media: vicodec: add support for CROP and COMPOSE selection

Add support for the selection api for the crop and compose targets.
The driver rounds up the coded width and height such that
all planes dimensions are multiple of 8.

Signed-off-by: Dafna Hirschfeld <dafna3@gmail.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>

1 files changed, 200 insertions, 93 deletions

diff --git a/drivers/media/platform/vicodec/codec-v4l2-fwht.c b/drivers/media/platform/vicodec/codec-v4l2-fwht.c
index 5e9040f6c902..e9c522d209ab 100644
--- a/drivers/media/platform/vicodec/codec-v4l2-fwht.c
+++ b/drivers/media/platform/vicodec/codec-v4l2-fwht.c
@@ -56,7 +56,8 @@ const struct v4l2_fwht_pixfmt_info *v4l2_fwht_get_pixfmt(u32 idx)
 
 int v4l2_fwht_encode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 {
-	unsigned int size = state->width * state->height;
+	unsigned int size = state->stride * state->coded_height;
+	unsigned int chroma_stride = state->stride;
 	const struct v4l2_fwht_pixfmt_info *info = state->info;
 	struct fwht_cframe_hdr *p_hdr;
 	struct fwht_cframe cf;
@@ -66,8 +67,7 @@ int v4l2_fwht_encode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 
 	if (!info)
 		return -EINVAL;
-	rf.width = state->width;
-	rf.height = state->height;
+
 	rf.luma = p_in;
 	rf.width_div = info->width_div;
 	rf.height_div = info->height_div;
@@ -84,14 +84,17 @@ int v4l2_fwht_encode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 	case V4L2_PIX_FMT_YUV420:
 		rf.cb = rf.luma + size;
 		rf.cr = rf.cb + size / 4;
+		chroma_stride /= 2;
 		break;
 	case V4L2_PIX_FMT_YVU420:
 		rf.cr = rf.luma + size;
 		rf.cb = rf.cr + size / 4;
+		chroma_stride /= 2;
 		break;
 	case V4L2_PIX_FMT_YUV422P:
 		rf.cb = rf.luma + size;
 		rf.cr = rf.cb + size / 2;
+		chroma_stride /= 2;
 		break;
 	case V4L2_PIX_FMT_NV12:
 	case V4L2_PIX_FMT_NV16:
@@ -163,15 +166,16 @@ int v4l2_fwht_encode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 		return -EINVAL;
 	}
 
-	cf.width = state->width;
-	cf.height = state->height;
 	cf.i_frame_qp = state->i_frame_qp;
 	cf.p_frame_qp = state->p_frame_qp;
 	cf.rlc_data = (__be16 *)(p_out + sizeof(*p_hdr));
 
 	encoding = fwht_encode_frame(&rf, &state->ref_frame, &cf,
 				     !state->gop_cnt,
-				     state->gop_cnt == state->gop_size - 1);
+				     state->gop_cnt == state->gop_size - 1,
+				     state->visible_width,
+				     state->visible_height,
+				     state->stride, chroma_stride);
 	if (!(encoding & FWHT_FRAME_PCODED))
 		state->gop_cnt = 0;
 	if (++state->gop_cnt >= state->gop_size)
@@ -181,8 +185,8 @@ int v4l2_fwht_encode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 	p_hdr->magic1 = FWHT_MAGIC1;
 	p_hdr->magic2 = FWHT_MAGIC2;
 	p_hdr->version = htonl(FWHT_VERSION);
-	p_hdr->width = htonl(cf.width);
-	p_hdr->height = htonl(cf.height);
+	p_hdr->width = htonl(state->visible_width);
+	p_hdr->height = htonl(state->visible_height);
 	flags |= (info->components_num - 1) << FWHT_FL_COMPONENTS_NUM_OFFSET;
 	if (encoding & FWHT_LUMA_UNENCODED)
 		flags |= FWHT_FL_LUMA_IS_UNCOMPRESSED;
@@ -202,29 +206,26 @@ int v4l2_fwht_encode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 	p_hdr->ycbcr_enc = htonl(state->ycbcr_enc);
 	p_hdr->quantization = htonl(state->quantization);
 	p_hdr->size = htonl(cf.size);
-	state->ref_frame.width = cf.width;
-	state->ref_frame.height = cf.height;
 	return cf.size + sizeof(*p_hdr);
 }
 
