Messages in this thread | | | Date | Fri, 30 Aug 2013 05:20:13 -0700 | From | Guenter Roeck <> | Subject | Re: [PATCH v2] h8300/kernel/setup.c: add "linux/initrd.h" to pass compiling |
| |
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
| |