Re: [PATCH 06/11] media: exynos4-is: Properly set JPEG options when not using CSIS

From: Jonathan Bakker <xc-racer2@live.ca>
To: Sylwester Nawrocki <s.nawrocki@samsung.com>,
	Tomasz Figa <tfiga@chromium.org>
Cc: kyungmin.park@samsung.com, mchehab@kernel.org, kgene@kernel.org,
	krzk@kernel.org, linux-media@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	linux-samsung-soc@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 06/11] media: exynos4-is: Properly set JPEG options when not using CSIS
Date: Sat, 11 Jul 2020 09:43:55 -0700	[thread overview]
Message-ID: <BN6PR04MB06601BC74285644C47ED8BB6A3620@BN6PR04MB0660.namprd04.prod.outlook.com> (raw)
In-Reply-To: <e60ff1bb-730a-11b5-f870-61a4f24f6195@samsung.com>

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@live.ca>
>>> ---
>>>  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