详解ARM Linux 2.4.x进程调度

时间:2011-09-04

  Linux2.4.x是一个基于非抢占式的多任务的分时操作系统,虽然在用户进程的调度上采用抢占式策略,但是而在内核还是采用了轮转的方法,如果有个内核态的线程恶性占有CPU不释放,那系统无法从中解脱出来,所以实时性并不是很强。这种情况有望在Linux 2.6版本中得到改善,在2.6版本中采用了抢占式的调度策略。

  内核中根据任务的实时程度提供了三种调度策略:

  ① SCHED_OTHER为非实时任务,采用常规的分时调度策略;

  ② SCHED_FIFO为短小的实时任务,采用先进先出式调度,除非有更高优先级进程申请运行,否则该进程将保持运行至退出才让出CPU;

  ③ SCHED_RR任务较长的实时任务,由于任务较长,不能采用FIFO的策略,而是采用轮转式调度,该进程被调度下来后将被置于运行队列的末尾,以保证其他实时进程有机会运行。

  在上述三种调度策略的基础上,进程依照优先级的高低被分别调系统。优先级是一些简单的整数,它代表了为决定应该允许哪一个进程使用CPU的资源时判断方便而赋予进程的权值——优先级越高,它得到CPU时间的机会也就越大。

  在Linux中,非实时进程有两种优先级,一种是静态优先级,另一种是动态优先级。实时进程又增加了第三种优先级,实时优先级。

  ① 静态优先级(priority)——被称为“静态”是因为它不随时间而改变,只能由用户进行修改。它指明了在被迫和其它进程竞争CPU之前该进程所应该被允许的时间片的值(20)。

  ② 动态优先级(counter)——counter 即系统为每个进程运行而分配的时间片,Linux兼用它来表示进程的动态优先级。只要进程拥有CPU,它就随着时间不断减小;当它为0时,标记进程重新调度。它指明了在当前时间片中所剩余的时间量(初为20)。

  ③ 实时优先级(rt_priority)——值为1000。Linux把实时优先级与counter值相加作为实时进程的优先权值。较高权值的进程总是优先于较低权值的进程,如果一个进程不是实时进程,其优先权就远小于1000,所以实时进程总是优先。

  在每个tick到来的时候(也就是时钟中断发生),系统减小当前占有CPU的进程的counter,如果counter减小到0,则将need_resched置1,中断返回过程中进行调度。update_process_times()为时钟中断处理程序调用的一个子函数:

  void update_process_times(int user_tick)
  {
  struct task_struct *p = current;
  int cpu = smp_processor_id(), system = user_tick ^ 1;
  update_ONe_process(p, user_tick, system, cpu);
  if (p->pid) {
  if (--p->counter <= 0) {
  p->counter = 0;
  p->need_resched = 1;
  }
  if (p->nice > 0)
  kstat.per_cpu_nice[cpu] = user_tick;
  else
  kstat.per_cpu_user[cpu] = user_tick;
  kstat.per_cpu_system[cpu] = system;
  } else if (local_bh_count(cpu) || local_irq_count(cpu) > 1)
  kstat.per_cpu_system[cpu] = system;
  }


  Linux中进程的调度使在schedule()函数中实现的,该函数在下面的ARM汇编片断中被调用到:


  /*
  * This is the fast syscall return path. We do as little as
  * possible here, and this includes saving r0 back into the SVC
  * stack.
  */
  ret_fast_syscall:
  ldr r1, [tsk, #TSK_NEED_RESCHED]
  ldr r2, [tsk, #TSK_SIGPENDING]
  teq r1, #0  need_resched || sigpending
  teqeq r2, #0
  bne slow
  fast_restore_user_regs
  /*
  * Ok, we need to do extra processing, enter the slow path.
  */
  slow: str r0, [sp, #S_R0 S_OFF]!  returned r0
  b 1f
  /*
  * "slow" syscall return path. "why" tells us if this was a real syscall.
  */
  reschedule:
  bl SYMBOL_NAME(schedule)
  ENTRY(ret_to_user)
  ret_slow_syscall:
  ldr r1, [tsk, #TSK_NEED_RESCHED]
  ldr r2, [tsk, #TSK_SIGPENDING]
  1: teq r1, #0  need_resched => schedule()
  bne reschedule   teq r2, #0  sigpending => do_signal()
  blne __do_signal
  restore_user_regs

