Arm-linux的进程调度（1）

1、大家应该都知道到Linux内核的用于进程调度的主要函数就是schedule函数，当然要进行进程调度，有许多条件需要满足，现在假设所有的条件都已经满足，要进行调度了。

/*

 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;


need_resched:
........


#ifdef CONFIG_SMP
.........
#endif


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


prev->sched_class->put_prev_task(rq, prev);
next = pick_next_task(rq, prev);应该是选择出下一个需要运行的进程，当然很复杂，与进程的三种分类和优先级都有关系，就不细讲了。


if (likely(prev != next)) {
sched_info_switch(prev, next);


rq->nr_switches++;
rq->curr = next;
++*switch_count;

context_switch(rq, prev, next); /* unlocks the rq */

我们重点讲这个函数，先列出它的源码：如下所示：

/*
 * context_switch - switch to the new MM and the new
 * thread's register state.看注释，即可知道这个函数的主要作用，就是切换MM（内存管理方面的）和thread（CPU此时的状态）
 */
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);对ARM来说是空函数
trace_sched_switch(rq, prev, next);
mm = next->mm;
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_enter_lazy_cpu_mode();


if (unlikely(!mm)) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
switch_mm(oldmm, mm, next);

数据结构mm_struct描述着一个地址空间，每个进程控制块中有两个mm_struct结构指针。一个是mm,指向描述着本进程运行空间的mm_struct结构，如果mm为NULL，就表示本进程是个线程。而active_mm则指向进程或线程实际使用的空间，如果是线程就指向其所“挂靠”进程的空间。“内核线程”则使用系统空间，其指针active_mm指向描述这内核空间的mm_struct结构。下面是struct task_struct结构中的一小段

struct list_head tasks;


struct mm_struct *mm, *active_mm;


/* task state */
struct linux_binfmt *binfmt;
int exit_state;
int exit_code, exit_signal;
int pdeath_signal;  /*  The signal sent when the parent dies  */
/* ??? */
unsigned int personality;
unsigned did_exec:1;
pid_t pid;
pid_t tgid;

现在列出switch_mm函数的源码，如下所示：

/*
 * This is the actual mm switch as far as the scheduler
 * is concerned.  No registers are touched.  We avoid
 * calling the CPU specific function when the mm hasn't
 * actually changed.
 */
static inline void
switch_mm(struct mm_struct *prev, struct mm_struct *next,
 struct task_struct *tsk)
{
#ifdef CONFIG_MMU
unsigned int cpu = smp_processor_id();


#ifdef CONFIG_SMP
/* check for possible thread migration */
if (!cpus_empty(next->cpu_vm_mask) && !cpu_isset(cpu, next->cpu_vm_mask))
__flush_icache_all();
#endif
if (!cpu_test_and_set(cpu, next->cpu_vm_mask) || prev != next) {
check_context(next);
cpu_switch_mm(next->pgd, next);

切换空间，实际上就是换一套页面映射目录和映射表。看下这个宏的展开：

#define cpu_switch_mm(pgd,mm) cpu_do_switch_mm(virt_to_phys(pgd),mm)

#define cpu_do_switch_mm(pgd,mm)processor.switch_mm(pgd,mm)

出现了一个新的结构体

/*
 * Don't change this structure - ASM code
 * relies on it.
 */
extern struct processor {
/* MISC
* get data abort address/flags
*/
void (*_data_abort)(unsigned long pc);
/*
* Retrieve prefetch fault address
*/
unsigned long (*_prefetch_abort)(unsigned long lr);
/*
* Set up any processor specifics
*/
void (*_proc_init)(void);
/*
* Disable any processor specifics
*/
void (*_proc_fin)(void);
/*
* Special stuff for a reset
*/
void (*reset)(unsigned long addr) __attribute__((noreturn));
/*
* Idle the processor
*/
int (*_do_idle)(void);
/*
* Processor architecture specific
*/
/*
* clean a virtual address range from the
* D-cache without flushing the cache.
*/
void (*dcache_clean_area)(void *addr, int size);


/*
* Set the page table
*/
void (*switch_mm)(unsigned long pgd_phys, struct mm_struct *mm);
/*
* Set a possibly extended PTE.  Non-extended PTEs should
* ignore 'ext'.
*/
void (*set_pte_ext)(pte_t *ptep, pte_t pte, unsigned int ext);
} processor;

一看就知道这个结构应该和具体CPU有关，而却成员都是函数指针，那么这些函数指针在你赋值的呢？

举个例子，如下所示：在文件linux/arch/arm/mm/proc-sa110.S有如下定义：

.typesa110_processor_functions, #object
ENTRY(sa110_processor_functions)
.word v4_early_abort
.word pabort_noifar
.word cpu_sa110_proc_init
.word cpu_sa110_proc_fin
.word cpu_sa110_reset
.word cpu_sa110_do_idle
.word cpu_sa110_dcache_clean_area
.wordcpu_sa110_switch_mm
.word cpu_sa110_set_pte_ext

对应的有

ENTRY(cpu_sa110_switch_mm)
#ifdef CONFIG_MMU
str lr, [sp, #-4]!
bl v4wb_flush_kern_cache_all@ clears IP
mcrp15, 0, r0, c2, c0, 0 @ load page table pointer

将指向新进程的首层映射表的指针写入MMU中的寄存器c2，即地址转化表基地址寄存器，
mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs

丢掉高速缓存中原有的地址映射表
ldr pc, [sp], #4
#else
mov pc, lr
#endif

这样，CPU的用户空间映射就改变了，但是对当前程序的运行没影响，因为现在CPU运行在系统空间中。

注：进程的调度、切换只能在系统空间中进行。

if (cache_is_vivt())
cpu_clear(cpu, prev->cpu_vm_mask);
}
#endif
}switch_mm函数源码到此结束。

if (unlikely(!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:
*/
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
#endif


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


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);

这一部分，下篇再说。
}context_switch到此结束。

/*
* the context switch might have flipped the stack from under
* us, hence refresh the local variables.
*/
cpu = smp_processor_id();
rq = cpu_rq(cpu);
} else
spin_unlock_irq(&rq->lock);

..........

preempt_enable_no_resched();
if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
goto need_resched;

}schedule函数到此结束

这篇写到这里，也就结束了，我们主要讲述的就是已经找到下一个要运行的进程，现在进行切换，这一篇说的主要是内存管理的切换，即mm_struct结构体。其实，它的切换就是页面目录的切换，当然，不同的处理其会不同。