CSAPP Bomb Lab phase6 解题记录

最近下班无聊的时候把CSAPP Bomb Lab做完了(Bomb Lab作业地址: http://csapp.cs.cmu.edu/3e/labs.html）

写一下最难的phase6的解题记录：

phase_6的反汇编代码如下：

Dump of assembler code for function phase_6:

   0x00000000004010f4 <+0>:	    push   %r14
   0x00000000004010f6 <+2>:	    push   %r13
   0x00000000004010f8 <+4>:	    push   %r12
   0x00000000004010fa <+6>:	    push   %rbp
   0x00000000004010fb <+7>: 	push   %rbx
   0x00000000004010fc <+8>:	    sub    $0x50,%rsp
   0x0000000000401100 <+12>:	mov    %rsp,%r13
   0x0000000000401103 <+15>:	mov    %rsp,%rsi
   0x0000000000401106 <+18>:	callq  0x40145c <read_six_numbers> 
   0x000000000040110b <+23>:	mov    %rsp,%r14
   0x000000000040110e <+26>:	mov    $0x0,%r12d
   0x0000000000401114 <+32>:	mov    %r13,%rbp
   0x0000000000401117 <+35>:	mov    0x0(%r13),%eax
   0x000000000040111b <+39>:	sub    $0x1,%eax
   0x000000000040111e <+42>:	cmp    $0x5,%eax
   0x0000000000401121 <+45>:	jbe    0x401128 <phase_6+52>
   0x0000000000401123 <+47>:	callq  0x40143a <explode_bomb>
   0x0000000000401128 <+52>:	add    $0x1,%r12d
   0x000000000040112c <+56>:	cmp    $0x6,%r12d
   0x0000000000401130 <+60>:	je     0x401153 <phase_6+95>
   0x0000000000401132 <+62>:	mov    %r12d,%ebx
   0x0000000000401135 <+65>:	movslq %ebx,%rax
   0x0000000000401138 <+68>:	mov    (%rsp,%rax,4),%eax
   0x000000000040113b <+71>:	cmp    %eax,0x0(%rbp)
   0x000000000040113e <+74>:	jne    0x401145 <phase_6+81>
   0x0000000000401140 <+76>:	callq  0x40143a <explode_bomb>
   0x0000000000401145 <+81>:	add    $0x1,%ebx
   0x0000000000401148 <+84>:	cmp    $0x5,%ebx
   0x000000000040114b <+87>:	jle    0x401135 <phase_6+65>
   0x000000000040114d <+89>:	add    $0x4,%r13
   0x0000000000401151 <+93>:	jmp    0x401114 <phase_6+32>
   0x0000000000401153 <+95>:	lea    0x18(%rsp),%rsi
   0x0000000000401158 <+100>:	mov    %r14,%rax
   0x000000000040115b <+103>:	mov    $0x7,%ecx
   0x0000000000401160 <+108>:	mov    %ecx,%edx
   0x0000000000401162 <+110>:	sub    (%rax),%edx
   0x0000000000401164 <+112>:	mov    %edx,(%rax)
   0x0000000000401166 <+114>:	add    $0x4,%rax
   0x000000000040116a <+118>:	cmp    %rsi,%rax
   0x000000000040116d <+121>:	jne    0x401160 <phase_6+108>
   0x000000000040116f <+123>:	mov    $0x0,%esi
   0x0000000000401174 <+128>:	jmp    0x401197 <phase_6+163>
