Linux进程调度

进程的调度时机与进程的切换

操作系统原理中介绍了大量进程调度算法，这些算法从实现的角度看仅仅是从运行队列中选择一个新进程，选择的过程中运用了不同的策略而已。
对于理解操作系统的工作机制，反而是进程的调度时机与进程的切换机制更为关键。

进程调度的时机
中断处理过程（包括时钟中断、I/O中断、系统调用和异常）中，直接调用schedule()，或者返回用户态时根据need_resched标记调用schedule()；
内核线程可以直接调用schedule()进行进程切换，也可以在中断处理过程中进行调度，也就是说内核线程作为一类的特殊的进程可以主动调度，也可以被动调度；
用户态进程无法实现主动调度，仅能通过陷入内核态后的某个时机点进行调度，即在中断处理过程中进行调度。

进程的切换
为了控制进程的执行，内核必须有能力挂起正在CPU上执行的进程，并恢复以前挂起的某个进程的执行，这叫做进程切换、任务切换、上下文切换；
挂起正在CPU上执行的进程，与中断时保存现场是不同的，中断前后是在同一个进程上下文中，只是由用户态转向内核态执行；
进程上下文包含了进程执行需要的所有信息
用户地址空间： 包括程序代码，数据，用户堆栈等
控制信息 ：进程描述符，内核堆栈等
硬件上下文（注意中断也要保存硬件上下文只是保存的方法不同）
schedule()函数选择一个新的进程来运行，并调用context_switch进行上下文的切换，这个宏调用switch_to来进行关键上下文切换
next = pick_next_task(rq, prev);//进程调度算法都封装这个函数内部
context_switch(rq, prev, next);//进程上下文切换

switch_to利用了prev和next两个参数：prev指向当前进程，next指向被调度的进程

schedule()函数源码如下：

/*
 * __schedule() is the main scheduler function.
 *
 * The main means of driving the scheduler and thus entering this function are:
 *
 *   1. Explicit blocking: mutex, semaphore, waitqueue, etc.
 *
 *   2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
 *      paths. For example, see arch/x86/entry_64.S.
 *
 *      To drive preemption between tasks, the scheduler sets the flag in timer
 *      interrupt handler scheduler_tick().
 *
 *   3. Wakeups don't really cause entry into schedule(). They add a
 *      task to the run-queue and that's it.
 *
 *      Now, if the new task added to the run-queue preempts the current
 *      task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
 *      called on the nearest possible occasion:
 *
 *       - If the kernel is preemptible (CONFIG_PREEMPT=y):
 *
 *         - in syscall or exception context, at the next outmost
 *           preempt_enable(). (this might be as soon as the wake_up()'s
 *           spin_unlock()!)
 *
 *         - in IRQ context, return from interrupt-handler to
 *           preemptible context
 *
 *       - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
 *         then at the next:
 *
 *          - cond_resched() call
 *          - explicit schedule() call
 *          - return from syscall or exception to user-space
 *          - return from interrupt-handler to user-space
 */
static void __sched __schedule(void)
{
	struct task_struct *prev, *next;
	unsigned long *switch_count;
	struct rq *rq;
	int cpu;

need_resched:
	preempt_disable();
	cpu = smp_processor_id();
	rq = cpu_rq(cpu);
	rcu_note_context_switch(cpu);
	prev = rq->curr;

	schedule_debug(prev);

	if (sched_feat(HRTICK))
		hrtick_clear(rq);

	/*
	 * Make sure that signal_pending_state()->signal_pending() below
	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
	 * done by the caller to avoid the race with signal_wake_up().
	 */
	smp_mb__before_spinlock();
	raw_spin_lock_irq(&rq->lock);

