On Thu, 2011-12-01 at 22:40 -0800, Olof Johansson wrote: > Hi, > > On Thu, Dec 1, 2011 at 9:35 PM, Benjamin Herrenschmidt > <b...@kernel.crashing.org> wrote: > > > arch/powerpc/boot/dts/obs600.dts | 314 > > ++++++++++++++++++++++++++++ > > It'd be nice to have dtsi files for the SoCs, there's a lot of boiler > plate in there. That shouldn't hold up this specific patch though.
Right definitely. One thing that I wonder tho (I haven't looked at the dtsi stuff specifically), can it "remove" a node ? Ie. The 405EX dtsi will probably expose the PCIe bridges in that specific case, but I want them out as they aren't wired and trying to use them causes a hang on this board. Another approach is to stick in a disabled property and make sure the ppc4xx_pci code checks it. > > arch/powerpc/boot/wrapper | 22 ++- > > arch/powerpc/configs/40x/obs600_defconfig | 83 ++++++++ > > A new single-board defconfig? On arm that is a strong NACK, I'd say > it's a bad idea on powerpc as well. The defconfigs are just there for the user sake, I find them handy myself. I have no objection (as maintainer) to having them since nowadays they are really small and can be handy for embedded systems (ie, on a tiny 405 based machine you really want to cut out the bloat you don't need). As long as the board -can- be built as part of a combo that is. So as maintainer, I think I'll keep applying a different policy than ARM in that area ;-) Cheers, Ben. _______________________________________________ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev
