windbg的使用四（Windbg检查死锁 ）

Windbg定位死锁

  (2012-11-09 15:28:55)

转载▼

标签：  杂谈

分类： 测试

【转】原文链接 http://blog.csdn.net/hgy413/article/details/7572097#comments

先上个代码，自己随手写的：

[cpp]  view plain copy print ?

1. #include    
2.   
3. CRITICAL_SECTION cs1;  
4. CRITICAL_SECTION cs2;  
5.   
6. DWORD __stdcall thread1(LPVOID lp)  
7. {  
8.     EnterCriticalSection(&cs1);  
9.     Sleep(10);  
10.     EnterCriticalSection(&cs2);  
11.   
12.     return 0;  
13. }  
14.   
15. DWORD  __stdcall thread2(LPVOID lp)  
16. {  
17.     EnterCriticalSection(&cs2);  
18.     Sleep(10);  
19.     EnterCriticalSection(&cs1);  
20.   
21.     return 0;  
22. }  
23.   
24. int main()  
25. {  
26.     InitializeCriticalSection(&cs1);  
27.     InitializeCriticalSection(&cs2);  
28.   
29.     CreateThread(NULL, 0, thread1, 0, 0, NULL);  
30.     CreateThread(NULL, 0, thread2, 0, 0, NULL);  
31.   
32.     system("pause");  
33.     return 0;  
34.   
35. }  

运行，生成release版本，去掉pdb，运行，程序停住了，windbg加载到进程，

先用~*kb查看下所有的线程堆栈:

0:003> ~*kb

   0  Id: 1a98.24c Suspend: 1 Teb: 7ffdf000 Unfrozen ChildEBP RetAddr  Args to Child             0012fddc 7c92df5a 7c8025db 00000044 00000000 ntdll!KiFastSystemCallRet 0012fde0 7c8025db 00000044 00000000 00000000 ntdll!NtWaitForSingleObject+0xc 0012fe44 7c802542 00000044 ffffffff 00000000 kernel32!WaitForSingleObjectEx+0xa8 0012fe58 7854bd40 00000044 ffffffff 00000000 kernel32!WaitForSingleObject+0x12 0012fedc 7854c702 00000000 00392b98 00392de0 MSVCR90!_dospawn+0x1d1 [f:\dd\vctools\crt_bld\self_x86\crt\src\dospawn.c @ 215] 0012ff00 7854c84b 00000000 00392b98 0012ff5c MSVCR90!comexecmd+0x60 [f:\dd\vctools\crt_bld\self_x86\crt\src\spawnve.c @ 137] 0012ff38 7854cc71 00000000 00392b98 0012ff5c MSVCR90!_spawnve+0x12a [f:\dd\vctools\crt_bld\self_x86\crt\src\spawnve.c @ 273] 0012ff70 004010a8 004020f4 00000001 00401218 MSVCR90!system+0x8e [f:\dd\vctools\crt_bld\self_x86\crt\src\system.c @ 87] WARNING: Stack unwind information not available. Following frames may be wrong. 0012ffc0 7c817077 00300031 0032002d 7ffdc000 test2+0x10a8 0012fff0 00000000 00401360 00000000 78746341 kernel32!BaseProcessStart+0x23

   1  Id: 1a98.1588 Suspend: 1 Teb: 7ffde000 Unfrozen ChildEBP RetAddr  Args to Child             0050ff14 7c92df5a 7c939b23 0000002c 00000000 ntdll!KiFastSystemCallRet 0050ff18 7c939b23 0000002c 00000000 00000000 ntdll!NtWaitForSingleObject+0xc 0050ffa0 7c921046 00403370 0040101d 00403370 ntdll!RtlpWaitForCriticalSection+0x132 0050ffa8 0040101d 00403370 000203a8 7c80b729 ntdll!RtlEnterCriticalSection+0x46 WARNING: Stack unwind information not available. Following frames may be wrong. 0050ffec 00000000 00401000 00000000 00000000 test2+0x101d

   2  Id: 1a98.185c Suspend: 1 Teb: 7ffdd000 Unfrozen ChildEBP RetAddr  Args to Child             0060ff14 7c92df5a 7c939b23 00000034 00000000 ntdll!KiFastSystemCallRet 0060ff18 7c939b23 00000034 00000000 00000000 ntdll!NtWaitForSingleObject+0xc 0060ffa0 7c921046 00403388 0040104d 00403388 ntdll!RtlpWaitForCriticalSection+0x132 0060ffa8 0040104d 00403388 000203a8 7c80b729 ntdll!RtlEnterCriticalSection+0x46 WARNING: Stack unwind information not available. Following frames may be wrong. 0060ffec 00000000 00401030 00000000 00000000 test2+0x104d

#  3  Id: 1a98.159c Suspend: 1 Teb: 7ffdb000 Unfrozen ChildEBP RetAddr  Args to Child             003dffc8 7c972119 00000005 00000004 00000001 ntdll!DbgBreakPoint 003dfff4 00000000 00000000 00000000 00000000 ntdll!DbgUiRemoteBreakin+0x2d

[cpp]  view plain copy print ?

