| Message ID | 20231108163647.106853-21-harry.wentland@amd.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Color Pipeline API w/ VKMS | expand |
On Wed, 8 Nov 2023 11:36:39 -0500 Harry Wentland <harry.wentland@amd.com> wrote: > Certain operations require us to preserve values below 0.0 and > above 1.0 (0x0 and 0xffff respectively in 16 bpc unorm). One > such operation is a BT709 encoding operation followed by its > decoding operation, or the reverse. > > We'll use s32 values as intermediate in and outputs of our > color operations, for the operations where it matters. > > For now this won't apply to LUT operations. We might want to > update those to work on s32 as well, but it's unclear how > that should work for unorm LUT definitions. We'll revisit > that once we add LUT + CTM tests. I think it's quite clear how those LUTs work: the assumed domain is always [0.0, 1.0] unless otherwise stated. Anything outside of the domain is theoretically undefined, but since raising an error is out of the question, a LUT can clamp its input to its defined domain. Btw. this reflects all the way to the colorop UAPI. > In order to allow for this we'll also invert the nesting of our > colorop processing loops. We now use the pixel iteration loop > on the outside and the colorop iteration on the inside. Yes, that's how it is probably the best, which kind of breaks my previous comment about moving conditionals outside of the innermost loop. You could pre-construct an array of function pointers and arguments to run through in the innermost loop, but it's not clear to me if that has a significant performance improvement. > v3: > - Use new colorop->next pointer > > Signed-off-by: Harry Wentland <harry.wentland@amd.com> > --- > drivers/gpu/drm/vkms/vkms_composer.c | 55 +++++++++++++++++++++------- > drivers/gpu/drm/vkms/vkms_drv.h | 4 ++ > 2 files changed, 46 insertions(+), 13 deletions(-) > > diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c > index 9010415e4bd6..d04a235b9fcd 100644 > --- a/drivers/gpu/drm/vkms/vkms_composer.c > +++ b/drivers/gpu/drm/vkms/vkms_composer.c > @@ -164,7 +164,7 @@ static void apply_lut(const struct vkms_crtc_state *crtc_state, struct line_buff > } > } > > -static void apply_colorop(struct pixel_argb_u16 *pixel, struct drm_colorop *colorop) > +static void apply_colorop(struct pixel_argb_s32 *pixel, struct drm_colorop *colorop) IIRC, this will cause an implicit cast from s32 to u16, which is very different from a clamp. I wouldn't call this "won't apply". > { > /* TODO is this right? */ > struct drm_colorop_state *colorop_state = colorop->state; > @@ -191,25 +191,54 @@ static void apply_colorop(struct pixel_argb_u16 *pixel, struct drm_colorop *colo > > static void pre_blend_color_transform(const struct vkms_plane_state *plane_state, struct line_buffer *output_buffer) > { > - struct drm_colorop *colorop = plane_state->base.base.color_pipeline; > + struct drm_colorop *colorop; > + struct pixel_argb_s32 pixel; > > - while (colorop) { > - struct drm_colorop_state *colorop_state; > + for (size_t x = 0; x < output_buffer->n_pixels; x++) { > + > + /* > + * Some operations, such as applying a BT709 encoding matrix, > + * followed by a decoding matrix, require that we preserve > + * values above 1.0 and below 0.0 until the end of the pipeline. > + * > + * Convert values to s32 for our internal pipeline and go back > + * to u16 values at the end. > + */ > + pixel.a = output_buffer->pixels[x].a; > + pixel.r = output_buffer->pixels[x].r; > + pixel.g = output_buffer->pixels[x].g; > + pixel.b = output_buffer->pixels[x].b; > + > + colorop = plane_state->base.base.color_pipeline; > + while (colorop) { > + struct drm_colorop_state *colorop_state; > > - if (!colorop) > - return; > + if (!colorop) > + return; > > - /* TODO this is probably wrong */ > - colorop_state = colorop->state; > + /* TODO this is probably wrong */ > + colorop_state = colorop->state; > > - if (!colorop_state) > - return; > + if (!colorop_state) > + return; > > - for (size_t x = 0; x < output_buffer->n_pixels; x++) > if (!colorop_state->bypass) > - apply_colorop(&output_buffer->pixels[x], colorop); > + apply_colorop(&pixel, colorop); > + > + colorop = colorop->next; > + } > > - colorop = colorop->next; > + /* clamp pixel */ > + pixel.a = max(min(pixel.a, 0xffff), 0x0); > + pixel.r = max(min(pixel.r, 0xffff), 0x0); > + pixel.g = max(min(pixel.g, 0xffff), 0x0); > + pixel.b = max(min(pixel.b, 0xffff), 0x0); > + > + /* put back to output_buffer */ > + output_buffer->pixels[x].a = pixel.a; > + output_buffer->pixels[x].r = pixel.r; > + output_buffer->pixels[x].g = pixel.g; > + output_buffer->pixels[x].b = pixel.b; > } > } > > diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h > index 2bcc24c196a2..fadb7685a360 100644 > --- a/drivers/gpu/drm/vkms/vkms_drv.h > +++ b/drivers/gpu/drm/vkms/vkms_drv.h > @@ -36,6 +36,10 @@ struct vkms_frame_info { > unsigned int cpp; > }; > > +struct pixel_argb_s32 { > + s32 a, r, g, b; > +}; It would be good to document, that s32 here still uses 16-bit... err. It's an extended 16-bit UNORM format. It's not 16-bit fraction, because 1.0 is 0xffff, not 0x10000. > + > struct pixel_argb_u16 { > u16 a, r, g, b; > }; Thanks, pq
diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c index 9010415e4bd6..d04a235b9fcd 100644 --- a/drivers/gpu/drm/vkms/vkms_composer.c +++ b/drivers/gpu/drm/vkms/vkms_composer.c @@ -164,7 +164,7 @@ static void apply_lut(const struct vkms_crtc_state *crtc_state, struct line_buff } } -static void apply_colorop(struct pixel_argb_u16 *pixel, struct drm_colorop *colorop) +static void apply_colorop(struct pixel_argb_s32 *pixel, struct drm_colorop *colorop) { /* TODO is this right? */ struct drm_colorop_state *colorop_state = colorop->state; @@ -191,25 +191,54 @@ static void apply_colorop(struct pixel_argb_u16 *pixel, struct drm_colorop *colo static void pre_blend_color_transform(const struct vkms_plane_state *plane_state, struct line_buffer *output_buffer) { - struct drm_colorop *colorop = plane_state->base.base.color_pipeline; + struct drm_colorop *colorop; + struct pixel_argb_s32 pixel; - while (colorop) { - struct drm_colorop_state *colorop_state; + for (size_t x = 0; x < output_buffer->n_pixels; x++) { + + /* + * Some operations, such as applying a BT709 encoding matrix, + * followed by a decoding matrix, require that we preserve + * values above 1.0 and below 0.0 until the end of the pipeline. + * + * Convert values to s32 for our internal pipeline and go back + * to u16 values at the end. + */ + pixel.a = output_buffer->pixels[x].a; + pixel.r = output_buffer->pixels[x].r; + pixel.g = output_buffer->pixels[x].g; + pixel.b = output_buffer->pixels[x].b; + + colorop = plane_state->base.base.color_pipeline; + while (colorop) { + struct drm_colorop_state *colorop_state; - if (!colorop) - return; + if (!colorop) + return; - /* TODO this is probably wrong */ - colorop_state = colorop->state; + /* TODO this is probably wrong */ + colorop_state = colorop->state; - if (!colorop_state) - return; + if (!colorop_state) + return; - for (size_t x = 0; x < output_buffer->n_pixels; x++) if (!colorop_state->bypass) - apply_colorop(&output_buffer->pixels[x], colorop); + apply_colorop(&pixel, colorop); + + colorop = colorop->next; + } - colorop = colorop->next; + /* clamp pixel */ + pixel.a = max(min(pixel.a, 0xffff), 0x0); + pixel.r = max(min(pixel.r, 0xffff), 0x0); + pixel.g = max(min(pixel.g, 0xffff), 0x0); + pixel.b = max(min(pixel.b, 0xffff), 0x0); + + /* put back to output_buffer */ + output_buffer->pixels[x].a = pixel.a; + output_buffer->pixels[x].r = pixel.r; + output_buffer->pixels[x].g = pixel.g; + output_buffer->pixels[x].b = pixel.b; } } diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h index 2bcc24c196a2..fadb7685a360 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.h +++ b/drivers/gpu/drm/vkms/vkms_drv.h @@ -36,6 +36,10 @@ struct vkms_frame_info { unsigned int cpp; }; +struct pixel_argb_s32 { + s32 a, r, g, b; +}; + struct pixel_argb_u16 { u16 a, r, g, b; };
Certain operations require us to preserve values below 0.0 and above 1.0 (0x0 and 0xffff respectively in 16 bpc unorm). One such operation is a BT709 encoding operation followed by its decoding operation, or the reverse. We'll use s32 values as intermediate in and outputs of our color operations, for the operations where it matters. For now this won't apply to LUT operations. We might want to update those to work on s32 as well, but it's unclear how that should work for unorm LUT definitions. We'll revisit that once we add LUT + CTM tests. In order to allow for this we'll also invert the nesting of our colorop processing loops. We now use the pixel iteration loop on the outside and the colorop iteration on the inside. v3: - Use new colorop->next pointer Signed-off-by: Harry Wentland <harry.wentland@amd.com> --- drivers/gpu/drm/vkms/vkms_composer.c | 55 +++++++++++++++++++++------- drivers/gpu/drm/vkms/vkms_drv.h | 4 ++ 2 files changed, 46 insertions(+), 13 deletions(-)