/**
* sys_sched_getparam - get the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the RT priority.
*
* Return: On success, 0 and the RT priority is in @param. Otherwise, an error
* code.
*/
SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
struct sched_param lp = { .sched_priority = 0 };
struct task_struct *p;
int retval;
if (!param || pid < 0)
return -EINVAL;
rcu_read_lock();
p = find_process_by_pid(pid);
retval = -ESRCH;
if (!p)
goto out_unlock;
retval = security_task_getscheduler(p);
if (retval)
goto out_unlock;
if (task_has_rt_policy(p))
lp.sched_priority = p->rt_priority;
rcu_read_unlock();
/*
* This one might sleep, we cannot do it with a spinlock held ...
*/
retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
return retval;
out_unlock:
rcu_read_unlock();
return retval;
}
static int sched_read_attr(struct sched_attr __user *uattr,
struct sched_attr *attr,
unsigned int usize)
{
int ret;
if (!access_ok(VERIFY_WRITE, uattr, usize))
return -EFAULT;
/*
* If we're handed a smaller struct than we know of,
* ensure all the unknown bits are 0 - i.e. old
* user-space does not get uncomplete information.
*/
if (usize < sizeof(*attr)) {
unsigned char *addr;
unsigned char *end;
addr = (void *)attr + usize;
end = (void *)attr + sizeof(*attr);
for (; addr < end; addr++) {
if (*addr)
return -EFBIG;
}
attr->size = usize;
}
ret = copy_to_user(uattr, attr, attr->size);
if (ret)
return -EFAULT;
return 0;
}
/**
* sys_sched_getattr - similar to sched_getparam, but with sched_attr
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
* @size: sizeof(attr) for fwd/bwd comp.
* @flags: for future extension.
*/
SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
unsigned int, size, unsigned int, flags)
{
struct sched_attr attr = {
.size = sizeof(struct sched_attr),
};
struct task_struct *p;
int retval;
if (!uattr || pid < 0 || size > PAGE_SIZE ||
size < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;
rcu_read_lock();
p = find_process_by_pid(pid);
retval = -ESRCH;
if (!p)
goto out_unlock;
retval = security_task_getscheduler(p);
if (retval)
goto out_unlock;
attr.sched_policy = p->policy;
if (p->sched_reset_on_fork)
attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
if (task_has_dl_policy(p))
__getparam_dl(p, &attr);
else if (task_has_rt_policy(p))
attr.sched_priority = p->rt_priority;
else
attr.sched_nice = task_nice(p);
rcu_read_unlock();
retval = sched_read_attr(uattr, &attr, size);
return retval;
out_unlock:
rcu_read_unlock();
return retval;
}
long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
cpumask_var_t cpus_allowed, new_mask;
struct task_struct *p;
int retval;
rcu_read_lock();
p = find_process_by_pid(pid);
if (!p) {
rcu_read_unlock();
return -ESRCH;
}
/* Prevent p going away */
get_task_struct(p);
rcu_read_unlock();
if (p->flags & PF_NO_SETAFFINITY) {
retval = -EINVAL;
goto out_put_task;
}
if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
retval = -ENOMEM;
goto out_put_task;
}
if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
retval = -ENOMEM;
goto out_free_cpus_allowed;
}
retval = -EPERM;
if (!check_same_owner(p)) {
rcu_read_lock();
if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
rcu_read_unlock();
goto out_free_new_mask;
}
rcu_read_unlock();
}
retval = security_task_setscheduler(p);
if (retval)
goto out_free_new_mask;
cpuset_cpus_allowed(p, cpus_allowed);
cpumask_and(new_mask, in_mask, cpus_allowed);
/*
* Since bandwidth control happens on root_domain basis,
* if admission test is enabled, we only admit -deadline
* tasks allowed to run on all the CPUs in the task's
* root_domain.
*/
#ifdef CONFIG_SMP
if (task_has_dl_policy(p) && dl_bandwidth_enabled()) {
rcu_read_lock();
if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) {
retval = -EBUSY;
rcu_read_unlock();
goto out_free_new_mask;
}
rcu_read_unlock();
}
#endif
again:
retval = set_cpus_allowed_ptr(p, new_mask);
if (!retval) {
cpuset_cpus_allowed(p, cpus_allowed);
if (!cpumask_subset(new_mask, cpus_allowed)) {
/*
* We must have raced with a concurrent cpuset
* update. Just reset the cpus_allowed to the
* cpuset's cpus_allowed
*/
cpumask_copy(new_mask, cpus_allowed);
goto again;
}
}
out_free_new_mask:
free_cpumask_var(new_mask);
out_free_cpus_allowed:
free_cpumask_var(cpus_allowed);
out_put_task:
put_task_struct(p);
return retval;
}
static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
struct cpumask *new_mask)
{
if (len < cpumask_size())
cpumask_clear(new_mask);
else if (len > cpumask_size())
len = cpumask_size();
return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
}
/**
* 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
*
* Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
unsigned long __user *, user_mask_ptr)
{
cpumask_var_t new_mask;
int retval;
if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
return -ENOMEM;
retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
if (retval == 0)
retval = sched_setaffinity(pid, new_mask);
free_cpumask_var(new_mask);
return retval;
}
long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
struct task_struct *p;
unsigned long flags;
int retval;
rcu_read_lock();
retval = -ESRCH;
p = find_process_by_pid(pid);
if (!p)
goto out_unlock;
retval = security_task_getscheduler(p);
if (retval)
goto out_unlock;
raw_spin_lock_irqsave(&p->pi_lock, flags);
cpumask_and(mask, &p->cpus_allowed, cpu_active_mask);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
out_unlock:
rcu_read_unlock();
return retval;
}
/**
* 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
*
* Return: 0 on success. An error code otherwise.
*/
SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
unsigned long __user *, user_mask_ptr)
{
int ret;
cpumask_var_t mask;
if ((len * BITS_PER_BYTE) < nr_cpu_ids)
return -EINVAL;
if (len & (sizeof(unsigned long)-1))
return -EINVAL;
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
ret = sched_getaffinity(pid, mask);
if (ret == 0) {
size_t retlen = min_t(size_t, len, cpumask_size());
if (copy_to_user(user_mask_ptr, mask, retlen))
ret = -EFAULT;
else
ret = retlen;
}
free_cpumask_var(mask);
return ret;
}
/**
* sys_sched_yield - yield the current processor to other threads.
*
* This function yields the current CPU to other tasks. If there are no
* other threads running on this CPU then this function will return.
*
* Return: 0.
*/
SYSCALL_DEFINE0(sched_yield)
{
struct rq *rq = this_rq_lock();
schedstat_inc(rq, yld_count);
current->sched_class->yield_task(rq);
/*
* Since we are going to call schedule() anyway, there's
* no need to preempt or enable interrupts:
*/
__release(rq->lock);
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
do_raw_spin_unlock(&rq->lock);
sched_preempt_enable_no_resched();
schedule();
return 0;
}
int __sched _cond_resched(void)
{
if (should_resched(0)) {
preempt_schedule_common();
return 1;
}
return 0;
}
EXPORT_SYMBOL(_cond_resched);
/*
* __cond_resched_lock() - if a reschedule is pending, drop the given lock,
* call schedule, and on return reacquire the lock.
*
* This works OK both with and without CONFIG_PREEMPT. We do strange low-level
* operations here to prevent schedule() from being called twice (once via
* spin_unlock(), once by hand).
*/
int __cond_resched_lock(spinlock_t *lock)
{
int resched = should_resched(PREEMPT_LOCK_OFFSET);
int ret = 0;
lockdep_assert_held(lock);
if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
if (resched)
preempt_schedule_common();
else
cpu_relax();
ret = 1;
spin_lock(lock);
}
return ret;
}
EXPORT_SYMBOL(__cond_resched_lock);
int __sched __cond_resched_softirq(void)
{
BUG_ON(!in_softirq());
if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
local_bh_enable();
preempt_schedule_common();
local_bh_disable();
return 1;
}
return 0;
}
EXPORT_SYMBOL(__cond_resched_softirq);
/**
* yield - yield the current processor to other threads.
*
* Do not ever use this function, there's a 99% chance you're doing it wrong.
*
* The scheduler is at all times free to pick the calling task as the most
* eligible task to run, if removing the yield() call from your code breaks
* it, its already broken.
*
* Typical broken usage is:
*
* while (!event)
* 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
* happen. Never use yield() as a progress guarantee!!
*
* If you want to use yield() to wait for something, use wait_event().
* If you want to use yield() to be 'nice' for others, use cond_resched().
* If you still want to use yield(), do not!
*/
void __sched yield(void)
{
set_current_state(TASK_RUNNING);
sys_sched_yield();
}
EXPORT_SYMBOL(yield);
/**
* yield_to - yield the current processor to another thread in
* your thread group, or accelerate that thread toward the
* processor it's on.
* @p: target task
* @preempt: whether task preemption is allowed or not
*
* It's the caller's job to ensure that the target task struct
* can't go away on us before we can do any checks.
*
* Return:
* true (>0) if we indeed boosted the target task.
* false (0) if we failed to boost the target.
* -ESRCH if there's no task to yield to.
*/
int __sched yield_to(struct task_struct *p, bool preempt)
{
struct task_struct *curr = current;
struct rq *rq, *p_rq;
unsigned long flags;
int yielded = 0;
local_irq_save(flags);
rq = this_rq();
again:
p_rq = task_rq(p);
/*
* If we're the only runnable task on the rq and target rq also
* has only one task, there's absolutely no point in yielding.
*/
if (rq->nr_running == 1 && p_rq->nr_running == 1) {
yielded = -ESRCH;
goto out_irq;
}
double_rq_lock(rq, p_rq);
if (task_rq(p) != p_rq) {
double_rq_unlock(rq, p_rq);
goto again;
}
if (!curr->sched_class->yield_to_task)
goto out_unlock;
if (curr->sched_class != p->sched_class)
goto out_unlock;
if (task_running(p_rq, p) || p->state)
goto out_unlock;
yielded = curr->sched_class->yield_to_task(rq, p, preempt);
if (yielded) {
schedstat_inc(rq, yld_count);
/*
* Make p's CPU reschedule; pick_next_entity takes care of
* fairness.
*/
if (preempt && rq != p_rq)
resched_curr(p_rq);
}
out_unlock:
double_rq_unlock(rq, p_rq);
out_irq:
local_irq_restore(flags);
if (yielded > 0)
schedule();
return yielded;
}
EXPORT_SYMBOL_GPL(yield_to);
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
*/
long __sched io_schedule_timeout(long timeout)
{
int old_iowait = current->in_iowait;
struct rq *rq;
long ret;
current->in_iowait = 1;
blk_schedule_flush_plug(current);
delayacct_blkio_start();
rq = raw_rq();
atomic_inc(&rq->nr_iowait);
ret = schedule_timeout(timeout);
current->in_iowait = old_iowait;
atomic_dec(&rq->nr_iowait);
delayacct_blkio_end();
return ret;
}
EXPORT_SYMBOL(io_schedule_timeout);
/**
* sys_sched_get_priority_max - return maximum RT priority.
* @policy: scheduling class.
*
* Return: On success, this syscall returns the maximum
* rt_priority that can be used by a given scheduling class.
* On failure, a negative error code is returned.
*/
SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
{
int ret = -EINVAL;
switch (policy) {
case SCHED_FIFO:
case SCHED_RR:
ret = MAX_USER_RT_PRIO-1;
break;
case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
ret = 0;
break;
}
return ret;
}
/**
* sys_sched_get_priority_min - return minimum RT priority.
* @policy: scheduling class.
*
* Return: On success, this syscall returns the minimum
* rt_priority that can be used by a given scheduling class.
* On failure, a negative error code is returned.
*/
SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
{
int ret = -EINVAL;
switch (policy) {
case SCHED_FIFO:
case SCHED_RR:
ret = 1;
break;
case SCHED_DEADLINE:
case SCHED_NORMAL:
case SCHED_BATCH:
case SCHED_IDLE:
ret = 0;
}
return ret;
}
/**
* sys_sched_rr_get_interval - return the default timeslice of a process.
* @pid: pid of the process.
* @interval: userspace pointer to the timeslice value.
*
* this syscall writes the default timeslice value of a given process
* into the user-space timespec buffer. A value of '0' means infinity.
*
* Return: On success, 0 and the timeslice is in @interval. Otherwise,
* an error code.
*/
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
struct timespec __user *, interval)
{
struct task_struct *p;
unsigned int time_slice;
unsigned long flags;
struct rq *rq;
int retval;
struct timespec t;
if (pid < 0)
return -EINVAL;
retval = -ESRCH;
rcu_read_lock();
p = find_process_by_pid(pid);
if (!p)
goto out_unlock;
retval = security_task_getscheduler(p);
if (retval)
goto out_unlock;
rq = task_rq_lock(p, &flags);
time_slice = 0;
if (p->sched_class->get_rr_interval)
time_slice = p->sched_class->get_rr_interval(rq, p);
task_rq_unlock(rq, p, &flags);
rcu_read_unlock();
jiffies_to_timespec(time_slice, &t);
retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
return retval;
out_unlock:
rcu_read_unlock();
return retval;
}
static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
void sched_show_task(struct task_struct *p)
{
unsigned long free = 0;
int ppid;
unsigned long state = p->state;
if (state)
state = __ffs(state) + 1;
printk(KERN_INFO "%-15.15s %c", p->comm,
state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if BITS_PER_LONG == 32
if (state == TASK_RUNNING)
printk(KERN_CONT " running ");
else
printk(KERN_CONT " %08lx ", thread_saved_pc(p));
#else
if (state == TASK_RUNNING)
printk(KERN_CONT " running task ");
else
printk(KERN_CONT " %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
free = stack_not_used(p);
#endif
ppid = 0;
rcu_read_lock();
if (pid_alive(p))
ppid = task_pid_nr(rcu_dereference(p->real_parent));
rcu_read_unlock();
printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
task_pid_nr(p), ppid,
(unsigned long)task_thread_info(p)->flags);
print_worker_info(KERN_INFO, p);
show_stack(p, NULL);
}
void show_state_filter(unsigned long state_filter)
{
struct task_struct *g, *p;
#if BITS_PER_LONG == 32
printk(KERN_INFO
" task PC stack pid father\n");
#else
printk(KERN_INFO
" task PC stack pid father\n");
#endif
rcu_read_lock();
for_each_process_thread(g, p) {
/*
* reset the NMI-timeout, listing all files on a slow
* console might take a lot of time:
*/
touch_nmi_watchdog();
if (!state_filter || (p->state & state_filter))
sched_show_task(p);
}
touch_all_softlockup_watchdogs();
#ifdef CONFIG_SCHED_DEBUG
sysrq_sched_debug_show();
#endif
rcu_read_unlock();
/*
* Only show locks if all tasks are dumped:
*/
if (!state_filter)
debug_show_all_locks();
}
void init_idle_bootup_task(struct task_struct *idle)
{
idle->sched_class = &idle_sched_class;
}
/**
* init_idle - set up an idle thread for a given CPU
* @idle: task in question
* @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.
*/
void init_idle(struct task_struct *idle, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
__sched_fork(0, idle);
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
do_set_cpus_allowed(idle, cpumask_of(cpu));
/*
* 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
* lockdep check in task_group() will fail.
*
* Similar case to sched_fork(). / Alternatively we could
* use task_rq_lock() here and obtain the other rq->lock.
*
* Silence PROVE_RCU
*/
rcu_read_lock();
__set_task_cpu(idle, cpu);
rcu_read_unlock();
rq->curr = rq->idle = idle;
idle->on_rq = TASK_ON_RQ_QUEUED;
#if defined(CONFIG_SMP)
idle->on_cpu = 1;
#endif
raw_spin_unlock_irqrestore(&rq->lock, flags);
/* Set the preempt count _outside_ the spinlocks! */
init_idle_preempt_count(idle, cpu);
/*
* The idle tasks have their own, simple scheduling class:
*/
idle->sched_class = &idle_sched_class;
ftrace_graph_init_idle_task(idle, cpu);
vtime_init_idle(idle, cpu);
#if defined(CONFIG_SMP)
sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
#endif
}
int cpuset_cpumask_can_shrink(const struct cpumask *cur,
const struct cpumask *trial)
{
int ret = 1, trial_cpus;
struct dl_bw *cur_dl_b;
unsigned long flags;
if (!cpumask_weight(cur))
return ret;
rcu_read_lock_sched();
cur_dl_b = dl_bw_of(cpumask_any(cur));
trial_cpus = cpumask_weight(trial);
raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
if (cur_dl_b->bw != -1 &&
cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
ret = 0;
raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
rcu_read_unlock_sched();
return ret;
}
int task_can_attach(struct task_struct *p,
const struct cpumask *cs_cpus_allowed)
{
int ret = 0;
/*
* Kthreads which disallow setaffinity shouldn't be moved
* 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
* success of set_cpus_allowed_ptr() on all attached tasks
* before cpus_allowed may be changed.
*/
if (p->flags & PF_NO_SETAFFINITY) {
ret = -EINVAL;
goto out;
}
#ifdef CONFIG_SMP
if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
cs_cpus_allowed)) {
unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
cs_cpus_allowed);
struct dl_bw *dl_b;
bool overflow;
int cpus;
unsigned long flags;
rcu_read_lock_sched();
dl_b = dl_bw_of(dest_cpu);
raw_spin_lock_irqsave(&dl_b->lock, flags);
cpus = dl_bw_cpus(dest_cpu);
overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
if (overflow)
ret = -EBUSY;
else {
/*
* We reserve space for this task in the destination
* root_domain, as we can't fail after this point.
* We will free resources in the source root_domain
* later on (see set_cpus_allowed_dl()).
