diff options
Diffstat (limited to 'kernel')
55 files changed, 2131 insertions, 904 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 08561f1acd13..ebdb0043203a 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -235,9 +235,16 @@ config LOCK_SPIN_ON_OWNER def_bool y depends on MUTEX_SPIN_ON_OWNER || RWSEM_SPIN_ON_OWNER -config ARCH_USE_QUEUE_RWLOCK +config ARCH_USE_QUEUED_SPINLOCKS bool -config QUEUE_RWLOCK - def_bool y if ARCH_USE_QUEUE_RWLOCK +config QUEUED_SPINLOCKS + def_bool y if ARCH_USE_QUEUED_SPINLOCKS + depends on SMP + +config ARCH_USE_QUEUED_RWLOCKS + bool + +config QUEUED_RWLOCKS + def_bool y if ARCH_USE_QUEUED_RWLOCKS depends on SMP diff --git a/kernel/compat.c b/kernel/compat.c index 24f00610c575..333d364be29d 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -912,7 +912,8 @@ long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, * bitmap. We must however ensure the end of the * kernel bitmap is zeroed. */ - if (nr_compat_longs-- > 0) { + if (nr_compat_longs) { + nr_compat_longs--; if (__get_user(um, umask)) return -EFAULT; } else { @@ -954,7 +955,8 @@ long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, * We dont want to write past the end of the userspace * bitmap. */ - if (nr_compat_longs-- > 0) { + if (nr_compat_longs) { + nr_compat_longs--; if (__put_user(um, umask)) return -EFAULT; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 94bbe4695232..9c9c9fab16cc 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -398,7 +398,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ - smpboot_unpark_threads(cpu); cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); goto out_release; } @@ -463,6 +462,7 @@ static int smpboot_thread_call(struct notifier_block *nfb, switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_FAILED: case CPU_ONLINE: smpboot_unpark_threads(cpu); break; @@ -479,7 +479,7 @@ static struct notifier_block smpboot_thread_notifier = { .priority = CPU_PRI_SMPBOOT, }; -void __cpuinit smpboot_thread_init(void) +void smpboot_thread_init(void) { register_cpu_notifier(&smpboot_thread_notifier); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 1c6c2826af1e..8e13f3e54ec3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3418,7 +3418,6 @@ static void free_event_rcu(struct rcu_head *head) if (event->ns) put_pid_ns(event->ns); perf_event_free_filter(event); - perf_event_free_bpf_prog(event); kfree(event); } @@ -3549,6 +3548,8 @@ static void __free_event(struct perf_event *event) put_callchain_buffers(); } + perf_event_free_bpf_prog(event); + if (event->destroy) event->destroy(event); @@ -4306,20 +4307,20 @@ static void ring_buffer_attach(struct perf_event *event, WARN_ON_ONCE(event->rcu_pending); old_rb = event->rb; - event->rcu_batches = get_state_synchronize_rcu(); - event->rcu_pending = 1; - spin_lock_irqsave(&old_rb->event_lock, flags); list_del_rcu(&event->rb_entry); spin_unlock_irqrestore(&old_rb->event_lock, flags); - } - if (event->rcu_pending && rb) { - cond_synchronize_rcu(event->rcu_batches); - event->rcu_pending = 0; + event->rcu_batches = get_state_synchronize_rcu(); + event->rcu_pending = 1; } if (rb) { + if (event->rcu_pending) { + cond_synchronize_rcu(event->rcu_batches); + event->rcu_pending = 0; + } + spin_lock_irqsave(&rb->event_lock, flags); list_add_rcu(&event->rb_entry, &rb->event_list); spin_unlock_irqrestore(&rb->event_lock, flags); @@ -5356,9 +5357,9 @@ void perf_prepare_sample(struct perf_event_header *header, } } -static void perf_event_output(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) +void perf_event_output(struct perf_event *event, + struct perf_sample_data *data, + struct pt_regs *regs) { struct perf_output_handle handle; struct perf_event_header header; @@ -5950,6 +5951,39 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head, } /* + * Lost/dropped samples logging + */ +void perf_log_lost_samples(struct perf_event *event, u64 lost) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + int ret; + + struct { + struct perf_event_header header; + u64 lost; + } lost_samples_event = { + .header = { + .type = PERF_RECORD_LOST_SAMPLES, + .misc = 0, + .size = sizeof(lost_samples_event), + }, + .lost = lost, + }; + + perf_event_header__init_id(&lost_samples_event.header, &sample, event); + + ret = perf_output_begin(&handle, event, + lost_samples_event.header.size); + if (ret) + return; + + perf_output_put(&handle, lost_samples_event); + perf_event__output_id_sample(event, &handle, &sample); + perf_output_end(&handle); +} + +/* * IRQ throttle logging */ diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 9f6ce9ba4a04..2deb24c7a40d 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -72,15 +72,6 @@ static inline bool rb_has_aux(struct ring_buffer *rb) void perf_event_aux_event(struct perf_event *event, unsigned long head, unsigned long size, u64 flags); -extern void -perf_event_header__init_id(struct perf_event_header *header, - struct perf_sample_data *data, - struct perf_event *event); -extern void -perf_event__output_id_sample(struct perf_event *event, - struct perf_output_handle *handle, - struct perf_sample_data *sample); - extern struct page * perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 232f00f273cb..96472824a752 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 = ACCESS_ONCE(rb->user_page->data_tail); + tail = READ_ONCE_CTRL(rb->user_page->data_tail); offset = head = local_read(&rb->head); if (!rb->overwrite && unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size)) @@ -493,6 +493,20 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, rb->aux_pages[rb->aux_nr_pages] = page_address(page++); } + /* + * In overwrite mode, PMUs that don't support SG may not handle more + * than one contiguous allocation, since they rely on PMI to do double + * buffering. In this case, the entire buffer has to be one contiguous + * chunk. + */ + if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) && + overwrite) { + struct page *page = virt_to_page(rb->aux_pages[0]); + + if (page_private(page) != max_order) + goto out; + } + rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages, overwrite); if (!rb->aux_priv) diff --git a/kernel/fork.c b/kernel/fork.c index 03c1eaaa6ef5..0bb88b555550 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1091,10 +1091,7 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig) { unsigned long cpu_limit; - /* Thread group counters. */ - thread_group_cputime_init(sig); - - cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); + 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; @@ -1396,6 +1393,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->hardirq_context = 0; p->softirq_context = 0; #endif + + p->pagefault_disabled = 0; + #ifdef CONFIG_LOCKDEP p->lockdep_depth = 0; /* no locks held yet */ p->curr_chain_key = 0; diff --git a/kernel/futex.c b/kernel/futex.c index 720eacff6b58..ea6ca0bca525 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1090,9 +1090,11 @@ static void __unqueue_futex(struct futex_q *q) /* * The hash bucket lock must be held when this is called. - * Afterwards, the futex_q must not be accessed. + * Afterwards, the futex_q must not be accessed. Callers + * must ensure to later call wake_up_q() for the actual + * wakeups to occur. */ -static void wake_futex(struct futex_q *q) +static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) { struct task_struct *p = q->task; @@ -1100,14 +1102,10 @@ static void wake_futex(struct futex_q *q) return; /* - * We set q->lock_ptr = NULL _before_ we wake up the task. If - * a non-futex wake up happens on another CPU then the task - * might exit and p would dereference a non-existing task - * struct. Prevent this by holding a reference on p across the - * wake up. + * Queue the task for later wakeup for after we've released + * the hb->lock. wake_q_add() grabs reference to p. */ - get_task_struct(p); - + wake_q_add(wake_q, p); __unqueue_futex(q); /* * The waiting task can free the futex_q as soon as @@ -1117,9 +1115,6 @@ static void wake_futex(struct futex_q *q) */ smp_wmb(); q->lock_ptr = NULL; - - wake_up_state(p, TASK_NORMAL); - put_task_struct(p); } static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this) @@ -1217,6 +1212,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) struct futex_q *this, *next; union futex_key key = FUTEX_KEY_INIT; int ret; + WAKE_Q(wake_q); if (!bitset) return -EINVAL; @@ -1244,13 +1240,14 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) if (!(this->bitset & bitset)) continue; - wake_futex(this); + mark_wake_futex(&wake_q, this); if (++ret >= nr_wake) break; } } spin_unlock(&hb->lock); + wake_up_q(&wake_q); out_put_key: put_futex_key(&key); out: @@ -1269,6 +1266,7 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, struct futex_hash_bucket *hb1, *hb2; struct futex_q *this, *next; int ret, op_ret; + WAKE_Q(wake_q); retry: ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ); @@ -1320,7 +1318,7 @@ retry_private: ret = -EINVAL; goto out_unlock; } - wake_futex(this); + mark_wake_futex(&wake_q, this); if (++ret >= nr_wake) break; } @@ -1334,7 +1332,7 @@ retry_private: ret = -EINVAL; goto out_unlock; } - wake_futex(this); + mark_wake_futex(&wake_q, this); if (++op_ret >= nr_wake2) break; } @@ -1344,6 +1342,7 @@ retry_private: out_unlock: double_unlock_hb(hb1, hb2); + wake_up_q(&wake_q); out_put_keys: put_futex_key(&key2); out_put_key1: @@ -1503,6 +1502,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, struct futex_pi_state *pi_state = NULL; struct futex_hash_bucket *hb1, *hb2; struct futex_q *this, *next; + WAKE_Q(wake_q); if (requeue_pi) { /* @@ -1679,7 +1679,7 @@ retry_private: * woken by futex_unlock_pi(). */ if (++task_count <= nr_wake && !requeue_pi) { - wake_futex(this); + mark_wake_futex(&wake_q, this); continue; } @@ -1719,6 +1719,7 @@ retry_private: out_unlock: free_pi_state(pi_state); double_unlock_hb(hb1, hb2); + wake_up_q(&wake_q); hb_waiters_dec(hb2); /* @@ -2055,7 +2056,7 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, { /* * The task state is guaranteed to be set before another task can - * wake it. set_current_state() is implemented using set_mb() and + * wake it. set_current_state() is implemented using smp_store_mb() and * queue_me() calls spin_unlock() upon completion, both serializing * access to the hash list and forcing another memory barrier. */ diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index eb9a4ea394ab..55016b2151f3 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -950,6 +950,20 @@ int irq_chip_retrigger_hierarchy(struct irq_data *data) } /** + * irq_chip_set_vcpu_affinity_parent - Set vcpu affinity on the parent interrupt + * @data: Pointer to interrupt specific data + * @dest: The vcpu affinity information + */ +int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info) +{ + data = data->parent_data; + if (data->chip->irq_set_vcpu_affinity) + return data->chip->irq_set_vcpu_affinity(data, vcpu_info); + + return -ENOSYS; +} + +/** * irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt * @data: Pointer to interrupt specific data * @on: Whether to set or reset the wake-up capability of this irq diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index df553b0af936..b93d434e70bd 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -59,8 +59,6 @@ enum { #include "debug.h" #include "settings.h" -#define irq_data_to_desc(data) container_of(data, struct irq_desc, irq_data) - extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, unsigned long flags); extern void __disable_irq(struct irq_desc *desc, unsigned int irq); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index e68932bb308e..b1c7e8f46bfb 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -256,6 +256,37 @@ 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 = diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index ca3f4aaff707..dd203e276b07 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -7,7 +7,7 @@ void irq_move_masked_irq(struct irq_data *idata) { struct irq_desc *desc = irq_data_to_desc(idata); - struct irq_chip *chip = idata->chip; + struct irq_chip *chip = desc->irq_data.chip; if (likely(!irqd_is_setaffinity_pending(&desc->irq_data))) return; @@ -52,6 +52,13 @@ void irq_move_irq(struct irq_data *idata) { bool masked; + /* + * Get top level irq_data when CONFIG_IRQ_DOMAIN_HIERARCHY is enabled, + * and it should be optimized away when CONFIG_IRQ_DOMAIN_HIERARCHY is + * disabled. So we avoid an "#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY" here. + */ + idata = irq_desc_get_irq_data(irq_data_to_desc(idata)); + if (likely(!irqd_is_setaffinity_pending(idata))) return; diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index de7a416cca2a..7dd5c9918e4c 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_SMP) += spinlock.o obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o obj-$(CONFIG_SMP) += lglock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o +obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o @@ -25,5 +26,5 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o -obj-$(CONFIG_QUEUE_RWLOCK) += qrwlock.o +obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o diff --git a/kernel/locking/lglock.c b/kernel/locking/lglock.c index 86ae2aebf004..951cfcd10b4a 100644 --- a/kernel/locking/lglock.c +++ b/kernel/locking/lglock.c @@ -60,6 +60,28 @@ void lg_local_unlock_cpu(struct lglock *lg, int cpu) } EXPORT_SYMBOL(lg_local_unlock_cpu); +void lg_double_lock(struct lglock *lg, int cpu1, int cpu2) +{ + BUG_ON(cpu1 == cpu2); + + /* lock in cpu order, just like lg_global_lock */ + if (cpu2 < cpu1) + swap(cpu1, cpu2); + + preempt_disable(); + lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); + arch_spin_lock(per_cpu_ptr(lg->lock, cpu1)); + arch_spin_lock(per_cpu_ptr(lg->lock, cpu2)); +} + +void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2) +{ + lock_release(&lg->lock_dep_map, 1, _RET_IP_); + arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1)); + arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2)); + preempt_enable(); +} + void lg_global_lock(struct lglock *lg) { int i; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index a0831e1b99f4..456614136f1a 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3900,7 +3900,8 @@ static void zap_class(struct lock_class *class) list_del_rcu(&class->hash_entry); list_del_rcu(&class->lock_entry); - class->key = NULL; + RCU_INIT_POINTER(class->key, NULL); + RCU_INIT_POINTER(class->name, NULL); } static inline int within(const void *addr, void *start, unsigned long size) @@ -4066,8 +4067,7 @@ void __init lockdep_info(void) #ifdef CONFIG_DEBUG_LOCKDEP if (lockdep_init_error) { - printk("WARNING: lockdep init error! lock-%s was acquired" - "before lockdep_init\n", lock_init_error); + printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error); printk("Call stack leading to lockdep invocation was:\n"); print_stack_trace(&lockdep_init_trace, 0); } diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index ef43ac4bafb5..d83d798bef95 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -426,10 +426,12 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt) static void seq_stats(struct seq_file *m, struct lock_stat_data *data) { - char name[39]; - struct lock_class *class; + struct lockdep_subclass_key *ckey; struct lock_class_stats *stats; + struct lock_class *class; + const char *cname; int i, namelen; + char name[39]; class = data->class; stats = &data->stats; @@ -440,15 +442,25 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) if (class->subclass) namelen -= 2; - if (!class->name) { + rcu_read_lock_sched(); + cname = rcu_dereference_sched(class->name); + ckey = rcu_dereference_sched(class->key); + + if (!cname && !ckey) { + rcu_read_unlock_sched(); + return; + + } else if (!cname) { char str[KSYM_NAME_LEN]; const char *key_name; - key_name = __get_key_name(class->key, str); + key_name = __get_key_name(ckey, str); snprintf(name, namelen, "%s", key_name); } else { - snprintf(name, namelen, "%s", class->name); + snprintf(name, namelen, "%s", cname); } + rcu_read_unlock_sched(); + namelen = strlen(name); if (class->name_version > 1) { snprintf(name+namelen, 3, "#%d", class->name_version); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index ec8cce259779..32244186f1f2 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -122,12 +122,12 @@ static int torture_lock_busted_write_lock(void) static void torture_lock_busted_write_delay(struct torture_random_state *trsp) { - const unsigned long longdelay_us = 100; + const unsigned long longdelay_ms = 100; /* We want a long delay occasionally to force massive contention. */ if (!(torture_random(trsp) % - (cxt.nrealwriters_stress * 2000 * longdelay_us))) - mdelay(longdelay_us); + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms); #ifdef CONFIG_PREEMPT if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000))) preempt_schedule(); /* Allow test to be preempted. */ @@ -160,14 +160,14 @@ static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock) static void torture_spin_lock_write_delay(struct torture_random_state *trsp) { const unsigned long shortdelay_us = 2; - const unsigned long longdelay_us = 100; + 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_us))) - mdelay(longdelay_us); + (cxt.nrealwriters_stress * 2000 * longdelay_ms))) + mdelay(longdelay_ms); if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 2 * shortdelay_us))) udelay(shortdelay_us); @@ -309,7 +309,7 @@ static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock) static void torture_rwlock_read_unlock_irq(void) __releases(torture_rwlock) { - write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags); + read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags); } static struct lock_torture_ops rw_lock_irq_ops = { diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 75e114bdf3f2..fd91aaa4554c 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -17,6 +17,7 @@ struct mcs_spinlock { struct mcs_spinlock *next; int locked; /* 1 if lock acquired */ + int count; /* nesting count, see qspinlock.c */ }; #ifndef arch_mcs_spin_lock_contended diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index f956ede7f90d..6c5da483966b 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -1,5 +1,5 @@ /* - * Queue read/write lock + * Queued read/write locks * * 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 @@ -22,6 +22,26 @@ #include <linux/hardirq.h> #include <asm/qrwlock.h> +/* + * This internal data structure is used for optimizing access to some of + * the subfields within the atomic_t cnts. + */ +struct __qrwlock { + union { + atomic_t cnts; + struct { +#ifdef __LITTLE_ENDIAN + u8 wmode; /* Writer mode */ + u8 rcnts[3]; /* Reader counts */ +#else + u8 rcnts[3]; /* Reader counts */ + u8 wmode; /* Writer mode */ +#endif + }; + }; + arch_spinlock_t lock; +}; + /** * rspin_until_writer_unlock - inc reader count & spin until writer is gone * @lock : Pointer to queue rwlock structure @@ -107,10 +127,10 @@ void queue_write_lock_slowpath(struct qrwlock *lock) * or wait for a previous writer to go away. */ for (;;) { - cnts = atomic_read(&lock->cnts); - if (!(cnts & _QW_WMASK) && - (atomic_cmpxchg(&lock->cnts, cnts, - cnts | _QW_WAITING) == cnts)) + struct __qrwlock *l = (struct __qrwlock *)lock; + + if (!READ_ONCE(l->wmode) && + (cmpxchg(&l->wmode, 0, _QW_WAITING) == 0)) break; cpu_relax_lowlatency(); diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c new file mode 100644 index 000000000000..38c49202d532 --- /dev/null +++ b/kernel/locking/qspinlock.c @@ -0,0 +1,473 @@ +/* + * Queued spinlock + * + * 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. + * + * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. + * (C) Copyright 2013-2014 Red Hat, Inc. + * (C) Copyright 2015 Intel Corp. + * + * Authors: Waiman Long <waiman.long@hp.com> + * Peter Zijlstra <peterz@infradead.org> + */ + +#ifndef _GEN_PV_LOCK_SLOWPATH + +#include <linux/smp.h> +#include <linux/bug.h> +#include <linux/cpumask.