Hi Sylwester and Tomasz,
On 2020-07-08 8:45 a.m., Sylwester Nawrocki wrote:
> 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"?
Yes, that's a better way of stating it. I'll reword the commit message.
>
>>> 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.
>
Ok, good to know. I'll leave it as-is then.
Thanks,
Jonathan