*/
__dl_add(dl_b, p->dl.dl_bw);
}
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
rcu_read_unlock_sched();
}
#endif
out:
return ret;
}
#ifdef CONFIG_SMP
#ifdef CONFIG_NUMA_BALANCING
/* Migrate current task p to target_cpu */
int migrate_task_to(struct task_struct *p, int target_cpu)
{
struct migration_arg arg = { p, target_cpu };
int curr_cpu = task_cpu(p);
if (curr_cpu == target_cpu)
return 0;
if (!cpumask_test_cpu(target_cpu, tsk_cpus_allowed(p)))
return -EINVAL;
/* TODO: This is not properly updating schedstats */
trace_sched_move_numa(p, curr_cpu, target_cpu);
return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
}
/*
* Requeue a task on a given node and accurately track the number of NUMA
* tasks on the runqueues
*/
void sched_setnuma(struct task_struct *p, int nid)
{
struct rq *rq;
unsigned long flags;
bool queued, running;
rq = task_rq_lock(p, &flags);
queued = task_on_rq_queued(p);
running = task_current(rq, p);
if (queued)
dequeue_task(rq, p, 0);
if (running)
put_prev_task(rq, p);
p->numa_preferred_nid = nid;
if (running)
p->sched_class->set_curr_task(rq);
if (queued)
enqueue_task(rq, p, 0);
task_rq_unlock(rq, p, &flags);
}
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_HOTPLUG_CPU
/*
* Ensures that the idle task is using init_mm right before its cpu goes
* offline.
*/
void idle_task_exit(void)
{
struct mm_struct *mm = current->active_mm;
BUG_ON(cpu_online(smp_processor_id()));
if (mm != &init_mm) {
switch_mm(mm, &init_mm, current);
finish_arch_post_lock_switch();
}
mmdrop(mm);
}
/*
* Since this CPU is going 'away' for a while, fold any nr_active delta
* we might have. Assumes we're called after migrate_tasks() so that the
* nr_active count is stable.
*
* Also see the comment "Global load-average calculations".
*/
static void calc_load_migrate(struct rq *rq)
{
long delta = calc_load_fold_active(rq);
if (delta)
atomic_long_add(delta, &calc_load_tasks);
}
static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
{
}
static const struct sched_class fake_sched_class = {
.put_prev_task = put_prev_task_fake,
};
static struct task_struct fake_task = {
/*
* Avoid pull_{rt,dl}_task()
*/
.prio = MAX_PRIO + 1,
.sched_class = &fake_sched_class,
};
/*
* Migrate all tasks from the rq, sleeping tasks will be migrated by
* try_to_wake_up()->select_task_rq().
*
* Called with rq->lock held even though we'er in stop_machine() and
* there's no concurrency possible, we hold the required locks anyway
* because of lock validation efforts.
*/
static void migrate_tasks(struct rq *dead_rq)
{
struct rq *rq = dead_rq;
struct task_struct *next, *stop = rq->stop;
int dest_cpu;
/*
* Fudge the rq selection such that the below task selection loop
* doesn't get stuck on the currently eligible stop task.
*
* We're currently inside stop_machine() and the rq is either stuck
* in the stop_machine_cpu_stop() loop, or we're executing this code,
* either way we should never end up calling schedule() until we're
* done here.
*/
rq->stop = NULL;
/*
* put_prev_task() and pick_next_task() sched
* class method both need to have an up-to-date
* value of rq->clock[_task]
*/
update_rq_clock(rq);
for (;;) {
/*
* There's this thread running, bail when that's the only
* remaining thread.
*/
if (rq->nr_running == 1)
break;
/*
* Ensure rq->lock covers the entire task selection
* until the migration.
*/
lockdep_pin_lock(&rq->lock);
next = pick_next_task(rq, &fake_task);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);
/* Find suitable destination for @next, with force if needed. */
dest_cpu = select_fallback_rq(dead_rq->cpu, next);
lockdep_unpin_lock(&rq->lock);
rq = __migrate_task(rq, next, dest_cpu);
if (rq != dead_rq) {
raw_spin_unlock(&rq->lock);
rq = dead_rq;
raw_spin_lock(&rq->lock);
}
}
rq->stop = stop;
}
#endif /* CONFIG_HOTPLUG_CPU */
#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
static struct ctl_table sd_ctl_dir[] = {
{
.procname = "sched_domain",
.mode = 0555,
},
{}
};
static struct ctl_table sd_ctl_root[] = {
{
.procname = "kernel",
.mode = 0555,
.child = sd_ctl_dir,
},
{}
};
static struct ctl_table *sd_alloc_ctl_entry(int n)
{
struct ctl_table *entry =
kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
return entry;
}
static void sd_free_ctl_entry(struct ctl_table **tablep)
{
struct ctl_table *entry;
/*
* In the intermediate directories, both the child directory and
* procname are dynamically allocated and could fail but the mode
* will always be set. In the lowest directory the names are
* static strings and all have proc handlers.
*/
for (entry = *tablep; entry->mode; entry++) {
if (entry->child)
sd_free_ctl_entry(&entry->child);
if (entry->proc_handler == NULL)
kfree(entry->procname);
}
kfree(*tablep);
*tablep = NULL;
}
static int min_load_idx = 0;
static int max_load_idx = CPU_LOAD_IDX_MAX-1;
static void
set_table_entry(struct ctl_table *entry,
const char *procname, void *data, int maxlen,
umode_t mode, proc_handler *proc_handler,
bool load_idx)
{
entry->procname = procname;
entry->data = data;
entry->maxlen = maxlen;
entry->mode = mode;
entry->proc_handler = proc_handler;
if (load_idx) {
entry->extra1 = &min_load_idx;
entry->extra2 = &max_load_idx;
}
}
static struct ctl_table *
sd_alloc_ctl_domain_table(struct sched_domain *sd)
{
struct ctl_table *table = sd_alloc_ctl_entry(14);
if (table == NULL)
return NULL;
set_table_entry(&table[0], "min_interval", &sd->min_interval,
sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[1], "max_interval", &sd->max_interval,
sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[9], "cache_nice_tries",
&sd->cache_nice_tries,
sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[10], "flags", &sd->flags,
sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[11], "max_newidle_lb_cost",
&sd->max_newidle_lb_cost,
sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[12], "name", sd->name,
CORENAME_MAX_SIZE, 0444, proc_dostring, false);
/* &table[13] is terminator */
return table;
}
static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu)
{
struct ctl_table *entry, *table;
struct sched_domain *sd;
int domain_num = 0, i;
char buf[32];
for_each_domain(cpu, sd)
domain_num++;
entry = table = sd_alloc_ctl_entry(domain_num + 1);
if (table == NULL)
return NULL;
i = 0;
for_each_domain(cpu, sd) {
snprintf(buf, 32, "domain%d", i);
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->mode = 0555;
entry->child = sd_alloc_ctl_domain_table(sd);
entry++;
i++;
}
return table;
}
static struct ctl_table_header *sd_sysctl_header;
static void register_sched_domain_sysctl(void)
{
int i, cpu_num = num_possible_cpus();
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
char buf[32];
WARN_ON(sd_ctl_dir[0].child);
sd_ctl_dir[0].child = entry;
if (entry == NULL)
return;
for_each_possible_cpu(i) {
snprintf(buf, 32, "cpu%d", i);
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->mode = 0555;
entry->child = sd_alloc_ctl_cpu_table(i);
entry++;
}
WARN_ON(sd_sysctl_header);
sd_sysctl_header = register_sysctl_table(sd_ctl_root);
}
/* may be called multiple times per register */
static void unregister_sched_domain_sysctl(void)
{
if (sd_sysctl_header)
unregister_sysctl_table(sd_sysctl_header);
sd_sysctl_header = NULL;
if (sd_ctl_dir[0].child)
sd_free_ctl_entry(&sd_ctl_dir[0].child);
}
#else
static void register_sched_domain_sysctl(void)
{
}
static void unregister_sched_domain_sysctl(void)
{
}
#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */
static void set_rq_online(struct rq *rq)
{
if (!rq->online) {
const struct sched_class *class;
cpumask_set_cpu(rq->cpu, rq->rd->online);
rq->online = 1;
for_each_class(class) {
if (class->rq_online)
class->rq_online(rq);
}
}
}
static void set_rq_offline(struct rq *rq)
{
if (rq->online) {
const struct sched_class *class;
for_each_class(class) {
if (class->rq_offline)
class->rq_offline(rq);
}
cpumask_clear_cpu(rq->cpu, rq->rd->online);
rq->online = 0;
}
}
/*
* migration_call - callback that gets triggered when a CPU is added.
* Here we can start up the necessary migration thread for the new CPU.
*/
static int
migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
int cpu = (long)hcpu;
unsigned long flags;
struct rq *rq = cpu_rq(cpu);
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
rq->calc_load_update = calc_load_update;
break;
case CPU_ONLINE:
/* Update our root-domain */
raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_online(rq);
}
raw_spin_unlock_irqrestore(&rq->lock, flags);
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DYING:
sched_ttwu_pending();
/* Update our root-domain */
raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
}
migrate_tasks(rq);
BUG_ON(rq->nr_running != 1); /* the migration thread */
raw_spin_unlock_irqrestore(&rq->lock, flags);
break;
case CPU_DEAD:
calc_load_migrate(rq);
break;
#endif
}
update_max_interval();
return NOTIFY_OK;
}
/*
* Register at high priority so that task migration (migrate_all_tasks)
* happens before everything else. This has to be lower priority than
* the notifier in the perf_event subsystem, though.
*/
static struct notifier_block migration_notifier = {
.notifier_call = migration_call,
.priority = CPU_PRI_MIGRATION,
};
static void set_cpu_rq_start_time(void)
{
int cpu = smp_processor_id();
struct rq *rq = cpu_rq(cpu);
rq->age_stamp = sched_clock_cpu(cpu);
}
static int sched_cpu_active(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_STARTING:
set_cpu_rq_start_time();
return NOTIFY_OK;
case CPU_ONLINE:
/*
* At this point a starting CPU has marked itself as online via
* set_cpu_online(). But it might not yet have marked itself
* as active, which is essential from here on.
*
* Thus, fall-through and help the starting CPU along.
*/
case CPU_DOWN_FAILED:
set_cpu_active((long)hcpu, true);
return NOTIFY_OK;
default:
return NOTIFY_DONE;
}
}
static int sched_cpu_inactive(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
set_cpu_active((long)hcpu, false);
return NOTIFY_OK;
default:
return NOTIFY_DONE;
}
}
static int __init migration_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err;
/* Initialize migration for the boot CPU */
err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
BUG_ON(err == NOTIFY_BAD);
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
/* Register cpu active notifiers */
cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE);
cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE);
return 0;
}
early_initcall(migration_init);
static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
#ifdef CONFIG_SCHED_DEBUG
static __read_mostly int sched_debug_enabled;
static int __init sched_debug_setup(char *str)
{
sched_debug_enabled = 1;
return 0;
}
early_param("sched_debug", sched_debug_setup);
static inline bool sched_debug(void)
{
return sched_debug_enabled;
}
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask)
{
struct sched_group *group = sd->groups;
cpumask_clear(groupmask);
printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
if (!(sd->flags & SD_LOAD_BALANCE)) {
printk("does not load-balance\n");
if (sd->parent)
printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
" has parent");
return -1;
}
printk(KERN_CONT "span %*pbl level %s\n",
cpumask_pr_args(sched_domain_span(sd)), sd->name);
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
printk(KERN_ERR "ERROR: domain->span does not contain "
"CPU%d\n", cpu);
}
if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
printk(KERN_ERR "ERROR: domain->groups does not contain"
" CPU%d\n", cpu);
}
printk(KERN_DEBUG "%*s groups:", level + 1, "");
do {
if (!group) {
printk("\n");
printk(KERN_ERR "ERROR: group is NULL\n");
break;
}
if (!cpumask_weight(sched_group_cpus(group))) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: empty group\n");
break;
}
if (!(sd->flags & SD_OVERLAP) &&
cpumask_intersects(groupmask, sched_group_cpus(group))) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: repeated CPUs\n");
break;
}
cpumask_or(groupmask, groupmask, sched_group_cpus(group));
printk(KERN_CONT " %*pbl",
cpumask_pr_args(sched_group_cpus(group)));
if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
printk(KERN_CONT " (cpu_capacity = %d)",
group->sgc->capacity);
}
group = group->next;
} while (group != sd->groups);
printk(KERN_CONT "\n");
if (!cpumask_equal(sched_domain_span(sd), groupmask))
printk(KERN_ERR "ERROR: groups don't span domain->span\n");
if (sd->parent &&
!cpumask_subset(groupmask, sched_domain_span(sd->parent)))
printk(KERN_ERR "ERROR: parent span is not a superset "
"of domain->span\n");
return 0;
}
static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
int level = 0;
if (!sched_debug_enabled)
return;
if (!sd) {
printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
return;
}
printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
for (;;) {
if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
break;
level++;
sd = sd->parent;
if (!sd)
break;
}
}
#else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0)
static inline bool sched_debug(void)
{
return false;
}
#endif /* CONFIG_SCHED_DEBUG */
static int sd_degenerate(struct sched_domain *sd)
{
if (cpumask_weight(sched_domain_span(sd)) == 1)
return 1;
/* Following flags need at least 2 groups */
if (sd->flags & (SD_LOAD_BALANCE |
SD_BALANCE_NEWIDLE |
SD_BALANCE_FORK |
SD_BALANCE_EXEC |
SD_SHARE_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
SD_SHARE_POWERDOMAIN)) {
if (sd->groups != sd->groups->next)
return 0;
}
/* Following flags don't use groups */
if (sd->flags & (SD_WAKE_AFFINE))
return 0;
return 1;
}
static int
sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
{
unsigned long cflags = sd->flags, pflags = parent->flags;
if (sd_degenerate(parent))
return 1;
if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
return 0;
/* Flags needing groups don't count if only 1 group in parent */
if (parent->groups == parent->groups->next) {
pflags &= ~(SD_LOAD_BALANCE |
SD_BALANCE_NEWIDLE |
SD_BALANCE_FORK |
SD_BALANCE_EXEC |
SD_SHARE_CPUCAPACITY |
SD_SHARE_PKG_RESOURCES |
SD_PREFER_SIBLING |
SD_SHARE_POWERDOMAIN);
if (nr_node_ids == 1)
pflags &= ~SD_SERIALIZE;
}
if (~cflags & pflags)
return 0;
return 1;
}
static void free_rootdomain(struct rcu_head *rcu)
{
struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
cpupri_cleanup(&rd->cpupri);
cpudl_cleanup(&rd->cpudl);
free_cpumask_var(rd->dlo_mask);
free_cpumask_var(rd->rto_mask);
free_cpumask_var(rd->online);
free_cpumask_var(rd->span);
kfree(rd);
}
static void rq_attach_root(struct rq *rq, struct root_domain *rd)
{
struct root_domain *old_rd = NULL;
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
old_rd = rq->rd;
if (cpumask_test_cpu(rq->cpu, old_rd->online))
set_rq_offline(rq);
cpumask_clear_cpu(rq->cpu, old_rd->span);
/*
* If we dont want to free the old_rd yet then
* set old_rd to NULL to skip the freeing later
* in this function:
*/
if (!atomic_dec_and_test(&old_rd->refcount))
old_rd = NULL;
}
atomic_inc(&rd->refcount);
rq->rd = rd;
cpumask_set_cpu(rq->cpu, rd->span);
if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
set_rq_online(rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
if (old_rd)
call_rcu_sched(&old_rd->rcu, free_rootdomain);
}
static int init_rootdomain(struct root_domain *rd)
{
memset(rd, 0, sizeof(*rd));
if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
goto out;
if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
goto free_span;
if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
goto free_online;
if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
goto free_dlo_mask;
init_dl_bw(&rd->dl_bw);
if (cpudl_init(&rd->cpudl) != 0)
goto free_dlo_mask;
if (cpupri_init(&rd->cpupri) != 0)
goto free_rto_mask;
return 0;
free_rto_mask:
free_cpumask_var(rd->rto_mask);
free_dlo_mask:
free_cpumask_var(rd->dlo_mask);
free_online:
free_cpumask_var(rd->online);
free_span:
free_cpumask_var(rd->span);
out:
return -ENOMEM;
}
/*
* 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;
static void init_defrootdomain(void)
{
init_rootdomain(&def_root_domain);
atomic_set(&def_root_domain.refcount, 1);
}
static struct root_domain *alloc_rootdomain(void)
{
struct root_domain *rd;
rd = kmalloc(sizeof(*rd), GFP_KERNEL);
if (!rd)
return NULL;
if (init_rootdomain(rd) != 0) {
kfree(rd);
return NULL;
}
return rd;
}
static void free_sched_groups(struct sched_group *sg, int free_sgc)
{
struct sched_group *tmp, *first;
if (!sg)
return;
first = sg;
do {
tmp = sg->next;
if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
kfree(sg->sgc);
kfree(sg);
sg = tmp;
} while (sg != first);
}
static void free_sched_domain(struct rcu_head *rcu)
{
struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
/*
* If its an overlapping domain it has private groups, iterate and
* nuke them all.
