize_irq); +#ifdef CONFIG_SMP +cpumask_var_t irq_default_affinity; + /** * irq_can_set_affinity - Check if the affinity of a given irq can be set * @irq: Interrupt to check @@ -72,6 +80,18 @@ int irq_can_set_affinity(unsigned int irq) return 1; } +static void +irq_set_thread_affinity(struct irq_desc *desc, const struct cpumask *cpumask) +{ + struct irqaction *action = desc->action; + + while (action) { + if (action->thread) + set_cpus_allowed_ptr(action->thread, cpumask); + action = action->next; + } +} + /** * irq_set_affinity - Set the irq affinity of a given irq * @irq: Interrupt to set affinity @@ -100,6 +120,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) cpumask_copy(desc->affinity, cpumask); desc->chip->set_affinity(irq, cpumask); #endif + irq_set_thread_affinity(desc, cpumask); desc->status |= IRQ_AFFINITY_SET; spin_unlock_irqrestore(&desc->lock, flags); return 0; @@ -150,6 +171,8 @@ int irq_select_affinity_usr(unsigned int irq) spin_lock_irqsave(&desc->lock, flags); ret = setup_affinity(irq, desc); + if (!ret) + irq_set_thread_affinity(desc, desc->affinity); spin_unlock_irqrestore(&desc->lock, flags); return ret; @@ -384,6 +407,93 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, return ret; } +static inline int irq_thread_should_run(struct irqaction *action) +{ + return test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags); +} + +static int irq_wait_for_interrupt(struct irqaction *action) +{ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + if (irq_thread_should_run(action)) { + __set_current_state(TASK_RUNNING); + return 0; + } else + schedule(); + } + return -1; +} + +/* + * Interrupt handler thread + */ +static int irq_thread(void *data) +{ + struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, }; + struct irqaction *action = data; + struct irq_desc *desc = irq_to_desc(action->irq); + int wake; + + sched_setscheduler(current, SCHED_FIFO, ¶m); + current->irqaction = action; + + while (!irq_wait_for_interrupt(action)) { + + atomic_inc(&desc->threads_active); + + 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; + spin_unlock_irq(&desc->lock); + } else { + spin_unlock_irq(&desc->lock); + + action->thread_fn(action->irq, action->dev_id); + } + + wake = atomic_dec_and_test(&desc->threads_active); + + if (wake && waitqueue_active(&desc->wait_for_threads)) + wake_up(&desc->wait_for_threads); + } + + /* + * Clear irqaction. Otherwise exit_irq_thread() would make + * fuzz about an active irq thread going into nirvana. + */ + current->irqaction = NULL; + return 0; +} + +/* + * Called from do_exit() + */ +void exit_irq_thread(void) +{ + struct task_struct *tsk = current; + + if (!tsk->irqaction) + 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); + + /* + * Set the THREAD DIED flag to prevent further wakeups of the + * soon to be gone threaded handler. + */ + set_bit(IRQTF_DIED, &tsk->irqaction->flags); +} + /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. @@ -419,6 +529,26 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) rand_initialize_irq(irq); } + /* + * Threaded handler ? + */ + if (new->thread_fn) { + struct task_struct *t; + + t = kthread_create(irq_thread, new, "irq/%d-%s", irq, + new->name); + if (IS_ERR(t)) + return PTR_ERR(t); + /* + * We keep the reference to the task struct even if + * the thread dies to avoid that the interrupt code + * references an already freed task_struct. + */ + get_task_struct(t); + new->thread = t; + wake_up_process(t); + } + /* * The following block of code has to be executed atomically */ @@ -456,15 +586,15 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (!shared) { irq_chip_set_defaults(desc->chip); + init_waitqueue_head(&desc->wait_for_threads); + /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { ret = __irq_set_trigger(desc, irq, new->flags & IRQF_TRIGGER_MASK); - if (ret) { - spin_unlock_irqrestore(&desc->lock, flags); - return ret; - } + if (ret) + goto out_thread; } else compat_irq_chip_set_default_handler(desc); #if defined(CONFIG_IRQ_PER_CPU) @@ -532,8 +662,19 @@ mismatch: dump_stack(); } #endif + ret = -EBUSY; + +out_thread: spin_unlock_irqrestore(&desc->lock, flags); - return -EBUSY; + if (new->thread) { + struct task_struct *t = new->thread; + + new->thread = NULL; + if (likely(!test_bit(IRQTF_DIED, &new->thread_flags))) + kthread_stop(t); + put_task_struct(t); + } + return ret; } /** @@ -559,6 +700,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) { struct irq_desc *desc = irq_to_desc(irq); struct irqaction *action, **action_ptr; + struct task_struct *irqthread; unsigned long flags; WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq); @@ -605,6 +747,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) else desc->chip->disable(irq); } + + irqthread = action->thread; + action->thread = NULL; + spin_unlock_irqrestore(&desc->lock, flags); unregister_handler_proc(irq, action); @@ -612,6 +758,12 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) /* Make sure it's not being used on another CPU: */ synchronize_irq(irq); + if (irqthread) { + if (!test_bit(IRQTF_DIED, &action->thread_flags)) + kthread_stop(irqthread); + put_task_struct(irqthread); + } + #ifdef CONFIG_DEBUG_SHIRQ /* * It's a shared IRQ -- the driver ought to be prepared for an IRQ @@ -664,9 +816,12 @@ void free_irq(unsigned int irq, void *dev_id) EXPORT_SYMBOL(free_irq); /** - * request_irq - allocate an interrupt line + * request_threaded_irq - allocate an interrupt line * @irq: Interrupt line to allocate - * @handler: Function to be called when the IRQ occurs + * @handler: Function to be called when the IRQ occurs. + * Primary handler for threaded interrupts + * @thread_fn: Function called from the irq handler thread + * If NULL, no irq thread is created * @irqflags: Interrupt type flags * @devname: An ascii name for the claiming device * @dev_id: A cookie passed back to the handler function @@ -678,6 +833,15 @@ EXPORT_SYMBOL(free_irq); * raises, you must take care both to initialise your hardware * 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 + * 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 + * IRQ_THREAD_WAKE which will wake up the handler thread and run + * @thread_fn. This split handler design is necessary to support + * shared interrupts. + * * Dev_id must be globally unique. Normally the address of the * device data structure is used as the cookie. Since the handler * receives this value it makes sense to use it. @@ -693,8 +857,9 @@ EXPORT_SYMBOL(free_irq); * IRQF_TRIGGER_* Specify active edge(s) or level * */ -int request_irq(unsigned int irq, irq_handler_t handler, - unsigned long irqflags, const char *devname, void *dev_id) +int request_threaded_irq(unsigned int irq, irq_handler_t handler, + irq_handler_t thread_fn, unsigned long irqflags, + const char *devname, void *dev_id) { struct irqaction *action; struct irq_desc *desc; @@ -742,6 +907,7 @@ int request_irq(unsigned int irq, irq_handler_t handler, return -ENOMEM; action->handler = handler; + action->thread_fn = thread_fn; action->flags = irqflags; action->name = devname; action->dev_id = dev_id; @@ -771,4 +937,4 @@ int request_irq(unsigned int irq, irq_handler_t handler, #endif return retval; } -EXPORT_SYMBOL(request_irq); +EXPORT_SYMBOL(request_threaded_irq); -- cgit v1.2.3 From 935bd5b971f0df7c06d214d022cf8392e2f37952 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 23 Mar 2009 18:28:16 +0100 Subject: genirq: add support for threaded interrupts to devres Some devices use devres_request_irq() for to install their interrupt handler. Add support for threaded interrupts to devres as well. [tglx - simplified and adapted to latest threadirq version] Signed-off-by: Arjan van de Ven Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 17 ++++++++++++++--- kernel/irq/devres.c | 16 ++++++++++------ 2 files changed, 24 insertions(+), 9 deletions(-) (limited to 'kernel/irq') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 6fc2b720c231..dbf6a6fd116c 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -123,9 +123,20 @@ extern void free_irq(unsigned int, void *); struct device; -extern int __must_check devm_request_irq(struct device *dev, unsigned int irq, - irq_handler_t handler, unsigned long irqflags, - const char *devname, void *dev_id); +extern int __must_check +devm_request_threaded_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, irq_handler_t thread_fn, + unsigned long irqflags, const char *devname, + void *dev_id); + +static inline int __must_check +devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler, + unsigned long irqflags, const char *devname, void *dev_id) +{ + return devm_request_threaded_irq(dev, irq, handler, NULL, irqflags, + devname, dev_id); +} + extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); /* diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 38a25b8d8bff..d06df9c41cba 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -26,10 +26,12 @@ static int devm_irq_match(struct device *dev, void *res, void *data) } /** - * devm_request_irq - allocate an interrupt line for a managed device + * devm_request_threaded_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 @@ -42,9 +44,10 @@ static int devm_irq_match(struct device *dev, void *res, void *data) * If an IRQ allocated with this function needs to be freed * separately, dev_free_irq() must be used. */ -int devm_request_irq(struct device *dev, unsigned int irq, - irq_handler_t handler, unsigned long irqflags, - const char *devname, void *dev_id) +int devm_request_threaded_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, irq_handler_t thread_fn, + unsigned long irqflags, const char *devname, + void *dev_id) { struct irq_devres *dr; int rc; @@ -54,7 +57,8 @@ int devm_request_irq(struct device *dev, unsigned int irq, if (!dr) return -ENOMEM; - rc = request_irq(irq, handler, irqflags, devname, dev_id); + rc = request_threaded_irq(irq, handler, thread_fn, irqflags, devname, + dev_id); if (rc) { devres_free(dr); return rc; @@ -66,7 +70,7 @@ int devm_request_irq(struct device *dev, unsigned int irq, return 0; } -EXPORT_SYMBOL(devm_request_irq); +EXPORT_SYMBOL(devm_request_threaded_irq); /** * devm_free_irq - free an interrupt -- cgit v1.2.3 From f48fe81e5b032914183e9a17052313720c2cac56 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 24 Mar 2009 11:46:22 +0100 Subject: genirq: threaded irq handlers review fixups Delta patch to address the review comments. - Implement warning when IRQ_WAKE_THREAD is requested and no thread handler installed - coding style fixes Pointed-out-by: Christoph Hellwig Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 2 ++ kernel/irq/handle.c | 29 ++++++++++++++++++++++++----- kernel/irq/manage.c | 17 +++++++---------- 3 files changed, 33 insertions(+), 15 deletions(-) (limited to 'kernel/irq') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index dbf6a6fd116c..266a5f5f57cc 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -63,10 +63,12 @@ * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run * IRQTF_DIED - handler thread died + * IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed */ enum { IRQTF_RUNTHREAD, IRQTF_DIED, + IRQTF_WARNED, }; typedef irqreturn_t (*irq_handler_t)(int, void *); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index fe8f45374e86..38b49a9e508a 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -338,6 +338,15 @@ irqreturn_t no_action(int cpl, void *dev_id) return IRQ_NONE; } +static void warn_no_thread(unsigned int irq, struct irqaction *action) +{ + if (test_and_set_bit(IRQTF_WARNED, &action->thread_flags)) + return; + + printk(KERN_WARNING "IRQ %d device %s returned IRQ_WAKE_THREAD " + "but no thread function available.", irq, action->name); +} + /** * handle_IRQ_event - irq action chain handler * @irq: the interrupt number @@ -360,6 +369,21 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) switch (ret) { case IRQ_WAKE_THREAD: + /* + * Set result to handled so the spurious check + * does not trigger. + */ + ret = IRQ_HANDLED; + + /* + * Catch drivers which return WAKE_THREAD but + * did not set up a thread function + */ + if (unlikely(!action->thread_fn)) { + warn_no_thread(irq, action); + break; + } + /* * Wake up the handler thread for this * action. In case the thread crashed and was @@ -374,11 +398,6 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action) wake_up_process(action->thread); } - /* - * Set