1. 我们注意到1号线程的线程堆栈是从ntdll!RtlEnterCriticalSection中开始的，那么ntdll!RtlEnterCriticalSection又是什么函数的入口呢，首先猜到的是EnterCriticalSection,这个函数是kernel32.dll中的，为了验证猜测，我们用dump查看到kernel32.dll的导出函数：  

果然如此，

1. !cs

!cs 扩展显示一个或多个临界区(critical section)或者整个临界区树

前面说的ntdll!RtlEnterCriticalSection的第一个参数是临界区的地址，事实上用uf反汇编它，可以看到是ret 4，说明就只有一个参数

那么，

!cs Address 指定要显示的临界区地址。如果省略该参数，调试器显示当前进程中所有临界区。

[cpp]  view plain copy print ?

1. 0:003> ~1kb  
2. ChildEBP RetAddr  Args to Child                
3. 0050ff14 7c92df5a 7c939b23 0000002c 00000000 ntdll!KiFastSystemCallRet  
4. 0050ff18 7c939b23 0000002c 00000000 00000000 ntdll!NtWaitForSingleObject+0xc  
5. 0050ffa0 7c921046 00403370 0040101d 00403370 ntdll!RtlpWaitForCriticalSection+0x132  
6. 0050ffa8 0040101d 00403370 000203a8 7c80b729 ntdll!RtlEnterCriticalSection+0x46  
7. WARNING: Stack unwind information not available. Following frames may be wrong.  
8. 0050ffec 00000000 00401000 00000000 00000000 test2+0x101d  
9. 0:003> !cs 00403370   
10. -----------------------------------------  
11. Critical section   = 0x00403370 (test2+0x3370)  
12. DebugInfo          = 0x7c99e9e0  
13. LOCKED  
14. LockCount          = 0x1  
15. OwningThread       = 0x0000185c  
16. RecursionCount     = 0x1  
17. LockSemaphore      = 0x2C  
18. SpinCount          = 0x00000000  

[cpp]  view plain copy print ?

1.    

[cpp]  view plain copy print ?

1. 这里LockCount为1意思为除了一个线程拥有它外，另外还有一个线程在等待它，它是由EnterCriticalSection增加，LeaveCriticalSection来减小的,比如我再加一点代码:  

[cpp]  view plain copy print ?

1. DWORD  __stdcall thread3(LPVOID lp)  
2. {  
3.     EnterCriticalSection(&cs2);  
4.     Sleep(10);  
5.     EnterCriticalSection(&cs1);  
6.   
7.     return 0;  
8. }  
9.   
10. int main()  
11. {  
12.     InitializeCriticalSection(&cs1);  
13.     InitializeCriticalSection(&cs2);  
14.   
15.     CreateThread(NULL, 0, thread1, 0, 0, NULL);  
16.     CreateThread(NULL, 0, thread2, 0, 0, NULL);  
17.     CreateThread(NULL, 0, thread3, 0, 0, NULL);  
18.   
19.     system("pause");  
20.     return 0;  
21.   
22. }  

这时运行windbg：

[cpp]  view plain copy print ?

1. 0:004> ~1kb  
2. ChildEBP RetAddr  Args to Child                
3. 0051fe48 7c92df5a 7c939b23 00000034 00000000 ntdll!KiFastSystemCallRet  
4. 0051fe4c 7c939b23 00000034 00000000 00000000 ntdll!NtWaitForSingleObject+0xc  
5. 0051fed4 7c921046 00417140 00411420 00417140 ntdll!RtlpWaitForCriticalSection+0x132  
6. *** WARNING: Unable to verify checksum for D:\Project1\test2\Debug\test2.exe  
7. 0051fedc 00411420 00417140 00000000 00000000 ntdll!RtlEnterCriticalSection+0x46  
8. 0051ffb4 7c80b729 00000000 00000000 00000000 test2!thread1+0x50 [d:\project1\test2\test2\test2.cpp @ 10]  
9. 0051ffec 00000000 00411122 00000000 00000000 kernel32!BaseThreadStart+0x37  
10. 0:004> !cs 00417140  
11. -----------------------------------------  
12. Critical section   = 0x00417140 (test2!cs2+0x0)  
13. DebugInfo          = 0x7c99ea00  
14. LOCKED  
15. LockCount          = 0x2  
16. OwningThread       = 0x00001f60  
17. RecursionCount     = 0x1  
18. LockSemaphore      = 0x34  
19. SpinCount          = 0x00000000  

可以发现LockCount变成了2，如果临界区是有信号的，则显示NOT LOCKED(值为-1)

OwningThread表示拥有这个临界区的线程ID,RecursionCount表示拥有线程调了几次EnterCriticalSection，这其实也影响到了LockCount,如果拥有线程多调用一次EnterCriticalSection,那么 LockCount也会相应加1，因为LockCount标识了任意线程调用EnterCriticalSection请求这个互斥量的次数减1,(所以0-1=-1为NOT LOCKED)当然，前面如果调用了LeaveCriticalSection,那么 LockCount也会相应减1

我们继续看原有的程序：

~~[TID]线程 ID 为 TID 的线程。（中括号是必需的，而且在第二个~和左括号间不能有空格）

[cpp]  view plain copy print ?

