Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 325 insertions, 192 deletions

diff --git a/drivers/media/platform/rockchip/rga/rga-buf.c b/drivers/media/platform/rockchip/rga/rga-buf.c
index 81508ed5ab..662c81b6d0 100644
--- a/drivers/media/platform/rockchip/rga/rga-buf.c
+++ b/drivers/media/platform/rockchip/rga/rga-buf.c
@@ -5,7 +5,9 @@
  */
 
 #include <linux/pm_runtime.h>
+#include <linux/scatterlist.h>
 
+#include <media/v4l2-common.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-mem2mem.h>
@@ -15,6 +17,26 @@
 #include "rga-hw.h"
 #include "rga.h"
 
+static ssize_t fill_descriptors(struct rga_dma_desc *desc, size_t max_desc,
+				struct sg_table *sgt)
+{
+	struct sg_dma_page_iter iter;
+	struct rga_dma_desc *tmp = desc;
+	size_t n_desc = 0;
+	dma_addr_t addr;
+
+	for_each_sgtable_dma_page(sgt, &iter, 0) {
+		if (n_desc > max_desc)
+			return -EINVAL;
+		addr = sg_page_iter_dma_address(&iter);
+		tmp->addr = lower_32_bits(addr);
+		tmp++;
+		n_desc++;
+	}
+
+	return n_desc;
+}
+
 static int
 rga_queue_setup(struct vb2_queue *vq,
 		unsigned int *nbuffers, unsigned int *nplanes,
@@ -22,28 +44,105 @@ rga_queue_setup(struct vb2_queue *vq,
 {
 	struct rga_ctx *ctx = vb2_get_drv_priv(vq);
 	struct rga_frame *f = rga_get_frame(ctx, vq->type);
+	const struct v4l2_pix_format_mplane *pix_fmt;
+	int i;
 
 	if (IS_ERR(f))
 		return PTR_ERR(f);
 
-	if (*nplanes)
-		return sizes[0] < f->size ? -EINVAL : 0;
+	pix_fmt = &f->pix;
+
+	if (*nplanes) {
+		if (*nplanes != pix_fmt->num_planes)
+			return -EINVAL;
+
+		for (i = 0; i < pix_fmt->num_planes; i++)
+			if (sizes[i] < pix_fmt->plane_fmt[i].sizeimage)
+				return -EINVAL;
+
+		return 0;
+	}
+
+	*nplanes = pix_fmt->num_planes;
+
+	for (i = 0; i < pix_fmt->num_planes; i++)
+		sizes[i] = pix_fmt->plane_fmt[i].sizeimage;
+
+	return 0;
+}
+
+static int rga_buf_init(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rga_vb_buffer *rbuf = vb_to_rga(vbuf);
+	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct rockchip_rga *rga = ctx->rga;
+	struct rga_frame *f = rga_get_frame(ctx, vb->vb2_queue->type);
+	size_t n_desc = 0;
 
-	sizes[0] = f->size;
-	*nplanes = 1;
+	n_desc = DIV_ROUND_UP(f->size, PAGE_SIZE);
+
+	rbuf->n_desc = n_desc;
+	rbuf->dma_desc = dma_alloc_coherent(rga->dev,
+					    rbuf->n_desc * sizeof(*rbuf->dma_desc),
+					    &rbuf->dma_desc_pa, GFP_KERNEL);
+	if (!rbuf->dma_desc)
+		return -ENOMEM;
 
 	return 0;
 }
 
+static int get_plane_offset(struct rga_frame *f, int plane)
+{
+	if (plane == 0)
+		return 0;
+	if (plane == 1)
+		return f->width * f->height;
+	if (plane == 2)
+		return f->width * f->height + (f->width * f->height / f->fmt->uv_factor);
+
+	return -EINVAL;
+}
+
 static int rga_buf_prepare(struct vb2_buffer *vb)
 {
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rga_vb_buffer *rbuf = vb_to_rga(vbuf);
 	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
 	struct rga_frame *f = rga_get_frame(ctx, vb->vb2_queue->type);
+	ssize_t n_desc = 0;
+	size_t curr_desc = 0;
+	int i;
+	const struct v4l2_format_info *info;
+	unsigned int offsets[VIDEO_MAX_PLANES];
 
 	if (IS_ERR(f))
 		return PTR_ERR(f);
 
