Linux进场调度-中断/系统调用调度与进程的调度类型

中断调度/系统调用调度时机

本文主要以linux-3.10为源码分析学习。

中断调度

中断通用的入口，为前文中断概述中讲述的common_interrupt。

common_interrupt:
	XCPT_FRAME
	ASM_CLAC
	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
	interrupt do_IRQ     # 调用中断处理函数进行处理
	/* 0(%rsp): old_rsp-ARGOFFSET */
ret_from_intr:                   # 中断处理返回
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	decl PER_CPU_VAR(irq_count)

	/* Restore saved previous stack */
	popq %rsi
	CFI_DEF_CFA rsi,SS+8-RBP	/* reg/off reset after def_cfa_expr */
	leaq ARGOFFSET-RBP(%rsi), %rsp
	CFI_DEF_CFA_REGISTER	rsp
	CFI_ADJUST_CFA_OFFSET	RBP-ARGOFFSET

exit_intr:
	GET_THREAD_INFO(%rcx)
	testl $3,CS-ARGOFFSET(%rsp)
	je retint_kernel    # 是否返回内核状态
	/* Interrupt came from user space */
	/*
	 * Has a correct top of stack, but a partial stack frame
	 * %rcx: thread info. Interrupts off.
	 */
retint_with_reschedule:    # 检查是否需要进行调度
	movl $_TIF_WORK_MASK,%edi
retint_check:
	LOCKDEP_SYS_EXIT_IRQ
	movl TI_flags(%rcx),%edx
	andl %edi,%edx
	CFI_REMEMBER_STATE
	jnz  retint_careful

retint_swapgs:		/* return to user-space */
	/*
	 * The iretq could re-enable interrupts:
	 */
	DISABLE_INTERRUPTS(CLBR_ANY)
	TRACE_IRQS_IRETQ
	SWAPGS
	jmp restore_args

retint_restore_args:	/* return to kernel space */
	DISABLE_INTERRUPTS(CLBR_ANY)
	/*
	 * The iretq could re-enable interrupts:
	 */
	TRACE_IRQS_IRETQ
restore_args:
	RESTORE_ARGS 1,8,1

irq_return:
	INTERRUPT_RETURN
	_ASM_EXTABLE(irq_return, bad_iret)

#ifdef CONFIG_PARAVIRT
ENTRY(native_iret)
	iretq
	_ASM_EXTABLE(native_iret, bad_iret)
#endif

	.section .fixup,"ax"
bad_iret:
	/*
	 * The iret traps when the %cs or %ss being restored is bogus.
	 * We've lost the original trap vector and error code.
	 * #GPF is the most likely one to get for an invalid selector.
	 * So pretend we completed the iret and took the #GPF in user mode.
	 *
	 * We are now running with the kernel GS after exception recovery.
	 * But error_entry expects us to have user GS to match the user %cs,
	 * so swap back.
	 */
	pushq $0

	SWAPGS
	jmp general_protection

	.previous

	/* edi: workmask, edx: work */
retint_careful:
	CFI_RESTORE_STATE
	bt    $TIF_NEED_RESCHED,%edx   # 检查调度标致位
	jnc   retint_signal            # 处理之前先处理信号
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	pushq_cfi %rdi
	SCHEDULE_USER                  # 调用主动调取
	popq_cfi %rdi
	GET_THREAD_INFO(%rcx)
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	jmp retint_check

retint_signal:
	testl $_TIF_DO_NOTIFY_MASK,%edx
	jz    retint_swapgs
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	SAVE_REST
	movq $-1,ORIG_RAX(%rsp)
	xorl %esi,%esi		# oldset
	movq %rsp,%rdi		# &pt_regs
	call do_notify_resume
	RESTORE_REST
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	GET_THREAD_INFO(%rcx)
	jmp retint_with_reschedule   # 检查是否需要再调度

#ifdef CONFIG_PREEMPT
	/* Returning to kernel space. Check if we need preemption */
	/* rcx:	 threadinfo. interrupts off. */
ENTRY(retint_kernel)
	cmpl $0,TI_preempt_count(%rcx)   # 检查是否加锁
	jnz  retint_restore_args
	bt  $TIF_NEED_RESCHED,TI_flags(%rcx)  # 判断调度标志位是否需要调度
	jnc  retint_restore_args
	bt   $9,EFLAGS-ARGOFFSET(%rsp)	/* interrupts off? */
	jnc  retint_restore_args
	call preempt_schedule_irq          # 主动调度
	jmp exit_intr
#endif

