/*
* kernel/sched/core.c
*
- * Kernel scheduler and related syscalls
+ * Core kernel scheduler code and related syscalls
*
* Copyright (C) 1991-2002 Linus Torvalds
- *
- * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and
- * make semaphores SMP safe
- * 1998-11-19 Implemented schedule_timeout() and related stuff
- * by Andrea Arcangeli
- * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar:
- * hybrid priority-list and round-robin design with
- * an array-switch method of distributing timeslices
- * and per-CPU runqueues. Cleanups and useful suggestions
- * by Davide Libenzi, preemptible kernel bits by Robert Love.
- * 2003-09-03 Interactivity tuning by Con Kolivas.
- * 2004-04-02 Scheduler domains code by Nick Piggin
- * 2007-04-15 Work begun on replacing all interactivity tuning with a
- * fair scheduling design by Con Kolivas.
- * 2007-05-05 Load balancing (smp-nice) and other improvements
- * by Peter Williams
- * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith
- * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
- * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins,
- * Thomas Gleixner, Mike Kravetz
*/
-
#include <linux/kasan.h>
#include <linux/mm.h>
#include <linux/module.h>
const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
/*
- * period over which we measure -rt task cpu usage in us.
+ * period over which we measure -rt task CPU usage in us.
* default: 1s
*/
unsigned int sysctl_sched_rt_period = 1000000;
*/
int sysctl_sched_rt_runtime = 950000;
-/* cpus with isolated domains */
+/* CPUs with isolated domains */
cpumask_var_t cpu_isolated_map;
/*
* If we observe the old cpu in task_rq_lock, the acquire of
* the old rq->lock will fully serialize against the stores.
*
- * If we observe the new cpu in task_rq_lock, the acquire will
+ * If we observe the new CPU in task_rq_lock, the acquire will
* pair with the WMB to ensure we must then also see migrating.
*/
if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
task = container_of(node, struct task_struct, wake_q);
BUG_ON(!task);
- /* task can safely be re-inserted now */
+ /* Task can safely be re-inserted now: */
node = node->next;
task->wake_q.next = NULL;
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ_COMMON
/*
- * In the semi idle case, use the nearest busy cpu for migrating timers
- * from an idle cpu. This is good for power-savings.
+ * In the semi idle case, use the nearest busy CPU for migrating timers
+ * from an idle CPU. This is good for power-savings.
*
* We don't do similar optimization for completely idle system, as
- * selecting an idle cpu will add more delays to the timers than intended
- * (as that cpu's timer base may not be uptodate wrt jiffies etc).
+ * selecting an idle CPU will add more delays to the timers than intended
+ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
*/
int get_nohz_timer_target(void)
{
rcu_read_unlock();
return cpu;
}
+
/*
* When add_timer_on() enqueues a timer into the timer wheel of an
* idle CPU then this timer might expire before the next timer event
};
/*
- * Move (not current) task off this cpu, onto dest cpu. We're doing
+ * Move (not current) task off this CPU, onto the destination CPU. We're doing
* this because either it can't run here any more (set_cpus_allowed()
* away from this CPU, or CPU going down), or because we're
* attempting to rebalance this task on exec (sched_exec).
struct rq *rq = this_rq();
/*
- * The original target cpu might have gone down and we might
- * be on another cpu but it doesn't matter.
+ * The original target CPU might have gone down and we might
+ * be on another CPU but it doesn't matter.
*/
local_irq_disable();
/*
if (p->flags & PF_KTHREAD) {
/*
* For kernel threads that do indeed end up on online &&
- * !active we want to ensure they are strict per-cpu threads.
+ * !active we want to ensure they are strict per-CPU threads.
*/
WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) &&
!cpumask_intersects(new_mask, cpu_active_mask) &&
/*
* Task isn't running anymore; make it appear like we migrated
* it before it went to sleep. This means on wakeup we make the
- * previous cpu our target instead of where it really is.
+ * previous CPU our target instead of where it really is.
*/
p->wake_cpu = cpu;
}
*
* - on cpu-up we allow per-cpu kthreads on the online && !active cpu,
* see __set_cpus_allowed_ptr(). At this point the newly online
- * cpu isn't yet part of the sched domains, and balancing will not
+ * CPU isn't yet part of the sched domains, and balancing will not
* see it.
