diff options
Diffstat (limited to 'kernel')
54 files changed, 1906 insertions, 728 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c index 82cf9df..14a9cdf 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -102,19 +102,6 @@ void get_online_cpus(void) } EXPORT_SYMBOL_GPL(get_online_cpus); -bool try_get_online_cpus(void) -{ - if (cpu_hotplug.active_writer == current) - return true; - if (!mutex_trylock(&cpu_hotplug.lock)) - return false; - cpuhp_lock_acquire_tryread(); - atomic_inc(&cpu_hotplug.refcount); - mutex_unlock(&cpu_hotplug.lock); - return true; -} -EXPORT_SYMBOL_GPL(try_get_online_cpus); - void put_online_cpus(void) { int refcount; diff --git a/kernel/events/core.c b/kernel/events/core.c index b11756f..ea02109 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -196,7 +196,7 @@ static int perf_sample_period_ns __read_mostly = DEFAULT_SAMPLE_PERIOD_NS; static int perf_sample_allowed_ns __read_mostly = DEFAULT_SAMPLE_PERIOD_NS * DEFAULT_CPU_TIME_MAX_PERCENT / 100; -void update_perf_cpu_limits(void) +static void update_perf_cpu_limits(void) { u64 tmp = perf_sample_period_ns; @@ -472,7 +472,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, * mode SWOUT : schedule out everything * mode SWIN : schedule in based on cgroup for next */ -void perf_cgroup_switch(struct task_struct *task, int mode) +static void perf_cgroup_switch(struct task_struct *task, int mode) { struct perf_cpu_context *cpuctx; struct pmu *pmu; @@ -1939,7 +1939,7 @@ group_sched_in(struct perf_event *group_event, if (group_event->state == PERF_EVENT_STATE_OFF) return 0; - pmu->start_txn(pmu); + pmu->start_txn(pmu, PERF_PMU_TXN_ADD); if (event_sched_in(group_event, cpuctx, ctx)) { pmu->cancel_txn(pmu); @@ -3209,14 +3209,22 @@ void perf_event_exec(void) rcu_read_unlock(); } +struct perf_read_data { + struct perf_event *event; + bool group; + int ret; +}; + /* * Cross CPU call to read the hardware event */ static void __perf_event_read(void *info) { - struct perf_event *event = info; + struct perf_read_data *data = info; + struct perf_event *sub, *event = data->event; struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct pmu *pmu = event->pmu; /* * If this is a task context, we need to check whether it is @@ -3233,9 +3241,35 @@ static void __perf_event_read(void *info) update_context_time(ctx); update_cgrp_time_from_event(event); } + update_event_times(event); - if (event->state == PERF_EVENT_STATE_ACTIVE) - event->pmu->read(event); + if (event->state != PERF_EVENT_STATE_ACTIVE) + goto unlock; + + if (!data->group) { + pmu->read(event); + data->ret = 0; + goto unlock; + } + + pmu->start_txn(pmu, PERF_PMU_TXN_READ); + + pmu->read(event); + + list_for_each_entry(sub, &event->sibling_list, group_entry) { + update_event_times(sub); + if (sub->state == PERF_EVENT_STATE_ACTIVE) { + /* + * Use sibling's PMU rather than @event's since + * sibling could be on different (eg: software) PMU. + */ + sub->pmu->read(sub); + } + } + + data->ret = pmu->commit_txn(pmu); + +unlock: raw_spin_unlock(&ctx->lock); } @@ -3300,15 +3334,23 @@ u64 perf_event_read_local(struct perf_event *event) return val; } -static u64 perf_event_read(struct perf_event *event) +static int perf_event_read(struct perf_event *event, bool group) { + int ret = 0; + /* * If event is enabled and currently active on a CPU, update the * value in the event structure: */ if (event->state == PERF_EVENT_STATE_ACTIVE) { + struct perf_read_data data = { + .event = event, + .group = group, + .ret = 0, + }; smp_call_function_single(event->oncpu, - __perf_event_read, event, 1); + __perf_event_read, &data, 1); + ret = data.ret; } else if (event->state == PERF_EVENT_STATE_INACTIVE) { struct perf_event_context *ctx = event->ctx; unsigned long flags; @@ -3323,11 +3365,14 @@ static u64 perf_event_read(struct perf_event *event) update_context_time(ctx); update_cgrp_time_from_event(event); } - update_event_times(event); + if (group) + update_group_times(event); + else + update_event_times(event); raw_spin_unlock_irqrestore(&ctx->lock, flags); } - return perf_event_count(event); + return ret; } /* @@ -3769,7 +3814,7 @@ static void put_event(struct perf_event *event) * see the comment there. * * 2) there is a lock-inversion with mmap_sem through - * perf_event_read_group(), which takes faults while + * perf_read_group(), which takes faults while * holding ctx->mutex, however this is called after * the last filedesc died, so there is no possibility * to trigger the AB-BA case. @@ -3843,14 +3888,18 @@ u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) *running = 0; mutex_lock(&event->child_mutex); - total += perf_event_read(event); + + (void)perf_event_read(event, false); + total += perf_event_count(event); + *enabled += event->total_time_enabled + atomic64_read(&event->child_total_time_enabled); *running += event->total_time_running + atomic64_read(&event->child_total_time_running); list_for_each_entry(child, &event->child_list, child_list) { - total += perf_event_read(child); + (void)perf_event_read(child, false); + total += perf_event_count(child); *enabled += child->total_time_enabled; *running += child->total_time_running; } @@ -3860,55 +3909,95 @@ u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) } EXPORT_SYMBOL_GPL(perf_event_read_value); -static int perf_event_read_group(struct perf_event *event, - u64 read_format, char __user *buf) +static int __perf_read_group_add(struct perf_event *leader, + u64 read_format, u64 *values) { - struct perf_event *leader = event->group_leader, *sub; - struct perf_event_context *ctx = leader->ctx; - int n = 0, size = 0, ret; - u64 count, enabled, running; - u64 values[5]; + struct perf_event *sub; + int n = 1; /* skip @nr */ + int ret; - lockdep_assert_held(&ctx->mutex); + ret = perf_event_read(leader, true); + if (ret) + return ret; - count = perf_event_read_value(leader, &enabled, &running); + /* + * Since we co-schedule groups, {enabled,running} times of siblings + * will be identical to those of the leader, so we only publish one + * set. + */ + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { + values[n++] += leader->total_time_enabled + + atomic64_read(&leader->child_total_time_enabled); + } - values[n++] = 1 + leader->nr_siblings; - if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) - values[n++] = enabled; - if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) - values[n++] = running; - values[n++] = count; + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { + values[n++] += leader->total_time_running + + atomic64_read(&leader->child_total_time_running); + } + + /* + * Write {count,id} tuples for every sibling. + */ + values[n++] += perf_event_count(leader); if (read_format & PERF_FORMAT_ID) values[n++] = primary_event_id(leader); - size = n * sizeof(u64); + list_for_each_entry(sub, &leader->sibling_list, group_entry) { + values[n++] += perf_event_count(sub); + if (read_format & PERF_FORMAT_ID) + values[n++] = primary_event_id(sub); + } - if (copy_to_user(buf, values, size)) - return -EFAULT; + return 0; +} + +static int perf_read_group(struct perf_event *event, + u64 read_format, char __user *buf) +{ + struct perf_event *leader = event->group_leader, *child; + struct perf_event_context *ctx = leader->ctx; + int ret; + u64 *values; - ret = size; + lockdep_assert_held(&ctx->mutex); - list_for_each_entry(sub, &leader->sibling_list, group_entry) { - n = 0; + values = kzalloc(event->read_size, GFP_KERNEL); + if (!values) + return -ENOMEM; - values[n++] = perf_event_read_value(sub, &enabled, &running); - if (read_format & PERF_FORMAT_ID) - values[n++] = primary_event_id(sub); + values[0] = 1 + leader->nr_siblings; - size = n * sizeof(u64); + /* + * By locking the child_mutex of the leader we effectively + * lock the child list of all siblings.. XXX explain how. + */ + mutex_lock(&leader->child_mutex); - if (copy_to_user(buf + ret, values, size)) { - return -EFAULT; - } + ret = __perf_read_group_add(leader, read_format, values); + if (ret) + goto unlock; - ret += size; + list_for_each_entry(child, &leader->child_list, child_list) { + ret = __perf_read_group_add(child, read_format, values); + if (ret) + goto unlock; } + mutex_unlock(&leader->child_mutex); + + ret = event->read_size; + if (copy_to_user(buf, values, event->read_size)) + ret = -EFAULT; + goto out; + +unlock: + mutex_unlock(&leader->child_mutex); +out: + kfree(values); return ret; } -static int perf_event_read_one(struct perf_event *event, +static int perf_read_one(struct perf_event *event, u64 read_format, char __user *buf) { u64 enabled, running; @@ -3946,7 +4035,7 @@ static bool is_event_hup(struct perf_event *event) * Read the performance event - simple non blocking version for now */ static ssize_t -perf_read_hw(struct perf_event *event, char __user *buf, size_t count) +__perf_read(struct perf_event *event, char __user *buf, size_t count) { u64 read_format = event->attr.read_format; int ret; @@ -3964,9 +4053,9 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count) WARN_ON_ONCE(event->ctx->parent_ctx); if (read_format & PERF_FORMAT_GROUP) - ret = perf_event_read_group(event, read_format, buf); + ret = perf_read_group(event, read_format, buf); else - ret = perf_event_read_one(event, read_format, buf); + ret = perf_read_one(event, read_format, buf); return ret; } @@ -3979,7 +4068,7 @@ perf_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) int ret; ctx = perf_event_ctx_lock(event); - ret = perf_read_hw(event, buf, count); + ret = __perf_read(event, buf, count); perf_event_ctx_unlock(event, ctx); return ret; @@ -4010,7 +4099,7 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) static void _perf_event_reset(struct perf_event *event) { - (void)perf_event_read(event); + (void)perf_event_read(event, false); local64_set(&event->count, 0); perf_event_update_userpage(event); } @@ -7292,24 +7381,49 @@ static void perf_pmu_nop_void(struct pmu *pmu) { } +static void perf_pmu_nop_txn(struct pmu *pmu, unsigned int flags) +{ +} + static int perf_pmu_nop_int(struct pmu *pmu) { return 0; } -static void perf_pmu_start_txn(struct pmu *pmu) +static DEFINE_PER_CPU(unsigned int, nop_txn_flags); + +static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags) { + __this_cpu_write(nop_txn_flags, flags); + + if (flags & ~PERF_PMU_TXN_ADD) + return; + perf_pmu_disable(pmu); } static int perf_pmu_commit_txn(struct pmu *pmu) { + unsigned int flags = __this_cpu_read(nop_txn_flags); + + __this_cpu_write(nop_txn_flags, 0); + + if (flags & ~PERF_PMU_TXN_ADD) + return 0; + perf_pmu_enable(pmu); return 0; } static void perf_pmu_cancel_txn(struct pmu *pmu) { + unsigned int flags = __this_cpu_read(nop_txn_flags); + + __this_cpu_write(nop_txn_flags, 0); + + if (flags & ~PERF_PMU_TXN_ADD) + return; + perf_pmu_enable(pmu); } @@ -7548,7 +7662,7 @@ got_cpu_context: pmu->commit_txn = perf_pmu_commit_txn; pmu->cancel_txn = perf_pmu_cancel_txn; } else { - pmu->start_txn = perf_pmu_nop_void; + pmu->start_txn = perf_pmu_nop_txn; pmu->commit_txn = perf_pmu_nop_int; pmu->cancel_txn = perf_pmu_nop_void; } @@ -7636,7 +7750,7 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) return ret; } -struct pmu *perf_init_event(struct perf_event *event) +static struct pmu *perf_init_event(struct perf_event *event) { struct pmu *pmu = NULL; int idx; @@ -9345,14 +9459,6 @@ static void perf_cgroup_exit(struct cgroup_subsys_state *css, struct cgroup_subsys_state *old_css, struct task_struct *task) { - /* - * cgroup_exit() is called in the copy_process() failure path. - * Ignore this case since the task hasn't ran yet, this avoids - * trying to poke a half freed task state from generic code. - */ - if (!(task->flags & PF_EXITING)) - return; - task_function_call(task, __perf_cgroup_move, task); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 182bc30..b5d1ea7 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -141,7 +141,7 @@ int perf_output_begin(struct perf_output_handle *handle, perf_output_get_handle(handle); do { - tail = READ_ONCE_CTRL(rb->user_page->data_tail); + tail = READ_ONCE(rb->user_page->data_tail); offset = head = local_read(&rb->head); if (!rb->overwrite && unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size)) diff --git a/kernel/exit.c b/kernel/exit.c index ea95ee1..0e93b63 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -761,7 +761,9 @@ void do_exit(long code) */ flush_ptrace_hw_breakpoint(tsk); + TASKS_RCU(preempt_disable()); TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu)); + TASKS_RCU(preempt_enable()); exit_notify(tsk, group_dead); proc_exit_connector(tsk); #ifdef CONFIG_NUMA diff --git a/kernel/fork.c b/kernel/fork.c index 2845623..6ac8942 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1101,7 +1101,7 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (cpu_limit != RLIM_INFINITY) { sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit); - sig->cputimer.running = 1; + sig->cputimer.running = true; } /* The timer lists. */ diff --git a/kernel/futex.c b/kernel/futex.c index 6e443ef..dfc86e9 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -255,9 +255,18 @@ struct futex_hash_bucket { struct plist_head chain; } ____cacheline_aligned_in_smp; -static unsigned long __read_mostly futex_hashsize; +/* + * The base of the bucket array and its size are always used together + * (after initialization only in hash_futex()), so ensure that they + * reside in the same cacheline. + */ +static struct { + struct futex_hash_bucket *queues; + unsigned long hashsize; +} __futex_data __read_mostly __aligned(2*sizeof(long)); +#define futex_queues (__futex_data.queues) +#define futex_hashsize (__futex_data.hashsize) -static struct futex_hash_bucket *futex_queues; /* * Fault injections for futexes. diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 9a76e3b..3b48dab 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -30,6 +30,10 @@ config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ config GENERIC_PENDING_IRQ bool +# Support for generic irq migrating off cpu before the cpu is offline. +config GENERIC_IRQ_MIGRATION + bool + # Alpha specific irq affinity mechanism config AUTO_IRQ_AFFINITY bool diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index d121235..2fc9cbd 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -5,5 +5,6 @@ obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o +obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o obj-$(CONFIG_PM_SLEEP) += pm.o obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index e28169d..1520645 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -21,6 +21,20 @@ #include "internals.h" +static irqreturn_t bad_chained_irq(int irq, void *dev_id) +{ + WARN_ONCE(1, "Chained irq %d should not call an action\n", irq); + return IRQ_NONE; +} + +/* + * Chained handlers should never call action on their IRQ. This default + * action will emit warning if such thing happens. + */ +struct irqaction chained_action = { + .handler = bad_chained_irq, +}; + /** * irq_set_chip - set the irq chip for an irq * @irq: irq number @@ -227,6 +241,13 @@ void irq_enable(struct irq_desc *desc) * disabled. If an interrupt happens, then the interrupt flow * handler masks the line at the hardware level and marks it * pending. + * + * If the interrupt chip does not implement the irq_disable callback, + * a driver can disable the lazy approach for a particular irq line by + * calling 'irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY)'. This can + * be used for devices which cannot disable the interrupt at the + * device level under certain circumstances and have to use + * disable_irq[_nosync] instead. */ void irq_disable(struct irq_desc *desc) { @@ -234,6 +255,8 @@ void irq_disable(struct irq_desc *desc) if (desc->irq_data.chip->irq_disable) { desc->irq_data.chip->irq_disable(&desc->irq_data); irq_state_set_masked(desc); + } else if (irq_settings_disable_unlazy(desc)) { + mask_irq(desc); } } @@ -669,7 +692,7 @@ void handle_percpu_irq(struct irq_desc *desc) if (chip->irq_ack) chip->irq_ack(&desc->irq_data); - handle_irq_event_percpu(desc, desc->action); + handle_irq_event_percpu(desc); if (chip->irq_eoi) chip->irq_eoi(&desc->irq_data); @@ -746,6 +769,8 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, if (desc->irq_data.chip != &no_irq_chip) mask_ack_irq(desc); irq_state_set_disabled(desc); + if (is_chained) + desc->action = NULL; desc->depth = 1; } desc->handle_irq = handle; @@ -755,6 +780,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); + desc->action = &chained_action; irq_startup(desc, true); } } diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c new file mode 100644 index 0000000..80f4f4e --- /dev/null +++ b/kernel/irq/cpuhotplug.c @@ -0,0 +1,82 @@ +/* + * Generic cpu hotunplug interrupt migration code copied from the + * arch/arm implementation + * + * Copyright (C) Russell King + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/interrupt.h> +#include <linux/ratelimit.h> +#include <linux/irq.h> + +#include "internals.h" + +static bool migrate_one_irq(struct irq_desc *desc) +{ + struct irq_data *d = irq_desc_get_irq_data(desc); + const struct cpumask *affinity = d->common->affinity; + struct irq_chip *c; + bool ret = false; + + /* + * If this is a per-CPU interrupt, or the affinity does not + * include this CPU, then we have nothing to do. + */ + if (irqd_is_per_cpu(d) || + !cpumask_test_cpu(smp_processor_id(), affinity)) + return false; + + if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { + affinity = cpu_online_mask; + ret = true; + } + + c = irq_data_get_irq_chip(d); + if (!c->irq_set_affinity) { + pr_warn_ratelimited("IRQ%u: unable to set affinity\n", d->irq); + } else { + int r = irq_do_set_affinity(d, affinity, false); + if (r) + pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n", + d->irq, r); + } + + return ret; +} + +/** + * irq_migrate_all_off_this_cpu - Migrate irqs away from offline cpu + * + * The current CPU has been marked offline. Migrate IRQs off this CPU. + * If the affinity settings do not allow other CPUs, force them onto any + * available CPU. + * + * Note: we must iterate over all IRQs, whether they have an attached + * action structure or not, as we need to get chained interrupts too. + */ +void irq_migrate_all_off_this_cpu(void) +{ + unsigned int irq; + struct irq_desc *desc; + unsigned long flags; + + local_irq_save(flags); + + for_each_active_irq(irq) { + bool affinity_broken; + + desc = irq_to_desc(irq); + raw_spin_lock(&desc->lock); + affinity_broken = migrate_one_irq(desc); + raw_spin_unlock(&desc->lock); + + if (affinity_broken) + pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n", + irq, smp_processor_id()); + } + + local_irq_restore(flags); +} diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index e25a83b..a302cf9 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -132,11 +132,11 @@ void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action) wake_up_process(action->thread); } -irqreturn_t -handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) +irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) { irqreturn_t retval = IRQ_NONE; unsigned int flags = 0, irq = desc->irq_data.irq; + struct irqaction *action = desc->action; do { irqreturn_t res; @@ -184,14 +184,13 