其中preempt_schedule_irq函数就是调用主动调度的函数，如下。

asmlinkage void __sched preempt_schedule_irq(void)
{
	struct thread_info *ti = current_thread_info();
	enum ctx_state prev_state;

	/* Catch callers which need to be fixed */
	BUG_ON(ti->preempt_count || !irqs_disabled());

	prev_state = exception_enter();

	do {
		add_preempt_count(PREEMPT_ACTIVE);
		local_irq_enable();
		__schedule();   // 主动调度
		local_irq_disable();
		sub_preempt_count(PREEMPT_ACTIVE);

		/*
		 * Check again in case we missed a preemption opportunity
		 * between schedule and now.
		 */
		barrier();
	} while (need_resched());

	exception_exit(prev_state);
}

系统调用

在Linux系统中，系统调用的方式主要就是常见的三种形式。

1. 通过int 80陷入内核进行系统调用。
2. 通过Intel32位sysenter/sysexit快速系统调用。
3. 通过64位模式下的syscall/sysret快速系统调用。

其中方式1为Linux传统的系统调用的方式该方式需要陷入通过中断陷入内核，执行完成之后再返回用户空间，主要的问题就是通过软中断效率较低，故方式2、3就是为了避开频繁的中断来提高系统调用的效率，其主要原理是通过将运行的可执行文件执行一个vdso的映射的__kernel_vsyscall函数，从而能够提升效率快速进行系统调用。

syscall初始化(64位)

在进行trap_init->cpu_init->syscall_init，初始化快速调用的处理函数。

void syscall_init(void)
{
	/*
	 * LSTAR and STAR live in a bit strange symbiosis.
	 * They both write to the same internal register. STAR allows to
	 * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
	 */
	wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
	wrmsrl(MSR_LSTAR, system_call);  //设置处理的回调函数
	wrmsrl(MSR_CSTAR, ignore_sysret);

#ifdef CONFIG_IA32_EMULATION
	syscall32_cpu_init();
#endif

	/* Flags to clear on syscall */
	wrmsrl(MSR_SYSCALL_MASK,
	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
	       X86_EFLAGS_IOPL|X86_EFLAGS_AC);
}

MSR_LSTAR代表的就是快速回调处理的函数即system_call函数。详细的可咨询查阅syscall的资料。

int 80初始化

在调用trap_init->set_system_trap_gate(SYSCALL_VECTOR, &system_call);

此时就是设置的80为符合的中断处理函数。

# define SYSCALL_VECTOR			0x80

system_call流程

ENTRY(system_call)
	CFI_STARTPROC	simple
	CFI_SIGNAL_FRAME
	CFI_DEF_CFA	rsp,KERNEL_STACK_OFFSET
	CFI_REGISTER	rip,rcx
	/*CFI_REGISTER	rflags,r11*/
	SWAPGS_UNSAFE_STACK
	/*
	 * A hypervisor implementation might want to use a label
	 * after the swapgs, so that it can do the swapgs
	 * for the guest and jump here on syscall.
	 */
GLOBAL(system_call_after_swapgs)

	movq	%rsp,PER_CPU_VAR(old_rsp)
	movq	PER_CPU_VAR(kernel_stack),%rsp
	/*
	 * No need to follow this irqs off/on section - it's straight
	 * and short:
	 */
	ENABLE_INTERRUPTS(CLBR_NONE)
	SAVE_ARGS 8,0
	movq  %rax,ORIG_RAX-ARGOFFSET(%rsp)
	movq  %rcx,RIP-ARGOFFSET(%rsp)
	CFI_REL_OFFSET rip,RIP-ARGOFFSET
	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
	jnz tracesys
system_call_fastpath:
#if __SYSCALL_MASK == ~0
	cmpq $__NR_syscall_max,%rax
#else
	andl $__SYSCALL_MASK,%eax
	cmpl $__NR_syscall_max,%eax
#endif
	ja badsys
	movq %r10,%rcx
	call *sys_call_table(,%rax,8)  # XXX:	 rip relative   // 跳入系统调用的回调函数执行
	movq %rax,RAX-ARGOFFSET(%rsp)
/*
 * Syscall return path ending with SYSRET (fast path)
 * Has incomplete stack frame and undefined top of stack.
 */
ret_from_sys_call:      # 返回检查系统调用
	movl $_TIF_ALLWORK_MASK,%edi
	/* edi:	flagmask */
sysret_check:
	LOCKDEP_SYS_EXIT
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	movl TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET),%edx
	andl %edi,%edx
	jnz  sysret_careful
	CFI_REMEMBER_STATE
	/*
	 * sysretq will re-enable interrupts:
	 */
	TRACE_IRQS_ON
	movq RIP-ARGOFFSET(%rsp),%rcx
	CFI_REGISTER	rip,rcx
	RESTORE_ARGS 1,-ARG_SKIP,0
	/*CFI_REGISTER	rflags,r11*/
	movq	PER_CPU_VAR(old_rsp), %rsp
	USERGS_SYSRET64