*
- * - on cpu-down we clear cpu_active() to mask the sched domains and
+ * - on CPU-down we clear cpu_active() to mask the sched domains and
* avoid the load balancer to place new tasks on the to be removed
- * cpu. Existing tasks will remain running there and will be taken
+ * CPU. Existing tasks will remain running there and will be taken
* off.
*
* This means that fallback selection must not select !active CPUs.
int dest_cpu;
/*
- * If the node that the cpu is on has been offlined, cpu_to_node()
- * will return -1. There is no cpu on the node, and we should
- * select the cpu on the other node.
+ * If the node that the CPU is on has been offlined, cpu_to_node()
+ * will return -1. There is no CPU on the node, and we should
+ * select the CPU on the other node.
*/
if (nid != -1) {
nodemask = cpumask_of_node(nid);
state = possible;
break;
}
- /* fall-through */
+ /* Fall-through */
case possible:
do_set_cpus_allowed(p, cpu_possible_mask);
state = fail;
/*
* In order not to call set_task_cpu() on a blocking task we need
* to rely on ttwu() to place the task on a valid ->cpus_allowed
- * cpu.
+ * CPU.
*
* Since this is common to all placement strategies, this lives here.
*
activate_task(rq, p, en_flags);
p->on_rq = TASK_ON_RQ_QUEUED;
- /* if a worker is waking up, notify workqueue */
+ /* If a worker is waking up, notify the workqueue: */
if (p->flags & PF_WQ_WORKER)
wq_worker_waking_up(p, cpu_of(rq));
}
raw_spin_lock_irqsave(&rq->lock, flags);
if (is_idle_task(rq->curr))
smp_send_reschedule(cpu);
- /* Else cpu is not in idle, do nothing here */
+ /* Else CPU is not idle, do nothing here: */
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
#if defined(CONFIG_SMP)
if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
- sched_clock_cpu(cpu); /* sync clocks x-cpu */
+ sched_clock_cpu(cpu); /* Sync clocks across CPUs */
ttwu_queue_remote(p, cpu, wake_flags);
return;
}
* MIGRATION
*
* The basic program-order guarantee on SMP systems is that when a task [t]
- * migrates, all its activity on its old cpu [c0] happens-before any subsequent
- * execution on its new cpu [c1].
+ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
+ * execution on its new CPU [c1].
*
* For migration (of runnable tasks) this is provided by the following means:
*
*
* Transitivity guarantees that B happens after A and C after B.
* Note: we only require RCpc transitivity.
- * Note: the cpu doing B need not be c0 or c1
+ * Note: the CPU doing B need not be c0 or c1
*
* Example:
*
trace_sched_waking(p);
- success = 1; /* we're going to change ->state */
+ /* We're going to change ->state: */
+ success = 1;
cpu = task_cpu(p);
/*
smp_rmb();
/*
- * If the owning (remote) cpu is still in the middle of schedule() with
+ * If the owning (remote) CPU is still in the middle of schedule() with
* this task as prev, wait until its done referencing the task.
*
* Pairs with the smp_store_release() in finish_lock_switch().
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
/*
- * We're setting the cpu for the first time, we don't migrate,
+ * We're setting the CPU for the first time, we don't migrate,
* so use __set_task_cpu().
*/
__set_task_cpu(p, cpu);
/*
* Fork balancing, do it here and not earlier because:
* - cpus_allowed can change in the fork path
- * - any previously selected cpu might disappear through hotplug
+ * - any previously selected CPU might disappear through hotplug
*
* Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
* as we're not fully set-up yet.
}
/*
- * Check if only the current task is running on the cpu.
+ * Check if only the current task is running on the CPU.
*
* Caution: this function does not check that the caller has disabled
* preemption, thus the result might have a time-of-check-to-time-of-use
* So we have a optimization chance when the task's delta_exec is 0.
* Reading ->on_cpu is racy, but this is ok.
*
- * If we race with it leaving cpu, we'll take a lock. So we're correct.
- * If we race with it entering cpu, unaccounted time is 0. This is
+ * If we race with it leaving CPU, we'll take a lock. So we're correct.
+ * If we race with it entering CPU, unaccounted time is 0. This is
* indistinguishable from the read occurring a few cycles earlier.
