[Crash-utility][PATCH 0/8] Support RISCV64 arch and common commands

Xianting Tian xianting.tian at linux.alibaba.com
Sat Jul 30 01:56:30 PDT 2022


在 2022/7/30 上午7:29, Yixun Lan 写道:
> HI Xianting
>
> On Fri, Jul 29, 2022 at 3:11 PM Xianting Tian
> <xianting.tian at linux.alibaba.com> wrote:
>>
>> 在 2022/7/29 下午9:44, Yixun Lan 写道:
>>> Hi Xianting
>>>
>>> On Mon, Jul 18, 2022 at 2:55 AM Xianting Tian
>>> <xianting.tian at linux.alibaba.com> wrote:
>>>> This series of patches are for Crash-utility tool, it make crash tool support
>>>> RISCV64 arch and the common commands(*, bt, p, rd, mod, log, set, struct, task,
>>>> dis and so on).
>>>>
>>>> To make the crash tool work normally for RISCV64 arch, we need a Linux kernel
>>>> patch(under reviewing), which exports the kernel virtual memory layout, va_bits,
>>>> phys_ram_base to vmcoreinfo, it can simplify the development of crash tool.
>>>>
>>>> The Linux kernel patches:
>>>> https://lore.kernel.org/linux-riscv/20220717101323.370245-1-xianting.tian@linux.alibaba.com/
>>>>
>>>> This series of patches are tested on QEMU RISCV64 env and SoC platform of
>>>> T-head Xuantie 910 CPU.
>>>>
>>>> ====================================
>>>>     Some test examples list as below
>>>> ====================================
>>>> ... ...
>>>>         KERNEL: vmlinux
>>>>       DUMPFILE: vmcore
>>>>           CPUS: 1
>>>>           DATE: Fri Jul 15 10:24:25 CST 2022
>>>>         UPTIME: 00:00:33
>>>> LOAD AVERAGE: 0.05, 0.01, 0.00
>>>>          TASKS: 41
>>>>       NODENAME: buildroot
>>>>        RELEASE: 5.18.9
>>>>        VERSION: #30 SMP Fri Jul 15 09:47:03 CST 2022
>>>>        MACHINE: riscv64  (unknown Mhz)
>>>>         MEMORY: 1 GB
>>>>          PANIC: "Kernel panic - not syncing: sysrq triggered crash"
>>>>            PID: 113
>>>>        COMMAND: "sh"
>>>>           TASK: ff60000002269600  [THREAD_INFO: ff60000002269600]
>>>>            CPU: 0
>>>>          STATE: TASK_RUNNING (PANIC)
>>>>
>>>> carsh>
>>>>
>>>> crash> p mem_map
>>>> mem_map = $1 = (struct page *) 0xff6000003effbf00
>>>>
>>>> crash> p /x *(struct page *) 0xff6000003effbf00
>>>> $5 = {
>>>>     flags = 0x1000,
>>>>     {
>>>>       {
>>>>         {
>>>>           lru = {
>>>>             next = 0xff6000003effbf08,
>>>>             prev = 0xff6000003effbf08
>>>>           },
>>>>           {
>>>>             __filler = 0xff6000003effbf08,
>>>>             mlock_count = 0x3effbf08
>>>>           }
>>>>         },
>>>>         mapping = 0x0,
>>>>         index = 0x0,
>>>>         private = 0x0
>>>>       },
>>>>     ... ...
>>>>
>>>> crash> mod
>>>>        MODULE       NAME             BASE         SIZE  OBJECT FILE
>>>> ffffffff0113e740  nvme_core  ffffffff01133000  98304  (not loaded)  [CONFIG_KALLSYMS]
>>>> ffffffff011542c0  nvme       ffffffff0114c000  61440  (not loaded)  [CONFIG_KALLSYMS]
>>>>
>>>> crash> rd ffffffff0113e740 8
>>>> ffffffff0113e740:  0000000000000000 ffffffff810874f8   .........t......
>>>> ffffffff0113e750:  ffffffff011542c8 726f635f656d766e   .B......nvme_cor
>>>> ffffffff0113e760:  0000000000000065 0000000000000000   e...............
>>>> ffffffff0113e770:  0000000000000000 0000000000000000   ................
>>>>
>>>> crash> vtop ffffffff0113e740
>>>> VIRTUAL           PHYSICAL
>>>> ffffffff0113e740  8254d740
>>>>
>>>>      PGD: ffffffff810e9ff8 => 2ffff001
>>>>     P4D: 0000000000000000 => 000000002fffec01
>>>>     PUD: 00005605c2957470 => 0000000020949801
>>>>     PMD: 00007fff7f1750c0 => 0000000020947401
>>>>      PTE: 0 => 209534e7
>>>>    PAGE: 000000008254d000
>>>>
>>>>     PTE     PHYSICAL  FLAGS
>>>> 209534e7  8254d000  (PRESENT|READ|WRITE|GLOBAL|ACCESSED|DIRTY)
>>>>
>>>>         PAGE       PHYSICAL      MAPPING       INDEX CNT FLAGS
