diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/irq/Kconfig | 3 | ||||
| -rw-r--r-- | kernel/irq/Makefile | 1 | ||||
| -rw-r--r-- | kernel/irq/autoprobe.c | 2 | ||||
| -rw-r--r-- | kernel/irq/chip.c | 35 | ||||
| -rw-r--r-- | kernel/irq/debugfs.c | 12 | ||||
| -rw-r--r-- | kernel/irq/internals.h | 19 | ||||
| -rw-r--r-- | kernel/irq/irqdesc.c | 9 | ||||
| -rw-r--r-- | kernel/irq/irqdomain.c | 60 | ||||
| -rw-r--r-- | kernel/irq/manage.c | 23 | ||||
| -rw-r--r-- | kernel/irq/matrix.c | 443 | ||||
| -rw-r--r-- | kernel/irq/msi.c | 32 | ||||
| -rw-r--r-- | kernel/irq/proc.c | 5 | ||||
| -rw-r--r-- | kernel/irq_work.c | 10 |
13 files changed, 600 insertions, 54 deletions
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index a117adf7084b..ac1a3e29d3b9 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -97,6 +97,9 @@ config HANDLE_DOMAIN_IRQ config IRQ_TIMINGS bool +config GENERIC_IRQ_MATRIX_ALLOCATOR + bool + config IRQ_DOMAIN_DEBUG bool "Expose hardware/virtual IRQ mapping via debugfs" depends on IRQ_DOMAIN && DEBUG_FS diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index ed15d142694b..ff6e352e3a6c 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -14,3 +14,4 @@ obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o obj-$(CONFIG_SMP) += affinity.o obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o +obj-$(CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR) += matrix.o diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index befa671fba64..4e8089b319ae 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -54,7 +54,7 @@ unsigned long probe_irq_on(void) if (desc->irq_data.chip->irq_set_type) desc->irq_data.chip->irq_set_type(&desc->irq_data, IRQ_TYPE_PROBE); - irq_startup(desc, IRQ_NORESEND, IRQ_START_FORCE); + irq_activate_and_startup(desc, IRQ_NORESEND); } raw_spin_unlock_irq(&desc->lock); } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 5a2ef92c2782..043bfc35b353 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -207,20 +207,24 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) * Catch code which fiddles with enable_irq() on a managed * and potentially shutdown IRQ. Chained interrupt * installment or irq auto probing should not happen on - * managed irqs either. Emit a warning, break the affinity - * and start it up as a normal interrupt. + * managed irqs either. */ if (WARN_ON_ONCE(force)) - return IRQ_STARTUP_NORMAL; + return IRQ_STARTUP_ABORT; /* * The interrupt was requested, but there is no online CPU * in it's affinity mask. Put it into managed shutdown * state and let the cpu hotplug mechanism start it up once * a CPU in the mask becomes available. */ - irqd_set_managed_shutdown(d); return IRQ_STARTUP_ABORT; } + /* + * Managed interrupts have reserved resources, so this should not + * happen. + */ + if (WARN_ON(irq_domain_activate_irq(d, false))) + return IRQ_STARTUP_ABORT; return IRQ_STARTUP_MANAGED; } #else @@ -236,7 +240,9 @@ static int __irq_startup(struct irq_desc *desc) struct irq_data *d = irq_desc_get_irq_data(desc); int ret = 0; - irq_domain_activate_irq(d); + /* Warn if this interrupt is not activated but try nevertheless */ + WARN_ON_ONCE(!irqd_is_activated(d)); + if (d->chip->irq_startup) { ret = d->chip->irq_startup(d); irq_state_clr_disabled(desc); @@ -269,6 +275,7 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) ret = __irq_startup(desc); break; case IRQ_STARTUP_ABORT: + irqd_set_managed_shutdown(d); return 0; } } @@ -278,6 +285,22 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) return ret; } +int irq_activate(struct irq_desc *desc) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + + if (!irqd_affinity_is_managed(d)) + return irq_domain_activate_irq(d, false); + return 0; +} + +void irq_activate_and_startup(struct irq_desc *desc, bool resend) +{ + if (WARN_ON(irq_activate(desc))) + return; + irq_startup(desc, resend, IRQ_START_FORCE); +} + static void __irq_disable(struct irq_desc *desc, bool mask); void irq_shutdown(struct irq_desc *desc) @@ -953,7 +976,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); desc->action = &chained_action; - irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE); + irq_activate_and_startup(desc, IRQ_RESEND); } } diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index c3fdb36dec30..7f608ac39653 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -81,6 +81,8 @@ irq_debug_show_data(struct seq_file *m, struct irq_data *data, int ind) data->domain ? data->domain->name : ""); seq_printf(m, "%*shwirq: 0x%lx\n", ind + 1, "", data->hwirq); irq_debug_show_chip(m, data, ind + 1); + if (data->domain && data->domain->ops && data->domain->ops->debug_show) + data->domain->ops->debug_show(m, NULL, data, ind + 1); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY if (!data->parent_data) return; @@ -149,6 +151,7 @@ static int irq_debug_show(struct seq_file *m, void *p) raw_spin_lock_irq(&desc->lock); data = irq_desc_get_irq_data(desc); seq_printf(m, "handler: %pf\n", desc->handle_irq); + seq_printf(m, "device: %s\n", desc->dev_name); seq_printf(m, "status: 0x%08x\n", desc->status_use_accessors); irq_debug_show_bits(m, 0, desc->status_use_accessors, irqdesc_states, ARRAY_SIZE(irqdesc_states)); @@ -226,6 +229,15 @@ static const struct file_operations dfs_irq_ops = { .release = single_release, }; +void irq_debugfs_copy_devname(int irq, struct device *dev) +{ + struct irq_desc *desc = irq_to_desc(irq); + const char *name = dev_name(dev); + + if (name) + desc->dev_name = kstrdup(name, GFP_KERNEL); +} + void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc) { char name [10]; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 44ed5f8c8759..07d08ca701ec 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -75,6 +75,8 @@ extern void __enable_irq(struct irq_desc *desc); #define IRQ_START_FORCE true #define IRQ_START_COND false +extern int irq_activate(struct irq_desc *desc); +extern void irq_activate_and_startup(struct irq_desc *desc, bool resend); extern int irq_startup(struct irq_desc *desc, bool resend, bool force); extern void irq_shutdown(struct irq_desc *desc); @@ -437,6 +439,18 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) } #endif /* !CONFIG_GENERIC_PENDING_IRQ */ +#if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) +static inline int irq_domain_activate_irq(struct irq_data *data, bool early) +{ + irqd_set_activated(data); + return 0; +} +static inline void irq_domain_deactivate_irq(struct irq_data *data) +{ + irqd_clr_activated(data); +} +#endif + #ifdef CONFIG_GENERIC_IRQ_DEBUGFS #include <linux/debugfs.h> @@ -444,7 +458,9 @@ void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc); static inline void irq_remove_debugfs_entry(struct irq_desc *desc) { debugfs_remove(desc->debugfs_file); + kfree(desc->dev_name); } +void irq_debugfs_copy_devname(int irq, struct device *dev); # ifdef CONFIG_IRQ_DOMAIN void irq_domain_debugfs_init(struct dentry *root); # else @@ -459,4 +475,7 @@ static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d) static inline void irq_remove_debugfs_entry(struct irq_desc *d) { } +static inline void irq_debugfs_copy_devname(int irq, struct device *dev) +{ +} #endif /* CONFIG_GENERIC_IRQ_DEBUGFS */ diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 82afb7ed369f..f2edcf85780d 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -27,7 +27,7 @@ static struct lock_class_key irq_desc_lock_class; #if defined(CONFIG_SMP) static int __init irq_affinity_setup(char *str) { - zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); + alloc_bootmem_cpumask_var(&irq_default_affinity); cpulist_parse(str, irq_default_affinity); /* * Set at least the boot cpu. We don't want to end up