 int v4l2_fwht_decode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 {
-	unsigned int size = state->width * state->height;
-	unsigned int chroma_size = size;
-	unsigned int i;
+	unsigned int i, j, k;
 	u32 flags;
 	struct fwht_cframe_hdr *p_hdr;
 	struct fwht_cframe cf;
-	u8 *p;
+	u8 *p, *ref_p;
 	unsigned int components_num = 3;
 	unsigned int version;
+	const struct v4l2_fwht_pixfmt_info *info;
+	unsigned int hdr_width_div, hdr_height_div;
 
 	if (!state->info)
 		return -EINVAL;
 
+	info = state->info;
 	p_hdr = (struct fwht_cframe_hdr *)p_in;
-	cf.width = ntohl(p_hdr->width);
-	cf.height = ntohl(p_hdr->height);
 
 	version = ntohl(p_hdr->version);
 	if (!version || version > FWHT_VERSION) {
@@ -234,12 +235,12 @@ int v4l2_fwht_decode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 	}
 
 	if (p_hdr->magic1 != FWHT_MAGIC1 ||
-	    p_hdr->magic2 != FWHT_MAGIC2 ||
-	    (cf.width & 7) || (cf.height & 7))
+	    p_hdr->magic2 != FWHT_MAGIC2)
 		return -EINVAL;
 
 	/* TODO: support resolution changes */
-	if (cf.width != state->width || cf.height != state->height)
+	if (ntohl(p_hdr->width)  != state->visible_width ||
+	    ntohl(p_hdr->height) != state->visible_height)
 		return -EINVAL;
 
 	flags = ntohl(p_hdr->flags);
@@ -255,12 +256,15 @@ int v4l2_fwht_decode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 	state->quantization = ntohl(p_hdr->quantization);
 	cf.rlc_data = (__be16 *)(p_in + sizeof(*p_hdr));
 
-	if (!(flags & FWHT_FL_CHROMA_FULL_WIDTH))
-		chroma_size /= 2;
-	if (!(flags & FWHT_FL_CHROMA_FULL_HEIGHT))
-		chroma_size /= 2;
+	hdr_width_div = (flags & FWHT_FL_CHROMA_FULL_WIDTH) ? 1 : 2;
+	hdr_height_div = (flags & FWHT_FL_CHROMA_FULL_HEIGHT) ? 1 : 2;
+	if (hdr_width_div != info->width_div ||
+	    hdr_height_div != info->height_div)
+		return -EINVAL;
 
-	fwht_decode_frame(&cf, &state->ref_frame, flags, components_num);
+	fwht_decode_frame(&cf, &state->ref_frame, flags, components_num,
+			  state->visible_width, state->visible_height,
+			  state->coded_width);
 