>>>> ff6000003f0777d8 8254d000                0        0  1 0
>>>>
>>>> crash> bt
>>>> PID: 113      TASK: ff6000000226c200  CPU: 0    COMMAND: "sh"
>>>>    #0 [ff20000010333b90] riscv_crash_save_regs at ffffffff800078f8
>>>>    #1 [ff20000010333cf0] panic at ffffffff806578c6
>>>>    #2 [ff20000010333d50] sysrq_reset_seq_param_set at ffffffff8038c03c
>>>>    #3 [ff20000010333da0] __handle_sysrq at ffffffff8038c604
>>>>    #4 [ff20000010333e00] write_sysrq_trigger at ffffffff8038cae4
>>>>    #5 [ff20000010333e20] proc_reg_write at ffffffff801b7ee8
>>>>    #6 [ff20000010333e40] vfs_write at ffffffff80152bb2
>>>>    #7 [ff20000010333e80] ksys_write at ffffffff80152eda
>>>>    #8 [ff20000010333ed0] sys_write at ffffffff80152f52
>>>>
>>>> Xianting Tian (8):
>>>>     Add RISCV64 framework code support
>>>>     RISCV64: Make crash tool enter command line and support some commands
>>>>     RISCV64: Add 'dis' command support
>>>>     RISCV64: Add 'irq' command support
>>>>     RISCV64: Add 'bt' command support
>>>>     RISCV64: Add 'help -r' command support
>>>>     RISCV64: Add 'mach' command support
>>>>     RISCV64: Add the implementation of symbol verify
>>>>
>>>>    Makefile            |    7 +-
>>>>    README              |    2 +-
>>>>    configure.c         |   39 +-
>>>>    defs.h              |  248 +++++++-
>>>>    diskdump.c          |   21 +-
>>>>    help.c              |    2 +-
>>>>    lkcd_vmdump_v2_v3.h |    2 +-
>>>>    netdump.c           |   22 +-
>>>>    ramdump.c           |    2 +
>>>>    riscv64.c           | 1414 +++++++++++++++++++++++++++++++++++++++++++
>>>>    symbols.c           |   10 +
>>>>    11 files changed, 1759 insertions(+), 10 deletions(-)
>>>>    create mode 100644 riscv64.c
>>>>
>>>> --
>>>> 2.17.1
>>>>
>>> I'm actually having problem with these patch set, got a compiling error:
>>>
>>> === error log ===
>>> riscv64-unknown-linux-gnu-gcc -c -g -DRISCV64  -DGDB_10_2 -O2 -pipe
>>> lkcd_common.c
>>> riscv64-unknown-linux-gnu-gcc -c -g -DRISCV64  -DGDB_10_2 -O2 -pipe
>>> lkcd_v1.c -DMCLX
>>> riscv64-unknown-linux-gnu-gcc -c -g -DRISCV64  -DGDB_10_2 -O2 -pipe
>>> lkcd_v2_v3.c -DMCLX
>>> In file included from lkcd_v1.c:21:
>>> lkcd_vmdump_v1.h:121:30: error: field ‘dh_regs’ has incomplete type
>>>     121 |         struct pt_regs       dh_regs;
>>>         |                              ^~~~~~~
>>> make[5]: *** [Makefile:385: lkcd_v1.o] Error 1
>>> make[5]: *** Waiting for unfinished jobs....
>>> In file included from lkcd_v2_v3.c:21:
>>> lkcd_vmdump_v2_v3.h:90:30: error: field ‘dha_regs’ has incomplete type
>>>      90 |         struct pt_regs       dha_regs;
>>>         |                              ^~~~~~~~
>>> make[5]: *** [Makefile:388: lkcd_v2_v3.o] Error 1
>>> make[4]: *** [Makefile:1871: gdb] Error 2
>>> make[3]: *** [Makefile:10072: all-gdb] Error 2
>>> make[2]: *** [Makefile:860: all] Error 2
>>>
>>> crash build failed
>> It's strange, actually I didn't meet such compiling error by 'make
>> target=RISCV64', the compiling is OK.
>>
>> Do you have more details for the build?
>>
> FYI, I'm using source code of crash, commit: f37df7df8a50
> I don't think it's necessary to pass 'target' variable explicitly, see
> the comment of Makefile
>
> ==== snip of Makefile
> # target could be set on command line when invoking make. Like: make target=ARM
> # otherwise target will be the same as the host
> ifneq ($(target),)
> CONF_TARGET_FLAG="-t$(target)"
> endif
> ====
>
> besides, it actually recognized the correct target successfully
>
> ==== snip of build log
> make -j8 CC=riscv64-unknown-linux-gnu-gcc
> AR=riscv64-unknown-linux-gnu-ar 'CFLAGS=-O2 -pipe' 'LDFLAGS=-Wl,-O1
> -Wl,--as-needed'
> TARGET: RISCV64
>   CRASH: 8.0.1++
>     GDB: 10.2
> ====