* If we see ->on_cpu without ->on_rq, the task is leaving, and has
* been accounted, so we're correct here as well.
if (unlikely(p == RETRY_TASK))
goto again;
- /* assumes fair_sched_class->next == idle_sched_class */
+ /* Assumes fair_sched_class->next == idle_sched_class */
if (unlikely(!p))
p = idle_sched_class.pick_next_task(rq, prev, rf);
}
}
- BUG(); /* the idle class will always have a runnable task */
+ /* The idle class should always have a runnable task: */
+ BUG();
}
/*
raw_spin_lock(&rq->lock);
rq_pin_lock(rq, &rf);
- rq->clock_update_flags <<= 1; /* promote REQ to ACT */
+ /* Promote REQ to ACT */
+ rq->clock_update_flags <<= 1;
switch_count = &prev->nivcsw;
if (!preempt && prev->state) {
++*switch_count;
trace_sched_switch(preempt, prev, next);
- rq = context_switch(rq, prev, next, &rf); /* unlocks the rq */
+
+ /* Also unlocks the rq: */
+ rq = context_switch(rq, prev, next, &rf);
} else {
rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
rq_unpin_lock(rq, &rf);
smp_mb();
raw_spin_unlock_wait(¤t->pi_lock);
- /* causes final put_task_struct in finish_task_switch(). */
+ /* Causes final put_task_struct in finish_task_switch(): */
__set_current_state(TASK_DEAD);
- current->flags |= PF_NOFREEZE; /* tell freezer to ignore us */
+
+ /* Tell freezer to ignore us: */
+ current->flags |= PF_NOFREEZE;
+
__schedule(false);
BUG();
- /* Avoid "noreturn function does return". */
+
+ /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
for (;;)
- cpu_relax(); /* For when BUG is null */
+ cpu_relax();
}
static inline void sched_submit_work(struct task_struct *tsk)
check_class_changed(rq, p, prev_class, oldprio);
out_unlock:
- preempt_disable(); /* avoid rq from going away on us */
+ /* Avoid rq from going away on us: */
+ preempt_disable();
__task_rq_unlock(rq, &rf);
balance_callback(rq);
*/
int can_nice(const struct task_struct *p, const int nice)
{
- /* convert nice value [19,-20] to rlimit style value [1,40] */
+ /* Convert nice value [19,-20] to rlimit style value [1,40]: */
int nice_rlim = nice_to_rlimit(nice);
return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
}
/**
- * idle_cpu - is a given cpu idle currently?
+ * idle_cpu - is a given CPU idle currently?
* @cpu: the processor in question.
*
* Return: 1 if the CPU is currently idle. 0 otherwise.
}
/**
- * idle_task - return the idle task for a given cpu.
+ * idle_task - return the idle task for a given CPU.
* @cpu: the processor in question.
*
- * Return: The idle task for the cpu @cpu.
+ * Return: The idle task for the CPU @cpu.
*/
struct task_struct *idle_task(int cpu)
{
}
/*
- * check the target process has a UID that matches the current process's
+ * Check the target process has a UID that matches the current process's:
*/
static bool check_same_owner(struct task_struct *p)
{
return match;
}
-static bool dl_param_changed(struct task_struct *p,
- const struct sched_attr *attr)
+static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
{
struct sched_dl_entity *dl_se = &p->dl;
int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
struct rq *rq;
- /* may grab non-irq protected spin_locks */
+ /* May grab non-irq protected spin_locks: */
BUG_ON(in_interrupt());
recheck:
- /* double check policy once rq lock held */
+ /* Double check policy once rq lock held: */
if (policy < 0) {
reset_on_fork = p->sched_reset_on_fork;
policy = oldpolicy = p->policy;
unsigned long rlim_rtprio =
task_rlimit(p, RLIMIT_RTPRIO);
- /* can't set/change the rt policy */
+ /* Can't set/change the rt policy: */
if (policy != p->policy && !rlim_rtprio)
return -EPERM;
- /* can't increase priority */
+ /* Can't increase priority: */
if (attr->sched_priority > p->rt_priority &&
attr->sched_priority > rlim_rtprio)
return -EPERM;
return -EPERM;
}
- /* can't change other user's priorities */
+ /* Can't change other user's priorities: */
if (!check_same_owner(p))
return -EPERM;
- /* Normal users shall not reset the sched_reset_on_fork flag */
+ /* Normal users shall not reset the sched_reset_on_fork flag: */
if (p->sched_reset_on_fork && !reset_on_fork)
return -EPERM;
}
}
/*
- * make sure no PI-waiters arrive (or leave) while we are
+ * Make sure no PI-waiters arrive (or leave) while we are
* changing the priority of the task:
*
* To be able to change p->policy safely, the appropriate
update_rq_clock(rq);
/*
- * Changing the policy of the stop threads its a very bad idea
+ * Changing the policy of the stop threads its a very bad idea:
*/
if (p == rq->stop) {
task_rq_unlock(rq, p, &rf);
#endif
}
- /* recheck policy now with rq lock held */
+ /* Re-check policy now with rq lock held: */
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
task_rq_unlock(rq, p, &rf);
set_curr_task(rq, p);
check_class_changed(rq, p, prev_class, oldprio);
- preempt_disable(); /* avoid rq from going away on us */
+
+ /* Avoid rq from going away on us: */
+ preempt_disable();
task_rq_unlock(rq, p, &rf);
if (pi)
rt_mutex_adjust_pi(p);
- /*
- * Run balance callbacks after we've adjusted the PI chain.
