From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754126Ab2FSMOa (ORCPT ); Tue, 19 Jun 2012 08:14:30 -0400 Received: from linux-sh.org ([111.68.239.195]:39363 "EHLO linux-sh.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754049Ab2FSMOD (ORCPT ); Tue, 19 Jun 2012 08:14:03 -0400 Date: Tue, 19 Jun 2012 21:13:38 +0900 From: Paul Mundt To: Geert Uytterhoeven Cc: Linus Torvalds , Andi Kleen , linux-kernel@vger.kernel.org, Linux-Next , Ingo Molnar Subject: Re: [PATCH] Makefile: fix up CROSS_COMPILE and READABLE_ASM interaction. Message-ID: <20120619121337.GA5623@linux-sh.org> References: <20120618045500.GC19803@linux-sh.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jun 19, 2012 at 11:17:59AM +0200, Geert Uytterhoeven wrote: > On Mon, Jun 18, 2012 at 6:55 AM, Paul Mundt wrote: > > (Apologies for the re-send, forgot to Cc linux-kernel) > > > > When the READABLE_ASM cc-option tests were added they were done so prior > > to the arch Makefile include, resulting in cc-option being run on the > > host cc instead of the factoring in the cross prefix set up by the > > architecture. > > > > This bumps the include back up so that cc-option actually runs on the > > compiler that we're building with. > > I find it a real pity these reported, hard to investigate, and fixed > build issues keep > flowing into mainline, without the corresponding fix... > > https://lkml.org/lkml/2012/5/12/36 > Agreed. These one-off things are always a nuisance, and often fall through the cracks. I've yet to find a good solution for them, although having them rolled in to -next helps. In this case I got bit by -fno-partial-inlining instead, and since you didn't have READABLE_ASM in the subject I missed your patch entirely. In retrospect I should have searched for cc-option. At least we've now both scratched our heads and come up with an identical fix independently, which counts a lot more than a Tested-by ;-)