	CFI_RESTORE_STATE
	/* Handle reschedules */
	/* edx:	work, edi: workmask */
sysret_careful:
	bt $TIF_NEED_RESCHED,%edx    # 检查是否需要调度，
	jnc sysret_signal            # 检查是否需要处理信号，优先处理信号
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	pushq_cfi %rdi
	SCHEDULE_USER                # 进行调度
	popq_cfi %rdi
	jmp sysret_check
	
	/* Handle a signal */
sysret_signal:
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
#ifdef CONFIG_AUDITSYSCALL
	bt $TIF_SYSCALL_AUDIT,%edx
	jc sysret_audit
#endif
	/*
	 * We have a signal, or exit tracing or single-step.
	 * These all wind up with the iret return path anyway,
	 * so just join that path right now.
	 */
	FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
	jmp int_check_syscall_exit_work

badsys:
	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
	jmp ret_from_sys_call

#ifdef CONFIG_AUDITSYSCALL
	/*
	 * Fast path for syscall audit without full syscall trace.
	 * We just call __audit_syscall_entry() directly, and then
	 * jump back to the normal fast path.
	 */
auditsys:
	movq %r10,%r9			/* 6th arg: 4th syscall arg */
	movq %rdx,%r8			/* 5th arg: 3rd syscall arg */
	movq %rsi,%rcx			/* 4th arg: 2nd syscall arg */
	movq %rdi,%rdx			/* 3rd arg: 1st syscall arg */
	movq %rax,%rsi			/* 2nd arg: syscall number */
	movl $AUDIT_ARCH_X86_64,%edi	/* 1st arg: audit arch */
	call __audit_syscall_entry
	LOAD_ARGS 0		/* reload call-clobbered registers */
	jmp system_call_fastpath

	/*
	 * Return fast path for syscall audit.  Call __audit_syscall_exit()
	 * directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
	 * masked off.
	 */
sysret_audit:
	movq RAX-ARGOFFSET(%rsp),%rsi	/* second arg, syscall return value */
	cmpq $-MAX_ERRNO,%rsi	/* is it < -MAX_ERRNO? */
	setbe %al		/* 1 if so, 0 if not */
	movzbl %al,%edi		/* zero-extend that into %edi */
	call __audit_syscall_exit
	movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
	jmp sysret_check
#endif	/* CONFIG_AUDITSYSCALL */

	/* Do syscall tracing */
tracesys:
#ifdef CONFIG_AUDITSYSCALL
	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
	jz auditsys
#endif
	SAVE_REST
	movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
	FIXUP_TOP_OF_STACK %rdi
	movq %rsp,%rdi
	call syscall_trace_enter
	/*
	 * Reload arg registers from stack in case ptrace changed them.
	 * We don't reload %rax because syscall_trace_enter() returned
	 * the value it wants us to use in the table lookup.
	 */
	LOAD_ARGS ARGOFFSET, 1
	RESTORE_REST
#if __SYSCALL_MASK == ~0
	cmpq $__NR_syscall_max,%rax
#else
	andl $__SYSCALL_MASK,%eax
	cmpl $__NR_syscall_max,%eax
#endif
	ja   int_ret_from_sys_call	/* RAX(%rsp) set to -ENOSYS above */
	movq %r10,%rcx	/* fixup for C */
	call *sys_call_table(,%rax,8)
	movq %rax,RAX-ARGOFFSET(%rsp)
	/* Use IRET because user could have changed frame */