- */
+ /* Run balance callbacks after we've adjusted the PI chain: */
balance_callback(rq);
preempt_enable();
/*
* Mimics kernel/events/core.c perf_copy_attr().
*/
-static int sched_copy_attr(struct sched_attr __user *uattr,
- struct sched_attr *attr)
+static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
{
u32 size;
int ret;
if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
return -EFAULT;
- /*
- * zero the full structure, so that a short copy will be nice.
- */
+ /* Zero the full structure, so that a short copy will be nice: */
memset(attr, 0, sizeof(*attr));
ret = get_user(size, &uattr->size);
if (ret)
return ret;
- if (size > PAGE_SIZE) /* silly large */
+ /* Bail out on silly large: */
+ if (size > PAGE_SIZE)
goto err_size;
- if (!size) /* abi compat */
+ /* ABI compatibility quirk: */
+ if (!size)
size = SCHED_ATTR_SIZE_VER0;
if (size < SCHED_ATTR_SIZE_VER0)
return -EFAULT;
/*
- * XXX: do we want to be lenient like existing syscalls; or do we want
+ * XXX: Do we want to be lenient like existing syscalls; or do we want
* to be strict and return an error on out-of-bounds values?
*/
attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
*
* Return: 0 on success. An error code otherwise.
*/
-SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
- struct sched_param __user *, param)
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
{
- /* negative values for policy are not valid */
if (policy < 0)
return -EINVAL;
}
/**
- * sys_sched_setaffinity - set the cpu affinity of a process
+ * sys_sched_setaffinity - set the CPU affinity of a process
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
- * @user_mask_ptr: user-space pointer to the new cpu mask
+ * @user_mask_ptr: user-space pointer to the new CPU mask
*
* Return: 0 on success. An error code otherwise.
*/
}
/**
- * sys_sched_getaffinity - get the cpu affinity of a process
+ * sys_sched_getaffinity - get the CPU affinity of a process
* @pid: pid of the process
* @len: length in bytes of the bitmask pointed to by user_mask_ptr
- * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ * @user_mask_ptr: user-space pointer to hold the current CPU mask
*
* Return: size of CPU mask copied to user_mask_ptr on success. An
* error code otherwise.
* Typical broken usage is:
*
* while (!event)
- * yield();
+ * yield();
*
* where one assumes that yield() will let 'the other' process run that will
* make event true. If the current task is a SCHED_FIFO task that will never
/**
* init_idle - set up an idle thread for a given CPU
* @idle: task in question
- * @cpu: cpu the idle task belongs to
+ * @cpu: CPU the idle task belongs to
*
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
#endif
/*
* We're having a chicken and egg problem, even though we are
- * holding rq->lock, the cpu isn't yet set to this cpu so the
+ * holding rq->lock, the CPU isn't yet set to this CPU so the
* lockdep check in task_group() will fail.
*
* Similar case to sched_fork(). / Alternatively we could
/*
* Kthreads which disallow setaffinity shouldn't be moved
- * to a new cpuset; we don't want to change their cpu
+ * to a new cpuset; we don't want to change their CPU
* affinity and isolating such threads by their set of
* allowed nodes is unnecessary. Thus, cpusets are not
* applicable for such threads. This prevents checking for
#ifdef CONFIG_HOTPLUG_CPU
/*
- * Ensures that the idle task is using init_mm right before its cpu goes
+ * Ensure that the idle task is using init_mm right before its CPU goes
* offline.
*/
void idle_task_exit(void)
for (;;) {
/*
* There's this thread running, bail when that's the only
- * remaining thread.
