diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/core.c | 103 | ||||
| -rw-r--r-- | kernel/sched/cpufreq.c | 4 | ||||
| -rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 2 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 15 | ||||
| -rw-r--r-- | kernel/sched/psi.c | 2 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 2 | ||||
| -rw-r--r-- | kernel/sched/topology.c | 4 |
7 files changed, 94 insertions, 38 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b7a4afdc33cb..4778c48a7fda 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -398,19 +398,7 @@ static bool set_nr_if_polling(struct task_struct *p) #endif #endif -/** - * wake_q_add() - queue a wakeup for 'later' waking. - * @head: the wake_q_head to add @task to - * @task: the task to queue for 'later' wakeup - * - * Queue a task for later wakeup, most likely by the wake_up_q() call in the - * same context, _HOWEVER_ this is not guaranteed, the wakeup can come - * instantly. - * - * This function must be used as-if it were wake_up_process(); IOW the task - * must be ready to be woken at this location. - */ -void wake_q_add(struct wake_q_head *head, struct task_struct *task) +static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) { struct wake_q_node *node = &task->wake_q; @@ -423,16 +411,56 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * state, even in the failed case, an explicit smp_mb() must be used. */ smp_mb__before_atomic(); - if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)) - return; - - get_task_struct(task); + if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))) + return false; /* * The head is context local, there can be no concurrency. */ *head->lastp = node; head->lastp = &node->next; + return true; +} + +/** + * wake_q_add() - queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + */ +void wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + if (__wake_q_add(head, task)) + get_task_struct(task); +} + +/** + * wake_q_add_safe() - safely queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + * + * This function is essentially a task-safe equivalent to wake_q_add(). Callers + * that already hold reference to @task can call the 'safe' version and trust + * wake_q to do the right thing depending whether or not the @task is already + * queued for wakeup. + */ +void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task) +{ + if (!__wake_q_add(head, task)) + put_task_struct(task); } void wake_up_q(struct wake_q_head *head) @@ -2192,6 +2220,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) INIT_HLIST_HEAD(&p->preempt_notifiers); #endif +#ifdef CONFIG_COMPACTION + p->capture_control = NULL; +#endif init_numa_balancing(clone_flags, p); } @@ -5267,9 +5298,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, - compat_pid_t, pid, - struct old_timespec32 __user *, interval) +SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid, + struct old_timespec32 __user *, interval) { struct timespec64 t; int retval = sched_rr_get_interval(pid, &t); @@ -5869,14 +5899,11 @@ void __init sched_init_smp(void) /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot - * happen. The hotplug lock is nevertheless taken to satisfy lockdep, - * but there won't be any contention on it. + * happen. */ - cpus_read_lock(); mutex_lock(&sched_domains_mutex); sched_init_domains(cpu_active_mask); mutex_unlock(&sched_domains_mutex); - cpus_read_unlock(); /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) @@ -6164,6 +6191,34 @@ void ___might_sleep(const char *file, int line, int preempt_offset) add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } EXPORT_SYMBOL(___might_sleep); + +void __cant_sleep(const char *file, int line, int preempt_offset) +{ + static unsigned long prev_jiffy; + + if (irqs_disabled()) + return; + + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return; + + if (preempt_count() > preempt_offset) + return; + + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line); + printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), + current->pid, current->comm); + + debug_show_held_locks(current); + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} +EXPORT_SYMBOL_GPL(__cant_sleep); #endif #ifdef CONFIG_MAGIC_SYSRQ diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index 22bd8980f32f..835671f0f917 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -48,8 +48,8 @@ EXPORT_SYMBOL_GPL(cpufreq_add_update_util_hook); * * Clear the update_util_data pointer for the given CPU. * - * Callers must use RCU-sched callbacks to free any