lab5 深入理解进程切换

__schedule函数

__schedule通过调度算法确定下一个需要调度的进程，之后调用context_switch完成进程的切换。

/*
 * __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_PREEMPTION=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_PREEMPTION 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
 *
 * WARNING: must be called with preemption disabled!
 */
static void __sched notrace __schedule(bool preempt)
{
	struct task_struct *prev, *next;
	unsigned long *switch_count;
	struct rq_flags rf;
	struct rq *rq;
	int cpu;

	cpu = smp_processor_id();
	rq = cpu_rq(cpu);
	prev = rq->curr;

	schedule_debug(prev, preempt);

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

	local_irq_disable();
	rcu_note_context_switch(preempt);

	/*
	 * 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().
	 *
	 * The membarrier system call requires a full memory barrier
	 * after coming from user-space, before storing to rq->curr.
	 */
	rq_lock(rq, &rf);
	smp_mb__after_spinlock();

	/* Promote REQ to ACT */
	rq->clock_update_flags <<= 1;
	update_rq_clock(rq);

	switch_count = &prev->nivcsw;
	if (!preempt && prev->state) {
		if (signal_pending_state(prev->state, prev)) {
			prev->state = TASK_RUNNING;
		} else {
			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);

			if (prev->in_iowait) {
				atomic_inc(&rq->nr_iowait);
				delayacct_blkio_start();
			}
		}
		switch_count = &prev->nvcsw;
	}

	next = pick_next_task(rq, prev, &rf);
	clear_tsk_need_resched(prev);
	clear_preempt_need_resched();

	if (likely(prev != next)) {
		rq->nr_switches++;
		/*
		 * RCU users of rcu_dereference(rq->curr) may not see
		 * changes to task_struct made by pick_next_task().
		 */
		RCU_INIT_POINTER(rq->curr, next);
		/*
		 * The membarrier system call requires each architecture
		 * to have a full memory barrier after updating
		 * rq->curr, before returning to user-space.
		 *
		 * Here are the schemes providing that barrier on the
		 * various architectures:
		 * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
		 *   switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
		 * - finish_lock_switch() for weakly-ordered
		 *   architectures where spin_unlock is a full barrier,
		 * - switch_to() for arm64 (weakly-ordered, spin_unlock
		 *   is a RELEASE barrier),
		 */
		++*switch_count;

		trace_sched_switch(preempt, prev, next);

		/* Also unlocks the rq: */
		rq = context_switch(rq, prev, next, &rf);
	} else {
		rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
		rq_unlock_irq(rq, &rf);
	}

	balance_callback(rq);
}

context_switch函数

函数context_switch完成进程地址空间的切换

content_switch 函数有三个参数：rq、prev、next，其中 rq 指向本次进程切换发生的 running queue；prev 和 next 分别指向切换前后进程的进程描述符。

/*
 * 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 rq_flags *rf)
{
	prepare_task_switch(rq, prev, next);

	/*
	 * 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);

	/*
	 * kernel -> kernel   lazy + transfer active
	 *   user -> kernel   lazy + mmgrab() active
	 *
	 * kernel ->   user   switch + mmdrop() active
	 *   user ->   user   switch
	 */
	if (!next->mm) {                                // to kernel
		enter_lazy_tlb(prev->active_mm, next);

		next->active_mm = prev->active_mm;
		if (prev->mm)                           // from user
			mmgrab(prev->active_mm);
		else
			prev->active_mm = NULL;
	} else {                                        // to user
		membarrier_switch_mm(rq, prev->active_mm, next->mm);
		/*
		 * sys_membarrier() requires an smp_mb() between setting
		 * rq->curr / membarrier_switch_mm() and returning to userspace.
		 *
		 * The below provides this either through switch_mm(), or in
		 * case 'prev->active_mm == next->mm' through
		 * finish_task_switch()'s mmdrop().
		 */
		switch_mm_irqs_off(prev->active_mm, next->mm, next);

		if (!prev->mm) {                        // from kernel
			/* will mmdrop() in finish_task_switch(). */
			rq->prev_mm = prev->active_mm;
			prev->active_mm = NULL;
		}
	}

	rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);

	prepare_lock_switch(rq, next, rf);

	/* Here we just switch the register state and the stack. */
	switch_to(prev, next, prev);
	barrier();

	return finish_task_switch(prev);
}

switch_to函数

切换寄存器状态和栈

#define switch_to(prev, next, last)					\
do {												\
	prepare_switch_to(next);						\
													\
	((last) = __switch_to_asm((prev), (next)));		\
} while (0)