   0x0000000000401176 <+130>:	mov    0x8(%rdx),%rdx
   0x000000000040117a <+134>:	add    $0x1,%eax
   0x000000000040117d <+137>:	cmp    %ecx,%eax
   0x000000000040117f <+139>:	jne    0x401176 <phase_6+130>
   0x0000000000401181 <+141>:	jmp    0x401188 <phase_6+148>
   0x0000000000401183 <+143>:	mov    $0x6032d0,%edx
   0x0000000000401188 <+148>:	mov    %rdx,0x20(%rsp,%rsi,2)
   0x000000000040118d <+153>:	add    $0x4,%rsi
   0x0000000000401191 <+157>:	cmp    $0x18,%rsi
   0x0000000000401195 <+161>:	je     0x4011ab <phase_6+183>
   0x0000000000401197 <+163>:	mov    (%rsp,%rsi,1),%ecx
   0x000000000040119a <+166>:	cmp    $0x1,%ecx
   0x000000000040119d <+169>:	jle    0x401183 <phase_6+143>
   0x000000000040119f <+171>:	mov    $0x1,%eax
   0x00000000004011a4 <+176>:	mov    $0x6032d0,%edx
   0x00000000004011a9 <+181>:	jmp    0x401176 <phase_6+130>
   0x00000000004011ab <+183>:	mov    0x20(%rsp),%rbx
   0x00000000004011b0 <+188>:	lea    0x28(%rsp),%rax
   0x00000000004011b5 <+193>:	lea    0x50(%rsp),%rsi
   0x00000000004011ba <+198>:	mov    %rbx,%rcx
   0x00000000004011bd <+201>:	mov    (%rax),%rdx
   0x00000000004011c0 <+204>:	mov    %rdx,0x8(%rcx)
   0x00000000004011c4 <+208>:	add    $0x8,%rax
   0x00000000004011c8 <+212>:	cmp    %rsi,%rax
   0x00000000004011cb <+215>:	je     0x4011d2 <phase_6+222>
   0x00000000004011cd <+217>:	mov    %rdx,%rcx
   0x00000000004011d0 <+220>:	jmp    0x4011bd <phase_6+201>
   0x00000000004011d2 <+222>:	movq   $0x0,0x8(%rdx)
   0x00000000004011da <+230>:	mov    $0x5,%ebp
   0x00000000004011df <+235>:	mov    0x8(%rbx),%rax
   0x00000000004011e3 <+239>:	mov    (%rax),%eax
   0x00000000004011e5 <+241>:	cmp    %eax,(%rbx)
   0x00000000004011e7 <+243>:	jge    0x4011ee <phase_6+250>
   0x00000000004011e9 <+245>:	callq  0x40143a <explode_bomb>
   0x00000000004011ee <+250>:	mov    0x8(%rbx),%rbx
   0x00000000004011f2 <+254>:	sub    $0x1,%ebp
   0x00000000004011f5 <+257>:	jne    0x4011df <phase_6+235>
   0x00000000004011f7 <+259>:	add    $0x50,%rsp
   0x00000000004011fb <+263>:	pop    %rbx
   0x00000000004011fc <+264>:	pop    %rbp
   0x00000000004011fd <+265>:	pop    %r12
   0x00000000004011ff <+267>:	pop    %r13
   0x0000000000401201 <+269>:	pop    %r14
   0x0000000000401203 <+271>:	retq
End of assembler dump.