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> +#include <linux/mutex.h> +#include <asm/byteorder.h> +#include <asm/qspinlock.h> + +/* + * The basic principle of a queue-based spinlock can best be understood + * by studying a classic queue-based spinlock implementation called the + * MCS lock. The paper below provides a good description for this kind + * of lock. + * + * http://www.cise.ufl.edu/tr/DOC/REP-1992-71.pdf + * + * This queued spinlock implementation is based on the MCS lock, however to make + * it fit the 4 bytes we assume spinlock_t to be, and preserve its existing + * API, we must modify it somehow. + * + * In particular; where the traditional MCS lock consists of a tail pointer + * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to + * unlock the next pending (next->locked), we compress both these: {tail, + * next->locked} into a single u32 value. + * + * Since a spinlock disables recursion of its own context and there is a limit + * to the contexts that can nest; namely: task, softirq, hardirq, nmi. As there + * are at most 4 nesting levels, it can be encoded by a 2-bit number. Now + * we can encode the tail by combining the 2-bit nesting level with the cpu + * number. With one byte for the lock value and 3 bytes for the tail, only a + * 32-bit word is now needed. Even though we only need 1 bit for the lock, + * we extend it to a full byte to achieve better performance for architectures + * that support atomic byte write. + * + * We also change the first spinner to spin on the lock bit instead of its + * node; whereby avoiding the need to carry a node from lock to unlock, and + * preserving existing lock API. This also makes the unlock code simpler and + * faster. + * + * N.B. The current implementation only supports architectures that allow + * atomic operations on smaller 8-bit and 16-bit data types. + * + */ + +#include "mcs_spinlock.h" + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +#define MAX_NODES 8 +#else +#define MAX_NODES 4 +#endif + +/* + * Per-CPU queue node structures; we can never have more than 4 nested + * contexts: task, softirq, hardirq, nmi. + * + * Exactly fits one 64-byte cacheline on a 64-bit architecture. + * + * PV doubles the storage and uses the second cacheline for PV state. + */ +static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]); + +/* + * We must be able to distinguish between no-tail and the tail at 0:0, + * therefore increment the cpu number by one. + */ + +static inline u32 encode_tail(int cpu, int idx) +{ + u32 tail; + +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(idx > 3); +#endif + tail = (cpu + 1) << _Q_TAIL_CPU_OFFSET; + tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */ + + return tail; +} + +static inline struct mcs_spinlock *decode_tail(u32 tail) +{ + int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1; + int idx = (tail & _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET; + + return per_cpu_ptr(&mcs_nodes[idx], cpu); +} + +#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK) + +/* + * By using the whole 2nd least significant byte for the pending bit, we + * can allow better optimization of the lock acquisition for the pending + * bit holder. + * + * This internal structure is also used by the set_locked function which + * is not restricted to _Q_PENDING_BITS == 8. + */ +struct __qspinlock { + union { + atomic_t val; +#ifdef __LITTLE_ENDIAN + struct { + u8 locked; + u8 pending; + }; + struct { + u16 locked_pending; + u16 tail; + }; +#else + struct { + u16 tail; + u16 locked_pending; + }; + struct { + u8 reserved[2]; + u8 pending; + u8 locked; + }; +#endif + }; +}; + +#if _Q_PENDING_BITS == 8 +/** + * clear_pending_set_locked - take ownership and clear the pending bit. + * @lock: Pointer to queued spinlock structure + * + * *,1,0 -> *,0,1 + * + * Lock stealing is not allowed if this function is used. + */ +static __always_inline void clear_pending_set_locked(struct qspinlock *lock) +{ + struct __qspinlock *l = (void *)lock; + + WRITE_ONCE(l->locked_pending, _Q_LOCKED_VAL); +} + +/* + * xchg_tail - Put in the new queue tail code word & retrieve previous one + * @lock : Pointer to queued spinlock structure + * @tail : The new queue tail code word + * Return: The previous queue tail code word + * + * xchg(lock, tail) + * + * p,*,* -> n,*,* ; prev = xchg(lock, node) + */ +static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) +{ + struct __qspinlock *l = (void *)lock; + + return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET; +} + +#else /* _Q_PENDING_BITS == 8 */ + +/** + * clear_pending_set_locked - take ownership and clear the pending bit. + * @lock: Pointer to queued spinlock structure + * + * *,1,0 -> *,0,1 + */ +static __always_inline void clear_pending_set_locked(struct qspinlock *lock) +{ + atomic_add(-_Q_PENDING_VAL + _Q_LOCKED_VAL, &lock->val); +} + +/** + * xchg_tail - Put in the new queue tail code word & retrieve previous one + * @lock : Pointer to queued spinlock structure + * @tail : The new queue tail code word + * Return: The previous queue tail code word + * + * xchg(lock, tail) + * + * p,*,* -> n,*,* ; prev = xchg(lock, node) + */ +static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) +{ + u32 old, new, val = atomic_read(&lock->val); + + for (;;) { + new = (val & _Q_LOCKED_PENDING_MASK) | tail; + old = atomic_cmpxchg(&lock->val, val, new); + if (old == val) + break; + + val = old; + } + return old; +} +#endif /* _Q_PENDING_BITS == 8 */ + +/** + * set_locked - Set the lock bit and own the lock + * @lock: Pointer to queued spinlock structure + * + * *,*,0 -> *,0,1 + */ +static __always_inline void set_locked(struct qspinlock *lock) +{ + struct __qspinlock *l = (void *)lock; + + WRITE_ONCE(l->locked, _Q_LOCKED_VAL); +} + + +/* + * Generate the native code for queued_spin_unlock_slowpath(); provide NOPs for + * all the PV callbacks. + */ + +static __always_inline void __pv_init_node(struct mcs_spinlock *node) { } +static __always_inline void __pv_wait_node(struct mcs_spinlock *node) { } +static __always_inline void __pv_kick_node(struct mcs_spinlock *node) { } + +static __always_inline void __pv_wait_head(struct qspinlock *lock, + struct mcs_spinlock *node) { } + +#define pv_enabled() false + +#define pv_init_node __pv_init_node +#define pv_wait_node __pv_wait_node +#define pv_kick_node __pv_kick_node +#define pv_wait_head __pv_wait_head + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +#define queued_spin_lock_slowpath native_queued_spin_lock_slowpath +#endif + +#endif /* _GEN_PV_LOCK_SLOWPATH */ + +/** + * queued_spin_lock_slowpath - acquire the queued spinlock + * @lock: Pointer to queued spinlock structure + * @val: Current value of the queued spinlock 32-bit word + * + * (queue tail, pending bit, lock value) + * + * fast : slow : unlock + * : : + * uncontended (0,0,0) -:--> (0,0,1) ------------------------------:--> (*,*,0) + * : | ^--------.------. / : + * : v \ \ | : + * pending : (0,1,1) +--> (0,1,0) \ | : + * : | ^--' | | : + * : v | | : + * uncontended : (n,x,y) +--> (n,0,0) --' | : + * queue : | ^--' | : + * : v | : + * contended : (*,x,y) +--> (*,0,0) ---> (*,0,1) -' : + * queue : ^--' : + */ +void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) +{ + struct mcs_spinlock *prev, *next, *node; + u32 new, old, tail; + int idx; + + BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS)); + + if (pv_enabled()) + goto queue; + + if (virt_queued_spin_lock(lock)) + return; + + /* + * wait for in-progress pending->locked hand-overs + * + * 0,1,0 -> 0,0,1 + */ + if (val == _Q_PENDING_VAL) { + while ((val = atomic_read(&lock->val)) == _Q_PENDING_VAL) + cpu_relax(); + } + + /* + * trylock || pending + * + * 0,0,0 -> 0,0,1 ; trylock + * 0,0,1 -> 0,1,1 ; pending + */ + for (;;) { + /* + * If we observe any contention; queue. + */ + if (val & ~_Q_LOCKED_MASK) + goto queue; + + new = _Q_LOCKED_VAL; + if (val == new) + new |= _Q_PENDING_VAL; + + old = atomic_cmpxchg(&lock->val, val, new); + if (old == val) + break; + + val = old; + } + + /* + * we won the trylock + */ + if (new == _Q_LOCKED_VAL) + return; + + /* + * we're pending, wait for the owner to go away. + * + * *,1,1 -> *,1,0 + * + * this wait loop must be a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because not all clear_pending_set_locked() + * implementations imply full barriers. + */ + while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK) + cpu_relax(); + + /* + * take ownership and clear the pending bit. + * + * *,1,0 -> *,0,1 + */ + clear_pending_set_locked(lock); + return; + + /* + * End of pending bit optimistic spinning and beginning of MCS + * queuing. + */ +queue: + node = this_cpu_ptr(&mcs_nodes[0]); + idx = node->count++; + tail = encode_tail(smp_processor_id(), idx); + + node += idx; + node->locked = 0; + node->next = NULL; + pv_init_node(node); + + /* + * We touched a (possibly) cold cacheline in the per-cpu queue node; + * attempt the trylock once more in the hope someone let go while we + * weren't watching. + */ + if (queued_spin_trylock(lock)) + goto release; + + /* + * We have already touched the queueing cacheline; don't bother with + * pending stuff. + * + * p,*,* -> n,*,* + */ + old = xchg_tail(lock, tail); + + /* + * if there was a previous node; link it and wait until reaching the + * head of the waitqueue. + */ + if (old & _Q_TAIL_MASK) { + prev = decode_tail(old); + WRITE_ONCE(prev->next, node); + + pv_wait_node(node); + arch_mcs_spin_lock_contended(&node->locked); + } + + /* + * we're at the head of the waitqueue, wait for the owner & pending to + * go away. + * + * *,x,y -> *,0,0 + * + * this wait loop must use a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because the set_locked() function below + * does not imply a full barrier. + * + */ + pv_wait_head(lock, node); + while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK) + cpu_relax(); + + /* + * claim the lock: + * + * n,0,0 -> 0,0,1 : lock, uncontended + * *,0,0 -> *,0,1 : lock, contended + * + * If the queue head is the only one in the queue (lock value == tail), + * clear the tail code and grab the lock. Otherwise, we only need + * to grab the lock. + */ + for (;;) { + if (val != tail) { + set_locked(lock); + break; + } + old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL); + if (old == val) + goto release; /* No contention */ + + val = old; + } + + /* + * contended path; wait for next, release. + */ + while (!(next = READ_ONCE(node->next))) + cpu_relax(); + + arch_mcs_spin_unlock_contended(&next->locked); + pv_kick_node(next); + +release: + /* + * release the node + */ + this_cpu_dec(mcs_nodes[0].count); +} +EXPORT_SYMBOL(queued_spin_lock_slowpath); + +/* + * Generate the paravirt code for queued_spin_unlock_slowpath(). + */ +#if !defined(_GEN_PV_LOCK_SLOWPATH) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#define _GEN_PV_LOCK_SLOWPATH + +#undef pv_enabled +#define pv_enabled() true + +#undef pv_init_node +#undef pv_wait_node +#undef pv_kick_node +#undef pv_wait_head + +#undef queued_spin_lock_slowpath +#define queued_spin_lock_slowpath __pv_queued_spin_lock_slowpath + +#include "qspinlock_paravirt.h" +#include "qspinlock.c" + +#endif diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h new file mode 100644 index 000000000000..04ab18151cc8 --- /dev/null +++ b/kernel/locking/qspinlock_paravirt.h @@ -0,0 +1,325 @@ +#ifndef _GEN_PV_LOCK_SLOWPATH +#error "do not include this file" +#endif + +#include <linux/hash.h> +#include <linux/bootmem.h> + +/* + * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead + * of spinning them. + * + * This relies on the architecture to provide two paravirt hypercalls: + * + * pv_wait(u8 *ptr, u8 val) -- suspends the vcpu if *ptr == val + * pv_kick(cpu) -- wakes a suspended vcpu + * + * Using these we implement __pv_queued_spin_lock_slowpath() and + * __pv_queued_spin_unlock() to replace native_queued_spin_lock_slowpath() and + * native_queued_spin_unlock(). + */ + +#define _Q_SLOW_VAL (3U << _Q_LOCKED_OFFSET) + +enum vcpu_state { + vcpu_running = 0, + vcpu_halted, +}; + +struct pv_node { + struct mcs_spinlock mcs; + struct mcs_spinlock __res[3]; + + int cpu; + u8 state; +}; + +/* + * Lock and MCS node addresses hash table for fast lookup + * + * Hashing is done on a per-cacheline basis to minimize the need to access + * more than one cacheline. + * + * Dynamically allocate a hash table big enough to hold at least 4X the + * number of possible cpus in the system. Allocation is done on page + * granularity. So the minimum number of hash buckets should be at least + * 256 (64-bit) or 512 (32-bit) to fully utilize a 4k page. + * + * Since we should not be holding locks from NMI context (very rare indeed) the + * max load factor is 0.75, which is around the point where open addressing + * breaks down. + * + */ +struct pv_hash_entry { + struct qspinlock *lock; + struct pv_node *node; +}; + +#define PV_HE_PER_LINE (SMP_CACHE_BYTES / sizeof(struct pv_hash_entry)) +#define PV_HE_MIN (PAGE_SIZE / sizeof(struct pv_hash_entry)) + +static struct pv_hash_entry *pv_lock_hash; +static unsigned int pv_lock_hash_bits __read_mostly; + +/* + * Allocate memory for the PV qspinlock hash buckets + * + * This function should be called from the paravirt spinlock initialization + * routine. + */ +void __init __pv_init_lock_hash(void) +{ + int pv_hash_size = ALIGN(4 * num_possible_cpus(), PV_HE_PER_LINE); + + if (pv_hash_size < PV_HE_MIN) + pv_hash_size = PV_HE_MIN; + + /* + * Allocate space from bootmem which should be page-size aligned + * and hence cacheline aligned. + */ + pv_lock_hash = alloc_large_system_hash("PV qspinlock", + sizeof(struct pv_hash_entry), + pv_hash_size, 0, HASH_EARLY, + &pv_lock_hash_bits, NULL, + pv_hash_size, pv_hash_size); +} + +#define for_each_hash_entry(he, offset, hash) \ + for (hash &= ~(PV_HE_PER_LINE - 1), he = &pv_lock_hash[hash], offset = 0; \ + offset < (1 << pv_lock_hash_bits); \ + offset++, he = &pv_lock_hash[(hash + offset) & ((1 << pv_lock_hash_bits) - 1)]) + +static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node) +{ + unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits); + struct pv_hash_entry *he; + + for_each_hash_entry(he, offset, hash) { + if (!cmpxchg(&he->lock, NULL, lock)) { + WRITE_ONCE(he->node, node); + return &he->lock; + } + } + /* + * Hard assume there is a free entry for us. + * + * This is guaranteed by ensuring every blocked lock only ever consumes + * a single entry, and since we only have 4 nesting levels per CPU + * and allocated 4*nr_possible_cpus(), this must be so. + * + * The single entry is guaranteed by having the lock owner unhash + * before it releases. + */ + BUG(); +} + +static struct pv_node *pv_unhash(struct qspinlock *lock) +{ + unsigned long offset, hash = hash_ptr(lock, pv_lock_hash_bits); + struct pv_hash_entry *he; + struct pv_node *node; + + for_each_hash_entry(he, offset, hash) { + if (READ_ONCE(he->lock) == lock) { + node = READ_ONCE(he->node); + WRITE_ONCE(he->lock, NULL); + return node; + } + } + /* + * Hard assume we'll find an entry. + * + * This guarantees a limited lookup time and is itself guaranteed by + * having the lock owner do the unhash -- IFF the unlock sees the + * SLOW flag, there MUST be a hash entry. + */ + BUG(); +} + +/* + * Initialize the PV part of the mcs_spinlock node. + */ +static void pv_init_node(struct mcs_spinlock *node) +{ + struct pv_node *pn = (struct pv_node *)node; + + BUILD_BUG_ON(sizeof(struct pv_node) > 5*sizeof(struct mcs_spinlock)); + + pn->cpu = smp_processor_id(); + pn->state = vcpu_running; +} + +/* + * Wait for node->locked to become true, halt the vcpu after a short spin. + * pv_kick_node() is used to wake the vcpu again. + */ +static void pv_wait_node(struct mcs_spinlock *node) +{ + struct pv_node *pn = (struct pv_node *)node; + int loop; + + for (;;) { + for (loop = SPIN_THRESHOLD; loop; loop--) { + if (READ_ONCE(node->locked)) + return; + cpu_relax(); + } + + /* + * Order pn->state vs pn->locked thusly: + * + * [S] pn->state = vcpu_halted [S] next->locked = 1 + * MB MB + * [L] pn->locked [RmW] pn->state = vcpu_running + * + * Matches the xchg() from pv_kick_node(). + */ + smp_store_mb(pn->state, vcpu_halted); + + if (!READ_ONCE(node->locked)) + pv_wait(&pn->state, vcpu_halted); + + /* + * Reset the vCPU state to avoid unncessary CPU kicking + */ + WRITE_ONCE(pn->state, vcpu_running); + + /* + * If the locked flag is still not set after wakeup, it is a + * spurious wakeup and the vCPU should wait again. However, + * there is a pretty high overhead for CPU halting and kicking. + * So it is better to spin for a while in the hope that the + * MCS lock will be released soon. + */ + } + /* + * By now our node->locked should be 1 and our caller will not actually + * spin-wait for it. We do however rely on our caller to do a + * load-acquire for us. + */ +} + +/* + * Called after setting next->locked = 1, used to wake those stuck in + * pv_wait_node(). + */ +static void pv_kick_node(struct mcs_spinlock *node) +{ + struct pv_node *pn = (struct pv_node *)node; + + /* + * Note that because node->locked is already set, this actual + * mcs_spinlock entry could be re-used already. + * + * This should be fine however, kicking people for no reason is + * harmless. + * + * See the comment in pv_wait_node(). + */ + if (xchg(&pn->state, vcpu_running) == vcpu_halted) + pv_kick(pn->cpu); +} + +/* + * Wait for l->locked to become clear; halt the vcpu after a short spin. + * __pv_queued_spin_unlock() will wake us. + */ +static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node) +{ + struct pv_node *pn = (struct pv_node *)node; + struct __qspinlock *l = (void *)lock; + struct qspinlock **lp = NULL; + int loop; + + for (;;) { + for (loop = SPIN_THRESHOLD; loop; loop--) { + if (!READ_ONCE(l->locked)) + return; + cpu_relax(); + } + + WRITE_ONCE(pn->state, vcpu_halted); + if (!lp) { /* ONCE */ + lp = pv_hash(lock, pn); + /* + * lp must be set before setting _Q_SLOW_VAL + * + * [S] lp = lock [RmW] l = l->locked = 0 + * MB MB + * [S] l->locked = _Q_SLOW_VAL [L] lp + * + * Matches the cmpxchg() in __pv_queued_spin_unlock(). + */ + if (!cmpxchg(&l->locked, _Q_LOCKED_VAL, _Q_SLOW_VAL)) { + /* + * The lock is free and _Q_SLOW_VAL has never + * been set. Therefore we need to unhash before + * getting the lock. + */ + WRITE_ONCE(*lp, NULL); + return; + } + } + pv_wait(&l->locked, _Q_SLOW_VAL); + + /* + * The unlocker should have freed the lock before kicking the + * CPU. So if the lock is still not free, it is a spurious + * wakeup and so the vCPU should wait again after spinning for + * a while. + */ + } + + /* + * Lock is unlocked now; the caller will acquire it without waiting. + * As with pv_wait_node() we rely on the caller to do a load-acquire + * for us. + */ +} + +/* + * PV version of the unlock function to be used in stead of + * queued_spin_unlock(). + */ +__visible void __pv_queued_spin_unlock(struct qspinlock *lock) +{ + struct __qspinlock *l = (void *)lock; + struct pv_node *node; + + /* + * We must not unlock if SLOW, because in that case we must first + * unhash. Otherwise it would be possible to have multiple @lock + * entries, which would be BAD. + */ + if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL)) + return; + + /* + * Since the above failed to release, this must be the SLOW path. + * Therefore start by looking up the blocked node and unhashing it. + */ + node = pv_unhash(lock); + + /* + * Now that we have a reference to the (likely) blocked pv_node, + * release the lock. + */ + smp_store_release(&l->locked, 0); + + /* + * At this point the memory pointed at by lock can be freed/reused, + * however we can still use the pv_node to kick the CPU. + */ + if (READ_ONCE(node->state) == vcpu_halted) + pv_kick(node->cpu); +} +/* + * Include the architecture specific callee-save thunk of the + * __pv_queued_spin_unlock(). This thunk is put together with + * __pv_queued_spin_unlock() near the top of the file to make sure + * that the callee-save thunk and the real unlock function are close + * to each other sharing consecutive instruction cachelines. + */ +#include <asm/qspinlock_paravirt.h> + diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 8b678cac7fbe..36573e96a477 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -70,10 +70,10 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock) } /* - * We can speed up the acquire/release, if the architecture - * supports cmpxchg and if there's no debugging state to be set up + * We can speed up the acquire/release, if there's no debugging state to be + * set up. */ -#if defined(__HAVE_ARCH_CMPXCHG) && !defined(CONFIG_DEBUG_RT_MUTEXES) +#ifndef CONFIG_DEBUG_RT_MUTEXES # define rt_mutex_cmpxchg(l,c,n) (cmpxchg(&l->owner, c, n) == c) static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) { @@ -1440,10 +1440,17 @@ EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); * * @lock: the rt_mutex to be locked * + * This function can only be called in thread context. It's safe to + * call it from atomic regions, but not from hard interrupt or soft + * interrupt context. + * * Returns 1 on success and 0 on contention */ int __sched rt_mutex_trylock(struct rt_mutex *lock) { + if (WARN_ON(in_irq() || in_nmi() || in_serving_softirq())) + return 0; + return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); } EXPORT_SYMBOL_GPL(rt_mutex_trylock); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 3417d0172a5d..0f189714e457 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -409,11 +409,24 @@ done: return taken; } +/* + * Return true if the rwsem has active spinner + */ +static inline bool rwsem_has_spinner(struct rw_semaphore *sem) +{ + return osq_is_locked(&sem->osq); +} + #else static bool rwsem_optimistic_spin(struct rw_semaphore *sem) { return false; } + +static inline bool rwsem_has_spinner(struct rw_semaphore *sem) +{ + return false; +} #endif /* @@ -496,7 +509,38 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) { unsigned long flags; + /* + * If a spinner is present, it is not necessary to do the wakeup. + * Try to do wakeup only if the trylock succeeds to minimize + * spinlock contention which may introduce too much delay in the + * unlock operation. + * + * spinning writer up_write/up_read caller + * --------------- ----------------------- + * [S] osq_unlock() [L] osq + * MB RMB + * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock) + * + * Here, it is important to make sure that there won't be a missed + * wakeup while the rwsem is free and the only spinning writer goes + * to sleep without taking the rwsem. Even when the spinning writer + * is just going to break out of the waiting loop, it will still do + * a trylock in rwsem_down_write_failed() before sleeping. IOW, if + * rwsem_has_spinner() is true, it will guarantee at least one + * trylock attempt on the rwsem later on. + */ + if (rwsem_has_spinner(sem)) { + /* + * The smp_rmb() here is to make sure that the spinner + * state is consulted before reading the wait_lock. + */ + smp_rmb(); + if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags)) + return sem; + goto locked; + } raw_spin_lock_irqsave(&sem->wait_lock, flags); +locked: /* do nothing if list empty */ if (!list_empty(&sem->wait_list)) diff --git a/kernel/module.c b/kernel/module.c index 42a1d2afb217..cfc9e843a924 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3370,6 +3370,9 @@ static int load_module(struct load_info *info, const char __user *uargs, module_bug_cleanup(mod); mutex_unlock(&module_mutex); + blocking_notifier_call_chain(&module_notify_list, + MODULE_STATE_GOING, mod); + /* we can't deallocate the module until we clear memory protection */ unset_module_init_ro_nx(mod); unset_module_core_ro_nx(mod); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 8dbe27611ec3..59e32684c23b 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -241,6 +241,7 @@ rcu_torture_free(struct rcu_torture *p) struct rcu_torture_ops { int ttype; void (*init)(void); + void (*cleanup)(void); int (*readlock)(void); void (*read_delay)(struct torture_random_state *rrsp); void (*readunlock)(int idx); @@ -477,10 +478,12 @@ static struct rcu_torture_ops rcu_busted_ops = { */ DEFINE_STATIC_SRCU(srcu_ctl); +static struct srcu_struct srcu_ctld; +static struct srcu_struct *srcu_ctlp = &srcu_ctl; -static int srcu_torture_read_lock(void) __acquires(&srcu_ctl) +static int srcu_torture_read_lock(void) __acquires(srcu_ctlp) { - return srcu_read_lock(&srcu_ctl); + return srcu_read_lock(srcu_ctlp); } static void srcu_read_delay(struct torture_random_state *rrsp) @@ -499,49 +502,49 @@ static void srcu_read_delay(struct torture_random_state *rrsp) rcu_read_delay(rrsp); } -static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl) +static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp) { - srcu_read_unlock(&srcu_ctl, idx); + srcu_read_unlock(srcu_ctlp, idx); } static unsigned long srcu_torture_completed(void) { - return srcu_batches_completed(&srcu_ctl); + return