*/
if (sd->flags & SD_OVERLAP) {
free_sched_groups(sd->groups, 1);
} else if (atomic_dec_and_test(&sd->groups->ref)) {
kfree(sd->groups->sgc);
kfree(sd->groups);
}
kfree(sd);
}
static void destroy_sched_domain(struct sched_domain *sd, int cpu)
{
call_rcu(&sd->rcu, free_sched_domain);
}
static void destroy_sched_domains(struct sched_domain *sd, int cpu)
{
for (; sd; sd = sd->parent)
destroy_sched_domain(sd, cpu);
}
/*
* Keep a special pointer to the highest sched_domain that has
* 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
* the cpumask of the domain), this allows us to quickly tell if
* 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);
DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
DEFINE_PER_CPU(struct sched_domain *, sd_busy);
DEFINE_PER_CPU(struct sched_domain *, sd_asym);
static void update_top_cache_domain(int cpu)
{
struct sched_domain *sd;
struct sched_domain *busy_sd = NULL;
int id = cpu;
int size = 1;
sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
if (sd) {
id = cpumask_first(sched_domain_span(sd));
size = cpumask_weight(sched_domain_span(sd));
busy_sd = sd->parent; /* sd_busy */
}
rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);
rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
per_cpu(sd_llc_size, cpu) = size;
per_cpu(sd_llc_id, cpu) = id;
sd = lowest_flag_domain(cpu, SD_NUMA);
rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
}
/*
* Attach the domain 'sd' to 'cpu' as its base domain. Callers must
* hold the hotplug lock.
*/
static void
cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct sched_domain *tmp;
/* Remove the sched domains which do not contribute to scheduling. */
for (tmp = sd; tmp; ) {
struct sched_domain *parent = tmp->parent;
if (!parent)
break;
if (sd_parent_degenerate(tmp, parent)) {
tmp->parent = parent->parent;
if (parent->parent)
parent->parent->child = tmp;
/*
* Transfer SD_PREFER_SIBLING down in case of a
* degenerate parent; the spans match for this
* so the property transfers.
*/
if (parent->flags & SD_PREFER_SIBLING)
tmp->flags |= SD_PREFER_SIBLING;
destroy_sched_domain(parent, cpu);
} else
tmp = tmp->parent;
}
if (sd && sd_degenerate(sd)) {
tmp = sd;
sd = sd->parent;
destroy_sched_domain(tmp, cpu);
if (sd)
sd->child = NULL;
}
sched_domain_debug(sd, cpu);
rq_attach_root(rq, rd);
tmp = rq->sd;
rcu_assign_pointer(rq->sd, sd);
destroy_sched_domains(tmp, cpu);
update_top_cache_domain(cpu);
}
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
alloc_bootmem_cpumask_var(&cpu_isolated_map);
cpulist_parse(str, cpu_isolated_map);
return 1;
}
__setup("isolcpus=", isolated_cpu_setup);
struct s_data {
struct sched_domain ** __percpu sd;
struct root_domain *rd;
};
enum s_alloc {
sa_rootdomain,
sa_sd,
sa_sd_storage,
sa_none,
};
/*
* Build an iteration mask that can exclude certain CPUs from the upwards
* domain traversal.
*
* Asymmetric node setups can result in situations where the domain tree is of
* unequal depth, make sure to skip domains that already cover the entire
* range.
*
* 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.
*
*/
static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
{
const struct cpumask *span = sched_domain_span(sd);
struct sd_data *sdd = sd->private;
struct sched_domain *sibling;
int i;
for_each_cpu(i, span) {
sibling = *per_cpu_ptr(sdd->sd, i);
if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
continue;
cpumask_set_cpu(i, sched_group_mask(sg));
}
}
/*
* 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)
{
return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
}
static int
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
{
struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
const struct cpumask *span = sched_domain_span(sd);
struct cpumask *covered = sched_domains_tmpmask;
struct sd_data *sdd = sd->private;
struct sched_domain *sibling;
int i;
cpumask_clear(covered);
for_each_cpu(i, span) {
struct cpumask *sg_span;
if (cpumask_test_cpu(i, covered))
continue;
sibling = *per_cpu_ptr(sdd->sd, i);
/* See the comment near build_group_mask(). */
if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
continue;
sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, cpu_to_node(cpu));
if (!sg)
goto fail;
sg_span = sched_group_cpus(sg);
if (sibling->child)
cpumask_copy(sg_span, sched_domain_span(sibling->child));
else
cpumask_set_cpu(i, sg_span);
cpumask_or(covered, covered, sg_span);
sg->sgc = *per_cpu_ptr(sdd->sgc, i);
if (atomic_inc_return(&sg->sgc->ref) == 1)
build_group_mask(sd, sg);
/*
* Initialize sgc->capacity such that even if we mess up the
* domains and no possible iteration will get us here, we won't
* die on a /0 trap.
*/
sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
/*
* Make sure the first group of this domain contains the
* canonical balance cpu. Otherwise the sched_domain iteration
* breaks. See update_sg_lb_stats().
*/
if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
group_balance_cpu(sg) == cpu)
groups = sg;
if (!first)
first = sg;
if (last)
last->next = sg;
last = sg;
last->next = first;
}
sd->groups = groups;
return 0;
fail:
free_sched_groups(first, 0);
return -ENOMEM;
}
static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
{
struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
struct sched_domain *child = sd->child;
if (child)
cpu = cpumask_first(sched_domain_span(child));
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 */
}
return cpu;
}
/*
* build_sched_groups will build a circular linked list of the groups
* covered by the given span, and will set each group's ->cpumask correctly,
* and ->cpu_capacity to 0.
*
* Assumes the sched_domain tree is fully constructed
*/
static int
build_sched_groups(struct sched_domain *sd, int cpu)
{
struct sched_group *first = NULL, *last = NULL;
struct sd_data *sdd = sd->private;
const struct cpumask *span = sched_domain_span(sd);
struct cpumask *covered;
int i;
get_group(cpu, sdd, &sd->groups);
atomic_inc(&sd->groups->ref);
if (cpu != cpumask_first(span))
return 0;
lockdep_assert_held(&sched_domains_mutex);
covered = sched_domains_tmpmask;
cpumask_clear(covered);
for_each_cpu(i, span) {
struct sched_group *sg;
int group, j;
if (cpumask_test_cpu(i, covered))
continue;
group = get_group(i, sdd, &sg);
cpumask_setall(sched_group_mask(sg));
for_each_cpu(j, span) {
if (get_group(j, sdd, NULL) != group)
continue;
cpumask_set_cpu(j, covered);
cpumask_set_cpu(j, sched_group_cpus(sg));
}
if (!first)
first = sg;
if (last)
last->next = sg;
last = sg;
}
last->next = first;
return 0;
}
/*
* Initialize sched groups cpu_capacity.
*
* cpu_capacity indicates the capacity of sched group, which is used while
* distributing the load between different sched groups in a sched domain.
* Typically cpu_capacity for all the groups in a sched domain will be same
* unless there are asymmetries in the topology. If there are asymmetries,
* group having more cpu_capacity will pickup more load compared to the
* group having less cpu_capacity.
*/
static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
{
struct sched_group *sg = sd->groups;
WARN_ON(!sg);
do {
sg->group_weight = cpumask_weight(sched_group_cpus(sg));
sg = sg->next;
} while (sg != sd->groups);
if (cpu != group_balance_cpu(sg))
return;
update_group_capacity(sd, cpu);
atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight);
}
/*
* Initializers for schedule domains
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
*/
static int default_relax_domain_level = -1;
int sched_domain_level_max;
static int __init setup_relax_domain_level(char *str)
{
if (kstrtoint(str, 0, &default_relax_domain_level))
pr_warn("Unable to set relax_domain_level\n");
return 1;
}
__setup("relax_domain_level=", setup_relax_domain_level);
static void set_domain_attribute(struct sched_domain *sd,
struct sched_domain_attr *attr)
{
int request;
if (!attr || attr->relax_domain_level < 0) {
if (default_relax_domain_level < 0)
return;
else
request = default_relax_domain_level;
} else
request = attr->relax_domain_level;
if (request < sd->level) {
/* turn off idle balance on this domain */
sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
} else {
/* turn on idle balance on this domain */
sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
}
}
static void __sdt_free(const struct cpumask *cpu_map);
static int __sdt_alloc(const struct cpumask *cpu_map);
static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
const struct cpumask *cpu_map)
{
switch (what) {
case sa_rootdomain:
if (!atomic_read(&d->rd->refcount))
free_rootdomain(&d->rd->rcu); /* fall through */
case sa_sd:
free_percpu(d->sd); /* fall through */
case sa_sd_storage:
__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)
{
memset(d, 0, sizeof(*d));
if (__sdt_alloc(cpu_map))
return sa_sd_storage;
d->sd = alloc_percpu(struct sched_domain *);
if (!d->sd)
return sa_sd_storage;
d->rd = alloc_rootdomain();
if (!d->rd)
return sa_sd;
return sa_rootdomain;
}
/*
* NULL the sd_data elements we've used to build the sched_domain and
* sched_group structure so that the subsequent __free_domain_allocs()
* will not free the data we're using.
*/
static void claim_allocations(int cpu, struct sched_domain *sd)
{
struct sd_data *sdd = sd->private;
WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
*per_cpu_ptr(sdd->sd, cpu) = NULL;
if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
*per_cpu_ptr(sdd->sg, cpu) = NULL;
if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref))
*per_cpu_ptr(sdd->sgc, cpu) = NULL;
}
#ifdef CONFIG_NUMA
static int sched_domains_numa_levels;
enum numa_topology_type sched_numa_topology_type;
static int *sched_domains_numa_distance;
int sched_max_numa_distance;
static struct cpumask ***sched_domains_numa_masks;
static int sched_domains_curr_level;
#endif
/*
* SD_flags allowed in topology descriptions.
*
* SD_SHARE_CPUCAPACITY - describes SMT topologies
* SD_SHARE_PKG_RESOURCES - describes shared caches
* SD_NUMA - describes NUMA topologies
* SD_SHARE_POWERDOMAIN - describes shared power domain
*
* Odd one out:
* SD_ASYM_PACKING - describes SMT quirks
*/
#define TOPOLOGY_SD_FLAGS \
(SD_SHARE_CPUCAPACITY | \
SD_SHARE_PKG_RESOURCES | \
SD_NUMA | \
SD_ASYM_PACKING | \
SD_SHARE_POWERDOMAIN)
static struct sched_domain *
sd_init(struct sched_domain_topology_level *tl, int cpu)
{
struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
int sd_weight, sd_flags = 0;
#ifdef CONFIG_NUMA
/*
* Ugly hack to pass state to sd_numa_mask()...
*/
sched_domains_curr_level = tl->numa_level;
#endif
sd_weight = cpumask_weight(tl->mask(cpu));
if (tl->sd_flags)
sd_flags = (*tl->sd_flags)();
if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
"wrong sd_flags in topology description\n"))
sd_flags &= ~TOPOLOGY_SD_FLAGS;
*sd = (struct sched_domain){
.min_interval = sd_weight,
.max_interval = 2*sd_weight,
.busy_factor = 32,
.imbalance_pct = 125,
.cache_nice_tries = 0,
.busy_idx = 0,
.idle_idx = 0,
.newidle_idx = 0,
.wake_idx = 0,
.forkexec_idx = 0,
.flags = 1*SD_LOAD_BALANCE
| 1*SD_BALANCE_NEWIDLE
| 1*SD_BALANCE_EXEC
| 1*SD_BALANCE_FORK
| 0*SD_BALANCE_WAKE
| 1*SD_WAKE_AFFINE
| 0*SD_SHARE_CPUCAPACITY
| 0*SD_SHARE_PKG_RESOURCES
| 0*SD_SERIALIZE
| 0*SD_PREFER_SIBLING
| 0*SD_NUMA
| sd_flags
,
.last_balance = jiffies,
.balance_interval = sd_weight,
.smt_gain = 0,
.max_newidle_lb_cost = 0,
.next_decay_max_lb_cost = jiffies,
#ifdef CONFIG_SCHED_DEBUG
.name = tl->name,
#endif
};
/*
* Convert topological properties into behaviour.
*/
if (sd->flags & SD_SHARE_CPUCAPACITY) {
sd->flags |= SD_PREFER_SIBLING;
sd->imbalance_pct = 110;
sd->smt_gain = 1178; /* ~15% */
} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
sd->imbalance_pct = 117;
sd->cache_nice_tries = 1;
sd->busy_idx = 2;
#ifdef CONFIG_NUMA
} else if (sd->flags & SD_NUMA) {
sd->cache_nice_tries = 2;
sd->busy_idx = 3;
sd->idle_idx = 2;
sd->flags |= SD_SERIALIZE;
if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
sd->flags &= ~(SD_BALANCE_EXEC |
SD_BALANCE_FORK |
SD_WAKE_AFFINE);
}
#endif
} else {
sd->flags |= SD_PREFER_SIBLING;
sd->cache_nice_tries = 1;
sd->busy_idx = 2;
sd->idle_idx = 1;
}
sd->private = &tl->data;
return sd;
}
/*
* Topology list, bottom-up.
*/
static struct sched_domain_topology_level default_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
#endif
#ifdef CONFIG_SCHED_MC
{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
#endif
{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
{ NULL, },
};
struct sched_domain_topology_level *sched_domain_topology = default_topology;
#define for_each_sd_topology(tl) \
for (tl = sched_domain_topology; tl->mask; tl++)
void set_sched_topology(struct sched_domain_topology_level *tl)
{
sched_domain_topology = tl;
}
#ifdef CONFIG_NUMA
static const struct cpumask *sd_numa_mask(int cpu)
{
return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
}
static void sched_numa_warn(const char *str)
{
static int done = false;
int i,j;
if (done)
return;
done = true;
printk(KERN_WARNING "ERROR: %s\n\n", str);
for (i = 0; i < nr_node_ids; i++) {
printk(KERN_WARNING " ");
for (j = 0; j < nr_node_ids; j++)
printk(KERN_CONT "%02d ", node_distance(i,j));
printk(KERN_CONT "\n");
}
printk(KERN_WARNING "\n");
}
bool find_numa_distance(int distance)
{
int i;
if (distance == node_distance(0, 0))
return true;
for (i = 0; i < sched_domains_numa_levels; i++) {
if (sched_domains_numa_distance[i] == distance)
return true;
}
return false;
}
/*
* A system can have three types of NUMA topology:
* NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
* NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
* NUMA_BACKPLANE: nodes can reach other nodes through a backplane
*
* The difference between a glueless mesh topology and a backplane
* topology lies in whether communication between not directly
* connected nodes goes through intermediary nodes (where programs
* could run), or through backplane controllers. This affects
* placement of programs.
*
* The type of topology can be discerned with the following tests:
* - If the maximum distance between any nodes is 1 hop, the system
* is directly connected.
* - If for two nodes A and B, located N > 1 hops away from each other,
* there is an intermediary node C, which is < N hops away from both
* nodes A and B, the system is a glueless mesh.
*/
static void init_numa_topology_type(void)
{
int a, b, c, n;
n = sched_max_numa_distance;
if (n <= 1)
sched_numa_topology_type = NUMA_DIRECT;
for_each_online_node(a) {
for_each_online_node(b) {
/* Find two nodes furthest removed from each other. */
if (node_distance(a, b) < n)
continue;
/* Is there an intermediary node between a and b? */
for_each_online_node(c) {
if (node_distance(a, c) < n &&
node_distance(b, c) < n) {
sched_numa_topology_type =
NUMA_GLUELESS_MESH;
return;
}
}
sched_numa_topology_type = NUMA_BACKPLANE;
return;
}
}
}
static void sched_init_numa(void)
{
int next_distance, curr_distance = node_distance(0, 0);
struct sched_domain_topology_level *tl;
int level = 0;
int i, j, k;
sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
if (!sched_domains_numa_distance)
return;
/*
* O(nr_nodes^2) deduplicating selection sort -- in order to find the
* unique distances in the node_distance() table.
*
* Assumes node_distance(0,j) includes all distances in
* node_distance(i,j) in order to avoid cubic time.
*/
next_distance = curr_distance;
for (i = 0; i < nr_node_ids; i++) {
for (j = 0; j < nr_node_ids; j++) {
for (k = 0; k < nr_node_ids; k++) {
int distance = node_distance(i, k);
if (distance > curr_distance &&
(distance < next_distance ||
next_distance == curr_distance))
next_distance = distance;
/*
* While not a strong assumption it would be nice to know
* about cases where if node A is connected to B, B is not
* equally connected to A.
*/
if (sched_debug() && node_distance(k, i) != distance)
sched_numa_warn("Node-distance not symmetric");
if (sched_debug() && i && !find_numa_distance(distance))
sched_numa_warn("Node-0 not representative");
}
if (next_distance != curr_distance) {
sched_domains_numa_distance[level++] = next_distance;
sched_domains_numa_levels = level;
curr_distance = next_distance;
} else break;
}
/*
* In case of sched_debug() we verify the above assumption.
*/
if (!sched_debug())
break;
}
if (!level)
return;
/*
* 'level' contains the number of unique distances, excluding the
* identity distance node_distance(i,i).
*
* The sched_domains_numa_distance[] array includes the actual distance
* numbers.
*/
/*
* Here, we should temporarily reset sched_domains_numa_levels to 0.
* If it fails to allocate memory for array sched_domains_numa_masks[][],
* the array will contain less then 'level' members. This could be
* dangerous when we use it to iterate array sched_domains_numa_masks[][]
* in other functions.
*
* We reset it to 'level' at the end of this function.
*/
sched_domains_numa_levels = 0;
sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
if (!sched_domains_numa_masks)
return;
/*
* Now for each level, construct a mask per node which contains all
* cpus of nodes that are that many hops away from us.
*/
for (i = 0; i < level; i++) {
sched_domains_numa_masks[i] =
kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
if (!sched_domains_numa_masks[i])
return;
for (j = 0; j < nr_node_ids; j++) {
struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
if (!mask)
return;
sched_domains_numa_masks[i][j] = mask;
for (k = 0; k < nr_node_ids; k++) {
if (node_distance(j, k) > sched_domains_numa_distance[i])
continue;
cpumask_or(mask, mask, cpumask_of_node(k));
}
}
}
/* Compute default topology size */
for (i = 0; sched_domain_topology[i].mask; i++);
tl = kzalloc((i + level + 1) *
sizeof(struct sched_domain_topology_level), GFP_KERNEL);
if (!tl)
return;
/*
* Copy the default topology bits..
*/
for (i = 0; sched_domain_topology[i].mask; i++)
tl[i] = sched_domain_topology[i];
/*
* .. and append 'j' levels of NUMA goodness.
*/
for (j = 0; j < level; i++, j++) {
tl[i] = (struct sched_domain_topology_level){
.mask = sd_numa_mask,
.sd_flags = cpu_numa_flags,
.flags = SDTL_OVERLAP,
.numa_level = j,
SD_INIT_NAME(NUMA)
};
}
sched_domain_topology = tl;
sched_domains_numa_levels = level;
sched_max_numa_distance = sched_domains_numa_distance[level - 1];
init_numa_topology_type();
}
static void sched_domains_numa_masks_set(int cpu)
{
int i, j;
int node = cpu_to_node(cpu);
for (i = 0; i < sched_domains_numa_levels; i++) {
for (j = 0; j < nr_node_ids; j++) {
if (node_distance(j, node) <= sched_domains_numa_distance[i])
cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
}
}
}
static void sched_domains_numa_masks_clear(int cpu)
{
int i, j;
for (i = 0; i < sched_domains_numa_levels; i++) {
for (j = 0; j < nr_node_ids; j++)
cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
}
}
/*
* Update sched_domains_numa_masks[level][node] array when new cpus
* are onlined.
*/
static int sched_domains_numa_masks_update(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
int cpu = (long)hcpu;
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
sched_domains_numa_masks_set(cpu);
break;
case CPU_DEAD:
sched_domains_numa_masks_clear(cpu);
break;
default:
return NOTIFY_DONE;
}
return NOTIFY_OK;
}
#else
static inline void sched_init_numa(void)
{
}
static int sched_domains_numa_masks_update(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
return 0;
}
#endif /* CONFIG_NUMA */
static int __sdt_alloc(const struct cpumask *cpu_map)
{
struct sched_domain_topology_level *tl;
int j;
for_each_sd_topology(tl) {
struct sd_data *sdd = &tl->data;
sdd->sd = alloc_percpu(struct sched_domain *);
if (!sdd->sd)
return -ENOMEM;
sdd->sg = alloc_percpu(struct sched_group *);
if (!sdd->sg)
return -ENOMEM;
sdd->sgc = alloc_percpu(struct sched_group_capacity *);
if (!sdd->sgc)
return -ENOMEM;
for_each_cpu(j, cpu_map) {
struct sched_domain *sd;
struct sched_group *sg;
struct sched_group_capacity *sgc;
sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
GFP_KERNEL, cpu_to_node(j));
if (!sd)
return -ENOMEM;
*per_cpu_ptr(sdd->sd, j) = sd;
sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
GFP_KERNEL, cpu_to_node(j));
if (!sg)
return -ENOMEM;
sg->next = sg;
*per_cpu_ptr(sdd->sg, j) = sg;
sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(),
GFP_KERNEL, cpu_to_node(j));
if (!sgc)
return -ENOMEM;
*per_cpu_ptr(sdd->sgc, j) = sgc;
}
}
return 0;
}
static void __sdt_free(const struct cpumask *cpu_map)
{
struct sched_domain_topology_level *tl;
int j;
for_each_sd_topology(tl) {
struct sd_data *sdd = &tl->data;
for_each_cpu(j, cpu_map) {
struct sched_domain *sd;
if (sdd->sd) {
sd = *per_cpu_ptr(sdd->sd, j);
if (sd && (sd->flags & SD_OVERLAP))
free_sched_groups(sd->groups, 0);
kfree(*per_cpu_ptr(sdd->sd, j));
}
if (sdd->sg)
kfree(*per_cpu_ptr(sdd->sg, j));
if (sdd->sgc)
kfree(*per_cpu_ptr(sdd->sgc, j));
}
free_percpu(sdd->sd);
sdd->sd = NULL;
free_percpu(sdd->sg);
sdd->sg = NULL;
free_percpu(sdd->sgc);
sdd->sgc = NULL;
}
}
struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
const struct cpumask *cpu_map, struct sched_domain_attr *attr,
struct sched_domain *child, int cpu)
{
struct sched_domain *sd = sd_init(tl, cpu);
if (!sd)
return child;
cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
if (child) {
sd->level = child->level + 1;
sched_domain_level_max = max(sched_domain_level_max, sd->level);
child->parent = sd;
sd->child = child;
if (!cpumask_subset(sched_domain_span(child),
sched_domain_span(sd))) {
pr_err("BUG: arch topology borken\n");
#ifdef CONFIG_SCHED_DEBUG
pr_err(" the %s domain not a subset of the %s domain\n",
child->name, sd->name);
#endif
/* Fixup, ensure @sd has at least @child cpus. */
cpumask_or(sched_domain_span(sd),
sched_domain_span(sd),
sched_domain_span(child));
}
}
set_domain_attribute(sd, attr);
return sd;
}
/*
* 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)
{
enum s_alloc alloc_state;
struct sched_domain *sd;
struct s_data d;
int i, ret = -ENOMEM;
alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
if (alloc_state != sa_rootdomain)
goto error;
/* Set up domains for cpus specified by the cpu_map. */
for_each_cpu(i, cpu_map) {
struct sched_domain_topology_level *tl;
sd = NULL;
for_each_sd_topology(tl) {
sd = build_sched_domain(tl, cpu_map, attr, sd, i);
if (tl == sched_domain_topology)
*per_cpu_ptr(d.sd, i) = sd;
if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
sd->flags |= SD_OVERLAP;
if (cpumask_equal(cpu_map, sched_domain_span(sd)))
break;
}
}
/* Build the groups for the domains */
for_each_cpu(i, cpu_map) {
for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
sd->span_weight = cpumask_weight(sched_domain_span(sd));
if (sd->flags & SD_OVERLAP) {
if (build_overlap_sched_groups(sd, i))
goto error;
} else {
if (build_sched_groups(sd, i))
goto error;
}
}
}
/* Calculate CPU capacity for physical packages and nodes */
for (i = nr_cpumask_bits-1; i >= 0; i--) {
if (!cpumask_test_cpu(i, cpu_map))
continue;
for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
claim_allocations(i, sd);
init_sched_groups_capacity(i, sd);
}
}
/* Attach the domains */
rcu_read_lock();
for_each_cpu(i, cpu_map) {
sd = *per_cpu_ptr(d.sd, i);
cpu_attach_domain(sd, d.rd, i);
}
rcu_read_unlock();
ret = 0;
error:
__free_domain_allocs(&d, alloc_state, cpu_map);
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' */
/*
* 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;
/*
* arch_update_cpu_topology lets virtualized architectures update the
* 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)
{
return 0;
}
cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
{
int i;
cpumask_var_t *doms;
doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
if (!doms)
return NULL;
for (i = 0; i < ndoms; i++) {
if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
free_sched_domains(doms, i);
return NULL;
}
}
return doms;
}
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
{
unsigned int i;
for (i = 0; i < ndoms; i++)
free_cpumask_var(doms[i]);
kfree(doms);
}
/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
* 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)
{
int err;
arch_update_cpu_topology();
ndoms_cur = 1;
doms_cur = alloc_sched_domains(ndoms_cur);
if (!doms_cur)
doms_cur = &fallback_doms;
cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
err = build_sched_domains(doms_cur[0], NULL);
register_sched_domain_sysctl();
return err;
}
/*
* 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)
{
int i;
rcu_read_lock();
for_each_cpu(i, cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
rcu_read_unlock();
}
/* handle null as "default" */
static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
struct sched_domain_attr *new, int idx_new)
{
struct sched_domain_attr tmp;
/* fast path */
if (!new && !cur)
return 1;
tmp = SD_ATTR_INIT;
return !memcmp(cur ? (cur + idx_cur) : &tmp,
new ? (new + idx_new) : &tmp,
sizeof(struct sched_domain_attr));
}
/*
* Partition sched domains as specified by the 'ndoms_new'
* cpumasks in the array doms_new[] of cpumasks. This compares
* doms_new[] to the current sched domain partitioning, doms_cur[].
* It destroys each deleted domain and builds each new domain.
*
* 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
* The masks don't intersect (don't overlap.) We should setup one
* sched domain for each mask. CPUs not in any of the cpumasks will
* not be load balanced. If the same cpumask appears both in the
* current 'doms_cur' domains and in the new 'doms_new', we can leave
* it as it is.
*
* The passed in 'doms_new' should be allocated using
* alloc_sched_domains. This routine takes ownership of it and will
* free_sched_domains it when done with it. If the caller failed the
* alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
* and partition_sched_domains() will fallback to the single partition
* 'fallback_doms', it also forces the domains to be rebuilt.
*
* If doms_new == NULL it will be replaced with cpu_online_mask.
* ndoms_new == 0 is a special case for destroying existing domains,
* and it will not create the default domain.
*
* Call with hotplug lock held
*/
void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
int i, j, n;
int new_topology;
mutex_lock(&sched_domains_mutex);
/* always unregister in case we don't destroy any domains */
unregister_sched_domain_sysctl();
/* Let architecture update cpu core mappings. */
new_topology = arch_update_cpu_topology();
n = doms_new ? ndoms_new : 0;
/* 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[] */
detach_destroy_domains(doms_cur[i]);
match1:
;
}
n = ndoms_cur;
if (doms_new == NULL) {
n = 0;
doms_new = &fallback_doms;
cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
WARN_ON_ONCE(dattr_new);
}
/* 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 */
build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
match2:
;
}
/* Remember the new sched domains */
if (doms_cur != &fallback_doms)
free_sched_domains(doms_cur, ndoms_cur);
kfree(dattr_cur); /* kfree(NULL) is safe */
doms_cur = doms_new;
dattr_cur = dattr_new;
ndoms_cur = ndoms_new;
register_sched_domain_sysctl();
mutex_unlock(&sched_domains_mutex);
}
static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */
/*
* Update cpusets according to cpu_active mask. If cpusets are
* disabled, cpuset_update_active_cpus() becomes a simple wrapper
* around partition_sched_domains().
*
* If we come here as part of a suspend/resume, don't touch cpusets because we
* want to restore it back to its original state upon resume anyway.
*/
static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
switch (action) {
case CPU_ONLINE_FROZEN:
case CPU_DOWN_FAILED_FROZEN:
/*
* num_cpus_frozen tracks how many CPUs are involved in suspend
* resume sequence. As long as this is not the last online
* operation in the resume sequence, just build a single sched
* domain, ignoring cpusets.
*/
num_cpus_frozen--;
if (likely(num_cpus_frozen)) {
partition_sched_domains(1, NULL, NULL);
break;
}
/*
* This is the last CPU online operation. So fall through and
* restore the original sched domains by considering the
* cpuset configurations.
*/
case CPU_ONLINE:
cpuset_update_active_cpus(true);
break;
default:
return NOTIFY_DONE;
}
return NOTIFY_OK;
}
static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
unsigned long flags;
long cpu = (long)hcpu;
struct dl_bw *dl_b;
bool overflow;
int cpus;
switch (action) {
case CPU_DOWN_PREPARE:
rcu_read_lock_sched();
dl_b = dl_bw_of(cpu);
raw_spin_lock_irqsave(&dl_b->lock, flags);
cpus = dl_bw_cpus(cpu);
overflow = __dl_overflow(dl_b, cpus, 0, 0);
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
rcu_read_unlock_sched();
if (overflow)
return notifier_from_errno(-EBUSY);
cpuset_update_active_cpus(false);
break;
case CPU_DOWN_PREPARE_FROZEN:
num_cpus_frozen++;
partition_sched_domains(1, NULL, NULL);
break;
default:
return NOTIFY_DONE;
}
return NOTIFY_OK;
}
void __init sched_init_smp(void)
{
cpumask_var_t non_isolated_cpus;
alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
/* nohz_full won't take effect without isolating the cpus. */
tick_nohz_full_add_cpus_to(cpu_isolated_map);
sched_init_numa();
/*
* 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.
*/
mutex_lock(&sched_domains_mutex);
init_sched_domains(cpu_active_mask);
cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
if (cpumask_empty(non_isolated_cpus))
cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
mutex_unlock(&sched_domains_mutex);
hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE);
hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
init_hrtick();
/* Move init over to a non-isolated CPU */
if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
BUG();
sched_init_granularity();
free_cpumask_var(non_isolated_cpus);
init_sched_rt_class();
init_sched_dl_class();
}
#else
void __init sched_init_smp(void)
{
sched_init_granularity();
}
#endif /* CONFIG_SMP */
int in_sched_functions(unsigned long addr)
{
return in_lock_functions(addr) ||
(addr >= (unsigned long)__sched_text_start
&& addr < (unsigned long)__sched_text_end);
}
#ifdef CONFIG_CGROUP_SCHED
/*
* Default task group.
* Every task in system belongs to this group at bootup.
*/
struct task_group root_task_group;
LIST_HEAD(task_groups);
#endif
DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
void __init sched_init(void)
{
int i, j;
unsigned long alloc_size = 0, ptr;
#ifdef CONFIG_FAIR_GROUP_SCHED
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
if (alloc_size) {
ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.se = (struct sched_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.cfs_rq = (struct cfs_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
root_task_group.rt_rq = (struct rt_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_RT_GROUP_SCHED */
}
#ifdef CONFIG_CPUMASK_OFFSTACK
for_each_possible_cpu(i) {
per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
cpumask_size(), GFP_KERNEL, cpu_to_node(i));
}
#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());
#ifdef CONFIG_SMP
init_defrootdomain();
#endif
#ifdef CONFIG_RT_GROUP_SCHED
init_rt_bandwidth(&root_task_group.rt_bandwidth,
global_rt_period(), global_rt_runtime());
#endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_CGROUP_SCHED
list_add(&root_task_group.list, &task_groups);
INIT_LIST_HEAD(&root_task_group.children);
INIT_LIST_HEAD(&root_task_group.siblings);
autogroup_init(&init_task);
#endif /* CONFIG_CGROUP_SCHED */
for_each_possible_cpu(i) {
struct rq *rq;
rq = cpu_rq(i);
raw_spin_lock_init(&rq->lock);
rq->nr_running = 0;
rq->calc_load_active = 0;
rq->calc_load_update = jiffies + LOAD_FREQ;
init_cfs_rq(&rq->cfs);
init_rt_rq(&rq->rt);
init_dl_rq(&rq->dl);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
/*
* 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
* 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:
*
* A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
*
* We achieve this by letting root_task_group's tasks sit
* directly in rq->cfs (i.e root_task_group->se[] = NULL).
*/
init_cfs_bandwidth(&root_task_group.cfs_bandwidth);
init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
#endif
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
rq->cpu_load[j] = 0;
rq->last_load_update_tick = jiffies;
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
rq->balance_callback = NULL;
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
rq->cpu = i;
rq->online = 0;
rq->idle_stamp = 0;
rq->avg_idle = 2*sysctl_sched_migration_cost;
rq->max_idle_balance_cost = sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->cfs_tasks);
rq_attach_root(rq, &def_root_domain);
#ifdef CONFIG_NO_HZ_COMMON
rq->nohz_flags = 0;
#endif
#ifdef CONFIG_NO_HZ_FULL
rq->last_sched_tick = 0;
#endif
#endif
init_rq_hrtick(rq);
atomic_set(&rq->nr_iowait, 0);
}
set_load_weight(&init_task);
#ifdef CONFIG_PREEMPT_NOTIFIERS
INIT_HLIST_HEAD(&init_task.preempt_notifiers);
#endif
/*
* The boot idle thread does lazy MMU switching as well:
*/
atomic_inc(&init_mm.mm_count);
enter_lazy_tlb(&init_mm, current);
/*
* During early bootup we pretend to be a normal task:
*/
current->sched_class = &fair_sched_class;
/*
* Make us the idle thread. Technically, schedule() should not be
* called from this thread, however somewhere below it might be,
* but because we are the idle thread, we just pick up running again
* when this runqueue becomes "idle".
*/
init_idle(current, smp_processor_id());
calc_load_update = jiffies + LOAD_FREQ;
#ifdef CONFIG_SMP
zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
/* May be allocated at isolcpus cmdline parse time */
if (cpu_isolated_map == NULL)
zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
idle_thread_set_boot_cpu();
set_cpu_rq_start_time();
#endif
init_sched_fair_class();
scheduler_running = 1;
}
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
static inline int preempt_count_equals(int preempt_offset)
{
int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
return (nested == preempt_offset);
}
void __might_sleep(const char *file, int line, int preempt_offset)
{
/*
* Blocking primitives will set (and therefore destroy) current->state,
* since we will exit with TASK_RUNNING make sure we enter with it,
* otherwise we will destroy state.
