Linux 进程调度之schdule主调度器

struct task_struct {......(1)volatile long state;(2)const struct sched_class *sched_class;(3)void *stack;struct Thread_struct thread;struct mm_struct *mm, *active_mm;......}

//  kernel/sched/sched.hstruct sched_class {......//将任务加入可运行的队列中void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);//将任务移除可运行的队列中void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);//选择一下将要运行的任务struct task_struct * (*pick_next_task) (struct rq *rq,struct task_struct *prev,struct pin_cookie cookie);......}extern const struct sched_class fair_sched_class;

//  kernel/sched/fair.cconst struct sched_class fair_sched_class;/* * All the scheduling class methods: */const struct sched_class fair_sched_class = {.......enqueue_task= enqueue_task_fair,    //CFS 的 enqueue_task 实例.dequeue_task= dequeue_task_fair,//CFS 的 dequeue_task 实例.pick_next_task= pick_next_task_fair,//CFS 的 pick_next_task 实例......}

DEFINE_PER_CPU_SHAred_ALIGNED(struct rq, runqueues);

struct rq {    .......unsigned int nr_running;   //运行队列上可运行任务的个数struct cfs_rq cfs;         // CFS 运行队列struct task_struct *curr,  //当前正在运行任务的 task_struct 实例struct task_struct *idle,  //指向idle任务的实例，在没有其它可运行任务的时候执行......}

asmlinkage __visible void __sched schedule(void){......preempt_disable();//禁止内核抢占__schedule(false);//任务开始调度，调度的过程中禁止其它任务抢占sched_preempt_enable_no_resched();//开启内核抢占......}

/* * The below macro ___wait_event() has an explicit shadow of the __ret * variable when used from the wait_event_*() macros. * * This is so that both can use the ___wait_cond_timeout() construct * to wrap the condition. * * The type inconsistency of the wait_event_*() __ret variable is also * on purpose; we use long where we can return timeout values and int * otherwise. */#define ___wait_event(wq, condition, state, exclusive, ret, cmd)({__label__ __out;wait_queue_t __wait;long __ret = ret;/* explicit shadow */init_wait_entry(&__wait, exclusive ? WQ_FLAG_EXCLUSIVE : 0);or (;;) {long __int = prepare_to_wait_event(&wq, &__wait, state);if (condition)reak;if (___wait_is_interruptible(state) && __int) {__ret = __int;goto __out;}cmd;}inish_wait(&wq, &__wait);__out:__ret;})#define __wait_event(wq, condition)(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,    schedule())/** * wait_event - sleep until a condition gets true * @wq: the waitqueue to wait on * @condition: a C expression for the event to wait for * * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the * @condition evaluates to true. The @condition is checked each time * the waitqueue @wq is woken up. * * wake_up() has to be called after changing any variable that could * change the result of the wait condition. */#define wait_event(wq, condition)do {might_sleep();if (condition)reak;__wait_event(wq, condition);} while (0)

/** * 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;}

static void __sched notrace preempt_schedule_common(void){do {/* * Because the function tracer can trace preempt_count_sub() * and it also uses preempt_enable/disable_notrace(), if * NEED_RESCHED is set, the preempt_enable_notrace() called * by the function tracer will call this function again and * cause infinite recursion. * * Preemption must be disabled here before the function * tracer can trace. Break up preempt_disable() into two * calls. One to disable preemption without fear of being * traced. The other to still record the preemption latency, * which can also be traced by the function tracer. */preempt_disable_notrace();preempt_latency_start(1);//抢占调度__schedule(true);preempt_latency_stop(1);preempt_enable_no_resched_notrace();/* * Check again in case we missed a preemption opportunity * between schedule and now. */} while (need_resched());}#ifdef CONFIG_PREEMPT/* * this is the entry point to schedule() from in-kernel preemption * off of preempt_enable. Kernel preemptions off return from interrupt * occur there and call schedule directly. */asmlinkage __visible void __sched notrace preempt_schedule(void){/* * If there is a non-zero preempt_count or interrupts are disabled, * we do not want to preempt the current task. Just return.. */if (likely(!preemptible()))return;preempt_schedule_common();}NOKPROBE_SYMBOL(preempt_schedule);EXPORT_SYMBOL(preempt_schedule);/** * preempt_schedule_notrace - preempt_schedule called by tracing * * The tracing infrastructure uses preempt_enable_notrace to prevent * recursion and tracing preempt enabling caused by the tracing * infrastructure itself. But as tracing can happen in areas coming * from userspace or just about to enter userspace, a preempt enable * can occur before user_exit() is called. This will cause the scheduler * to be called when the system is still in usermode. * * To prevent this, the preempt_enable_notrace will use this function * instead of preempt_schedule() to exit user context if needed before * calling the scheduler. */asmlinkage __visible void __sched notrace preempt_schedule_notrace(void){enum ctx_state prev_ctx;if (likely(!preemptible()))return;do {/* * Because the function tracer can trace preempt_count_sub() * and it also uses preempt_enable/disable_notrace(), if * NEED_RESCHED is set, the preempt_enable_notrace() called * by the function tracer will call this function again and * cause infinite recursion. * * Preemption must be disabled here before the function * tracer can trace. Break up preempt_disable() into two * calls. One to disable preemption without fear of being * traced. The other to still record the preemption latency, * which can also be traced by the function tracer. */preempt_disable_notrace();preempt_latency_start(1);/* * Needs preempt disabled in case user_exit() is traced * and the tracer calls preempt_enable_notrace() causing * an infinite recursion. */prev_ctx = exception_enter();//抢占调度__schedule(true);exception_exit(prev_ctx);preempt_latency_stop(1);preempt_enable_no_resched_notrace();} while (need_resched());}EXPORT_SYMBOL_GPL(preempt_schedule_notrace);#endif /* CONFIG_PREEMPT *//* * this is the entry point to schedule() from kernel preemption * off of irq context. * Note, that this is called and return with irqs disabled. This will * protect us against recursive calling from irq. */asmlinkage __visible void __sched preempt_schedule_irq(void){enum ctx_state prev_state;/* Catch callers which need to be fixed */BUG_ON(preempt_count() || !irqs_disabled());prev_state = exception_enter();do {preempt_disable();local_irq_enable();//抢占调度__schedule(true);local_irq_disable();sched_preempt_enable_no_resched();} while (need_resched());exception_exit(prev_state);}

