pick_next_task_fair
从后缀的fair就知道，这是cfs调度类中的一个函数，用于在就绪队列中选择一个最优的进程来等待调度。类似的，其他sched_class也有其自己对应的pick_next_task函数。
struct sched_class {
#ifdef CONFIG_UCLAMP_TASK
int uclamp_enabled;
#endif
void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
void (*yield_task) (struct rq *rq);
bool (*yield_to_task)(struct rq *rq, struct task_struct *p);
void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
struct task_struct *(*pick_next_task)(struct rq *rq);
void (*put_prev_task)(struct rq *rq, struct task_struct *p);
void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
#ifdef CONFIG_SMP
int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
void (*task_woken)(struct rq *this_rq, struct task_struct *task);
void (*set_cpus_allowed)(struct task_struct *p,
const struct cpumask *newmask);
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
#endif
void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
void (*task_fork)(struct task_struct *p);
void (*task_dead)(struct task_struct *p);
/*
* The switched_from() call is allowed to drop rq->lock, therefore we
* cannot assume the switched_from/switched_to pair is serliazed by
* rq->lock. They are however serialized by p->pi_lock.
*/
void (*switched_from)(struct rq *this_rq, struct task_struct *task);
void (*switched_to) (struct rq *this_rq, struct task_struct *task);
void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
int oldprio);
unsigned int (*get_rr_interval)(struct rq *rq,
struct task_struct *task);
void (*update_curr)(struct rq *rq);
#define TASK_SET_GROUP 0
#define TASK_MOVE_GROUP 1
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*task_change_group)(struct task_struct *p, int type);
#endif
} __aligned(STRUCT_ALIGNMENT); /* STRUCT_ALIGN(), vmlinux.lds.h */
函数原型
struct task_struct *
pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
struct task_struct *p;
int new_tasks;
again:
/* 如果nr_running计数器为0，则当前队列上没有可运行的进程，调度idle进程。 */
if (!sched_fair_runnable(rq))
goto idle;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* 如果当前运行的进程prev不是被fair调度的普通非实时进程 */
if (!prev || prev->sched_class != &fair_sched_class)
goto simple;
/*
* Because of the set_next_buddy() in dequeue_task_fair() it is rather
* likely that a next task is from the same cgroup as the current.
*
* Therefore attempt to avoid putting and setting the entire cgroup
* hierarchy, only change the part that actually changes.
*/
do {
struct sched_entity *curr = cfs_rq->curr;
/*
* Since we got here without doing put_prev_entity() we also
* have to consider cfs_rq->curr. If it is still a runnable
* entity, update_curr() will update its vruntime, otherwise
* forget we've ever seen it.
*/
/*
如果当前进程在curr在队列上,
则需要更新其统计量和虚拟运行时间，
否则设置curr为空
*/
if (curr) {
if (curr->on_rq)
update_curr(cfs_rq);
else
curr = NULL;
/*
* This call to check_cfs_rq_runtime() will do the
* throttle and dequeue its entity in the parent(s).
* Therefore the nr_running test will indeed
* be correct.
*/
if (unlikely(check_cfs_rq_runtime(cfs_rq))) {
cfs_rq = &rq->cfs;
if (!cfs_rq->nr_running)
goto idle;
goto simple;
}
}
/* 选择一个最优的调度实体 */
se = pick_next_entity(cfs_rq, curr);
/* 获取调度实体所处的cfs队列 */
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
/* 获取该调度实体对应的task */
p = task_of(se);
/*
* Since we haven't yet done put_prev_entity and if the selected task
* is a different task than we started out with, try and touch the
* least amount of cfs_rqs.
*/
if (prev != p) {
struct sched_entity *pse = &prev->se;
while (!(cfs_rq = is_same_group(se, pse))) {
int se_depth = se->depth;
int pse_depth = pse->depth;
if (se_depth <= pse_depth) {
put_prev_entity(cfs_rq_of(pse), pse);
pse = parent_entity(pse);
}
if (se_depth >= pse_depth) {
set_next_entity(cfs_rq_of(se), se);
se = parent_entity(se);
}
}
put_prev_entity(cfs_rq, pse);
set_next_entity(cfs_rq, se);
}
goto done;
simple:
#endif
if (prev)
/* 将当前进程放入运行队列的合适位置 */
put_prev_task(rq, prev);
do {
/* 选出下一可执行的调度实体 */
se = pick_next_entity(cfs_rq, NULL);
/* 把选出的进程从红黑树中移除，更新红黑树,会调用__dequeue_entity完成此工作 */
set_next_entity(cfs_rq, se);
/* 在非组调度的情况下返回NULL */
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
done: __maybe_unused;
#ifdef CONFIG_SMP
/*
* Move the next running task to the front of
* the list, so our cfs_tasks list becomes MRU
* one.
*/
list_move(&p->se.group_node, &rq->cfs_tasks);
#endif
if (hrtick_enabled(rq))
hrtick_start_fair(rq, p);
update_misfit_status(p, rq);
return p;
idle:
if (!rf)
return NULL;
new_tasks = newidle_balance(rq, rf);
/*
* Because newidle_balance() releases (and re-acquires) rq->lock, it is
* possible for any higher priority task to appear. In that case we
* must re-start the pick_next_entity() loop.
*/
if (new_tasks < 0)
return RETRY_TASK;
if (new_tasks > 0)
goto again;
/*
* rq is about to be idle, check if we need to update the
* lost_idle_time of clock_pelt
*/
update_idle_rq_clock_pelt(rq);
return NULL;
}
将上文代码进行简化，可将pick_next_task_fair简化为：
again:
控制循环来读取最优进程
#ifdef CONFIG_FAIR_GROUP_SCHED
完成组调度下的pick_next函数
返回被选择的调度实体指针
#endif
simple:
最基础的pick_next函数
返回被选择的调度实体指针
idle:
如果系统中没有可运行的进程，则需要调度idle进程