为了便于分析，大致将上述代码分为了6段：

各段的简要分析结果如下：

第一段：

   第一段代码： 读取6个整数的值， 假设输入的6个整数位 Ai(1<=i<=6)

   0x00000000004010f4 <+0>:	    push   %r14
   0x00000000004010f6 <+2>:	    push   %r13
   0x00000000004010f8 <+4>:	    push   %r12
   0x00000000004010fa <+6>:	    push   %rbp
   0x00000000004010fb <+7>: 	push   %rbx
   0x00000000004010fc <+8>:	    sub    $0x50,%rsp
   0x0000000000401100 <+12>:	mov    %rsp,%r13
   0x0000000000401103 <+15>:	mov    %rsp,%rsi
   0x0000000000401106 <+18>:	callq  0x40145c <read_six_numbers> //读入6个整数
   0x000000000040110b <+23>:	mov    %rsp,%r14
   0x000000000040110e <+26>:	mov    $0x0,%r12d

第一段代码中，read_six_numbers的功能大致如下：

int read_six_numbers(char* str, int* p1, int* p2, int* p3, 
                            int* p4, int* p5, int* p6)
{
    sscanf(str, "%d %d %d %d %d %d", 
                     p1, p2, p3, p4, p5, p6);
}

 

第二段：

第二段代码： 一词判断上面输入的6个整数是否<=6,如果不是，爆炸;
   并且 Ai != Aj (1<=i<=6, i<j<=6)，如果不是，爆炸

   0x0000000000401114 <+32>:	mov    %r13,%rbp
   0x0000000000401117 <+35>:	mov    0x0(%r13),%eax
   0x000000000040111b <+39>:	sub    $0x1,%eax
   0x000000000040111e <+42>:	cmp    $0x5,%eax
   0x0000000000401121 <+45>:	jbe    0x401128 <phase_6+52>
   0x0000000000401123 <+47>:	callq  0x40143a <explode_bomb>
   0x0000000000401128 <+52>:	add    $0x1,%r12d
   0x000000000040112c <+56>:	cmp    $0x6,%r12d
   0x0000000000401130 <+60>:	je     0x401153 <phase_6+95>
   0x0000000000401132 <+62>:	mov    %r12d,%ebx
   0x0000000000401135 <+65>:	movslq %ebx,%rax
   0x0000000000401138 <+68>:	mov    (%rsp,%rax,4),%eax
   0x000000000040113b <+71>:	cmp    %eax,0x0(%rbp)
   0x000000000040113e <+74>:	jne    0x401145 <phase_6+81>
   0x0000000000401140 <+76>:	callq  0x40143a <explode_bomb>
   0x0000000000401145 <+81>:	add    $0x1,%ebx
   0x0000000000401148 <+84>:	cmp    $0x5,%ebx
   0x000000000040114b <+87>:	jle    0x401135 <phase_6+65>
   0x000000000040114d <+89>:	add    $0x4,%r13
   0x0000000000401151 <+93>:	jmp    0x401114 <phase_6+32>

 

第三段：

第三段代码:Ai = 7 - Ai (1 <= i <= 6)
   0x0000000000401153 <+95>:	lea    0x18(%rsp),%rsi
   0x0000000000401158 <+100>:	mov    %r14,%rax
   0x000000000040115b <+103>:	mov    $0x7,%ecx
   0x0000000000401160 <+108>:	mov    %ecx,%edx
   0x0000000000401162 <+110>:	sub    (%rax),%edx
   0x0000000000401164 <+112>:	mov    %edx,(%rax)
   0x0000000000401166 <+114>:	add    $0x4,%rax
   0x000000000040116a <+118>:	cmp    %rsi,%rax
   0x000000000040116d <+121>:	jne    0x401160 <phase_6+108>

第四段：

第四段代码：假设从 rsp+0x20 开始处的内存地址存放的6个元素（每个元素占8个字节）为 bi(1<=i<=6)
   则有:
   for(int i=1; i<=6; i++)
   {
      if(ai <= 1)
      {
          bi = 0x6032d0;
      }
      else
      {
          int j = 1;
          bi = 0x6032d0;
          while(j != ai)
          {
             bi = *(bi + 0x8);
             ++j;
          }
      }
   }

   0x000000000040116f <+123>:	mov    $0x0,%esi
   0x0000000000401174 <+128>:	jmp    0x401197 <phase_6+163>
   0x0000000000401176 <+130>:	mov    0x8(%rdx),%rdx
   0x000000000040117a <+134>:	add    $0x1,%eax
   0x000000000040117d <+137>:	cmp    %ecx,%eax
   0x000000000040117f <+139>:	jne    0x401176 <phase_6+130>
   0x0000000000401181 <+141>:	jmp    0x401188 <phase_6+148>
   0x0000000000401183 <+143>:	mov    $0x6032d0,%edx
   0x0000000000401188 <+148>:	mov    %rdx,0x20(%rsp,%rsi,2)
   0x000000000040118d <+153>:	add    $0x4,%rsi
   0x0000000000401191 <+157>:	cmp    $0x18,%rsi
   0x0000000000401195 <+161>:	je     0x4011ab <phase_6+183>
   0x0000000000401197 <+163>:	mov    (%rsp,%rsi,1),%ecx
   0x000000000040119a <+166>:	cmp    $0x1,%ecx
   0x000000000040119d <+169>:	jle    0x401183 <phase_6+143>
   0x000000000040119f <+171>:	mov    $0x1,%eax
   0x00000000004011a4 <+176>:	mov    $0x6032d0,%edx
   0x00000000004011a9 <+181>:	jmp    0x401176 <phase_6+130>

 

第五段：

第五段代码: 功能
   x = b1;

   for(int i=1; i<=5; i++)
   {
       *(bi + 0x8) = b(i+1);
   }

   0x00000000004011ab <+183>:	mov    0x20(%rsp),%rbx
   0x00000000004011b0 <+188>:	lea    0x28(%rsp),%rax
   0x00000000004011b5 <+193>:	lea    0x50(%rsp),%rsi
   0x00000000004011ba <+198>:	mov    %rbx,%rcx
   0x00000000004011bd <+201>:	mov    (%rax),%rdx
   0x00000000004011c0 <+204>:	mov    %rdx,0x8(%rcx)
   0x00000000004011c4 <+208>:	add    $0x8,%rax
   0x00000000004011c8 <+212>:	cmp    %rsi,%rax
   0x00000000004011cb <+215>:	je     0x4011d2 <phase_6+222>
   0x00000000004011cd <+217>:	mov    %rdx,%rcx
   0x00000000004011d0 <+220>:	jmp    0x4011bd <phase_6+201>

详细分析下第4，5段代码：

在第四段汇编代码中，可以理解为获取一个链表中各节点的首地址;

每个节点是一个结构体，如下

//由于系统是64位，故指针变量占8Byte
//字节对齐之后，结构体实际占16Byte
struct LISTNODE
{
   int nValue;
   LISTNODE* pNext;
}

第4和第5段转成C代码功能大致如下：

LISTNODE* arrAddress[6];

for(int i=0; i<6; i++)
{
   if(i == 0)
   {
     arrAddress[i] = (LISTNODE*)0x6032d0;
   }
   else
   {
     arrAddress[i] = (arrAddress[i-1])->pNext;
   }
}

//第4步后所得arrAddress就相当于b

 

第六段：

第6段代码：

   下面的x是第5步中的x
   大致功能伪代码如下：
   for(int i=1; i<=5; i++)
   {
      if(*(int*)x >= *( (int*)(x+0x8) ) )
      {
         x = *(x + 0x8);
         continue;
      }
      else
      {
         Boom!!!
      }
   }

   结束了！！！！！

   0x00000000004011d2 <+222>:	movq   $0x0,0x8(%rdx)
   0x00000000004011da <+230>:	mov    $0x5,%ebp
   0x00000000004011df <+235>:	mov    0x8(%rbx),%rax
   0x00000000004011e3 <+239>:	mov    (%rax),%eax
   0x00000000004011e5 <+241>:	cmp    %eax,(%rbx)
   0x00000000004011e7 <+243>:	jge    0x4011ee <phase_6+250>
   0x00000000004011e9 <+245>:	callq  0x40143a <explode_bomb>
   0x00000000004011ee <+250>:	mov    0x8(%rbx),%rbx
   0x00000000004011f2 <+254>:	sub    $0x1,%ebp
   0x00000000004011f5 <+257>:	jne    0x4011df <phase_6+235>
   0x00000000004011f7 <+259>:	add    $0x50,%rsp
   0x00000000004011fb <+263>:	pop    %rbx
   0x00000000004011fc <+264>:	pop    %rbp
   0x00000000004011fd <+265>:	pop    %r12
   0x00000000004011ff <+267>:	pop    %r13
   0x0000000000401201 <+269>:	pop    %r14
   0x0000000000401203 <+271>:	retq
End of assembler dump.

第六段代码相当于从第一个节点开始依次比较相邻节点中nValue的值，前一个节点中的nValue必须大于或等于后一个节点中nValue的值，如果不是则直接爆炸。

大致伪代码如下：

LISTNODE* arrAddress[6]; //arrAddress为第5中所得arrAddress

for(int i=0; i<5; i++)
{
   if(arrAddress[i]->nValue >= arrAddress[i+1]->nValue)
   {
      continue;
   }
   else
   {
     Boom!!!
   }
}

其中，链表中各节点中nValue的值如下图

从大到小排列依次是 3， 4， 5， 6， 1， 2，倒过来(7 - x)就是4， 3， 2， 1， 6， 5

 

所以，最后得出输入的6个整数是：4， 3， 2， 1， 6， 5