*/
WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change,
"do not call blocking ops when !TASK_RUNNING; "
"state=%lx set at [<%p>] %pS\n",
current->state,
(void *)current->task_state_change,
(void *)current->task_state_change);
___might_sleep(file, line, preempt_offset);
}
EXPORT_SYMBOL(__might_sleep);
void ___might_sleep(const char *file, int line, int preempt_offset)
{
static unsigned long prev_jiffy; /* ratelimiting */
rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
!is_idle_task(current)) ||
system_state != SYSTEM_RUNNING || oops_in_progress)
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
prev_jiffy = jiffies;
printk(KERN_ERR
"BUG: sleeping function called from invalid 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);
if (task_stack_end_corrupted(current))
printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
debug_show_held_locks(current);
if (irqs_disabled())
print_irqtrace_events(current);
#ifdef CONFIG_DEBUG_PREEMPT
if (!preempt_count_equals(preempt_offset)) {
pr_err("Preemption disabled at:");
print_ip_sym(current->preempt_disable_ip);
pr_cont("\n");
}
#endif
dump_stack();
}
EXPORT_SYMBOL(___might_sleep);
#endif
#ifdef CONFIG_MAGIC_SYSRQ
void normalize_rt_tasks(void)
{
struct task_struct *g, *p;
struct sched_attr attr = {
.sched_policy = SCHED_NORMAL,
};
read_lock(&tasklist_lock);
for_each_process_thread(g, p) {
/*
* Only normalize user tasks:
*/
if (p->flags & PF_KTHREAD)
continue;
p->se.exec_start = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.statistics.wait_start = 0;
p->se.statistics.sleep_start = 0;
p->se.statistics.block_start = 0;
#endif
if (!dl_task(p) && !rt_task(p)) {
/*
* Renice negative nice level userspace
* tasks back to 0:
*/
if (task_nice(p) < 0)
set_user_nice(p, 0);
continue;
}
__sched_setscheduler(p, &attr, false, false);
}
read_unlock(&tasklist_lock);
}
#endif /* CONFIG_MAGIC_SYSRQ */
#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
/*
* These functions are only useful for the IA64 MCA handling, or kdb.
*
* They can only be called when the whole system has been
* stopped - every CPU needs to be quiescent, and no scheduling
* activity can take place. Using them for anything else would
* be a serious bug, and as a result, they aren't even visible
* under any other configuration.
*/
/**
* curr_task - return the current task for a given cpu.
* @cpu: the processor in question.
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
*
* Return: The current task for @cpu.
*/
struct task_struct *curr_task(int cpu)
{
return cpu_curr(cpu);
}
#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */
#ifdef CONFIG_IA64
/**
* 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
* 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
* re-starting the system.
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
*/
void set_curr_task(int cpu, struct task_struct *p)
{
cpu_curr(cpu) = p;
}
#endif
#ifdef CONFIG_CGROUP_SCHED
/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);
static void free_sched_group(struct task_group *tg)
{
free_fair_sched_group(tg);
free_rt_sched_group(tg);
autogroup_free(tg);
kfree(tg);
}
/* allocate runqueue etc for a new task group */
struct task_group *sched_create_group(struct task_group *parent)
{
struct task_group *tg;
tg = kzalloc(sizeof(*tg), GFP_KERNEL);
if (!tg)
return ERR_PTR(-ENOMEM);
if (!alloc_fair_sched_group(tg, parent))
goto err;
if (!alloc_rt_sched_group(tg, parent))
goto err;
return tg;
err:
free_sched_group(tg);
return ERR_PTR(-ENOMEM);
}
void sched_online_group(struct task_group *tg, struct task_group *parent)
{
unsigned long flags;
spin_lock_irqsave(&task_group_lock, flags);
list_add_rcu(&tg->list, &task_groups);
WARN_ON(!parent); /* root should already exist */
tg->parent = parent;
INIT_LIST_HEAD(&tg->children);
list_add_rcu(&tg->siblings, &parent->children);
spin_unlock_irqrestore(&task_group_lock, flags);
}
/* rcu callback to free various structures associated with a task group */
static void free_sched_group_rcu(struct rcu_head *rhp)
{
/* now it should be safe to free those cfs_rqs */
free_sched_group(container_of(rhp, struct task_group, rcu));
}
/* Destroy runqueue etc associated with a task group */
void sched_destroy_group(struct task_group *tg)
{
/* wait for possible concurrent references to cfs_rqs complete */
call_rcu(&tg->rcu, free_sched_group_rcu);
}
void sched_offline_group(struct task_group *tg)
{
unsigned long flags;
int i;
/* end participation in shares distribution */
for_each_possible_cpu(i)
unregister_fair_sched_group(tg, i);
spin_lock_irqsave(&task_group_lock, flags);
list_del_rcu(&tg->list);
list_del_rcu(&tg->siblings);
spin_unlock_irqrestore(&task_group_lock, flags);
}
/* change task's runqueue when it moves between groups.
* The caller of this function should have put the task in its new group
* by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
* reflect its new group.
*/
void sched_move_task(struct task_struct *tsk)
{
struct task_group *tg;
int queued, running;
unsigned long flags;
struct rq *rq;
rq = task_rq_lock(tsk, &flags);
running = task_current(rq, tsk);
queued = task_on_rq_queued(tsk);
if (queued)
dequeue_task(rq, tsk, 0);
if (unlikely(running))
put_prev_task(rq, tsk);
/*
* All callers are synchronized by task_rq_lock(); we do not use RCU
* which is pointless here. Thus, we pass "true" to task_css_check()
* to prevent lockdep warnings.
*/
tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
struct task_group, css);
tg = autogroup_task_group(tsk, tg);
tsk->sched_task_group = tg;
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->task_move_group)
tsk->sched_class->task_move_group(tsk, queued);
else
#endif
set_task_rq(tsk, task_cpu(tsk));
if (unlikely(running))
tsk->sched_class->set_curr_task(rq);
if (queued)
enqueue_task(rq, tsk, 0);
task_rq_unlock(rq, tsk, &flags);
}
#endif /* CONFIG_CGROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
/*
* Ensure that the real time constraints are schedulable.
*/
static DEFINE_MUTEX(rt_constraints_mutex);
/* Must be called with tasklist_lock held */
static inline int tg_has_rt_tasks(struct task_group *tg)
{
struct task_struct *g, *p;
/*
* Autogroups do not have RT tasks; see autogroup_create().
*/
if (task_group_is_autogroup(tg))
return 0;
for_each_process_thread(g, p) {
if (rt_task(p) && task_group(p) == tg)
return 1;
}
return 0;
}
struct rt_schedulable_data {
struct task_group *tg;
u64 rt_period;
u64 rt_runtime;
};
static int tg_rt_schedulable(struct task_group *tg, void *data)
{
struct rt_schedulable_data *d = data;
struct task_group *child;
unsigned long total, sum = 0;
u64 period, runtime;
period = ktime_to_ns(tg->rt_bandwidth.rt_period);
runtime = tg->rt_bandwidth.rt_runtime;
if (tg == d->tg) {
period = d->rt_period;
runtime = d->rt_runtime;
}
/*
* Cannot have more runtime than the period.
*/
if (runtime > period && runtime != RUNTIME_INF)
return -EINVAL;
/*
* Ensure we don't starve existing RT tasks.
*/
if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
return -EBUSY;
total = to_ratio(period, runtime);
/*
* Nobody can have more than the global setting allows.
*/
if (total > to_ratio(global_rt_period(), global_rt_runtime()))
return -EINVAL;
/*
* The sum of our children's runtime should not exceed our own.
*/
list_for_each_entry_rcu(child, &tg->children, siblings) {
period = ktime_to_ns(child->rt_bandwidth.rt_period);
runtime = child->rt_bandwidth.rt_runtime;
if (child == d->tg) {
period = d->rt_period;
runtime = d->rt_runtime;
}
sum += to_ratio(period, runtime);
}
if (sum > total)
return -EINVAL;
return 0;
}
static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
{
int ret;
struct rt_schedulable_data data = {
.tg = tg,
.rt_period = period,
.rt_runtime = runtime,
};
rcu_read_lock();
ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
rcu_read_unlock();
return ret;
}
static int tg_set_rt_bandwidth(struct task_group *tg,
u64 rt_period, u64 rt_runtime)
{
int i, err = 0;
/*
* Disallowing the root group RT runtime is BAD, it would disallow the
* kernel creating (and or operating) RT threads.
*/
if (tg == &root_task_group && rt_runtime == 0)
return -EINVAL;
/* No period doesn't make any sense. */
if (rt_period == 0)
return -EINVAL;
mutex_lock(&rt_constraints_mutex);
read_lock(&tasklist_lock);
err = __rt_schedulable(tg, rt_period, rt_runtime);
if (err)
goto unlock;
raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
tg->rt_bandwidth.rt_runtime = rt_runtime;
for_each_possible_cpu(i) {
struct rt_rq *rt_rq = tg->rt_rq[i];
raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_runtime = rt_runtime;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
unlock:
read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
return err;
}
static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
{
u64 rt_runtime, rt_period;
rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
if (rt_runtime_us < 0)
rt_runtime = RUNTIME_INF;
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}
static long sched_group_rt_runtime(struct task_group *tg)
{
u64 rt_runtime_us;
if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
return -1;
rt_runtime_us = tg->rt_bandwidth.rt_runtime;
do_div(rt_runtime_us, NSEC_PER_USEC);
return rt_runtime_us;
}
static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
{
u64 rt_runtime, rt_period;
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);
}
static long sched_group_rt_period(struct task_group *tg)
{
u64 rt_period_us;
rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
do_div(rt_period_us, NSEC_PER_USEC);
return rt_period_us;
}
#endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
static int sched_rt_global_constraints(void)
{
int ret = 0;
mutex_lock(&rt_constraints_mutex);
read_lock(&tasklist_lock);
ret = __rt_schedulable(NULL, 0, 0);
read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
return ret;
}
static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
{
/* Don't accept realtime tasks when there is no way for them to run */
if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
return 0;
return 1;
}
#else /* !CONFIG_RT_GROUP_SCHED */
static int sched_rt_global_constraints(void)
{
unsigned long flags;
int i, ret = 0;
raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
for_each_possible_cpu(i) {
struct rt_rq *rt_rq = &cpu_rq(i)->rt;
raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_runtime = global_rt_runtime();
raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
return ret;
}
#endif /* CONFIG_RT_GROUP_SCHED */
static int sched_dl_global_validate(void)
{
u64 runtime = global_rt_runtime();
u64 period = global_rt_period();
u64 new_bw = to_ratio(period, runtime);
struct dl_bw *dl_b;
int cpu, ret = 0;
unsigned long flags;
/*
* Here we want to check the bandwidth not being set to some
* value smaller than the currently allocated bandwidth in
* any of the root_domains.
*
* FIXME: Cycling on all the CPUs is overdoing, but simpler than
* cycling on root_domains... Discussion on different/better
* solutions is welcome!
*/
for_each_possible_cpu(cpu) {
rcu_read_lock_sched();
dl_b = dl_bw_of(cpu);
raw_spin_lock_irqsave(&dl_b->lock, flags);
if (new_bw < dl_b->total_bw)
ret = -EBUSY;
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
rcu_read_unlock_sched();
if (ret)
break;
}
return ret;
}
static void sched_dl_do_global(void)
{
u64 new_bw = -1;
struct dl_bw *dl_b;
int cpu;
unsigned long flags;
def_dl_bandwidth.dl_period = global_rt_period();
def_dl_bandwidth.dl_runtime = global_rt_runtime();
if (global_rt_runtime() != RUNTIME_INF)
new_bw = to_ratio(global_rt_period(), global_rt_runtime());
/*
* FIXME: As above...
*/
for_each_possible_cpu(cpu) {
rcu_read_lock_sched();
dl_b = dl_bw_of(cpu);
raw_spin_lock_irqsave(&dl_b->lock, flags);
dl_b->bw = new_bw;
raw_spin_unlock_irqrestore(&dl_b->lock, flags);
rcu_read_unlock_sched();
}
}
static int sched_rt_global_validate(void)
{
if (sysctl_sched_rt_period <= 0)
return -EINVAL;
if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
return -EINVAL;
return 0;
}
static void sched_rt_do_global(void)
{
def_rt_bandwidth.rt_runtime = global_rt_runtime();
def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
}
int sched_rt_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int old_period, old_runtime;
static DEFINE_MUTEX(mutex);
int ret;
mutex_lock(&mutex);
old_period = sysctl_sched_rt_period;
old_runtime = sysctl_sched_rt_runtime;
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (!ret && write) {
ret = sched_rt_global_validate();
if (ret)
goto undo;
ret = sched_dl_global_validate();
if (ret)
goto undo;
ret = sched_rt_global_constraints();
if (ret)
goto undo;
sched_rt_do_global();
sched_dl_do_global();
}
if (0) {
undo:
sysctl_sched_rt_period = old_period;
sysctl_sched_rt_runtime = old_runtime;
}
mutex_unlock(&mutex);
return ret;
}
int sched_rr_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
static DEFINE_MUTEX(mutex);
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 */
if (!ret && write) {
sched_rr_timeslice = sched_rr_timeslice <= 0 ?
RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
}
mutex_unlock(&mutex);
return ret;
}
#ifdef CONFIG_CGROUP_SCHED
static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct task_group, css) : NULL;
}
static struct cgroup_subsys_state *
cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct task_group *parent = css_tg(parent_css);
struct task_group *tg;
if (!parent) {
/* This is early initialization for the top cgroup */
return &root_task_group.css;
}
tg = sched_create_group(parent);
if (IS_ERR(tg))
return ERR_PTR(-ENOMEM);
return &tg->css;
}
static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
struct task_group *parent = css_tg(css->parent);
if (parent)
sched_online_group(tg, parent);
return 0;
}
static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
sched_destroy_group(tg);
}
static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
sched_offline_group(tg);
}
static void cpu_cgroup_fork(struct task_struct *task)
{
sched_move_task(task);
}
static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *task;
cgroup_taskset_for_each(task, tset) {
#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(css_tg(css), task))
return -EINVAL;
#else
/* We don't support RT-tasks being in separate groups */
if (task->sched_class != &fair_sched_class)
return -EINVAL;
#endif
}
return 0;
}
static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
struct cgroup_taskset *tset)
{
struct task_struct *task;
cgroup_taskset_for_each(task, tset)
sched_move_task(task);
}
static void cpu_cgroup_exit(struct cgroup_subsys_state *css,
struct cgroup_subsys_state *old_css,
struct task_struct *task)
{
/*
* cgroup_exit() is called in the copy_process() failure path.
* Ignore this case since the task hasn't ran yet, this avoids
* trying to poke a half freed task state from generic code.
*/
if (!(task->flags & PF_EXITING))
return;
sched_move_task(task);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 shareval)
{
return sched_group_set_shares(css_tg(css), scale_load(shareval));
}
static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
struct task_group *tg = css_tg(css);
return (u64) scale_load_down(tg->shares);
}
#ifdef CONFIG_CFS_BANDWIDTH
static DEFINE_MUTEX(cfs_constraints_mutex);
const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
{
int i, ret = 0, runtime_enabled, runtime_was_enabled;
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
if (tg == &root_task_group)
return -EINVAL;
/*
* Ensure we have at some amount of bandwidth every period. This is
* to prevent reaching a state of large arrears when throttled via
* entity_tick() resulting in prolonged exit starvation.
*/
if (quota < min_cfs_quota_period || period < min_cfs_quota_period)
return -EINVAL;
/*
* Likewise, bound things on the otherside by preventing insane quota
* periods. This also allows us to normalize in computing quota
* feasibility.
*/
if (period > max_cfs_quota_period)
return -EINVAL;
/*
* Prevent race between setting of cfs_rq->runtime_enabled and
* unthrottle_offline_cfs_rqs().
*/
get_online_cpus();
mutex_lock(&cfs_constraints_mutex);
ret = __cfs_schedulable(tg, period, quota);
if (ret)
goto out_unlock;
runtime_enabled = quota != RUNTIME_INF;
runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
/*
* If we need to toggle cfs_bandwidth_used, off->on must occur
* before making related changes, and on->off must occur afterwards
*/
if (runtime_enabled && !runtime_was_enabled)
cfs_bandwidth_usage_inc();
raw_spin_lock_irq(&cfs_b->lock);
cfs_b->period = ns_to_ktime(period);
cfs_b->quota = quota;
__refill_cfs_bandwidth_runtime(cfs_b);
/* 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) {
struct cfs_rq *cfs_rq = tg->cfs_rq[i];
struct rq *rq = cfs_rq->rq;
raw_spin_lock_irq(&rq->lock);
cfs_rq->runtime_enabled = runtime_enabled;
cfs_rq->runtime_remaining = 0;
if (cfs_rq->throttled)
unthrottle_cfs_rq(cfs_rq);
raw_spin_unlock_irq(&rq->lock);
}
if (runtime_was_enabled && !runtime_enabled)
cfs_bandwidth_usage_dec();
out_unlock:
mutex_unlock(&cfs_constraints_mutex);
put_online_cpus();
return ret;
}
int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
{
u64 quota, period;
period = ktime_to_ns(tg->cfs_bandwidth.period);
if (cfs_quota_us < 0)
quota = RUNTIME_INF;
else
quota = (u64)cfs_quota_us * NSEC_PER_USEC;
return tg_set_cfs_bandwidth(tg, period, quota);
}
long tg_get_cfs_quota(struct task_group *tg)
{
u64 quota_us;
if (tg->cfs_bandwidth.quota == RUNTIME_INF)
return -1;
quota_us = tg->cfs_bandwidth.quota;
do_div(quota_us, NSEC_PER_USEC);
return quota_us;
}
int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
{
u64 quota, period;
period = (u64)cfs_period_us * NSEC_PER_USEC;
quota = tg->cfs_bandwidth.quota;
return tg_set_cfs_bandwidth(tg, period, quota);
}
long tg_get_cfs_period(struct task_group *tg)
{
u64 cfs_period_us;
cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period);
do_div(cfs_period_us, NSEC_PER_USEC);
return cfs_period_us;
}
static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return tg_get_cfs_quota(css_tg(css));
}
static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
struct cftype *cftype, s64 cfs_quota_us)
{
return tg_set_cfs_quota(css_tg(css), cfs_quota_us);
}
static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return tg_get_cfs_period(css_tg(css));
}
static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 cfs_period_us)
{
return tg_set_cfs_period(css_tg(css), cfs_period_us);
}
struct cfs_schedulable_data {
struct task_group *tg;
u64 period, quota;
};
/*
* normalize group quota/period to be quota/max_period
* note: units are usecs
*/
static u64 normalize_cfs_quota(struct task_group *tg,
struct cfs_schedulable_data *d)
{
u64 quota, period;
if (tg == d->tg) {
period = d->period;
quota = d->quota;
} else {
period = tg_get_cfs_period(tg);
quota = tg_get_cfs_quota(tg);
}
/* note: these should typically be equivalent */
if (quota == RUNTIME_INF || quota == -1)
return RUNTIME_INF;
return to_ratio(period, quota);
}
static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
{
struct cfs_schedulable_data *d = data;
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
s64 quota = 0, parent_quota = -1;
if (!tg->parent) {
quota = RUNTIME_INF;
} else {
struct cfs_bandwidth *parent_b = &tg->parent->cfs_bandwidth;
quota = normalize_cfs_quota(tg, d);
parent_quota = parent_b->hierarchical_quota;
/*
* ensure max(child_quota) <= parent_quota, inherit when no
* limit is set
*/
if (quota == RUNTIME_INF)
quota = parent_quota;
else if (parent_quota != RUNTIME_INF && quota > parent_quota)
return -EINVAL;
}
cfs_b->hierarchical_quota = quota;
return 0;
}
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
{
int ret;
struct cfs_schedulable_data data = {
.tg = tg,
.period = period,
.quota = quota,
};
if (quota != RUNTIME_INF) {
do_div(data.period, NSEC_PER_USEC);
do_div(data.quota, NSEC_PER_USEC);
}
rcu_read_lock();
ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
rcu_read_unlock();
return ret;
}
static int cpu_stats_show(struct seq_file *sf, void *v)
{
struct task_group *tg = css_tg(seq_css(sf));
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods);
seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
return 0;
}
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
struct cftype *cft, s64 val)
{
return sched_group_set_rt_runtime(css_tg(css), val);
}
static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return sched_group_rt_runtime(css_tg(css));
}
static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 rt_period_us)
{
return sched_group_set_rt_period(css_tg(css), rt_period_us);
}
static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
struct cftype *cft)
{
return sched_group_rt_period(css_tg(css));
}
#endif /* CONFIG_RT_GROUP_SCHED */
static struct cftype cpu_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
{
.name = "shares",
.read_u64 = cpu_shares_read_u64,
.write_u64 = cpu_shares_write_u64,
},
#endif
#ifdef CONFIG_CFS_BANDWIDTH
{
.name = "cfs_quota_us",
.read_s64 = cpu_cfs_quota_read_s64,
.write_s64 = cpu_cfs_quota_write_s64,
},
{
.name = "cfs_period_us",
.read_u64 = cpu_cfs_period_read_u64,
.write_u64 = cpu_cfs_period_write_u64,
},
{
.name = "stat",
.seq_show = cpu_stats_show,
},
#endif
#ifdef CONFIG_RT_GROUP_SCHED
{
.name = "rt_runtime_us",
.read_s64 = cpu_rt_runtime_read,
.write_s64 = cpu_rt_runtime_write,
},
{
.name = "rt_period_us",
.read_u64 = cpu_rt_period_read_uint,
.write_u64 = cpu_rt_period_write_uint,
},
#endif
{ } /* terminate */
};
struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
.css_free = cpu_cgroup_css_free,
.css_online = cpu_cgroup_css_online,
.css_offline = cpu_cgroup_css_offline,
.fork = cpu_cgroup_fork,
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
.exit = cpu_cgroup_exit,
.legacy_cftypes = cpu_files,
.early_init = 1,
};
#endif /* CONFIG_CGROUP_SCHED */
void dump_cpu_task(int cpu)
{
pr_info("Task dump for CPU %d:\n", cpu);
sched_show_task(cpu_curr(cpu));
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/sched/cpuacct.c
#include <linux/cgroup.h>
#include <linux/slab.h>
#include <linux/percpu.h>
#include <linux/spinlock.h>
#include <linux/cpumask.h>
#include <linux/seq_file.h>
#include <linux/rcupdate.h>
#include <linux/kernel_stat.h>
#include <linux/err.h>
#include "sched.h"
/*
* CPU accounting code for task groups.
*
* Based on the work by Paul Menage (menage@google.com) and Balbir Singh
* (balbir@in.ibm.com).
*/
/* Time spent by the tasks of the cpu accounting group executing in ... */
enum cpuacct_stat_index {
CPUACCT_STAT_USER, /* ... user mode */
CPUACCT_STAT_SYSTEM, /* ... kernel mode */
CPUACCT_STAT_NSTATS,
};
/* track cpu usage of a group of tasks and its child groups */
struct cpuacct {
struct cgroup_subsys_state css;
/* cpuusage holds pointer to a u64-type object on every cpu */
u64 __percpu *cpuusage;
struct kernel_cpustat __percpu *cpustat;
};
static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct cpuacct, css) : NULL;
}
/* return cpu accounting group to which this task belongs */
static inline struct cpuacct *task_ca(struct task_struct *tsk)
{
return css_ca(task_css(tsk, cpuacct_cgrp_id));
}
static inline struct cpuacct *parent_ca(struct cpuacct *ca)
{
return css_ca(ca->css.parent);
}
static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
static struct cpuacct root_cpuacct = {
.cpustat = &kernel_cpustat,
.cpuusage = &root_cpuacct_cpuusage,
};
/* create a new cpu accounting group */
static struct cgroup_subsys_state *
cpuacct_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct cpuacct *ca;
if (!parent_css)
return &root_cpuacct.css;
ca = kzalloc(sizeof(*ca), GFP_KERNEL);
if (!ca)
goto out;
ca->cpuusage = alloc_percpu(u64);
if (!ca->cpuusage)
goto out_free_ca;
ca->cpustat = alloc_percpu(struct kernel_cpustat);
if (!ca->cpustat)
goto out_free_cpuusage;
return &ca->css;
out_free_cpuusage:
free_percpu(ca->cpuusage);
out_free_ca:
kfree(ca);
out:
return ERR_PTR(-ENOMEM);
}
/* destroy an existing cpu accounting group */
static void cpuacct_css_free(struct cgroup_subsys_state *css)
{
struct cpuacct *ca = css_ca(css);
free_percpu(ca->cpustat);
free_percpu(ca->cpuusage);
kfree(ca);
}
static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
{
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
u64 data;
#ifndef CONFIG_64BIT
/*
* Take rq->lock to make 64-bit read safe on 32-bit platforms.
*/
raw_spin_lock_irq(&cpu_rq(cpu)->lock);
data = *cpuusage;
raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
#else
data = *cpuusage;
#endif
return data;
}
static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
{
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
#ifndef CONFIG_64BIT
/*
* Take rq->lock to make 64-bit write safe on 32-bit platforms.
*/
raw_spin_lock_irq(&cpu_rq(cpu)->lock);
*cpuusage = val;
raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
#else
*cpuusage = val;
#endif
}
/* return total cpu usage (in nanoseconds) of a group */
static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft)
{
struct cpuacct *ca = css_ca(css);
u64 totalcpuusage = 0;
int i;
for_each_present_cpu(i)
totalcpuusage += cpuacct_cpuusage_read(ca, i);
return totalcpuusage;
}
static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft,
u64 reset)
{
struct cpuacct *ca = css_ca(css);
int err = 0;
int i;
if (reset) {
err = -EINVAL;
goto out;
}
for_each_present_cpu(i)
cpuacct_cpuusage_write(ca, i, 0);
out:
return err;
}
static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
{
struct cpuacct *ca = css_ca(seq_css(m));
u64 percpu;
int i;
for_each_present_cpu(i) {
percpu = cpuacct_cpuusage_read(ca, i);
seq_printf(m, "%llu ", (unsigned long long) percpu);
}
seq_printf(m, "\n");
return 0;
}
static const char * const cpuacct_stat_desc[] = {
[CPUACCT_STAT_USER] = "user",
[CPUACCT_STAT_SYSTEM] = "system",
};
static int cpuacct_stats_show(struct seq_file *sf, void *v)
{
struct cpuacct *ca = css_ca(seq_css(sf));
int cpu;
s64 val = 0;
for_each_online_cpu(cpu) {
struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
val += kcpustat->cpustat[CPUTIME_USER];
val += kcpustat->cpustat[CPUTIME_NICE];
}
val = cputime64_to_clock_t(val);
seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);
val = 0;
for_each_online_cpu(cpu) {
struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
val += kcpustat->cpustat[CPUTIME_SYSTEM];
val += kcpustat->cpustat[CPUTIME_IRQ];
val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
}
val = cputime64_to_clock_t(val);
seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
return 0;
}
static struct cftype files[] = {
{
.name = "usage",
.read_u64 = cpuusage_read,
.write_u64 = cpuusage_write,
},
{
.name = "usage_percpu",
.seq_show = cpuacct_percpu_seq_show,
},
{
.name = "stat",
.seq_show = cpuacct_stats_show,
},
{ } /* terminate */
};
/*
* charge this task's execution time to its accounting group.
*
* called with rq->lock held.
*/
void cpuacct_charge(struct task_struct *tsk, u64 cputime)
{
struct cpuacct *ca;
int cpu;
cpu = task_cpu(tsk);
rcu_read_lock();
ca = task_ca(tsk);
while (true) {
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
*cpuusage += cputime;
ca = parent_ca(ca);
if (!ca)
break;
}
rcu_read_unlock();
}
/*
* Add user/system time to cpuacct.
*
* Note: it's the caller that updates the account of the root cgroup.
*/
void cpuacct_account_field(struct task_struct *p, int index, u64 val)
{
struct kernel_cpustat *kcpustat;
struct cpuacct *ca;
rcu_read_lock();
ca = task_ca(p);
while (ca != &root_cpuacct) {
kcpustat = this_cpu_ptr(ca->cpustat);
kcpustat->cpustat[index] += val;
ca = parent_ca(ca);
}
rcu_read_unlock();
}
struct cgroup_subsys cpuacct_cgrp_subsys = {
.css_alloc = cpuacct_css_alloc,
.css_free = cpuacct_css_free,
.legacy_cftypes = files,
.early_init = 1,
};
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/sched/cpuacct.h
#ifdef CONFIG_CGROUP_CPUACCT
extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
extern void cpuacct_account_field(struct task_struct *p, int index, u64 val);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime)
{
}
static inline void
cpuacct_account_field(struct task_struct *p, int index, u64 val)
{
}
#endif
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/sched/cpudeadline.c
/*
* kernel/sched/cpudl.c
*
* Global CPU deadline management
*
* Author: Juri Lelli <j.lelli@sssup.it>
*
* 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; version 2
* of the License.
*/
#include <linux/gfp.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include "cpudeadline.h"
static inline int parent(int i)
{
return (i - 1) >> 1;
}
static inline int left_child(int i)
{
return (i << 1) + 1;
}
static inline int right_child(int i)
{
return (i << 1) + 2;
}
static inline int dl_time_before(u64 a, u64 b)
{
return (s64)(a - b) < 0;
}
static void cpudl_exchange(struct cpudl *cp, int a, int b)
{
int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
swap(cp->elements[a].cpu, cp->elements[b].cpu);
swap(cp->elements[a].dl , cp->elements[b].dl );
swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx);
}
static void cpudl_heapify(struct cpudl *cp, int idx)
{
int l, r, largest;
/* adapted from lib/prio_heap.c */
while(1) {
l = left_child(idx);
r = right_child(idx);
largest = idx;
if ((l < cp->size) && dl_time_before(cp->elements[idx].dl,
cp->elements[l].dl))
largest = l;
if ((r < cp->size) && dl_time_before(cp->elements[largest].dl,
cp->elements[r].dl))
largest = r;
if (largest == idx)
break;
/* Push idx down the heap one level and bump one up */
cpudl_exchange(cp, largest, idx);
idx = largest;
}
}
static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
{
WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
if (dl_time_before(new_dl, cp->elements[idx].dl)) {
cp->elements[idx].dl = new_dl;
cpudl_heapify(cp, idx);
} else {
cp->elements[idx].dl = new_dl;
while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl,
cp->elements[idx].dl)) {
cpudl_exchange(cp, idx, parent(idx));
idx = parent(idx);
}
}
}
static inline int cpudl_maximum(struct cpudl *cp)
{
return cp->elements[0].cpu;
}
/*
* cpudl_find - find the best (later-dl) CPU in the system
* @cp: the cpudl max-heap context
* @p: the task
* @later_mask: a mask to fill in with the selected CPUs (or NULL)
*
* Returns: int - best CPU (heap maximum if suitable)
*/
int cpudl_find(struct cpudl *cp, struct task_struct *p,
struct cpumask *later_mask)
{
int best_cpu = -1;
const struct sched_dl_entity *dl_se = &p->dl;
if (later_mask &&
cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
best_cpu = cpumask_any(later_mask);
goto out;
} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
best_cpu = cpudl_maximum(cp);
if (later_mask)
cpumask_set_cpu(best_cpu, later_mask);
}
out:
WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
return best_cpu;
}
/*
* cpudl_set - update the cpudl max-heap
* @cp: the cpudl max-heap context
* @cpu: the target cpu
* @dl: the new earliest deadline for this cpu
*
* Notes: assumes cpu_rq(cpu)->lock is locked
*
* Returns: (void)
*/
void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
{
int old_idx, new_cpu;
unsigned long flags;
WARN_ON(!cpu_present(cpu));
raw_spin_lock_irqsave(&cp->lock, flags);
old_idx = cp->elements[cpu].idx;
if (!is_valid) {
/* remove item */
if (old_idx == IDX_INVALID) {
/*
* Nothing to remove if old_idx was invalid.
* This could happen if a rq_offline_dl is
* called for a CPU without -dl tasks running.
*/
goto out;
}
new_cpu = cp->elements[cp->size - 1].cpu;
cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
cp->elements[old_idx].cpu = new_cpu;
cp->size--;
cp->elements[new_cpu].idx = old_idx;
cp->elements[cpu].idx = IDX_INVALID;
while (old_idx > 0 && dl_time_before(
cp->elements[parent(old_idx)].dl,
cp->elements[old_idx].dl)) {
cpudl_exchange(cp, old_idx, parent(old_idx));
old_idx = parent(old_idx);
}
cpumask_set_cpu(cpu, cp->free_cpus);
cpudl_heapify(cp, old_idx);
goto out;
}
if (old_idx == IDX_INVALID) {
cp->size++;
cp->elements[cp->size - 1].dl = 0;
cp->elements[cp->size - 1].cpu = cpu;
cp->elements[cpu].idx = cp->size - 1;
cpudl_change_key(cp, cp->size - 1, dl);
cpumask_clear_cpu(cpu, cp->free_cpus);
} else {
cpudl_change_key(cp, old_idx, dl);
}
out:
raw_spin_unlock_irqrestore(&cp->lock, flags);
}
/*
* cpudl_set_freecpu - Set the cpudl.free_cpus
* @cp: the cpudl max-heap context
* @cpu: rd attached cpu
*/
void cpudl_set_freecpu(struct cpudl *cp, int cpu)
{
cpumask_set_cpu(cpu, cp->free_cpus);
}
/*
* cpudl_clear_freecpu - Clear the cpudl.free_cpus
* @cp: the cpudl max-heap context
* @cpu: rd attached cpu
*/
void cpudl_clear_freecpu(struct cpudl *cp, int cpu)
{
cpumask_clear_cpu(cpu, cp->free_cpus);
}
/*
* cpudl_init - initialize the cpudl structure
* @cp: the cpudl max-heap context
*/
int cpudl_init(struct cpudl *cp)
{
int i;
memset(cp, 0, sizeof(*cp));
raw_spin_lock_init(&cp->lock);
cp->size = 0;
cp->elements = kcalloc(nr_cpu_ids,
sizeof(struct cpudl_item),
GFP_KERNEL);
if (!cp->elements)
return -ENOMEM;
if (!zalloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
kfree(cp->elements);
return -ENOMEM;
}
for_each_possible_cpu(i)
cp->elements[i].idx = IDX_INVALID;
return 0;
}
/*
* cpudl_cleanup - clean up the cpudl structure
* @cp: the cpudl max-heap context
*/
void cpudl_cleanup(struct cpudl *cp)
{
free_cpumask_var(cp->free_cpus);
kfree(cp->elements);
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/sched/cpudeadline.h
#ifndef _LINUX_CPUDL_H
#define _LINUX_CPUDL_H
#include <linux/sched.h>
#define IDX_INVALID -1
struct cpudl_item {
u64 dl;
int cpu;
int idx;
};
struct cpudl {
raw_spinlock_t lock;
int size;
cpumask_var_t free_cpus;
struct cpudl_item *elements;
};
#ifdef CONFIG_SMP
int cpudl_find(struct cpudl *cp, struct task_struct *p,
struct cpumask *later_mask);
void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
int cpudl_init(struct cpudl *cp);
void cpudl_set_freecpu(struct cpudl *cp, int cpu);
void cpudl_clear_freecpu(struct cpudl *cp, int cpu);
void cpudl_cleanup(struct cpudl *cp);
#endif /* CONFIG_SMP */
#endif /* _LINUX_CPUDL_H */
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/sched/cpupri.c
/*
* kernel/sched/cpupri.c
*
* CPU priority management
*
* Copyright (C) 2007-2008 Novell
*
* Author: Gregory Haskins <ghaskins@novell.com>
*
* This code tracks the priority of each CPU so that global migration
* decisions are easy to calculate. Each CPU can be in a state as follows:
*
* (INVALID), IDLE, NORMAL, RT1, ... RT99
*
* going from the lowest priority to the highest. CPUs in the INVALID state
* are not eligible for routing. The system maintains this state with
* a 2 dimensional bitmap (the first for priority class, the second for cpus
* in that class). Therefore a typical application without affinity
* restrictions can find a suitable CPU with O(1) complexity (e.g. two bit
* searches). For tasks with affinity restrictions, the algorithm has a
* worst case complexity of O(min(102, nr_domcpus)), though the scenario that
* yields the worst case search is fairly contrived.