it to handled so the spurious check - * does not trigger. - */ - ret = IRQ_HANDLED; /* Fall through to add to randomness */ case IRQ_HANDLED: status |= action->flags; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index a4c1ab86cd25..a3eb7baf1e46 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -407,20 +407,17 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, return ret; } -static inline int irq_thread_should_run(struct irqaction *action) -{ - return test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags); -} - static int irq_wait_for_interrupt(struct irqaction *action) { while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); - if (irq_thread_should_run(action)) { + + if (test_and_clear_bit(IRQTF_RUNTHREAD, + &action->thread_flags)) { __set_current_state(TASK_RUNNING); return 0; - } else - schedule(); + } + schedule(); } return -1; } @@ -820,8 +817,8 @@ EXPORT_SYMBOL(free_irq); * @irq: Interrupt line to allocate * @handler: Function to be called when the IRQ occurs. * Primary handler for threaded interrupts - * @thread_fn: Function called from the irq handler thread - * If NULL, no irq thread is created + * @thread_fn: Function called from the irq handler thread + * If NULL, no irq thread is created * @irqflags: Interrupt type flags * @devname: An ascii name for the claiming device * @dev_id: A cookie passed back to the handler function -- cgit v1.2.3 From 0a0c5168df270a50e3518e4f12bddb31f8f5f38f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 16 Mar 2009 22:33:49 +0100 Subject: PM: Introduce functions for suspending and resuming device interrupts Introduce helper functions allowing us to prevent device drivers from getting any interrupts (without disabling interrupts on the CPU) during suspend (or hibernation) and to make them start to receive interrupts again during the subsequent resume. These functions make it possible to keep timer interrupts enabled while the "late" suspend and "early" resume callbacks provided by device drivers are being executed. In turn, this allows device drivers' "late" suspend and "early" resume callbacks to sleep, execute ACPI callbacks etc. The functions introduced here will be used to rework the handling of interrupts during suspend (hibernation) and resume. Namely, interrupts will only be disabled on the CPU right before suspending sysdevs, while device drivers will be prevented from receiving interrupts, with the help of the new helper function, before their "late" suspend callbacks run (and analogously during resume). Signed-off-by: Rafael J. Wysocki Acked-by: Ingo Molnar --- include/linux/interrupt.h | 9 ++++++ include/linux/irq.h | 1 + kernel/irq/Makefile | 1 + kernel/irq/internals.h | 2 ++ kernel/irq/manage.c | 31 ++++++++++++++----- kernel/irq/pm.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 116 insertions(+), 7 deletions(-) create mode 100644 kernel/irq/pm.c (limited to 'kernel/irq') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 0c9cb63e6895..c68bffd182bb 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -117,6 +117,15 @@ extern void disable_irq_nosync(unsigned int irq); extern void disable_irq(unsigned int irq); extern void enable_irq(unsigned int irq); +/* The following three functions are for the core kernel use only. */ +extern void suspend_device_irqs(void); +extern void resume_device_irqs(void); +#ifdef CONFIG_PM_SLEEP +extern int check_wakeup_irqs(void); +#else +static inline int check_wakeup_irqs(void) { return 0; } +#endif + #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS) extern cpumask_var_t irq_default_affinity; diff --git a/include/linux/irq.h b/include/linux/irq.h index 9c62fbe2ef30..974890b3c52f 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -67,6 +67,7 @@ typedef void (*irq_flow_handler_t)(unsigned int irq, #define IRQ_SPURIOUS_DISABLED 0x00800000 /* IRQ was disabled by the spurious trap */ #define IRQ_MOVE_PCNTXT 0x01000000 /* IRQ migration from process context */ #define IRQ_AFFINITY_SET 0x02000000 /* IRQ affinity was set from userspace*/ +#define IRQ_SUSPENDED 0x04000000 /* IRQ has gone through suspend