1.2 进程调度时机
进程调度时机分为3中情况:
(1)schedule()函数:
2865asmlinkage __visible void __sched schedule(void) 2866{ 2867 struct task_struct *tsk = current; 2868 2869 sched_submit_work(tsk); 2870 __schedule(); 2871}
(2)__schedule()函数:
2770static void __sched __schedule(void) 2771{ 2772 struct task_struct *prev, *next; 2773 unsigned long *switch_count; 2774 struct rq *rq; 2775 int cpu; 2776 2777need_resched: 2778 preempt_disable(); //禁止抢占, 2779 cpu = smp_processor_id(); //获取当前CPU的ID 2780 rq = cpu_rq(cpu); //获取当前CPU的运行队列rq(run queue) 2781 rcu_note_context_switch(cpu); 2782 prev = rq->curr; //将被切换出去的进程保存到prev中 2783 2784 schedule_debug(prev); //检查将被切换出去的进程的时间片是否被用完,若时间片用完了,则执行下面的步骤 2785 2786 if (sched_feat(HRTICK)) 2787 hrtick_clear(rq); 2788 2789 /* 2790 * Make sure that signal_pending_state()->signal_pending() below 2791 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) 2792 * done by the caller to avoid the race with signal_wake_up(). 2793 */ 2794 smp_mb__before_spinlock(); 2795 raw_spin_lock_irq(&rq->lock); 2796 2797 switch_count = &prev->nivcsw; 2798 if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { 2799 if (unlikely(signal_pending_state(prev->state, prev))) { //没有待处理的进程,将当前进程置为RUNNING 2800 prev->state = TASK_RUNNING; 2801 } else { 2802 deactivate_task(rq, prev, DEQUEUE_SLEEP); //<span style="font-family: Arial, Helvetica, sans-serif;">有待处理的进程,将当前进程从运行队列中移走</span> 2803 prev->on_rq = 0; //当期进行不在运行队列中 2804 2805 /* 2806 * If a worker went to sleep, notify and ask workqueue 2807 * whether it wants to wake up a task to maintain 2808 * concurrency. 2809 */ 2810 if (prev->flags & PF_WQ_WORKER) { 2811 struct task_struct *to_wakeup; 2812 2813 to_wakeup = wq_worker_sleeping(prev, cpu); 2814 if (to_wakeup) 2815 try_to_wake_up_local(to_wakeup); 2816 } 2817 } 2818 switch_count = &prev->nvcsw; 2819 } 2820 2821 if (task_on_rq_queued(prev) || rq->skip_clock_update < 0) 2822 update_rq_clock(rq); 2823 2824 next = pick_next_task(rq, prev); //这句是核心代码,包含了进程调度策略,即寻找下一个合适的进程以将其调度进来 2825 clear_tsk_need_resched(prev); 2826 clear_preempt_need_resched(); 2827 rq->skip_clock_update = 0; 2828 2829 if (likely(prev != next)) { //下一个进程不是当前进程 2830 rq->nr_switches++; 2831 rq->curr = next; //将运行队列的当前进程指向被选中的进程 2832 ++*switch_count; 2833 2834 context_switch(rq, prev, next); //切换到新进程后,需要进程切换进程上下文,该函数即完成该功能 2835 /* 2836 * The context switch have flipped the stack from under us 2837 * and restored the local variables which were saved when 2838 * this task called schedule() in the past. prev == current 2839 * is still correct, but it can be moved to another cpu/rq. 2840 */ 2841 cpu = smp_processor_id(); 2842 rq = cpu_rq(cpu); 2843 } else 2844 raw_spin_unlock_irq(&rq->lock); 2845 2846 post_schedule(rq); 2847 2848 sched_preempt_enable_no_resched(); 2849 if (need_resched()) //被切换进来的进程仍需要被调度,则返回至need_resched,才能重新调度 2850 goto need_resched; 2851}
(3)context_switch() //完成切换进程上下文