/*
 * Syscall return path ending with IRET.
 * Has correct top of stack, but partial stack frame.
 */
GLOBAL(int_ret_from_sys_call)
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	movl $_TIF_ALLWORK_MASK,%edi
	/* edi:	mask to check */
GLOBAL(int_with_check)
	LOCKDEP_SYS_EXIT_IRQ
	GET_THREAD_INFO(%rcx)
	movl TI_flags(%rcx),%edx
	andl %edi,%edx
	jnz   int_careful
	andl    $~TS_COMPAT,TI_status(%rcx)
	jmp   retint_swapgs

	/* Either reschedule or signal or syscall exit tracking needed. */
	/* First do a reschedule test. */
	/* edx:	work, edi: workmask */
int_careful:
	bt $TIF_NEED_RESCHED,%edx   # 检查是否需要调度 
	jnc  int_very_careful
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
	pushq_cfi %rdi
	SCHEDULE_USER         # 主动调度
	popq_cfi %rdi
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	jmp int_with_check

	/* handle signals and tracing -- both require a full stack frame */
int_very_careful:
	TRACE_IRQS_ON
	ENABLE_INTERRUPTS(CLBR_NONE)
int_check_syscall_exit_work:
	SAVE_REST
	/* Check for syscall exit trace */
	testl $_TIF_WORK_SYSCALL_EXIT,%edx
	jz int_signal
	pushq_cfi %rdi
	leaq 8(%rsp),%rdi	# &ptregs -> arg1
	call syscall_trace_leave
	popq_cfi %rdi
	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
	jmp int_restore_rest

int_signal:
	testl $_TIF_DO_NOTIFY_MASK,%edx
	jz 1f
	movq %rsp,%rdi		# &ptregs -> arg1
	xorl %esi,%esi		# oldset -> arg2
	call do_notify_resume
1:	movl $_TIF_WORK_MASK,%edi
int_restore_rest:
	RESTORE_REST
	DISABLE_INTERRUPTS(CLBR_NONE)
	TRACE_IRQS_OFF
	jmp int_with_check
	CFI_ENDPROC
END(system_call)

其中SCHEDULE_USER的定义如下

#ifdef CONFIG_CONTEXT_TRACKING
# define SCHEDULE_USER call schedule_user
#else
# define SCHEDULE_USER call schedule
#endif

调用schedule相关函数。至此中断调度和系统调用的时机检查基本如上流程。

进程的调度类型

在进程进行schedule的时候会选择下一个需要调度的进程。

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();   // 获取当前的cpu
	rq = cpu_rq(cpu);           // 获取当前的调度队列
	rcu_note_context_switch(cpu);
	prev = rq->curr;            // 获取当前进程
	...

	pre_schedule(rq, prev);

	if (unlikely(!rq->nr_running))
		idle_balance(cpu, rq);

	put_prev_task(rq, prev);  // 放置当前进程到队列中
	next = pick_next_task(rq);    // 选择下一个待执行进程
	clear_tsk_need_resched(prev);
	rq->skip_clock_update = 0;
	
  ...
}

调度的主要流程就是选择下一个可执行的进程pick_next_task。

static inline struct task_struct *
pick_next_task(struct rq *rq)
{
	const struct sched_class *class;
	struct task_struct *p;

	/*
	 * Optimization: we know that if all tasks are in
	 * the fair class we can call that function directly:
	 */
	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {  // 如果当前的都是cfs进程则直接进行调度
		p = fair_sched_class.pick_next_task(rq);
		if (likely(p))
			return p;
	}

	for_each_class(class) {
		p = class->pick_next_task(rq);  // 便利每一个class分别选用不用的策略来进行调度
		if (p)
			return p;
	}

	BUG(); /* the idle class will always have a runnable task */
}

...
  