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) irqreturn_t handle_irq_event(struct irq_desc *desc) { - struct irqaction *action = desc->action; irqreturn_t ret; desc->istate &= ~IRQS_PENDING; irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS); raw_spin_unlock(&desc->lock); - ret = handle_irq_event_percpu(desc, action); + ret = handle_irq_event_percpu(desc); raw_spin_lock(&desc->lock); irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 5ef0c2d..05c2188 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -18,6 +18,8 @@ extern bool noirqdebug; +extern struct irqaction chained_action; + /* * Bits used by threaded handlers: * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run @@ -81,7 +83,7 @@ extern void irq_mark_irq(unsigned int irq); extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); -irqreturn_t handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action); +irqreturn_t handle_irq_event_percpu(struct irq_desc *desc); irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index dc9d27c..22aa961 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -27,6 +27,57 @@ static int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, irq_hw_number_t hwirq, int node); static void irq_domain_check_hierarchy(struct irq_domain *domain); +struct irqchip_fwid { + struct fwnode_handle fwnode; + char *name; + void *data; +}; + +/** + * irq_domain_alloc_fwnode - Allocate a fwnode_handle suitable for + * identifying an irq domain + * @data: optional user-provided data + * + * Allocate a struct device_node, and return a poiner to the embedded + * fwnode_handle (or NULL on failure). + */ +struct fwnode_handle *irq_domain_alloc_fwnode(void *data) +{ + struct irqchip_fwid *fwid; + char *name; + + fwid = kzalloc(sizeof(*fwid), GFP_KERNEL); + name = kasprintf(GFP_KERNEL, "irqchip@%p", data); + + if (!fwid || !name) { + kfree(fwid); + kfree(name); + return NULL; + } + + fwid->name = name; + fwid->data = data; + fwid->fwnode.type = FWNODE_IRQCHIP; + return &fwid->fwnode; +} + +/** + * irq_domain_free_fwnode - Free a non-OF-backed fwnode_handle + * + * Free a fwnode_handle allocated with irq_domain_alloc_fwnode. + */ +void irq_domain_free_fwnode(struct fwnode_handle *fwnode) +{ + struct irqchip_fwid *fwid; + + if (WARN_ON(fwnode->type != FWNODE_IRQCHIP)) + return; + + fwid = container_of(fwnode, struct irqchip_fwid, fwnode); + kfree(fwid->name); + kfree(fwid); +} + /** * __irq_domain_add() - Allocate a new irq_domain data structure * @of_node: optional device-tree node of the interrupt controller @@ -40,23 +91,28 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain); * Allocates and initialize and irq_domain structure. * Returns pointer to IRQ domain, or NULL on failure. */ -struct irq_domain *__irq_domain_add(struct device_node *of_node, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data) { struct irq_domain *domain; + struct device_node *of_node; + + of_node = to_of_node(fwnode); domain = kzalloc_node(sizeof(*domain) + (sizeof(unsigned int) * size), GFP_KERNEL, of_node_to_nid(of_node)); if (WARN_ON(!domain)) return NULL; + of_node_get(of_node); + /* Fill structure */ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); domain->ops = ops; domain->host_data = host_data; - domain->of_node = of_node_get(of_node); + domain->fwnode = fwnode; domain->hwirq_max = hwirq_max; domain->revmap_size = size; domain->revmap_direct_max_irq = direct_max; @@ -102,7 +158,7 @@ void irq_domain_remove(struct irq_domain *domain) pr_debug("Removed domain %s\n", domain->name); - of_node_put(domain->of_node); + of_node_put(irq_domain_get_of_node(domain)); kfree(domain); } EXPORT_SYMBOL_GPL(irq_domain_remove); @@ -133,7 +189,7 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, { struct irq_domain *domain; - domain = __irq_domain_add(of_node, size, size, 0, ops, host_data); + domain = __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data); if (!domain) return NULL; @@ -177,7 +233,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, { struct irq_domain *domain; - domain = __irq_domain_add(of_node, first_hwirq + size, + domain = __irq_domain_add(of_node_to_fwnode(of_node), first_hwirq + size, first_hwirq + size, 0, ops, host_data); if (domain) irq_domain_associate_many(domain, first_irq, first_hwirq, size); @@ -187,12 +243,12 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, EXPORT_SYMBOL_GPL(irq_domain_add_legacy); /** - * irq_find_matching_host() - Locates a domain for a given device node - * @node: device-tree node of the interrupt controller + * irq_find_matching_fwnode() - Locates a domain for a given fwnode + * @fwnode: FW descriptor of the interrupt controller * @bus_token: domain-specific data */ -struct irq_domain *irq_find_matching_host(struct device_node *node, - enum irq_domain_bus_token bus_token) +struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode, + enum irq_domain_bus_token bus_token) { struct irq_domain *h, *found = NULL; int rc; @@ -209,9 +265,9 @@ struct irq_domain *irq_find_matching_host(struct device_node *node, mutex_lock(&irq_domain_mutex); list_for_each_entry(h, &irq_domain_list, link) { if (h->ops->match) - rc = h->ops->match(h, node, bus_token); + rc = h->ops->match(h, to_of_node(fwnode), bus_token); else - rc = ((h->of_node != NULL) && (h->of_node == node) && + rc = ((fwnode != NULL) && (h->fwnode == fwnode) && ((bus_token == DOMAIN_BUS_ANY) || (h->bus_token == bus_token))); @@ -223,7 +279,7 @@ struct irq_domain *irq_find_matching_host(struct device_node *node, mutex_unlock(&irq_domain_mutex); return found; } -EXPORT_SYMBOL_GPL(irq_find_matching_host); +EXPORT_SYMBOL_GPL(irq_find_matching_fwnode); /** * irq_set_default_host() - Set a "default" irq domain @@ -336,10 +392,12 @@ EXPORT_SYMBOL_GPL(irq_domain_associate); void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, irq_hw_number_t hwirq_base, int count) { + struct device_node *of_node; int i; + of_node = irq_domain_get_of_node(domain); pr_debug("%s(%s, irqbase=%i, hwbase=%i, count=%i)\n", __func__, - of_node_full_name(domain->of_node), irq_base, (int)hwirq_base, count); + of_node_full_name(of_node), irq_base, (int)hwirq_base, count); for (i = 0; i < count; i++) { irq_domain_associate(domain, irq_base + i, hwirq_base + i); @@ -359,12 +417,14 @@ EXPORT_SYMBOL_GPL(irq_domain_associate_many); */ unsigned int irq_create_direct_mapping(struct irq_domain *domain) { + struct device_node *of_node; unsigned int virq; if (domain == NULL) domain = irq_default_domain; - virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); + of_node = irq_domain_get_of_node(domain); + virq = irq_alloc_desc_from(1, of_node_to_nid(of_node)); if (!virq) { pr_debug("create_direct virq allocation failed\n"); return 0; @@ -399,6 +459,7 @@ EXPORT_SYMBOL_GPL(irq_create_direct_mapping); unsigned int irq_create_mapping(struct irq_domain *domain, irq_hw_number_t hwirq) { + struct device_node *of_node; int virq; pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); @@ -412,6 +473,8 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } pr_debug("-> using domain @%p\n", domain); + of_node = irq_domain_get_of_node(domain); + /* Check if mapping already exists */ virq = irq_find_mapping(domain, hwirq); if (virq) { @@ -420,8 +483,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } /* Allocate a virtual interrupt number */ - virq = irq_domain_alloc_descs(-1, 1, hwirq, - of_node_to_nid(domain->of_node)); + virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node)); if (virq <= 0) { pr_debug("-> virq allocation failed\n"); return 0; @@ -433,7 +495,7 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } pr_debug("irq %lu on domain %s mapped to virtual irq %u\n", - hwirq, of_node_full_name(domain->of_node), virq); + hwirq, of_node_full_name(of_node), virq); return virq; } @@ -460,10 +522,12 @@ EXPORT_SYMBOL_GPL(irq_create_mapping); int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base, irq_hw_number_t hwirq_base, int count) { + struct device_node *of_node; int ret; + of_node = irq_domain_get_of_node(domain); ret = irq_alloc_descs(irq_base, irq_base, count, - of_node_to_nid(domain->of_node)); + of_node_to_nid(of_node)); if (unlikely(ret < 0)) return ret; @@ -472,28 +536,56 @@ int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base, } EXPORT_SYMBOL_GPL(irq_create_strict_mappings); -unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) +static int irq_domain_translate(struct irq_domain *d, + struct irq_fwspec *fwspec, + irq_hw_number_t *hwirq, unsigned int *type) +{ +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + if (d->ops->translate) + return d->ops->translate(d, fwspec, hwirq, type); +#endif + if (d->ops->xlate) + return d->ops->xlate(d, to_of_node(fwspec->fwnode), + fwspec->param, fwspec->param_count, + hwirq, type); + + /* If domain has no translation, then we assume interrupt line */ + *hwirq = fwspec->param[0]; + return 0; +} + +static void of_phandle_args_to_fwspec(struct of_phandle_args *irq_data, + struct irq_fwspec *fwspec) +{ + int i; + + fwspec->fwnode = irq_data->np ? &irq_data->np->fwnode : NULL; + fwspec->param_count = irq_data->args_count; + + for (i = 0; i < irq_data->args_count; i++) + fwspec->param[i] = irq_data->args[i]; +} + +unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) { struct irq_domain *domain; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; int virq; - domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain; + if (fwspec->fwnode) + domain = irq_find_matching_fwnode(fwspec->fwnode, DOMAIN_BUS_ANY); + else + domain = irq_default_domain; + if (!domain) { pr_warn("no irq domain found for %s !\n", - of_node_full_name(irq_data->np)); + of_node_full_name(to_of_node(fwspec->fwnode))); return 0; } - /* If domain has no translation, then we assume interrupt line */ - if (domain->ops->xlate == NULL) - hwirq = irq_data->args[0]; - else { - if (domain->ops->xlate(domain, irq_data->np, irq_data->args, - irq_data->args_count, &hwirq, &type)) - return 0; - } + if (irq_domain_translate(domain, fwspec, &hwirq, &type)) + return 0; if (irq_domain_is_hierarchy(domain)) { /* @@ -504,7 +596,7 @@ unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) if (virq) return virq; - virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, irq_data); + virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, fwspec); if (virq <= 0) return 0; } else { @@ -520,6 +612,15 @@ unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) irq_set_irq_type(virq, type); return virq; } +EXPORT_SYMBOL_GPL(irq_create_fwspec_mapping); + +unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) +{ + struct irq_fwspec fwspec; + + of_phandle_args_to_fwspec(irq_data, &fwspec); + return irq_create_fwspec_mapping(&fwspec); +} EXPORT_SYMBOL_GPL(irq_create_of_mapping); /** @@ -590,14 +691,16 @@ static int virq_debug_show(struct seq_file *m, void *private) "name", "mapped", "linear-max", "direct-max", "devtree-node"); mutex_lock(&irq_domain_mutex); list_for_each_entry(domain, &irq_domain_list, link) { + struct device_node *of_node; int count = 0; + of_node = irq_domain_get_of_node(domain); radix_tree_for_each_slot(slot, &domain->revmap_tree, &iter, 0) count++; seq_printf(m, "%c%-16s %6u %10u %10u %s\n", domain == irq_default_domain ? '*' : ' ', domain->name, domain->revmap_size + count, domain->revmap_size, domain->revmap_direct_max_irq, - domain->of_node ? of_node_full_name(domain->of_node) : ""); + of_node ? of_node_full_name(of_node) : ""); } mutex_unlock(&irq_domain_mutex); @@ -751,11 +854,11 @@ static int irq_domain_alloc_descs(int virq, unsigned int cnt, #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY /** - * irq_domain_add_hierarchy - Add a irqdomain into the hierarchy + * irq_domain_create_hierarchy - Add a irqdomain into the hierarchy * @parent: Parent irq domain to associate with the new domain * @flags: Irq domain flags associated to the domain * @size: Size of the domain. See below - * @node: Optional device-tree node of the interrupt controller + * @fwnode: Optional fwnode of the interrupt controller * @ops: Pointer to the interrupt domain callbacks * @host_data: Controller private data pointer * @@ -765,19 +868,19 @@ static int irq_domain_alloc_descs(int virq, unsigned int cnt, * domain flags are set. * Returns pointer to IRQ domain, or NULL on failure. */ -struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, +struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, unsigned int flags, unsigned int size, - struct device_node *node, + struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data) { struct irq_domain *domain; if (size) - domain = irq_domain_add_linear(node, size, ops, host_data); + domain = irq_domain_create_linear(fwnode, size, ops, host_data); else - domain = irq_domain_add_tree(node, ops, host_data); + domain = irq_domain_create_tree(fwnode, ops, host_data); if (domain) { domain->parent = parent; domain->flags |= flags; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f9a59f6..a71175f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -258,37 +258,6 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) } EXPORT_SYMBOL_GPL(irq_set_affinity_hint); -/** - * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt - * @irq: interrupt number to set affinity - * @vcpu_info: vCPU specific data - * - * This function uses the vCPU specific data to set the vCPU - * affinity for an irq. The vCPU specific data is passed from - * outside, such as KVM. One example code path is as below: - * KVM -> IOMMU -> irq_set_vcpu_affinity(). - */ -int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info) -{ - unsigned long flags; - struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); - struct irq_data *data; - struct irq_chip *chip; - int ret = -ENOSYS; - - if (!desc) - return -EINVAL; - - data = irq_desc_get_irq_data(desc); - chip = irq_data_get_irq_chip(data); - if (chip && chip->irq_set_vcpu_affinity) - ret = chip->irq_set_vcpu_affinity(data, vcpu_info); - irq_put_desc_unlock(desc, flags); - - return ret; -} -EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity); - static void irq_affinity_notify(struct work_struct *work) { struct irq_affinity_notify *notify = @@ -424,6 +393,37 @@ setup_affinity(struct irq_desc *desc, struct cpumask *mask) } #endif +/** + * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt + * @irq: interrupt number to set affinity + * @vcpu_info: vCPU specific data + * + * This function uses the vCPU specific data to set the vCPU + * affinity for an irq. The vCPU specific data is passed from + * outside, such as KVM. One example code path is as below: + * KVM -> IOMMU -> irq_set_vcpu_affinity(). + */ +int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info) +{ + unsigned long flags; + struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); + struct irq_data *data; + struct irq_chip *chip; + int ret = -ENOSYS; + + if (!desc) + return -EINVAL; + + data = irq_desc_get_irq_data(desc); + chip = irq_data_get_irq_chip(data); + if (chip && chip->irq_set_vcpu_affinity) + ret = chip->irq_set_vcpu_affinity(data, vcpu_info); + irq_put_desc_unlock(desc, flags); + + return ret; +} +EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity); + void __disable_irq(struct irq_desc *desc) { if (!desc->depth++) @@ -730,6 +730,12 @@ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id) return IRQ_NONE; } +static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) +{ + WARN(1, "Secondary action handler called for irq %d\n", irq); + return IRQ_NONE; +} + static int irq_wait_for_interrupt(struct irqaction *action) { set_current_state(TASK_INTERRUPTIBLE); @@ -756,7 +762,8 @@ static int irq_wait_for_interrupt(struct irqaction *action) static void irq_finalize_oneshot(struct irq_desc *desc, struct irqaction *action) { - if (!(desc->istate & IRQS_ONESHOT)) + if (!(desc->istate & IRQS_ONESHOT) || + action->handler == irq_forced_secondary_handler) return; again: chip_bus_lock(desc); @@ -910,6 +917,18 @@ static void irq_thread_dtor(struct callback_head *unused) irq_finalize_oneshot(desc, action); } +static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action) +{ + struct irqaction *secondary = action->secondary; + + if (WARN_ON_ONCE(!secondary)) + return; + + raw_spin_lock_irq(&desc->lock); + __irq_wake_thread(desc, secondary); + raw_spin_unlock_irq(&desc->lock); +} + /* * Interrupt handler thread */ @@ -940,6 +959,8 @@ static int irq_thread(void *data) action_ret = handler_fn(desc, action); if (action_ret == IRQ_HANDLED) atomic_inc(&desc->threads_handled); + if (action_ret == IRQ_WAKE_THREAD) + irq_wake_secondary(desc, action); wake_threads_waitq(desc); } @@ -984,20 +1005,36 @@ void irq_wake_thread(unsigned int irq, void *dev_id) } EXPORT_SYMBOL_GPL(irq_wake_thread); -static void irq_setup_forced_threading(struct irqaction *new) +static int irq_setup_forced_threading(struct irqaction *new) { if (!force_irqthreads) - return; + return 0; if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) - return; + return 0; new->flags |= IRQF_ONESHOT; - if (!new->thread_fn) { - set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); - new->thread_fn = new->handler; - new->handler = irq_default_primary_handler; + /* + * Handle the case where we have a real primary handler and a + * thread handler. We force thread them as well by creating a + * secondary action. + */ + if (new->handler != irq_default_primary_handler && new->thread_fn) { + /* Allocate the secondary action */ + new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL); + if (!new->secondary) + return -ENOMEM; + new->secondary->handler = irq_forced_secondary_handler; + new->secondary->thread_fn = new->thread_fn; + new->secondary->dev_id = new->dev_id; + new->secondary->irq = new->irq; + new->secondary->name = new->name; } + /* Deal with the primary handler */ + set_bit(IRQTF_FORCED_THREAD, &new->thread_flags); + new->thread_fn = new->handler; + new->handler = irq_default_primary_handler; + return 0; } static int irq_request_resources(struct irq_desc *desc) @@ -1017,6 +1054,48 @@ static void irq_release_resources(struct irq_desc *desc) c->irq_release_resources(d); } +static int +setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary) +{ + struct task_struct *t; + struct sched_param param = { + .sched_priority = MAX_USER_RT_PRIO/2, + }; + + if (!secondary) { + t = kthread_create(irq_thread, new, "irq/%d-%s", irq, + new->name); + } else { + t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq, + new->name); + param.sched_priority -= 1; + } + + if (IS_ERR(t)) + return PTR_ERR(t); + + sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m); + + /* + * We keep the reference to the task struct even if + * the thread dies to avoid that the interrupt code + * references an already freed task_struct. + */ + get_task_struct(t); + new->thread = t; + /* + * Tell the thread to set its affinity. This is + * important for shared interrupt handlers as we do + * not invoke setup_affinity() for the secondary + * handlers as everything is already set up. Even for + * interrupts marked with IRQF_NO_BALANCE this is + * correct as we want the thread to move to the cpu(s) + * on which the requesting code placed the interrupt. + */ + set_bit(IRQTF_AFFINITY, &new->thread_flags); + return 