-	vb2_set_plane_payload(vb, 0, f->size);
+	for (i = 0; i < vb->num_planes; i++) {
+		vb2_set_plane_payload(vb, i, f->pix.plane_fmt[i].sizeimage);
+
+		/* Create local MMU table for RGA */
+		n_desc = fill_descriptors(&rbuf->dma_desc[curr_desc],
+					  rbuf->n_desc - curr_desc,
+					  vb2_dma_sg_plane_desc(vb, i));
+		if (n_desc < 0) {
+			v4l2_err(&ctx->rga->v4l2_dev,
+				 "Failed to map video buffer to RGA\n");
+			return n_desc;
+		}
+		offsets[i] = curr_desc << PAGE_SHIFT;
+		curr_desc += n_desc;
+	}
+
+	/* Fill the remaining planes */
+	info = v4l2_format_info(f->fmt->fourcc);
+	for (i = info->mem_planes; i < info->comp_planes; i++)
+		offsets[i] = get_plane_offset(f, i);
+
+	rbuf->offset.y_off = offsets[0];
+	rbuf->offset.u_off = offsets[1];
+	rbuf->offset.v_off = offsets[2];
 
 	return 0;
 }
@@ -56,6 +155,17 @@ static void rga_buf_queue(struct vb2_buffer *vb)
 	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
 }
 
+static void rga_buf_cleanup(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct rga_vb_buffer *rbuf = vb_to_rga(vbuf);
+	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct rockchip_rga *rga = ctx->rga;
+
+	dma_free_coherent(rga->dev, rbuf->n_desc * sizeof(*rbuf->dma_desc),
+			  rbuf->dma_desc, rbuf->dma_desc_pa);
+}
+
 static void rga_buf_return_buffers(struct vb2_queue *q,
 				   enum vb2_buffer_state state)
 {
@@ -99,50 +209,12 @@ static void rga_buf_stop_streaming(struct vb2_queue *q)
 
 const struct vb2_ops rga_qops = {
 	.queue_setup = rga_queue_setup,
+	.buf_init = rga_buf_init,
 	.buf_prepare = rga_buf_prepare,
 	.buf_queue = rga_buf_queue,
+	.buf_cleanup = rga_buf_cleanup,
 	.wait_prepare = vb2_ops_wait_prepare,
 	.wait_finish = vb2_ops_wait_finish,
 	.start_streaming = rga_buf_start_streaming,
 	.stop_streaming = rga_buf_stop_streaming,
 };
-
-/* RGA MMU is a 1-Level MMU, so it can't be used through the IOMMU API.
- * We use it more like a scatter-gather list.
- */
-void rga_buf_map(struct vb2_buffer *vb)
-{
-	struct rga_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
-	struct rockchip_rga *rga = ctx->rga;
-	struct sg_table *sgt;
-	struct scatterlist *sgl;
-	unsigned int *pages;
-	unsigned int address, len, i, p;
-	unsigned int mapped_size = 0;
-
-	if (vb->type == V4L2_BUF_TYPE_VIDEO_OUTPUT)
-		pages = rga->src_mmu_pages;
-	else
-		pages = rga->dst_mmu_pages;
-
-	/* Create local MMU table for RGA */
-	sgt = vb2_plane_cookie(vb, 0);
-
-	for_each_sg(sgt->sgl, sgl, sgt->nents, i) {
-		len = sg_dma_len(sgl) >> PAGE_SHIFT;
-		address = sg_phys(sgl);
-
-		for (p = 0; p < len; p++) {
-			dma_addr_t phys = address +
-					  ((dma_addr_t)p << PAGE_SHIFT);
-
-			pages[mapped_size + p] = phys;
-		}
-
-		mapped_size += len;
-	}
-
-	/* sync local MMU table for RGA */
-	dma_sync_single_for_device(rga->dev, virt_to_phys(pages),
-				   8 * PAGE_SIZE, DMA_BIDIRECTIONAL);
-}
diff --git a/drivers/media/platform/rockchip/rga/rga-hw.c b/drivers/media/platform/rockchip/rga/rga-hw.c
index aaa96f2563..11c3d72347 100644
--- a/drivers/media/platform/rockchip/rga/rga-hw.c
+++ b/drivers/media/platform/rockchip/rga/rga-hw.c
@@ -16,12 +16,6 @@ enum e_rga_start_pos {
 	RB = 3,
 };
 