*
* 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; version 2
* of the License.
*/
#include <linux/gfp.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/slab.h>
#include "cpupri.h"
/* Convert between a 140 based task->prio, and our 102 based cpupri */
static int convert_prio(int prio)
{
int cpupri;
if (prio == CPUPRI_INVALID)
cpupri = CPUPRI_INVALID;
else if (prio == MAX_PRIO)
cpupri = CPUPRI_IDLE;
else if (prio >= MAX_RT_PRIO)
cpupri = CPUPRI_NORMAL;
else
cpupri = MAX_RT_PRIO - prio + 1;
return cpupri;
}
/**
* cpupri_find - find the best (lowest-pri) CPU in the system
* @cp: The cpupri context
* @p: The task
* @lowest_mask: A mask to fill in with selected CPUs (or NULL)
*
* Note: This function returns the recommended CPUs as calculated during the
* current invocation. By the time the call returns, the CPUs may have in
* fact changed priorities any number of times. While not ideal, it is not
* an issue of correctness since the normal rebalancer logic will correct
* any discrepancies created by racing against the uncertainty of the current
* priority configuration.
*
* Return: (int)bool - CPUs were found
*/
int cpupri_find(struct cpupri *cp, struct task_struct *p,
struct cpumask *lowest_mask)
{
int idx = 0;
int task_pri = convert_prio(p->prio);
BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
for (idx = 0; idx < task_pri; idx++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[idx];
int skip = 0;
if (!atomic_read(&(vec)->count))
skip = 1;
/*
* When looking at the vector, we need to read the counter,
* do a memory barrier, then read the mask.
*
* Note: This is still all racey, but we can deal with it.
* Ideally, we only want to look at masks that are set.
*
* If a mask is not set, then the only thing wrong is that we
* did a little more work than necessary.
*
* If we read a zero count but the mask is set, because of the
* memory barriers, that can only happen when the highest prio
* task for a run queue has left the run queue, in which case,
* it will be followed by a pull. If the task we are processing
* fails to find a proper place to go, that pull request will
* pull this task if the run queue is running at a lower
* priority.
*/
smp_rmb();
/* Need to do the rmb for every iteration */
if (skip)
continue;
if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
continue;
if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
/*
* We have to ensure that we have at least one bit
* still set in the array, since the map could have
* been concurrently emptied between the first and
* second reads of vec->mask. If we hit this
* condition, simply act as though we never hit this
* priority level and continue on.
*/
if (cpumask_any(lowest_mask) >= nr_cpu_ids)
continue;
}
return 1;
}
return 0;
}
/**
* cpupri_set - update the cpu priority setting
* @cp: The cpupri context
* @cpu: The target cpu
* @newpri: The priority (INVALID-RT99) to assign to this CPU
*
* Note: Assumes cpu_rq(cpu)->lock is locked
*
* Returns: (void)
*/
void cpupri_set(struct cpupri *cp, int cpu, int newpri)
{
int *currpri = &cp->cpu_to_pri[cpu];
int oldpri = *currpri;
int do_mb = 0;
newpri = convert_prio(newpri);
BUG_ON(newpri >= CPUPRI_NR_PRIORITIES);
if (newpri == oldpri)
return;
/*
* If the cpu was currently mapped to a different value, we
* need to map it to the new value then remove the old value.
* Note, we must add the new value first, otherwise we risk the
* cpu being missed by the priority loop in cpupri_find.
*/
if (likely(newpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
cpumask_set_cpu(cpu, vec->mask);
/*
* When adding a new vector, we update the mask first,
* do a write memory barrier, and then update the count, to
* make sure the vector is visible when count is set.
*/
smp_mb__before_atomic();
atomic_inc(&(vec)->count);
do_mb = 1;
}
if (likely(oldpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri];
/*
* Because the order of modification of the vec->count
* is important, we must make sure that the update
* of the new prio is seen before we decrement the
* old prio. This makes sure that the loop sees
* one or the other when we raise the priority of
* the run queue. We don't care about when we lower the
* priority, as that will trigger an rt pull anyway.
*
* We only need to do a memory barrier if we updated
* the new priority vec.
*/
if (do_mb)
smp_mb__after_atomic();
/*
* When removing from the vector, we decrement the counter first
* do a memory barrier and then clear the mask.
*/
atomic_dec(&(vec)->count);
smp_mb__after_atomic();
cpumask_clear_cpu(cpu, vec->mask);
}
*currpri = newpri;
}
/**
* cpupri_init - initialize the cpupri structure
* @cp: The cpupri context
*
* Return: -ENOMEM on memory allocation failure.
*/
int cpupri_init(struct cpupri *cp)
{
int i;
memset(cp, 0, sizeof(*cp));
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[i];
atomic_set(&vec->count, 0);
if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
goto cleanup;
}
cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL);
if (!cp->cpu_to_pri)
goto cleanup;
for_each_possible_cpu(i)
cp->cpu_to_pri[i] = CPUPRI_INVALID;
return 0;
cleanup:
for (i--; i >= 0; i--)
free_cpumask_var(cp->pri_to_cpu[i].mask);
return -ENOMEM;
}
/**
* cpupri_cleanup - clean up the cpupri structure
* @cp: The cpupri context
*/
void cpupri_cleanup(struct cpupri *cp)
{
int i;
kfree(cp->cpu_to_pri);
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
free_cpumask_var(cp->pri_to_cpu[i].mask);
}
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/sched/cpupri.h
#ifndef _LINUX_CPUPRI_H
#define _LINUX_CPUPRI_H
#include <linux/sched.h>
#define CPUPRI_NR_PRIORITIES (MAX_RT_PRIO + 2)
#define CPUPRI_INVALID -1
#define CPUPRI_IDLE 0
#define CPUPRI_NORMAL 1
/* values 2-101 are RT priorities 0-99 */
struct cpupri_vec {
atomic_t count;
cpumask_var_t mask;
};
struct cpupri {
struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES];
int *cpu_to_pri;
};
#ifdef CONFIG_SMP
int cpupri_find(struct cpupri *cp,
struct task_struct *p, struct cpumask *lowest_mask);
void cpupri_set(struct cpupri *cp, int cpu, int pri);
int cpupri_init(struct cpupri *cp);
void cpupri_cleanup(struct cpupri *cp);
#endif
#endif /* _LINUX_CPUPRI_H */
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/sched/cputime.c
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/tsacct_kern.h>
#include <linux/kernel_stat.h>
#include <linux/static_key.h>
#include <linux/context_tracking.h>
#include "sched.h"
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
/*
* There are no locks covering percpu hardirq/softirq time.
* They are only modified in vtime_account, on corresponding CPU
* with interrupts disabled. So, writes are safe.
* They are read and saved off onto struct rq in update_rq_clock().
* This may result in other CPU reading this CPU's irq time and can
* race with irq/vtime_account on this CPU. We would either get old
* or new value with a side effect of accounting a slice of irq time to wrong
* task when irq is in progress while we read rq->clock. That is a worthy
* compromise in place of having locks on each irq in account_system_time.
*/
DEFINE_PER_CPU(u64, cpu_hardirq_time);
DEFINE_PER_CPU(u64, cpu_softirq_time);
static DEFINE_PER_CPU(u64, irq_start_time);
static int sched_clock_irqtime;
void enable_sched_clock_irqtime(void)
{
sched_clock_irqtime = 1;
}
void disable_sched_clock_irqtime(void)
{
sched_clock_irqtime = 0;
}
#ifndef CONFIG_64BIT
DEFINE_PER_CPU(seqcount_t, irq_time_seq);
#endif /* CONFIG_64BIT */
/*
* Called before incrementing preempt_count on {soft,}irq_enter
* and before decrementing preempt_count on {soft,}irq_exit.
*/
void irqtime_account_irq(struct task_struct *curr)
{
unsigned long flags;
s64 delta;
int cpu;
if (!sched_clock_irqtime)
return;
local_irq_save(flags);
cpu = smp_processor_id();
delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
__this_cpu_add(irq_start_time, delta);
irq_time_write_begin();
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
* in that case, so as not to confuse scheduler with a special task
* that do not consume any time, but still wants to run.
*/
if (hardirq_count())
__this_cpu_add(cpu_hardirq_time, delta);
else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
__this_cpu_add(cpu_softirq_time, delta);
irq_time_write_end();
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(irqtime_account_irq);
static int irqtime_account_hi_update(void)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
unsigned long flags;
u64 latest_ns;
int ret = 0;
local_irq_save(flags);
latest_ns = this_cpu_read(cpu_hardirq_time);
if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
ret = 1;
local_irq_restore(flags);
return ret;
}
static int irqtime_account_si_update(void)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
unsigned long flags;
u64 latest_ns;
int ret = 0;
local_irq_save(flags);
latest_ns = this_cpu_read(cpu_softirq_time);
if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ])
ret = 1;
local_irq_restore(flags);
return ret;
}
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
#define sched_clock_irqtime (0)
#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
static inline void task_group_account_field(struct task_struct *p, int index,
u64 tmp)
{
/*
* Since all updates are sure to touch the root cgroup, we
* get ourselves ahead and touch it first. If the root cgroup
* is the only cgroup, then nothing else should be necessary.
*
*/
__this_cpu_add(kernel_cpustat.cpustat[index], tmp);
cpuacct_account_field(p, index, tmp);
}
/*
* Account user cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in user space since the last update
* @cputime_scaled: cputime scaled by cpu frequency
*/
void account_user_time(struct task_struct *p, cputime_t cputime,
cputime_t cputime_scaled)
{
int index;
/* Add user time to process. */
p->utime += cputime;
p->utimescaled += cputime_scaled;
account_group_user_time(p, cputime);
index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
/* Add user time to cpustat. */
task_group_account_field(p, index, (__force u64) cputime);
/* Account for user time used */
acct_account_cputime(p);
}
/*
* Account guest cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in virtual machine since the last update
* @cputime_scaled: cputime scaled by cpu frequency
*/
static void account_guest_time(struct task_struct *p, cputime_t cputime,
cputime_t cputime_scaled)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
/* Add guest time to process. */
p->utime += cputime;
p->utimescaled += cputime_scaled;
account_group_user_time(p, cputime);
p->gtime += cputime;
/* Add guest time to cpustat. */
if (task_nice(p) > 0) {
cpustat[CPUTIME_NICE] += (__force u64) cputime;
cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
} else {
cpustat[CPUTIME_USER] += (__force u64) cputime;
cpustat[CPUTIME_GUEST] += (__force u64) cputime;
}
}
/*
* Account system cpu time to a process and desired cpustat field
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in kernel space since the last update
* @cputime_scaled: cputime scaled by cpu frequency
* @target_cputime64: pointer to cpustat field that has to be updated
*/
static inline
void __account_system_time(struct task_struct *p, cputime_t cputime,
cputime_t cputime_scaled, int index)
{
/* Add system time to process. */
p->stime += cputime;
p->stimescaled += cputime_scaled;
account_group_system_time(p, cputime);
/* Add system time to cpustat. */
task_group_account_field(p, index, (__force u64) cputime);
/* Account for system time used */
acct_account_cputime(p);
}
/*
* Account system cpu time to a process.
* @p: the process that the cpu time gets accounted to
* @hardirq_offset: the offset to subtract from hardirq_count()
* @cputime: the cpu time spent in kernel space since the last update
* @cputime_scaled: cputime scaled by cpu frequency
*/
void account_system_time(struct task_struct *p, int hardirq_offset,
cputime_t cputime, cputime_t cputime_scaled)
{
int index;
if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
account_guest_time(p, cputime, cputime_scaled);
return;
}
if (hardirq_count() - hardirq_offset)
index = CPUTIME_IRQ;
else if (in_serving_softirq())
index = CPUTIME_SOFTIRQ;
else
index = CPUTIME_SYSTEM;
__account_system_time(p, cputime, cputime_scaled, index);
}
/*
* Account for involuntary wait time.
* @cputime: the cpu time spent in involuntary wait
*/
void account_steal_time(cputime_t cputime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
cpustat[CPUTIME_STEAL] += (__force u64) cputime;
}
/*
* Account for idle time.
* @cputime: the cpu time spent in idle wait
*/
void account_idle_time(cputime_t cputime)
{
u64 *cpustat = kcpustat_this_cpu->cpustat;
struct rq *rq = this_rq();
if (atomic_read(&rq->nr_iowait) > 0)
cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
else
cpustat[CPUTIME_IDLE] += (__force u64) cputime;
}
static __always_inline bool steal_account_process_tick(void)
{
#ifdef CONFIG_PARAVIRT
if (static_key_false(¶virt_steal_enabled)) {
u64 steal;
cputime_t steal_ct;
steal = paravirt_steal_clock(smp_processor_id());
steal -= this_rq()->prev_steal_time;
/*
* cputime_t may be less precise than nsecs (eg: if it's
* based on jiffies). Lets cast the result to cputime
* granularity and account the rest on the next rounds.
*/
steal_ct = nsecs_to_cputime(steal);
this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct);
account_steal_time(steal_ct);
return steal_ct;
}
#endif
return false;
}
/*
* Accumulate raw cputime values of dead tasks (sig->[us]time) and live
* tasks (sum on group iteration) belonging to @tsk's group.
*/
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
{
struct signal_struct *sig = tsk->signal;
cputime_t utime, stime;
struct task_struct *t;
unsigned int seq, nextseq;
unsigned long flags;
rcu_read_lock();
/* Attempt a lockless read on the first round. */
nextseq = 0;
do {
seq = nextseq;
flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
times->utime = sig->utime;
times->stime = sig->stime;
times->sum_exec_runtime = sig->sum_sched_runtime;
for_each_thread(tsk, t) {
task_cputime(t, &utime, &stime);
times->utime += utime;
times->stime += stime;
times->sum_exec_runtime += task_sched_runtime(t);
}
/* If lockless access failed, take the lock. */
nextseq = 1;
} while (need_seqretry(&sig->stats_lock, seq));
done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
rcu_read_unlock();
}
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
/*
* Account a tick to a process and cpustat
* @p: the process that the cpu time gets accounted to
* @user_tick: is the tick from userspace
* @rq: the pointer to rq
*
* Tick demultiplexing follows the order
* - pending hardirq update
* - pending softirq update
* - user_time
* - idle_time
* - system time
* - check for guest_time
* - else account as system_time
*
* Check for hardirq is done both for system and user time as there is
* no timer going off while we are on hardirq and hence we may never get an
* opportunity to update it solely in system time.
* p->stime and friends are only updated on system time and not on irq
* softirq as those do not count in task exec_runtime any more.
*/
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
struct rq *rq, int ticks)
{
cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
u64 cputime = (__force u64) cputime_one_jiffy;
u64 *cpustat = kcpustat_this_cpu->cpustat;
if (steal_account_process_tick())
return;
cputime *= ticks;
scaled *= ticks;
if (irqtime_account_hi_update()) {
cpustat[CPUTIME_IRQ] += cputime;
} else if (irqtime_account_si_update()) {
cpustat[CPUTIME_SOFTIRQ] += cputime;
} else if (this_cpu_ksoftirqd() == p) {
/*
* ksoftirqd time do not get accounted in cpu_softirq_time.
* So, we have to handle it separately here.
* Also, p->stime needs to be updated for ksoftirqd.
*/
__account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
} else if (user_tick) {
account_user_time(p, cputime, scaled);
} else if (p == rq->idle) {
account_idle_time(cputime);
} else if (p->flags & PF_VCPU) { /* System time or guest time */
account_guest_time(p, cputime, scaled);
} else {
__account_system_time(p, cputime, scaled, CPUTIME_SYSTEM);
}
}
static void irqtime_account_idle_ticks(int ticks)
{
struct rq *rq = this_rq();
irqtime_account_process_tick(current, 0, rq, ticks);
}
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
static inline void irqtime_account_idle_ticks(int ticks) {}
static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
struct rq *rq, int nr_ticks) {}
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
/*
* Use precise platform statistics if available:
*/
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
#ifndef __ARCH_HAS_VTIME_TASK_SWITCH
void vtime_common_task_switch(struct task_struct *prev)
{
if (is_idle_task(prev))
vtime_account_idle(prev);
else
vtime_account_system(prev);
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
vtime_account_user(prev);
#endif
arch_vtime_task_switch(prev);
}
#endif
/*
* Archs that account the whole time spent in the idle task
* (outside irq) as idle time can rely on this and just implement
* vtime_account_system() and vtime_account_idle(). Archs that
* have other meaning of the idle time (s390 only includes the
* time spent by the CPU when it's in low power mode) must override
* vtime_account().
*/
#ifndef __ARCH_HAS_VTIME_ACCOUNT
void vtime_common_account_irq_enter(struct task_struct *tsk)
{
if (!in_interrupt()) {
/*
* If we interrupted user, context_tracking_in_user()
* is 1 because the context tracking don't hook
* on irq entry/exit. This way we know if
* we need to flush user time on kernel entry.
*/
if (context_tracking_in_user()) {
vtime_account_user(tsk);
return;
}
if (is_idle_task(tsk)) {
vtime_account_idle(tsk);
return;
}
}
vtime_account_system(tsk);
}
EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter);
#endif /* __ARCH_HAS_VTIME_ACCOUNT */
#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
*ut = p->utime;
*st = p->stime;
}
void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
struct task_cputime cputime;
thread_group_cputime(p, &cputime);
*ut = cputime.utime;
*st = cputime.stime;
}
#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
/*
* Account a single tick of cpu time.