0; +} + /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. @@ -1037,6 +1116,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (!try_module_get(desc->owner)) return -ENODEV; + new->irq = irq; + /* * Check whether the interrupt nests into another interrupt * thread. @@ -1054,8 +1135,11 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ new->handler = irq_nested_primary_handler; } else { - if (irq_settings_can_thread(desc)) - irq_setup_forced_threading(new); + if (irq_settings_can_thread(desc)) { + ret = irq_setup_forced_threading(new); + if (ret) + goto out_mput; + } } /* @@ -1064,37 +1148,14 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * thread. */ if (new->thread_fn && !nested) { - struct task_struct *t; - static const struct sched_param param = { - .sched_priority = MAX_USER_RT_PRIO/2, - }; - - t = kthread_create(irq_thread, new, "irq/%d-%s", irq, - new->name); - if (IS_ERR(t)) { - ret = PTR_ERR(t); + ret = setup_irq_thread(new, irq, false); + if (ret) goto out_mput; + if (new->secondary) { + ret = setup_irq_thread(new->secondary, irq, true); + if (ret) + goto out_thread; } - - sched_setscheduler_nocheck(t, SCHED_FIFO, ¶m); - - /* - * We keep the reference to the task struct even if - * the thread dies to avoid that the interrupt code - * references an already freed task_struct. - */ - get_task_struct(t); - new->thread = t; - /* - * Tell the thread to set its affinity. This is - * important for shared interrupt handlers as we do - * not invoke setup_affinity() for the secondary - * handlers as everything is already set up. Even for - * interrupts marked with IRQF_NO_BALANCE this is - * correct as we want the thread to move to the cpu(s) - * on which the requesting code placed the interrupt. - */ - set_bit(IRQTF_AFFINITY, &new->thread_flags); } if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { @@ -1267,7 +1328,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irq, nmsk, omsk); } - new->irq = irq; *old_ptr = new; irq_pm_install_action(desc, new); @@ -1293,6 +1353,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) */ if (new->thread) wake_up_process(new->thread); + if (new->secondary) + wake_up_process(new->secondary->thread); register_irq_proc(irq, desc); new->dir = NULL; @@ -1323,6 +1385,13 @@ out_thread: kthread_stop(t); put_task_struct(t); } + if (new->secondary && new->secondary->thread) { + struct task_struct *t = new->secondary->thread; + + new->secondary->thread = NULL; + kthread_stop(t); + put_task_struct(t); + } out_mput: module_put(desc->owner); return ret; @@ -1394,6 +1463,7 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) /* If this was the last handler, shut down the IRQ line: */ if (!desc->action) { + irq_settings_clr_disable_unlazy(desc); irq_shutdown(desc); irq_release_resources(desc); } @@ -1430,9 +1500,14 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) if (action->thread) { kthread_stop(action->thread); put_task_struct(action->thread); + if (action->secondary && action->secondary->thread) { + kthread_stop(action->secondary->thread); + put_task_struct(action->secondary->thread); + } } module_put(desc->owner); + kfree(action->secondary); return action; } @@ -1576,8 +1651,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, retval = __setup_irq(irq, desc, action); chip_bus_sync_unlock(desc); - if (retval) + if (retval) { + kfree(action->secondary); kfree(action); + } #ifdef CONFIG_DEBUG_SHIRQ_FIXME if (!retval && (irqflags & IRQF_SHARED)) { diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 7e6512b..6b0c0b7 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -228,22 +228,18 @@ static void msi_domain_update_chip_ops(struct msi_domain_info *info) { struct irq_chip *chip = info->chip; - BUG_ON(!chip); - if (!chip->irq_mask) - chip->irq_mask = pci_msi_mask_irq; - if (!chip->irq_unmask) - chip->irq_unmask = pci_msi_unmask_irq; + BUG_ON(!chip || !chip->irq_mask || !chip->irq_unmask); if (!chip->irq_set_affinity) chip->irq_set_affinity = msi_domain_set_affinity; } /** * msi_create_irq_domain - Create a MSI interrupt domain - * @of_node: Optional device-tree node of the interrupt controller + * @fwnode: Optional fwnode of the interrupt controller * @info: MSI domain info * @parent: Parent irq domain */ -struct irq_domain *msi_create_irq_domain(struct device_node *node, +struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent) { @@ -252,8 +248,8 @@ struct irq_domain *msi_create_irq_domain(struct device_node *node, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) msi_domain_update_chip_ops(info); - return irq_domain_add_hierarchy(parent, 0, 0, node, &msi_domain_ops, - info); + return irq_domain_create_hierarchy(parent, 0, 0, fwnode, + &msi_domain_ops, info); } /** diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index a50ddc9..a916cf1 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -475,7 +475,7 @@ int show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(j) any_count |= kstat_irqs_cpu(i, j); action = desc->action; - if (!action && !any_count) + if ((!action || action == &chained_action) && !any_count) goto out; seq_printf(p, "%*d: ", prec, i); diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 3320b84..320579d 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -15,6 +15,7 @@ enum { _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, _IRQ_IS_POLLED = IRQ_IS_POLLED, + _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; @@ -28,6 +29,7 @@ enum { #define IRQ_NESTED_THREAD GOT_YOU_MORON #define IRQ_PER_CPU_DEVID GOT_YOU_MORON #define IRQ_IS_POLLED GOT_YOU_MORON +#define IRQ_DISABLE_UNLAZY GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON @@ -154,3 +156,13 @@ static inline bool irq_settings_is_polled(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_IS_POLLED; } + +static inline bool irq_settings_disable_unlazy(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_DISABLE_UNLAZY; +} + +static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc) +{ + desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY; +} diff --git a/kernel/kmod.c b/kernel/kmod.c index da98d05..0277d12 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -327,9 +327,13 @@ static void call_usermodehelper_exec_work(struct work_struct *work) call_usermodehelper_exec_sync(sub_info); } else { pid_t pid; - + /* + * Use CLONE_PARENT to reparent it to kthreadd; we do not + * want to pollute current->children, and we need a parent + * that always ignores SIGCHLD to ensure auto-reaping. + */ pid = kernel_thread(call_usermodehelper_exec_async, sub_info, - SIGCHLD); + CLONE_PARENT | SIGCHLD); if (pid < 0) { sub_info->retval = pid; umh_complete(sub_info); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 3224418..8ef1919 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -17,12 +17,14 @@ * * Copyright (C) IBM Corporation, 2014 * - * Author: Paul E. McKenney <paulmck@us.ibm.com> + * Authors: Paul E. McKenney <paulmck@us.ibm.com> + * Davidlohr Bueso <dave@stgolabs.net> * Based on kernel/rcu/torture.c. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/kthread.h> +#include <linux/sched/rt.h> #include <linux/spinlock.h> #include <linux/rwlock.h> #include <linux/mutex.h> @@ -34,6 +36,7 @@ #include <linux/moduleparam.h> #include <linux/delay.h> #include <linux/slab.h> +#include <linux/percpu-rwsem.h> #include <linux/torture.h> MODULE_LICENSE("GPL"); @@ -91,11 +94,13 @@ struct lock_torture_ops { void (*init)(void); int (*writelock)(void); void (*write_delay)(struct torture_random_state *trsp); + void (*task_boost)(struct torture_random_state *trsp); void (*writeunlock)(void); int (*readlock)(void); void (*read_delay)(struct torture_random_state *trsp); void (*readunlock)(void); - unsigned long flags; + + unsigned long flags; /* for irq spinlocks */ const char *name; }; @@ -139,9 +144,15 @@ static void torture_lock_busted_write_unlock(void) /* BUGGY, do not use in real life!!! */ } +static void torture_boost_dummy(struct torture_random_state *trsp) +{ + /* Only rtmutexes care about priority */ +} + static struct lock_torture_ops lock_busted_ops = { .writelock = torture_lock_busted_write_lock, .write_delay = torture_lock_busted_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_lock_busted_write_unlock, .readlock = NULL, .read_delay = NULL, @@ -185,6 +196,7 @@ static void torture_spin_lock_write_unlock(void) __releases(torture_spinlock) static struct lock_torture_ops spin_lock_ops = { .writelock = torture_spin_lock_write_lock, .write_delay = torture_spin_lock_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_spin_lock_write_unlock, .readlock = NULL, .read_delay = NULL, @@ -211,6 +223,7 @@ __releases(torture_spinlock) static struct lock_torture_ops spin_lock_irq_ops = { .writelock = torture_spin_lock_write_lock_irq, .write_delay = torture_spin_lock_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_lock_spin_write_unlock_irq, .readlock = NULL, .read_delay = NULL, @@ -275,6 +288,7 @@ static void torture_rwlock_read_unlock(void) __releases(torture_rwlock) static struct lock_torture_ops rw_lock_ops = { .writelock = torture_rwlock_write_lock, .write_delay = torture_rwlock_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_rwlock_write_unlock, .readlock = torture_rwlock_read_lock, .read_delay = torture_rwlock_read_delay, @@ -315,6 +329,7 @@ __releases(torture_rwlock) static struct lock_torture_ops rw_lock_irq_ops = { .writelock = torture_rwlock_write_lock_irq, .write_delay = torture_rwlock_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_rwlock_write_unlock_irq, .readlock = torture_rwlock_read_lock_irq, .read_delay = torture_rwlock_read_delay, @@ -354,6 +369,7 @@ static void torture_mutex_unlock(void) __releases(torture_mutex) static struct lock_torture_ops mutex_lock_ops = { .writelock = torture_mutex_lock, .write_delay = torture_mutex_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_mutex_unlock, .readlock = NULL, .read_delay = NULL, @@ -361,6 +377,90 @@ static struct lock_torture_ops mutex_lock_ops = { .name = "mutex_lock" }; +#ifdef CONFIG_RT_MUTEXES +static DEFINE_RT_MUTEX(torture_rtmutex); + +static int torture_rtmutex_lock(void) __acquires(torture_rtmutex) +{ + rt_mutex_lock(&torture_rtmutex); + return 0; +} + +static void torture_rtmutex_boost(struct torture_random_state *trsp) +{ + int policy; + struct sched_param param; + const unsigned int factor = 50000; /* yes, quite arbitrary */ + + if (!rt_task(current)) { + /* + * (1) Boost priority once every ~50k operations. When the + * task tries to take the lock, the rtmutex it will account + * for the new priority, and do any corresponding pi-dance. + */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * factor))) { + policy = SCHED_FIFO; + param.sched_priority = MAX_RT_PRIO - 1; + } else /* common case, do nothing */ + return; + } else { + /* + * The task will remain boosted for another ~500k operations, + * then restored back to its original prio, and so forth. + * + * When @trsp is nil, we want to force-reset the task for + * stopping the kthread. + */ + if (!trsp || !(torture_random(trsp) % + (cxt.nrealwriters_stress * factor * 2))) { + policy = SCHED_NORMAL; + param.sched_priority = 0; + } else /* common case, do nothing */ + return; + } + + sched_setscheduler_nocheck(current, policy, ¶m); +} + +static void torture_rtmutex_delay(struct torture_random_state *trsp) +{ + const unsigned long shortdelay_us = 2; + const unsigned long longdelay_ms = 100; + + /* + * We want a short delay mostly to emulate likely code, and + * we want a long delay occasionally to force massive contention. + */ + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms); + if (!(torture_random(trsp) % + (cxt.nrealwriters_stress * 2 * shortdelay_us))) + udelay(shortdelay_us); +#ifdef CONFIG_PREEMPT + if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) + preempt_schedule(); /* Allow test to be preempted. */ +#endif +} + +static void torture_rtmutex_unlock(void) __releases(torture_rtmutex) +{ + rt_mutex_unlock(&torture_rtmutex); +} + +static struct lock_torture_ops rtmutex_lock_ops = { + .writelock = torture_rtmutex_lock, + .write_delay = torture_rtmutex_delay, + .task_boost = torture_rtmutex_boost, + .writeunlock = torture_rtmutex_unlock, + .readlock = NULL, + .read_delay = NULL, + .readunlock = NULL, + .name = "rtmutex_lock" +}; +#endif + static DECLARE_RWSEM(torture_rwsem); static int torture_rwsem_down_write(void) __acquires(torture_rwsem) { @@ -419,6 +519,7 @@ static void torture_rwsem_up_read(void) __releases(torture_rwsem) static struct lock_torture_ops rwsem_lock_ops = { .writelock = torture_rwsem_down_write, .write_delay = torture_rwsem_write_delay, + .task_boost = torture_boost_dummy, .writeunlock = torture_rwsem_up_write, .readlock = torture_rwsem_down_read, .read_delay = torture_rwsem_read_delay, @@ -426,6 +527,48 @@ static struct lock_torture_ops rwsem_lock_ops = { .name = "rwsem_lock" }; +#include <linux/percpu-rwsem.h> +static struct percpu_rw_semaphore pcpu_rwsem; + +void torture_percpu_rwsem_init(void) +{ + BUG_ON(percpu_init_rwsem(&pcpu_rwsem)); +} + +static int torture_percpu_rwsem_down_write(void) __acquires(pcpu_rwsem) +{ + percpu_down_write(&pcpu_rwsem); + return 0; +} + +static void torture_percpu_rwsem_up_write(void) __releases(pcpu_rwsem) +{ + percpu_up_write(&pcpu_rwsem); +} + +static int torture_percpu_rwsem_down_read(void) __acquires(pcpu_rwsem) +{ + percpu_down_read(&pcpu_rwsem); + return 0; +} + +static void torture_percpu_rwsem_up_read(void) __releases(pcpu_rwsem) +{ + percpu_up_read(&pcpu_rwsem); +} + +static struct lock_torture_ops percpu_rwsem_lock_ops = { + .init = torture_percpu_rwsem_init, + .writelock = torture_percpu_rwsem_down_write, + .write_delay = torture_rwsem_write_delay, + .task_boost = torture_boost_dummy, + .writeunlock = torture_percpu_rwsem_up_write, + .readlock = torture_percpu_rwsem_down_read, + .read_delay = torture_rwsem_read_delay, + .readunlock = torture_percpu_rwsem_up_read, + .name = "percpu_rwsem_lock" +}; + /* * Lock torture writer kthread. Repeatedly acquires and releases * the lock, checking for duplicate acquisitions. @@ -442,6 +585,7 @@ static int lock_torture_writer(void *arg) if ((torture_random(&rand) & 0xfffff) == 0) schedule_timeout_uninterruptible(1); + cxt.cur_ops->task_boost(&rand); cxt.cur_ops->writelock(); if (WARN_ON_ONCE(lock_is_write_held)) lwsp->n_lock_fail++; @@ -456,6 +600,8 @@ static int lock_torture_writer(void *arg) stutter_wait("lock_torture_writer"); } while (!torture_must_stop()); + + cxt.cur_ops->task_boost(NULL); /* reset prio */ torture_kthread_stopping("lock_torture_writer"); return 0; } @@ -642,7 +788,11 @@ static int __init lock_torture_init(void) &spin_lock_ops, &spin_lock_irq_ops, &rw_lock_ops, &rw_lock_irq_ops, &mutex_lock_ops, +#ifdef CONFIG_RT_MUTEXES + &rtmutex_lock_ops, +#endif &rwsem_lock_ops, + &percpu_rwsem_lock_ops, }; if (!torture_init_begin(torture_type, verbose, &torture_runnable)) @@ -661,11 +811,11 @@ static int __init lock_torture_init(void) for (i = 0; i < ARRAY_SIZE(torture_ops); i++) pr_alert(" %s", torture_ops[i]->name); pr_alert("\n"); - torture_init_end(); - return -EINVAL; + firsterr = -EINVAL; + goto unwind; } if (cxt.cur_ops->init) - cxt.cur_ops->init(); /* no "goto unwind" prior to this point!!! */ + cxt.cur_ops->init(); if (nwriters_stress >= 0) cxt.nrealwriters_stress = nwriters_stress; @@ -676,6 +826,10 @@ static int __init lock_torture_init(void) if (strncmp(torture_type, "mutex", 5) == 0) cxt.debug_lock = true; #endif +#ifdef CONFIG_DEBUG_RT_MUTEXES + if (strncmp(torture_type, "rtmutex", 7) == 0) + cxt.debug_lock = true; +#endif #ifdef CONFIG_DEBUG_SPINLOCK if ((strncmp(torture_type, "spin", 4) == 0) || (strncmp(torture_type, "rw_lock", 7) == 0)) diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index fd91aaa..5b9102a 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -67,7 +67,7 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) node->locked = 0; node->next = NULL; - prev = xchg(lock, node); + prev = xchg_acquire(lock, node); if (likely(prev == NULL)) { /* * Lock acquired, don't need to set node->locked to 1. Threads @@ -98,7 +98,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) /* * Release the lock by setting it to NULL */ - if (likely(cmpxchg(lock, node, NULL) == node)) + if (likely(cmpxchg_release(lock, node, NULL) == node)) return; /* Wait until the next pointer is set */ while (!