diff options
Diffstat (limited to 'kernel')
59 files changed, 2304 insertions, 1098 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c index 82cf9dff4295..85ff5e26e23b 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; @@ -304,8 +291,8 @@ static inline void check_for_tasks(int dead_cpu) { struct task_struct *g, *p; - read_lock_irq(&tasklist_lock); - do_each_thread(g, p) { + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { if (!p->on_rq) continue; /* @@ -320,8 +307,8 @@ static inline void check_for_tasks(int dead_cpu) pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n", p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags); - } while_each_thread(g, p); - read_unlock_irq(&tasklist_lock); + } + read_unlock(&tasklist_lock); } struct take_cpu_down_param { @@ -344,7 +331,7 @@ static int take_cpu_down(void *_param) /* Give up timekeeping duties */ tick_handover_do_timer(); /* Park the stopper thread */ - kthread_park(current); + stop_machine_park((long)param->hcpu); return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 64754bfecd70..39db20c6248e 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); } @@ -7297,24 +7386,49 @@ 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); } @@ -7553,7 +7667,7 @@ 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; } @@ -7641,7 +7755,7 @@ 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; @@ -9350,14 +9464,6 @@ 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 182bc30899d5..b5d1ea79c595 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 ea95ee1b5ef7..07110c6020a0 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -706,10 +706,12 @@ void do_exit(long code) smp_mb(); raw_spin_unlock_wait(&tsk->pi_lock); - if (unlikely(in_atomic())) + if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), preempt_count()); + preempt_count_set(PREEMPT_ENABLED); + } /* sync mm's RSS info before statistics gathering */ if (tsk->mm) @@ -761,7 +763,9 @@ 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 2845623fb582..6ac894244d39 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 6e443efc65f4..dfc86e93c31d 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 9a76e3beda54..3b48dab80164 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 d12123526e2b..2fc9cbdf35b6 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 e28169dd1c36..15206453b12a 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, + |