-struct rga_addr_offset {
-	unsigned int y_off;
-	unsigned int u_off;
-	unsigned int v_off;
-};
-
 struct rga_corners_addr_offset {
 	struct rga_addr_offset left_top;
 	struct rga_addr_offset right_top;
@@ -43,13 +37,13 @@ static unsigned int rga_get_scaling(unsigned int src, unsigned int dst)
 }
 
 static struct rga_corners_addr_offset
-rga_get_addr_offset(struct rga_frame *frm, unsigned int x, unsigned int y,
-		    unsigned int w, unsigned int h)
+rga_get_addr_offset(struct rga_frame *frm, struct rga_addr_offset *offset,
+		    unsigned int x, unsigned int y, unsigned int w, unsigned int h)
 {
 	struct rga_corners_addr_offset offsets;
 	struct rga_addr_offset *lt, *lb, *rt, *rb;
 	unsigned int x_div = 0,
-		     y_div = 0, uv_stride = 0, pixel_width = 0, uv_factor = 0;
+		     y_div = 0, uv_stride = 0, pixel_width = 0;
 
 	lt = &offsets.left_top;
 	lb = &offsets.left_bottom;
@@ -58,14 +52,12 @@ rga_get_addr_offset(struct rga_frame *frm, unsigned int x, unsigned int y,
 
 	x_div = frm->fmt->x_div;
 	y_div = frm->fmt->y_div;
-	uv_factor = frm->fmt->uv_factor;
 	uv_stride = frm->stride / x_div;
 	pixel_width = frm->stride / frm->width;
 
-	lt->y_off = y * frm->stride + x * pixel_width;
-	lt->u_off =
-		frm->width * frm->height + (y / y_div) * uv_stride + x / x_div;
-	lt->v_off = lt->u_off + frm->width * frm->height / uv_factor;
+	lt->y_off = offset->y_off + y * frm->stride + x * pixel_width;
+	lt->u_off = offset->u_off + (y / y_div) * uv_stride + x / x_div;
+	lt->v_off = offset->v_off + (y / y_div) * uv_stride + x / x_div;
 
 	lb->y_off = lt->y_off + (h - 1) * frm->stride;
 	lb->u_off = lt->u_off + (h / y_div - 1) * uv_stride;
@@ -119,40 +111,40 @@ static struct rga_addr_offset *rga_lookup_draw_pos(struct
 	return NULL;
 }
 
-static void rga_cmd_set_src_addr(struct rga_ctx *ctx, void *mmu_pages)
+static void rga_cmd_set_src_addr(struct rga_ctx *ctx, dma_addr_t dma_addr)
 {
 	struct rockchip_rga *rga = ctx->rga;
 	u32 *dest = rga->cmdbuf_virt;
 	unsigned int reg;
 
 	reg = RGA_MMU_SRC_BASE - RGA_MODE_BASE_REG;
-	dest[reg >> 2] = virt_to_phys(mmu_pages) >> 4;
+	dest[reg >> 2] = dma_addr >> 4;
 
 	reg = RGA_MMU_CTRL1 - RGA_MODE_BASE_REG;
 	dest[reg >> 2] |= 0x7;
 }
 
-static void rga_cmd_set_src1_addr(struct rga_ctx *ctx, void *mmu_pages)
+static void rga_cmd_set_src1_addr(struct rga_ctx *ctx, dma_addr_t dma_addr)
 {
 	struct rockchip_rga *rga = ctx->rga;
 	u32 *dest = rga->cmdbuf_virt;
 	unsigned int reg;
 
 	reg = RGA_MMU_SRC1_BASE - RGA_MODE_BASE_REG;
-	dest[reg >> 2] = virt_to_phys(mmu_pages) >> 4;
+	dest[reg >> 2] = dma_addr >> 4;
 