srcu_batches_completed(srcu_ctlp); } static void srcu_torture_deferred_free(struct rcu_torture *rp) { - call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb); + call_srcu(srcu_ctlp, &rp->rtort_rcu, rcu_torture_cb); } static void srcu_torture_synchronize(void) { - synchronize_srcu(&srcu_ctl); + synchronize_srcu(srcu_ctlp); } static void srcu_torture_call(struct rcu_head *head, void (*func)(struct rcu_head *head)) { - call_srcu(&srcu_ctl, head, func); + call_srcu(srcu_ctlp, head, func); } static void srcu_torture_barrier(void) { - srcu_barrier(&srcu_ctl); + srcu_barrier(srcu_ctlp); } static void srcu_torture_stats(void) { int cpu; - int idx = srcu_ctl.completed & 0x1; + int idx = srcu_ctlp->completed & 0x1; pr_alert("%s%s per-CPU(idx=%d):", torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { long c0, c1; - c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx]; - c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]; + c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx]; + c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx]; pr_cont(" %d(%ld,%ld)", cpu, c0, c1); } pr_cont("\n"); @@ -549,7 +552,7 @@ static void srcu_torture_stats(void) static void srcu_torture_synchronize_expedited(void) { - synchronize_srcu_expedited(&srcu_ctl); + synchronize_srcu_expedited(srcu_ctlp); } static struct rcu_torture_ops srcu_ops = { @@ -569,6 +572,38 @@ static struct rcu_torture_ops srcu_ops = { .name = "srcu" }; +static void srcu_torture_init(void) +{ + rcu_sync_torture_init(); + WARN_ON(init_srcu_struct(&srcu_ctld)); + srcu_ctlp = &srcu_ctld; +} + +static void srcu_torture_cleanup(void) +{ + cleanup_srcu_struct(&srcu_ctld); + srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */ +} + +/* As above, but dynamically allocated. */ +static struct rcu_torture_ops srcud_ops = { + .ttype = SRCU_FLAVOR, + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock, + .read_delay = srcu_read_delay, + .readunlock = srcu_torture_read_unlock, + .started = NULL, + .completed = srcu_torture_completed, + .deferred_free = srcu_torture_deferred_free, + .sync = srcu_torture_synchronize, + .exp_sync = srcu_torture_synchronize_expedited, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, + .stats = srcu_torture_stats, + .name = "srcud" +}; + /* * Definitions for sched torture testing. */ @@ -672,8 +707,8 @@ static void rcu_torture_boost_cb(struct rcu_head *head) struct rcu_boost_inflight *rbip = container_of(head, struct rcu_boost_inflight, rcu); - smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */ - rbip->inflight = 0; + /* Ensure RCU-core accesses precede clearing ->inflight */ + smp_store_release(&rbip->inflight, 0); } static int rcu_torture_boost(void *arg) @@ -710,9 +745,9 @@ static int rcu_torture_boost(void *arg) call_rcu_time = jiffies; while (ULONG_CMP_LT(jiffies, endtime)) { /* If we don't have a callback in flight, post one. */ - if (!rbi.inflight) { - smp_mb(); /* RCU core before ->inflight = 1. */ - rbi.inflight = 1; + if (!smp_load_acquire(&rbi.inflight)) { + /* RCU core before ->inflight = 1. */ + smp_store_release(&rbi.inflight, 1); call_rcu(&rbi.rcu, rcu_torture_boost_cb); if (jiffies - call_rcu_time > test_boost_duration * HZ - HZ / 2) { @@ -751,11 +786,10 @@ checkwait: stutter_wait("rcu_torture_boost"); } while (!torture_must_stop()); /* Clean up and exit. */ - while (!kthread_should_stop() || rbi.inflight) { + while (!kthread_should_stop() || smp_load_acquire(&rbi.inflight)) { torture_shutdown_absorb("rcu_torture_boost"); schedule_timeout_uninterruptible(1); } - smp_mb(); /* order accesses to ->inflight before stack-frame death. */ destroy_rcu_head_on_stack(&rbi.rcu); torture_kthread_stopping("rcu_torture_boost"); return 0; @@ -1054,7 +1088,7 @@ static void rcu_torture_timer(unsigned long unused) p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || - srcu_read_lock_held(&srcu_ctl)); + srcu_read_lock_held(srcu_ctlp)); if (p == NULL) { /* Leave because rcu_torture_writer is not yet underway */ cur_ops->readunlock(idx); @@ -1128,7 +1162,7 @@ rcu_torture_reader(void *arg) p = rcu_dereference_check(rcu_torture_current, rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || - srcu_read_lock_held(&srcu_ctl)); + srcu_read_lock_held(srcu_ctlp)); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ cur_ops->readunlock(idx); @@ -1413,12 +1447,15 @@ static int rcu_torture_barrier_cbs(void *arg) do { wait_event(barrier_cbs_wq[myid], (newphase = - ACCESS_ONCE(barrier_phase)) != lastphase || + smp_load_acquire(&barrier_phase)) != lastphase || torture_must_stop()); lastphase = newphase; - smp_mb(); /* ensure barrier_phase load before ->call(). */ if (torture_must_stop()) break; + /* + * The above smp_load_acquire() ensures barrier_phase load + * is ordered before the folloiwng ->call(). + */ cur_ops->call(&rcu, rcu_torture_barrier_cbf); if (atomic_dec_and_test(&barrier_cbs_count)) wake_up(&barrier_wq); @@ -1439,8 +1476,8 @@ static int rcu_torture_barrier(void *arg) do { atomic_set(&barrier_cbs_invoked, 0); atomic_set(&barrier_cbs_count, n_barrier_cbs); - smp_mb(); /* Ensure barrier_phase after prior assignments. */ - barrier_phase = !barrier_phase; + /* Ensure barrier_phase ordered after prior assignments. */ + smp_store_release(&barrier_phase, !barrier_phase); for (i = 0; i < n_barrier_cbs; i++) wake_up(&barrier_cbs_wq[i]); wait_event(barrier_wq, @@ -1588,10 +1625,14 @@ rcu_torture_cleanup(void) rcutorture_booster_cleanup(i); } - /* Wait for all RCU callbacks to fire. */ - + /* + * Wait for all RCU callbacks to fire, then do flavor-specific + * cleanup operations. + */ if (cur_ops->cb_barrier != NULL) cur_ops->cb_barrier(); + if (cur_ops->cleanup != NULL) + cur_ops->cleanup(); rcu_torture_stats_print(); /* -After- the stats thread is stopped! */ @@ -1668,8 +1709,8 @@ rcu_torture_init(void) int cpu; int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { - &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops, - RCUTORTURE_TASKS_OPS + &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, + &sched_ops, RCUTORTURE_TASKS_OPS }; if (!torture_init_begin(torture_type, verbose, &torture_runnable)) @@ -1701,7 +1742,7 @@ rcu_torture_init(void) if (nreaders >= 0) { nrealreaders = nreaders; } else { - nrealreaders = num_online_cpus() - 1; + nrealreaders = num_online_cpus() - 2 - nreaders; if (nrealreaders <= 0) nrealreaders = 1; } diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index cad76e76b4e7..fb33d35ee0b7 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -151,7 +151,7 @@ static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx) unsigned long t; for_each_possible_cpu(cpu) { - t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]); + t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]); sum += t; } return sum; @@ -168,7 +168,7 @@ static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx) unsigned long t; for_each_possible_cpu(cpu) { - t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]); + t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]); sum += t; } return sum; @@ -265,8 +265,8 @@ static int srcu_readers_active(struct srcu_struct *sp) unsigned long sum = 0; for_each_possible_cpu(cpu) { - sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]); - sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]); + sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]); + sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]); } return sum; } @@ -296,7 +296,7 @@ int __srcu_read_lock(struct srcu_struct *sp) { int idx; - idx = ACCESS_ONCE(sp->completed) & 0x1; + 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. */ diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 069742d61c68..591af0cb7b9f 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -49,39 +49,6 @@ static void __call_rcu(struct rcu_head *head, #include "tiny_plugin.h" -/* - * Enter idle, which is an extended quiescent state if we have fully - * entered that mode. - */ -void rcu_idle_enter(void) -{ -} -EXPORT_SYMBOL_GPL(rcu_idle_enter); - -/* - * Exit an interrupt handler towards idle. - */ -void rcu_irq_exit(void) -{ -} -EXPORT_SYMBOL_GPL(rcu_irq_exit); - -/* - * Exit idle, so that we are no longer in an extended quiescent state. - */ -void rcu_idle_exit(void) -{ -} -EXPORT_SYMBOL_GPL(rcu_idle_exit); - -/* - * Enter an interrupt handler, moving away from idle. - */ -void rcu_irq_enter(void) -{ -} -EXPORT_SYMBOL_GPL(rcu_irq_enter); - #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) /* @@ -170,6 +137,11 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); + if (rcp->donetail == &rcp->rcucblist) { + /* No callbacks ready, so just leave. */ + local_irq_restore(flags); + return; + } RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1)); list = rcp->rcucblist; rcp->rcucblist = *rcp->donetail; diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index f94e209a10d6..e492a5253e0f 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -144,16 +144,17 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp) return; rcp->ticks_this_gp++; j = jiffies; - js = ACCESS_ONCE(rcp->jiffies_stall); + js = READ_ONCE(rcp->jiffies_stall); if (rcp->rcucblist && ULONG_CMP_GE(j, js)) { pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n", rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE, jiffies - rcp->gp_start, rcp->qlen); dump_stack(); - ACCESS_ONCE(rcp->jiffies_stall) = jiffies + - 3 * rcu_jiffies_till_stall_check() + 3; + WRITE_ONCE(rcp->jiffies_stall, + jiffies + 3 * rcu_jiffies_till_stall_check() + 3); } else if (ULONG_CMP_GE(j, js)) { - ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check(); + WRITE_ONCE(rcp->jiffies_stall, + jiffies + rcu_jiffies_till_stall_check()); } } @@ -161,7 +162,8 @@ static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp) { rcp->ticks_this_gp = 0; rcp->gp_start = jiffies; - ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check(); + WRITE_ONCE(rcp->jiffies_stall, + jiffies + rcu_jiffies_till_stall_check()); } static void check_cpu_stalls(void) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8cf7304b2867..add042926a66 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -91,7 +91,7 @@ static const char *tp_##sname##_varname __used __tracepoint_string = sname##_var #define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ DEFINE_RCU_TPS(sname) \ -DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \ struct rcu_state sname##_state = { \ .level = { &sname##_state.node[0] }, \ .rda = &sname##_data, \ @@ -110,11 +110,18 @@ struct rcu_state sname##_state = { \ RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh); -static struct rcu_state *rcu_state_p; +static struct rcu_state *const rcu_state_p; +static struct rcu_data __percpu *const rcu_data_p; LIST_HEAD(rcu_struct_flavors); -/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ -static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF; +/* Dump rcu_node combining tree at boot to verify correct setup. */ +static bool dump_tree; +module_param(dump_tree, bool, 0444); +/* Control rcu_node-tree auto-balancing at boot time. */ +static bool rcu_fanout_exact; +module_param(rcu_fanout_exact, bool, 0444); +/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */ +static int rcu_fanout_leaf = RCU_FANOUT_LEAF; module_param(rcu_fanout_leaf, int, 0444); int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */ @@ -159,17 +166,46 @@ static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); /* rcuc/rcub kthread realtime priority */ +#ifdef CONFIG_RCU_KTHREAD_PRIO static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; +#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */ +static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0; +#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */ module_param(kthread_prio, int, 0644); /* Delay in jiffies for grace-period initialization delays, debug only. */ + +#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT +static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY; +module_param(gp_preinit_delay, int, 0644); +#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */ +static const int gp_preinit_delay; +#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */ + #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY; module_param(gp_init_delay, int, 0644); #else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ static const int gp_init_delay; #endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ -#define PER_RCU_NODE_PERIOD 10 /* Number of grace periods between delays. */ + +#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP +static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY; +module_param(gp_cleanup_delay, int, 0644); +#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */ +static const int gp_cleanup_delay; +#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */ + +/* + * Number of grace periods between delays, normalized by the duration of + * the delay. The longer the the delay, the more the grace periods between + * each delay. The reason for this normalization is that it means that, + * for non-zero delays, the overall slowdown of grace periods is constant + * regardless of the duration of the delay. This arrangement balances + * the need for long delays to increase some race probabilities with the + * need for fast grace periods to increase other race probabilities. + */ +#define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays. */ /* * Track the rcutorture test sequence number and the update version @@ -191,17 +227,17 @@ unsigned long rcutorture_vernum; */ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) { - return ACCESS_ONCE(rnp->qsmaskinitnext); + return READ_ONCE(rnp->qsmaskinitnext); } /* - * Return true if an RCU grace period is in progress. The ACCESS_ONCE()s + * Return true if an RCU grace period is in progress. The READ_ONCE()s * permit this function to be invoked without holding the root rcu_node * structure's ->lock, but of course results can be subject to change. */ static int rcu_gp_in_progress(struct rcu_state *rsp) { - return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum); + return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum); } /* @@ -278,8 +314,8 @@ static void rcu_momentary_dyntick_idle(void) if (!(resched_mask & rsp->flavor_mask)) continue; smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */ - if (ACCESS_ONCE(rdp->mynode->completed) != - ACCESS_ONCE(rdp->cond_resched_completed)) + if (READ_ONCE(rdp->mynode->completed) != + READ_ONCE(rdp->cond_resched_completed)) continue; /* @@ -491,9 +527,9 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, break; } if (rsp != NULL) { - *flags = ACCESS_ONCE(rsp->gp_flags); - *gpnum = ACCESS_ONCE(rsp->gpnum); - *completed = ACCESS_ONCE(rsp->completed); + *flags = READ_ONCE(rsp->gp_flags); + *gpnum = READ_ONCE(rsp->gpnum); + *completed = READ_ONCE(rsp->completed); return; } *flags = 0; @@ -539,10 +575,10 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) static int rcu_future_needs_gp(struct rcu_state *rsp) { struct rcu_node *rnp = rcu_get_root(rsp); - int idx = (ACCESS_ONCE(rnp->completed) + 1) & 0x1; + int idx = (READ_ONCE(rnp->completed) + 1) & 0x1; int *fp = &rnp->need_future_gp[idx]; - return ACCESS_ONCE(*fp); + return READ_ONCE(*fp); } /* @@ -565,7 +601,7 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) return 1; /* Yes, this CPU has newly registered callbacks. */ for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) if (rdp->nxttail[i - 1] != rdp->nxttail[i] && - ULONG_CMP_LT(ACCESS_ONCE(rsp->completed), + ULONG_CMP_LT(READ_ONCE(rsp->completed), rdp->nxtcompleted[i])) return 1; /* Yes, CBs for future grace period. */ return 0; /* No grace period needed. */ @@ -585,7 +621,8 @@ static void rcu_eqs_enter_common(long long oldval, bool user) struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting); - if (!user && !is_idle_task(current)) { + if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && + !user && !is_idle_task(current)) { struct task_struct *idle __maybe_unused = idle_task(smp_processor_id()); @@ -604,7 +641,8 @@ static void rcu_eqs_enter_common(long long oldval, bool user) smp_mb__before_atomic(); /* See above. */ atomic_inc(&rdtp->dynticks); smp_mb__after_atomic(); /* Force ordering with next sojourn. */ - WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && + atomic_read(&rdtp->dynticks) & 0x1); rcu_dynticks_task_enter(); /* @@ -630,7 +668,8 @@ static void rcu_eqs_enter(bool user) rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && + (oldval & DYNTICK_TASK_NEST_MASK) == 0); if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) { rdtp->dynticks_nesting = 0; rcu_eqs_enter_common(oldval, user); @@ -703,7 +742,8 @@ void rcu_irq_exit(void) rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting--; - WARN_ON_ONCE(rdtp->dynticks_nesting < 0); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && + rdtp->dynticks_nesting < 0); if (rdtp->dynticks_nesting) trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting); else @@ -728,10 +768,12 @@ static void rcu_eqs_exit_common(long long oldval, int user) atomic_inc(&rdtp->dynticks); /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ smp_mb__after_atomic(); /* See above. */ - WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && + !(atomic_read(&rdtp->dynticks) & 0x1)); rcu_cleanup_after_idle(); trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting); - if (!user && !is_idle_task(current)) { + if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && + !user && !is_idle_task(current)) { struct task_struct *idle __maybe_unused = idle_task(smp_processor_id()); @@ -755,7 +797,7 @@ static void rcu_eqs_exit(bool user) rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE(oldval < 0); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); if (oldval & DYNTICK_TASK_NEST_MASK) { rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; } else { @@ -828,7 +870,8 @@ void rcu_irq_enter(void) rdtp = this_cpu_ptr(&rcu_dynticks); oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; - WARN_ON_ONCE(rdtp->dynticks_nesting == 0); + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && + rdtp->dynticks_nesting == 0); if (oldval) trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting); else @@ -1011,9 +1054,9 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp, trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti")); return 1; } else { - if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4, + if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rdp->mynode->gpnum)) - ACCESS_ONCE(rdp->gpwrap) = true; + WRITE_ONCE(rdp->gpwrap, true); return 0; } } @@ -1093,12 +1136,12 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp, if (ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs) || ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { - if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) { - ACCESS_ONCE(rdp->cond_resched_completed) = - ACCESS_ONCE(rdp->mynode->completed); + if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) { + WRITE_ONCE(rdp->cond_resched_completed, + READ_ONCE(rdp->mynode->completed)); smp_mb(); /* ->cond_resched_completed before *rcrmp. */ - ACCESS_ONCE(*rcrmp) = - ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask; + WRITE_ONCE(*rcrmp, + READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask); resched_cpu(rdp->cpu); /* Force CPU into scheduler. */ rdp->rsp->jiffies_resched += 5; /* Enable beating. */ } else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) { @@ -1119,9 +1162,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp) rsp->gp_start = j; smp_wmb(); /* Record start time before stall time. */ j1 = rcu_jiffies_till_stall_check(); - ACCESS_ONCE(rsp->jiffies_stall) = j + j1; + WRITE_ONCE(rsp->jiffies_stall, j + j1); rsp->jiffies_resched = j + j1 / 2; - rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs); + rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs); } /* @@ -1133,10 +1176,11 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) unsigned long j; j = jiffies; - gpa = ACCESS_ONCE(rsp->gp_activity); + gpa = READ_ONCE(rsp->gp_activity); if (j - gpa > 2 * HZ) - pr_err("%s kthread starved for %ld jiffies!\n", - rsp->name, j - gpa); + pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n", + rsp->name, j - gpa, + rsp->gpnum, rsp->completed, rsp->gp_flags); } /* @@ -1173,12 +1217,13 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) /* Only let one CPU complain about others per time interval. */ raw_spin_lock_irqsave(&rnp->lock, flags); - delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall); + delta = jiffies - READ_ONCE(rsp->jiffies_stall); if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) { raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } - ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; + WRITE_ONCE(rsp->jiffies_stall, + jiffies + 3 * rcu_jiffies_till_stall_check() + 3); raw_spin_unlock_irqrestore(&rnp->lock, flags); /* @@ -1212,12 +1257,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum) if (ndetected) { rcu_dump_cpu_stacks(rsp); } else { - if (ACCESS_ONCE(rsp->gpnum) != gpnum || - ACCESS_ONCE(rsp->completed) == gpnum) { + if (READ_ONCE(rsp->gpnum) != gpnum || + READ_ONCE(rsp->completed) == gpnum) { pr_err("INFO: Stall ended before state dump start\n"); } else { j = jiffies; - gpa = ACCESS_ONCE(rsp->gp_activity); + gpa = READ_ONCE(rsp->gp_activity); pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n", rsp->name, j - gpa, j, gpa, jiffies_till_next_fqs, @@ -1262,9 +1307,9 @@ static void print_cpu_stall(struct rcu_state *rsp) rcu_dump_cpu_stacks(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); - if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall))) - ACCESS_ONCE(rsp->jiffies_stall) = jiffies + - 3 * rcu_jiffies_till_stall_check() + 3; + if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) + WRITE_ONCE(rsp->jiffies_stall, + jiffies + 3 * rcu_jiffies_till_stall_check() + 3); raw_spin_unlock_irqrestore(&rnp->lock, flags); /* @@ -1307,20 +1352,20 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) * Given this check, comparisons of jiffies, rsp->jiffies_stall, * and rsp->gp_start suffice to forestall false positives. */ - gpnum = ACCESS_ONCE(rsp->gpnum); + gpnum = READ_ONCE(rsp->gpnum); smp_rmb(); /* Pick up ->gpnum first... */ - js = ACCESS_ONCE(rsp->jiffies_stall); + js = READ_ONCE(rsp->jiffies_stall); smp_rmb(); /* ...then ->jiffies_stall before the rest... */ - gps = ACCESS_ONCE(rsp->gp_start); + gps = READ_ONCE(rsp->gp_start); smp_rmb(); /* ...and finally ->gp_start before ->completed. */ - completed = ACCESS_ONCE(rsp->completed); + completed = READ_ONCE(rsp->completed); if (ULONG_CMP_GE(completed, gpnum) || ULONG_CMP_LT(j, js) || ULONG_CMP_GE(gps, js)) return; /* No stall or GP completed since entering function. */ rnp = rdp->mynode; if (rcu_gp_in_progress(rsp) && - (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask)) { + (READ_ONCE(rnp->qsmask) & rdp->grpmask)) { /* We haven't checked in, so go dump stack. */ print_cpu_stall(rsp); @@ -1347,7 +1392,7 @@ void rcu_cpu_stall_reset(void) struct rcu_state *rsp; for_each_rcu_flavor(rsp) - ACCESS_ONCE(rsp->jiffies_stall) = jiffies + ULONG_MAX / 2; + WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2); } /* @@ -1457,7 +1502,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp, * doing some extra useless work. */ if (rnp->gpnum != rnp->completed || - ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) { + READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) { rnp->need_future_gp[c & 0x1]++; trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf")); goto out; @@ -1542,7 +1587,7 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) static void rcu_gp_kthread_wake(struct rcu_state *rsp) { if (current == rsp->gp_kthread || - !ACCESS_ONCE(rsp->gp_flags) || + !