with @@ -40,10 +40,8 @@ __setup("irqaffinity=", irq_affinity_setup); static void __init init_irq_default_affinity(void) { -#ifdef CONFIG_CPUMASK_OFFSTACK - if (!irq_default_affinity) + if (!cpumask_available(irq_default_affinity)) zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); -#endif if (cpumask_empty(irq_default_affinity)) cpumask_setall(irq_default_affinity); } @@ -448,7 +446,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node, } } - flags = affinity ? IRQD_AFFINITY_MANAGED : 0; + flags = affinity ? IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN : 0; mask = NULL; for (i = 0; i < cnt; i++) { @@ -462,6 +460,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node, goto err; irq_insert_desc(start + i, desc); irq_sysfs_add(start + i, desc); + irq_add_debugfs_entry(start + i, desc); } bitmap_set(allocated_irqs, start, cnt); return start; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index ac4644e92b49..4f4f60015e8a 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -21,7 +21,6 @@ static LIST_HEAD(irq_domain_list); static DEFINE_MUTEX(irq_domain_mutex); -static DEFINE_MUTEX(revmap_trees_mutex); static struct irq_domain *irq_default_domain; static void irq_domain_check_hierarchy(struct irq_domain *domain); @@ -211,6 +210,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, /* Fill structure */ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); + mutex_init(&domain->revmap_tree_mutex); domain->ops = ops; domain->host_data = host_data; domain->hwirq_max = hwirq_max; @@ -462,9 +462,9 @@ static void irq_domain_clear_mapping(struct irq_domain *domain, if (hwirq < domain->revmap_size) { domain->linear_revmap[hwirq] = 0; } else { - mutex_lock(&revmap_trees_mutex); + mutex_lock(&domain->revmap_tree_mutex); radix_tree_delete(&domain->revmap_tree, hwirq); - mutex_unlock(&revmap_trees_mutex); + mutex_unlock(&domain->revmap_tree_mutex); } } @@ -475,9 +475,9 @@ static void irq_domain_set_mapping(struct irq_domain *domain, if (hwirq < domain->revmap_size) { domain->linear_revmap[hwirq] = irq_data->irq; } else { - mutex_lock(&revmap_trees_mutex); + mutex_lock(&domain->revmap_tree_mutex); radix_tree_insert(&domain->revmap_tree, hwirq, irq_data); - mutex_unlock(&revmap_trees_mutex); + mutex_unlock(&domain->revmap_tree_mutex); } } @@ -921,8 +921,7 @@ static void virq_debug_show_one(struct seq_file *m, struct irq_desc *desc) chip = irq_data_get_irq_chip(data); seq_printf(m, "%-15s ", (chip && chip->name) ? chip->name : "none"); - seq_printf(m, data ? "0x%p " : " %p ", - irq_data_get_irq_chip_data(data)); + seq_printf(m, "0x%p ", irq_data_get_irq_chip_data(data)); seq_printf(m, " %c ", (desc->action && desc->action->handler) ? '*' : ' '); direct = (irq == hwirq) && (irq < domain->revmap_direct_max_irq); @@ -1459,11 +1458,11 @@ static void irq_domain_fix_revmap(struct irq_data *d) return; /* Not using radix tree. */ /* Fix up the revmap. */ - mutex_lock(&revmap_trees_mutex); + mutex_lock(&d->domain->revmap_tree_mutex); slot = radix_tree_lookup_slot(&d->domain->revmap_tree, d->hwirq); if (slot) radix_tree_replace_slot(&d->domain->revmap_tree, slot, d); - mutex_unlock(&revmap_trees_mutex); + mutex_unlock(&d->domain->revmap_tree_mutex); } /** @@ -1682,28 +1681,36 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, } EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); -static void __irq_domain_activate_irq(struct irq_data *irq_data) +static void __irq_domain_deactivate_irq(struct irq_data *irq_data) { if (irq_data && irq_data->domain) { struct irq_domain *domain = irq_data->domain; + if (domain->ops->deactivate) + domain->ops->deactivate(domain, irq_data); if (irq_data->parent_data) - __irq_domain_activate_irq(irq_data->parent_data); - if (domain->ops->activate) - domain->ops->activate(domain, irq_data); + __irq_domain_deactivate_irq(irq_data->parent_data); } } -static