 	reg = RGA_MMU_CTRL1 - RGA_MODE_BASE_REG;
 	dest[reg >> 2] |= 0x7 << 4;
 }
 
-static void rga_cmd_set_dst_addr(struct rga_ctx *ctx, void *mmu_pages)
+static void rga_cmd_set_dst_addr(struct rga_ctx *ctx, dma_addr_t dma_addr)
 {
 	struct rockchip_rga *rga = ctx->rga;
 	u32 *dest = rga->cmdbuf_virt;
 	unsigned int reg;
 
 	reg = RGA_MMU_DST_BASE - RGA_MODE_BASE_REG;
-	dest[reg >> 2] = virt_to_phys(mmu_pages) >> 4;
+	dest[reg >> 2] = dma_addr >> 4;
 
 	reg = RGA_MMU_CTRL1 - RGA_MODE_BASE_REG;
 	dest[reg >> 2] |= 0x7 << 8;
@@ -163,7 +155,7 @@ static void rga_cmd_set_trans_info(struct rga_ctx *ctx)
 	struct rockchip_rga *rga = ctx->rga;
 	u32 *dest = rga->cmdbuf_virt;
 	unsigned int scale_dst_w, scale_dst_h;
-	unsigned int src_h, src_w, src_x, src_y, dst_h, dst_w, dst_x, dst_y;
+	unsigned int src_h, src_w, dst_h, dst_w;
 	union rga_src_info src_info;
 	union rga_dst_info dst_info;
 	union rga_src_x_factor x_factor;
@@ -173,18 +165,10 @@ static void rga_cmd_set_trans_info(struct rga_ctx *ctx)
 	union rga_dst_vir_info dst_vir_info;
 	union rga_dst_act_info dst_act_info;
 
-	struct rga_addr_offset *dst_offset;
-	struct rga_corners_addr_offset offsets;
-	struct rga_corners_addr_offset src_offsets;
-
 	src_h = ctx->in.crop.height;
 	src_w = ctx->in.crop.width;
-	src_x = ctx->in.crop.left;
-	src_y = ctx->in.crop.top;
 	dst_h = ctx->out.crop.height;
 	dst_w = ctx->out.crop.width;
-	dst_x = ctx->out.crop.left;
-	dst_y = ctx->out.crop.top;
 
 	src_info.val = dest[(RGA_SRC_INFO - RGA_MODE_BASE_REG) >> 2];
 	dst_info.val = dest[(RGA_DST_INFO - RGA_MODE_BASE_REG) >> 2];
@@ -312,18 +296,37 @@ static void rga_cmd_set_trans_info(struct rga_ctx *ctx)
 	dst_act_info.data.act_height = dst_h - 1;
 	dst_act_info.data.act_width = dst_w - 1;
 
-	/*
-	 * Calculate the source framebuffer base address with offset pixel.
-	 */
-	src_offsets = rga_get_addr_offset(&ctx->in, src_x, src_y,
-					  src_w, src_h);
+	dest[(RGA_SRC_X_FACTOR - RGA_MODE_BASE_REG) >> 2] = x_factor.val;
+	dest[(RGA_SRC_Y_FACTOR - RGA_MODE_BASE_REG) >> 2] = y_factor.val;
+	dest[(RGA_SRC_VIR_INFO - RGA_MODE_BASE_REG) >> 2] = src_vir_info.val;
+	dest[(RGA_SRC_ACT_INFO - RGA_MODE_BASE_REG) >> 2] = src_act_info.val;
+
+	dest[(RGA_SRC_INFO - RGA_MODE_BASE_REG) >> 2] = src_info.val;
+
+	dest[(RGA_DST_VIR_INFO - RGA_MODE_BASE_REG) >> 2] = dst_vir_info.val;
+	dest[(RGA_DST_ACT_INFO - RGA_MODE_BASE_REG) >> 2] = dst_act_info.val;
+
+	dest[(RGA_DST_INFO - RGA_MODE_BASE_REG) >> 2] = dst_info.val;
+}
+
+static void rga_cmd_set_src_info(struct rga_ctx *ctx,
+				 struct rga_addr_offset *offset)
+{
+	struct rga_corners_addr_offset src_offsets;
+	struct rockchip_rga *rga = ctx->rga;
+	u32 *dest = rga->cmdbuf_virt;
+	unsigned int src_h, src_w, src_x, src_y;
+
+	src_h = ctx->in.crop.height;
+	src_w = ctx->in.crop.width;
+	src_x = ctx->in.crop.left;
+	src_y = ctx->in.crop.top;
 