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; wake_up(&rsp->gp_wq); @@ -1677,7 +1722,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, /* Handle the ends of any preceding grace periods first. */ if (rdp->completed == rnp->completed && - !unlikely(ACCESS_ONCE(rdp->gpwrap))) { + !unlikely(READ_ONCE(rdp->gpwrap))) { /* No grace period end, so just accelerate recent callbacks. */ ret = rcu_accelerate_cbs(rsp, rnp, rdp); @@ -1692,7 +1737,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend")); } - if (rdp->gpnum != rnp->gpnum || unlikely(ACCESS_ONCE(rdp->gpwrap))) { + if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) { /* * If the current grace period is waiting for this CPU, * set up to detect a quiescent state, otherwise don't @@ -1704,7 +1749,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); - ACCESS_ONCE(rdp->gpwrap) = false; + WRITE_ONCE(rdp->gpwrap, false); } return ret; } @@ -1717,9 +1762,9 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_save(flags); rnp = rdp->mynode; - if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) && - rdp->completed == ACCESS_ONCE(rnp->completed) && - !unlikely(ACCESS_ONCE(rdp->gpwrap))) || /* w/out lock. */ + if ((rdp->gpnum == READ_ONCE(rnp->gpnum) && + rdp->completed == READ_ONCE(rnp->completed) && + !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */ !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */ local_irq_restore(flags); return; @@ -1731,6 +1776,13 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) rcu_gp_kthread_wake(rsp); } +static void rcu_gp_slow(struct rcu_state *rsp, int delay) +{ + if (delay > 0 && + !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) + schedule_timeout_uninterruptible(delay); +} + /* * Initialize a new grace period. Return 0 if no grace period required. */ @@ -1740,15 +1792,15 @@ static int rcu_gp_init(struct rcu_state *rsp) struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); - ACCESS_ONCE(rsp->gp_activity) = jiffies; + WRITE_ONCE(rsp->gp_activity, jiffies); raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); - if (!ACCESS_ONCE(rsp->gp_flags)) { + if (!READ_ONCE(rsp->gp_flags)) { /* Spurious wakeup, tell caller to go back to sleep. */ raw_spin_unlock_irq(&rnp->lock); return 0; } - ACCESS_ONCE(rsp->gp_flags) = 0; /* Clear all flags: New grace period. */ + WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */ if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) { /* @@ -1773,6 +1825,7 @@ static int rcu_gp_init(struct rcu_state *rsp) * will handle subsequent offline CPUs. */ rcu_for_each_leaf_node(rsp, rnp) { + rcu_gp_slow(rsp, gp_preinit_delay); raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); if (rnp->qsmaskinit == rnp->qsmaskinitnext && @@ -1829,14 +1882,15 @@ static int rcu_gp_init(struct rcu_state *rsp) * process finishes, because this kthread handles both. */ rcu_for_each_node_breadth_first(rsp, rnp) { + rcu_gp_slow(rsp, gp_init_delay); raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); rdp = this_cpu_ptr(rsp->rda); rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; - ACCESS_ONCE(rnp->gpnum) = rsp->gpnum; + WRITE_ONCE(rnp->gpnum, rsp->gpnum); if (WARN_ON_ONCE(rnp->completed != rsp->completed)) - ACCESS_ONCE(rnp->completed) = rsp->completed; + WRITE_ONCE(rnp->completed, rsp->completed); if (rnp == rdp->mynode) (void)__note_gp_changes(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); @@ -1845,10 +1899,7 @@ static int rcu_gp_init(struct rcu_state *rsp) rnp->grphi, rnp->qsmask); raw_spin_unlock_irq(&rnp->lock); cond_resched_rcu_qs(); - ACCESS_ONCE(rsp->gp_activity) = jiffies; - if (gp_init_delay > 0 && - !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD))) - schedule_timeout_uninterruptible(gp_init_delay); + WRITE_ONCE(rsp->gp_activity, jiffies); } return 1; @@ -1864,7 +1915,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) unsigned long maxj; struct rcu_node *rnp = rcu_get_root(rsp); - ACCESS_ONCE(rsp->gp_activity) = jiffies; + WRITE_ONCE(rsp->gp_activity, jiffies); rsp->n_force_qs++; if (fqs_state == RCU_SAVE_DYNTICK) { /* Collect dyntick-idle snapshots. */ @@ -1882,11 +1933,11 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj); } /* Clear flag to prevent immediate re-entry. */ - if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); - ACCESS_ONCE(rsp->gp_flags) = - ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS; + WRITE_ONCE(rsp->gp_flags, + READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS); raw_spin_unlock_irq(&rnp->lock); } return fqs_state; @@ -1903,7 +1954,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); - ACCESS_ONCE(rsp->gp_activity) = jiffies; + WRITE_ONCE(rsp->gp_activity, jiffies); raw_spin_lock_irq(&rnp->lock); smp_mb__after_unlock_lock(); gp_duration = jiffies - rsp->gp_start; @@ -1934,7 +1985,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) smp_mb__after_unlock_lock(); WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)); WARN_ON_ONCE(rnp->qsmask); - ACCESS_ONCE(rnp->completed) = rsp->gpnum; + WRITE_ONCE(rnp->completed, rsp->gpnum); rdp = this_cpu_ptr(rsp->rda); if (rnp == rdp->mynode) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; @@ -1942,7 +1993,8 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) nocb += rcu_future_gp_cleanup(rsp, rnp); raw_spin_unlock_irq(&rnp->lock); cond_resched_rcu_qs(); - ACCESS_ONCE(rsp->gp_activity) = jiffies; + WRITE_ONCE(rsp->gp_activity, jiffies); + rcu_gp_slow(rsp, gp_cleanup_delay); } rnp = rcu_get_root(rsp); raw_spin_lock_irq(&rnp->lock); @@ -1950,16 +2002,16 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) rcu_nocb_gp_set(rnp, nocb); /* Declare grace period done. */ - ACCESS_ONCE(rsp->completed) = rsp->gpnum; + WRITE_ONCE(rsp->completed, rsp->gpnum); trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end")); rsp->fqs_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; if (needgp || cpu_needs_another_gp(rsp, rdp)) { - ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT; + WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); trace_rcu_grace_period(rsp->name, - ACCESS_ONCE(rsp->gpnum), + READ_ONCE(rsp->gpnum), TPS("newreq")); } raw_spin_unlock_irq(&rnp->lock); @@ -1983,20 +2035,20 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Handle grace-period start. */ for (;;) { trace_rcu_grace_period(rsp->name, - ACCESS_ONCE(rsp->gpnum), + READ_ONCE(rsp->gpnum), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; wait_event_interruptible(rsp->gp_wq, - ACCESS_ONCE(rsp->gp_flags) & + READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); /* Locking provides needed memory barrier. */ if (rcu_gp_init(rsp)) break; cond_resched_rcu_qs(); - ACCESS_ONCE(rsp->gp_activity) = jiffies; + WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - ACCESS_ONCE(rsp->gpnum), + READ_ONCE(rsp->gpnum), TPS("reqwaitsig")); } @@ -2012,39 +2064,39 @@ static int __noreturn rcu_gp_kthread(void *arg) if (!ret) rsp->jiffies_force_qs = jiffies + j; trace_rcu_grace_period(rsp->name, - ACCESS_ONCE(rsp->gpnum), + READ_ONCE(rsp->gpnum), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; ret = wait_event_interruptible_timeout(rsp->gp_wq, - ((gf = ACCESS_ONCE(rsp->gp_flags)) & + ((gf = READ_ONCE(rsp->gp_flags)) & RCU_GP_FLAG_FQS) || - (!ACCESS_ONCE(rnp->qsmask) && + (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)), j); /* Locking provides needed memory barriers. */ /* If grace period done, leave loop. */ - if (!ACCESS_ONCE(rnp->qsmask) && + if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp)) break; /* If time for quiescent-state forcing, do it. */ if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) || (gf & RCU_GP_FLAG_FQS)) { trace_rcu_grace_period(rsp->name, - ACCESS_ONCE(rsp->gpnum), + READ_ONCE(rsp->gpnum), TPS("fqsstart")); fqs_state = rcu_gp_fqs(rsp, fqs_state); trace_rcu_grace_period(rsp->name, - ACCESS_ONCE(rsp->gpnum), + READ_ONCE(rsp->gpnum), TPS("fqsend")); cond_resched_rcu_qs(); - ACCESS_ONCE(rsp->gp_activity) = jiffies; + WRITE_ONCE(rsp->gp_activity, jiffies); } else { /* Deal with stray signal. */ cond_resched_rcu_qs(); - ACCESS_ONCE(rsp->gp_activity) = jiffies; + WRITE_ONCE(rsp->gp_activity, jiffies); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, - ACCESS_ONCE(rsp->gpnum), + READ_ONCE(rsp->gpnum), TPS("fqswaitsig")); } j = jiffies_till_next_fqs; @@ -2086,8 +2138,8 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, */ return false; } - ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT; - trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), + WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); + trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq")); /* @@ -2137,6 +2189,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) __releases(rcu_get_root(rsp)->lock) { WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); rcu_gp_kthread_wake(rsp); } @@ -2334,8 +2387,6 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) rcu_report_qs_rdp(rdp->cpu, rsp, rdp); } -#ifdef CONFIG_HOTPLUG_CPU - /* * Send the specified CPU's RCU callbacks to the orphanage. The * specified CPU must be offline, and the caller must hold the @@ -2346,7 +2397,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { /* No-CBs CPUs do not have orphanable callbacks. */ - if (rcu_is_nocb_cpu(rdp->cpu)) + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu)) return; /* @@ -2359,7 +2410,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, rsp->qlen += rdp->qlen; rdp->n_cbs_orphaned += rdp->qlen; rdp->qlen_lazy = 0; - ACCESS_ONCE(rdp->qlen) = 0; + WRITE_ONCE(rdp->qlen, 0); } /* @@ -2405,7 +2456,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags) struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); /* No-CBs CPUs are handled specially. */ - if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags)) + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || + rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags)) return; /* Do the accounting first. */ @@ -2452,6 +2504,9 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda)); RCU_TRACE(struct rcu_node *rnp = rdp->mynode); + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return; + RCU_TRACE(mask = rdp->grpmask); trace_rcu_grace_period(rsp->name, rnp->gpnum + 1 - !!(rnp->qsmask & mask), @@ -2480,7 +2535,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) long mask; struct rcu_node *rnp = rnp_leaf; - if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || + rnp->qsmaskinit || rcu_preempt_has_tasks(rnp)) return; for (;;) { mask = rnp->grpmask; @@ -2511,6 +2567,9 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return; + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; raw_spin_lock_irqsave(&rnp->lock, flags); @@ -2532,6 +2591,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return; + /* Adjust any no-longer-needed kthreads. */ rcu_boost_kthread_setaffinity(rnp, -1); @@ -2546,26 +2608,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) cpu, rdp->qlen, rdp->nxtlist); } -#else /* #ifdef CONFIG_HOTPLUG_CPU */ - -static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) -{ -} - -static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) -{ -} - -static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) -{ -} - -static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) -{ -} - -#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ - /* * Invoke any RCU callbacks that have made it to the end of their grace * period. Thottle as specified by rdp->blimit. @@ -2580,7 +2622,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* If no callbacks are ready, just return. */ if (!cpu_has_callbacks_ready_to_invoke(rdp)) { trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0); - trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist), + trace_rcu_batch_end(rsp->name, 0, !!READ_ONCE(rdp->nxtlist), need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); return; @@ -2636,7 +2678,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) } smp_mb(); /* List handling before counting for rcu_barrier(). */ rdp->qlen_lazy -= count_lazy; - ACCESS_ONCE(rdp->qlen) = rdp->qlen - count; + WRITE_ONCE(rdp->qlen, rdp->qlen - count); rdp->n_cbs_invoked += count; /* Reinstate batch limit if we have worked down the excess. */ @@ -2730,10 +2772,6 @@ static void force_qs_rnp(struct rcu_state *rsp, mask = 0; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - if (!rcu_gp_in_progress(rsp)) { - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } if (rnp->qsmask == 0) { if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p || @@ -2763,8 +2801,6 @@ static void force_qs_rnp(struct rcu_state *rsp, bit = 1; for (; cpu <= rnp->grphi; cpu++, bit <<= 1) { if ((rnp->qsmask & bit) != 0) { - if ((rnp->qsmaskinit & bit) == 0) - *isidle = false; /* Pending hotplug. */ if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj)) mask |= bit; } @@ -2793,7 +2829,7 @@ static void force_quiescent_state(struct rcu_state *rsp) /* Funnel through hierarchy to reduce memory contention. */ rnp = __this_cpu_read(rsp->rda->mynode); for (; rnp != NULL; rnp = rnp->parent) { - ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || + ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || !raw_spin_trylock(&rnp->fqslock); if (rnp_old != NULL) raw_spin_unlock(&rnp_old->fqslock); @@ -2809,13 +2845,12 @@ static void force_quiescent_state(struct rcu_state *rsp) raw_spin_lock_irqsave(&rnp_old->lock, flags); smp_mb__after_unlock_lock(); raw_spin_unlock(&rnp_old->fqslock); - if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { rsp->n_force_qs_lh++; raw_spin_unlock_irqrestore(&rnp_old->lock, flags); return; /* Someone beat us to it. */ } - ACCESS_ONCE(rsp->gp_flags) = - ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS; + WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore(&rnp_old->lock, flags); rcu_gp_kthread_wake(rsp); } @@ -2881,7 +2916,7 @@ static void rcu_process_callbacks(struct softirq_action *unused) */ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) { - if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active))) + if (unlikely(!READ_ONCE(rcu_scheduler_fully_active))) return; if (likely(!rsp->boost)) { rcu_do_batch(rsp, rdp); @@ -2972,7 +3007,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */ if (debug_rcu_head_queue(head)) { /* Probable double call_rcu(), so leak the callback. */ - ACCESS_ONCE(head->func) = rcu_leak_callback; + WRITE_ONCE(head->func, rcu_leak_callback); WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n"); return; } @@ -3011,7 +3046,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), if (!likely(rdp->nxtlist)) init_default_callback_list(rdp); } - ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1; + WRITE_ONCE(rdp->qlen, rdp->qlen + 1); if (lazy) rdp->qlen_lazy++; else @@ -3287,7 +3322,7 @@ void synchronize_sched_expedited(void) if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start), (ulong)atomic_long_read(&rsp->expedited_done) + ULONG_MAX / 8)) { - synchronize_sched(); + wait_rcu_gp(call_rcu_sched); atomic_long_inc(&rsp->expedited_wrap); return; } @@ -3450,14 +3485,14 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) } /* Has another RCU grace period completed? */ - if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */ + if (READ_ONCE(rnp->completed) != rdp->completed) { /* outside lock */ rdp->n_rp_gp_completed++; return 1; } /* Has a new RCU grace period started? */ - if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum || - unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* outside lock */ + if (READ_ONCE(rnp->gpnum) != rdp->gpnum || + unlikely(READ_ONCE(rdp->gpwrap))) { /* outside lock */ rdp->n_rp_gp_started++; return 1; } @@ -3493,7 +3528,7 @@ static int rcu_pending(void) * non-NULL, store an indication of whether all callbacks are lazy. * (If there are no callbacks, all of them are deemed to be lazy.) */ -static int __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy) +static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy) { bool al = true; bool hc = false; @@ -3564,7 +3599,7 @@ static void _rcu_barrier(struct rcu_state *rsp) { int cpu; struct rcu_data *rdp; - unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done); + unsigned long snap = READ_ONCE(rsp->n_barrier_done); unsigned long snap_done; _rcu_barrier_trace(rsp, "Begin", -1, snap); @@ -3606,10 +3641,10 @@ static void _rcu_barrier(struct rcu_state *rsp) /* * Increment ->n_barrier_done to avoid duplicate work. Use - * ACCESS_ONCE() to prevent the compiler from speculating + * WRITE_ONCE() to prevent the compiler from speculating * the increment to precede the early-exit check. */ - ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1; + WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1); WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1); _rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done); smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */ @@ -3645,7 +3680,7 @@ static void _rcu_barrier(struct rcu_state *rsp) __call_rcu(&rdp->barrier_head, rcu_barrier_callback, rsp, cpu, 0); } - } else if (ACCESS_ONCE(rdp->qlen)) { + } else if (READ_ONCE(rdp->qlen)) { _rcu_barrier_trace(rsp, "OnlineQ", cpu, rsp->n_barrier_done); smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); @@ -3665,7 +3700,7 @@ static void _rcu_barrier(struct rcu_state *rsp) /* Increment ->n_barrier_done to prevent duplicate work. */ smp_mb(); /* Keep increment after above mechanism. */ - ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1; + WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1); WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0); _rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done); smp_mb(); /* Keep increment before caller's subsequent code. */ @@ -3780,7 +3815,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */ rdp->completed = rnp->completed; rdp->passed_quiesce = false; - rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr); + rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu); rdp->qs_pending = false; trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl")); raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -3924,16 +3959,16 @@ void rcu_scheduler_starting(void) /* * Compute the per-level fanout, either using the exact fanout specified - * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT. + * or balancing the tree, depending on the rcu_fanout_exact boot parameter. */ static void __init rcu_init_levelspread(struct rcu_state *rsp) { int i; - if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) { + if (rcu_fanout_exact) { rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf; for (i = rcu_num_lvls - 2; i >= 0; i--) - rsp->levelspread[i] = CONFIG_RCU_FANOUT; + rsp->levelspread[i] = RCU_FANOUT; } else { int ccur; int cprv; @@ -3971,9 +4006,9 @@ static void __init rcu_init_one(struct rcu_state *rsp, BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf)); /* Fix buf[] init! */ - /* Silence gcc 4.8 warning about array index out of range. */ - if (rcu_num_lvls > RCU_NUM_LVLS) - panic("rcu_init_one: rcu_num_lvls overflow"); + /* Silence gcc 4.8 false positive about array index out of range. */ + if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS) + panic("rcu_init_one: rcu_num_lvls out of range"); /* Initialize the level-tracking arrays. */ @@ -4059,7 +4094,7 @@ static void __init rcu_init_geometry(void) jiffies_till_next_fqs = d; /* If the compile-time values are accurate, just leave. */ - if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF && + if (rcu_fanout_leaf == RCU_FANOUT_LEAF && nr_cpu_ids == NR_CPUS) return; pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n", @@ -4073,7 +4108,7 @@ static void __init rcu_init_geometry(void) rcu_capacity[0] = 1; rcu_capacity[1] = rcu_fanout_leaf; for (i = 2; i <= MAX_RCU_LVLS; i++) - rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT; + rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT; /* * The boot-time rcu_fanout_leaf parameter is only permitted @@ -4083,7 +4118,7 @@ static void __init rcu_init_geometry(void) * the configured number of CPUs. Complain and fall back to the * compile-time values if these limits are exceeded. */ - if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF || + if (rcu_fanout_leaf < RCU_FANOUT_LEAF || rcu_fanout_leaf > sizeof(unsigned long) * 8 || n > rcu_capacity[MAX_RCU_LVLS]) { WARN_ON(1); @@ -4109,6 +4144,28 @@ static void __init rcu_init_geometry(void) rcu_num_nodes -= n; } +/* + * Dump out the structure of the rcu_node combining tree associated + * with the rcu_state structure referenced by rsp. + */ +static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp) +{ + int level = 0; + struct rcu_node *rnp; + + pr_info("rcu_node tree layout dump\n"); + pr_info(" "); + rcu_for_each_node_breadth_first(rsp, rnp) { + if (rnp->level != level) { + pr_cont("\n"); + pr_info(" "); + level = rnp->level; + } + pr_cont("%d:%d ^%d ", rnp->grplo, rnp->grphi, rnp->grpnum); + } + pr_cont("\n"); +} + void __init rcu_init(void) { int cpu; @@ -4119,6 +4176,8 @@ void __init rcu_init(void) rcu_init_geometry(); rcu_init_one(&rcu_bh_state, &rcu_bh_data); rcu_init_one(&rcu_sched_state, &rcu_sched_data); + if (dump_tree) + rcu_dump_rcu_node_tree(&rcu_sched_state); __rcu_init_preempt(); open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index a69d3dab2ec4..4adb7ca0bf47 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -35,11 +35,33 @@ * In practice, this did work well going from three levels to four. * Of course, your mileage may vary. */ + #define MAX_RCU_LVLS 4 -#define RCU_FANOUT_1 (CONFIG_RCU_FANOUT_LEAF) -#define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT) -#define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT) -#define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT) + +#ifdef CONFIG_RCU_FANOUT +#define RCU_FANOUT CONFIG_RCU_FANOUT +#else /* #ifdef CONFIG_RCU_FANOUT */ +# ifdef CONFIG_64BIT +# define RCU_FANOUT 64 +# else +# define RCU_FANOUT 32 +# endif +#endif /* #else #ifdef CONFIG_RCU_FANOUT */ + +#ifdef CONFIG_RCU_FANOUT_LEAF +#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF +#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */ +# ifdef CONFIG_64BIT +# define RCU_FANOUT_LEAF 64 +# else +# define RCU_FANOUT_LEAF 32 +# endif +#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */ + +#define RCU_FANOUT_1 (RCU_FANOUT_LEAF) +#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT) +#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT) +#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT) #if NR_CPUS <= RCU_FANOUT_1 # define RCU_NUM_LVLS 1 @@ -170,7 +192,6 @@ struct rcu_node { /* if there is no such task. If there */ /* is no current expedited grace period, */ /* then there can cannot be any such task. */ -#ifdef CONFIG_RCU_BOOST struct list_head *boost_tasks; /* Pointer to first task that needs to be */ /* priority boosted, or NULL if no priority */ @@ -208,7 +229,6 @@ struct rcu_node { unsigned long n_balk_nos; /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */ -#endif /* #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_NOCB_CPU wait_queue_head_t nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ @@ -519,14 +539,11 @@ extern struct list_head rcu_struct_flavors; * RCU implementation internal declarations: */ extern struct rcu_state rcu_sched_state; -DECLARE_PER_CPU(struct rcu_data, rcu_sched_data); extern struct rcu_state rcu_bh_state; -DECLARE_PER_CPU(struct rcu_data, rcu_bh_data); #ifdef CONFIG_PREEMPT_RCU extern struct rcu_state rcu_preempt_state; -DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_BOOST diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index d72fa24f2312..013485fb2b06 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -43,7 +43,17 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); -#endif /* #ifdef CONFIG_RCU_BOOST */ +#else /* #ifdef CONFIG_RCU_BOOST */ + +/* + * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST, + * all uses are in dead code. Provide a definition to keep the compiler + * happy, but add WARN_ON_ONCE() to complain if used in the wrong place. + * This probably needs to be excluded from -rt builds. + */ +#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; }) + +#endif /* #else #ifdef CONFIG_RCU_BOOST */ #ifdef CONFIG_RCU_NOCB_CPU static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ @@ -60,11 +70,11 @@ static void __init rcu_bootup_announce_oddness(void) { if (IS_ENABLED(CONFIG_RCU_TRACE)) pr_info("\tRCU debugfs-based tracing is enabled.