2336context_switch(struct rq *rq, struct task_struct *prev, 2337 struct task_struct *next) 2338{ 2339 struct mm_struct *mm, *oldmm; 2340 2341 prepare_task_switch(rq, prev, next); 2342 2343 mm = next->mm; 2344 oldmm = prev->active_mm; 2345 /* 2346 * For paravirt, this is coupled with an exit in switch_to to 2347 * combine the page table reload and the switch backend into 2348 * one hypercall. 2349 */ 2350 arch_start_context_switch(prev); 2351 2352 if (!mm) { //内核线程,无需切换进程上下文 2353 next->active_mm = oldmm; //内核线程active_mm将借用上一个进程的active_mm 2354 atomic_inc(&oldmm->mm_count); 2355 enter_lazy_tlb(oldmm, next); 2356 } else 2357 switch_mm(oldmm, mm, next); 2358 2359 if (!prev->mm) { //如果被切换出去的进程是内核线程 2360 prev->active_mm = NULL; 2361 rq->prev_mm = oldmm; //则需要归还oldmm 2362 } 2363 /* 2364 * Since the runqueue lock will be released by the next 2365 * task (which is an invalid locking op but in the case 2366 * of the scheduler it's an obvious special-case), so we 2367 * do an early lockdep release here: 2368 */ 2369 spin_release(&rq->lock.dep_map, 1, _THIS_IP_); 2370 2371 context_tracking_task_switch(prev, next); 2372 /* Here we just switch the register state and the stack. */ 2373 switch_to(prev, next, prev); //该函数进行堆栈和寄存器的切换,switch_to函数主要是汇编代码,进行最底层的切换 2374 2375 barrier(); 2376 /* 2377 * this_rq must be evaluated again because prev may have moved 2378 * CPUs since it called schedule(), thus the 'rq' on its stack 2379 * frame will be invalid. 2380 */ 2381 finish_task_switch(this_rq(), prev); 2382}(4)switch_to()函数:(重点理解)
31#define switch_to(prev, next, last) \ 32do { \ 33 /* \ 34 * Context-switching clobbers all registers, so we clobber \ 35 * them explicitly, via unused output variables. \ 36 * (EAX and EBP is not listed because EBP is saved/restored \ 37 * explicitly for wchan access and EAX is the return value of \ 38 * __switch_to()) \ 39 */ \ 40 unsigned long ebx, ecx, edx, esi, edi; \ 41 \ 42 asm volatile("pushfl\n\t" /* save flags */ \ 43 "pushl %%ebp\n\t" /* save EBP */ \ 44 "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ //44 and 45行完成内核堆栈的切换 45 "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ 46 "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ //切换到新进程是从标号1开始执行,但切换到子进程一般是从ret_from_fork开始执行,即next_ip一般是$1f,对于新创建的子进程是ret_from_fork 47 "pushl %[next_ip]\n\t" /* restore EIP */ \ //将EIP的值加入到next_ip进程的堆栈中 48 __switch_canary \ 49 "jmp __switch_to\n" /* regparm call */ \ 50 "1:\t" \ 51 "popl %%ebp\n\t" /* restore EBP */ \ 52 "popfl\n" /* restore flags */ \ 53 \ 54 /* output parameters */ \ 55 : [prev_sp] "=m" (prev->thread.sp), \ //当前进程的内核堆栈的栈顶 56 [prev_ip] "=m" (prev->thread.ip), \ //当前进程的EIP 57 "=a" (last), \ 58 \ 59 /* clobbered output registers: */ \ 60 "=b" (ebx), "=c" (ecx), "=d" (edx), \ //b 变量放入ebx,c表示放入ecx,d放入edx,S放入si,D放入edi 61 "=S" (esi), "=D" (edi) \ 62 \ 63 __switch_canary_oparam \ 64 \ 65 /* input parameters: */ \ 66 : [next_sp] "m" (next->thread.sp), \ //下一个进程的内核堆栈的栈顶 67 [next_ip] "m" (next->thread.ip), \ //下一个进程的EIP 68 \ 69 /* regparm parameters for __switch_to(): */ \ 70 [prev] "a" (prev), \ 71 [next] "d" (next) \ 72 \ 73 __switch_canary_iparam \ 74 \ 75 : /* reloaded segment registers */ \ 76 "memory"); \ 77} while (0)
3.1 打开实验楼虚拟机,重新clone下载menu文件,之后编译运行,进入调试环境:
3.2 设置断点:schedule,context_switch,switch_to处设置3个断点:
3.3 在gdb环境下,输入命令:c,开始运行程序,可以发现,程序在前面设置的断点:schedule处停下来:
3.4 单步执行程序,发现schedule()函数中调用了context_switch()函数:
3.5 继续执行指令:n
3.6 继续执行程序,会发现context_switch()函数调用了__switch_to()函数:
3.7 单步执行程序,进入switch_to()函数,如下图:
3.8 输入finish命令,执行程序到结束