 	/*
-	 * Configure the dest framebuffer base address with pixel offset.
+	 * Calculate the source framebuffer base address with offset pixel.
 	 */
-	offsets = rga_get_addr_offset(&ctx->out, dst_x, dst_y, dst_w, dst_h);
-	dst_offset = rga_lookup_draw_pos(&offsets, src_info.data.rot_mode,
-					 src_info.data.mir_mode);
+	src_offsets = rga_get_addr_offset(&ctx->in, offset,
+					  src_x, src_y, src_w, src_h);
 
 	dest[(RGA_SRC_Y_RGB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
 		src_offsets.left_top.y_off;
@@ -331,13 +334,49 @@ static void rga_cmd_set_trans_info(struct rga_ctx *ctx)
 		src_offsets.left_top.u_off;
 	dest[(RGA_SRC_CR_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
 		src_offsets.left_top.v_off;
+}
 
-	dest[(RGA_SRC_X_FACTOR - RGA_MODE_BASE_REG) >> 2] = x_factor.val;
-	dest[(RGA_SRC_Y_FACTOR - RGA_MODE_BASE_REG) >> 2] = y_factor.val;
-	dest[(RGA_SRC_VIR_INFO - RGA_MODE_BASE_REG) >> 2] = src_vir_info.val;
-	dest[(RGA_SRC_ACT_INFO - RGA_MODE_BASE_REG) >> 2] = src_act_info.val;
+static void rga_cmd_set_dst_info(struct rga_ctx *ctx,
+				 struct rga_addr_offset *offset)
+{
+	struct rga_addr_offset *dst_offset;
+	struct rga_corners_addr_offset offsets;
+	struct rockchip_rga *rga = ctx->rga;
+	u32 *dest = rga->cmdbuf_virt;
+	unsigned int dst_h, dst_w, dst_x, dst_y;
+	unsigned int mir_mode = 0;
+	unsigned int rot_mode = 0;
 
-	dest[(RGA_SRC_INFO - RGA_MODE_BASE_REG) >> 2] = src_info.val;
+	dst_h = ctx->out.crop.height;
+	dst_w = ctx->out.crop.width;
+	dst_x = ctx->out.crop.left;
+	dst_y = ctx->out.crop.top;
+
+	if (ctx->vflip)
+		mir_mode |= RGA_SRC_MIRR_MODE_X;
+	if (ctx->hflip)
+		mir_mode |= RGA_SRC_MIRR_MODE_Y;
+
+	switch (ctx->rotate) {
+	case 90:
+		rot_mode = RGA_SRC_ROT_MODE_90_DEGREE;
+		break;
+	case 180:
+		rot_mode = RGA_SRC_ROT_MODE_180_DEGREE;
+		break;
+	case 270:
+		rot_mode = RGA_SRC_ROT_MODE_270_DEGREE;
+		break;
+	default:
+		rot_mode = RGA_SRC_ROT_MODE_0_DEGREE;
+		break;
+	}
+
+	/*
+	 * Configure the dest framebuffer base address with pixel offset.
+	 */
+	offsets = rga_get_addr_offset(&ctx->out, offset, dst_x, dst_y, dst_w, dst_h);
+	dst_offset = rga_lookup_draw_pos(&offsets, mir_mode, rot_mode);
 
 	dest[(RGA_DST_Y_RGB_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
 		dst_offset->y_off;
@@ -345,11 +384,6 @@ static void rga_cmd_set_trans_info(struct rga_ctx *ctx)
 		dst_offset->u_off;
 	dest[(RGA_DST_CR_BASE_ADDR - RGA_MODE_BASE_REG) >> 2] =
 		dst_offset->v_off;
-
-	dest[(RGA_DST_VIR_INFO - RGA_MODE_BASE_REG) >> 2] = dst_vir_info.val;
-	dest[(RGA_DST_ACT_INFO - RGA_MODE_BASE_REG) >> 2] = dst_act_info.val;
-
-	dest[(RGA_DST_INFO - RGA_MODE_BASE_REG) >> 2] = dst_info.val;
 }
 
 static void rga_cmd_set_mode(struct rga_ctx *ctx)
@@ -375,22 +409,25 @@ static void rga_cmd_set_mode(struct rga_ctx *ctx)
 	dest[(RGA_MODE_CTRL - RGA_MODE_BASE_REG) >> 2] = mode.val;
 }
 