 	/*
 	 * TODO - handle the case where the compressed stream encodes a
@@ -268,123 +272,226 @@ int v4l2_fwht_decode(struct v4l2_fwht_state *state, u8 *p_in, u8 *p_out)
 	 */
 	switch (state->info->id) {
 	case V4L2_PIX_FMT_GREY:
-		memcpy(p_out, state->ref_frame.luma, size);
+		ref_p = state->ref_frame.luma;
+		for (i = 0; i < state->coded_height; i++)  {
+			memcpy(p_out, ref_p, state->visible_width);
+			p_out += state->stride;
+			ref_p += state->coded_width;
+		}
 		break;
 	case V4L2_PIX_FMT_YUV420:
 	case V4L2_PIX_FMT_YUV422P:
-		memcpy(p_out, state->ref_frame.luma, size);
-		p_out += size;
-		memcpy(p_out, state->ref_frame.cb, chroma_size);
-		p_out += chroma_size;
-		memcpy(p_out, state->ref_frame.cr, chroma_size);
+		ref_p = state->ref_frame.luma;
+		for (i = 0; i < state->coded_height; i++)  {
+			memcpy(p_out, ref_p, state->visible_width);
+			p_out += state->stride;
+			ref_p += state->coded_width;
+		}
+
+		ref_p = state->ref_frame.cb;
+		for (i = 0; i < state->coded_height / 2; i++)  {
+			memcpy(p_out, ref_p, state->visible_width / 2);
+			p_out += state->stride / 2;
+			ref_p += state->coded_width / 2;
+		}
+		ref_p = state->ref_frame.cr;
+		for (i = 0; i < state->coded_height / 2; i++)  {
+			memcpy(p_out, ref_p, state->visible_width / 2);
+			p_out += state->stride / 2;
+			ref_p += state->coded_width / 2;
+		}
 		break;
 	case V4L2_PIX_FMT_YVU420:
-		memcpy(p_out, state->ref_frame.luma, size);
-		p_out += size;
-		memcpy(p_out, state->ref_frame.cr, chroma_size);
-		p_out += chroma_size;
-		memcpy(p_out, state->ref_frame.cb, chroma_size);
+		ref_p = state->ref_frame.luma;
+		for (i = 0; i < state->coded_height; i++)  {
+			memcpy(p_out, ref_p, state->visible_width);
+			p_out += state->stride;
+			ref_p += state->coded_width;
+		}
+
+		ref_p = state->ref_frame.cr;
+		for (i = 0; i < state->coded_height / 2; i++)  {
+			memcpy(p_out, ref_p, state->visible_width / 2);
+			p_out += state->stride / 2;
+			ref_p += state->coded_width / 2;
+		}
+		ref_p = state->ref_frame.cb;
+		for (i = 0; i < state->coded_height / 2; i++)  {
+			memcpy(p_out, ref_p, state->visible_width / 2);
+			p_out += state->stride / 2;
+			ref_p += state->coded_width / 2;
+		}
 		break;
 	case V4L2_PIX_FMT_NV12:
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV24:
-		memcpy(p_out, state->ref_frame.luma, size);
-		p_out += size;
-		for (i = 0, p = p_out; i < chroma_size; i++) {
-			*p++ = state->ref_frame.cb[i];
-			*p++ = state->ref_frame.cr[i];
+		ref_p = state->ref_frame.luma;
+		for (i = 0; i < state->coded_height; i++)  {
+			memcpy(p_out, ref_p, state->visible_width);
+			p_out += state->stride;
+			ref_p += state->coded_width;
+		}
+
+		k = 0;
+		for (i = 0; i < state->coded_height / 2; i++) {
+			for (j = 0, p = p_out; j < state->coded_width / 2; j++) {
+				*p++ = state->ref_frame.cb[k];
+				*p++ = state->ref_frame.cr[k];
+				k++;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_NV21:
 	case V4L2_PIX_FMT_NV61:
 	case V4L2_PIX_FMT_NV42:
-		memcpy(p_out, state->ref_frame.luma, size);
-		p_out += size;
-		for (i = 0, p = p_out; i < chroma_size; i++) {
-			*p++ = state->ref_frame.cr[i];
-			*p++ = state->ref_frame.cb[i];
+		ref_p = state->ref_frame.luma;
+		for (i = 0; i < state->coded_height; i++)  {
+			memcpy(p_out, ref_p, state->visible_width);
+			p_out += state->stride;
+			ref_p += state->coded_width;
+		}
+
+		k = 0;
+		for (i = 0; i < state->coded_height / 2; i++) {
+			for (j = 0, p = p_out; j < state->coded_width / 2; j++) {
+				*p++ = state->ref_frame.cr[k];
+				*p++ = state->ref_frame.cb[k];
+				k++;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_YUYV:
-		for (i = 0, p = p_out; i < size; i += 2) {
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cb[i / 2];
-			*p++ = state->ref_frame.luma[i + 1];
-			*p++ = state->ref_frame.cr[i / 2];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width / 2; j++) {
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cb[k / 2];
+				*p++ = state->ref_frame.luma[k + 1];
+				*p++ = state->ref_frame.cr[k / 2];
+				k += 2;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_YVYU:
-		for (i = 0, p = p_out; i < size; i += 2) {
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cr[i / 2];
-			*p++ = state->ref_frame.luma[i + 1];
-			*p++ = state->ref_frame.cb[i / 2];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width / 2; j++) {
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cr[k / 2];
+				*p++ = state->ref_frame.luma[k + 1];
+				*p++ = state->ref_frame.cb[k / 2];
+				k += 2;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_UYVY:
-		for (i = 0, p = p_out; i < size; i += 2) {
-			*p++ = state->ref_frame.cb[i / 2];
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cr[i / 2];
-			*p++ = state->ref_frame.luma[i + 1];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width / 2; j++) {
+				*p++ = state->ref_frame.cb[k / 2];
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cr[k / 2];
+				*p++ = state->ref_frame.luma[k + 1];
+				k += 2;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_VYUY:
-		for (i = 0, p = p_out; i < size; i += 2) {
-			*p++ = state->ref_frame.cr[i / 2];
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cb[i / 2];
-			*p++ = state->ref_frame.luma[i + 1];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width / 2; j++) {
+				*p++ = state->ref_frame.cr[k / 2];
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cb[k / 2];
+				*p++ = state->ref_frame.luma[k + 1];
+				k += 2;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_RGB24:
 	case V4L2_PIX_FMT_HSV24:
-		for (i = 0, p = p_out; i < size; i++) {
-			*p++ = state->ref_frame.cr[i];
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cb[i];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width; j++) {
+				*p++ = state->ref_frame.cr[k];
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cb[k];
+				k++;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_BGR24:
-		for (i = 0, p = p_out; i < size; i++) {
-			*p++ = state->ref_frame.cb[i];
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cr[i];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width; j++) {
+				*p++ = state->ref_frame.cb[k];
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cr[k];
+				k++;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_RGB32:
 	case V4L2_PIX_FMT_XRGB32:
 	case V4L2_PIX_FMT_HSV32:
-		for (i = 0, p = p_out; i < size; i++) {
-			*p++ = 0;
-			*p++ = state->ref_frame.cr[i];
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cb[i];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width; j++) {
+				*p++ = 0;
+				*p++ = state->ref_frame.cr[k];
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cb[k];
+				k++;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_BGR32:
 	case V4L2_PIX_FMT_XBGR32:
-		for (i = 0, p = p_out; i < size; i++) {
-			*p++ = state->ref_frame.cb[i];
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cr[i];
-			*p++ = 0;
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width; j++) {
+				*p++ = state->ref_frame.cb[k];
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cr[k];
+				*p++ = 0;
+				k++;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_ARGB32:
-		for (i = 0, p = p_out; i < size; i++) {
-			*p++ = state->ref_frame.alpha[i];
-			*p++ = state->ref_frame.cr[i];
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cb[i];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width; j++) {
+				*p++ = state->ref_frame.alpha[k];
+				*p++ = state->ref_frame.cr[k];
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cb[k];
+				k++;
+			}
+			p_out += state->stride;
 		}
 		break;
 	case V4L2_PIX_FMT_ABGR32:
-		for (i = 0, p = p_out; i < size; i++) {
-			*p++ = state->ref_frame.cb[i];
-			*p++ = state->ref_frame.luma[i];
-			*p++ = state->ref_frame.cr[i];
-			*p++ = state->ref_frame.alpha[i];
+		k = 0;
+		for (i = 0; i < state->coded_height; i++) {
+			for (j = 0, p = p_out; j < state->coded_width; j++) {
+				*p++ = state->ref_frame.cb[k];
+				*p++ = state->ref_frame.luma[k];
+				*p++ = state->ref_frame.cr[k];
+				*p++ = state->ref_frame.alpha[k];
+				k++;
+			}
+			p_out += state->stride;
 		}
 		break;
 	default: