Hi,
On 07.07.2020 20:23, Tomasz Figa wrote:
> On Sat, Apr 25, 2020 at 07:26:45PM -0700, Jonathan Bakker wrote:
>> Commit ee7160e57c98 ("[media] s5p-fimc: Add support for JPEG capture")
>> added support for JPEG capture, but missed setting a register when the
>> CSIS device wasn't in use.
> nit: Since this isn't really about using the CSIS device or not, but
> rather about the interface that the sensor is connected with, could we
> instead say "when a parallel interface is used"?
>> Signed-off-by: Jonathan Bakker <xc-racer2@xxxxxxx>
>> ---
>> drivers/media/platform/exynos4-is/fimc-reg.c | 7 +++++++
>> 1 file changed, 7 insertions(+)
>>
>> diff --git a/drivers/media/platform/exynos4-is/fimc-reg.c b/drivers/media/platform/exynos4-is/fimc-reg.c
>> index 5ce2bdebd424..269a98fca1e8 100644
>> --- a/drivers/media/platform/exynos4-is/fimc-reg.c
>> +++ b/drivers/media/platform/exynos4-is/fimc-reg.c
>> @@ -606,6 +606,11 @@ int fimc_hw_set_camera_source(struct fimc_dev *fimc,
>> switch (source->fimc_bus_type) {
>> case FIMC_BUS_TYPE_ITU_601:
>> case FIMC_BUS_TYPE_ITU_656:
>> + if (fimc_fmt_is_user_defined(f->fmt->color)) {
>> + cfg |= FIMC_REG_CISRCFMT_ITU601_8BIT;
>> + break;
>> + }
>> +
>> for (i = 0; i < ARRAY_SIZE(pix_desc); i++) {
>> if (vc->ci_fmt.code == pix_desc[i].pixelcode) {
>> cfg = pix_desc[i].cisrcfmt;
>> @@ -707,6 +712,8 @@ int fimc_hw_set_camera_type(struct fimc_dev *fimc,
>> case FIMC_BUS_TYPE_ITU_601...FIMC_BUS_TYPE_ITU_656:
>> if (source->mux_id == 0) /* ITU-A, ITU-B: 0, 1 */
>> cfg |= FIMC_REG_CIGCTRL_SELCAM_ITU_A;
>> + if (vid_cap->ci_fmt.code == MEDIA_BUS_FMT_JPEG_1X8)
>> + cfg |= FIMC_REG_CIGCTRL_CAM_JPEG;
>
> Should we also handle MEDIA_BUS_FMT_S5C_UYVY_JPEG_1X8 as in the CSI
> case? The S5C73M3 sensor supports the parallel interface as well.
The parallel interface has too low bandwidth to transfer image data
with the maximum supported resolution and frame rate, I doubt anyone would
ever use S5C73MC in such a configuration.
--
Regards,
Sylwester
