Re: [Qemu-devel] tcg/tcg.c:1892: tcg fatal error

[Artyom Tarasenko]

On Sun, Apr 10, 2011 at 4:44 PM, Blue Swirl <address@hidden> wrote:
> On Sun, Apr 10, 2011 at 5:09 PM, Artyom Tarasenko <address@hidden> wrote:
>> On Sun, Apr 10, 2011 at 3:24 PM, Aurelien Jarno <address@hidden> wrote:
>>> On Sun, Apr 10, 2011 at 02:29:59PM +0200, Artyom Tarasenko wrote:
>>>> Trying to boot some proprietary OS I get qemu-system-sparc64 crash with a
>>>>
>>>> tcg/tcg.c:1892: tcg fatal error
>>>>
>>>> error message.
>>>>
>>>> It looks like it can be a platform independent bug though, because
>>>> when a '-singlestep' option IS present, qemu doesn't crash and seems
>>>> to translate the code properly.
>>>>
>>>> (gdb) bt
>>>> #0  0x00000032c2e327f5 in raise () from /lib64/libc.so.6
>>>> #1  0x00000032c2e33fd5 in abort () from /lib64/libc.so.6
>>>> #2  0x000000000051933d in tcg_reg_alloc_call (s=<value optimized out>,
>>>> def=0x89d340, opc=INDEX_op_call, args=0x10acc98, dead_iargs=3) at
>>>> qemu/tcg/tcg.c:1892
>>>> #3  0x000000000051a557 in tcg_gen_code_common (s=0x10b8940,
>>>> gen_code_buf=0x40338b60 "address@hidden 3\355I\211\256\220") at
>>>> qemu/tcg/tcg.c:2099
>>>> #4  tcg_gen_code (s=0x10b8940, gen_code_buf=0x40338b60 "address@hidden
>>>> 3\355I\211\256\220") at qemu/tcg/tcg.c:2142
>>>> #5  0x00000000004d38f1 in cpu_sparc_gen_code (env=0x10cce10,
>>>> tb=0x7fffe91bc218, gen_code_size_ptr=0x7fffffffd9b4) at
>>>> qemu/translate-all.c:93
>>>> #6  0x00000000004d1fd7 in tb_gen_code (env=0x10cce10, pc=18868776,
>>>> cs_base=18868780, flags=15, cflags=0) at qemu/exec.c:989
>>>> #7  0x00000000004d4029 in tb_find_slow (env1=<value optimized out>) at
>>>> qemu/cpu-exec.c:167
>>>> #8  tb_find_fast (env1=<value optimized out>) at cpu-exec.c:194
>>>> #9  cpu_sparc_exec (env1=<value optimized out>) at qemu/cpu-exec.c:556
>>>> #10 0x0000000000408868 in tcg_cpu_exec () at qemu/cpus.c:1066
>>>> #11 cpu_exec_all () at qemu/cpus.c:1102
>>>> #12 0x000000000053c756 in main_loop (argc=<value optimized out>,
>>>> argv=<value optimized out>, envp=<value optimized out>) at
>>>> qemu/vl.c:1430
>>>>
>>>> I inspected ts->val_type causing the abort() case and it turned out to be 
>>>> 0.
>>>>
>>>> The last lines of qemu.log (without -singlestep)
>>>> IN:
>>>> 0x00000000011fe9f0:  rdpr  %pstate, %g1
>>>> 0x00000000011fe9f4:  wrpr  %g1, 2, %pstate
>>>> --------------
>>>> IN:
>>>> 0x00000000011fe9f8:  ldub  [ %o0 ], %o1
>>>> 0x00000000011fe9fc:  mov  %o1, %o2
>>>> 0x00000000011fea00:  rdpr  %tick, %o3
>>>> 0x00000000011fea04:  cmp  %o1, %o2
>>>> 0x00000000011fea08:  be  %icc, 0x11fea00
>>>> 0x00000000011fea0c:  ldub  [ %o0 ], %o2
>>>>
>>>> Search PC...
>>>> Search PC...
>>>> Search PC...
>>>> Search PC...
>>>> Search PC...
>>>> Search PC...
>>>> --------------
>>>> IN:
>>>> 0x00000000011fe9f8:  ldub  [ %o0 ], %o1
>>>> 0x00000000011fe9fc:  mov  %o1, %o2
>>>> 0x00000000011fea00:  rdpr  %tick, %o3
>>>> 0x00000000011fea04:  cmp  %o1, %o2
>>>> 0x00000000011fea08:  be  %icc, 0x11fea00
>>>> 0x00000000011fea0c:  ldub  [ %o0 ], %o2