1. 0:003> ~~[0x0000185c]  
2.    2  Id: 1a98.185c Suspend: 1 Teb: 7ffdd000 Unfrozen  
3.       Start: test2+0x1030 (00401030)   
4.       Priority: 0  Priority class: 32  Affinity: f  

 这意思就是1号线程等待的临界区拥有者是2号线程，那么同样我们对2号线程进行分析:

[cpp]  view plain copy print ?

1. 0:003> ~2kb  
2. ChildEBP RetAddr  Args to Child                
3. 0060ff14 7c92df5a 7c939b23 00000034 00000000 ntdll!KiFastSystemCallRet  
4. 0060ff18 7c939b23 00000034 00000000 00000000 ntdll!NtWaitForSingleObject+0xc  
5. 0060ffa0 7c921046 00403388 0040104d 00403388 ntdll!RtlpWaitForCriticalSection+0x132  
6. 0060ffa8 0040104d 00403388 000203a8 7c80b729 ntdll!RtlEnterCriticalSection+0x46  
7. WARNING: Stack unwind information not available. Following frames may be wrong.  
8. 0060ffec 00000000 00401030 00000000 00000000 test2+0x104d  
9. 0:003> !cs 00403388   
10. -----------------------------------------  
11. Critical section   = 0x00403388 (test2+0x3388)  
12. DebugInfo          = 0x7c99e9c0  
13. LOCKED  
14. LockCount          = 0x1  
15. OwningThread       = 0x00001588  
16. RecursionCount     = 0x1  
17. LockSemaphore      = 0x34  
18. SpinCount          = 0x00000000  
19. 0:003> ~~[0x00001588]  
20.    1  Id: 1a98.1588 Suspend: 1 Teb: 7ffde000 Unfrozen  
21.       Start: test2+0x1000 (00401000)   
22.       Priority: 0  Priority class: 32  Affinity: f  

原来2号线程等待的临界区拥有者是1号线程，所以经典的死锁现象出现了！！！！！！！！！！！！！！！！！！！！！！！！

 

下面继续介绍下!cs的扩展:

!cs -s 如果可能的话，显示每个临界区的初始堆栈回溯。 !cs -l 仅显示锁定的临界区。

[cpp]  view plain copy print ?

1. 0:003> !cs -l   
2. -----------------------------------------  
3. DebugInfo          = 0x7c99e9c0  
4. Critical section   = 0x00403388 (test2+0x3388)  
5. LOCKED  
6. LockCount          = 0x1  
7. OwningThread       = 0x00001588  
8. RecursionCount     = 0x1  
9. LockSemaphore      = 0x34  
10. SpinCount          = 0x00000000  
11. -----------------------------------------  
12. DebugInfo          = 0x7c99e9e0  
13. Critical section   = 0x00403370 (test2+0x3370)  
14. LOCKED  
15. LockCount          = 0x1  
16. OwningThread       = 0x0000185c  
17. RecursionCount     = 0x1  
18. LockSemaphore      = 0x2C  
19. SpinCount          = 0x00000000  

!cs starAddress EndAddress指定要搜索临界区的地址范围

[cpp]  view plain copy print ?

1. 0:003> !cs 0x00400000 0x00500000  
2. -----------------------------------------  
3. DebugInfo          = 0x7c99e9c0  
4. Critical section   = 0x00403388 (test2+0x3388)  
5. LOCKED  
6. LockCount          = 0x1  
7. OwningThread       = 0x00001588  
8. RecursionCount     = 0x1  
9. LockSemaphore      = 0x34  
10. SpinCount          = 0x00000000  
11. -----------------------------------------  
12. DebugInfo          = 0x7c99e9e0  
13. Critical section   = 0x00403370 (test2+0x3370)  
14. LOCKED  
15. LockCount          = 0x1  
16. OwningThread       = 0x0000185c  
17. RecursionCount     = 0x1  
18. LockSemaphore      = 0x2C  
19. SpinCount          = 0x00000000  

!cs -o 对所有显示出来的已锁定的临界区，显示所有者的堆栈。
!cs -?显示该命令的帮助文本。

[cpp]  view plain copy print ?

1. 0:003> !cs -?  
2. !cs [-s] [-l] [-o]                   - dump all the active critical sections in the current process.  
3. !cs [-s] [-o] address                - dump critical section at this address.  
4. !cs [-s] [-l] [-o] address1 address2 - dump all the active critical sections in this range.  
5. !cs [-s] [-o] -d address             - dump critical section corresponding to DebugInfo at this address.  
6.   
7. "-s" will dump the critical section initialization stack trace if it is available.  
8.   
9. "-l" will dump only the locked critical sections.  
10.   
11. "-o" will dump the critical section owner's stack.