Re: [PATCH 06/14] media: sun4i-csi: Add support for A10 CSI1 camera sensor interface

From: Sakari Ailus
Date: Thu Jan 02 2020 - 06:33:26 EST


Hi Chen-Yu,

Thanks for the patchset.

On Mon, Dec 16, 2019 at 12:59:16AM +0800, Chen-Yu Tsai wrote:
> From: Chen-Yu Tsai <wens@xxxxxxxx>
>
> The A10/A20 Allwinner SoCs have two camera sensor interface blocks,
> named CSI0 and CSI1. The two have the same register layouts with
> slightly different features:
>
> - CSI0 has an image signal processor (ISP); CSI1 doesn't
>
> - CSI0 can support up to four separate channels under CCIR656;
> CSI1 can only support one
>
> - CSI0 can support up to 16-bit wide bus with YUV422;
> CSI1 can support up to 24-bit wide bus with YUV444
>
> For now the driver doesn't support wide busses, nor CCIR656. So the
> only relevant difference is whether a clock needs to be taken and
> enabled for the ISP.
>
> Add structs to record the differences, tie them to the compatible
> strings, and deal with the ISP clock. Support for the new CSI1
> hardware block is added as well.
>
> Signed-off-by: Chen-Yu Tsai <wens@xxxxxxxx>
> ---
> .../platform/sunxi/sun4i-csi/sun4i_csi.c | 35 ++++++++++++++++---
> .../platform/sunxi/sun4i-csi/sun4i_csi.h | 2 ++
> 2 files changed, 32 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> index b8b07c1de2a8..be2466930a49 100644
> --- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> +++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.c
> @@ -29,6 +29,12 @@
>
> #include "sun4i_csi.h"
>
> +struct sun4i_csi_traits {
> + unsigned int channels;
> + unsigned int max_width;
> + bool has_isp;
> +};
> +
> static const struct media_entity_operations sun4i_csi_video_entity_ops = {
> .link_validate = v4l2_subdev_link_validate,
> };
> @@ -156,6 +162,10 @@ static int sun4i_csi_probe(struct platform_device *pdev)
> subdev = &csi->subdev;
> vdev = &csi->vdev;
>
> + csi->traits = of_device_get_match_data(&pdev->dev);
> + if (!csi->traits)
> + return -EINVAL;
> +
> /*
> * On Allwinner SoCs, some high memory bandwidth devices do DMA
> * directly over the memory bus (called MBUS), instead of the
> @@ -199,10 +209,12 @@ static int sun4i_csi_probe(struct platform_device *pdev)
> return PTR_ERR(csi->bus_clk);
> }
>
> - csi->isp_clk = devm_clk_get(&pdev->dev, "isp");
> - if (IS_ERR(csi->isp_clk)) {
> - dev_err(&pdev->dev, "Couldn't get our ISP clock\n");
> - return PTR_ERR(csi->isp_clk);
> + if (csi->traits->has_isp) {
> + csi->isp_clk = devm_clk_get(&pdev->dev, "isp");
> + if (IS_ERR(csi->isp_clk)) {
> + dev_err(&pdev->dev, "Couldn't get our ISP clock\n");
> + return PTR_ERR(csi->isp_clk);
> + }
> }
>
> csi->ram_clk = devm_clk_get(&pdev->dev, "ram");
> @@ -280,8 +292,21 @@ static int sun4i_csi_remove(struct platform_device *pdev)
> return 0;
> }
>
> +struct sun4i_csi_traits sun4i_a10_csi1_traits = {
> + .channels = 1,
> + .max_width = 24,
> + .has_isp = false,
> +};
> +
> +struct sun4i_csi_traits sun7i_a20_csi0_traits = {

These two should be static const, right?

> + .channels = 4,
> + .max_width = 16,
> + .has_isp = true,
> +};
> +
> static const struct of_device_id sun4i_csi_of_match[] = {
> - { .compatible = "allwinner,sun7i-a20-csi0" },
> + { .compatible = "allwinner,sun4i-a10-csi1", .data = &sun4i_a10_csi1_traits },
> + { .compatible = "allwinner,sun7i-a20-csi0", .data = &sun7i_a20_csi0_traits },
> { /* Sentinel */ }
> };
> MODULE_DEVICE_TABLE(of, sun4i_csi_of_match);
> diff --git a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
> index 88d39b3554c4..0f67ff652c2e 100644
> --- a/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
> +++ b/drivers/media/platform/sunxi/sun4i-csi/sun4i_csi.h
> @@ -108,6 +108,8 @@ struct sun4i_csi {
> /* Device resources */
> struct device *dev;
>
> + const struct sun4i_csi_traits *traits;
> +
> void __iomem *regs;
> struct clk *bus_clk;
> struct clk *isp_clk;

--
Kind regards,

Sakari Ailus