#define sched_class_highest (&stop_sched_class)
#define for_each_class(class) \
   for (class = sched_class_highest; class; class = class->next)

此时就是从stop_sched_class开始一路往最低优先级便利选择。

stop_sched_class->rt_sched_class->fair_sched_class->idle_sched_class

优先级如上所示，先是stop_sched_class，再是实时进程，然后是cfs公平调度算法，最后就是空闲算法。每个class都调度pick_next_task函数来选择下一个运行的进程。

stop_sched_class

static struct task_struct *pick_next_task_stop(struct rq *rq)
{
	struct task_struct *stop = rq->stop;

	if (stop && stop->on_rq) {
		stop->se.exec_start = rq->clock_task;  // 检查是否有 有则选择stop的进程
		return stop;
	}

	return NULL;  // 否则返回空
}

该类用在内核任务，迁移任务时采用。

rt_sched_class

static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
						   struct rt_rq *rt_rq)
{
	struct rt_prio_array *array = &rt_rq->active;
	struct sched_rt_entity *next = NULL;
	struct list_head *queue;
	int idx;

	idx = sched_find_first_bit(array->bitmap);  // 比较进程的优先级 根据优先级选择进程
	BUG_ON(idx >= MAX_RT_PRIO);

	queue = array->queue + idx;
	next = list_entry(queue->next, struct sched_rt_entity, run_list);

	return next;
}

static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
	struct sched_rt_entity *rt_se;
	struct task_struct *p;
	struct rt_rq *rt_rq;

	rt_rq = &rq->rt;

	if (!rt_rq->rt_nr_running)
		return NULL;

	if (rt_rq_throttled(rt_rq))
		return NULL;

	do {
		rt_se = pick_next_rt_entity(rq, rt_rq);  // 获取下一个高优先级进程
		BUG_ON(!rt_se);
		rt_rq = group_rt_rq(rt_se);  // 选择下一个优先组队列
	} while (rt_rq);

	p = rt_task_of(rt_se);
	p->se.exec_start = rq->clock_task;  // 设置

	return p;
}

static struct task_struct *pick_next_task_rt(struct rq *rq)
{
	struct task_struct *p = _pick_next_task_rt(rq);  // 选择下一个进程

	/* The running task is never eligible for pushing */
	if (p)
		dequeue_pushable_task(rq, p);

#ifdef CONFIG_SMP
	/*
	 * We detect this state here so that we can avoid taking the RQ
	 * lock again later if there is no need to push
	 */
	rq->post_schedule = has_pushable_tasks(rq);
#endif

	return p;
}

主要是通过优先级来进行选择下一个待运行的进程，该调度策略为实时调度策略，在进程响应要求较高的时候优势比较明显。

fair_sched_class

该策略为公平调度策略，是当前应用较为广泛的一种调度策略，将进程分为不同的调度组，根据组的运行的整体时间来进行调度。

static struct task_struct *pick_next_task_fair(struct rq *rq)
{
	struct task_struct *p;
	struct cfs_rq *cfs_rq = &rq->cfs;
	struct sched_entity *se;

	if (!cfs_rq->nr_running)
		return NULL;

	do {
		se = pick_next_entity(cfs_rq);  // 选择下一个调度实体
		set_next_entity(cfs_rq, se);
		cfs_rq = group_cfs_rq(se);
	} while (cfs_rq);

	p = task_of(se);
	if (hrtick_enabled(rq))
		hrtick_start_fair(rq, p);    // 选择调度实体中可调度的进程

	return p;
}

/*
 * Pick the next process, keeping these things in mind, in this order:
 * 1) keep things fair between processes/task groups
 * 2) pick the "next" process, since someone really wants that to run
 * 3) pick the "last" process, for cache locality
 * 4) do not run the "skip" process, if something else is available
 */
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
	struct sched_entity *se = __pick_first_entity(cfs_rq);  // 获取下一个运行的节点
	struct sched_entity *left = se;

	/*
	 * Avoid running the skip buddy, if running something else can
	 * be done without getting too unfair.
	 */
	if (cfs_rq->skip == se) {   // 是否skip如果跳过则选择下一个
		struct sched_entity *second = __pick_next_entity(se);  // 
		if (second && wakeup_preempt_entity(second, left) < 1)
			se = second;
	}

	/*
	 * Prefer last buddy, try to return the CPU to a preempted task.
	 */
	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
		se = cfs_rq->last;  

