Peter De Schrijver wrote at Thursday, November 17, 2011 9:19 AM:
> Add support for tegra30 SoC. This includes a device tree compatible type for
> this SoC ("nvidia,tegra30") and adds L2 cache initialization for this new SoC.
> The clock framework is still missing, which prevents most drivers from
> working.
> The basic IRQs are the same, so remove the dependency on
> CONFIG_ARCH_TEGRA_2x_SOC.
> diff --git a/arch/arm/mach-tegra/board-dt.c b/arch/arm/mach-tegra/board-dt.c
> index 416446b..0b9d184 100644
> --- a/arch/arm/mach-tegra/board-dt.c
> +++ b/arch/arm/mach-tegra/board-dt.c
> @@ -149,3 +149,11 @@ DT_MACHINE_START(TEGRA_DT, "nVidia Tegra20 (Flattened
> Device Tree)")
> .init_machine = tegra_dt_init,
> .dt_compat = tegra20_dt_board_compat,
> MACHINE_END
Since you're reving the patch, a blank line between the two machines would
be nice.
> +DT_MACHINE_START(TEGRA30_DT, "nVidia Tegra30 (Flattened Device Tree)")
> + .map_io = tegra_map_common_io,
> + .init_early = tegra30_init_early,
> + .init_irq = tegra_init_irq,
> + .timer = &tegra_timer,
> + .init_machine = tegra_dt_init,
> + .dt_compat = tegra30_dt_board_compat,
That variable doesn't exist until the next patch; that'll break git bisect.
Do the two DT_MACHINE_START's need if be ifdef'd based on CONFIG variables too?
If not, I'm not sure how a Tegra20- or Tegra30-only kernel builds, since aren't
some of those init functions ifdef'd out but referenced here?
> +MACHINE_END
--
nvpublic
_______________________________________________
devicetree-discuss mailing list
devicetree-discuss@lists.ozlabs.org
https://lists.ozlabs.org/listinfo/devicetree-discuss