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

			/*
			 * If a worker went to sleep, notify and ask workqueue
			 * whether it wants to wake up a task to maintain
			 * concurrency.
			 */
			if (prev->flags & PF_WQ_WORKER) {
				struct task_struct *to_wakeup;

				to_wakeup = wq_worker_sleeping(prev, cpu);
				if (to_wakeup)
					try_to_wake_up_local(to_wakeup);
			}
		}
		switch_count = &prev->nvcsw;
	}

	if (task_on_rq_queued(prev) || rq->skip_clock_update < 0)
		update_rq_clock(rq);

	next = pick_next_task(rq, prev);//从等待队列中挑选出下一个等待调度的进程
	clear_tsk_need_resched(prev);
	clear_preempt_need_resched();
	rq->skip_clock_update = 0;

	if (likely(prev != next)) {
		rq->nr_switches++;
		rq->curr = next;
		++*switch_count;

		context_switch(rq, prev, next); /* unlocks the rq ，进行进程上下文的切换*/
		/*
		 * The context switch have flipped the stack from under us
		 * and restored the local variables which were saved when
		 * this task called schedule() in the past. prev == current
		 * is still correct, but it can be moved to another cpu/rq.
		 */
		cpu = smp_processor_id();
		rq = cpu_rq(cpu);
	} else
		raw_spin_unlock_irq(&rq->lock);

	post_schedule(rq);

	sched_preempt_enable_no_resched();
	if (need_resched())
		goto need_resched;
}

context_switch代码如下：

/*
 * context_switch - switch to the new MM and the new
 * thread's register state.
 */
static inline void
context_switch(struct rq *rq, struct task_struct *prev,
	       struct task_struct *next)
{
	struct mm_struct *mm, *oldmm;

	prepare_task_switch(rq, prev, next);

	mm = next->mm;//mm指向了next进程的内存空间
	oldmm = prev->active_mm;
	/*
	 * For paravirt, this is coupled with an exit in switch_to to
	 * combine the page table reload and the switch backend into
	 * one hypercall.
	 */
	arch_start_context_switch(prev);

	if (!mm) {
		next->active_mm = oldmm;
		atomic_inc(&oldmm->mm_count);
		enter_lazy_tlb(oldmm, next);
	} else
		switch_mm(oldmm, mm, next);//进程内存空间切换

	if (!prev->mm) {
		prev->active_mm = NULL;
		rq->prev_mm = oldmm;
	}
	/*
	 * Since the runqueue lock will be released by the next
	 * task (which is an invalid locking op but in the case
	 * of the scheduler it's an obvious special-case), so we
	 * do an early lockdep release here:
	 */
	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);

	context_tracking_task_switch(prev, next);
	/* Here we just switch the register state and the stack. */
	switch_to(prev, next, prev);//进程切换的宏，切换寄存器、栈空间

	barrier();
	/*
	 * this_rq must be evaluated again because prev may have moved
	 * CPUs since it called schedule(), thus the 'rq' on its stack
	 * frame will be invalid.
	 */
	finish_task_switch(this_rq(), prev);
}

swith_to宏的代码如下，这是一段汇编代码，源码中已经注释的很明确了，直接看注释

#define switch_to(prev, next, last)					\
do {									\
	/*								\
	 * Context-switching clobbers all registers, so we clobber	\
	 * them explicitly, via unused output variables.		\
	 * (EAX and EBP is not listed because EBP is saved/restored	\
	 * explicitly for wchan access and EAX is the return value of	\
	 * __switch_to())						\
	 */								\
	unsigned long ebx, ecx, edx, esi, edi;				\
									\
	asm volatile("pushfl\n\t"		/* save    flags */	\
		     "pushl %%ebp\n\t"		/* save    EBP   */	\
		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
		     __switch_canary					\
		     "jmp __switch_to\n"	/* regparm call  */	\
		     "1:\t"						\
		     "popl %%ebp\n\t"		/* restore EBP   */	\
		     "popfl\n"			/* restore flags */	\
									\
		     /* output parameters */				\
		     : [prev_sp] "=m" (prev->thread.sp),		\
		       [prev_ip] "=m" (prev->thread.ip),		\
		       "=a" (last),					\
									\
		       /* clobbered output registers: */		\
		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
		       "=S" (esi), "=D" (edi)				\
		       							\
		       __switch_canary_oparam				\
									\
		       /* input parameters: */				\
		     : [next_sp]  "m" (next->thread.sp),		\
		       [next_ip]  "m" (next->thread.ip),		\
		       							\
		       /* regparm parameters for __switch_to(): */	\
		       [prev]     "a" (prev),				\
		       [next]     "d" (next)				\
									\
		       __switch_canary_iparam				\
									\
		     : /* reloaded segment registers */			\
			"memory");					\
} while (0)