void __irq_domain_deactivate_irq(struct irq_data *irq_data) +static int __irq_domain_activate_irq(struct irq_data *irqd, bool early) { - if (irq_data && irq_data->domain) { - struct irq_domain *domain = irq_data->domain; + int ret = 0; - if (domain->ops->deactivate) - domain->ops->deactivate(domain, irq_data); - if (irq_data->parent_data) - __irq_domain_deactivate_irq(irq_data->parent_data); + if (irqd && irqd->domain) { + struct irq_domain *domain = irqd->domain; + + if (irqd->parent_data) + ret = __irq_domain_activate_irq(irqd->parent_data, + early); + if (!ret && domain->ops->activate) { + ret = domain->ops->activate(domain, irqd, early); + /* Rollback in case of error */ + if (ret && irqd->parent_data) + __irq_domain_deactivate_irq(irqd->parent_data); + } } + return ret; } /** @@ -1714,12 +1721,15 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data) * This is the second step to call domain_ops->activate to program interrupt * controllers, so the interrupt could actually get delivered. */ -void irq_domain_activate_irq(struct irq_data *irq_data) +int irq_domain_activate_irq(struct irq_data *irq_data, bool early) { - if (!irqd_is_activated(irq_data)) { - __irq_domain_activate_irq(irq_data); + int ret = 0; + + if (!irqd_is_activated(irq_data)) + ret = __irq_domain_activate_irq(irq_data, early); + if (!ret) irqd_set_activated(irq_data); - } + return ret; } /** @@ -1810,6 +1820,8 @@ irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind) d->revmap_size + d->revmap_direct_max_irq); seq_printf(m, "%*smapped: %u\n", ind + 1, "", d->mapcount); seq_printf(m, "%*sflags: 0x%08x\n", ind +1 , "", d->flags); + if (d->ops && d->ops->debug_show) + d->ops->debug_show(m, d, NULL, ind + 1); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY if (!d->parent) return; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 4bff6a10ae8e..2ff1c0c82fc9 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -398,7 +398,8 @@ int irq_select_affinity_usr(unsigned int irq) /** * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt * @irq: interrupt number to set affinity - * @vcpu_info: vCPU specific data + * @vcpu_info: vCPU specific data or pointer to a percpu array of vCPU + * specific data for percpu_devid interrupts * * This function uses the vCPU specific data to set the vCPU * affinity for an irq. The vCPU specific data is passed from @@ -536,7 +537,7 @@ void __enable_irq(struct irq_desc *desc) * time. If it was already started up, then irq_startup() * will invoke irq_enable() under the hood. */ - irq_startup(desc, IRQ_RESEND, IRQ_START_COND); + irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE); break; } default: @@ -1305,7 +1306,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * thread_mask assigned. See the loop above which or's * all existing action->thread_mask bits. */ - new->thread_mask = 1 << ffz(thread_mask); + new->thread_mask = 1UL << ffz(thread_mask); } else if (new->handler == irq_default_primary_handler && !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) { @@ -1342,6 +1343,21 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) goto out_unlock; } + /* + * Activate the interrupt. That activation must happen + * independently of IRQ_NOAUTOEN. request_irq() can fail + * and the callers are supposed to handle + * that. enable_irq() of an interrupt requested with + * IRQ_NOAUTOEN is not supposed to fail. The activation + * keeps it in shutdown mode, it merily associates + * resources if necessary and if that's not possible it + * fails. Interrupts which are in managed shutdown mode + * will simply ignore that activation request. + */ + ret = irq_activate(desc); + if (ret) + goto out_unlock; + desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \ IRQS_ONESHOT | IRQS_WAITING); irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); @@ -1417,7 +1433,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) wake_up_process(new->secondary->thread); register_irq_proc(irq, desc); - irq_add_debugfs_entry(irq, desc); new->dir = NULL; register_handler_proc(irq, new); return 0; diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c new file mode 100644 index 000000000000..a3cbbc8191c5 --- /dev/null +++ b/kernel/irq/matrix.c @@ -0,0 +1,443 @@ +/* + * Copyright (C) 2017 Thomas Gleixner <tglx@linutronix.de> + * + * SPDX-License-Identifier: GPL-2.0 + */ +#include <linux/spinlock.h> +#include <linux/seq_file.h> +#include <linux/bitmap.h> +#include <linux/percpu.h> +#include <linux/cpu.h> +#include <linux/irq.h> + +#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS) * sizeof(unsigned long)) + +struct cpumap { + unsigned int available; + unsigned int allocated; + unsigned int managed; + bool online; + unsigned long alloc_map[IRQ_MATRIX_SIZE]; + unsigned long managed_map[IRQ_MATRIX_SIZE]; +}; + +struct irq_matrix { + unsigned int matrix_bits; + unsigned int alloc_start; + unsigned int alloc_end; + unsigned int alloc_size; + unsigned int global_available; + unsigned int global_reserved; + unsigned int systembits_inalloc; + unsigned int total_allocated; + unsigned int online_maps; + struct cpumap __percpu *maps; + unsigned long scratch_map[IRQ_MATRIX_SIZE]; + unsigned long system_map[IRQ_MATRIX_SIZE]; +}; + +#define CREATE_TRACE_POINTS +#include <trace/events/irq_matrix.h> + +/** + * irq_alloc_matrix - Allocate a irq_matrix structure and initialize it + * @matrix_bits: Number of matrix bits must be <= IRQ_MATRIX_BITS + * @alloc_start: From which bit the allocation search starts + * @alloc_end: At which bit the allocation search ends, i.e first + * invalid bit + */ +__init struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits, + unsigned int alloc_start, + unsigned int alloc_end) +{ + struct irq_matrix *m; + + if (matrix_bits > IRQ_MATRIX_BITS) + return NULL; + + m = kzalloc(sizeof(*m), GFP_KERNEL); + if (!m) + return NULL; + + m->matrix_bits = matrix_bits; + m->alloc_start = alloc_start; + m->alloc_end = alloc_end; + m->alloc_size = alloc_end - alloc_start; + m->maps = alloc_percpu(*m->maps); + if (!m->maps) { + kfree(m); + return NULL; + } + return m; +} + +/** + * irq_matrix_online - Bring the local CPU matrix online + * @m: Matrix pointer + */ +void irq_matrix_online(struct irq_matrix *m) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + BUG_ON(cm->online); + + bitmap_zero(cm->alloc_map, m->matrix_bits); + cm->available = m->alloc_size - (cm->managed + m->systembits_inalloc); + cm->allocated = 0; + m->global_available += cm->available; + cm->online = true; + m->online_maps++; + trace_irq_matrix_online(m); +} + +/** + * irq_matrix_offline - Bring the local CPU matrix offline + * @m: Matrix pointer + */ +void irq_matrix_offline(struct irq_matrix *m) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + /* Update the global available size */ + m->global_available -= cm->available; + cm->online = false; + m->online_maps--; + trace_irq_matrix_offline(m); +} + +static unsigned int matrix_alloc_area(struct irq_matrix *m, struct cpumap *cm, + unsigned int num, bool managed) +{ + unsigned int area, start = m->alloc_start; + unsigned int end = m->alloc_end; + + bitmap_or(m->scratch_map, cm->managed_map, m->system_map, end); + bitmap_or(m->scratch_map, m->scratch_map, cm->alloc_map, end); + area = bitmap_find_next_zero_area(m->scratch_map, end, start, num, 0); + if (area >= end) + return area; + if (managed) + bitmap_set(cm->managed_map, area, num); + else + bitmap_set(cm->alloc_map, area, num); + return area; +} + +/** + * irq_matrix_assign_system - Assign system wide entry in the matrix + * @m: Matrix pointer + * @bit: Which bit to reserve + * @replace: Replace an already allocated vector with a system + * vector at the same bit position. + * + * The BUG_ON()s below are on purpose. If this goes wrong in the + * early boot process, then the chance to survive is about zero. + * If this happens when the system is life, it's not much better. + */ +void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, + bool replace) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + BUG_ON(bit > m->matrix_bits); + BUG_ON(m->online_maps > 1 || (m->online_maps && !replace)); + + set_bit(bit, m->system_map); + if (replace) { + BUG_ON(!test_and_clear_bit(bit, cm->alloc_map)); + cm->allocated--; + m->total_allocated--; + } + if (bit >= m->alloc_start && bit < m->alloc_end) + m->systembits_inalloc++; + + trace_irq_matrix_assign_system(bit, m); +} + +/** + * irq_matrix_reserve_managed - Reserve a managed interrupt in a CPU map + * @m: Matrix pointer + * @msk: On which CPUs the bits should be reserved. + * + * Can be called for offline CPUs. Note, this will only reserve one bit + * on all CPUs in @msk, but it's not guaranteed that the bits are at the + * same offset on all CPUs + */ +int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk) +{ + unsigned int cpu, failed_cpu; + + for_each_cpu(cpu, msk) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + unsigned int bit; + + bit = matrix_alloc_area(m, cm, 1, true); + if (bit >= m->alloc_end) + goto cleanup; + cm->managed++; + if (cm->online) { + cm->available--; + m->global_available--; + } + trace_irq_matrix_reserve_managed(bit, cpu, m, cm); + } + return 0; +cleanup: + failed_cpu = cpu; + for_each_cpu(cpu, msk) { + if (cpu == failed_cpu) + break; + irq_matrix_remove_managed(m, cpumask_of(cpu)); + } + return -ENOSPC; +} + +/** + * irq_matrix_remove_managed - Remove managed interrupts in a CPU map + * @m: Matrix pointer + * @msk: On which CPUs the bits should be removed + * + * Can be called for offline CPUs + * + * This removes not allocated managed interrupts from the map. It does + * not matter which one because the managed interrupts free their + * allocation when they shut down. If not, the accounting is screwed, + * but all what can be done at this point is warn about it. + */ +void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) +{ + unsigned int cpu; + + for_each_cpu(cpu, msk) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + unsigned int bit, end = m->alloc_end; + + if (WARN_ON_ONCE(!cm->managed)) + continue; + + /* Get managed bit which are not allocated */ + bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); + + bit = find_first_bit(m->scratch_map, end); + if (WARN_ON_ONCE(bit >= end)) + continue; + + clear_bit(bit, cm->managed_map); + + cm->managed--; + if (cm->online) { + cm->available++; + m->global_available++; + } + trace_irq_matrix_remove_managed(bit, cpu, m, cm); + } +} + +/** + * irq_matrix_alloc_managed - Allocate a managed interrupt in a CPU map + * @m: Matrix pointer + * @cpu: On which CPU the interrupt should be allocated + */ +int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu) +{ + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + unsigned int bit, end = m->alloc_end; + + /* Get managed bit which are not allocated */ + bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); + bit = find_first_bit(m->scratch_map, end); + if (bit >= end) + return -ENOSPC; + set_bit(bit, cm->alloc_map); + cm->allocated++; + m->total_allocated++; + trace_irq_matrix_alloc_managed(bit, cpu, m, cm); + return bit; +} + +/** + * irq_matrix_assign - Assign a preallocated interrupt in the local CPU map + * @m: Matrix pointer + * @bit: Which bit to mark + * + * This should only be used to mark preallocated vectors + */ +void irq_matrix_assign(struct irq_matrix *m, unsigned int bit) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end)) + return; + if (WARN_ON_ONCE(test_and_set_bit(bit, cm->alloc_map))) + return; + cm->allocated++; + m->total_allocated++; + cm->available--; + m->global_available--; + trace_irq_matrix_assign(bit, smp_processor_id(), m, cm); +} + +/** + * irq_matrix_reserve - Reserve interrupts + * @m: Matrix pointer + * + * This is merily a book keeping call. It increments the number of globally + * reserved interrupt bits w/o actually allocating them. This allows to + * setup interrupt descriptors w/o assigning low level resources to it. + * The actual allocation happens when the interrupt gets activated. + */ +void irq_matrix_reserve(struct irq_matrix *m) +{ + if (m->global_reserved <= m->global_available && + m->global_reserved + 1 > m->global_available) + pr_warn("Interrupt reservation exceeds available resources\n"); + + m->global_reserved++; + trace_irq_matrix_reserve(m); +} + +/** + * irq_matrix_remove_reserved - Remove interrupt reservation + * @m: Matrix pointer + * + * This is merily a book keeping call. It decrements the number of globally + * reserved interrupt bits. This is used to undo irq_matrix_reserve() when the + * interrupt was never in use and a real vector allocated, which undid the + * reservation. + */ +void irq_matrix_remove_reserved(struct irq_matrix *m) +{ + m->global_reserved--; + trace_irq_matrix_remove_reserved(m); +} + +/** + * irq_matrix_alloc - Allocate a regular interrupt in a CPU map + * @m: Matrix pointer + * @msk: Which CPUs to search in + * @reserved: Allocate previously reserved interrupts + * @mapped_cpu: Pointer to store the CPU for which the irq was allocated + */ +int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, + bool reserved, unsigned int *mapped_cpu) +{ + unsigned int cpu; + + for_each_cpu(cpu, msk) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + unsigned int bit; + + if (!cm->online) + continue; + + bit = matrix_alloc_area(m, cm, 1, false); + if (bit < m->alloc_end) { + cm->allocated++; + cm->available--; + m->total_allocated++; + m->global_available--; + if (reserved) + m->global_reserved--; + *mapped_cpu = cpu; + trace_irq_matrix_alloc(bit, cpu, m, cm); + return bit; + } + } + return -ENOSPC; +} + +/** + * irq_matrix_free - Free allocated interrupt in the matrix + * @m: Matrix pointer + * @cpu: Which CPU map needs be updated + * @bit: The bit to remove + * @managed: If true, the interrupt is managed and not accounted + * as available. + */ +void irq_matrix_free(struct irq_matrix *m, unsigned int cpu, + unsigned int bit, bool managed) +{ + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + + if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end)) + return; + + if (cm->online) { + clear_bit(bit, cm->alloc_map); + cm->allocated--; + m->total_allocated--; + if (!managed) { + cm->available++; + m->global_available++; + } + } + trace_irq_matrix_free(bit, cpu, m, cm); +} + +/** + * irq_matrix_available - Get the number of globally available irqs + * @m: Pointer to the matrix to query + * @cpudown: If true, the local CPU is about to go down, adjust + * the number of available irqs accordingly + */ +unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + return m->global_available - cpudown ? cm->available : 0; +} + +/** + * irq_matrix_reserved - Get the number of globally reserved irqs + * @m: Pointer to the matrix to query + */ +unsigned int irq_matrix_reserved(struct irq_matrix *m) +{ + return m->global_reserved; +} + +/** + * irq_matrix_allocated - Get the number of allocated irqs on the local cpu + * @m: Pointer to the matrix to search + * + * This returns number of allocated irqs + */ +unsigned int irq_matrix_allocated(struct irq_matrix *m) +{ + struct cpumap *cm = this_cpu_ptr(m->maps); + + return cm->allocated; +} + +#ifdef CONFIG_GENERIC_IRQ_DEBUGFS +/** + * irq_matrix_debug_show - Show detailed allocation information + * @sf: Pointer to the seq_file to print to + * @m: Pointer to the