(next = READ_ONCE(node->next))) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 4cccea6..0551c21 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -277,7 +277,7 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) static inline bool mutex_try_to_acquire(struct mutex *lock) { return !mutex_is_locked(lock) && - (atomic_cmpxchg(&lock->count, 1, 0) == 1); + (atomic_cmpxchg_acquire(&lock->count, 1, 0) == 1); } /* @@ -529,7 +529,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * Once more, try to acquire the lock. Only try-lock the mutex if * it is unlocked to reduce unnecessary xchg() operations. */ - if (!mutex_is_locked(lock) && (atomic_xchg(&lock->count, 0) == 1)) + if (!mutex_is_locked(lock) && + (atomic_xchg_acquire(&lock->count, 0) == 1)) goto skip_wait; debug_mutex_lock_common(lock, &waiter); @@ -553,7 +554,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * non-negative in order to avoid unnecessary xchg operations: */ if (atomic_read(&lock->count) >= 0 && - (atomic_xchg(&lock->count, -1) == 1)) + (atomic_xchg_acquire(&lock->count, -1) == 1)) break; /* @@ -867,7 +868,7 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) spin_lock_mutex(&lock->wait_lock, flags); - prev = atomic_xchg(&lock->count, -1); + prev = atomic_xchg_acquire(&lock->count, -1); if (likely(prev == 1)) { mutex_set_owner(lock); mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index dc85ee2..d092a0c 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -50,7 +50,7 @@ osq_wait_next(struct optimistic_spin_queue *lock, for (;;) { if (atomic_read(&lock->tail) == curr && - atomic_cmpxchg(&lock->tail, curr, old) == curr) { + atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) { /* * We were the last queued, we moved @lock back. @prev * will now observe @lock and will complete its @@ -92,7 +92,11 @@ bool osq_lock(struct optimistic_spin_queue *lock) node->next = NULL; node->cpu = curr; - old = atomic_xchg(&lock->tail, curr); + /* + * ACQUIRE semantics, pairs with corresponding RELEASE + * in unlock() uncontended, or fastpath. + */ + old = atomic_xchg_acquire(&lock->tail, curr); if (old == OSQ_UNLOCKED_VAL) return true; @@ -184,7 +188,8 @@ void osq_unlock(struct optimistic_spin_queue *lock) /* * Fast path for the uncontended case. */ - if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr)) + if (likely(atomic_cmpxchg_release(&lock->tail, curr, + OSQ_UNLOCKED_VAL) == curr)) return; /* diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index f325672..f231e0b 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -17,50 +17,43 @@ int __percpu_init_rwsem(struct percpu_rw_semaphore *brw, /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ __init_rwsem(&brw->rw_sem, name, rwsem_key); - atomic_set(&brw->write_ctr, 0); + rcu_sync_init(&brw->rss, RCU_SCHED_SYNC); atomic_set(&brw->slow_read_ctr, 0); init_waitqueue_head(&brw->write_waitq); return 0; } +EXPORT_SYMBOL_GPL(__percpu_init_rwsem); void percpu_free_rwsem(struct percpu_rw_semaphore *brw) { + /* + * XXX: temporary kludge. The error path in alloc_super() + * assumes that percpu_free_rwsem() is safe after kzalloc(). + */ + if (!brw->fast_read_ctr) + return; + + rcu_sync_dtor(&brw->rss); free_percpu(brw->fast_read_ctr); brw->fast_read_ctr = NULL; /* catch use after free bugs */ } /* - * This is the fast-path for down_read/up_read, it only needs to ensure - * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the - * fast per-cpu counter. The writer uses synchronize_sched_expedited() to - * serialize with the preempt-disabled section below. - * - * The nontrivial part is that we should guarantee acquire/release semantics - * in case when - * - * R_W: down_write() comes after up_read(), the writer should see all - * changes done by the reader - * or - * W_R: down_read() comes after up_write(), the reader should see all - * changes done by the writer + * This is the fast-path for down_read/up_read. If it succeeds we rely + * on the barriers provided by rcu_sync_enter/exit; see the comments in + * percpu_down_write() and percpu_up_write(). * * If this helper fails the callers rely on the normal rw_semaphore and * atomic_dec_and_test(), so in this case we have the necessary barriers. - * - * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or - * __this_cpu_add() below can be reordered with any LOAD/STORE done by the - * reader inside the critical section. See the comments in down_write and - * up_write below. */ static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) { - bool success = false; + bool success; preempt_disable(); - if (likely(!atomic_read(&brw->write_ctr))) { + success = rcu_sync_is_idle(&brw->rss); + if (likely(success)) __this_cpu_add(*brw->fast_read_ctr, val); - success = true; - } preempt_enable(); return success; @@ -77,16 +70,17 @@ static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) void percpu_down_read(struct percpu_rw_semaphore *brw) { might_sleep(); - if (likely(update_fast_ctr(brw, +1))) { - rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); + rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); + + if (likely(update_fast_ctr(brw, +1))) return; - } - down_read(&brw->rw_sem); + /* Avoid rwsem_acquire_read() and rwsem_release() */ + __down_read(&brw->rw_sem); atomic_inc(&brw->slow_read_ctr); - /* avoid up_read()->rwsem_release() */ __up_read(&brw->rw_sem); } +EXPORT_SYMBOL_GPL(percpu_down_read); int percpu_down_read_trylock(struct percpu_rw_semaphore *brw) { @@ -112,6 +106,7 @@ void percpu_up_read(struct percpu_rw_semaphore *brw) if (atomic_dec_and_test(&brw->slow_read_ctr)) wake_up_all(&brw->write_waitq); } +EXPORT_SYMBOL_GPL(percpu_up_read); static int clear_fast_ctr(struct percpu_rw_semaphore *brw) { @@ -126,33 +121,17 @@ static int clear_fast_ctr(struct percpu_rw_semaphore *brw) return sum; } -/* - * A writer increments ->write_ctr to force the readers to switch to the - * slow mode, note the atomic_read() check in update_fast_ctr(). - * - * After that the readers can only inc/dec the slow ->slow_read_ctr counter, - * ->fast_read_ctr is stable. Once the writer moves its sum into the slow - * counter it represents the number of active readers. - * - * Finally the writer takes ->rw_sem for writing and blocks the new readers, - * then waits until the slow counter becomes zero. - */ void percpu_down_write(struct percpu_rw_semaphore *brw) { - /* tell update_fast_ctr() there is a pending writer */ - atomic_inc(&brw->write_ctr); /* - * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read - * so that update_fast_ctr() can't succeed. - * - * 2. Ensures we see the result of every previous this_cpu_add() in - * update_fast_ctr(). + * Make rcu_sync_is_idle() == F and thus disable the fast-path in + * percpu_down_read() and percpu_up_read(), and wait for gp pass. * - * 3. Ensures that if any reader has exited its critical section via - * fast-path, it executes a full memory barrier before we return. - * See R_W case in the comment above update_fast_ctr(). + * The latter synchronises us with the preceding readers which used + * the fast-past, so we can not miss the result of __this_cpu_add() + * or anything else inside their criticial sections. */ - synchronize_sched_expedited(); + rcu_sync_enter(&brw->rss); /* exclude other writers, and block the new readers completely */ down_write(&brw->rw_sem); @@ -163,16 +142,17 @@ void percpu_down_write(struct percpu_rw_semaphore *brw) /* wait for all readers to complete their percpu_up_read() */ wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr)); } +EXPORT_SYMBOL_GPL(percpu_down_write); void percpu_up_write(struct percpu_rw_semaphore *brw) { /* release the lock, but the readers can't use the fast-path */ up_write(&brw->rw_sem); /* - * Insert the barrier before the next fast-path in down_read, - * see W_R case in the comment above update_fast_ctr(). + * Enable the fast-path in percpu_down_read() and percpu_up_read() + * but only after another gp pass; this adds the necessary barrier + * to ensure the reader can't miss the changes done by us. */ - synchronize_sched_expedited(); - /* the last writer unblocks update_fast_ctr() */ - atomic_dec(&brw->write_ctr); + rcu_sync_exit(&brw->rss); } +EXPORT_SYMBOL_GPL(percpu_up_write); diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index f17a3e3..fec0823 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -86,7 +86,7 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts) /* * Put the reader into the wait queue */ - arch_spin_lock(&lock->lock); + arch_spin_lock(&lock->wait_lock); /* * The ACQUIRE semantics of the following spinning code ensure @@ -99,7 +99,7 @@ void queued_read_lock_slowpath(struct qrwlock *lock, u32 cnts) /* * Signal the next one in queue to become queue head */ - arch_spin_unlock(&lock->lock); + arch_spin_unlock(&lock->wait_lock); } EXPORT_SYMBOL(queued_read_lock_slowpath); @@ -112,7 +112,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock) u32 cnts; /* Put the writer into the wait queue */ - arch_spin_lock(&lock->lock); + arch_spin_lock(&lock->wait_lock); /* Try to acquire the lock directly if no reader is present */ if (!atomic_read(&lock->cnts) && @@ -144,6 +144,6 @@ void queued_write_lock_slowpath(struct qrwlock *lock) cpu_relax_lowlatency(); } unlock: - arch_spin_unlock(&lock->lock); + arch_spin_unlock(&lock->wait_lock); } EXPORT_SYMBOL(queued_write_lock_slowpath); diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index c8e6e9a..f0450ff 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -267,7 +267,6 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node) } if (!lp) { /* ONCE */ - WRITE_ONCE(pn->state, vcpu_hashed); lp = pv_hash(lock, pn); /* @@ -275,11 +274,9 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node) * when we observe _Q_SLOW_VAL in __pv_queued_spin_unlock() * we'll be sure to be able to observe our hash entry. * - * [S] pn->state * [S] <hash> [Rmw] l->locked == _Q_SLOW_VAL * MB RMB * [RmW] l->locked = _Q_SLOW_VAL [L] <unhash> - * [L] pn->state * * Matches the smp_rmb() in __pv_queued_spin_unlock(). */ @@ -364,8 +361,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock) * vCPU is harmless other than the additional latency in completing * the unlock. */ - if (READ_ONCE(node->state) == vcpu_hashed) - pv_kick(node->cpu); + pv_kick(node->cpu); } /* * Include the architecture specific callee-save thunk of the diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 7781d80..bbb72b4 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -74,14 +74,23 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) * set up. */ #ifndef CONFIG_DEBUG_RT_MUTEXES -# define rt_mutex_cmpxchg(l,c,n) (cmpxchg(&l->owner, c, n) == c) +# define rt_mutex_cmpxchg_relaxed(l,c,n) (cmpxchg_relaxed(&l->owner, c, n) == c) +# define rt_mutex_cmpxchg_acquire(l,c,n) (cmpxchg_acquire(&l->owner, c, n) == c) +# define rt_mutex_cmpxchg_release(l,c,n) (cmpxchg_release(&l->owner, c, n) == c) + +/* + * Callers must hold the ->wait_lock -- which is the whole purpose as we force + * all future threads that attempt to [Rmw] the lock to the slowpath. As such + * relaxed semantics suffice. + */ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) { unsigned long owner, *p = (unsigned long *) &lock->owner; do { owner = *p; - } while (cmpxchg(p, owner, owner | RT_MUTEX_HAS_WAITERS) != owner); + } while (cmpxchg_relaxed(p, owner, + owner | RT_MUTEX_HAS_WAITERS) != owner); } /* @@ -121,11 +130,14 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) * lock(wait_lock); * acquire(lock); */ - return rt_mutex_cmpxchg(lock, owner, NULL); + return rt_mutex_cmpxchg_release(lock, owner, NULL); } #else -# define rt_mutex_cmpxchg(l,c,n) (0) +# define rt_mutex_cmpxchg_relaxed(l,c,n) (0) +# define rt_mutex_cmpxchg_acquire(l,c,n) (0) +# define rt_mutex_cmpxchg_release(l,c,n) (0) + static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) { lock->owner = (struct task_struct *) @@ -1321,7 +1333,7 @@ rt_mutex_fastlock(struct rt_mutex *lock, int state, struct hrtimer_sleeper *timeout, enum rtmutex_chainwalk chwalk)) { - if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else @@ -1337,7 +1349,7 @@ rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, enum rtmutex_chainwalk chwalk)) { if (chwalk == RT_MUTEX_MIN_CHAINWALK && - likely(rt_mutex_cmpxchg(lock, NULL, current))) { + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 0; } else @@ -1348,7 +1360,7 @@ static inline int rt_mutex_fasttrylock(struct rt_mutex *lock, int (*slowfn)(struct rt_mutex *lock)) { - if (likely(rt_mutex_cmpxchg(lock, NULL, current))) { + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) { rt_mutex_deadlock_account_lock(lock, current); return 1; } @@ -1362,7 +1374,7 @@ rt_mutex_fastunlock(struct rt_mutex *lock, { WAKE_Q(wake_q); - if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { rt_mutex_deadlock_account_unlock(current); } else { @@ -1484,7 +1496,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_unlock); bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock, struct wake_q_head *wqh) { - if (likely(rt_mutex_cmpxchg(lock, current, NULL))) { + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { rt_mutex_deadlock_account_unlock(current); return false; } diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 0f18971..a4d4de0 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -262,7 +262,7 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem) * to reduce unnecessary expensive cmpxchg() operations. */ if (count == RWSEM_WAITING_BIAS && - cmpxchg(&sem->count, RWSEM_WAITING_BIAS, + cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, RWSEM_ACTIVE_WRITE_BIAS) == RWSEM_WAITING_BIAS) { if (!list_is_singular(&sem->wait_list)) rwsem_atomic_update(RWSEM_WAITING_BIAS, sem); @@ -285,7 +285,8 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) if (!(count == 0 || count == RWSEM_WAITING_BIAS)) return false; - old = cmpxchg(&sem->count, count, count + RWSEM_ACTIVE_WRITE_BIAS); + old = cmpxchg_acquire(&sem->count, count, + count + RWSEM_ACTIVE_WRITE_BIAS); if (old == count) { rwsem_set_owner(sem); return true; diff --git a/kernel/memremap.c b/kernel/memremap.c index 72b0c66..9d6b555 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -24,6 +24,16 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) } #endif +static void *try_ram_remap(resource_size_t offset, size_t size) +{ + struct page *page = pfn_to_page(offset >> PAGE_SHIFT); + + /* In the simple case just return the existing linear address */ + if (!PageHighMem(page)) + return __va(offset); + return NULL; /* fallback to ioremap_cache */ +} + /** * memremap() - remap an iomem_resource as cacheable memory * @offset: iomem resource start address @@ -66,8 +76,8 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) * the requested range is potentially in "System RAM" */ if (is_ram == REGION_INTERSECTS) - addr = __va(offset); - else + addr = try_ram_remap(offset, size); + if (!addr) addr = ioremap_cache(offset, size); } diff --git a/kernel/module.c b/kernel/module.c index b86b7bf..8f051a1 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1063,11 +1063,15 @@ void symbol_put_addr(void *addr) if (core_kernel_text(a)) return; - /* module_text_address is safe here: we're supposed to have reference - * to module from symbol_get, so it can't go away. */ + /* + * Even though we hold a reference on the module; we still need to + * disable preemption in order to safely traverse the data structure. + */ + preempt_disable(); modaddr = __module_text_address(a); BUG_ON(!modaddr); module_put(modaddr); + preempt_enable(); } EXPORT_SYMBOL_GPL(symbol_put_addr); diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 50a8084..61a1656 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -1,4 +1,4 @@ -obj-y += update.o +obj-y += update.o sync.o obj-$(CONFIG_SRCU) += srcu.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_TREE_RCU) += tree.o diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 7719295..d89328e 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -252,7 +252,7 @@ struct rcu_torture_ops { void (*exp_sync)(void); unsigned long (*get_state)(void); void (*cond_sync)(unsigned long oldstate); - void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); + call_rcu_func_t call; void (*cb_barrier)(void); void (*fqs)(void); void (*stats)(void); @@ -448,7 +448,7 @@ static void synchronize_rcu_busted(void) } static void -call_rcu_busted(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +call_rcu_busted(struct rcu_head *head, rcu_callback_t func) { /* This is a deliberate bug for testing purposes only! */ func(head); @@ -523,7 +523,7 @@ static void srcu_torture_synchronize(void) } static void srcu_torture_call(struct rcu_head *head, - void (*func)(struct rcu_head *head)) + rcu_callback_t func) { call_srcu(srcu_ctlp, head, func); } @@ -695,7 +695,7 @@ static bool __maybe_unused torturing_tasks(void) #define RCUTORTURE_TASKS_OPS -static bool torturing_tasks(void) +static bool __maybe_unused torturing_tasks(void) { return false; } @@ -768,7 +768,6 @@ static int rcu_torture_boost(void *arg) } call_rcu_time = jiffies; } - cond_resched_rcu_qs(); stutter_wait("rcu_torture_boost"); if (torture_must_stop()) goto checkwait; @@ -1208,7 +1207,6 @@ rcu_torture_reader(void *arg) __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); cur_ops->readunlock(idx); - cond_resched_rcu_qs(); stutter_wait("rcu_torture_reader"); } while (!torture_must_stop()); if (irqreader && cur_ops->irq_capable) { @@ -1742,15 +1740,15 @@ rcu_torture_init(void) for (i = 0; i < ARRAY_SIZE(torture_ops); i++) pr_alert(" %s", torture_ops[i]->name); pr_alert("\n"); - torture_init_end(); - return -EINVAL; + firsterr = -EINVAL; + goto unwind; } if (cur_ops->fqs == NULL && fqs_duration != 0) { pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n"); fqs_duration = 0; } if (cur_ops->init) - cur_ops->init(); /* no "goto unwind" prior to this point!!! */ + cur_ops->init(); if (nreaders >= 0) { nrealreaders = nreaders; diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index d3fcb2e..a63a1ea 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -298,11 +298,9 @@ int __srcu_read_lock(struct srcu_struct *sp) int idx; idx = READ_ONCE(sp->completed) & 0x1; - preempt_disable(); __this_cpu_inc(sp->per_cpu_ref->c[idx]); smp_mb(); /* B */ /* Avoid leaking the critical section. */ __this_cpu_inc(sp->per_cpu_ref->seq[idx]); - preempt_enable(); return idx; } EXPORT_SYMBOL_GPL(__srcu_read_lock); @@ -387,7 +385,7 @@ static void srcu_flip(struct srcu_struct *sp) * srcu_struct structure. */ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, - void (*func)(struct rcu_head *head)) + rcu_callback_t func) { unsigned long flags; diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c new file mode 100644 index 0000000..be922c9 --- /dev/null +++ b/kernel/rcu/sync.c @@ -0,0 +1,223 @@ +/* + * RCU-based infrastructure for lightweight reader-writer locking + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, you can access it online at + * http://www.gnu.org/licenses/gpl-2.0.html. + * + * Copyright (c) 2015, Red Hat, Inc. + * + * Author: Oleg Nesterov <oleg@redhat.com> + */ + +#include <linux/rcu_sync.h> +#include <linux/sched.h> + +#ifdef CONFIG_PROVE_RCU +#define __INIT_HELD(func) .held = func, +#else +#define __INIT_HELD(func) +#endif + +static const struct { + void (*sync)(void); + void (*call)(struct rcu_head *, void (*)(struct rcu_head *)); + void (*wait)(void); +#ifdef CONFIG_PROVE_RCU + int (*held)(void); +#endif +} gp_ops[] = { + [RCU_SYNC] = { + .sync = synchronize_rcu, + .call = call_rcu, + .wait = rcu_barrier, + __INIT_HELD(rcu_read_lock_held) + }, + [RCU_SCHED_SYNC] = { + .sync = synchronize_sched, + .call = call_rcu_sched, + .wait = rcu_barrier_sched, + __INIT_HELD(rcu_read_lock_sched_held) + }, + [RCU_BH_SYNC] = { + .sync = synchronize_rcu_bh, + .call = call_rcu_bh, + .wait = rcu_barrier_bh, + __INIT_HELD(rcu_read_lock_bh_held) + }, +}; + +enum { GP_IDLE = 0, GP_PENDING, GP_PASSED }; +enum { CB_IDLE = 0, CB_PENDING, CB_REPLAY }; + +#define rss_lock gp_wait.lock + +#ifdef CONFIG_PROVE_RCU +void rcu_sync_lockdep_assert(struct rcu_sync *rsp) +{ + RCU_LOCKDEP_WARN(!gp_ops[rsp->gp_type].held(), + "suspicious rcu_sync_is_idle() usage"); +} +#endif + +/** + * rcu_sync_init() - Initialize an rcu_sync structure + * @rsp: Pointer to rcu_sync structure to be initialized + * @type: Flavor of RCU with which to synchronize rcu_sync structure + */ +void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type) +{ + memset(rsp, 0, sizeof(*rsp)); + init_waitqueue_head(&rsp->gp_wait); + rsp->gp_type = type; +} + +/** + * rcu_sync_enter() - Force readers onto slowpath + * @rsp: Pointer to rcu_sync structure to use for synchronization + * + * This function is used by updaters who need readers to make use of + * a slowpath during the update. After this function returns, all + * subsequent calls to rcu_sync_is_idle() will return false, which + * tells readers to stay off their fastpaths. A later call to + * rcu_sync_exit() re-enables reader slowpaths. + * + * When called in isolation, rcu_sync_enter() must wait for a grace + * period, however, closely spaced calls to rcu_sync_enter() can + * optimize away the grace-period wait via a state machine implemented + * by rcu_sync_enter(), rcu_sync_exit(), and rcu_sync_func(). + */ +void rcu_sync_enter(struct rcu_sync *rsp) +{ + bool need_wait, need_sync; + + spin_lock_irq(&rsp->rss_lock); + need_wait = rsp->gp_count++; + need_sync = rsp->gp_state == GP_IDLE; + if (need_sync) + rsp->gp_state = GP_PENDING; + spin_unlock_irq(&rsp->rss_lock); + + BUG_ON(need_wait && need_sync); + + if (need_sync) { + gp_ops[rsp->gp_type].sync(); + rsp->gp_state = GP_PASSED; + wake_up_all(&rsp->gp_wait); + } else if (need_wait) { + wait_event(rsp->gp_wait, rsp->gp_state == GP_PASSED); + } else { + /* + * Possible when there's a pending CB from a rcu_sync_exit(). + * Nobody has yet been allowed the 'fast' path and thus we can + * avoid doing any sync(). The callback will get 'dropped'. + */ + BUG_ON(rsp->gp_state != GP_PASSED); + } +} + +/** + * rcu_sync_func() - Callback function managing reader access to fastpath + * @rsp: Pointer to rcu_sync structure to use for synchronization + * + * This function is passed to one of the call_rcu() functions by + * rcu_sync_exit(), so that it is invoked after a grace period following the + * that invocation of rcu_sync_exit(). It takes action based on events that + * have taken place in the meantime, so that closely spaced rcu_sync_enter() + * and rcu_sync_exit() pairs need not wait for a grace period. + * + * If another rcu_sync_enter() is invoked before the grace period + * ended, reset state to allow the next rcu_sync_exit() to let the + * readers back onto their fastpaths (after a grace period). If both + * another rcu_sync_enter() and its matching rcu_sync_exit() are invoked + * before the grace period ended, re-invoke call_rcu() on behalf of that + * rcu_sync_exit(). Otherwise, set all state back to idle so that readers + * can again use their fastpaths. + */ +static void rcu_sync_func(struct rcu_head *rcu) +{ + struct rcu_sync *rsp = container_of(rcu, struct rcu_sync, cb_head); + unsigned long flags; + + BUG_ON(rsp->gp_state != GP_PASSED); + BUG_ON(rsp->cb_state == CB_IDLE); + + spin_lock_irqsave(&rsp->rss_lock, flags); + if (rsp->gp_count) { + /* + * A new rcu_sync_begin() has happened; drop the callback. + */ + rsp->cb_state = CB_IDLE; + } else if (rsp->cb_state == CB_REPLAY) { + /* + * A new rcu_sync_exit() has happened; requeue the callback + * to catch a later GP. + */ + rsp->cb_state = CB_PENDING; + gp_ops[rsp->gp_type].call(&rsp->cb_head, rcu_sync_func); + } else { + /* + * We're at least a GP after rcu_sync_exit(); eveybody will now + * have observed the write side critical section. Let 'em rip!. + */ + rsp->cb_state = CB_IDLE; + rsp->gp_state = GP_IDLE; + } + spin_unlock_irqrestore(&rsp->rss_lock, flags); +} + +/** + * rcu_sync_exit() - Allow readers back onto fast patch after grace period + * @rsp: Pointer to rcu_sync structure to use for synchronization + * + * This function is used by updaters who have completed, and can therefore + * now allow readers to make use of their fastpaths after a grace period + * has elapsed. After this grace period has completed, all subsequent + * calls to rcu_sync_is_idle() will return true, which tells readers that + * they can once again use their fastpaths. + */ +void rcu_sync_exit(struct rcu_sync *rsp) +{ + spin_lock_irq(&rsp->rss_lock); + if (!