\n"); - if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) || - (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32)) + if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) || + (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32)) pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n", - CONFIG_RCU_FANOUT); - if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) + RCU_FANOUT); + if (rcu_fanout_exact) pr_info("\tHierarchical RCU autobalancing is disabled.\n"); if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ)) pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n"); @@ -76,10 +86,10 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tAdditional per-CPU info printed with stalls.\n"); if (NUM_RCU_LVL_4 != 0) pr_info("\tFour-level hierarchy is enabled.\n"); - if (CONFIG_RCU_FANOUT_LEAF != 16) + if (RCU_FANOUT_LEAF != 16) pr_info("\tBuild-time adjustment of leaf fanout to %d.\n", - CONFIG_RCU_FANOUT_LEAF); - if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF) + RCU_FANOUT_LEAF); + if (rcu_fanout_leaf != RCU_FANOUT_LEAF) pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf); if (nr_cpu_ids != NR_CPUS) pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids); @@ -90,7 +100,8 @@ static void __init rcu_bootup_announce_oddness(void) #ifdef CONFIG_PREEMPT_RCU RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu); -static struct rcu_state *rcu_state_p = &rcu_preempt_state; +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, @@ -116,11 +127,11 @@ static void __init rcu_bootup_announce(void) */ static void rcu_preempt_qs(void) { - if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) { + if (!__this_cpu_read(rcu_data_p->passed_quiesce)) { trace_rcu_grace_period(TPS("rcu_preempt"), - __this_cpu_read(rcu_preempt_data.gpnum), + __this_cpu_read(rcu_data_p->gpnum), TPS("cpuqs")); - __this_cpu_write(rcu_preempt_data.passed_quiesce, 1); + __this_cpu_write(rcu_data_p->passed_quiesce, 1); barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ current->rcu_read_unlock_special.b.need_qs = false; } @@ -150,7 +161,7 @@ static void rcu_preempt_note_context_switch(void) !t->rcu_read_unlock_special.b.blocked) { /* Possibly blocking in an RCU read-side critical section. */ - rdp = this_cpu_ptr(rcu_preempt_state.rda); + rdp = this_cpu_ptr(rcu_state_p->rda); rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); @@ -180,10 +191,9 @@ static void rcu_preempt_note_context_switch(void) 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; -#ifdef CONFIG_RCU_BOOST - if (rnp->boost_tasks != NULL) + if (IS_ENABLED(CONFIG_RCU_BOOST) && + rnp->boost_tasks != NULL) rnp->boost_tasks = rnp->gp_tasks; -#endif /* #ifdef CONFIG_RCU_BOOST */ } else { list_add(&t->rcu_node_entry, &rnp->blkd_tasks); if (rnp->qsmask & rdp->grpmask) @@ -263,9 +273,7 @@ void rcu_read_unlock_special(struct task_struct *t) bool empty_exp_now; unsigned long flags; struct list_head *np; -#ifdef CONFIG_RCU_BOOST bool drop_boost_mutex = false; -#endif /* #ifdef CONFIG_RCU_BOOST */ struct rcu_node *rnp; union rcu_special special; @@ -307,9 +315,11 @@ void rcu_read_unlock_special(struct task_struct *t) t->rcu_read_unlock_special.b.blocked = false; /* - * Remove this task from the list it blocked on. The - * task can migrate while we acquire the lock, but at - * most one time. So at most two passes through loop. + * Remove this task from the list it blocked on. The task + * now remains queued on the rcu_node corresponding to + * the CPU it first blocked on, so the first attempt to + * acquire the task's rcu_node's ->lock will succeed. + * Keep the loop and add a WARN_ON() out of sheer paranoia. */ for (;;) { rnp = t->rcu_blocked_node; @@ -317,6 +327,7 @@ void rcu_read_unlock_special(struct task_struct *t) smp_mb__after_unlock_lock(); if (rnp == t->rcu_blocked_node) break; + WARN_ON_ONCE(1); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ } empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); @@ -331,12 +342,12 @@ void rcu_read_unlock_special(struct task_struct *t) rnp->gp_tasks = np; if (&t->rcu_node_entry == rnp->exp_tasks) rnp->exp_tasks = np; -#ifdef CONFIG_RCU_BOOST - if (&t->rcu_node_entry == rnp->boost_tasks) - rnp->boost_tasks = np; - /* Snapshot ->boost_mtx ownership with rcu_node lock held. */ - drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t; -#endif /* #ifdef CONFIG_RCU_BOOST */ + if (IS_ENABLED(CONFIG_RCU_BOOST)) { + if (&t->rcu_node_entry == rnp->boost_tasks) + rnp->boost_tasks = np; + /* Snapshot ->boost_mtx ownership w/rnp->lock held. */ + drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t; + } /* * If this was the last task on the current list, and if @@ -353,24 +364,21 @@ void rcu_read_unlock_special(struct task_struct *t) rnp->grplo, rnp->grphi, !!rnp->gp_tasks); - rcu_report_unblock_qs_rnp(&rcu_preempt_state, - rnp, flags); + rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags); } else { raw_spin_unlock_irqrestore(&rnp->lock, flags); } -#ifdef CONFIG_RCU_BOOST /* Unboost if we were boosted. */ - if (drop_boost_mutex) + if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) rt_mutex_unlock(&rnp->boost_mtx); -#endif /* #ifdef CONFIG_RCU_BOOST */ /* * If this was the last task on the expedited lists, * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && empty_exp_now) - rcu_report_exp_rnp(&rcu_preempt_state, rnp, true); + rcu_report_exp_rnp(rcu_state_p, rnp, true); } else { local_irq_restore(flags); } @@ -390,7 +398,7 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) raw_spin_unlock_irqrestore(&rnp->lock, flags); return; } - t = list_entry(rnp->gp_tasks, + t = list_entry(rnp->gp_tasks->prev, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) sched_show_task(t); @@ -447,7 +455,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) if (!rcu_preempt_blocked_readers_cgp(rnp)) return 0; rcu_print_task_stall_begin(rnp); - t = list_entry(rnp->gp_tasks, + t = list_entry(rnp->gp_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); @@ -491,8 +499,8 @@ static void rcu_preempt_check_callbacks(void) return; } if (t->rcu_read_lock_nesting > 0 && - __this_cpu_read(rcu_preempt_data.qs_pending) && - !__this_cpu_read(rcu_preempt_data.passed_quiesce)) + __this_cpu_read(rcu_data_p->qs_pending) && + !__this_cpu_read(rcu_data_p->passed_quiesce)) t->rcu_read_unlock_special.b.need_qs = true; } @@ -500,7 +508,7 @@ static void rcu_preempt_check_callbacks(void) static void rcu_preempt_do_callbacks(void) { - rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data)); + rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p)); } #endif /* #ifdef CONFIG_RCU_BOOST */ @@ -510,7 +518,7 @@ static void rcu_preempt_do_callbacks(void) */ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) { - __call_rcu(head, func, &rcu_preempt_state, -1, 0); + __call_rcu(head, func, rcu_state_p, -1, 0); } EXPORT_SYMBOL_GPL(call_rcu); @@ -570,7 +578,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp) static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) { return !rcu_preempted_readers_exp(rnp) && - ACCESS_ONCE(rnp->expmask) == 0; + READ_ONCE(rnp->expmask) == 0; } /* @@ -711,12 +719,12 @@ sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp) void synchronize_rcu_expedited(void) { struct rcu_node *rnp; - struct rcu_state *rsp = &rcu_preempt_state; + struct rcu_state *rsp = rcu_state_p; unsigned long snap; int trycount = 0; smp_mb(); /* Caller's modifications seen first by other CPUs. */ - snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1; + snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1; smp_mb(); /* Above access cannot bleed into critical section. */ /* @@ -740,7 +748,7 @@ void synchronize_rcu_expedited(void) */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { if (ULONG_CMP_LT(snap, - ACCESS_ONCE(sync_rcu_preempt_exp_count))) { + READ_ONCE(sync_rcu_preempt_exp_count))) { put_online_cpus(); goto mb_ret; /* Others did our work for us. */ } @@ -752,7 +760,7 @@ void synchronize_rcu_expedited(void) return; } } - if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) { + if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) { put_online_cpus(); goto unlock_mb_ret; /* Others did our work for us. */ } @@ -780,8 +788,7 @@ void synchronize_rcu_expedited(void) /* Clean up and exit. */ smp_mb(); /* ensure expedited GP seen before counter increment. */ - ACCESS_ONCE(sync_rcu_preempt_exp_count) = - sync_rcu_preempt_exp_count + 1; + WRITE_ONCE(sync_rcu_preempt_exp_count, sync_rcu_preempt_exp_count + 1); unlock_mb_ret: mutex_unlock(&sync_rcu_preempt_exp_mutex); mb_ret: @@ -799,7 +806,7 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); */ void rcu_barrier(void) { - _rcu_barrier(&rcu_preempt_state); + _rcu_barrier(rcu_state_p); } EXPORT_SYMBOL_GPL(rcu_barrier); @@ -808,7 +815,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier); */ static void __init __rcu_init_preempt(void) { - rcu_init_one(&rcu_preempt_state, &rcu_preempt_data); + rcu_init_one(rcu_state_p, rcu_data_p); } /* @@ -831,7 +838,8 @@ void exit_rcu(void) #else /* #ifdef CONFIG_PREEMPT_RCU */ -static struct rcu_state *rcu_state_p = &rcu_sched_state; +static struct rcu_state *const rcu_state_p = &rcu_sched_state; +static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data; /* * Tell them what RCU they are running. @@ -994,8 +1002,8 @@ static int rcu_boost(struct rcu_node *rnp) struct task_struct *t; struct list_head *tb; - if (ACCESS_ONCE(rnp->exp_tasks) == NULL && - ACCESS_ONCE(rnp->boost_tasks) == NULL) + if (READ_ONCE(rnp->exp_tasks) == NULL && + READ_ONCE(rnp->boost_tasks) == NULL) return 0; /* Nothing left to boost. */ raw_spin_lock_irqsave(&rnp->lock, flags); @@ -1048,8 +1056,8 @@ static int rcu_boost(struct rcu_node *rnp) rt_mutex_lock(&rnp->boost_mtx); rt_mutex_unlock(&rnp->boost_mtx); /* Then keep lockdep happy. */ - return ACCESS_ONCE(rnp->exp_tasks) != NULL || - ACCESS_ONCE(rnp->boost_tasks) != NULL; + return READ_ONCE(rnp->exp_tasks) != NULL || + READ_ONCE(rnp->boost_tasks) != NULL; } /* @@ -1173,7 +1181,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, struct sched_param sp; struct task_struct *t; - if (&rcu_preempt_state != rsp) + if (rcu_state_p != rsp) return 0; if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0) @@ -1367,13 +1375,12 @@ static void rcu_prepare_kthreads(int cpu) * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs * any flavor of RCU. */ -#ifndef CONFIG_RCU_NOCB_CPU_ALL int rcu_needs_cpu(u64 basemono, u64 *nextevt) { *nextevt = KTIME_MAX; - return rcu_cpu_has_callbacks(NULL); + return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) + ? 0 : rcu_cpu_has_callbacks(NULL); } -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up @@ -1460,7 +1467,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) * callbacks not yet ready to invoke. */ if ((rdp->completed != rnp->completed || - unlikely(ACCESS_ONCE(rdp->gpwrap))) && + unlikely(READ_ONCE(rdp->gpwrap))) && rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL]) note_gp_changes(rsp, rdp); @@ -1478,12 +1485,16 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) * * The caller must have disabled interrupts. */ -#ifndef CONFIG_RCU_NOCB_CPU_ALL int rcu_needs_cpu(u64 basemono, u64 *nextevt) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); unsigned long dj; + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) { + *nextevt = KTIME_MAX; + return 0; + } + /* Snapshot to detect later posting of non-lazy callback. */ rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted; @@ -1511,7 +1522,6 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) *nextevt = basemono + dj * TICK_NSEC; return 0; } -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ /* * Prepare a CPU for idle from an RCU perspective. The first major task @@ -1525,7 +1535,6 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) */ static void rcu_prepare_for_idle(void) { -#ifndef CONFIG_RCU_NOCB_CPU_ALL bool needwake; struct rcu_data *rdp; struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); @@ -1533,8 +1542,11 @@ static void rcu_prepare_for_idle(void) struct rcu_state *rsp; int tne; + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) + return; + /* Handle nohz enablement switches conservatively. */ - tne = ACCESS_ONCE(tick_nohz_active); + tne = READ_ONCE(tick_nohz_active); if (tne != rdtp->tick_nohz_enabled_snap) { if (rcu_cpu_has_callbacks(NULL)) invoke_rcu_core(); /* force nohz to see update. */ @@ -1580,7 +1592,6 @@ static void rcu_prepare_for_idle(void) if (needwake) rcu_gp_kthread_wake(rsp); } -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ } /* @@ -1590,12 +1601,11 @@ static void rcu_prepare_for_idle(void) */ static void rcu_cleanup_after_idle(void) { -#ifndef CONFIG_RCU_NOCB_CPU_ALL - if (rcu_is_nocb_cpu(smp_processor_id())) + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) || + rcu_is_nocb_cpu(smp_processor_id())) return; if (rcu_try_advance_all_cbs()) invoke_rcu_core(); -#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */ } /* @@ -1760,7 +1770,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) atomic_read(&rdtp->dynticks) & 0xfff, rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), - ACCESS_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart, + READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart, fast_no_hz); } @@ -1898,11 +1908,11 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) { struct rcu_data *rdp_leader = rdp->nocb_leader; - if (!ACCESS_ONCE(rdp_leader->nocb_kthread)) + if (!READ_ONCE(rdp_leader->nocb_kthread)) return; - if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) { + if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { /* Prior smp_mb__after_atomic() orders against prior enqueue. */ - ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false; + WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); wake_up(&rdp_leader->nocb_wq); } } @@ -1934,14 +1944,14 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) ret = atomic_long_read(&rdp->nocb_q_count); #ifdef CONFIG_PROVE_RCU - rhp = ACCESS_ONCE(rdp->nocb_head); + rhp = READ_ONCE(rdp->nocb_head); if (!rhp) - rhp = ACCESS_ONCE(rdp->nocb_gp_head); + rhp = READ_ONCE(rdp->nocb_gp_head); if (!rhp) - rhp = ACCESS_ONCE(rdp->nocb_follower_head); + rhp = READ_ONCE(rdp->nocb_follower_head); /* Having no rcuo kthread but CBs after scheduler starts is bad! */ - if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp && + if (!READ_ONCE(rdp->nocb_kthread) && rhp && rcu_scheduler_fully_active) { /* RCU callback enqueued before CPU first came online??? */ pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n", @@ -1975,12 +1985,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, atomic_long_add(rhcount, &rdp->nocb_q_count); /* rcu_barrier() relies on ->nocb_q_count add before xchg. */ old_rhpp = xchg(&rdp->nocb_tail, rhtp); - ACCESS_ONCE(*old_rhpp) = rhp; + WRITE_ONCE(*old_rhpp, rhp); atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy); smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */ /* If we are not being polled and there is a kthread, awaken it ... */ - t = ACCESS_ONCE(rdp->nocb_kthread); + t = READ_ONCE(rdp->nocb_kthread); if (rcu_nocb_poll || !t) { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNotPoll")); @@ -2118,7 +2128,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) for (;;) { wait_event_interruptible( rnp->nocb_gp_wq[c & 0x1], - (d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c))); + (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); if (likely(d)) break; WARN_ON(signal_pending(current)); @@ -2145,7 +2155,7 @@ wait_again: if (!rcu_nocb_poll) { trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); wait_event_interruptible(my_rdp->nocb_wq, - !ACCESS_ONCE(my_rdp->nocb_leader_sleep)); + !READ_ONCE(my_rdp->nocb_leader_sleep)); /* Memory barrier handled by smp_mb() calls below and repoll. */ } else if (firsttime) { firsttime = false; /* Don't drown trace log with "Poll"! */ @@ -2159,12 +2169,12 @@ wait_again: */ gotcbs = false; for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { - rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head); + rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head); if (!rdp->nocb_gp_head) continue; /* No CBs here, try next follower. */ /* Move callbacks to wait-for-GP list, which is empty. */ - ACCESS_ONCE(rdp->nocb_head) = NULL; + WRITE_ONCE(rdp->nocb_head, NULL); rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head); gotcbs = true; } @@ -2184,7 +2194,7 @@ wait_again: my_rdp->nocb_leader_sleep = true; smp_mb(); /* Ensure _sleep true before scan. */ for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) - if (ACCESS_ONCE(rdp->nocb_head)) { + if (READ_ONCE(rdp->nocb_head)) { /* Found CB, so short-circuit next wait. */ my_rdp->nocb_leader_sleep = false; break; @@ -2205,7 +2215,7 @@ wait_again: /* Each pass through the following loop wakes a follower, if needed. */ for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) { - if (ACCESS_ONCE(rdp->nocb_head)) + if (READ_ONCE(rdp->nocb_head)) my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/ if (!rdp->nocb_gp_head) continue; /* No CBs, so no need to wake follower. */ @@ -2241,7 +2251,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "FollowerSleep"); wait_event_interruptible(rdp->nocb_wq, - ACCESS_ONCE(rdp->nocb_follower_head)); + READ_ONCE(rdp->nocb_follower_head)); } else if (firsttime) { /* Don't drown trace log with "Poll"! */ firsttime = false; @@ -2282,10 +2292,10 @@ static int rcu_nocb_kthread(void *arg) nocb_follower_wait(rdp); /* Pull the ready-to-invoke callbacks onto local list. */ - list = ACCESS_ONCE(rdp->nocb_follower_head); + list = READ_ONCE(rdp->nocb_follower_head); BUG_ON(!list); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty"); - ACCESS_ONCE(rdp->nocb_follower_head) = NULL; + WRITE_ONCE(rdp->nocb_follower_head, NULL); tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head); /* Each pass through the following loop invokes a callback. */ @@ -2324,7 +2334,7 @@ static int rcu_nocb_kthread(void *arg) /* Is a deferred wakeup of rcu_nocb_kthread() required? */ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) { - return ACCESS_ONCE(rdp->nocb_defer_wakeup); + return READ_ONCE(rdp->nocb_defer_wakeup); } /* Do a deferred wakeup of rcu_nocb_kthread(). */ @@ -2334,8 +2344,8 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) if (!rcu_nocb_need_deferred_wakeup(rdp)) return; - ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup); - ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT; + ndw = READ_ONCE(rdp->nocb_defer_wakeup); + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_NOT); wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE); trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); } @@ -2448,7 +2458,7 @@ static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu) t = kthread_run(rcu_nocb_kthread, rdp_spawn, "rcuo%c/%d", rsp->abbr, cpu); BUG_ON(IS_ERR(t)); - ACCESS_ONCE(rdp_spawn->nocb_kthread) = t; + WRITE_ONCE(rdp_spawn->nocb_kthread, t); } /* @@ -2663,7 +2673,7 @@ static void rcu_sysidle_enter(int irq) /* Record start of fully idle period. */ j = jiffies; - ACCESS_ONCE(rdtp->dynticks_idle_jiffies) = j; + WRITE_ONCE(rdtp->dynticks_idle_jiffies, j); smp_mb__before_atomic(); atomic_inc(&rdtp->dynticks_idle); smp_mb__after_atomic(); @@ -2681,7 +2691,7 @@ static void rcu_sysidle_enter(int irq) */ void rcu_sysidle_force_exit(void) { - int oldstate = ACCESS_ONCE(full_sysidle_state); + int oldstate = READ_ONCE(full_sysidle_state); int newoldstate; /* @@ -2794,7 +2804,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle, smp_mb(); /* Read counters before timestamps. */ /* Pick up timestamps. */ - j = ACCESS_ONCE(rdtp->dynticks_idle_jiffies); + j = READ_ONCE(rdtp->dynticks_idle_jiffies); /* If this CPU entered idle more recently, update maxj timestamp. */ if (ULONG_CMP_LT(*maxj, j)) *maxj = j; @@ -2831,11 +2841,11 @@ static unsigned long rcu_sysidle_delay(void) static void rcu_sysidle(unsigned long j) { /* Check the current state. */ - switch (ACCESS_ONCE(full_sysidle_state)) { + switch (READ_ONCE(full_sysidle_state)) { case RCU_SYSIDLE_NOT: /* First time all are idle, so note a short idle period. */ - ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_SHORT; + WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_SHORT); break; case RCU_SYSIDLE_SHORT: @@ -2873,7 +2883,7 @@ static void rcu_sysidle_cancel(void) { smp_mb(); if (full_sysidle_state > RCU_SYSIDLE_SHORT) - ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT; + WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_NOT); } /* @@ -2925,7 +2935,7 @@ static void rcu_sysidle_cb(struct rcu_head *rhp) smp_mb(); /* grace period precedes setting inuse. */ rshp = container_of(rhp, struct rcu_sysidle_head, rh); - ACCESS_ONCE(rshp->inuse) = 0; + WRITE_ONCE(rshp->inuse, 0); } /* @@ -2936,7 +2946,7 @@ static void rcu_sysidle_cb(struct rcu_head *rhp) bool rcu_sys_is_idle(void) { static struct rcu_sysidle_head rsh; - int rss = ACCESS_ONCE(full_sysidle_state); + int rss = READ_ONCE(full_sysidle_state); if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu)) return false; @@ -2964,7 +2974,7 @@ bool rcu_sys_is_idle(void) } rcu_sysidle_report(rcu_state_p, isidle, maxj, false); oldrss = rss; - rss = ACCESS_ONCE(full_sysidle_state); + rss = READ_ONCE(full_sysidle_state); } } @@ -3048,10 +3058,10 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp) #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_cpu(smp_processor_id()) && (!rcu_gp_in_progress(rsp) || - ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ))) - return 1; + ULONG_CMP_LT(jiffies, READ_ONCE(rsp->gp_start) + HZ))) + return true; #endif /* #ifdef CONFIG_NO_HZ_FULL */ - return 0; + return false; } /* @@ -3077,7 +3087,7 @@ static void rcu_bind_gp_kthread(void) static void rcu_dynticks_task_enter(void) { #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) - ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id(); + WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id()); #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ } @@ -3085,6 +3095,6 @@ static void rcu_dynticks_task_enter(void) static void rcu_dynticks_task_exit(void) { #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) - ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1; + WRITE_ONCE(current->rcu_tasks_idle_cpu, -1); #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ } diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c index f92361efd0f5..3ea7ffc7d5c4 100644 --- a/kernel/rcu/tree_trace.c +++ b/kernel/rcu/tree_trace.c @@ -277,7 +277,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n", rsp->n_force_qs, rsp->n_force_qs_ngp, rsp->n_force_qs - rsp->n_force_qs_ngp, - ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen); + READ_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen); for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) { if (rnp->level != level) { seq_puts(m, "\n"); @@ -323,8 +323,8 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp) struct rcu_node *rnp = &rsp->node[0]; raw_spin_lock_irqsave(&rnp->lock, flags); - completed = ACCESS_ONCE(rsp->completed); - gpnum = ACCESS_ONCE(rsp->gpnum); + completed = READ_ONCE(rsp->completed); + gpnum = READ_ONCE(rsp->gpnum); if (completed == gpnum) gpage = 0; else diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 1f133350da01..afaecb7a799a 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -150,14 +150,14 @@ void __rcu_read_unlock(void) barrier(); /* critical section before exit code. */ t->rcu_read_lock_nesting = INT_MIN; barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s))) + if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); barrier(); /* ->rcu_read_unlock_special load before assign */ t->rcu_read_lock_nesting = 0; } #ifdef CONFIG_PROVE_LOCKING { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + int rrln = READ_ONCE(t->rcu_read_lock_nesting); WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); } @@ -389,17 +389,17 @@ module_param(rcu_cpu_stall_timeout, int, 0644); int rcu_jiffies_till_stall_check(void) { - int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout); + int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout); /* * Limit check must be consistent with the Kconfig limits * for CONFIG_RCU_CPU_STALL_TIMEOUT. */ if (till_stall_check < 3) { - ACCESS_ONCE(rcu_cpu_stall_timeout) = 3; + WRITE_ONCE(rcu_cpu_stall_timeout, 3); till_stall_check = 3; } else if (till_stall_check > 300) { - ACCESS_ONCE(rcu_cpu_stall_timeout) = 300; + WRITE_ONCE(rcu_cpu_stall_timeout, 300); till_stall_check = 300; } return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; @@ -550,12 +550,12 @@ static void check_holdout_task(struct task_struct *t, { int cpu; - if (!ACCESS_ONCE(t->rcu_tasks_holdout) || - t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) || - !ACCESS_ONCE(t->on_rq) || + if (!READ_ONCE(t->rcu_tasks_holdout) || + t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) || + !READ_ONCE(t->on_rq) || (IS_ENABLED(CONFIG_NO_HZ_FULL) && !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) { - ACCESS_ONCE(t->rcu_tasks_holdout) = false; + WRITE_ONCE(t->rcu_tasks_holdout, false); list_del_init(&t->rcu_tasks_holdout_list); put_task_struct(t); return; @@ -639,11 +639,11 @@ static int __noreturn rcu_tasks_kthread(void *arg) */ rcu_read_lock(); for_each_process_thread(g, t) { - if (t != current && ACCESS_ONCE(t->on_rq) && + if (t != current && READ_ONCE(t->on_rq) && !is_idle_task(t)) { get_task_struct(t); - t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw); - ACCESS_ONCE(t->rcu_tasks_holdout) = true; + t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw); + WRITE_ONCE(t->rcu_tasks_holdout, true); list_add(&t->rcu_tasks_holdout_list, &rcu_tasks_holdouts); } @@ -672,7 +672,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) struct task_struct *t1; schedule_timeout_interruptible(HZ); - rtst = ACCESS_ONCE(rcu_task_stall_timeout); + rtst = READ_ONCE(rcu_task_stall_timeout); needreport = rtst > 0 && time_after(jiffies, lastreport + rtst); if (needreport) @@ -728,7 +728,7 @@ static void rcu_spawn_tasks_kthread(void) static struct task_struct *rcu_tasks_kthread_ptr; struct task_struct *t; - if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) { + if (READ_ONCE(rcu_tasks_kthread_ptr)) { smp_mb(); /* Ensure caller sees full kthread. */ return; } @@ -740,7 +740,7 @@ static void rcu_spawn_tasks_kthread(void) t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread"); BUG_ON(IS_ERR(t)); smp_mb(); /* Ensure others see full kthread. */ - ACCESS_ONCE(rcu_tasks_kthread_ptr) = t; + WRITE_ONCE(rcu_tasks_kthread_ptr, t); mutex_unlock(&rcu_tasks_kthread_mutex); } diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 46be87024875..67687973ce80 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -11,7 +11,7 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif -obj-y += core.o proc.o clock.o cputime.o +obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o obj-y += wait.o completion.o idle.o obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index eae160dd669d..750ed601ddf7 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -1,5 +1,3 @@ -#ifdef CONFIG_SCHED_AUTOGROUP - #include "sched.h" #include <linux/proc_fs.h> @@ -141,7 +139,7 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag) p->signal->autogroup = autogroup_kref_get(ag); - if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled)) + if (!READ_ONCE(sysctl_sched_autogroup_enabled)) goto out; for_each_thread(p, t) @@ -249,5 +247,3 @@ int autogroup_path(struct task_group *tg, char *buf, int buflen) return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); } #endif /* CONFIG_SCHED_DEBUG */ - -#endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/sched/auto_group.h b/kernel/sched/auto_group.h index 8bd047142816..890c95f2587a 100644 --- a/kernel/sched/auto_group.h +++ b/kernel/sched/auto_group.h @@ -29,7 +29,7 @@ extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg); static inline struct task_group * autogroup_task_group(struct task_struct *p, struct task_group *tg) { - int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled); + int enabled = READ_ONCE(sysctl_sched_autogroup_enabled); if (enabled && task_wants_autogroup(p, tg)) return p->signal->autogroup->tg; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e9f25ce70c77..c9a707b59331 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -490,7 +490,7 @@ static bool set_nr_and_not_polling(struct task_struct *p) static bool set_nr_if_polling(struct task_struct *p) { struct thread_info *ti = task_thread_info(p); - typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags); + typeof(ti->flags) old, val = READ_ONCE(ti->flags); for (;;) { if (!(val & _TIF_POLLING_NRFLAG)) @@ -520,6 +520,52 @@ static bool set_nr_if_polling(struct task_struct *p) #endif #endif +void wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + struct wake_q_node *node = &task->wake_q; + + /* + * Atomically grab the task, if ->wake_q is !nil already it means + * its already queued (either by us or someone else) and will get the + * wakeup due to that. + * + * This cmpxchg() implies a full barrier, which pairs with the write + * barrier implied by the wakeup in wake_up_list(). + */ + if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) + return; + + get_task_struct(task); + + /* + * The head is context local, there can be no concurrency. + */ + *head->lastp = node; + head->lastp = &node->next; +} + +void wake_up_q(struct wake_q_head *head) +{ + struct wake_q_node *node = head->first; + + while (node != WAKE_Q_TAIL) { + struct task_struct *task; + + task = container_of(node, struct task_struct, wake_q); + BUG_ON(!task); + /* task can safely be re-inserted now */ + node = node->next; + task->wake_q.next = NULL; + + /* + * wake_up_process() implies a wmb() to pair with the queueing + * in wake_q_add() so as not to miss wakeups. + */ + wake_up_process(task); + put_task_struct(task); + } +} + /* * resched_curr - mark rq's current task 'to be rescheduled now'. * @@ -1027,7 +1073,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; - perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); + perf_event_task_migrate(p); } __set_task_cpu(p, new_cpu); @@ -2083,12 +2129,15 @@ void wake_up_new_task(struct task_struct *p) #ifdef CONFIG_PREEMPT_NOTIFIERS +static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE; + /** * preempt_notifier_register - tell me when current is being preempted & rescheduled * @notifier: notifier struct to register */ void preempt_notifier_register(struct preempt_notifier *notifier) { + static_key_slow_inc(&preempt_notifier_key); hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); } EXPORT_SYMBOL_GPL(preempt_notifier_register); @@ -2097,15 +2146,16 @@ EXPORT_SYMBOL_GPL(preempt_notifier_register); * preempt_notifier_unregister - no longer interested in preemption notifications * @notifier: notifier struct to unregister * - * This is safe to call from within a preemption notifier. + * This is *not* safe to call from within a preemption notifier. */ void preempt_notifier_unregister(struct preempt_notifier *notifier) { hlist_del(¬ifier->link); + static_key_slow_dec(&preempt_notifier_key); } EXPORT_SYMBOL_GPL(preempt_notifier_unregister); -static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +static void __fire_sched_in_preempt_notifiers(struct task_struct *curr) { struct preempt_notifier *notifier; @@ -2113,9 +2163,15 @@ static void fire_sched_in_preempt_notifiers(struct task_struct *curr) notifier->ops->sched_in(notifier, raw_smp_processor_id()); } +static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + if (static_key_false(&preempt_notifier_key)) + __fire_sched_in_preempt_notifiers(curr); +} + static void -fire_sched_out_preempt_notifiers(struct task_struct *curr, - struct task_struct *next) +__fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) { struct preempt_notifier *notifier; @@ -2123,13 +2179,21 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, notifier->ops->sched_out(notifier, next); } +static __always_inline void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + if (static_key_false(&preempt_notifier_key)) + __fire_sched_out_preempt_notifiers(curr, next); +} + #else /* !CONFIG_PREEMPT_NOTIFIERS */ -static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr) { } -static void +static inline void fire_sched_out_preempt_notifiers(struct task_struct *curr, struct task_struct *next) { @@ -2375,9 +2439,9 @@ unsigned long nr_iowait_cpu(int cpu) void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) { - struct rq *this = this_rq(); - *nr_waiters = atomic_read(&this->nr_iowait); - *load = this->cpu_load[0]; + struct rq *rq = this_rq(); + *nr_waiters = atomic_read(&rq->nr_iowait); + *load = rq->load.weight; } #ifdef CONFIG_SMP @@ -2475,6 +2539,7 @@ void scheduler_tick(void) update_rq_clock(rq); curr->sched_class->task_tick(rq, curr, 0); update_cpu_load_active(rq); + calc_global_load_tick(rq); raw_spin_unlock(&rq->lock); perf_event_task_tick(); @@ -2503,7 +2568,7 @@ void scheduler_tick(void) u64 scheduler_tick_max_deferment(void) { struct rq *rq = this_rq(); - unsigned long next, now = ACCESS_ONCE(jiffies); + unsigned long next, now = READ_ONCE(jiffies); next = rq->last_sched_tick + HZ; @@ -2704,9 +2769,7 @@ again: * - return from syscall or exception to user-space * - return from interrupt-handler to user-space * - * WARNING: all callers must re-check need_resched() afterward and reschedule - * accordingly in case an event triggered the need for rescheduling (such as - * an interrupt waking up a task) while preemption was disabled in __schedule(). + * WARNING: must be called with preemption disabled! */ static void __sched __schedule(void) { @@ -2715,7 +2778,6 @@ static void __sched __schedule(void) struct rq *rq; int cpu; - preempt_disable(); cpu = smp_processor_id(); rq = cpu_rq(cpu); rcu_note_context_switch(); @@ -2779,8 +2841,6 @@ static void __sched __schedule(void) raw_spin_unlock_irq(&rq->lock); post_schedule(rq); - - sched_preempt_enable_no_resched(); } static inline void sched_submit_work(struct task_struct *tsk) @@ -2801,7 +2861,9 @@ asmlinkage __visible void __sched schedule(void) sched_submit_work(tsk); do { + preempt_disable(); __schedule(); + sched_preempt_enable_no_resched(); } while (need_resched()); } EXPORT_SYMBOL(schedule); @@ -2840,15 +2902,14 @@ void __sched schedule_preempt_disabled(void) static void __sched notrace preempt_schedule_common(void) { do { - __preempt_count_add(PREEMPT_ACTIVE); + preempt_active_enter(); __schedule(); - __preempt_count_sub(PREEMPT_ACTIVE); + preempt_active_exit(); /* * Check again in case we missed a preemption opportunity * between schedule and now. */ - barrier(); } while (need_resched()); } @@ -2872,9 +2933,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) NOKPROBE_SYMBOL(preempt_schedule); EXPORT_SYMBOL(preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING /** - * preempt_schedule_context - preempt_schedule called by tracing + * preempt_schedule_notrace - preempt_schedule called by tracing * * The tracing infrastructure uses preempt_enable_notrace to prevent * recursion and tracing preempt enabling caused by the tracing @@ -2887,7 +2947,7 @@ EXPORT_SYMBOL(preempt_schedule); * instead of preempt_schedule() to exit user context if needed before * calling the scheduler. */ -asmlinkage __visible void __sched notrace preempt_schedule_context(void) +asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) { enum ctx_state prev_ctx; @@ -2895,7 +2955,13 @@ asmlinkage __visible void __sched notrace preempt_schedule_context(void) return; do { - __preempt_count_add(PREEMPT_ACTIVE); + /* + * Use raw __prempt_count() ops that don't call function. + * We can't call functions before disabling preemption which + * disarm preemption tracing recursions. + */ + __preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); + barrier(); /* * Needs preempt disabled in case user_exit() is traced * and the tracer calls preempt_enable_notrace() causing @@ -2905,12 +2971,11 @@ asmlinkage __visible void __sched notrace preempt_schedule_context(void) __schedule(); exception_exit(prev_ctx); - __preempt_count_sub(PREEMPT_ACTIVE); barrier(); + __preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); } while (need_resched()); } -EXPORT_SYMBOL_GPL(preempt_schedule_context); -#endif /* CONFIG_CONTEXT_TRACKING */ +EXPORT_SYMBOL_GPL(preempt_schedule_notrace); #endif /* CONFIG_PREEMPT */ @@ -2930,17 +2995,11 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) prev_state = exception_enter(); do { - __preempt_count_add(PREEMPT_ACTIVE); + preempt_active_enter(); local_irq_enable(); __schedule(); local_irq_disable(); - __preempt_count_sub(PREEMPT_ACTIVE); - - /* - * Check again in case we missed a preemption opportunity - * between schedule and now. - */ - barrier(); + preempt_active_exit(); } while (need_resched()); exception_exit(prev_state); @@ -3018,7 +3077,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (!dl_prio(p->normal_prio) || (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; - p->dl.dl_throttled = 0; enqueue_flag = ENQUEUE_REPLENISH; } else p->dl.dl_boosted = 0; @@ -4367,10 +4425,7 @@ long __sched io_schedule_timeout(long timeout) long ret; current->in_iowait = 1; - if (old_iowait) - blk_schedule_flush_plug(current); - else - blk_flush_plug(current); + blk_schedule_flush_plug(current); delayacct_blkio_start(); rq = raw_rq(); @@ -5295,7 +5350,7 @@ static struct notifier_block migration_notifier = { .priority = CPU_PRI_MIGRATION, }; -static void __cpuinit set_cpu_rq_start_time(void) +static void set_cpu_rq_start_time(void) { int cpu = smp_processor_id(); struct rq *rq = cpu_rq(cpu); @@ -7713,11 +7768,11 @@ static long sched_group_rt_runtime(struct task_group *tg) return rt_runtime_us; } -static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) +static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us) { u64 rt_runtime, rt_period; - rt_period = (u64)rt_period_us * NSEC_PER_USEC; + rt_period = rt_period_us * NSEC_PER_USEC; rt_runtime = tg->rt_bandwidth.rt_runtime; return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 8394b1ee600c..f5a64ffad176 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -567,7 +567,7 @@ static void cputime_advance(cputime_t *counter, cputime_t new) { cputime_t old; - while (new > (old = ACCESS_ONCE(*counter))) + while (new > (old = READ_ONCE(*counter))) cmpxchg_cputime(counter, old, new); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 21d6907d2b9f..eac20c557a55 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -632,7 +632,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) } static -int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) +int dl_runtime_exceeded(struct sched_dl_entity *dl_se) { return (dl_se->runtime <= 0); } @@ -676,7 +676,7 @@ static void update_curr_dl(struct rq *rq) sched_rt_avg_update(rq, delta_exec); dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec; - if (dl_runtime_exceeded(rq, dl_se)) { + if (dl_runtime_exceeded(dl_se)) { dl_se->dl_throttled = 1; __dequeue_task_dl(rq, curr, 0); if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted))) @@ -987,7 +987,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) rq = cpu_rq(cpu); rcu_read_lock(); - curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + curr = READ_ONCE(rq->curr); /* unlocked access */ /* * If we are dealing with a -deadline task, we must @@ -1004,7 +1004,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) (p->nr_cpus_allowed > 1)) { int target = find_later_rq(p); - if (target != -1) + if (target != -1 && + dl_time_before(p->dl.deadline, + cpu_rq(target)->dl.earliest_dl.curr)) cpu = target; } rcu_read_unlock(); @@ -1222,6 +1224,32 @@ next_node: return NULL; } +/* + * Return the earliest pushable rq's task, which is suitable to be executed + * on the CPU, NULL otherwise: + */ +static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq, int cpu) +{ + struct rb_node *next_node = rq->dl.pushable_dl_tasks_leftmost; + struct task_struct *p = NULL; + + if (!has_pushable_dl_tasks(rq)) + return NULL; + +next_node: + if (next_node) { + p = rb_entry(next_node, struct task_struct, pushable_dl_tasks); + + if (pick_dl_task(rq, p, cpu)) + return p; + + next_node = rb_next(next_node); + goto next_node; + } + + return NULL; +} + static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl); static int find_later_rq(struct task_struct *task) @@ -1325,6 +1353,17 @@ 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, + later_rq->dl.earliest_dl.curr)) { + /* + * Target rq has tasks of equal or earlier deadline, + * retrying does not release any lock and is unlikely + * to yield a different result. + */ + later_rq = NULL; + break; + } + /* Retry if something changed. */ if (double_lock_balance(rq, later_rq)) { if (unlikely(task_rq(task) != rq || @@ -1506,7 +1545,7 @@ static int pull_dl_task(struct rq *this_rq) if (src_rq->dl.dl_nr_running <= 1) goto skip; - p = pick_next_earliest_dl_task(src_rq, this_cpu); + p = pick_earliest_pushable_dl_task(src_rq, this_cpu); /* * We found a task to be pulled if: @@ -1651,7 +1690,7 @@ static void rq_offline_dl(struct rq *rq) cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu); } -void init_sched_dl_class(void) +void __init init_sched_dl_class(void) { unsigned int i; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index f94724eda407..315c68e015d9 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -132,12 +132,14 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) p->prio); #ifdef CONFIG_SCHEDSTATS SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - SPLIT_NS(p->se.vruntime), + SPLIT_NS(p->se.statistics.wait_sum), SPLIT_NS(p->se.sum_exec_runtime), SPLIT_NS(p->se.statistics.sum_sleep_runtime)); #else - SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld", - 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L); + SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", + 0LL, 0L, + SPLIT_NS(p->se.sum_exec_runtime), + 0LL, 0L); #endif #ifdef CONFIG_NUMA_BALANCING SEQ_printf(m, " %d", task_node(p)); @@ -156,7 +158,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) SEQ_printf(m, "\nrunnable tasks:\n" " task PID tree-key switches prio" - " exec-runtime sum-exec sum-sleep\n" + " wait-time sum-exec sum-sleep\n" "------------------------------------------------------" "----------------------------------------------------\n"); @@ -580,6 +582,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) nr_switches = p->nvcsw + p->nivcsw; #ifdef CONFIG_SCHEDSTATS + PN(se.statistics.sum_sleep_runtime); PN(se.statistics.wait_start); PN(se.statistics.sleep_start); PN(se.statistics.block_start); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 69be2825262d..40a7fcbf491e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -141,9 +141,9 @@ static inline void update_load_set(struct load_weight *lw, unsigned long w) * * This idea comes from the SD scheduler of Con Kolivas: */ -static int get_update_sysctl_factor(void) +static unsigned int get_update_sysctl_factor(void) { - unsigned int cpus = min_t(int, num_online_cpus(), 8); + unsigned int cpus = min_t(unsigned int, num_online_cpus(), 8); unsigned int factor; switch (sysctl_sched_tunable_scaling) { @@ -576,7 +576,7 @@ int sched_proc_update_handler(struct ctl_table *table, int write, loff_t *ppos) { int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - int factor = get_update_sysctl_factor(); + unsigned int factor = get_update_sysctl_factor(); if (ret || !write) return ret; @@ -834,7 +834,7 @@ static unsigned int task_nr_scan_windows(struct task_struct *p) static unsigned int task_scan_min(struct task_struct *p) { - unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size); + unsigned int scan_size = READ_ONCE(sysctl_numa_balancing_scan_size); unsigned int scan, floor; unsigned int windows = 1; @@ -1198,11 +1198,9 @@ static void task_numa_assign(struct task_numa_env *env, static bool load_too_imbalanced(long src_load, long dst_load, struct task_numa_env *env) { + long imb, old_imb; + long orig_src_load, orig_dst_load; long src_capacity, dst_capacity; - long orig_src_load; - long load_a, load_b; - long moved_load; - long imb; /* * The load is corrected for the CPU capacity available on each node. @@ -1215,39 +1213,30 @@ static bool load_too_imbalanced(long src_load, long dst_load, dst_capacity = env->dst_stats.compute_capacity; /* We care about the slope of the imbalance, not the direction. */ - load_a = dst_load; - load_b = src_load; - if (load_a < load_b) - swap(load_a, load_b); + if (dst_load < src_load) + swap(dst_load, src_load); /* Is the difference below the threshold? */ - imb = load_a * src_capacity * 100 - - load_b * dst_capacity * env->imbalance_pct; + imb = dst_load * src_capacity * 100 - + src_load * dst_capacity * env->imbalance_pct; if (imb <= 0) return false; /* * The imbalance is above the allowed threshold. - * Allow a move that brings us closer to a balanced situation, - * without moving things past the point of balance. + * Compare it with the old imbalance. */ orig_src_load = env->src_stats.load; + orig_dst_load = env->dst_stats.load; - /* - * In a task swap, there will be one load moving from src to dst, - * and another moving back. This is the net sum of both moves. - * A simple task move will always have a positive value. - * Allow the move if it brings the system closer to a balanced - * situation, without crossing over the balance point. - */ - moved_load = orig_src_load - src_load; + if (orig_dst_load < orig_src_load) + swap(orig_dst_load, orig_src_load); - if (moved_load > 0) - /* Moving src -> dst. Did we overshoot balance? */ - return src_load * dst_capacity < dst_load * src_capacity; - else - /* Moving dst -> src. Did we overshoot balance? */ - return dst_load * src_capacity < src_load * dst_capacity; + old_imb = orig_dst_load * src_capacity * 100 - + orig_src_load * dst_capacity * env->imbalance_pct; + + /* Would this change make things worse? */ + return (imb > old_imb); } /* @@ -1409,6 +1398,30 @@ static void task_numa_find_cpu(struct task_numa_env *env, } } +/* Only move tasks to a NUMA node less busy than the current node. */ +static bool numa_has_capacity(struct task_numa_env *env) +{ + struct numa_stats *src = &env->src_stats; + struct numa_stats *dst = &env->dst_stats; + + if (src->has_free_capacity && !dst->has_free_capacity) + return false; + + /* + * Only consider a task move if the source has a higher load + * than the destination, corrected for CPU capacity on each node. + * + * src->load dst->load + * --------------------- vs --------------------- + * src->compute_capacity dst->compute_capacity + */ + if (src->load * dst->compute_capacity > + dst->load * src->compute_capacity) + return true; + + return false; +} + static int task_numa_migrate(struct task_struct *p) { struct task_numa_env env = { @@ -1463,7 +1476,8 @@ static int task_numa_migrate(struct task_struct *p) update_numa_stats(&env.dst_stats, env.dst_nid); /* Try to find a spot on the preferred nid. */ - task_numa_find_cpu(&env, taskimp, groupimp); + if (numa_has_capacity(&env)) + task_numa_find_cpu(&env, taskimp, groupimp); /* * Look at other nodes in these cases: @@ -1494,7 +1508,8 @@ static int task_numa_migrate(struct task_struct *p) env.dist = dist; env.dst_nid = nid; update_numa_stats(&env.dst_stats, env.dst_nid); - task_numa_find_cpu(&env, taskimp, groupimp); + if (numa_has_capacity(&env)) + task_numa_find_cpu(&env, taskimp, groupimp); } } @@ -1794,7 +1809,12 @@ static void task_numa_placement(struct task_struct *p) u64 runtime, period; spinlock_t *group_lock = NULL; - seq = ACCESS_ONCE(p->mm->numa_scan_seq); + /* + * The p->mm->numa_scan_seq field gets updated without + * exclusive access. Use READ_ONCE() here to ensure + * that the field is read in a single access: + */ + seq = READ_ONCE(p->mm->numa_scan_seq); if (p->numa_scan_seq == seq) return; p->numa_scan_seq = seq; @@ -1938,7 +1958,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, } rcu_read_lock(); - tsk = ACCESS_ONCE(cpu_rq(cpu)->curr); + tsk = READ_ONCE(cpu_rq(cpu)->curr); if (!cpupid_match_pid(tsk, cpupid)) goto no_join; @@ -2107,7 +2127,15 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) static void reset_ptenuma_scan(struct task_struct *p) { - ACCESS_ONCE(p->mm->numa_scan_seq)++; + /* + * We only did a read acquisition of the mmap sem, so + * p->mm->numa_scan_seq is written to without exclusive access + * and the update is not guaranteed to be atomic. That's not + * much of an issue though, since this is just used for + * statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not + * expensive, to avoid any form of compiler optimizations: + */ + WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1); p->mm->numa_scan_offset = 0; } @@ -2181,7 +2209,7 @@ void task_numa_work(struct callback_head *work) } for (; vma; vma = vma->vm_next) { if (!vma_migratable(vma) || !vma_policy_mof(vma) || - is_vm_hugetlb_page(vma)) { + is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { continue; } @@ -4303,6 +4331,189 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) } #ifdef CONFIG_SMP + +/* + * per rq 'load' arrray crap; XXX kill this. + */ + +/* + * The exact cpuload at various idx values, calculated at every tick would be + * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load + * + * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called + * on nth tick when cpu may be busy, then we have: + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load + * + * decay_load_missed() below does efficient calculation of + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load + * + * The calculation is approximated on a 128 point scale. + * degrade_zero_ticks is the number of ticks after which load at any + * particular idx is approximated to be zero. + * degrade_factor is a precomputed table, a row for each load idx. + * Each column corresponds to degradation factor for a power of two ticks, + * based on 128 point scale. + * Example: + * row 2, col 3 (=12) says that the degradation at load idx 2 after + * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). + * + * With this power of 2 load factors, we can degrade the load n times + * by looking at 1 bits in n and doing as many mult/shift instead of + * n mult/shifts needed by the exact degradation. + */ +#define DEGRADE_SHIFT 7 +static const unsigned char + degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; +static const unsigned char + degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { + {0, 0, 0, 0, 0, 0, 0, 0}, + {64, 32, 8, 0, 0, 0, 0, 0}, + {96, 72, 40, 12, 1, 0, 0}, + {112, 98, 75, 43, 15, 1, 0}, + {120, 112, 98, 76, 45, 16, 2} }; + +/* + * Update cpu_load for any missed ticks, due to tickless idle. The backlog + * would be when CPU is idle and so we just decay the old load without + * adding any new load. + */ +static unsigned long +decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) +{ + int j = 0; + + if (!missed_updates) + return load; + + if (missed_updates >= degrade_zero_ticks[idx]) + return 0; + + if (idx == 1) + return load >> missed_updates; + + while (missed_updates) { + if (missed_updates % 2) + load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; + + missed_updates >>= 1; + j++; + } + return load; +} + +/* + * Update rq->cpu_load[] statistics. This function is usually called every + * scheduler tick (TICK_NSEC). With tickless idle this will not be called + * every tick. We fix it up based on jiffies. + */ +static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, + unsigned long pending_updates) +{ + int i, scale; + + this_rq->nr_load_updates++; + + /* Update our load: */ + this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ + for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { + unsigned long old_load, new_load; + + /* scale is effectively 1 << i now, and >> i divides by scale */ + + old_load = this_rq->cpu_load[i]; + old_load = decay_load_missed(old_load, pending_updates - 1, i); + new_load = this_load; + /* + * Round up the averaging division if load is increasing. This + * prevents us from getting stuck on 9 if the load is 10, for + * example. + */ + if (new_load > old_load) + new_load += scale - 1; + + this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; + } + + sched_avg_update(this_rq); +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * There is no sane way to deal with nohz on smp when using jiffies because the + * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading + * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}. + * + * Therefore we cannot use the delta approach from the regular tick since that + * would seriously skew the load calculation. However we'll make do for those + * updates happening while idle (nohz_idle_balance) or coming out of idle + * (tick_nohz_idle_exit). + * + * This means we might still be one tick off for nohz periods. + */ + +/* + * Called from nohz_idle_balance() to update the load ratings before doing the + * idle balance. + */ +static void update_idle_cpu_load(struct rq *this_rq) +{ + unsigned long curr_jiffies = READ_ONCE(jiffies); + unsigned long load = this_rq->cfs.runnable_load_avg; + unsigned long pending_updates; + + /* + * bail if there's load or we're actually up-to-date. + */ + if (load || curr_jiffies == this_rq->last_load_update_tick) + return; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + this_rq->last_load_update_tick = curr_jiffies; + + __update_cpu_load(this_rq, load, pending_updates); +} + +/* + * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed. + */ +void update_cpu_load_nohz(void) +{ + struct rq *this_rq = this_rq(); + unsigned long curr_jiffies = READ_ONCE(jiffies); + unsigned long pending_updates; + + if (curr_jiffies == this_rq->last_load_update_tick) + return; + + raw_spin_lock(&this_rq->lock); + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + if (pending_updates) { + this_rq->last_load_update_tick = curr_jiffies; + /* + * We were idle, this means load 0, the current load might be + * !0 due to remote wakeups and the sort. + */ + __update_cpu_load(this_rq, 0, pending_updates); + } + raw_spin_unlock(&this_rq->lock); +} +#endif /* CONFIG_NO_HZ */ + +/* + * Called from scheduler_tick() + */ +void update_cpu_load_active(struct rq *this_rq) +{ + unsigned long load = this_rq->cfs.runnable_load_avg; + /* + * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). + */ + this_rq->last_load_update_tick = jiffies; + __update_cpu_load(this_rq, load, 1); +} + /* Used instead of source_load when we know the type == 0 */ static unsigned long weighted_cpuload(const int cpu) { @@ -4355,7 +4566,7 @@ static unsigned long capacity_orig_of(int cpu) static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); - unsigned long nr_running = ACCESS_ONCE(rq->cfs.h_nr_running); + unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running); unsigned long load_avg = rq->cfs.runnable_load_avg; if (nr_running) @@ -5106,18 +5317,21 @@ again: * entity, update_curr() will update its vruntime, otherwise * forget we've ever seen it. */ - if (curr && curr->on_rq) - update_curr(cfs_rq); - else - curr = NULL; + if (curr) { + if (curr->on_rq) + update_curr(cfs_rq); + else + curr = NULL; - /* - * This call to check_cfs_rq_runtime() will do the throttle and - * dequeue its entity in the parent(s). Therefore the 'simple' - * nr_running test will indeed be correct. - */ - if (unlikely(check_cfs_rq_runtime(cfs_rq))) - goto simple; + /* + * This call to check_cfs_rq_runtime() will do the + * throttle and dequeue its entity in the parent(s). + * Therefore the 'simple' nr_running test will indeed + * be correct. + */ + if (unlikely(check_cfs_rq_runtime(cfs_rq))) + goto simple; + } se = pick_next_entity(cfs_rq, curr); cfs_rq = group_cfs_rq(se); @@ -5447,10 +5661,15 @@ static int task_hot(struct task_struct *p, struct lb_env *env) } #ifdef CONFIG_NUMA_BALANCING -/* Returns true if the destination node has incurred more faults */ +/* + * Returns true if the destination node is the preferred node. + * Needs to match fbq_classify_rq(): if there is a runnable task + * that is not on its preferred node, we should identify it. + */ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) { struct numa_group *numa_group = rcu_dereference(p->numa_group); + unsigned long src_faults, dst_faults; int src_nid, dst_nid; if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults || @@ -5464,29 +5683,30 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) if (src_nid == dst_nid) return false; - if (numa_group) { - /* Task is already in the group's interleave set. */ - if (node_isset(src_nid, numa_group->active_nodes)) - return false; - - /* Task is moving into the group's interleave set. */ - if (node_isset(dst_nid, numa_group->active_nodes)) - return true; - - return group_faults(p, dst_nid) > group_faults(p, src_nid); - } - /* Encourage migration to the preferred node. */ if (dst_nid == p->numa_preferred_nid) return true; - return task_faults(p, dst_nid) > task_faults(p, src_nid); + /* Migrating away from the preferred node is bad. */ + if (src_nid == p->numa_preferred_nid) + return false; + + if (numa_group) { + src_faults = group_faults(p, src_nid); + dst_faults = group_faults(p, dst_nid); + } else { + src_faults = task_faults(p, src_nid); + dst_faults = task_faults(p, dst_nid); + } + + return dst_faults > src_faults; } static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { struct numa_group *numa_group = rcu_dereference(p->numa_group); + unsigned long src_faults, dst_faults; int src_nid, dst_nid; if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) @@ -5501,23 +5721,23 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) if (src_nid == dst_nid) return false; - if (numa_group) { - /* Task is moving within/into the group's interleave set. */ - if (node_isset(dst_nid, numa_group->active_nodes)) - return false; + /* Migrating away from the preferred node is bad. */ + if (src_nid == p->numa_preferred_nid) + return true; - /* Task is moving out of the group's interleave set. */ - if (node_isset(src_nid, numa_group->active_nodes)) - return true; + /* Encourage migration to the preferred node. */ + if (dst_nid == p->numa_preferred_nid) + return false; - return group_faults(p, dst_nid) < group_faults(p, src_nid); + if (numa_group) { + src_faults = group_faults(p, src_nid); + dst_faults = group_faults(p, dst_nid); + } else { + src_faults = task_faults(p, src_nid); + dst_faults = task_faults(p, dst_nid); } - /* Migrating away from the preferred node is always bad. */ - if (src_nid == p->numa_preferred_nid) - return true; - - return task_faults(p, dst_nid) < task_faults(p, src_nid); + return dst_faults < src_faults; } #else @@ -6017,8 +6237,8 @@ static unsigned long scale_rt_capacity(int cpu) * Since we're reading these variables without serialization make sure * we read them once before doing sanity checks on them. */ - age_stamp = ACCESS_ONCE(rq->age_stamp); - avg = ACCESS_ONCE(rq->rt_avg); + age_stamp = READ_ONCE(rq->age_stamp); + avg = READ_ONCE(rq->rt_avg); delta = __rq_clock_broken(rq) - age_stamp; if (unlikely(delta < 0)) diff --git a/kernel/sched/proc.c b/kernel/sched/loadavg.c index 8ecd552fe4f2..ef7159012cf3 100644 --- a/kernel/sched/proc.c +++ b/kernel/sched/loadavg.c @@ -1,7 +1,9 @@ /* - * kernel/sched/proc.c + * kernel/sched/loadavg.c * - * Kernel load calculations, forked from sched/core.c + * This file contains the magic bits required to compute the global loadavg + * figure. Its a silly number but people think its important. We go through + * great pains to make it work on big machines and tickless kernels. */ #include <linux/export.h> @@ -81,7 +83,7 @@ long calc_load_fold_active(struct rq *this_rq) long nr_active, delta = 0; nr_active = this_rq->nr_running; - nr_active += (long) this_rq->nr_uninterruptible; + nr_active += (long)this_rq->nr_uninterruptible; if (nr_active != this_rq->calc_load_active) { delta = nr_active - this_rq->calc_load_active; @@ -186,6 +188,7 @@ void calc_load_enter_idle(void) delta = calc_load_fold_active(this_rq); if (delta) { int idx = calc_load_write_idx(); + atomic_long_add(delta, &calc_load_idle[idx]); } } @@ -241,18 +244,20 @@ fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) { unsigned long result = 1UL << frac_bits; - if (n) for (;;) { - if (n & 1) { - result *= x; - result += 1UL << (frac_bits - 1); - result >>= frac_bits; + if (n) { + for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; } - n >>= 1; - if (!n) - break; - x *= x; - x += 1UL << (frac_bits - 1); - x >>= frac_bits; } return result; @@ -285,7 +290,6 @@ static unsigned long calc_load_n(unsigned long load, unsigned long exp, unsigned long active, unsigned int n) { - return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); } @@ -339,6 +343,8 @@ static inline void calc_global_nohz(void) { } /* * calc_load - update the avenrun load estimates 10 ticks after the * CPUs have updated calc_load_tasks. + * + * Called from the global timer code. */ void calc_global_load(unsigned long ticks) { @@ -370,10 +376,10 @@ void calc_global_load(unsigned long ticks) } /* - * Called from update_cpu_load() to periodically update this CPU's + * Called from scheduler_tick() to periodically update this CPU's * active count. */ -static void calc_load_account_active(struct rq *this_rq) +void calc_global_load_tick(struct rq *this_rq) { long delta; @@ -386,199 +392,3 @@ static void calc_load_account_active(struct rq *this_rq) this_rq->calc_load_update += LOAD_FREQ; } - -/* - * End of global load-average stuff - */ - -/* - * The exact cpuload at various idx values, calculated at every tick would be - * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load - * - * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called - * on nth tick when cpu may be busy, then we have: - * load = ((2^idx - 1) / 2^idx)^(n-1) * load - * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load - * - * decay_load_missed() below does efficient calculation of - * load = ((2^idx - 1) / 2^idx)^(n-1) * load - * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load - * - * The calculation is approximated on a 128 point scale. - * degrade_zero_ticks is the number of ticks after which load at any - * particular idx is approximated to be zero. - * degrade_factor is a precomputed table, a row for each load idx. - * Each column corresponds to degradation factor for a power of two ticks, - * based on 128 point scale. - * Example: - * row 2, col 3 (=12) says that the degradation at load idx 2 after - * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). - * - * With this power of 2 load factors, we can degrade the load n times - * by looking at 1 bits in n and doing as many mult/shift instead of - * n mult/shifts needed by the exact degradation. - */ -#define DEGRADE_SHIFT 7 -static const unsigned char - degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; -static const unsigned char - degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { - {0, 0, 0, 0, 0, 0, 0, 0}, - {64, 32, 8, 0, 0, 0, 0, 0}, - {96, 72, 40, 12, 1, 0, 0}, - {112, 98, 75, 43, 15, 1, 0}, - {120, 112, 98, 76, 45, 16, 2} }; - -/* - * Update cpu_load for any missed ticks, due to tickless idle. The backlog - * would be when CPU is idle and so we just decay the old load without - * adding any new load. - */ -static unsigned long -decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) -{ - int j = 0; - - if (!missed_updates) - return load; - - if (missed_updates >= degrade_zero_ticks[idx]) - return 0; - - if (idx == 1) - return load >> missed_updates; - - while (missed_updates) { - if (missed_updates % 2) - load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; - - missed_updates >>= 1; - j++; - } - return load; -} - -/* - * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). With tickless idle this will not be called - * every tick. We fix it up based on jiffies. - */ -static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, - unsigned long pending_updates) -{ - int i, scale; - - this_rq->nr_load_updates++; - - /* Update our load: */ - this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ - for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { - unsigned long old_load, new_load; - - /* scale is effectively 1 << i now, and >> i divides by scale */ - - old_load = this_rq->cpu_load[i]; - old_load = decay_load_missed(old_load, pending_updates - 1, i); - new_load = this_load; - /* - * Round up the averaging division if load is increasing. This - * prevents us from getting stuck on 9 if the load is 10, for - * example. - */ - if (new_load > old_load) - new_load += scale - 1; - - this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; - } - - sched_avg_update(this_rq); -} - -#ifdef CONFIG_SMP -static inline unsigned long get_rq_runnable_load(struct rq *rq) -{ - return rq->cfs.runnable_load_avg; -} -#else -static inline unsigned long get_rq_runnable_load(struct rq *rq) -{ - return rq->load.weight; -} -#endif - -#ifdef CONFIG_NO_HZ_COMMON -/* - * There is no sane way to deal with nohz on smp when using jiffies because the - * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading - * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}. - * - * Therefore we cannot use the delta approach from the regular tick since that - * would seriously skew the load calculation. However we'll make do for those - * updates happening while idle (nohz_idle_balance) or coming out of idle - * (tick_nohz_idle_exit). - * - * This means we might still be one tick off for nohz periods. - */ - -/* - * Called from nohz_idle_balance() to update the load ratings before doing the - * idle balance. - */ -void update_idle_cpu_load(struct rq *this_rq) -{ - unsigned long curr_jiffies = ACCESS_ONCE(jiffies); - unsigned long load = get_rq_runnable_load(this_rq); - unsigned long pending_updates; - - /* - * bail if there's load or we're actually up-to-date. - */ - if (load || curr_jiffies == this_rq->last_load_update_tick) - return; - - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - this_rq->last_load_update_tick = curr_jiffies; - - __update_cpu_load(this_rq, load, pending_updates); -} - -/* - * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed. - */ -void update_cpu_load_nohz(void) -{ - struct rq *this_rq = this_rq(); - unsigned long curr_jiffies = ACCESS_ONCE(jiffies); - unsigned long pending_updates; - - if (curr_jiffies == this_rq->last_load_update_tick) - return; - - raw_spin_lock(&this_rq->lock); - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - if (pending_updates) { - this_rq->last_load_update_tick = curr_jiffies; - /* - * We were idle, this means load 0, the current load might be - * !0 due to remote wakeups and the sort. - */ - __update_cpu_load(this_rq, 0, pending_updates); - } - raw_spin_unlock(&this_rq->lock); -} -#endif /* CONFIG_NO_HZ */ - -/* - * Called from scheduler_tick() - */ -void update_cpu_load_active(struct rq *this_rq) -{ - unsigned long load = get_rq_runnable_load(this_rq); - /* - * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). - */ - this_rq->last_load_update_tick = jiffies; - __update_cpu_load(this_rq, load, 1); - - calc_load_account_active(this_rq); -} diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e43da5391dcd..7d7093c51f8d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1327,7 +1327,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) rq = cpu_rq(cpu); rcu_read_lock(); - curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + curr = READ_ONCE(rq->curr); /* unlocked access */ /* * If the current task on @p's runqueue is an RT task, then diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f9a58ef373b4..aea7c1f393cb 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -26,8 +26,14 @@ extern __read_mostly int scheduler_running; extern unsigned long calc_load_update; extern atomic_long_t calc_load_tasks; +extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq); + +#ifdef CONFIG_SMP extern void update_cpu_load_active(struct rq *this_rq); +#else +static inline void update_cpu_load_active(struct rq *this_rq) { } +#endif /* * Helpers for converting nanosecond timing to jiffy resolution @@ -708,7 +714,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); static inline u64 __rq_clock_broken(struct rq *rq) { - return ACCESS_ONCE(rq->clock); + return READ_ONCE(rq->clock); } static inline u64 rq_clock(struct rq *rq) @@ -1285,7 +1291,6 @@ extern void update_max_interval(void); extern void init_sched_dl_class(void); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); -extern void init_sched_dl_class(void); extern void resched_curr(struct rq *rq); extern void resched_cpu(int cpu); @@ -1299,8 +1304,6 @@ extern void init_dl_task_timer(struct sched_dl_entity *dl_se); unsigned long to_ratio(u64 period, u64 runtime); -extern void update_idle_cpu_load(struct rq *this_rq); - extern void init_task_runnable_average(struct task_struct *p); static inline void add_nr_running(struct rq *rq, unsigned count) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 4ab704339656..077ebbd5e10f 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -174,7 +174,8 @@ static inline bool cputimer_running(struct task_struct *tsk) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + /* Check if cputimer isn't running. This is accessed without locking. */ + if (!READ_ONCE(cputimer->running)) return false; /* @@ -215,9 +216,7 @@ static inline void account_group_user_time(struct task_struct *tsk, if (!cputimer_running(tsk)) return; - raw_spin_lock(&cputimer->lock); - cputimer->cputime.utime += cputime; - raw_spin_unlock(&cputimer->lock); + atomic64_add(cputime, &cputimer->cputime_atomic.utime); } /** @@ -238,9 +237,7 @@ static inline void account_group_system_time(struct task_struct *tsk, if (!cputimer_running(tsk)) return; - raw_spin_lock(&cputimer->lock); - cputimer->cputime.stime += cputime; - raw_spin_unlock(&cputimer->lock); + atomic64_add(cputime, &cputimer->cputime_atomic.stime); } /** @@ -261,7 +258,5 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, if (!cputimer_running(tsk)) return; - raw_spin_lock(&cputimer->lock); - cputimer->cputime.sum_exec_runtime += ns; - raw_spin_unlock(&cputimer->lock); + atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); } diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 852143a79f36..052e02672d12 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -341,7 +341,7 @@ long wait_woken(wait_queue_t *wait, unsigned mode, long timeout) * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss * an event. */ - set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */ + smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */ return timeout; } @@ -354,7 +354,7 @@ int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) * doesn't imply write barrier and the users expects write * barrier semantics on wakeup functions. The following * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up() - * and is paired with set_mb() in wait_woken(). + * and is paired with smp_store_mb() in wait_woken(). */ smp_wmb(); /* C */ wait->flags |= WQ_FLAG_WOKEN; @@ -601,7 +601,7 @@ EXPORT_SYMBOL(bit_wait_io); __sched int bit_wait_timeout(struct wait_bit_key *word) { - unsigned long now = ACCESS_ONCE(jiffies); + unsigned long now = READ_ONCE(jiffies); if (signal_pending_state(current->state, current)) return 1; if (time_after_eq(now, word->timeout)) @@ -613,7 +613,7 @@ EXPORT_SYMBOL_GPL(bit_wait_timeout); __sched int bit_wait_io_timeout(struct wait_bit_key *word) { - unsigned long now = ACCESS_ONCE(jiffies); + unsigned long now = READ_ONCE(jiffies); if (signal_pending_state(current->state, current)) return 1; if (time_after_eq(now, word->timeout)) diff --git a/kernel/signal.c b/kernel/signal.c index d51c5ddd855c..f19833b5db3c 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -245,7 +245,7 @@ static inline void print_dropped_signal(int sig) * RETURNS: * %true if @mask is set, %false if made noop because @task was dying. */ -bool task_set_jobctl_pending(struct task_struct *task, unsigned int mask) +bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask) { BUG_ON(mask & ~(JOBCTL_PENDING_MASK | JOBCTL_STOP_CONSUME | JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING)); @@ -297,7 +297,7 @@ void task_clear_jobctl_trapping(struct task_struct *task) * CONTEXT: * Must be called with @task->sighand->siglock held. */ -void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask) +void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask) { BUG_ON(mask & ~JOBCTL_PENDING_MASK); @@ -2000,7 +2000,7 @@ static bool do_signal_stop(int signr) struct signal_struct *sig = current->signal; if (!(current->jobctl & JOBCTL_STOP_PENDING)) { - unsigned int gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; + unsigned long gstop = JOBCTL_STOP_PENDING | JOBCTL_STOP_CONSUME; struct task_struct *t; /* signr will be recorded in task->jobctl for retries */ diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 695f0c6cd169..fd643d8c4b42 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -211,25 +211,6 @@ static int multi_cpu_stop(void *data) return err; } -struct irq_cpu_stop_queue_work_info { - int cpu1; - int cpu2; - struct cpu_stop_work *work1; - struct cpu_stop_work *work2; -}; - -/* - * This function is always run with irqs and preemption disabled. - * This guarantees that both work1 and work2 get queued, before - * our local migrate thread gets the chance to preempt us. - */ -static void irq_cpu_stop_queue_work(void *arg) -{ - struct irq_cpu_stop_queue_work_info *info = arg; - cpu_stop_queue_work(info->cpu1, info->work1); - cpu_stop_queue_work(info->cpu2, info->work2); -} - /** * stop_two_cpus - stops two cpus * @cpu1: the cpu to stop @@ -245,7 +226,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * { struct cpu_stop_done done; struct cpu_stop_work work1, work2; - struct irq_cpu_stop_queue_work_info call_args; struct multi_stop_data msdata; preempt_disable(); @@ -262,13 +242,6 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * .done = &done }; - call_args = (struct irq_cpu_stop_queue_work_info){ - .cpu1 = cpu1, - .cpu2 = cpu2, - .work1 = &work1, - .work2 = &work2, - }; - cpu_stop_init_done(&done, 2); set_state(&msdata, MULTI_STOP_PREPARE); @@ -285,16 +258,11 @@ int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void * return -ENOENT; } - lg_local_lock(&stop_cpus_lock); - /* - * Queuing needs to be done by the lowest numbered CPU, to ensure - * that works are always queued in the same order on every CPU. - * This prevents deadlocks. - */ - smp_call_function_single(min(cpu1, cpu2), - &irq_cpu_stop_queue_work, - &call_args, 1); - lg_local_unlock(&stop_cpus_lock); + lg_double_lock(&stop_cpus_lock, cpu1, cpu2); + cpu_stop_queue_work(cpu1, &work1); + cpu_stop_queue_work(cpu2, &work2); + lg_double_unlock(&stop_cpus_lock, cpu1, cpu2); + preempt_enable(); wait_for_completion(&done.completion); diff --git a/kernel/sys.c b/kernel/sys.c index a4e372b798a5..8571296b7ddb 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -92,10 +92,10 @@ # define SET_TSC_CTL(a) (-EINVAL) #endif #ifndef MPX_ENABLE_MANAGEMENT -# define MPX_ENABLE_MANAGEMENT(a) (-EINVAL) +# define MPX_ENABLE_MANAGEMENT() (-EINVAL) #endif #ifndef MPX_DISABLE_MANAGEMENT -# define MPX_DISABLE_MANAGEMENT(a) (-EINVAL) +# define MPX_DISABLE_MANAGEMENT() (-EINVAL) #endif #ifndef GET_FP_MODE # define GET_FP_MODE(a) (-EINVAL) @@ -2230,12 +2230,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_MPX_ENABLE_MANAGEMENT: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; - error = MPX_ENABLE_MANAGEMENT(me); + error = MPX_ENABLE_MANAGEMENT(); break; case PR_MPX_DISABLE_MANAGEMENT: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; - error = MPX_DISABLE_MANAGEMENT(me); + error = MPX_DISABLE_MANAGEMENT(); break; case PR_SET_FP_MODE: error = SET_FP_MODE(me, arg2); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index db5c9508ed95..5c7ae4b641c4 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -272,21 +272,23 @@ lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) /* * Divide a ktime value by a nanosecond value */ -u64 __ktime_divns(const ktime_t kt, s64 div) +s64 __ktime_divns(const ktime_t kt, s64 div) { - u64 dclc; int sft = 0; + s64 dclc; + u64 tmp; dclc = ktime_to_ns(kt); + tmp = dclc < 0 ? -dclc : dclc; + /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } - dclc >>= sft; - do_div(dclc, (unsigned long) div); - - return dclc; + tmp >>= sft; + do_div(tmp, (unsigned long) div); + return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 0075da74abf0..892e3dae0aac 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -196,39 +196,62 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, return 0; } -static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b) +/* + * Set cputime to sum_cputime if sum_cputime > cputime. Use cmpxchg + * to avoid race conditions with concurrent updates to cputime. + */ +static inline void __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime) { - if (b->utime > a->utime) - a->utime = b->utime; + u64 curr_cputime; +retry: + curr_cputime = atomic64_read(cputime); + if (sum_cputime > curr_cputime) { + if (atomic64_cmpxchg(cputime, curr_cputime, sum_cputime) != curr_cputime) + goto retry; + } +} - if (b->stime > a->stime) - a->stime = b->stime; +static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, struct task_cputime *sum) +{ + __update_gt_cputime(&cputime_atomic->utime, sum->utime); + __update_gt_cputime(&cputime_atomic->stime, sum->stime); + __update_gt_cputime(&cputime_atomic->sum_exec_runtime, sum->sum_exec_runtime); +} - if (b->sum_exec_runtime > a->sum_exec_runtime) - a->sum_exec_runtime = b->sum_exec_runtime; +/* Sample task_cputime_atomic values in "atomic_timers", store results in "times". */ +static inline void sample_cputime_atomic(struct task_cputime *times, + struct task_cputime_atomic *atomic_times) +{ + times->utime = atomic64_read(&atomic_times->utime); + times->stime = atomic64_read(&atomic_times->stime); + times->sum_exec_runtime = atomic64_read(&atomic_times->sum_exec_runtime); } void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; struct task_cputime sum; - unsigned long flags; - if (!cputimer->running) { + /* Check if cputimer isn't running. This is accessed without locking. */ + if (!READ_ONCE(cputimer->running)) { /* * The POSIX timer interface allows for absolute time expiry * values through the TIMER_ABSTIME flag, therefore we have - * to synchronize the timer to the clock every time we start - * it. + * to synchronize the timer to the clock every time we start it. */ thread_group_cputime(tsk, &sum); - raw_spin_lock_irqsave(&cputimer->lock, flags); - cputimer->running = 1; - update_gt_cputime(&cputimer->cputime, &sum); - } else - raw_spin_lock_irqsave(&cputimer->lock, flags); - *times = cputimer->cputime; - raw_spin_unlock_irqrestore(&cputimer->lock, flags); + update_gt_cputime(&cputimer->cputime_atomic, &sum); + + /* + * We're setting cputimer->running without a lock. Ensure + * this only gets written to in one operation. We set + * running after update_gt_cputime() as a small optimization, + * but barriers are not required because update_gt_cputime() + * can handle concurrent updates. + */ + WRITE_ONCE(cputimer->running, 1); + } + sample_cputime_atomic(times, &cputimer->cputime_atomic); } /* @@ -582,7 +605,8 @@ bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk) if (!task_cputime_zero(&tsk->cputime_expires)) return false; - if (tsk->signal->cputimer.running) + /* Check if cputimer is running. This is accessed without locking. */ + if (READ_ONCE(tsk->signal->cputimer.running)) return false; return true; @@ -852,10 +876,10 @@ static void check_thread_timers(struct task_struct *tsk, /* * Check for the special case thread timers. */ - soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur); + soft = READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur); if (soft != RLIM_INFINITY) { unsigned long hard = - ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max); + READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max); if (hard != RLIM_INFINITY && tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { @@ -882,14 +906,12 @@ static void check_thread_timers(struct task_struct *tsk, } } -static void stop_process_timers(struct signal_struct *sig) +static inline void stop_process_timers(struct signal_struct *sig) { struct thread_group_cputimer *cputimer = &sig->cputimer; - unsigned long flags; - raw_spin_lock_irqsave(&cputimer->lock, flags); - cputimer->running = 0; - raw_spin_unlock_irqrestore(&cputimer->lock, flags); + /* Turn off cputimer->running. This is done without locking. */ + WRITE_ONCE(cputimer->running, 0); } static u32 onecputick; @@ -958,11 +980,11 @@ static void check_process_timers(struct task_struct *tsk, SIGPROF); check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime, SIGVTALRM); - soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); + soft = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); if (soft != RLIM_INFINITY) { unsigned long psecs = cputime_to_secs(ptime); unsigned long hard = - ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max); + READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_max); cputime_t x; if (psecs >= hard) { /* @@ -1111,12 +1133,11 @@ static inline int fastpath_timer_check(struct task_struct *tsk) } sig = tsk->signal; - if (sig->cputimer.running) { + /* Check if cputimer is running. This is accessed without locking. */ + if (READ_ONCE(sig->cputimer.running)) { struct task_cputime group_sample; - raw_spin_lock(&sig->cputimer.lock); - group_sample = sig->cputimer.cputime; - raw_spin_unlock(&sig->cputimer.lock); + sample_cputime_atomic(&group_sample, &sig->cputimer.cputime_atomic); if (task_cputime_expired(&group_sample, &sig->cputime_expires)) return 1; @@ -1157,7 +1178,7 @@ void run_posix_cpu_timers(struct task_struct *tsk) * If there are any active process wide timers (POSIX 1.b, itimers, * RLIMIT_CPU) cputimer must be running. */ - if (tsk->signal->cputimer.running) + if (READ_ONCE(tsk->signal->cputimer.running)) check_process_timers(tsk, &firing); /* diff --git a/kernel/torture.c b/kernel/torture.c index dd70993c266c..3e4840633d3e 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -409,7 +409,7 @@ static void (*torture_shutdown_hook)(void); */ void torture_shutdown_absorb(const char *title) { - while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { + while (READ_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { pr_notice("torture thread %s parking due to system shutdown\n", title); schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT); @@ -480,9 +480,9 @@ static int torture_shutdown_notify(struct notifier_block *unused1, unsigned long unused2, void *unused3) { mutex_lock(&fullstop_mutex); - if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) { + if (READ_ONCE(fullstop) == FULLSTOP_DONTSTOP) { VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected"); - ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN; + WRITE_ONCE(fullstop, FULLSTOP_SHUTDOWN); } else { pr_warn("Concurrent rmmod and shutdown illegal!\n"); } @@ -523,13 +523,13 @@ static int stutter; */ void stutter_wait(const char *title) { - while (ACCESS_ONCE(stutter_pause_test) || - (torture_runnable && !ACCESS_ONCE(*torture_runnable))) { + while (READ_ONCE(stutter_pause_test) || + (torture_runnable && !READ_ONCE(*torture_runnable))) { if (stutter_pause_test) - if (ACCESS_ONCE(stutter_pause_test) == 1) + if (READ_ONCE(stutter_pause_test) == 1) schedule_timeout_interruptible(1); else - while (ACCESS_ONCE(stutter_pause_test)) + while (READ_ONCE(stutter_pause_test)) cond_resched(); else schedule_timeout_interruptible(round_jiffies_relative(HZ)); @@ -549,14 +549,14 @@ static int torture_stutter(void *arg) if (!torture_must_stop()) { if (stutter > 1) { schedule_timeout_interruptible(stutter - 1); - ACCESS_ONCE(stutter_pause_test) = 2; + WRITE_ONCE(stutter_pause_test, 2); } schedule_timeout_interruptible(1); - ACCESS_ONCE(stutter_pause_test) = 1; + WRITE_ONCE(stutter_pause_test, 1); } if (!torture_must_stop()) schedule_timeout_interruptible(stutter); - ACCESS_ONCE(stutter_pause_test) = 0; + WRITE_ONCE(stutter_pause_test, 0); torture_shutdown_absorb("torture_stutter"); } while (!torture_must_stop()); torture_kthread_stopping("torture_stutter"); @@ -642,13 +642,13 @@ EXPORT_SYMBOL_GPL(torture_init_end); bool torture_cleanup_begin(void) { mutex_lock(&fullstop_mutex); - if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { + if (READ_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { pr_warn("Concurrent rmmod and shutdown illegal!\n"); mutex_unlock(&fullstop_mutex); schedule_timeout_uninterruptible(10); return true; } - ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD; + WRITE_ONCE(fullstop, FULLSTOP_RMMOD); mutex_unlock(&fullstop_mutex); torture_shutdown_cleanup(); torture_shuffle_cleanup(); @@ -681,7 +681,7 @@ EXPORT_SYMBOL_GPL(torture_must_stop); */ bool torture_must_stop_irq(void) { - return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP; + return READ_ONCE(fullstop) != FULLSTOP_DONTSTOP; } EXPORT_SYMBOL_GPL(torture_must_stop_irq); diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 13d945c0d03f..1b28df2d9104 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -450,7 +450,7 @@ static int __init ring_buffer_benchmark_init(void) if (producer_fifo >= 0) { struct sched_param param = { - .sched_priority = consumer_fifo + .sched_priority = producer_fifo }; sched_setscheduler(producer, SCHED_FIFO, ¶m); } else diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index ced69da0ff55..7f2e97ce71a7 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1369,19 +1369,26 @@ static int check_preds(struct filter_parse_state *ps) { int n_normal_preds = 0, n_logical_preds = 0; struct postfix_elt *elt; + int cnt = 0; list_for_each_entry(elt, &ps->postfix, list) { - if (elt->op == OP_NONE) + if (elt->op == OP_NONE) { + cnt++; continue; + } if (elt->op == OP_AND || elt->op == OP_OR) { n_logical_preds++; + cnt--; continue; } + if (elt->op != OP_NOT) + cnt--; n_normal_preds++; + WARN_ON_ONCE(cnt < 0); } - if (!n_normal_preds || n_logical_preds >= n_normal_preds) { + if (cnt != 1 || !n_normal_preds || n_logical_preds >= n_normal_preds) { parse_error(ps, FILT_ERR_INVALID_FILTER, 0); return -EINVAL; } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 506edcc500c4..581a68a04c64 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -621,7 +621,7 @@ void watchdog_nmi_enable_all(void) put_online_cpus(); unlock: - mutex_lock(&watchdog_proc_mutex); + mutex_unlock(&watchdog_proc_mutex); } void watchdog_nmi_disable_all(void) |