| Message ID | BN6PR04MB06606F63C7ACE765B57331A1A3AE0@BN6PR04MB0660.namprd04.prod.outlook.com (mailing list archive) |
|---|---|
| State | Not Applicable |
| Headers | show |
| Series | media: exynos4-is: Improve support for s5pv210 and parallel ports | expand |
Hi Jonathan, 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@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. Best regards, Tomasz
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@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.
On 26.04.2020 04:26, 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. > > Signed-off-by: Jonathan Bakker <xc-racer2@live.ca> Reviewed-by: Sylwester Nawrocki <s.nawrocki@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
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; break; case FIMC_BUS_TYPE_LCD_WRITEBACK_A: cfg |= FIMC_REG_CIGCTRL_CAMIF_SELWB;
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. Signed-off-by: Jonathan Bakker <xc-racer2@live.ca> --- drivers/media/platform/exynos4-is/fimc-reg.c | 7 +++++++ 1 file changed, 7 insertions(+)