--rsp->gp_count) { + if (rsp->cb_state == CB_IDLE) { + rsp->cb_state = CB_PENDING; + gp_ops[rsp->gp_type].call(&rsp->cb_head, rcu_sync_func); + } else if (rsp->cb_state == CB_PENDING) { + rsp->cb_state = CB_REPLAY; + } + } + spin_unlock_irq(&rsp->rss_lock); +} + +/** + * rcu_sync_dtor() - Clean up an rcu_sync structure + * @rsp: Pointer to rcu_sync structure to be cleaned up + */ +void rcu_sync_dtor(struct rcu_sync *rsp) +{ + int cb_state; + + BUG_ON(rsp->gp_count); + + spin_lock_irq(&rsp->rss_lock); + if (rsp->cb_state == CB_REPLAY) + rsp->cb_state = CB_PENDING; + cb_state = rsp->cb_state; + spin_unlock_irq(&rsp->rss_lock); + + if (cb_state != CB_IDLE) { + gp_ops[rsp->gp_type].wait(); + BUG_ON(rsp->cb_state != CB_IDLE); + } +} diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index d047105..944b1b4 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -44,7 +44,7 @@ struct rcu_ctrlblk; static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp); static void rcu_process_callbacks(struct softirq_action *unused); static void __call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *rcu), + rcu_callback_t func, struct rcu_ctrlblk *rcp); #include "tiny_plugin.h" @@ -203,7 +203,7 @@ EXPORT_SYMBOL_GPL(synchronize_sched); * Helper function for call_rcu() and call_rcu_bh(). */ static void __call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *rcu), + rcu_callback_t func, struct rcu_ctrlblk *rcp) { unsigned long flags; @@ -229,7 +229,7 @@ static void __call_rcu(struct rcu_head *head, * period. But since we have but one CPU, that would be after any * quiescent state. */ -void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) { __call_rcu(head, func, &rcu_sched_ctrlblk); } @@ -239,7 +239,7 @@ EXPORT_SYMBOL_GPL(call_rcu_sched); * Post an RCU bottom-half callback to be invoked after any subsequent * quiescent state. */ -void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) { __call_rcu(head, func, &rcu_bh_ctrlblk); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 775d36c..f07343b 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -71,7 +71,6 @@ MODULE_ALIAS("rcutree"); static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS]; -static struct lock_class_key rcu_exp_sched_class[RCU_NUM_LVLS]; /* * In order to export the rcu_state name to the tracing tools, it @@ -98,7 +97,7 @@ struct rcu_state sname##_state = { \ .level = { &sname##_state.node[0] }, \ .rda = &sname##_data, \ .call = cr, \ - .fqs_state = RCU_GP_IDLE, \ + .gp_state = RCU_GP_IDLE, \ .gpnum = 0UL - 300UL, \ .completed = 0UL - 300UL, \ .orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \ @@ -161,6 +160,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); +static void rcu_report_exp_rdp(struct rcu_state *rsp, + struct rcu_data *rdp, bool wake); /* rcuc/rcub kthread realtime priority */ #ifdef CONFIG_RCU_KTHREAD_PRIO @@ -245,21 +246,33 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) */ void rcu_sched_qs(void) { - if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) { + unsigned long flags; + + if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_sched"), __this_cpu_read(rcu_sched_data.gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_sched_data.passed_quiesce, 1); + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); + if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) + return; + local_irq_save(flags); + if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) { + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(&rcu_sched_data), + true); + } + local_irq_restore(flags); } } void rcu_bh_qs(void) { - if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) { + if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_bh"), __this_cpu_read(rcu_bh_data.gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_bh_data.passed_quiesce, 1); + __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); } } @@ -337,12 +350,14 @@ static void rcu_momentary_dyntick_idle(void) */ void rcu_note_context_switch(void) { + barrier(); /* Avoid RCU read-side critical sections leaking down. */ trace_rcu_utilization(TPS("Start context switch")); rcu_sched_qs(); rcu_preempt_note_context_switch(); if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) rcu_momentary_dyntick_idle(); trace_rcu_utilization(TPS("End context switch")); + barrier(); /* Avoid RCU read-side critical sections leaking up. */ } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -353,12 +368,19 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); * RCU flavors in desperate need of a quiescent state, which will normally * be none of them). Either way, do a lightweight quiescent state for * all RCU flavors. + * + * The barrier() calls are redundant in the common case when this is + * called externally, but just in case this is called from within this + * file. + * */ void rcu_all_qs(void) { + barrier(); /* Avoid RCU read-side critical sections leaking down. */ if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) rcu_momentary_dyntick_idle(); this_cpu_inc(rcu_qs_ctr); + barrier(); /* Avoid RCU read-side critical sections leaking up. */ } EXPORT_SYMBOL_GPL(rcu_all_qs); @@ -1744,9 +1766,9 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, */ rdp->gpnum = rnp->gpnum; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart")); - rdp->passed_quiesce = 0; + rdp->cpu_no_qs.b.norm = true; rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); - rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); + rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); WRITE_ONCE(rdp->gpwrap, false); } @@ -1927,16 +1949,15 @@ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) /* * Do one round of quiescent-state forcing. */ -static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) +static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) { - int fqs_state = fqs_state_in; bool isidle = false; unsigned long maxj; struct rcu_node *rnp = rcu_get_root(rsp); WRITE_ONCE(rsp->gp_activity, jiffies); rsp->n_force_qs++; - if (fqs_state == RCU_SAVE_DYNTICK) { + if (first_time) { /* Collect dyntick-idle snapshots. */ if (is_sysidle_rcu_state(rsp)) { isidle = true; @@ -1945,7 +1966,6 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) force_qs_rnp(rsp, dyntick_save_progress_counter, &isidle, &maxj); rcu_sysidle_report_gp(rsp, isidle, maxj); - fqs_state = RCU_FORCE_QS; } else { /* Handle dyntick-idle and offline CPUs. */ isidle = true; @@ -1959,7 +1979,6 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS); raw_spin_unlock_irq(&rnp->lock); } - return fqs_state; } /* @@ -2023,7 +2042,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) /* Declare grace period done. */ WRITE_ONCE(rsp->completed, rsp->gpnum); trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); - rsp->fqs_state = RCU_GP_IDLE; + rsp->gp_state = RCU_GP_IDLE; rdp = this_cpu_ptr(rsp->rda); /* Advance CBs to reduce false positives below. */ needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp; @@ -2041,7 +2060,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) */ static int __noreturn rcu_gp_kthread(void *arg) { - int fqs_state; + bool first_gp_fqs; int gf; unsigned long j; int ret; @@ -2073,7 +2092,7 @@ static int __noreturn rcu_gp_kthread(void *arg) } /* Handle quiescent-state forcing. */ - fqs_state = RCU_SAVE_DYNTICK; + first_gp_fqs = true; j = jiffies_till_first_fqs; if (j > HZ) { j = HZ; @@ -2101,7 +2120,8 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("fqsstart")); - fqs_state = rcu_gp_fqs(rsp, fqs_state); + rcu_gp_fqs(rsp, first_gp_fqs); + first_gp_fqs = false; trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("fqsend")); @@ -2337,7 +2357,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - if ((rdp->passed_quiesce == 0 && + if ((rdp->cpu_no_qs.b.norm && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) || rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum || rdp->gpwrap) { @@ -2348,7 +2368,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * We will instead need a new quiescent state that lies * within the current grace period. */ - rdp->passed_quiesce = 0; /* need qs for new gp. */ + rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); raw_spin_unlock_irqrestore(&rnp->lock, flags); return; @@ -2357,7 +2377,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) if ((rnp->qsmask & mask) == 0) { raw_spin_unlock_irqrestore(&rnp->lock, flags); } else { - rdp->qs_pending = 0; + rdp->core_needs_qs = 0; /* * This GP can't end until cpu checks in, so all of our @@ -2388,14 +2408,14 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Does this CPU still need to do its part for current grace period? * If no, return and let the other CPUs do their part as well. */ - if (!rdp->qs_pending) + if (!rdp->core_needs_qs) return; /* * Was there a quiescent state since the beginning of the grace * period? If no, then exit and wait for the next call. */ - if (!rdp->passed_quiesce && + if (rdp->cpu_no_qs.b.norm && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) return; @@ -3017,7 +3037,7 @@ static void rcu_leak_callback(struct rcu_head *rhp) * is expected to specify a CPU. */ static void -__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), +__call_rcu(struct rcu_head *head, rcu_callback_t func, struct rcu_state *rsp, int cpu, bool lazy) { unsigned long flags; @@ -3088,7 +3108,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), /* * Queue an RCU-sched callback for invocation after a grace period. */ -void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) { __call_rcu(head, func, &rcu_sched_state, -1, 0); } @@ -3097,7 +3117,7 @@ EXPORT_SYMBOL_GPL(call_rcu_sched); /* * Queue an RCU callback for invocation after a quicker grace period. */ -void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) { __call_rcu(head, func, &rcu_bh_state, -1, 0); } @@ -3111,7 +3131,7 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); * function may only be called from __kfree_rcu(). */ void kfree_call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *rcu)) + rcu_callback_t func) { __call_rcu(head, func, rcu_state_p, -1, 1); } @@ -3379,6 +3399,191 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) return rcu_seq_done(&rsp->expedited_sequence, s); } +/* + * Reset the ->expmaskinit values in the rcu_node tree to reflect any + * recent CPU-online activity. Note that these masks are not cleared + * when CPUs go offline, so they reflect the union of all CPUs that have + * ever been online. This means that this function normally takes its + * no-work-to-do fastpath. + */ +static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) +{ + bool done; + unsigned long flags; + unsigned long mask; + unsigned long oldmask; + int ncpus = READ_ONCE(rsp->ncpus); + struct rcu_node *rnp; + struct rcu_node *rnp_up; + + /* If no new CPUs onlined since last time, nothing to do. */ + if (likely(ncpus == rsp->ncpus_snap)) + return; + rsp->ncpus_snap = ncpus; + + /* + * Each pass through the following loop propagates newly onlined + * CPUs for the current rcu_node structure up the rcu_node tree. + */ + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + if (rnp->expmaskinit == rnp->expmaskinitnext) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + continue; /* No new CPUs, nothing to do. */ + } + + /* Update this node's mask, track old value for propagation. */ + oldmask = rnp->expmaskinit; + rnp->expmaskinit = rnp->expmaskinitnext; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + /* If was already nonzero, nothing to propagate. */ + if (oldmask) + continue; + + /* Propagate the new CPU up the tree. */ + mask = rnp->grpmask; + rnp_up = rnp->parent; + done = false; + while (rnp_up) { + raw_spin_lock_irqsave(&rnp_up->lock, flags); + smp_mb__after_unlock_lock(); + if (rnp_up->expmaskinit) + done = true; + rnp_up->expmaskinit |= mask; + raw_spin_unlock_irqrestore(&rnp_up->lock, flags); + if (done) + break; + mask = rnp_up->grpmask; + rnp_up = rnp_up->parent; + } + } +} + +/* + * Reset the ->expmask values in the rcu_node tree in preparation for + * a new expedited grace period. + */ +static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) +{ + unsigned long flags; + struct rcu_node *rnp; + + sync_exp_reset_tree_hotplug(rsp); + rcu_for_each_node_breadth_first(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + WARN_ON_ONCE(rnp->expmask); + rnp->expmask = rnp->expmaskinit; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } +} + +/* + * Return non-zero if there is no RCU expedited grace period in progress + * for the specified rcu_node structure, in other words, if all CPUs and + * tasks covered by the specified rcu_node structure have done their bit + * for the current expedited grace period. Works only for preemptible + * RCU -- other RCU implementation use other means. + * + * Caller must hold the root rcu_node's exp_funnel_mutex. + */ +static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) +{ + return rnp->exp_tasks == NULL && + READ_ONCE(rnp->expmask) == 0; +} + +/* + * Report the exit from RCU read-side critical section for the last task + * that queued itself during or before the current expedited preemptible-RCU + * grace period. This event is reported either to the rcu_node structure on + * which the task was queued or to one of that rcu_node structure's ancestors, + * recursively up the tree. (Calm down, calm down, we do the recursion + * iteratively!) + * + * Caller must hold the root rcu_node's exp_funnel_mutex and the + * specified rcu_node structure's ->lock. + */ +static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake, unsigned long flags) + __releases(rnp->lock) +{ + unsigned long mask; + + for (;;) { + if (!sync_rcu_preempt_exp_done(rnp)) { + if (!rnp->expmask) + rcu_initiate_boost(rnp, flags); + else + raw_spin_unlock_irqrestore(&rnp->lock, flags); + break; + } + if (rnp->parent == NULL) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (wake) { + smp_mb(); /* EGP done before wake_up(). */ + wake_up(&rsp->expedited_wq); + } + break; + } + mask = rnp->grpmask; + raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ + rnp = rnp->parent; + raw_spin_lock(&rnp->lock); /* irqs already disabled */ + smp_mb__after_unlock_lock(); + WARN_ON_ONCE(!(rnp->expmask & mask)); + rnp->expmask &= ~mask; + } +} + +/* + * Report expedited quiescent state for specified node. This is a + * lock-acquisition wrapper function for __rcu_report_exp_rnp(). + * + * Caller must hold the root rcu_node's exp_funnel_mutex. + */ +static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, + struct rcu_node *rnp, bool wake) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + __rcu_report_exp_rnp(rsp, rnp, wake, flags); +} + +/* + * Report expedited quiescent state for multiple CPUs, all covered by the + * specified leaf rcu_node structure. Caller must hold the root + * rcu_node's exp_funnel_mutex. + */ +static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, + unsigned long mask, bool wake) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + if (!(rnp->expmask & mask)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + rnp->expmask &= ~mask; + __rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */ +} + +/* + * Report expedited quiescent state for specified rcu_data (CPU). + * Caller must hold the root rcu_node's exp_funnel_mutex. + */ +static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp, + bool wake) +{ + rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake); +} + /* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp, @@ -3455,16 +3660,111 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s) } /* Invoked on each online non-idle CPU for expedited quiescent state. */ -static int synchronize_sched_expedited_cpu_stop(void *data) +static void sync_sched_exp_handler(void *data) { - struct rcu_data *rdp = data; - struct rcu_state *rsp = rdp->rsp; + struct rcu_data *rdp; + struct rcu_node *rnp; + struct rcu_state *rsp = data; - /* We are here: If we are last, do the wakeup. */ - rdp->exp_done = true; - if (atomic_dec_and_test(&rsp->expedited_need_qs)) - wake_up(&rsp->expedited_wq); - return 0; + rdp = this_cpu_ptr(rsp->rda); + rnp = rdp->mynode; + if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) || + __this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) + return; + __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true); + resched_cpu(smp_processor_id()); +} + +/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */ +static void sync_sched_exp_online_cleanup(int cpu) +{ + struct rcu_data *rdp; + int ret; + struct rcu_node *rnp; + struct rcu_state *rsp = &rcu_sched_state; + + rdp = per_cpu_ptr(rsp->rda, cpu); + rnp = rdp->mynode; + if (!