	/*
	 * Someone really wants this to run. If it's not unfair, run it.
	 */
	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
		se = cfs_rq->next;

	clear_buddies(cfs_rq, se);

	return se;
}


static struct sched_entity *__pick_next_entity(struct sched_entity *se)
{
	struct rb_node *next = rb_next(&se->run_node);  // 获取树中最小的节点运行

	if (!next)
		return NULL;

	return rb_entry(next, struct sched_entity, run_node); // 获取节点
}

因为cfs基于红黑树来进行组织的故在获取调度进程的时候可直接选择，下一个待调度组织的最少执行节点进程，其中有关进程的运行和计算的内容会跟随schedule_tick来给进程进行标记（有机会后续分析）。

idle_sched_class

static struct task_struct *pick_next_task_idle(struct rq *rq)
{
	schedstat_inc(rq, sched_goidle);
#ifdef CONFIG_SMP
	/* Trigger the post schedule to do an idle_enter for CFS */
	rq->post_schedule = 1;
#endif
	return rq->idle;
}

这个空闲的进程是在start_kernel之后，给每个cpu都复制了一个进程。

kernel_init->kernel_init_freeable->smp_init->idle_threads_init->idle_init->fork_idle->idle_init->

struct task_struct * __cpuinit fork_idle(int cpu)
{
	struct task_struct *task;
	task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0); // 拷贝0号进场当做idle进场
	if (!IS_ERR(task)) {
		init_idle_pids(task->pids);
		init_idle(task, cpu);  // 设置task相关信息
	}

	return task;
}

此时init_struct_pid就是初始化的进程，即拷贝的进程运行如下逻辑。

start_kernel->rest_init->cpu_startup_entry流程，

// idle.c
void cpu_startup_entry(enum cpuhp_state state)
{
	/*
	 * This #ifdef needs to die, but it's too late in the cycle to
	 * make this generic (arm and sh have never invoked the canary
	 * init for the non boot cpus!). Will be fixed in 3.11
	 */
#ifdef CONFIG_X86
	/*
	 * If we're the non-boot CPU, nothing set the stack canary up
	 * for us. The boot CPU already has it initialized but no harm
	 * in doing it again. This is a good place for updating it, as
	 * we wont ever return from this function (so the invalid
	 * canaries already on the stack wont ever trigger).
	 */
	boot_init_stack_canary();
#endif
	current_set_polling();
	arch_cpu_idle_prepare();
	cpu_idle_loop();
}

/*
 * Generic idle loop implementation
 */
static void cpu_idle_loop(void)
{
	while (1) {
		tick_nohz_idle_enter();

		while (!need_resched()) {  // 检查是否需要调度
			check_pgt_cache();
			rmb();

			if (cpu_is_offline(smp_processor_id()))
				arch_cpu_idle_dead();

			local_irq_disable();
			arch_cpu_idle_enter();

			/*
			 * In poll mode we reenable interrupts and spin.
			 *
			 * Also if we detected in the wakeup from idle
			 * path that the tick broadcast device expired
			 * for us, we don't want to go deep idle as we
			 * know that the IPI is going to arrive right
			 * away
			 */
			if (cpu_idle_force_poll || tick_check_broadcast_expired()) {
				cpu_idle_poll();
			} else {
				current_clr_polling();
				if (!need_resched()) {
					stop_critical_timings();
					rcu_idle_enter();
					arch_cpu_idle();
					WARN_ON_ONCE(irqs_disabled());
					rcu_idle_exit();
					start_critical_timings();
				} else {
					local_irq_enable();
				}
				current_set_polling();
			}
			arch_cpu_idle_exit();
		}
		tick_nohz_idle_exit();
		schedule_preempt_disabled();  // 检查是否需要调度其他进程
	}
}

此时如上就是每个cpu都会被调度到的idle的进程主要就是检查是否有需要调度的进程然后进行调度。

总结

本文主要就是了解了一下中断调度和系统调用的场景下的调度时机，有关中断和系统调用的逻辑流程本文没有深入学习（可查阅相关资料），在了解了调度时机之后在了解了有关进程调度的类型，在Linux3.10中有四种调度的类型，本文也并没有深入去分析每个调度类的具体的逻辑详细，只是简单的概述了rt的优先级和cfs公平调度的红黑树的选择下一个进场的内容，后续有机会再深入学习。由于本人才疏学浅，如有错误请批评指正。

https://zhuanlan.zhihu.com/p/79236207

https://www.cnblogs.com/hellokitty2/p/16703115.html