+ * remaining thread:
*/
if (rq->nr_running == 1)
break;
/*
- * pick_next_task assumes pinned rq->lock.
+ * pick_next_task() assumes pinned rq->lock:
*/
rq_pin_lock(rq, &rf);
next = pick_next_task(rq, &fake_task, &rf);
rq->age_stamp = sched_clock_cpu(cpu);
}
-static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
+/* Protected by sched_domains_mutex: */
+static cpumask_var_t sched_domains_tmpmask;
#ifdef CONFIG_SCHED_DEBUG
}
/*
- * By default the system creates a single root-domain with all cpus as
+ * By default the system creates a single root-domain with all CPUs as
* members (mimicking the global state we have today).
*/
struct root_domain def_root_domain;
* SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
* allows us to avoid some pointer chasing select_idle_sibling().
*
- * Also keep a unique ID per domain (we use the first cpu number in
+ * Also keep a unique ID per domain (we use the first CPU number in
* the cpumask of the domain), this allows us to quickly tell if
- * two cpus are in the same cache domain, see cpus_share_cache().
+ * two CPUs are in the same cache domain, see cpus_share_cache().
*/
DEFINE_PER_CPU(struct sched_domain *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
update_top_cache_domain(cpu);
}
-/* Setup the mask of cpus configured for isolated domains */
+/* Setup the mask of CPUs configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
int ret;
*
* In that case build_sched_domains() will have terminated the iteration early
* and our sibling sd spans will be empty. Domains should always include the
- * cpu they're built on, so check that.
- *
+ * CPU they're built on, so check that.
*/
static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
{
}
/*
- * Return the canonical balance cpu for this group, this is the first cpu
+ * Return the canonical balance CPU for this group, this is the first CPU
* of this group that's also in the iteration mask.
*/
int group_balance_cpu(struct sched_group *sg)
/*
* Make sure the first group of this domain contains the
- * canonical balance cpu. Otherwise the sched_domain iteration
+ * canonical balance CPU. Otherwise the sched_domain iteration
* breaks. See update_sg_lb_stats().
*/
if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
if (sg) {
*sg = *per_cpu_ptr(sdd->sg, cpu);
(*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
- atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */
+
+ /* For claim_allocations: */
+ atomic_set(&(*sg)->sgc->ref, 1);
}
return cpu;
} else
request = attr->relax_domain_level;
if (request < sd->level) {
- /* turn off idle balance on this domain */
+ /* Turn off idle balance on this domain: */
sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
} else {
- /* turn on idle balance on this domain */
+ /* Turn on idle balance on this domain: */
sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
}
}
switch (what) {
case sa_rootdomain:
if (!atomic_read(&d->rd->refcount))
- free_rootdomain(&d->rd->rcu); /* fall through */
+ free_rootdomain(&d->rd->rcu);
+ /* Fall through */
case sa_sd:
- free_percpu(d->sd); /* fall through */
+ free_percpu(d->sd);
+ /* Fall through */
case sa_sd_storage:
- __sdt_free(cpu_map); /* fall through */
+ __sdt_free(cpu_map);
+ /* Fall through */
case sa_none:
break;
}
}
-static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
- const struct cpumask *cpu_map)
+static enum s_alloc
+__visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map)
{
memset(d, 0, sizeof(*d));
/*
* Now for each level, construct a mask per node which contains all
- * cpus of nodes that are that many hops away from us.
+ * CPUs of nodes that are that many hops away from us.
*/
for (i = 0; i < level; i++) {
sched_domains_numa_masks[i] =
}
/*
- * Build sched domains for a given set of cpus and attach the sched domains
- * to the individual cpus
+ * Build sched domains for a given set of CPUs and attach the sched domains
+ * to the individual CPUs
*/
-static int build_sched_domains(const struct cpumask *cpu_map,
- struct sched_domain_attr *attr)
+static int
+build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr)
{
enum s_alloc alloc_state;
struct sched_domain *sd;
if (alloc_state != sa_rootdomain)
goto error;
- /* Set up domains for cpus specified by the cpu_map. */
+ /* Set up domains for CPUs specified by the cpu_map: */
for_each_cpu(i, cpu_map) {
struct sched_domain_topology_level *tl;
return ret;
}
-static cpumask_var_t *doms_cur; /* current sched domains */
-static int ndoms_cur; /* number of sched domains in 'doms_cur' */
-static struct sched_domain_attr *dattr_cur;
- /* attribues of custom domains in 'doms_cur' */
+/* Current sched domains: */
+static cpumask_var_t *doms_cur;
+
+/* Number of sched domains in 'doms_cur': */
+static int ndoms_cur;
+
+/* Attribues of custom domains in 'doms_cur' */
+static struct sched_domain_attr *dattr_cur;
/*
- * Special case: If a kmalloc of a doms_cur partition (array of
+ * Special case: If a kmalloc() of a doms_cur partition (array of
* cpumask) fails, then fallback to a single sched domain,
* as determined by the single cpumask fallback_doms.