//__schedule() is the main scheduler function.static void __sched notrace __schedule(bool preempt){    (1)struct task_struct *prev, *next;unsigned long *switch_count;struct pin_cookie cookie;struct rq *rq;int cpu;    (2)cpu = smp_processor_id();rq = cpu_rq(cpu);prev = rq->curr;(3)if (!preempt && prev->state) {if (unlikely(signal_pending_state(prev->state, prev))) {prev->state = TASK_RUNNING;} else {deactivate_task(rq, prev, DEQUEUE_SLEEP);prev->on_rq = 0;}}(4)next = pick_next_task(rq, prev, cookie);clear_tsk_need_resched(prev);clear_preempt_need_resched();(5)if (likely(prev != next)) {rq->nr_switches++;rq->curr = next;++*switch_count;rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */} else {lockdep_unpin_lock(&rq->lock, cookie);raw_spin_unlock_irq(&rq->lock);}}

struct task_struct *prev, *next;

int cpu = smp_processor_id();struct rq = cpu_rq(cpu);struct task_struct *prev = rq->curr;

#define TASK_RUNNING0#define TASK_INTERRUPTIBLE1#define TASK_UNINTERRUPTIBLE2......

if (!preempt && prev->state) {if (unlikely(signal_pending_state(prev->state, prev))) {prev->state = TASK_RUNNING;} else {deactivate_task(rq, prev, DEQUEUE_SLEEP);prev->on_rq = 0;}}

switch_mm();switch_to(){switch_register();switch_stack();}

/* * context_switch - switch to the new MM and the new thread's register state. */static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev,       struct task_struct *next, struct pin_cookie cookie){struct mm_struct *mm, *oldmm;(1)prepare_task_switch(rq, prev, next);(2)mm = next->mm;oldmm = prev->active_mm;if (!mm) {next->active_mm = oldmm;atomic_inc(&oldmm->mm_count);enter_lazy_tlb(oldmm, next);} elseswitch_mm_irqs_off(oldmm, mm, next);    (3)/* Here we just switch the register state and the stack. */switch_to(prev, next, prev);(4)return finish_task_switch(prev);}

prepare_task_switch(rq, prev, next);-->fire_sched_out_preempt_notifiers(prev, next);   -->__fire_sched_out_preempt_notifiers(curr, next);      -->hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)notifier->ops->sched_out(notifier, next);

struct preempt_ops {void (*sched_in)(struct preempt_notifier *notifier, int cpu);void (*sched_out)(struct preempt_notifier *notifier,  struct task_struct *next);};struct preempt_notifier {struct hlist_node link;struct preempt_ops *ops;};

mm = next->mm;oldmm = prev->active_mm;if (!mm) {   //mm == NULL,代表任务是内核线程//  直接用 被切换进程prev的active_mmnext->active_mm = oldmm;atomic_inc(&oldmm->mm_count);//通知处理器不需要切换虚拟地址空间的用户空间部分，用来加速上下文切换enter_lazy_tlb(oldmm, next);} else//不是内核线程，那么就要切换用户态的虚拟地址空间，也就是切换任务的CR3switch_mm_irqs_off(oldmm, mm, next);-->load_cr3(next->pgd); //加载下一个任务的CR3

switch_to(prev, next, prev);-->__switch_to_asm((prev), (next)))-->ENTRY(__switch_to_asm)/* switch stack */movq%rsp, TASK_threadsp(%rdi)movqTASK_threadsp(%rsi), %rspjmp__switch_toEND(__switch_to_asm)-->__switch_to()

finish_task_switch(prev)-->fire_sched_in_preempt_notifiers(current);-->__fire_sched_in_preempt_notifiers(curr)-->hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)notifier->ops->sched_in(notifier, raw_smp_processor_id());