From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754792Ab3H3LoH (ORCPT ); Fri, 30 Aug 2013 07:44:07 -0400 Received: from mail-ve0-f180.google.com ([209.85.128.180]:49839 "EHLO mail-ve0-f180.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753996Ab3H3LoF (ORCPT ); Fri, 30 Aug 2013 07:44:05 -0400 MIME-Version: 1.0 In-Reply-To: <52207F74.6000702@roeck-us.net> References: <521B2E75.1040802@asianux.com> <5220177E.709@asianux.com> <52201896.9040309@asianux.com> <5220254E.3050704@roeck-us.net> <52203CF0.5040600@asianux.com> <52207F74.6000702@roeck-us.net> Date: Fri, 30 Aug 2013 13:44:03 +0200 Message-ID: Subject: Re: [PATCH v2] h8300/kernel/setup.c: add "linux/initrd.h" to pass compiling From: richard -rw- weinberger To: Guenter Roeck Cc: Chen Gang , Yoshinori Sato , Geert Uytterhoeven , "linux-kernel@vger.kernel.org" Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Aug 30, 2013 at 1:18 PM, Guenter Roeck 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 >>>> --- >>> >>> >>> 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. :-\ -- Thanks, //richard