(READ_ONCE(rnp->expmask) & rdp->grpmask)) + return; + ret = smp_call_function_single(cpu, sync_sched_exp_handler, rsp, 0); + WARN_ON_ONCE(ret); +} + +/* + * Select the nodes that the upcoming expedited grace period needs + * to wait for. + */ +static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, + smp_call_func_t func) +{ + int cpu; + unsigned long flags; + unsigned long mask; + unsigned long mask_ofl_test; + unsigned long mask_ofl_ipi; + int ret; + struct rcu_node *rnp; + + sync_exp_reset_tree(rsp); + rcu_for_each_leaf_node(rsp, rnp) { + raw_spin_lock_irqsave(&rnp->lock, flags); + smp_mb__after_unlock_lock(); + + /* Each pass checks a CPU for identity, offline, and idle. */ + mask_ofl_test = 0; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { + struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + + if (raw_smp_processor_id() == cpu || + !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) + mask_ofl_test |= rdp->grpmask; + } + mask_ofl_ipi = rnp->expmask & ~mask_ofl_test; + + /* + * Need to wait for any blocked tasks as well. Note that + * additional blocking tasks will also block the expedited + * GP until such time as the ->expmask bits are cleared. + */ + if (rcu_preempt_has_tasks(rnp)) + rnp->exp_tasks = rnp->blkd_tasks.next; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + + /* IPI the remaining CPUs for expedited quiescent state. */ + mask = 1; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { + if (!(mask_ofl_ipi & mask)) + continue; +retry_ipi: + ret = smp_call_function_single(cpu, func, rsp, 0); + if (!ret) { + mask_ofl_ipi &= ~mask; + } else { + /* Failed, raced with offline. */ + raw_spin_lock_irqsave(&rnp->lock, flags); + if (cpu_online(cpu) && + (rnp->expmask & mask)) { + raw_spin_unlock_irqrestore(&rnp->lock, + flags); + schedule_timeout_uninterruptible(1); + if (cpu_online(cpu) && + (rnp->expmask & mask)) + goto retry_ipi; + raw_spin_lock_irqsave(&rnp->lock, + flags); + } + if (!(rnp->expmask & mask)) + mask_ofl_ipi &= ~mask; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + } + /* Report quiescent states for those that went offline. */ + mask_ofl_test |= mask_ofl_ipi; + if (mask_ofl_test) + rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false); + } } static void synchronize_sched_expedited_wait(struct rcu_state *rsp) @@ -3472,7 +3772,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) int cpu; unsigned long jiffies_stall; unsigned long jiffies_start; - struct rcu_data *rdp; + unsigned long mask; + struct rcu_node *rnp; + struct rcu_node *rnp_root = rcu_get_root(rsp); int ret; jiffies_stall = rcu_jiffies_till_stall_check(); @@ -3481,33 +3783,43 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) for (;;) { ret = wait_event_interruptible_timeout( rsp->expedited_wq, - !atomic_read(&rsp->expedited_need_qs), + sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); if (ret > 0) return; if (ret < 0) { /* Hit a signal, disable CPU stall warnings. */ wait_event(rsp->expedited_wq, - !atomic_read(&rsp->expedited_need_qs)); + sync_rcu_preempt_exp_done(rnp_root)); return; } - pr_err("INFO: %s detected expedited stalls on CPUs: {", + pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {", rsp->name); - for_each_online_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - - if (rdp->exp_done) - continue; - pr_cont(" %d", cpu); + rcu_for_each_leaf_node(rsp, rnp) { + (void)rcu_print_task_exp_stall(rnp); + mask = 1; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { + struct rcu_data *rdp; + + if (!(rnp->expmask & mask)) + continue; + rdp = per_cpu_ptr(rsp->rda, cpu); + pr_cont(" %d-%c%c%c", cpu, + "O."[cpu_online(cpu)], + "o."[!!(rdp->grpmask & rnp->expmaskinit)], + "N."[!!(rdp->grpmask & rnp->expmaskinitnext)]); + } + mask <<= 1; } pr_cont(" } %lu jiffies s: %lu\n", jiffies - jiffies_start, rsp->expedited_sequence); - for_each_online_cpu(cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - - if (rdp->exp_done) - continue; - dump_cpu_task(cpu); + rcu_for_each_leaf_node(rsp, rnp) { + mask = 1; + for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) { + if (!(rnp->expmask & mask)) + continue; + dump_cpu_task(cpu); + } } jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3; } @@ -3531,7 +3843,6 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) */ void synchronize_sched_expedited(void) { - int cpu; unsigned long s; struct rcu_node *rnp; struct rcu_state *rsp = &rcu_sched_state; @@ -3539,48 +3850,16 @@ void synchronize_sched_expedited(void) /* Take a snapshot of the sequence number. */ s = rcu_exp_gp_seq_snap(rsp); - if (!try_get_online_cpus()) { - /* CPU hotplug operation in flight, fall back to normal GP. */ - wait_rcu_gp(call_rcu_sched); - atomic_long_inc(&rsp->expedited_normal); - return; - } - WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id())); - rnp = exp_funnel_lock(rsp, s); - if (rnp == NULL) { - put_online_cpus(); + if (rnp == NULL) return; /* Someone else did our work for us. */ - } rcu_exp_gp_seq_start(rsp); - - /* Stop each CPU that is online, non-idle, and not us. */ - init_waitqueue_head(&rsp->expedited_wq); - atomic_set(&rsp->expedited_need_qs, 1); /* Extra count avoids race. */ - for_each_online_cpu(cpu) { - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); - - rdp->exp_done = false; - - /* Skip our CPU and any idle CPUs. */ - if (raw_smp_processor_id() == cpu || - !(atomic_add_return(0, &rdtp->dynticks) & 0x1)) - continue; - atomic_inc(&rsp->expedited_need_qs); - stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop, - rdp, &rdp->exp_stop_work); - } - - /* Remove extra count and, if necessary, wait for CPUs to stop. */ - if (!atomic_dec_and_test(&rsp->expedited_need_qs)) - synchronize_sched_expedited_wait(rsp); + sync_rcu_exp_select_cpus(rsp, sync_sched_exp_handler); + synchronize_sched_expedited_wait(rsp); rcu_exp_gp_seq_end(rsp); mutex_unlock(&rnp->exp_funnel_mutex); - - put_online_cpus(); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); @@ -3606,11 +3885,11 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && - rdp->qs_pending && !rdp->passed_quiesce && + rdp->core_needs_qs && rdp->cpu_no_qs.b.norm && rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) { - rdp->n_rp_qs_pending++; - } else if (rdp->qs_pending && - (rdp->passed_quiesce || + rdp->n_rp_core_needs_qs++; + } else if (rdp->core_needs_qs && + (!rdp->cpu_no_qs.b.norm || rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) { rdp->n_rp_report_qs++; return 1; @@ -3868,7 +4147,6 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) static void __init rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) { - static struct lock_class_key rcu_exp_sched_rdp_class; unsigned long flags; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); @@ -3884,10 +4162,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) mutex_init(&rdp->exp_funnel_mutex); rcu_boot_init_nocb_percpu_data(rdp); raw_spin_unlock_irqrestore(&rnp->lock, flags); - if (rsp == &rcu_sched_state) - lockdep_set_class_and_name(&rdp->exp_funnel_mutex, - &rcu_exp_sched_rdp_class, - "rcu_data_exp_sched"); } /* @@ -3906,7 +4180,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); - rdp->beenonline = 1; /* We have now been online. */ rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; @@ -3928,11 +4201,15 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) raw_spin_lock(&rnp->lock); /* irqs already disabled. */ smp_mb__after_unlock_lock(); rnp->qsmaskinitnext |= mask; + rnp->expmaskinitnext |= mask; + if (!rdp->beenonline) + WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1); + rdp->beenonline = true; /* We have now been online. */ rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ rdp->completed = rnp->completed; - rdp->passed_quiesce = false; + rdp->cpu_no_qs.b.norm = true; rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu); - rdp->qs_pending = false; + rdp->core_needs_qs = false; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); raw_spin_unlock_irqrestore(&rnp->lock, flags); } @@ -3965,6 +4242,7 @@ int rcu_cpu_notify(struct notifier_block *self, break; case CPU_ONLINE: case CPU_DOWN_FAILED: + sync_sched_exp_online_cleanup(cpu); rcu_boost_kthread_setaffinity(rnp, -1); break; case CPU_DOWN_PREPARE: @@ -3976,6 +4254,12 @@ int rcu_cpu_notify(struct notifier_block *self, rcu_cleanup_dying_cpu(rsp); break; case CPU_DYING_IDLE: + /* QS for any half-done expedited RCU-sched GP. */ + preempt_disable(); + rcu_report_exp_rdp(&rcu_sched_state, + this_cpu_ptr(rcu_sched_state.rda), true); + preempt_enable(); + for_each_rcu_flavor(rsp) { rcu_cleanup_dying_idle_cpu(cpu, rsp); } @@ -4107,7 +4391,6 @@ static void __init rcu_init_one(struct rcu_state *rsp, static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; static const char * const exp[] = RCU_EXP_NAME_INIT; - static const char * const exp_sched[] = RCU_EXP_SCHED_NAME_INIT; static u8 fl_mask = 0x1; int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */ @@ -4167,18 +4450,13 @@ static void __init rcu_init_one(struct rcu_state *rsp, INIT_LIST_HEAD(&rnp->blkd_tasks); rcu_init_one_nocb(rnp); mutex_init(&rnp->exp_funnel_mutex); - if (rsp == &rcu_sched_state) - lockdep_set_class_and_name( - &rnp->exp_funnel_mutex, - &rcu_exp_sched_class[i], exp_sched[i]); - else - lockdep_set_class_and_name( - &rnp->exp_funnel_mutex, - &rcu_exp_class[i], exp[i]); + lockdep_set_class_and_name(&rnp->exp_funnel_mutex, + &rcu_exp_class[i], exp[i]); } } init_waitqueue_head(&rsp->gp_wq); + init_waitqueue_head(&rsp->expedited_wq); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) @@ -4221,13 +4499,12 @@ static void __init rcu_init_geometry(void) rcu_fanout_leaf, nr_cpu_ids); /* - * The boot-time rcu_fanout_leaf parameter is only permitted - * to increase the leaf-level fanout, not decrease it. Of course, - * the leaf-level fanout cannot exceed the number of bits in - * the rcu_node masks. Complain and fall back to the compile- - * time values if these limits are exceeded. + * The boot-time rcu_fanout_leaf parameter must be at least two + * and cannot exceed the number of bits in the rcu_node masks. + * Complain and fall back to the compile-time values if this + * limit is exceeded. */ - if (rcu_fanout_leaf < RCU_FANOUT_LEAF || + if (rcu_fanout_leaf < 2 || rcu_fanout_leaf > sizeof(unsigned long) * 8) { rcu_fanout_leaf = RCU_FANOUT_LEAF; WARN_ON(1); @@ -4244,10 +4521,13 @@ static void __init rcu_init_geometry(void) /* * The tree must be able to accommodate the configured number of CPUs. - * If this limit is exceeded than we have a serious problem elsewhere. + * If this limit is exceeded, fall back to the compile-time values. */ - if (nr_cpu_ids > rcu_capacity[RCU_NUM_LVLS - 1]) - panic("rcu_init_geometry: rcu_capacity[] is too small"); + if (nr_cpu_ids > rcu_capacity[RCU_NUM_LVLS - 1]) { + rcu_fanout_leaf = RCU_FANOUT_LEAF; + WARN_ON(1); + return; + } /* Calculate the number of levels in the tree. */ for (i = 0; nr_cpu_ids > rcu_capacity[i]; i++) { diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 2e991f8..9fb4e23 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -70,8 +70,6 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0" } -# define RCU_EXP_SCHED_NAME_INIT \ - { "rcu_node_exp_sched_0" } #elif NR_CPUS <= RCU_FANOUT_2 # define RCU_NUM_LVLS 2 # define NUM_RCU_LVL_0 1 @@ -81,8 +79,6 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1" } -# define RCU_EXP_SCHED_NAME_INIT \ - { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1" } #elif NR_CPUS <= RCU_FANOUT_3 # define RCU_NUM_LVLS 3 # define NUM_RCU_LVL_0 1 @@ -93,8 +89,6 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" } -# define RCU_EXP_SCHED_NAME_INIT \ - { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2" } #elif NR_CPUS <= RCU_FANOUT_4 # define RCU_NUM_LVLS 4 # define NUM_RCU_LVL_0 1 @@ -106,8 +100,6 @@ # define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" } # define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" } # define RCU_EXP_NAME_INIT { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" } -# define RCU_EXP_SCHED_NAME_INIT \ - { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2", "rcu_node_exp_sched_3" } #else # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS" #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */ @@ -171,16 +163,21 @@ struct rcu_node { /* an rcu_data structure, otherwise, each */ /* bit corresponds to a child rcu_node */ /* structure. */ - unsigned long expmask; /* Groups that have ->blkd_tasks */ - /* elements that need to drain to allow the */ - /* current expedited grace period to */ - /* complete (only for PREEMPT_RCU). */ unsigned long qsmaskinit; - /* Per-GP initial value for qsmask & expmask. */ + /* Per-GP initial value for qsmask. */ /* Initialized from ->qsmaskinitnext at the */ /* beginning of each grace period. */ unsigned long qsmaskinitnext; /* Online CPUs for next grace period. */ + unsigned long expmask; /* CPUs or groups that need to check in */ + /* to allow the current expedited GP */ + /* to complete. */ + unsigned long expmaskinit; + /* Per-GP initial values for expmask. */ + /* Initialized from ->expmaskinitnext at the */ + /* beginning of each expedited GP. */ + unsigned long expmaskinitnext; + /* Online CPUs for next expedited GP. */ unsigned long grpmask; /* Mask to apply to parent qsmask. */ /* Only one bit will be set in this mask. */ int grplo; /* lowest-numbered CPU or group here. */ @@ -281,6 +278,18 @@ struct rcu_node { for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \ (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) +/* + * Union to allow "aggregate OR" operation on the need for a quiescent + * state by the normal and expedited grace periods. + */ +union rcu_noqs { + struct { + u8 norm; + u8 exp; + } b; /* Bits. */ + u16 s; /* Set of bits, aggregate OR here. */ +}; + /* Index values for nxttail array in struct rcu_data. */ #define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */ #define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */ @@ -297,8 +306,8 @@ struct rcu_data { /* is aware of having started. */ unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ /* for rcu_all_qs() invocations. */ - bool passed_quiesce; /* User-mode/idle loop etc. */ - bool qs_pending; /* Core waits for quiesc state. */ + union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ + bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ bool gpwrap; /* Possible gpnum/completed wrap. */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ @@ -307,9 +316,6 @@ struct rcu_data { /* ticks this CPU has handled */ /* during and after the last grace */ /* period it is aware of. */ - struct cpu_stop_work exp_stop_work; - /* Expedited grace-period control */ - /* for CPU stopping. */ /* 2) batch handling */ /* @@ -363,7 +369,7 @@ struct rcu_data { /* 5) __rcu_pending() statistics. */ unsigned long n_rcu_pending; /* rcu_pending() calls since boot. */ - unsigned long n_rp_qs_pending; + unsigned long n_rp_core_needs_qs; unsigned long n_rp_report_qs; unsigned long n_rp_cb_ready; unsigned long n_rp_cpu_needs_gp; @@ -378,7 +384,6 @@ struct rcu_data { struct rcu_head oom_head; #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ struct mutex exp_funnel_mutex; - bool exp_done; /* Expedited QS for this CPU? */ /* 7) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU @@ -412,13 +417,6 @@ struct rcu_data { struct rcu_state *rsp; }; -/* Values for fqs_state field in struct rcu_state. */ -#define RCU_GP_IDLE 0 /* No grace period in progress. */ -#define RCU_GP_INIT 1 /* Grace period being initialized. */ -#define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */ -#define RCU_FORCE_QS 3 /* Need to force quiescent state. */ -#define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK - /* Values for nocb_defer_wakeup field in struct rcu_data. */ #define RCU_NOGP_WAKE_NOT 0 #define RCU_NOGP_WAKE 1 @@ -464,14 +462,13 @@ struct rcu_state { /* shut bogus gcc warning) */ u8 flavor_mask; /* bit in flavor mask. */ struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ - void (*call)(struct rcu_head *head, /* call_rcu() flavor. */ - void (*func)(struct rcu_head *head)); + call_rcu_func_t call; /* call_rcu() flavor. */ + int ncpus; /* # CPUs seen so far. */ /* The following fields are guarded by the root rcu_node's lock. */ - u8 fqs_state ____cacheline_internodealigned_in_smp; - /* Force QS state. */ - u8 boost; /* Subject to priority boost. */ + u8 boost ____cacheline_internodealigned_in_smp; + /* Subject to priority boost. */ unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ @@ -508,6 +505,7 @@ struct rcu_state { atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ wait_queue_head_t expedited_wq; /* Wait for check-ins. */ + int ncpus_snap; /* # CPUs seen last time. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ @@ -538,8 +536,8 @@ struct rcu_state { #define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */ #define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */ -/* Values for rcu_state structure's gp_flags field. */ -#define RCU_GP_WAIT_INIT 0 /* Initial state. */ +/* Values for rcu_state structure's gp_state field. */ +#define RCU_GP_IDLE 0 /* Initial state and no GP in progress. */ #define RCU_GP_WAIT_GPS 1 /* Wait for grace-period start. */ #define RCU_GP_DONE_GPS 2 /* Wait done for grace-period start. */ #define RCU_GP_WAIT_FQS 3 /* Wait for force-quiescent-state time. */ @@ -582,9 +580,10 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); +static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_preempt_check_callbacks(void); -void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); +void call_rcu(struct rcu_head *head, rcu_callback_t func); static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index b2bf396..630c197 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -101,7 +101,6 @@ RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu); static struct rcu_state *const rcu_state_p = &rcu_preempt_state; static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; -static int rcu_preempted_readers_exp(struct rcu_node *rnp); static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, bool wake); @@ -114,6 +113,147 @@ static void __init rcu_bootup_announce(void) rcu_bootup_announce_oddness(); } +/* Flags for rcu_preempt_ctxt_queue() decision table. */ +#define RCU_GP_TASKS 0x8 +#define RCU_EXP_TASKS 0x4 +#define RCU_GP_BLKD 0x2 +#define RCU_EXP_BLKD 0x1 + +/* + * Queues a task preempted within an RCU-preempt read-side critical + * section into the appropriate location within the ->blkd_tasks list, + * depending on the states of any ongoing normal and expedited grace + * periods. The ->gp_tasks pointer indicates which element the normal + * grace period is waiting on (NULL if none), and the ->exp_tasks pointer + * indicates which element the expedited grace period is waiting on (again, + * NULL if none). If a grace period is waiting on a given element in the + * ->blkd_tasks list, it also waits on all subsequent elements. Thus, + * adding a task to the tail of the list blocks any grace period that is + * already waiting on one of the elements. In contrast, adding a task + * to the head of the list won't block any grace period that is already + * waiting on one of the elements. + * + * This queuing is imprecise, and can sometimes make an ongoing grace + * period wait for a task that is not strictly speaking blocking it. + * Given the choice, we needlessly block a normal grace period rather than + * blocking an expedited grace period. + * + * Note that an endless sequence of expedited grace periods still cannot + * indefinitely postpone a normal grace period. Eventually, all of the + * fixed number of preempted tasks blocking the normal grace period that are + * not also blocking the expedited grace period will resume and complete + * their RCU read-side critical sections. At that point, the ->gp_tasks + * pointer will equal the ->exp_tasks pointer, at which point the end of + * the corresponding expedited grace period will also be the end of the + * normal grace period. + */ +static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp, + unsigned long flags) __releases(rnp->lock) +{ + int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) + + (rnp->exp_tasks ? RCU_EXP_TASKS : 0) + + (rnp->qsmask & rdp->grpmask ? RCU_GP_BLKD : 0) + + (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0); + struct task_struct *t = current; + + /* + * Decide where to queue the newly blocked task. In theory, + * this could be an if-statement. In practice, when I tried + * that, it was quite messy. + */ + switch (blkd_state) { + case 0: + case RCU_EXP_TASKS: + case RCU_EXP_TASKS + RCU_GP_BLKD: + case RCU_GP_TASKS: + case RCU_GP_TASKS + RCU_EXP_TASKS: + + /* + * Blocking neither GP, or first task blocking the normal + * GP but not blocking the already-waiting expedited GP. + * Queue at the head of the list to avoid unnecessarily + * blocking the already-waiting GPs. + */ + list_add(&t->rcu_node_entry, &rnp->blkd_tasks); + break; + + case RCU_EXP_BLKD: + case RCU_GP_BLKD: + case RCU_GP_BLKD + RCU_EXP_BLKD: + case RCU_GP_TASKS + RCU_EXP_BLKD: + case RCU_GP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: + case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: + + /* + * First task arriving that blocks either GP, or first task + * arriving that blocks the expedited GP (with the normal + * GP already waiting), or a task arriving that blocks + * both GPs with both GPs already waiting. Queue at the + * tail of the list to avoid any GP waiting on any of the + * already queued tasks that are not blocking it. + */ + list_add_tail(&t->rcu_node_entry, &rnp->blkd_tasks); + break; + + case RCU_EXP_TASKS + RCU_EXP_BLKD: + case RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD: + case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_EXP_BLKD: + + /* + * Second or subsequent task blocking the expedited GP. + * The task either does not block the normal GP, or is the + * first task blocking the normal GP. Queue just after + * the first task blocking the expedited GP. + */ + list_add(&t->rcu_node_entry, rnp->exp_tasks); + break; + + case RCU_GP_TASKS + RCU_GP_BLKD: + case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD: + + /* + * Second or subsequent task blocking the normal GP. + * The task does not block the expedited GP. Queue just + * after the first task blocking the normal GP. + */ + list_add(&t->rcu_node_entry, rnp->gp_tasks); + break; + + default: + + /* Yet another exercise in excessive paranoia. */ + WARN_ON_ONCE(1); + break; + } + + /* + * We have now queued the task. If it was the first one to + * block either grace period, update the ->gp_tasks and/or + * ->exp_tasks pointers, respectively, to reference the newly + * blocked tasks. + */ + if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) + rnp->gp_tasks = &t->rcu_node_entry; + if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) + rnp->exp_tasks = &t->rcu_node_entry; + raw_spin_unlock(&rnp->lock); + + /* + * Report the quiescent state for the expedited GP. This expedited + * GP should not be able to end until we report, so there should be + * no need to check for a subsequent expedited GP. (Though we are + * still in a quiescent state in any case.) + */ + if (blkd_state & RCU_EXP_BLKD && + t->rcu_read_unlock_special.b.exp_need_qs) { + t->rcu_read_unlock_special.b.exp_need_qs = false; + rcu_report_exp_rdp(rdp->rsp, rdp, true); + } else { + WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs); + } + local_irq_restore(flags); +} + /* * Record a preemptible-RCU quiescent state for the specified CPU. Note * that this just means that the task currently running on the CPU is @@ -125,11 +265,11 @@ static void __init rcu_bootup_announce(void) */ static void rcu_preempt_qs(void) { - if (!__this_cpu_read(rcu_data_p->passed_quiesce)) { + if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), __this_cpu_read(rcu_data_p->gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_data_p->passed_quiesce, 1); + __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ current->rcu_read_unlock_special.b.need_qs = false; } @@ -167,42 +307,18 @@ static void rcu_preempt_note_context_switch(void) t->rcu_blocked_node = rnp; /* - * If this CPU has already checked in, then this task - * will hold up the next grace period rather than the - * current grace period. Queue the task accordingly. - * If the task is queued for the current grace period - * (i.e., this CPU has not yet passed through a quiescent - * state for the current grace period), then as long - * as that task remains queued, the current grace period - * cannot end. Note that there is some uncertainty as - * to exactly when the current grace period started. - * We take a conservative approach, which can result - * in unnecessarily waiting on tasks that started very - * slightly after the current grace period began. C'est - * la vie!!! - * - * But first, note that the current CPU must still be - * on line! + * Verify the CPU's sanity, trace the preemption, and + * then queue the task as required based on the states + * of any ongoing and expedited grace periods. */ WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); - if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) { - list_add(&t->rcu_node_entry, rnp->gp_tasks->prev); - rnp->gp_tasks = &t->rcu_node_entry; - if (IS_ENABLED(CONFIG_RCU_BOOST) && - rnp->boost_tasks != NULL) - rnp->boost_tasks = rnp->gp_tasks; - } else { - list_add(&t->rcu_node_entry, &rnp->blkd_tasks); - if (rnp->qsmask & rdp->grpmask) - rnp->gp_tasks = &t->rcu_node_entry; - } trace_rcu_preempt_task(rdp->rsp->name, t->pid, (rnp->qsmask & rdp->grpmask) ? rnp->gpnum : rnp->gpnum + 1); - raw_spin_unlock_irqrestore(&rnp->lock, flags); + rcu_preempt_ctxt_queue(rnp, rdp, flags); } else if (t->rcu_read_lock_nesting < 0 && t->rcu_read_unlock_special.s) { @@ -272,6 +388,7 @@ void rcu_read_unlock_special(struct task_struct *t) unsigned long flags; struct list_head *np; bool drop_boost_mutex = false; + struct rcu_data *rdp; struct rcu_node *rnp; union rcu_special special; @@ -282,8 +399,8 @@ void rcu_read_unlock_special(struct task_struct *t) local_irq_save(flags); /* - * If RCU core is waiting for this CPU to exit critical section, - * let it know that we have done so. Because irqs are disabled, + * If RCU core is waiting for this CPU to exit its critical section, + * report the fact that it has exited. Because irqs are disabled, * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; @@ -296,13 +413,32 @@ void rcu_read_unlock_special(struct task_struct *t) } } + /* + * Respond to a request for an expedited grace period, but only if + * we were not preempted, meaning that we were running on the same + * CPU throughout. If we were preempted, the exp_need_qs flag + * would have been cleared at the time of the first preemption, + * and the quiescent state would be reported when we were dequeued. + */ + if (special.b.exp_need_qs) { + WARN_ON_ONCE(special.b.blocked); + t->rcu_read_unlock_special.b.exp_need_qs = false; + rdp = this_cpu_ptr(rcu_state_p->rda); + rcu_report_exp_rdp(rcu_state_p, rdp, true); + if (!t->rcu_read_unlock_special.s) { + local_irq_restore(flags); + return; + } + } + /* Hardware IRQ handlers cannot block, complain if they get here. */ if (in_irq() || in_serving_softirq()) { lockdep_rcu_suspicious(__FILE__, __LINE__, "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); - pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n", + pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", t->rcu_read_unlock_special.s, t->rcu_read_unlock_special.b.blocked, + t->rcu_read_unlock_special.b.exp_need_qs, t->rcu_read_unlock_special.b.need_qs); local_irq_restore(flags); return; @@ -329,7 +465,7 @@ void rcu_read_unlock_special(struct task_struct *t) raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); - empty_exp = !rcu_preempted_readers_exp(rnp); + empty_exp = sync_rcu_preempt_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); @@ -353,7 +489,7 @@ void rcu_read_unlock_special(struct task_struct *t) * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, * so we must take a snapshot of the expedited state. */ - empty_exp_now = !rcu_preempted_readers_exp(rnp); + empty_exp_now = sync_rcu_preempt_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), rnp->gpnum, @@ -450,6 +586,27 @@ static int rcu_print_task_stall(struct rcu_node *rnp) } /* + * Scan the current list of tasks blocked within RCU read-side critical + * sections, printing out the tid of each that is blocking the current + * expedited grace period. + */ +static int rcu_print_task_exp_stall(struct rcu_node *rnp) +{ + struct task_struct *t; + int ndetected = 0; + + if (!rnp->exp_tasks) + return 0; + t = list_entry(rnp->exp_tasks->prev, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + pr_cont(" P%d", t->pid); + ndetected++; + } + return ndetected; +} + +/* * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be @@ -483,8 +640,8 @@ static void rcu_preempt_check_callbacks(void) return; } if (t->rcu_read_lock_nesting > 0 && - __this_cpu_read(rcu_data_p->qs_pending) && - !__this_cpu_read(rcu_data_p->passed_quiesce)) + __this_cpu_read(rcu_data_p->core_needs_qs) && + __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm)) t->rcu_read_unlock_special.b.need_qs = true; } @@ -500,7 +657,7 @@ static void rcu_preempt_do_callbacks(void) /* * Queue a preemptible-RCU callback for invocation after a grace period. */ -void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +void call_rcu(struct rcu_head *head, rcu_callback_t func) { __call_rcu(head, func, rcu_state_p, -1, 0); } @@ -535,155 +692,41 @@ void synchronize_rcu(void) } EXPORT_SYMBOL_GPL(synchronize_rcu); -static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); - -/* - * Return non-zero if there are any tasks in RCU read-side critical - * sections blocking the current preemptible-RCU expedited grace period. - * If there is no preemptible-RCU expedited grace period currently in - * progress, returns zero unconditionally. - */ -static int rcu_preempted_readers_exp(struct rcu_node *rnp) -{ - return rnp->exp_tasks != NULL; -} - -/* - * return non-zero if there is no RCU expedited grace period in progress - * for the specified rcu_node structure, in other words, if all CPUs and - * tasks covered by the specified rcu_node structure have done their bit - * for the current expedited grace period. Works only for preemptible - * RCU -- other RCU implementation use other means. - * - * Caller must hold the root rcu_node's exp_funnel_mutex. - */ -static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) -{ - return !rcu_preempted_readers_exp(rnp) && - READ_ONCE(rnp->expmask) == 0; -} - -/* - * Report the exit from RCU read-side critical section for the last task - * that queued itself during or before the current expedited preemptible-RCU - * grace period. This event is reported either to the rcu_node structure on - * which the task was queued or to one of that rcu_node structure's ancestors, - * recursively up the tree. (Calm down, calm down, we do the recursion - * iteratively!) - * - * Caller must hold the root rcu_node's exp_funnel_mutex. - */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, - bool wake) -{ - unsigned long flags; - unsigned long mask; - - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - for (;;) { - if (!sync_rcu_preempt_exp_done(rnp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); - break; - } - if (rnp->parent == NULL) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); - if (wake) { - smp_mb(); /* EGP done before wake_up(). */ - wake_up(&sync_rcu_preempt_exp_wq); - } - break; - } - mask = rnp->grpmask; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ - rnp = rnp->parent; - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - smp_mb__after_unlock_lock(); - rnp->expmask &= ~mask; - } -} - /* - * Snapshot the tasks blocking the newly started preemptible-RCU expedited - * grace period for the specified rcu_node structure, phase 1. If there - * are such tasks, set the ->expmask bits up the rcu_node tree and also - * set the ->expmask bits on the leaf rcu_node structures to tell phase 2 - * that work is needed here. - * - * Caller must hold the root rcu_node's exp_funnel_mutex. + * Remote handler for smp_call_function_single(). If there is an + * RCU read-side critical section in effect, request that the + * next rcu_read_unlock() record the quiescent state up the + * ->expmask fields in the rcu_node tree. Otherwise, immediately + * report the quiescent state. */ -static void -sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp) +static void sync_rcu_exp_handler(void *info) { - unsigned long flags; - unsigned long mask; - struct rcu_node *rnp_up; - - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - WARN_ON_ONCE(rnp->expmask); - WARN_ON_ONCE(rnp->exp_tasks); - if (!rcu_preempt_has_tasks(rnp)) { - /* No blocked tasks, nothing to do. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } - /* Call for Phase 2 and propagate ->expmask bits up the tree. */ - rnp->expmask = 1; - rnp_up = rnp; - while (rnp_up->parent) { - mask = rnp_up->grpmask; - rnp_up = rnp_up->parent; - if (rnp_up->expmask & mask) - break; - raw_spin_lock(&rnp_up->lock); /* irqs already off */ - smp_mb__after_unlock_lock(); - rnp_up->expmask |= mask; - raw_spin_unlock(&rnp_up->lock); /* irqs still off */ - } - raw_spin_unlock_irqrestore(&rnp->lock, flags); -} - -/* - * Snapshot the tasks blocking the newly started preemptible-RCU expedited - * grace period for the specified rcu_node structure, phase 2. If the - * leaf rcu_node structure has its ->expmask field set, check for tasks. - * If there are some, clear ->expmask and set ->exp_tasks accordingly, - * then initiate RCU priority boosting. Otherwise, clear ->expmask and - * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits, - * enabling rcu_read_unlock_special() to do the bit-clearing. - * - * Caller must hold the root rcu_node's exp_funnel_mutex. - */ -static void -sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&rnp->lock, flags); - smp_mb__after_unlock_lock(); - if (!rnp->expmask) { - /* Phase 1 didn't do anything, so Phase 2 doesn't either. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } - - /* Phase 1 is over. */ - rnp->expmask = 0; + struct rcu_data *rdp; + struct rcu_state *rsp = info; + struct task_struct *t = current; /* - * If there are still blocked tasks, set up ->exp_tasks so that - * rcu_read_unlock_special() will wake us and then boost them. + * Within an RCU read-side critical section, request that the next + * rcu_read_unlock() report. Unless this RCU read-side critical + * section has already blocked, in which case it is already set + * up for the expedited grace period to wait on it. */ - if (rcu_preempt_has_tasks(rnp)) { - rnp->exp_tasks = rnp->blkd_tasks.next; - rcu_initiate_boost(rnp, flags); /* releases rnp->lock */ + if (t->rcu_read_lock_nesting > 0 && + !t->rcu_read_unlock_special.b.blocked) { + t->rcu_read_unlock_special.b.exp_need_qs = true; return; } - /* No longer any blocked tasks, so undo bit setting. */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - rcu_report_exp_rnp(rsp, rnp, false); + /* + * We are either exiting an RCU read-side critical section (negative + * values of t->rcu_read_lock_nesting) or are not in one at all + * (zero value of t->rcu_read_lock_nesting). Or we are in an RCU + * read-side critical section that blocked before this expedited + * grace period started. Either way, we can immediately report + * the quiescent state. + */ + rdp = this_cpu_ptr(rsp->rda); + rcu_report_exp_rdp(rsp, rdp, true); } /** @@ -713,24 +756,12 @@ void synchronize_rcu_expedited(void) rcu_exp_gp_seq_start(rsp); - /* force all RCU readers onto ->blkd_tasks lists. */ - synchronize_sched_expedited(); - - /* - * Snapshot current state of ->blkd_tasks lists into ->expmask. - * Phase 1 sets bits and phase 2 permits rcu_read_unlock_special() - * to start clearing them. Doing this in one phase leads to - * strange races between setting and clearing bits, so just say "no"! - */ - rcu_for_each_leaf_node(rsp, rnp) - sync_rcu_preempt_exp_init1(rsp, rnp); - rcu_for_each_leaf_node(rsp, rnp) - sync_rcu_preempt_exp_init2(rsp, rnp); + /* Initialize the rcu_node tree in preparation for the wait. */ + sync_rcu_exp_select_cpus(rsp, sync_rcu_exp_handler); /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); - wait_event(sync_rcu_preempt_exp_wq, - sync_rcu_preempt_exp_done(rnp)); + synchronize_sched_expedited_wait(rsp); /* Clean up and exit. */ rcu_exp_gp_seq_end(rsp); @@ -835,6 +866,16 @@ static int rcu_print_task_stall(struct rcu_node *rnp) } /* + * Because preemptible RCU does not exist, we never have to check for + * tasks blocked within RCU read-side critical sections that are + * blocking the current expedited grace period. + */ +static int rcu_print_task_exp_stall(struct rcu_node *rnp) +{ + return 0; +} + +/* * Because there is no preemptible RCU, there can be no readers blocked, * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. @@ -1702,8 +1743,12 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) ticks_value = rsp->gpnum - rdp->gpnum; } print_cpu_stall_fast_no_hz(fast_no_hz, cpu); - pr_err("\t%d: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n", - cpu, ticks_value, ticks_title, + pr_err("\t%d-%c%c%c: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n", + cpu, + "O."