-static void rga_cmd_set(struct rga_ctx *ctx)
+static void rga_cmd_set(struct rga_ctx *ctx,
+			struct rga_vb_buffer *src, struct rga_vb_buffer *dst)
 {
 	struct rockchip_rga *rga = ctx->rga;
 
 	memset(rga->cmdbuf_virt, 0, RGA_CMDBUF_SIZE * 4);
 
-	rga_cmd_set_src_addr(ctx, rga->src_mmu_pages);
+	rga_cmd_set_src_addr(ctx, src->dma_desc_pa);
 	/*
 	 * Due to hardware bug,
 	 * src1 mmu also should be configured when using alpha blending.
 	 */
-	rga_cmd_set_src1_addr(ctx, rga->dst_mmu_pages);
+	rga_cmd_set_src1_addr(ctx, dst->dma_desc_pa);
 
-	rga_cmd_set_dst_addr(ctx, rga->dst_mmu_pages);
+	rga_cmd_set_dst_addr(ctx, dst->dma_desc_pa);
 	rga_cmd_set_mode(ctx);
 
+	rga_cmd_set_src_info(ctx, &src->offset);
+	rga_cmd_set_dst_info(ctx, &dst->offset);
 	rga_cmd_set_trans_info(ctx);
 
 	rga_write(rga, RGA_CMD_BASE, rga->cmdbuf_phy);
@@ -400,11 +437,12 @@ static void rga_cmd_set(struct rga_ctx *ctx)
 		PAGE_SIZE, DMA_BIDIRECTIONAL);
 }
 
-void rga_hw_start(struct rockchip_rga *rga)
+void rga_hw_start(struct rockchip_rga *rga,
+		  struct rga_vb_buffer *src, struct rga_vb_buffer *dst)
 {
 	struct rga_ctx *ctx = rga->curr;
 
-	rga_cmd_set(ctx);
+	rga_cmd_set(ctx, src, dst);
 
 	rga_write(rga, RGA_SYS_CTRL, 0x00);
 
diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c
index 25f5b5eebf..00fdfa9e10 100644
--- a/drivers/media/platform/rockchip/rga/rga.c
+++ b/drivers/media/platform/rockchip/rga/rga.c
@@ -45,10 +45,7 @@ static void device_run(void *prv)
 	src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
 	dst = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
 
-	rga_buf_map(&src->vb2_buf);
-	rga_buf_map(&dst->vb2_buf);
-
-	rga_hw_start(rga);
+	rga_hw_start(rga, vb_to_rga(src), vb_to_rga(dst));
 
 	spin_unlock_irqrestore(&rga->ctrl_lock, flags);
 }
@@ -96,12 +93,13 @@ queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_queue *dst_vq)
 	struct rga_ctx *ctx = priv;
 	int ret;
 
-	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT;
+	src_vq->type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
 	src_vq->io_modes = VB2_MMAP | VB2_DMABUF;
 	src_vq->drv_priv = ctx;
 	src_vq->ops = &rga_qops;
 	src_vq->mem_ops = &vb2_dma_sg_memops;
-	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	dst_vq->gfp_flags = __GFP_DMA32;
+	src_vq->buf_struct_size = sizeof(struct rga_vb_buffer);
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->lock = &ctx->rga->mutex;
 	src_vq->dev = ctx->rga->v4l2_dev.dev;
@@ -110,12 +108,13 @@ queue_init(void *priv, struct vb2_queue *src_vq, struct vb2_queue *dst_vq)
 	if (ret)
 		return ret;
 
