How dump trace is generated in Linux kernel

Note for myself to remember how call trace is generated in Kernel

/*
 * The architecture-independent dump_stack generator
 */
void dump_stack(void)
{
  unsigned long stack;
  
  printk("Pid: %d, comm: %.20s %s %s %.*sn",
    current->pid, current->comm, print_tainted(),
    init_utsname()->release,
    (int)strcspn(init_utsname()->version, " "),
    init_utsname()->version);
  show_trace(NULL, NULL, &stack);
} 

void show_trace(struct task_struct *task, struct pt_regs *regs,
    unsigned long *stack)
{
  show_trace_log_lvl(task, regs, stack, "");
}

void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
    unsigned long *stack, char *log_lvl)
{
  printk("%sCall Trace:n", log_lvl);
  dump_trace(task, regs, stack, &print_trace_ops, log_lvl);
}

/*
 * x86-64 can have up to three kernel stacks:
 * process stack
 * interrupt stack
 * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
 */

void dump_trace(struct task_struct *task, struct pt_regs *regs,
    unsigned long *stack,
    const struct stacktrace_ops *ops, void *data)
{   
  const unsigned cpu = get_cpu();
  unsigned long *irq_stack_end =
    (unsigned long *)per_cpu(irq_stack_ptr, cpu);
  unsigned used = 0;
  struct thread_info *tinfo;
  int graph = 0;
  unsigned long bp;
  
  if (!task)
    task = current;
    
  if (!stack) {
    unsigned long dummy;
    stack = &dummy;
    if (task && task != current)
      stack = (unsigned long *)task->thread.sp;
  }

  bp = stack_frame(task, regs);
  /*
   * Print function call entries in all stacks, starting at the
   * current stack address. If the stacks consist of nested
   * exceptions
   */
  tinfo = task_thread_info(task);
  for (;;) {
    char *id;
    unsigned long *estack_end;
    estack_end = in_exception_stack(cpu, (unsigned long)stack,
            &used, &id);

    if (estack_end) {
      if (ops->stack(data, id) walk_stack(tinfo, stack, bp, ops,
               data, estack_end, &graph);
      ops->stack(data, "");
      /*
       * We link to the next stack via the
       * second-to-last pointer (index -2 to end) in the
       * exception stack:
       */
      stack = (unsigned long *) estack_end[-2];
      continue;
    }
    if (irq_stack_end) {
      unsigned long *irq_stack;
      irq_stack = irq_stack_end -
        (IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);

      if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
        if (ops->stack(data, "IRQ") walk_stack(tinfo, stack, bp,
          ops, data, irq_stack_end, &graph);
        /*
         * We link to the next stack (which would be
         * the process stack normally) the last
         * pointer (index -1 to end) in the IRQ stack:
         */
        stack = (unsigned long *) (irq_stack_end[-1]);
        bp = fixup_bp_irq_link(bp, stack, irq_stack,
                   irq_stack_end);
        irq_stack_end = NULL;
        ops->stack(data, "EOI");
        continue;
      }
    }
    break;
  }
  
  /*
   * This handles the process stack:
   */
  bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
  put_cpu();
}


static const struct stacktrace_ops print_trace_ops = {
  .warning    = print_trace_warning,
  .warning_symbol   = print_trace_warning_symbol,
  .stack      = print_trace_stack,
  .address    = print_trace_address,
  .walk_stack   = print_context_stack,
};


unsigned long
print_context_stack(struct thread_info *tinfo,
    unsigned long *stack, unsigned long bp,
    const struct stacktrace_ops *ops, void *data,
    unsigned long *end, int *graph)
{   
  struct stack_frame *frame = (struct stack_frame *)bp;
  
  while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
    unsigned long addr;
    
    addr = *stack;
    if (__kernel_text_address(addr)) {      address(data, addr, 1);        next_frame;
        bp = (unsigned long) frame;
      } else {
        ops->address(data, addr, 0);        <-- Unreliable address
      } 
      print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
    } 
    stack++;
  } 
  return bp;
} 


/*
 * Print one address/symbol entries per line.
 */
static void print_trace_address(void *data, unsigned long addr, int reliable)
{
  touch_nmi_watchdog();
  printk(data);
  printk_address(addr, reliable);
}

void printk_address(unsigned long address, int reliable)
{
  printk(" [] %s%pSn", (void *) address,
      reliable ? "" : "? ", (void *) address);
}     

Leave a Comment

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.