*/
-static cpumask_var_t fallback_doms;
+static cpumask_var_t fallback_doms;
/*
* arch_update_cpu_topology lets virtualized architectures update the
- * cpu core maps. It is supposed to return 1 if the topology changed
+ * CPU core maps. It is supposed to return 1 if the topology changed
* or 0 if it stayed the same.
*/
int __weak arch_update_cpu_topology(void)
/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
- * For now this just excludes isolated cpus, but could be used to
+ * For now this just excludes isolated CPUs, but could be used to
* exclude other special cases in the future.
*/
static int init_sched_domains(const struct cpumask *cpu_map)
}
/*
- * Detach sched domains from a group of cpus specified in cpu_map
- * These cpus will now be attached to the NULL domain
+ * Detach sched domains from a group of CPUs specified in cpu_map
+ * These CPUs will now be attached to the NULL domain
*/
static void detach_destroy_domains(const struct cpumask *cpu_map)
{
{
struct sched_domain_attr tmp;
- /* fast path */
+ /* Fast path: */
if (!new && !cur)
return 1;
mutex_lock(&sched_domains_mutex);
- /* always unregister in case we don't destroy any domains */
+ /* Always unregister in case we don't destroy any domains: */
unregister_sched_domain_sysctl();
- /* Let architecture update cpu core mappings. */
+ /* Let the architecture update CPU core mappings: */
new_topology = arch_update_cpu_topology();
n = doms_new ? ndoms_new : 0;
- /* Destroy deleted domains */
+ /* Destroy deleted domains: */
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < n && !new_topology; j++) {
if (cpumask_equal(doms_cur[i], doms_new[j])
&& dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
- /* no match - a current sched domain not in new doms_new[] */
+ /* No match - a current sched domain not in new doms_new[] */
detach_destroy_domains(doms_cur[i]);
match1:
;
WARN_ON_ONCE(dattr_new);
}
- /* Build new domains */
+ /* Build new domains: */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < n && !new_topology; j++) {
if (cpumask_equal(doms_new[i], doms_cur[j])
&& dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
- /* no match - add a new doms_new */
+ /* No match - add a new doms_new */
build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
match2:
;
}
- /* Remember the new sched domains */
+ /* Remember the new sched domains: */
if (doms_cur != &fallback_doms)
free_sched_domains(doms_cur, ndoms_cur);
- kfree(dattr_cur); /* kfree(NULL) is safe */
+
+ kfree(dattr_cur);
doms_cur = doms_new;
dattr_cur = dattr_new;
ndoms_cur = ndoms_new;
mutex_unlock(&sched_domains_mutex);
}
-static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */
+/*
+ * used to mark begin/end of suspend/resume:
+ */
+static int num_cpus_frozen;
/*
* Update cpusets according to cpu_active mask. If cpusets are
* Put the rq online, if not already. This happens:
*
* 1) In the early boot process, because we build the real domains
- * after all cpus have been brought up.
+ * after all CPUs have been brought up.
*
* 2) At runtime, if cpuset_cpu_active() fails to rebuild the
* domains.
/*
* 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
+ * CPU masks are stable and all blatant races in the below code cannot
* happen.
*/
mutex_lock(&sched_domains_mutex);
}
#endif /* CONFIG_CPUMASK_OFFSTACK */
- init_rt_bandwidth(&def_rt_bandwidth,
- global_rt_period(), global_rt_runtime());
- init_dl_bandwidth(&def_dl_bandwidth,
- global_rt_period(), global_rt_runtime());
+ init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
+ init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());
#ifdef CONFIG_SMP
init_defrootdomain();
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
/*
- * How much cpu bandwidth does root_task_group get?
+ * How much CPU bandwidth does root_task_group get?