[!!cpu_online(cpu)], + "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)], + "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)], + ticks_value, ticks_title, atomic_read(&rdtp->dynticks) & 0xfff, rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index 6fc4c5f..ef7093c 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -117,13 +117,13 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) if (!rdp->beenonline) return; - seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d", + seq_printf(m, "%3d%cc=%ld g=%ld cnq=%d/%d:%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', ulong2long(rdp->completed), ulong2long(rdp->gpnum), - rdp->passed_quiesce, + rdp->cpu_no_qs.b.norm, rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu), - rdp->qs_pending); + rdp->core_needs_qs); seq_printf(m, " dt=%d/%llx/%d df=%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, @@ -268,7 +268,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) gpnum = rsp->gpnum; seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x ", ulong2long(rsp->completed), ulong2long(gpnum), - rsp->fqs_state, + rsp->gp_state, (long)(rsp->jiffies_force_qs - jiffies), (int)(jiffies & 0xffff)); seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", @@ -361,7 +361,7 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) cpu_is_offline(rdp->cpu) ? '!' : ' ', rdp->n_rcu_pending); seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ", - rdp->n_rp_qs_pending, + rdp->n_rp_core_needs_qs, rdp->n_rp_report_qs, rdp->n_rp_cb_ready, rdp->n_rp_cpu_needs_gp); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 7a0b3bc..5f748c5 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -534,7 +534,7 @@ static void rcu_spawn_tasks_kthread(void); * Post an RCU-tasks callback. First call must be from process context * after the scheduler if fully operational. */ -void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) +void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func) { unsigned long flags; bool needwake; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 10a8faa..f7402f7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2366,8 +2366,15 @@ void wake_up_new_task(struct task_struct *p) trace_sched_wakeup_new(p); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP - if (p->sched_class->task_woken) + if (p->sched_class->task_woken) { + /* + * Nothing relies on rq->lock after this, so its fine to + * drop it. + */ + lockdep_unpin_lock(&rq->lock); p->sched_class->task_woken(rq, p); + lockdep_pin_lock(&rq->lock); + } #endif task_rq_unlock(rq, p, &flags); } @@ -4022,6 +4029,7 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy, { return _sched_setscheduler(p, policy, param, false); } +EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck); static int do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) @@ -7238,9 +7246,6 @@ void __init sched_init_smp(void) alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); alloc_cpumask_var(&fallback_doms, GFP_KERNEL); - /* nohz_full won't take effect without isolating the cpus. */ - tick_nohz_full_add_cpus_to(cpu_isolated_map); - sched_init_numa(); /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fc8f010..8b0a15e 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -668,8 +668,15 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * Queueing this task back might have overloaded rq, check if we need * to kick someone away. */ - if (has_pushable_dl_tasks(rq)) + if (has_pushable_dl_tasks(rq)) { + /* + * Nothing relies on rq->lock after this, so its safe to drop + * rq->lock. + */ + lockdep_unpin_lock(&rq->lock); push_dl_task(rq); + lockdep_pin_lock(&rq->lock); + } #endif unlock: @@ -1066,8 +1073,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) int target = find_later_rq(p); if (target != -1 && - dl_time_before(p->dl.deadline, - cpu_rq(target)->dl.earliest_dl.curr)) + (dl_time_before(p->dl.deadline, + cpu_rq(target)->dl.earliest_dl.curr) || + (cpu_rq(target)->dl.dl_nr_running == 0))) cpu = target; } rcu_read_unlock(); @@ -1417,7 +1425,8 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) later_rq = cpu_rq(cpu); - if (!dl_time_before(task->dl.deadline, + if (later_rq->dl.dl_nr_running && + !dl_time_before(task->dl.deadline, later_rq->dl.earliest_dl.curr)) { /* * Target rq has tasks of equal or earlier deadline, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6e2e348..9a5e60f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2363,7 +2363,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) */ tg_weight = atomic_long_read(&tg->load_avg); tg_weight -= cfs_rq->tg_load_avg_contrib; - tg_weight += cfs_rq_load_avg(cfs_rq); + tg_weight += cfs_rq->load.weight; return tg_weight; } @@ -2373,7 +2373,7 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) long tg_weight, load, shares; tg_weight = calc_tg_weight(tg, cfs_rq); - load = cfs_rq_load_avg(cfs_rq); + load = cfs_rq->load.weight; shares = (tg->shares * load); if (tg_weight) @@ -2664,13 +2664,14 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); /* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) { - int decayed; struct sched_avg *sa = &cfs_rq->avg; + int decayed, removed = 0; if (atomic_long_read(&cfs_rq->removed_load_avg)) { long r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); sa->load_avg = max_t(long, sa->load_avg - r, 0); sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); + removed = 1; } if (atomic_long_read(&cfs_rq->removed_util_avg)) { @@ -2688,7 +2689,7 @@ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) cfs_rq->load_last_update_time_copy = sa->last_update_time; #endif - return decayed; + return decayed || removed; } /* Update task and its cfs_rq load average */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f177c7..4a2ef5a 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -57,9 +57,11 @@ static inline int cpu_idle_poll(void) rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); + stop_critical_timings(); while (!tif_need_resched() && (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); + start_critical_timings(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); rcu_idle_exit(); return 1; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 3a38775..0d8fe8b 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -479,7 +479,7 @@ static u32 clocksource_max_adjustment(struct clocksource *cs) * return half the number of nanoseconds the hardware counter can technically * cover. This is done so that we can potentially detect problems caused by * delayed timers or bad hardware, which might result in time intervals that - * are larger then what the math used can handle without overflows. + * are larger than what the math used can handle without overflows. */ u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cyc) { @@ -595,16 +595,15 @@ static void __clocksource_select(bool skipcur) */ static void clocksource_select(void) { - return __clocksource_select(false); + __clocksource_select(false); } static void clocksource_select_fallback(void) { - return __clocksource_select(true); + __clocksource_select(true); } #else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */ - static inline void clocksource_select(void) { } static inline void clocksource_select_fallback(void) { } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 457a373..435b885 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -59,7 +59,7 @@ /* * The timer bases: * - * There are more clockids then hrtimer bases. Thus, we index + * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index df68cb8..149cc80 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -99,7 +99,7 @@ static time64_t ntp_next_leap_sec = TIME64_MAX; static int pps_valid; /* signal watchdog counter */ static long pps_tf[3]; /* phase median filter */ static long pps_jitter; /* current jitter (ns) */ -static struct timespec pps_fbase; /* beginning of the last freq interval */ +static struct timespec64 pps_fbase; /* beginning of the last freq interval */ static int pps_shift; /* current interval duration (s) (shift) */ static int pps_intcnt; /* interval counter */ static s64 pps_freq; /* frequency offset (scaled ns/s) */ @@ -509,7 +509,7 @@ static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); static void sync_cmos_clock(struct work_struct *work) { struct timespec64 now; - struct timespec next; + struct timespec64 next; int fail = 1; /* @@ -559,7 +559,7 @@ static void sync_cmos_clock(struct work_struct *work) next.tv_nsec -= NSEC_PER_SEC; } queue_delayed_work(system_power_efficient_wq, - &sync_cmos_work, timespec_to_jiffies(&next)); + &sync_cmos_work, timespec64_to_jiffies(&next)); } void ntp_notify_cmos_timer(void) @@ -773,13 +773,13 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) * pps_normtime.nsec has a range of ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] * while timespec.tv_nsec has a range of [0, NSEC_PER_SEC) */ struct pps_normtime { - __kernel_time_t sec; /* seconds */ + s64 sec; /* seconds */ long nsec; /* nanoseconds */ }; /* normalize the timestamp so that nsec is in the ( -NSEC_PER_SEC / 2, NSEC_PER_SEC / 2 ] interval */ -static inline struct pps_normtime pps_normalize_ts(struct timespec ts) +static inline struct pps_normtime pps_normalize_ts(struct timespec64 ts) { struct pps_normtime norm = { .sec = ts.tv_sec, @@ -861,7 +861,7 @@ static long hardpps_update_freq(struct pps_normtime freq_norm) pps_errcnt++; pps_dec_freq_interval(); printk_deferred(KERN_ERR - "hardpps: PPSERROR: interval too long - %ld s\n", + "hardpps: PPSERROR: interval too long - %lld s\n", freq_norm.sec); return 0; } @@ -948,7 +948,7 @@ static void hardpps_update_phase(long error) * This code is based on David Mills's reference nanokernel * implementation. It was mostly rewritten but keeps the same idea. */ -void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) +void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { struct pps_normtime pts_norm, freq_norm; @@ -969,7 +969,7 @@ void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) } /* ok, now we have a base for frequency calculation */ - freq_norm = pps_normalize_ts(timespec_sub(*raw_ts, pps_fbase)); + freq_norm = pps_normalize_ts(timespec64_sub(*raw_ts, pps_fbase)); /* check that the signal is in the range * [1s - MAXFREQ us, 1s + MAXFREQ us], otherwise reject it */ diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 6543050..af92447 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -9,5 +9,5 @@ extern ktime_t ntp_get_next_leap(void); extern int second_overflow(unsigned long secs); extern int ntp_validate_timex(struct timex *); extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); -extern void __hardpps(const struct timespec *, const struct timespec *); +extern void __hardpps(const struct timespec64 *, const struct timespec64 *); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 892e3da..f5e86d2 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -249,7 +249,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) * but barriers are not required because update_gt_cputime() * can handle concurrent updates. */ - WRITE_ONCE(cputimer->running, 1); + WRITE_ONCE(cputimer->running, true); } sample_cputime_atomic(times, &cputimer->cputime_atomic); } @@ -864,6 +864,13 @@ static void check_thread_timers(struct task_struct *tsk, unsigned long long expires; unsigned long soft; + /* + * If cputime_expires is zero, then there are no active + * per thread CPU timers. + */ + if (task_cputime_zero(&tsk->cputime_expires)) + return; + expires = check_timers_list(timers, firing, prof_ticks(tsk)); tsk_expires->prof_exp = expires_to_cputime(expires); @@ -911,7 +918,7 @@ static inline void stop_process_timers(struct signal_struct *sig) struct thread_group_cputimer *cputimer = &sig->cputimer; /* Turn off cputimer->running. This is done without locking. */ - WRITE_ONCE(cputimer->running, 0); + WRITE_ONCE(cputimer->running, false); } static u32 onecputick; @@ -962,6 +969,19 @@ static void check_process_timers(struct task_struct *tsk, unsigned long soft; /* + * If cputimer is not running, then there are no active + * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU). + */ + if (!READ_ONCE(tsk->signal->cputimer.running)) + return; + + /* + * Signify that a thread is checking for process timers. + * Write access to this field is protected by the sighand lock. + */ + sig->cputimer.checking_timer = true; + + /* * Collect the current process totals. */ thread_group_cputimer(tsk, &cputime); @@ -1015,6 +1035,8 @@ static void check_process_timers(struct task_struct *tsk, sig->cputime_expires.sched_exp = sched_expires; if (task_cputime_zero(&sig->cputime_expires)) stop_process_timers(sig); + + sig->cputimer.checking_timer = false; } /* @@ -1117,24 +1139,33 @@ static inline int task_cputime_expired(const struct task_cputime *sample, static inline int fastpath_timer_check(struct task_struct *tsk) { struct signal_struct *sig; - cputime_t utime, stime; - - task_cputime(tsk, &utime, &stime); if (!task_cputime_zero(&tsk->cputime_expires)) { - struct task_cputime task_sample = { - .utime = utime, - .stime = stime, - .sum_exec_runtime = tsk->se.sum_exec_runtime - }; + struct task_cputime task_sample; + task_cputime(tsk, &task_sample.utime, &task_sample.stime); + task_sample.sum_exec_runtime = tsk->se.sum_exec_runtime; if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) return 1; } sig = tsk->signal; - /* Check if cputimer is running. This is accessed without locking. */ - if (READ_ONCE(sig->cputimer.running)) { + /* + * Check if thread group timers expired when the cputimer is + * running and no other thread in the group is already checking + * for thread group cputimers. These fields are read without the + * sighand lock. However, this is fine because this is meant to + * be a fastpath heuristic to determine whether we should try to + * acquire the sighand lock to check/handle timers. + * + * In the worst case scenario, if 'running' or 'checking_timer' gets + * set but the current thread doesn't see the change yet, we'll wait + * until the next thread in the group gets a scheduler interrupt to + * handle the timer. This isn't an issue in practice because these + * types of delays with signals actually getting sent are expected. + */ + if (READ_ONCE(sig->cputimer.running) && + !READ_ONCE(sig->cputimer.checking_timer)) { struct task_cputime group_sample; sample_cputime_atomic(&group_sample, &sig->cputimer.cputime_atomic); @@ -1174,12 +1205,8 @@ void run_posix_cpu_timers(struct task_struct *tsk) * put them on the firing list. */ check_thread_timers(tsk, &firing); - /* - * If there are any active process wide timers (POSIX 1.b, itimers, - * RLIMIT_CPU) cputimer must be running. - */ - if (READ_ONCE(tsk->signal->cputimer.running)) - check_process_timers(tsk, &firing); + + check_process_timers(tsk, &firing); /* * We must release these locks before taking any timer's lock. diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc index c7388de..c486889 100644 --- a/kernel/time/timeconst.bc +++ b/kernel/time/timeconst.bc @@ -39,7 +39,7 @@ define fmuls(b,n,d) { } define timeconst(hz) { - print "/* Automatically generated by kernel/timeconst.bc */\n" + print "/* Automatically generated by kernel/time/timeconst.bc */\n" print "/* Time conversion constants for HZ == ", hz, " */\n" print "\n" diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3739ac6..b1356b7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -849,7 +849,7 @@ EXPORT_SYMBOL_GPL(ktime_get_real_seconds); #ifdef CONFIG_NTP_PPS /** - * getnstime_raw_and_real - get day and raw monotonic time in timespec format + * ktime_get_raw_and_real_ts64 - get day and raw monotonic time in timespec format * @ts_raw: pointer to the timespec to be set to raw monotonic time * @ts_real: pointer to the timespec to be set to the time of day * @@ -857,7 +857,7 @@ EXPORT_SYMBOL_GPL(ktime_get_real_seconds); * same time atomically and stores the resulting timestamps in timespec * format. */ -void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) +void ktime_get_raw_and_real_ts64(struct timespec64 *ts_raw, struct timespec64 *ts_real) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long seq; @@ -868,7 +868,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) do { seq = read_seqcount_begin(&tk_core.seq); - *ts_raw = timespec64_to_timespec(tk->raw_time); + *ts_raw = tk->raw_time; ts_real->tv_sec = tk->xtime_sec; ts_real->tv_nsec = 0; @@ -877,10 +877,10 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real) } while (read_seqcount_retry(&tk_core.seq, seq)); - timespec_add_ns(ts_raw, nsecs_raw); - timespec_add_ns(ts_real, nsecs_real); + timespec64_add_ns(ts_raw, nsecs_raw); + timespec64_add_ns(ts_real, nsecs_real); } -EXPORT_SYMBOL(getnstime_raw_and_real); +EXPORT_SYMBOL(ktime_get_raw_and_real_ts64); #endif /* CONFIG_NTP_PPS */ @@ -1251,7 +1251,7 @@ void __init timekeeping_init(void) set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec); tk_set_wall_to_mono(tk, tmp); - timekeeping_update(tk, TK_MIRROR); + timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -1674,7 +1674,7 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) /** * accumulate_nsecs_to_secs - Accumulates nsecs into secs * - * Helper function that accumulates a the nsecs greater then a second + * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. * @@ -1726,7 +1726,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, cycle_t interval = tk->cycle_interval << shift; u64 raw_nsecs; - /* If the offset is smaller then a shifted interval, do nothing */ + /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; @@ -2025,7 +2025,7 @@ int do_adjtimex(struct timex *txc) /** * hardpps() - Accessor function to NTP __hardpps function */ -void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) +void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { unsigned long flags; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 84190f0..74591ba 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -461,10 +461,17 @@ void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr) static void timer_stats_account_timer(struct timer_list *timer) { - if (likely(!timer->start_site)) + void *site; + + /* + * start_site can be concurrently reset by + * timer_stats_timer_clear_start_info() + */ + site = READ_ONCE(timer->start_site); + if (likely(!site)) return; - timer_stats_update_stats(timer, timer->start_pid, timer->start_site, + timer_stats_update_stats(timer, timer->start_pid, site, timer->function, timer->start_comm, timer->flags); } @@ -867,7 +874,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires) if (mask == 0) return expires; - bit = find_last_bit(&mask, BITS_PER_LONG); + bit = __fls(mask); mask = (1UL << bit) - 1; diff --git a/kernel/torture.c b/kernel/torture.c index 3e48406..44aa462 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -523,6 +523,7 @@ static int stutter; */ void stutter_wait(const char *title) { + cond_resched_rcu_qs(); while (READ_ONCE(stutter_pause_test) || (torture_runnable && !READ_ONCE(*torture_runnable))) { if (stutter_pause_test) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index b746399..8abf1ba 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -85,9 +85,19 @@ check_stack(unsigned long ip, unsigned long *stack) if (!object_is_on_stack(stack)) return; + /* Can't do this from NMI context (can cause deadlocks) */ + if (in_nmi()) + return; + local_irq_save(flags); arch_spin_lock(&max_stack_lock); + /* + * RCU may not be watching, make it see us. + * The stack trace code uses rcu_sched. + */ + rcu_irq_enter(); + /* In case another CPU set the tracer_frame on us */ if (unlikely(!frame_size)) this_size -= tracer_frame; @@ -169,6 +179,7 @@ check_stack(unsigned long ip, unsigned long *stack) } out: + rcu_irq_exit(); arch_spin_unlock(&max_stack_lock); local_irq_restore(flags); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index ca71582..bcb14ca 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1458,13 +1458,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); dwork->wq = wq; + /* timer isn't guaranteed to run in this cpu, record earlier */ + if (cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); dwork->cpu = cpu; timer->expires = jiffies + delay; - if (unlikely(cpu != WORK_CPU_UNBOUND)) - add_timer_on(timer, cpu); - else - add_timer(timer); + add_timer_on(timer, cpu); } /** |