  而这段代码在中断返回或者系统调用返回中反复被调用到:

   进程状态转换时: 如进程终止,睡眠等,当进程要调用sleep()或exit()等函数使进程状态发生改变时,这些函数会主动调用schedule()转入进程调度。

   可运行队列中增加新的进程时。


  ENTRY(ret_from_fork)
  bl SYMBOL_NAME(schedule_tail)
  get_current_task tsk
  ldr ip, [tsk, #TSK_PTRACE]  check for syscall tracing
  mov why, #1
  tst ip, #PT_TRACESYS  are we tracing syscalls?
  beq ret_slow_syscall
  mov r1, sp
  mov r0, #1  trace exit [IP = 1]
  bl SYMBOL_NAME(syscall_trace)
  b ret_slow_syscall

  ③ 在时钟中断到来后:Linux初始化时,设定系统定时器的周期为10毫秒。当时钟中断发生时,时钟中断服务程序timer_interrupt立即调用时钟处理函数do_timer( ),在do_timer()会将当前进程的counter减1,如果counter为0则置need_resched标志,在从时钟中断返回的过程中会调用schedule.


  ④进程从系统调用返回到用户态时;判断need_resched标志是否置位,若是则转入执行schedule()。系统调用实际上就是通过软中断实现的,下面是ARM平台下软中断处理代码:


  .align 5
  ENTRY(vector_swi)
  save_user_regs
  zero_fp
  get_scno
  enable_irqs ip
  str r4, [sp, #-S_OFF]!  push fifth arg
  get_current_task tsk
  ldr ip, [tsk, #TSK_PTRACE]  check for syscall tracing
  bic scno, scno, #0xff000000  mask off SWI op-code
  eor scno, scno, #OS_NUMBER 《 20  check OS number
  adr tbl, sys_call_table  load syscall table pointer
  tst ip, #PT_TRACESYS  are we tracing syscalls?
  bne __sys_trace
  adrsvc al, lr, ret_fast_syscall 

    装载返回地址,用于在跳转调用后返回到上面的代码片断中的

    ret_fast_syscall
  cmp scno, #NR_syscalls  check upper syscall limit
  ldrcc pc, [tbl, scno, lsl #2]  call sys_* routine
  add r1, sp, #S_OFF
  2: mov why, #0  no longer a real syscall
  cmp scno, #ARMSWI_OFFSET
  eor r0, scno, #OS_NUMBER 《 20  put OS number back
  bcs SYMBOL_NAME(arm_syscall)
  b SYMBOL_NAME(sys_ni_syscall)  not private func


  ⑤ 内核处理完中断后,进程返回到用户态。


  ⑥ 进程主动调用schedule()请求进行进程调度。


  ----------------------------------------------

  ARM Linux 进程调度:

  switch_mm中是进行页表的切换,即将下一个的pgd的开始物理地址放入CP15中的C2寄存器。进程的pgd的虚拟地址存放在task_struct结构中的pgd指针中,通过__virt_to_phys宏可以转变成成物理地址。
  