Sorry, I don't quite understand, we usually build crash tool on x86_64 
for analyzing other ARCH's vmcore.

As README shows, we need type target=XXX for analyzing XXX arch vmcore. 
If we only use 'make' to build on X86_64, it is used to analyze x86_64's 
vmcore.

I don't think "make -j8 CC=riscv64-unknown-linux-gnu-gcc" is ok for the 
build.  If I am wrong, please correct me. thanks

README:

   The crash binary can only be used on systems of the same architecture as
   the host build system.  There are a few optional manners of building the
   crash binary:

   o  On an x86_64 host, a 32-bit x86 binary that can be used to analyze
      32-bit x86 dumpfiles may be built by typing "make target=X86".
   o  On an x86 or x86_64 host, a 32-bit x86 binary that can be used to 
analyze
      32-bit arm dumpfiles may be built by typing "make target=ARM".
   o  On an x86 or x86_64 host, a 32-bit x86 binary that can be used to 
analyze
      32-bit mips dumpfiles may be built by typing "make target=MIPS".
   o  On an ppc64 host, a 32-bit ppc binary that can be used to analyze
      32-bit ppc dumpfiles may be built by typing "make target=PPC".
   o  On an x86_64 host, an x86_64 binary that can be used to analyze
      arm64 dumpfiles may be built by typing "make target=ARM64".
   o  On an x86_64 host, an x86_64 binary that can be used to analyze
      ppc64le dumpfiles may be built by typing "make target=PPC64".
   o  On an x86_64 host, an x86_64 binary that can be used to analyze
      riscv64 dumpfiles may be built by typing "make target=RISCV64".

>
> please check [1] for full build log
> [1] https://dev.gentoo.org/~dlan/logs/crash-build.log.xz
>
>>> =====
>>> and this error can be fixed by applying the following patch,
>>> can you help to double check if it's a correct fix?
>>>
>>> diff --git a/lkcd_vmdump_v1.h b/lkcd_vmdump_v1.h
>>> index 4933427..f6c4a26 100644
>>> --- a/lkcd_vmdump_v1.h
>>> +++ b/lkcd_vmdump_v1.h
>>> @@ -118,10 +118,12 @@ typedef struct _dump_header_s {
>>>    #ifndef S390
>>>    #ifndef S390X
>>>    #ifndef ARM64
>>> +#ifndef RISCV64
>>>           struct pt_regs       dh_regs;
>>>    #endif
>>>    #endif
>>>    #endif
>>> +#endif
>>>    #endif
>>>
>>>           /* the address of the current task */
>>> diff --git a/lkcd_vmdump_v2_v3.h b/lkcd_vmdump_v2_v3.h
>>> index 7fa70b9..6d4fd27 100644
>>> --- a/lkcd_vmdump_v2_v3.h
>>> +++ b/lkcd_vmdump_v2_v3.h
>>> @@ -87,10 +87,12 @@ typedef struct _dump_header_asm_s {
>>>    #ifndef S390
>>>    #ifndef S390X
>>>    #ifndef ARM64
>>> +#ifndef RISCV64
>>>           struct pt_regs       dha_regs;
>>>    #endif
>>>    #endif
>>>    #endif
>>> +#endif
>>>
>>>    } dump_header_asm_t;
>>>
>>> ===
>>>
>>> Yixun Lan



More information about the linux-riscv mailing list