Re: [PATCH v2] h8300/kernel/setup.c: add "linux/initrd.h" to pass compiling

[Guenter Roeck <linux@roeck-us.net>]

On 08/30/2013 04:44 AM, richard -rw- weinberger wrote:
> On Fri, Aug 30, 2013 at 1:18 PM, Guenter Roeck <linux@roeck-us.net> wrote:
>> On 08/29/2013 11:34 PM, Chen Gang wrote:
>>>
>>> On 08/30/2013 12:53 PM, Guenter Roeck wrote:
>>>>
>>>> On 08/29/2013 08:59 PM, Chen Gang wrote:
>>>>>
>>>>> The related error (allmodconfig for h8300):
>>>>>
>>>>>      arch/h8300/kernel/setup.c: In function 'setup_arch':
>>>>>      arch/h8300/kernel/setup.c:103:3: error: 'initrd_start' undeclared
>>>>> (first use in this function)
>>>>>         initrd_start = memory_start;
>>>>>         ^
>>>>>      arch/h8300/kernel/setup.c:103:3: note: each undeclared identifier
>>>>> is reported only once for each function it appears in
>>>>>      arch/h8300/kernel/setup.c:104:3: error: 'initrd_end' undeclared
>>>>> (first use in this function)
>>>>>         initrd_end = memory_start += be32_to_cpu(((unsigned long *)
>>>>> (memory_start))[2]);
>>>>>         ^
>>>>>
>>>>> Signed-off-by: Chen Gang <gang.chen@asianux.com>
>>>>> ---
>>>>
>>>>
>>>> Maybe an odd question, but is there a way to actually compile the h8300
>>>> target
>>>
>>>
>>> Firstly, at least for me, I don't think it is an odd question.  :-)
>>>
>>> For the tool-chain:
>>>
>>>     I compiled the cross-compiler from the gcc and binutils source code.
>>>     GCC has too many bugs to compile kernel with -Os (normal make will
>>> fail).
>>>     If without -Os (no optimization), it can work correctly which is enough
>>> for my goal: "let h8300 pass allmodconfig".  ;-)
>>>
>>>>  From building with allmodconfig for h8300:
>>>
>>>
>>>     I can find more chances to provide contributes (both for h8300 and for
>>> others).
>>>     I can learn more in kernel wide.
>>>     I can familiar the gcc and binutils step by step (especially to
>>> familiar with their issues).
>>>
>>> Next:
>>>
>>>     I will communicate/work with the gcc guys for the gcc issues which
>>> found by building kernel.
>>>
>>>     :-)
>>>
>>>
>>>
>>>> in the first place ? The cross compiler on kernel.org doesn't work, nor
>>>> does
>>>> the one available through Ubuntu.
>>>>
>>>> Guenter
>>>>
>>>
>>> For binutils, no release under Ubuntu, and the Fedora17's is incorrect
>>> (can not use), but the binutils-2.22 from gnu is OK.
>>>
>>> For gcc, no release under Ubuntu, for Fedora17's, gcc-4.9, gcc-4.8,
>>> gcc-4.7.4, and gcc-4.4.7 all have bugs for compiling kernel(their bugs
>>> are different too).
>>>
>>> It is really not easy to fix these bugs (gcc guys have too many issues
>>> to fix), even if really find the root cause, it is still difficult to
>>> fix (fix one bug is very easy to cause another more issues).
>>>
>>
>> I have to wonder ... is this all worth it ? It almost looks like no one
>> is using this architecture anymore. Do you have target hardware to test
>> any of your changes ?
>
> Chen has to achieve his 10 patches/month quota. :-\
>

I don't mind that, but there might be more valuable targets to achieve that goal
than a potentially dead architecture.

A more useful change may be to remove the code from the kernel if there is no plan
to fix it (for real, I mean).

Guenter