-	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
+	dst_vq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
 	dst_vq->io_modes = VB2_MMAP | VB2_DMABUF;
 	dst_vq->drv_priv = ctx;
 	dst_vq->ops = &rga_qops;
 	dst_vq->mem_ops = &vb2_dma_sg_memops;
-	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	dst_vq->gfp_flags = __GFP_DMA32;
+	dst_vq->buf_struct_size = sizeof(struct rga_vb_buffer);
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->lock = &ctx->rga->mutex;
 	dst_vq->dev = ctx->rga->v4l2_dev.dev;
@@ -282,6 +281,15 @@ static struct rga_fmt formats[] = {
 		.x_div = 1,
 	},
 	{
+		.fourcc = V4L2_PIX_FMT_NV12M,
+		.color_swap = RGA_COLOR_NONE_SWAP,
+		.hw_format = RGA_COLOR_FMT_YUV420SP,
+		.depth = 12,
+		.uv_factor = 4,
+		.y_div = 2,
+		.x_div = 1,
+	},
+	{
 		.fourcc = V4L2_PIX_FMT_NV16,
 		.color_swap = RGA_COLOR_NONE_SWAP,
 		.hw_format = RGA_COLOR_FMT_YUV422SP,
@@ -321,12 +329,12 @@ static struct rga_fmt formats[] = {
 
 #define NUM_FORMATS ARRAY_SIZE(formats)
 
-static struct rga_fmt *rga_fmt_find(struct v4l2_format *f)
+static struct rga_fmt *rga_fmt_find(u32 pixelformat)
 {
 	unsigned int i;
 
 	for (i = 0; i < NUM_FORMATS; i++) {
-		if (formats[i].fourcc == f->fmt.pix.pixelformat)
+		if (formats[i].fourcc == pixelformat)
 			return &formats[i];
 	}
 	return NULL;
@@ -345,14 +353,11 @@ static struct rga_frame def_frame = {
 
 struct rga_frame *rga_get_frame(struct rga_ctx *ctx, enum v4l2_buf_type type)
 {
-	switch (type) {
-	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+	if (V4L2_TYPE_IS_OUTPUT(type))
 		return &ctx->in;
-	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	if (V4L2_TYPE_IS_CAPTURE(type))
 		return &ctx->out;
-	default:
-		return ERR_PTR(-EINVAL);
-	}
+	return ERR_PTR(-EINVAL);
 }
 
 static int rga_open(struct file *file)
@@ -369,6 +374,11 @@ static int rga_open(struct file *file)
 	ctx->in = def_frame;
 	ctx->out = def_frame;
 
+	v4l2_fill_pixfmt_mp(&ctx->in.pix,
+			    ctx->in.fmt->fourcc, ctx->out.width, ctx->out.height);
+	v4l2_fill_pixfmt_mp(&ctx->out.pix,
+			    ctx->out.fmt->fourcc, ctx->out.width, ctx->out.height);
+
 	if (mutex_lock_interruptible(&rga->mutex)) {
 		kfree(ctx);
 		return -ERESTARTSYS;
@@ -449,6 +459,7 @@ static int vidioc_enum_fmt(struct file *file, void *prv, struct v4l2_fmtdesc *f)
 
 static int vidioc_g_fmt(struct file *file, void *prv, struct v4l2_format *f)
 {
+	struct v4l2_pix_format_mplane *pix_fmt = &f->fmt.pix_mp;
 	struct rga_ctx *ctx = prv;
 	struct vb2_queue *vq;
 	struct rga_frame *frm;
@@ -460,58 +471,43 @@ static int vidioc_g_fmt(struct file *file, void *prv, struct v4l2_format *f)
 	if (IS_ERR(frm))
 		return PTR_ERR(frm);
 
-	f->fmt.pix.width = frm->width;
-	f->fmt.pix.height = frm->height;
-	f->fmt.pix.field = V4L2_FIELD_NONE;
-	f->fmt.pix.pixelformat = frm->fmt->fourcc;
-	f->fmt.pix.bytesperline = frm->stride;
-	f->fmt.pix.sizeimage = frm->size;
-	f->fmt.pix.colorspace = frm->colorspace;
+	v4l2_fill_pixfmt_mp(pix_fmt, frm->fmt->fourcc, frm->width, frm->height);
+
+	pix_fmt->field = V4L2_FIELD_NONE;
+	pix_fmt->colorspace = frm->colorspace;
 
 	return 0;
 }
 
 static int vidioc_try_fmt(struct file *file, void *prv, struct v4l2_format *f)
 {
+	struct v4l2_pix_format_mplane *pix_fmt = &f->fmt.pix_mp;
 	struct rga_fmt *fmt;
 