matrix allocator + * @ind: Indentation for the print format + * + * Note, this is a lockless snapshot. + */ +void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind) +{ + unsigned int nsys = bitmap_weight(m->system_map, m->matrix_bits); + int cpu; + + seq_printf(sf, "Online bitmaps: %6u\n", m->online_maps); + seq_printf(sf, "Global available: %6u\n", m->global_available); + seq_printf(sf, "Global reserved: %6u\n", m->global_reserved); + seq_printf(sf, "Total allocated: %6u\n", m->total_allocated); + seq_printf(sf, "System: %u: %*pbl\n", nsys, m->matrix_bits, + m->system_map); + seq_printf(sf, "%*s| CPU | avl | man | act | vectors\n", ind, " "); + cpus_read_lock(); + for_each_online_cpu(cpu) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + + seq_printf(sf, "%*s %4d %4u %4u %4u %*pbl\n", ind, " ", + cpu, cm->available, cm->managed, cm->allocated, + m->matrix_bits, cm->alloc_map); + } + cpus_read_unlock(); +} +#endif diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 3fa4bd59f569..edb987b2c58d 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -16,6 +16,8 @@ #include <linux/msi.h> #include <linux/slab.h> +#include "internals.h" + /** * alloc_msi_entry - Allocate an initialize msi_entry * @dev: Pointer to the device for which this is allocated @@ -100,13 +102,14 @@ int msi_domain_set_affinity(struct irq_data *irq_data, return ret; } -static void msi_domain_activate(struct irq_domain *domain, - struct irq_data *irq_data) +static int msi_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool early) { struct msi_msg msg; BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg)); irq_chip_write_msi_msg(irq_data, &msg); + return 0; } static void msi_domain_deactivate(struct irq_domain *domain, @@ -373,8 +376,10 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, return ret; } - for (i = 0; i < desc->nvec_used; i++) + for (i = 0; i < desc->nvec_used; i++) { irq_set_msi_desc_off(virq, i, desc); + irq_debugfs_copy_devname(virq + i, dev); + } } if (ops->msi_finish) @@ -396,11 +401,28 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, struct irq_data *irq_data; irq_data = irq_domain_get_irq_data(domain, desc->irq); - irq_domain_activate_irq(irq_data); + ret = irq_domain_activate_irq(irq_data, true); + if (ret) + goto cleanup; + if (info->flags & MSI_FLAG_MUST_REACTIVATE) + irqd_clr_activated(irq_data); } } - return 0; + +cleanup: + for_each_msi_entry(desc, dev) { + struct irq_data *irqd; + + if (desc->irq == virq) + break; + + irqd = irq_domain_get_irq_data(domain, desc->irq); + if (irqd_is_activated(irqd)) + irq_domain_deactivate_irq(irqd); + } + msi_domain_free_irqs(domain, dev); + return ret; } /** diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index c010cc0daf79..e8f374971e37 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -155,8 +155,9 @@ static ssize_t write_irq_affinity(int type, struct file *file, */ err = irq_select_affinity_usr(irq) ? -EINVAL : count; } else { - irq_set_affinity(irq, new_value); - err = count; + err = irq_set_affinity(irq, new_value); + if (!err) + err = count; } free_cpumask: diff --git a/kernel/irq_work.c b/kernel/irq_work.c index ec8ac337404d..40e9d739c169 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -131,9 +131,9 @@ bool irq_work_needs_cpu(void) static void irq_work_run_list(struct llist_head *list) { - unsigned long flags; - struct irq_work *work; + struct irq_work *work, *tmp; struct llist_node *llnode; + unsigned long flags; BUG_ON(!irqs_disabled()); @@ -141,11 +141,7 @@ static void irq_work_run_list(struct llist_head *list) return; llnode = llist_del_all(list); - while (llnode != NULL) { - work = llist_entry(llnode, struct irq_work, llnode); - - llnode = llist_next(llnode); - + llist_for_each_entry_safe(work, tmp, llnode, llnode) { /* * Clear the PENDING bit, after this point the @work * can be re-used. |