>>>>
>>>> 110521: Data Access MMU Miss (v=0068) pc=00000000011fe9f8
>>>> npc=00000000011fe9fc SP=000000000180ae41
>>>> pc: 00000000011fe9f8  npc: 00000000011fe9fc
>>>>
>>>> IN:
>>>> 0x00000000011fea00:  rdpr  %tick, %o3
>>>> 0x00000000011fea04:  cmp  %o1, %o2
>>>> 0x00000000011fea08:  be  %icc, 0x11fea00
>>>> 0x00000000011fea0c:  ldub  [ %o0 ], %o2
>>>> --------------
>>>> IN:
>>>> 0x00000000011fea10:  brz,pn   %o2, 0x11fe9f8
>>>> 0x00000000011fea14:  mov  %o2, %o4
>>>> --------------
>>>> IN:
>>>> 0x00000000011fea18:  rdpr  %tick, %o5
>>>> 0x00000000011fea1c:  cmp  %o2, %o4
>>>> 0x00000000011fea20:  be  %icc, 0x11fea18
>>>> 0x00000000011fea24:  ldub  [ %o0 ], %o4
>>>> --------------
>>>> IN:
>>>> 0x00000000011fea28:  brz,pn   %o4, 0x11fe9f4
>>>> 0x00000000011fea2c:  wrpr  %g0, %g1, %pstate
>>>> <EOF>
>>>>
>>>> The crash is 100% reproducible and happens always on the same place,
>>>> so it's probably a pure TCG issue, not related on getting the
>>>> external/timer interrupts.
>>>>
>>>> Do you need any additional info?
>>>>
>>>
>>> What would be interesting would be to get the corresponding TCG code
>>> from qemu.log (-d op,op_opt).
>>
>>
>> OP:
>>  ---- 0x11fea28
>>  ld_i64 tmp6,regwptr,$0x20
>>  movi_i64 cond,$0x0
>>  movi_i64 tmp8,$0x0
>>  brcond_i64 tmp6,tmp8,ne,$0x0
>>  movi_i64 cond,$0x1
>>  set_label $0x0
>>
>>  ---- 0x11fea2c
>>  movi_i64 tmp7,$0x0
>>  xor_i64 tmp0,tmp7,g1
>>  movi_i64 pc,$0x11fea2c
>>  movi_i64 tmp8,$compute_psr
>>  call tmp8,$0x0,$0
>>  movi_i64 tmp8,$0x0
>>  brcond_i64 cond,tmp8,eq,$0x1
>>  movi_i64 npc,$0x11fe9f4
>>  br $0x2
>>  set_label $0x1
>>  movi_i64 npc,$0x11fea30
>>  set_label $0x2
>>  movi_i64 tmp8,$wrpstate
>>  call tmp8,$0x0,$0,tmp0
>>  mov_i64 pc,npc
>>  movi_i64 tmp8,$0x4
>>  add_i64 npc,npc,tmp8
>>  exit_tb $0x0
>>
>> OP after liveness analysis:
>>  ---- 0x11fea28
>>  ld_i64 tmp6,regwptr,$0x20
>>  movi_i64 cond,$0x0
>>  movi_i64 tmp8,$0x0
>>  brcond_i64 tmp6,tmp8,ne,$0x0
>>  movi_i64 cond,$0x1
>>  set_label $0x0
>>
>>  ---- 0x11fea2c
>>  nopn $0x2,$0x2
>>  nopn $0x3,$0x68,$0x3
>>  movi_i64 pc,$0x11fea2c
>>  movi_i64 tmp8,$compute_psr
>>  call tmp8,$0x0,$0
>>  movi_i64 tmp8,$0x0
>>  brcond_i64 cond,tmp8,eq,$0x1
>>  movi_i64 npc,$0x11fe9f4
>>  br $0x2
>>  set_label $0x1
>>  movi_i64 npc,$0x11fea30
>>  set_label $0x2
>>  movi_i64 tmp8,$wrpstate
>>  call tmp8,$0x0,$0,tmp0
>>  mov_i64 pc,npc
>>  movi_i64 tmp8,$0x4
>>  add_i64 npc,npc,tmp8
>>  exit_tb $0x0
>>  end
>>
>> Does it mean the last block is processed correctly and the crash
>> happens on the next instruction which doesn't make it to the log?
>> The next instruction would be a
>>
>> 0x00000000011fea30:  retl
>>
>> Since it's a branch instruction I guess this would also be a tcg block 
>> boundary.
>
> Because abort() was called from tcg_reg_alloc_call, I'd say 'retl'
> (synthetic op for 'jmpl %o8 + 8, %g0') was the problem.

Any idea why? retl is not a rare instruction...


-- 
Regards,
Artyom Tarasenko

solaris/sparc under qemu blog: http://tyom.blogspot.com/