  static inline void
  switch_mm(struct mm_struct *prev, struct mm_struct *next,
  struct task_struct *tsk, unsigned int cpu)
  {
  if (prev != next)
  cpu_switch_mm(next->pgd, tsk);
  }
  #define cpu_switch_mm(pgd,tsk) cpu_set_pgd(__virt_to_phys((unsigned long)(pgd)
  ))
  #define cpu_get_pgd() \
  ({ \
  unsigned long pg; \
  __asm__("mrc p15, 0, %0, c2, c0, 0" \
  : "=r" (pg)); \
  pg &= ~0x3fff; \
  (pgd_t *)phys_to_virt(pg); \
  })
  switch_to()完成进程上下文的切换,通过调用汇编函数__switch_to完成,其实现比较简单,也就是保存prev进程的上下文信息,该上下文信息由context_save_struct结构描述,包括主要的寄存器,然后将next的上下文信息读出,信息保存在task_struct中的thread.save中TSS_SAVE标识了thread.save在task_struct中的位置。
  /*
  * Register switch for ARMv3 and ARMv4 processors
  * r0 = previous, r1 = next, return previous.
  * previous and next are guaranteed not to be the same.
  */
  ENTRY(__switch_to)
  stmfd sp!, {r4 - sl, fp, lr}  Store most regs on
  stack
  mrs ip, cpsr
  str ip, [sp, #-4]!  Save cpsr_SVC
  str sp, [r0, #TSS_SAVE]  Save sp_SVC
  ldr sp, [r1, #TSS_SAVE]  Get saved sp_SVC
  ldr r2, [r1, #TSS_DOMAIN]
  *
  * Returns amount of memory which needs to be reserved.
  */
  long ed_init(long mem_start, int mem_end)
  {
  int i,
  ep;
  short tshort,
  version,
  length,
  s_ofs;
  if (register_blkdev(EPROM_MAJOR,"ed",&ed_fops)) {
  printk("EPROMDISK: Unable to get major %d.\n", EPROM_MAJOR);
  return 0;
  }
  blk_dev[EPROM_MAJOR].request_fn = DEVICE_REQUEST;
  for(i=0;i< 4) {
  printk("EPROMDISK: Length (%d) Too short.\n", length);
  return 0;
  }
  ed_length = length * 512;
  sector_map = ep 6;
  sector_offset = ep s_ofs;
  printk("EPROMDISK: Version %d installed, %d bytes\n", (int)version, ed_length);
  return 0;
  }
  int get_edisk(unsigned char *buf, int sect, int num_sect)
  {
  short ss, /* Sector start */
  tshort;
  int s; /* Sector offset */
  for(s=0;s0;) {
  sock = bp / EPROM_SIZE;
  page = (bp % EPROM_SIZE) / EPAGE_SIZE;
  offset = bp % EPAGE_SIZE;
  nb = (len offset)>EPAGE_SIZE?EPAGE_SIZE-(offset%EPAGE_SIZE):len;
  cr1 = socket[sock] | ((page 《 4) & 0x30) | 0x40; /* no board select for now */
  cr2 = (page 》 2) & 0x03;
  outb((char)cr1,CONTROL_REG1);
  outb((char)cr2,CONTROL_REG2);
  memcpy(buf bofs,(char *)(EPROM_WINDOW offset),nb);
  len -= nb;
  bp = nb;
  bofs = nb;
  }
  return 0;
  }
  med.c代码如下:
  /* med.c - make eprom disk image from ramdisk image */
  #include
  #include
  #include
  #define DISK_SIZE (6291456)
  #define NUM_SECT (DISK_SIZE/512)
  void write_eprom_image(FILE *fi, FILE *fo);
  int main(int ac, char **av)
  {
  FILE *fi,
  *fo;
  char fin[44],
  fon[44];
  if (ac > 1) {
  strcpy(fin,av[1]);
  } else {
  strcpy(fin,"hda3.ram");
  }
  if (ac > 2) {
  strcpy(fon,av[2]);
  } else {
  strcpy(fon,"hda3.eprom");
  }
  fi = fopen(fin,"r");
  fo = fopen(fon,"w");
  if (fi == 0 || fo == 0) {
  printf("Can't open files\n");
  exit(0);
  }
  write_eprom_image(fi,fo);
  fclose(fi);
  fclose(fo);
  }
  void write_eprom_image(FILE *fi, FILE *fo)
  {
  char *ini;
  char *outi; /* In and out images */
  short *smap; /* Sector map */
  char *sp;
  char c = 0;
  struct {
  unsigned short version;
  unsigned short blocks;
  unsigned short sect_ofs;
  } hdr;
  int ns,
  s,
  i,
  fs;
  ini = (char *)malloc(DISK_SIZE); /* Max disk size is currently 6M */
  outi = (char *)malloc(DISK_SIZE); /* Max disk size is currently 6M */
  smap = (short *)malloc(NUM_SECT*sizeof(short));
  if (ini == NULL || outi == NULL || smap == NULL) {
  printf("Can't allocate memory :(\n");
  exit(0);
  }
  if (DISK_SIZE != fread(ini,1,DISK_SIZE,fi)) {
  printf("Can't read input file :(\n");
  exit(0);
  }
  memcpy(outi,ini,512); /* Copy in first sector */
  smap[0] = 0;
  ns = 1; /* Number of sectors in outi */



  
上一篇:分析Linux init进程
下一篇:介绍Linux 升级的汉子显示解决方法

免责声明: 凡注明来源本网的所有作品,均为本网合法拥有版权或有权使用的作品,欢迎转载,注明出处。非本网作品均来自互联网,转载目的在于传递更多信息,并不代表本网赞同其观点和对其真实性负责。

相关技术资料