memory that might be - * accessed via the old update_util_data pointer or invoke synchronize_sched() + * Callers must use RCU callbacks to free any memory that might be + * accessed via the old update_util_data pointer or invoke synchronize_rcu() * right after this function to avoid use-after-free. */ void cpufreq_remove_update_util_hook(int cpu) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 1ccf77f6d346..5c41ea367422 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -850,7 +850,7 @@ static void sugov_stop(struct cpufreq_policy *policy) for_each_cpu(cpu, policy->cpus) cpufreq_remove_update_util_hook(cpu); - synchronize_sched(); + synchronize_rcu(); if (!policy->fast_switch_enabled) { irq_work_sync(&sg_policy->irq_work); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 51003e1c794d..fdab7eb6f351 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1173,7 +1173,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) /* New address space, reset the preferred nid */ if (!(clone_flags & CLONE_VM)) { - p->numa_preferred_nid = -1; + p->numa_preferred_nid = NUMA_NO_NODE; return; } @@ -1193,13 +1193,13 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) static void account_numa_enqueue(struct rq *rq, struct task_struct *p) { - rq->nr_numa_running += (p->numa_preferred_nid != -1); + rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE); rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p)); } static void account_numa_dequeue(struct rq *rq, struct task_struct *p) { - rq->nr_numa_running -= (p->numa_preferred_nid != -1); + rq->nr_numa_running -= (p->numa_preferred_nid != NUMA_NO_NODE); rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p)); } @@ -1413,7 +1413,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, * two full passes of the "multi-stage node selection" test that is * executed below. */ - if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) && + if ((p->numa_preferred_nid == NUMA_NO_NODE || p->numa_scan_seq <= 4) && (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid))) return true; @@ -1861,7 +1861,7 @@ static void numa_migrate_preferred(struct task_struct *p) unsigned long interval = HZ; /* This task has no NUMA fault statistics yet */ - if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) + if (unlikely(p->numa_preferred_nid == NUMA_NO_NODE || !p->numa_faults)) return; /* Periodically retry migrating the task to the preferred node */ @@ -2108,7 +2108,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) static void task_numa_placement(struct task_struct *p) { - int seq, nid, max_nid = -1; + int seq, nid, max_nid = NUMA_NO_NODE; unsigned long max_faults = 0; unsigned long fault_types[2] = { 0, 0 }; unsigned long total_faults; @@ -2651,7 +2651,8 @@ static void update_scan_period(struct task_struct *p, int new_cpu) * the preferred node. */ if (dst_nid == p->numa_preferred_nid || - (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid)) + (p->numa_preferred_nid != NUMA_NO_NODE && + src_nid != p->numa_preferred_nid)) return; } diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index c3484785b179..0e97ca9306ef 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -322,7 +322,7 @@ static bool update_stats(struct psi_group *group) expires = group->next_update; if (now < expires) goto out; - if (now - expires > psi_period) + if (now - expires >= psi_period) missed_periods = div_u64(now - expires, psi_period); /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 71208b67e58a..efa686eeff26 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1279,7 +1279,7 @@ extern void sched_ttwu_pending(void); /* * The domain tree (rq->sd) is protected by RCU's quiescent state transition. - * See detach_destroy_domains: synchronize_sched for details. + * See destroy_sched_domains: call_rcu for details. * * The domain tree of any CPU may only be accessed from within * preempt-disabled sections. diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 93ff526e77b0..ab7f371a3a17 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -471,7 +471,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd) raw_spin_unlock_irqrestore(&rq->lock, flags); if (old_rd) - call_rcu_sched(&old_rd->rcu, free_rootdomain); + call_rcu(&old_rd->rcu, free_rootdomain); } void sched_get_rd(struct root_domain *rd) @@ -484,7 +484,7 @@ void sched_put_rd(struct root_domain *rd) if (!atomic_dec_and_test(&rd->refcount)) return; - call_rcu_sched(&rd->rcu, free_rootdomain); + call_rcu(&rd->rcu, free_rootdomain); } static int init_rootdomain(struct root_domain *rd) |