* @p: the process that the cpu time gets accounted to
* @user_tick: indicates if the tick is a user or a system tick
*/
void account_process_tick(struct task_struct *p, int user_tick)
{
cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
struct rq *rq = this_rq();
if (vtime_accounting_enabled())
return;
if (sched_clock_irqtime) {
irqtime_account_process_tick(p, user_tick, rq, 1);
return;
}
if (steal_account_process_tick())
return;
if (user_tick)
account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
one_jiffy_scaled);
else
account_idle_time(cputime_one_jiffy);
}
/*
* Account multiple ticks of steal time.
* @p: the process from which the cpu time has been stolen
* @ticks: number of stolen ticks
*/
void account_steal_ticks(unsigned long ticks)
{
account_steal_time(jiffies_to_cputime(ticks));
}
/*
* Account multiple ticks of idle time.
* @ticks: number of stolen ticks
*/
void account_idle_ticks(unsigned long ticks)
{
if (sched_clock_irqtime) {
irqtime_account_idle_ticks(ticks);
return;
}
account_idle_time(jiffies_to_cputime(ticks));
}
/*
* Perform (stime * rtime) / total, but avoid multiplication overflow by
* loosing precision when the numbers are big.
*/
static cputime_t scale_stime(u64 stime, u64 rtime, u64 total)
{
u64 scaled;
for (;;) {
/* Make sure "rtime" is the bigger of stime/rtime */
if (stime > rtime)
swap(rtime, stime);
/* Make sure 'total' fits in 32 bits */
if (total >> 32)
goto drop_precision;
/* Does rtime (and thus stime) fit in 32 bits? */
if (!(rtime >> 32))
break;
/* Can we just balance rtime/stime rather than dropping bits? */
if (stime >> 31)
goto drop_precision;
/* We can grow stime and shrink rtime and try to make them both fit */
stime <<= 1;
rtime >>= 1;
continue;
drop_precision:
/* We drop from rtime, it has more bits than stime */
rtime >>= 1;
total >>= 1;
}
/*
* Make sure gcc understands that this is a 32x32->64 multiply,
* followed by a 64/32->64 divide.
*/
scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
return (__force cputime_t) scaled;
}
/*
* Atomically advance counter to the new value. Interrupts, vcpu
* scheduling, and scaling inaccuracies can cause cputime_advance
* to be occasionally called with a new value smaller than counter.
* Let's enforce atomicity.
*
* Normally a caller will only go through this loop once, or not
* at all in case a previous caller updated counter the same jiffy.
*/
static void cputime_advance(cputime_t *counter, cputime_t new)
{
cputime_t old;
while (new > (old = READ_ONCE(*counter)))
cmpxchg_cputime(counter, old, new);
}
/*
* Adjust tick based cputime random precision against scheduler
* runtime accounting.
*/
static void cputime_adjust(struct task_cputime *curr,
struct cputime *prev,
cputime_t *ut, cputime_t *st)
{
cputime_t rtime, stime, utime;
/*
* Tick based cputime accounting depend on random scheduling
* timeslices of a task to be interrupted or not by the timer.
* Depending on these circumstances, the number of these interrupts
* may be over or under-optimistic, matching the real user and system
* cputime with a variable precision.
*
* Fix this by scaling these tick based values against the total
* runtime accounted by the CFS scheduler.
*/
rtime = nsecs_to_cputime(curr->sum_exec_runtime);
/*
* Update userspace visible utime/stime values only if actual execution
* time is bigger than already exported. Note that can happen, that we
* provided bigger values due to scaling inaccuracy on big numbers.
*/
if (prev->stime + prev->utime >= rtime)
goto out;
stime = curr->stime;
utime = curr->utime;
if (utime == 0) {
stime = rtime;
} else if (stime == 0) {
utime = rtime;
} else {
cputime_t total = stime + utime;
stime = scale_stime((__force u64)stime,
(__force u64)rtime, (__force u64)total);
utime = rtime - stime;
}
cputime_advance(&prev->stime, stime);
cputime_advance(&prev->utime, utime);
out:
*ut = prev->utime;
*st = prev->stime;
}
void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
struct task_cputime cputime = {
.sum_exec_runtime = p->se.sum_exec_runtime,
};
task_cputime(p, &cputime.utime, &cputime.stime);
cputime_adjust(&cputime, &p->prev_cputime, ut, st);
}
void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
struct task_cputime cputime;
thread_group_cputime(p, &cputime);
cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
}
#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
static unsigned long long vtime_delta(struct task_struct *tsk)
{
unsigned long long clock;
clock = local_clock();
if (clock < tsk->vtime_snap)
return 0;
return clock - tsk->vtime_snap;
}
static cputime_t get_vtime_delta(struct task_struct *tsk)
{
unsigned long long delta = vtime_delta(tsk);
WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING);
tsk->vtime_snap += delta;
/* CHECKME: always safe to convert nsecs to cputime? */
return nsecs_to_cputime(delta);
}
static void __vtime_account_system(struct task_struct *tsk)
{
cputime_t delta_cpu = get_vtime_delta(tsk);
account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu));
}
void vtime_account_system(struct task_struct *tsk)
{
write_seqlock(&tsk->vtime_seqlock);
__vtime_account_system(tsk);
write_sequnlock(&tsk->vtime_seqlock);
}
void vtime_gen_account_irq_exit(struct task_struct *tsk)
{
write_seqlock(&tsk->vtime_seqlock);
__vtime_account_system(tsk);
if (context_tracking_in_user())
tsk->vtime_snap_whence = VTIME_USER;
write_sequnlock(&tsk->vtime_seqlock);
}
void vtime_account_user(struct task_struct *tsk)
{
cputime_t delta_cpu;
write_seqlock(&tsk->vtime_seqlock);
delta_cpu = get_vtime_delta(tsk);
tsk->vtime_snap_whence = VTIME_SYS;
account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
write_sequnlock(&tsk->vtime_seqlock);
}
void vtime_user_enter(struct task_struct *tsk)
{
write_seqlock(&tsk->vtime_seqlock);
__vtime_account_system(tsk);
tsk->vtime_snap_whence = VTIME_USER;
write_sequnlock(&tsk->vtime_seqlock);
}
void vtime_guest_enter(struct task_struct *tsk)
{
/*
* The flags must be updated under the lock with
* the vtime_snap flush and update.
* That enforces a right ordering and update sequence
* synchronization against the reader (task_gtime())
* that can thus safely catch up with a tickless delta.
*/
write_seqlock(&tsk->vtime_seqlock);
__vtime_account_system(tsk);
current->flags |= PF_VCPU;
write_sequnlock(&tsk->vtime_seqlock);
}
EXPORT_SYMBOL_GPL(vtime_guest_enter);
void vtime_guest_exit(struct task_struct *tsk)
{
write_seqlock(&tsk->vtime_seqlock);
__vtime_account_system(tsk);
current->flags &= ~PF_VCPU;
write_sequnlock(&tsk->vtime_seqlock);
}
EXPORT_SYMBOL_GPL(vtime_guest_exit);
void vtime_account_idle(struct task_struct *tsk)
{
cputime_t delta_cpu = get_vtime_delta(tsk);
account_idle_time(delta_cpu);
}
void arch_vtime_task_switch(struct task_struct *prev)
{
write_seqlock(&prev->vtime_seqlock);
prev->vtime_snap_whence = VTIME_SLEEPING;
write_sequnlock(&prev->vtime_seqlock);
write_seqlock(¤t->vtime_seqlock);
current->vtime_snap_whence = VTIME_SYS;
current->vtime_snap = sched_clock_cpu(smp_processor_id());
write_sequnlock(¤t->vtime_seqlock);
}
void vtime_init_idle(struct task_struct *t, int cpu)
{
unsigned long flags;
write_seqlock_irqsave(&t->vtime_seqlock, flags);
t->vtime_snap_whence = VTIME_SYS;
t->vtime_snap = sched_clock_cpu(cpu);
write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
}
cputime_t task_gtime(struct task_struct *t)
{
unsigned int seq;
cputime_t gtime;
do {
seq = read_seqbegin(&t->vtime_seqlock);
gtime = t->gtime;
if (t->flags & PF_VCPU)
gtime += vtime_delta(t);
} while (read_seqretry(&t->vtime_seqlock, seq));
return gtime;
}
/*
* Fetch cputime raw values from fields of task_struct and
* add up the pending nohz execution time since the last
* cputime snapshot.
*/
static void
fetch_task_cputime(struct task_struct *t,
cputime_t *u_dst, cputime_t *s_dst,
cputime_t *u_src, cputime_t *s_src,
cputime_t *udelta, cputime_t *sdelta)
{
unsigned int seq;
unsigned long long delta;
do {
*udelta = 0;
*sdelta = 0;
seq = read_seqbegin(&t->vtime_seqlock);
if (u_dst)
*u_dst = *u_src;
if (s_dst)
*s_dst = *s_src;
/* Task is sleeping, nothing to add */
if (t->vtime_snap_whence == VTIME_SLEEPING ||
is_idle_task(t))
continue;
delta = vtime_delta(t);
/*
* Task runs either in user or kernel space, add pending nohz time to
* the right place.
*/
if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) {
*udelta = delta;
} else {
if (t->vtime_snap_whence == VTIME_SYS)
*sdelta = delta;
}
} while (read_seqretry(&t->vtime_seqlock, seq));
}
void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
{
cputime_t udelta, sdelta;
fetch_task_cputime(t, utime, stime, &t->utime,
&t->stime, &udelta, &sdelta);
if (utime)
*utime += udelta;
if (stime)
*stime += sdelta;
}
void task_cputime_scaled(struct task_struct *t,
cputime_t *utimescaled, cputime_t *stimescaled)
{
cputime_t udelta, sdelta;
fetch_task_cputime(t, utimescaled, stimescaled,
&t->utimescaled, &t->stimescaled, &udelta, &sdelta);
if (utimescaled)
*utimescaled += cputime_to_scaled(udelta);
if (stimescaled)
*stimescaled += cputime_to_scaled(sdelta);
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\kernel\/sched/deadline.c
/*
* Deadline Scheduling Class (SCHED_DEADLINE)
*
* Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS).
*
* Tasks that periodically executes their instances for less than their
* runtime won't miss any of their deadlines.
* Tasks that are not periodic or sporadic or that tries to execute more
* than their reserved bandwidth will be slowed down (and may potentially
* miss some of their deadlines), and won't affect any other task.
*
* Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
* Juri Lelli <juri.lelli@gmail.com>,
* Michael Trimarchi <michael@amarulasolutions.com>,
* Fabio Checconi <fchecconi@gmail.com>
*/
#include "sched.h"
#include <linux/slab.h>
struct dl_bandwidth def_dl_bandwidth;
static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
{
return container_of(dl_se, struct task_struct, dl);
}
static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
{
return container_of(dl_rq, struct rq, dl);
}
static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
{
struct task_struct *p = dl_task_of(dl_se);
struct rq *rq = task_rq(p);
return &rq->dl;
}
static inline int on_dl_rq(struct sched_dl_entity *dl_se)
{
return !RB_EMPTY_NODE(&dl_se->rb_node);
}
static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
{
struct sched_dl_entity *dl_se = &p->dl;
return dl_rq->rb_leftmost == &dl_se->rb_node;
}
void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
{
raw_spin_lock_init(&dl_b->dl_runtime_lock);
dl_b->dl_period = period;
dl_b->dl_runtime = runtime;
}
void init_dl_bw(struct dl_bw *dl_b)
{
raw_spin_lock_init(&dl_b->lock);
raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
if (global_rt_runtime() == RUNTIME_INF)
dl_b->bw = -1;
else
dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
dl_b->total_bw = 0;
}
void init_dl_rq(struct dl_rq *dl_rq)
{
dl_rq->rb_root = RB_ROOT;
#ifdef CONFIG_SMP
/* zero means no -deadline tasks */
dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
dl_rq->dl_nr_migratory = 0;
dl_rq->overloaded = 0;
dl_rq->pushable_dl_tasks_root = RB_ROOT;
#else
init_dl_bw(&dl_rq->dl_bw);
#endif
}
#ifdef CONFIG_SMP
static inline int dl_overloaded(struct rq *rq)
{
return atomic_read(&rq->rd->dlo_count);
}
static inline void dl_set_overload(struct rq *rq)
{
if (!rq->online)
return;
cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask);
/*
* Must be visible before the overload count is
* set (as in sched_rt.c).
*
* Matched by the barrier in pull_dl_task().
*/
smp_wmb();
atomic_inc(&rq->rd->dlo_count);
}
static inline void dl_clear_overload(struct rq *rq)
{
if (!rq->online)
return;
atomic_dec(&rq->rd->dlo_count);
cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
}
static void update_dl_migration(struct dl_rq *dl_rq)
{
if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) {
if (!dl_rq->overloaded) {
dl_set_overload(rq_of_dl_rq(dl_rq));
dl_rq->overloaded = 1;
}
} else if (dl_rq->overloaded) {
dl_clear_overload(rq_of_dl_rq(dl_rq));
dl_rq->overloaded = 0;
}
}
static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
struct task_struct *p = dl_task_of(dl_se);
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory++;
update_dl_migration(dl_rq);
}
static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
struct task_struct *p = dl_task_of(dl_se);
if (p->nr_cpus_allowed > 1)
dl_rq->dl_nr_migratory--;
update_dl_migration(dl_rq);
}
/*
* The list of pushable -deadline task is not a plist, like in
* sched_rt.c, it is an rb-tree with tasks ordered by deadline.
*/
static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
{
struct dl_rq *dl_rq = &rq->dl;
struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node;
struct rb_node *parent = NULL;
struct task_struct *entry;
int leftmost = 1;
BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
while (*link) {
parent = *link;
entry = rb_entry(parent, struct task_struct,
pushable_dl_tasks);
if (dl_entity_preempt(&p->dl, &entry->dl))
link = &parent->rb_left;
else {
link = &parent->rb_right;
leftmost = 0;
}
}
if (leftmost)
dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
rb_link_node(&p->pushable_dl_tasks, parent, link);
rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
}
static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
{
struct dl_rq *dl_rq = &rq->dl;
if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
return;
if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) {
struct rb_node *next_node;
next_node = rb_next(&p->pushable_dl_tasks);
dl_rq->pushable_dl_tasks_leftmost = next_node;
}
rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
}
static inline int has_pushable_dl_tasks(struct rq *rq)
{
return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root);
}
static int push_dl_task(struct rq *rq);
static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
{
return dl_task(prev);
}
static DEFINE_PER_CPU(struct callback_head, dl_push_head);
static DEFINE_PER_CPU(struct callback_head, dl_pull_head);
static void push_dl_tasks(struct rq *);
static void pull_dl_task(struct rq *);
static inline void queue_push_tasks(struct rq *rq)
{
if (!has_pushable_dl_tasks(rq))
return;
queue_balance_callback(rq, &per_cpu(dl_push_head, rq->cpu), push_dl_tasks);
}
static inline void queue_pull_task(struct rq *rq)
{
queue_balance_callback(rq, &per_cpu(dl_pull_head, rq->cpu), pull_dl_task);
}
static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq);
static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p)
{
struct rq *later_rq = NULL;
bool fallback = false;
later_rq = find_lock_later_rq(p, rq);
if (!later_rq) {
int cpu;
/*
* If we cannot preempt any rq, fall back to pick any
* online cpu.
*/
fallback = true;
cpu = cpumask_any_and(cpu_active_mask, tsk_cpus_allowed(p));
if (cpu >= nr_cpu_ids) {
/*
* Fail to find any suitable cpu.
* The task will never come back!
*/
BUG_ON(dl_bandwidth_enabled());
/*
* If admission control is disabled we
* try a little harder to let the task
* run.
*/
cpu = cpumask_any(cpu_active_mask);
}
later_rq = cpu_rq(cpu);
double_lock_balance(rq, later_rq);
}
/*
* By now the task is replenished and enqueued; migrate it.
*/
deactivate_task(rq, p, 0);
set_task_cpu(p, later_rq->cpu);
activate_task(later_rq, p, 0);
if (!fallback)
resched_curr(later_rq);
double_unlock_balance(later_rq, rq);
return later_rq;
}
#else
static inline
void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
{
}
static inline
void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
{
}
static inline
void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
}
static inline
void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
{
}
static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev)
{
return false;
}
static inline void pull_dl_task(struct rq *rq)
{
}
static inline void queue_push_tasks(struct rq *rq)
{
}
static inline void queue_pull_task(struct rq *rq)
{
}
#endif /* CONFIG_SMP */
static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
int flags);
/*
* We are being explicitly informed that a new instance is starting,
* and this means that:
* - the absolute deadline of the entity has to be placed at
* current time + relative deadline;
* - the runtime of the entity has to be set to the maximum value.
*
* The capability of specifying such event is useful whenever a -deadline
* entity wants to (try to!) synchronize its behaviour with the scheduler's
* one, and to (try to!) reconcile itself with its own scheduling
* parameters.
*/
static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
struct sched_dl_entity *pi_se)
{
struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
struct rq *rq = rq_of_dl_rq(dl_rq);
WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
/*
* We use the regular wall clock time to set deadlines in the
* future; in fact, we must consider execution overheads (time
* spent on hardirq context, etc.).
*/
dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
dl_se->runtime = pi_se->dl_runtime;
dl_se->dl_new = 0;
}
kkkkkkk33
最新推荐文章于 2024-07-24 10:40:52 发布