sequence */ #ifdef CONFIG_IRQ_PER_CPU # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU) diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 4dd5b1edac98..3394f8f52964 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -4,3 +4,4 @@ obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o +obj-$(CONFIG_PM_SLEEP) += pm.o diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index ee1aa9f8e8b9..01ce20eab38f 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -12,6 +12,8 @@ extern void compat_irq_chip_set_default_handler(struct irq_desc *desc); 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 cpu, int nr); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 6458e99984c0..1516ab77355c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -162,6 +162,20 @@ static inline int setup_affinity(unsigned int irq, struct irq_desc *desc) } #endif +void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend) +{ + if (suspend) { + if (!desc->action || (desc->action->flags & IRQF_TIMER)) + return; + desc->status |= IRQ_SUSPENDED; + } + + if (!desc->depth++) { + desc->status |= IRQ_DISABLED; + desc->chip->disable(irq); + } +} + /** * disable_irq_nosync - disable an irq without waiting * @irq: Interrupt to disable @@ -182,10 +196,7 @@ void disable_irq_nosync(unsigned int irq) return; spin_lock_irqsave(&desc->lock, flags); - if (!desc->depth++) { - desc->status |= IRQ_DISABLED; - desc->chip->disable(irq); - } + __disable_irq(desc, irq, false); spin_unlock_irqrestore(&desc->lock, flags); } EXPORT_SYMBOL(disable_irq_nosync); @@ -215,15 +226,21 @@ void disable_irq(unsigned int irq) } EXPORT_SYMBOL(disable_irq); -static void __enable_irq(struct irq_desc *desc, unsigned int irq) +void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume) { + if (resume) + desc->status &= ~IRQ_SUSPENDED; + switch (desc->depth) { case 0: + err_out: 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) + goto err_out; /* Prevent probing on this irq: */ desc->status = status | IRQ_NOPROBE; check_irq_resend(desc, irq); @@ -253,7 +270,7 @@ void enable_irq(unsigned int irq) return; spin_lock_irqsave(&desc->lock, flags); - __enable_irq(desc, irq); + __enable_irq(desc, irq, false); spin_unlock_irqrestore(&desc->lock, flags); } EXPORT_SYMBOL(enable_irq); @@ -511,7 +528,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ if (shared && (desc->status & IRQ_SPURIOUS_DISABLED)) { desc->status &= ~IRQ_SPURIOUS_DISABLED; - __enable_irq(desc, irq); + __enable_irq(desc, irq, false); } spin_unlock_irqrestore(&desc->lock, flags); diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c new file mode 100644 index 000000000000..638d8bedec14 --- /dev/null +++ b/kernel/irq/pm.c @@ -0,0 +1,79 @@ +/* + * linux/kernel/irq/pm.c + * + * Copyright (C) 2009 Rafael J. Wysocki , Novell Inc. + * + * This file contains power management functions related to interrupts. + */ + +#include +#include +#include + +#include "internals.h" + +/** + * suspend_device_irqs - disable all currently enabled interrupt lines + * + * During system-wide suspend or hibernation device interrupts need to be + * disabled at the chip level and this function is provided for this purpose. + * It disables all interrupt lines that are enabled at the moment and sets the + * IRQ_SUSPENDED flag for them. + */ +void suspend_device_irqs(void) +{ + struct irq_desc *desc; + int irq; + + for_each_irq_desc(irq, desc) { + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + __disable_irq(desc, irq, true); + spin_unlock_irqrestore(&desc->lock, flags); + } + + for_each_irq_desc(irq, desc) + if (desc->status & IRQ_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) +{ + struct irq_desc *desc; + int irq; + + for_each_irq_desc(irq, desc) { + unsigned long flags; + + if (!(desc->status & IRQ_SUSPENDED)) + continue; + + spin_lock_irqsave(&desc->lock, flags); + __enable_irq(desc, irq, true); + spin_unlock_irqrestore(&desc->lock, flags); + } +} +EXPORT_SYMBOL_GPL(resume_device_irqs); + +/** + * check_wakeup_irqs - check if any wake-up interrupts are pending + */ +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; + + return 0; +} -- cgit v1.2.3