*
* In case of task-groups formed thr' the cgroup filesystem, it
- * gets 100% of the cpu resources in the system. This overall
- * system cpu resource is divided among the tasks of
+ * gets 100% of the CPU resources in the system. This overall
+ * system CPU resource is divided among the tasks of
* root_task_group and its child task-groups in a fair manner,
* based on each entity's (task or task-group's) weight
* (se->load.weight).
*
* In other words, if root_task_group has 10 tasks of weight
* 1024) and two child groups A0 and A1 (of weight 1024 each),
- * then A0's share of the cpu resource is:
+ * then A0's share of the CPU resource is:
*
* A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
*
void ___might_sleep(const char *file, int line, int preempt_offset)
{
- static unsigned long prev_jiffy; /* ratelimiting */
+ /* Ratelimiting timestamp: */
+ static unsigned long prev_jiffy;
+
unsigned long preempt_disable_ip;
- rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
+ /* WARN_ON_ONCE() by default, no rate limit required: */
+ rcu_sleep_check();
+
if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
!is_idle_task(current)) ||
system_state != SYSTEM_RUNNING || oops_in_progress)
return;
prev_jiffy = jiffies;
- /* Save this before calling printk(), since that will clobber it */
+ /* Save this before calling printk(), since that will clobber it: */
preempt_disable_ip = get_preempt_disable_ip(current);
printk(KERN_ERR
*/
/**
- * curr_task - return the current task for a given cpu.
+ * curr_task - return the current task for a given CPU.
* @cpu: the processor in question.
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
#ifdef CONFIG_IA64
/**
- * set_curr_task - set the current task for a given cpu.
+ * set_curr_task - set the current task for a given CPU.
* @cpu: the processor in question.
* @p: the task pointer to set.
*
* Description: This function must only be used when non-maskable interrupts
* are serviced on a separate stack. It allows the architecture to switch the
- * notion of the current task on a cpu in a non-blocking manner. This function
+ * notion of the current task on a CPU in a non-blocking manner. This function
* must be called with all CPU's synchronized, and interrupts disabled, the
* and caller must save the original value of the current task (see
* curr_task() above) and restore that value before reenabling interrupts and
spin_lock_irqsave(&task_group_lock, flags);
list_add_rcu(&tg->list, &task_groups);
- WARN_ON(!parent); /* root should already exist */
+ /* Root should already exist: */
+ WARN_ON(!parent);
tg->parent = parent;
INIT_LIST_HEAD(&tg->children);
/* rcu callback to free various structures associated with a task group */
static void sched_free_group_rcu(struct rcu_head *rhp)
{
- /* now it should be safe to free those cfs_rqs */
+ /* Now it should be safe to free those cfs_rqs: */
sched_free_group(container_of(rhp, struct task_group, rcu));
}
void sched_destroy_group(struct task_group *tg)
{
- /* wait for possible concurrent references to cfs_rqs complete */
+ /* Wait for possible concurrent references to cfs_rqs complete: */
call_rcu(&tg->rcu, sched_free_group_rcu);
}
{
unsigned long flags;
- /* end participation in shares distribution */
+ /* End participation in shares distribution: */
unregister_fair_sched_group(tg);
spin_lock_irqsave(&task_group_lock, flags);
mutex_lock(&mutex);
ret = proc_dointvec(table, write, buffer, lenp, ppos);
- /* make sure that internally we keep jiffies */
- /* also, writing zero resets timeslice to default */
+ /*
+ * Make sure that internally we keep jiffies.
+ * Also, writing zero resets the timeslice to default:
+ */
if (!ret && write) {
sched_rr_timeslice =
sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
cfs_b->quota = quota;
__refill_cfs_bandwidth_runtime(cfs_b);
- /* restart the period timer (if active) to handle new period expiry */
+
+ /* Restart the period timer (if active) to handle new period expiry: */
if (runtime_enabled)
start_cfs_bandwidth(cfs_b);
+
raw_spin_unlock_irq(&cfs_b->lock);
for_each_online_cpu(i) {
parent_quota = parent_b->hierarchical_quota;
/*
- * ensure max(child_quota) <= parent_quota, inherit when no
- * limit is set
+ * Ensure max(child_quota) <= parent_quota, inherit when no
+ * limit is set:
*/
if (quota == RUNTIME_INF)
quota = parent_quota;
.write_u64 = cpu_rt_period_write_uint,
},
#endif
- { } /* terminate */
+ { } /* Terminate */
};
struct cgroup_subsys cpu_cgrp_subsys = {
projects / linux.git / commitdiff