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

[Chen Gang <gang.chen@asianux.com>]

On 08/30/2013 07:12 PM, Guenter Roeck wrote:
> On 08/29/2013 10:49 PM, Chen Gang wrote:
>> On 08/30/2013 12:32 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>
>>>> ---
>>>>    arch/h8300/kernel/setup.c |    4 ++++
>>>>    1 files changed, 4 insertions(+), 0 deletions(-)
>>>>
>>>> diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c
>>>> index d0b1607..85639a1 100644
>>>> --- a/arch/h8300/kernel/setup.c
>>>> +++ b/arch/h8300/kernel/setup.c
>>>> @@ -47,6 +47,10 @@
>>>>    #include <asm/regs267x.h>
>>>>    #endif
>>>>
>>>> +#if defined(CONFIG_BLK_DEV_INITRD)
>>>> +#include <linux/initrd.h>
>>>> +#endif
>>>> +
>>>
>>> Is the #ifdef/#endif really needed ? If not you should drop it.
>>>
>>
>> "linux/initrd.h" is needed by 'initrd_start' and 'initrd_end' when
>> BLK_DEV_INITRD enabled.
>>
>> 'memory_start' is defined within this file, and also only one place may
>> use "linux/initrd.h" within this file.
>>
>> So if BLK_DEV_INITRD disabled, do not need "linux/initrd.h" either.
>>
> 
> I didn't ask if the include is needed, I asked if the ifdef is needed.
> 

Adding "ifdef" can mach original/local code style (no matter whether the
code style is good or not),


> The goal is to reduce the number of ifdefs in the code. We should not
> include new ones if not necessary. That there are already other
> (possibly unnecessary) ifdefs in the code doesn't mean we should add new
> ones.
> 

Yeah, if necessary, we need send additional patch to try to reduce all
of "ifdef" within this ".c" file.

In my opinion, we'd better to avoid 2 or more coding styles in one ".c"
file.


> Guenter
> 

Thanks.
-- 
Chen Gang