-	fmt = rga_fmt_find(f);
-	if (!fmt) {
+	fmt = rga_fmt_find(pix_fmt->pixelformat);
+	if (!fmt)
 		fmt = &formats[0];
-		f->fmt.pix.pixelformat = fmt->fourcc;
-	}
 
-	f->fmt.pix.field = V4L2_FIELD_NONE;
+	pix_fmt->width = clamp(pix_fmt->width,
+			       (u32)MIN_WIDTH, (u32)MAX_WIDTH);
+	pix_fmt->height = clamp(pix_fmt->height,
+				(u32)MIN_HEIGHT, (u32)MAX_HEIGHT);
 
-	if (f->fmt.pix.width > MAX_WIDTH)
-		f->fmt.pix.width = MAX_WIDTH;
-	if (f->fmt.pix.height > MAX_HEIGHT)
-		f->fmt.pix.height = MAX_HEIGHT;
-
-	if (f->fmt.pix.width < MIN_WIDTH)
-		f->fmt.pix.width = MIN_WIDTH;
-	if (f->fmt.pix.height < MIN_HEIGHT)
-		f->fmt.pix.height = MIN_HEIGHT;
-
-	if (fmt->hw_format >= RGA_COLOR_FMT_YUV422SP)
-		f->fmt.pix.bytesperline = f->fmt.pix.width;
-	else
-		f->fmt.pix.bytesperline = (f->fmt.pix.width * fmt->depth) >> 3;
-
-	f->fmt.pix.sizeimage =
-		f->fmt.pix.height * (f->fmt.pix.width * fmt->depth) >> 3;
+	v4l2_fill_pixfmt_mp(pix_fmt, fmt->fourcc, pix_fmt->width, pix_fmt->height);
+	pix_fmt->field = V4L2_FIELD_NONE;
 
 	return 0;
 }
 
 static int vidioc_s_fmt(struct file *file, void *prv, struct v4l2_format *f)
 {
+	struct v4l2_pix_format_mplane *pix_fmt = &f->fmt.pix_mp;
 	struct rga_ctx *ctx = prv;
 	struct rockchip_rga *rga = ctx->rga;
 	struct vb2_queue *vq;
 	struct rga_frame *frm;
-	struct rga_fmt *fmt;
 	int ret = 0;
+	int i;
 
 	/* Adjust all values accordingly to the hardware capabilities
 	 * and chosen format.
@@ -527,15 +523,14 @@ static int vidioc_s_fmt(struct file *file, void *prv, struct v4l2_format *f)
 	frm = rga_get_frame(ctx, f->type);
 	if (IS_ERR(frm))
 		return PTR_ERR(frm);
-	fmt = rga_fmt_find(f);
-	if (!fmt)
-		return -EINVAL;
-	frm->width = f->fmt.pix.width;
-	frm->height = f->fmt.pix.height;
-	frm->size = f->fmt.pix.sizeimage;
-	frm->fmt = fmt;
-	frm->stride = f->fmt.pix.bytesperline;
-	frm->colorspace = f->fmt.pix.colorspace;
+	frm->width = pix_fmt->width;
+	frm->height = pix_fmt->height;
+	frm->size = 0;
+	for (i = 0; i < pix_fmt->num_planes; i++)
+		frm->size += pix_fmt->plane_fmt[i].sizeimage;
+	frm->fmt = rga_fmt_find(pix_fmt->pixelformat);
+	frm->stride = pix_fmt->plane_fmt[0].bytesperline;
+	frm->colorspace = pix_fmt->colorspace;
 
 	/* Reset crop settings */
 	frm->crop.left = 0;
@@ -543,6 +538,21 @@ static int vidioc_s_fmt(struct file *file, void *prv, struct v4l2_format *f)
 	frm->crop.width = frm->width;
 	frm->crop.height = frm->height;
 
+	frm->pix = *pix_fmt;
+
+	v4l2_dbg(debug, 1, &rga->v4l2_dev,
+		 "[%s] fmt - %p4cc %dx%d (stride %d, sizeimage %d)\n",
+		  V4L2_TYPE_IS_OUTPUT(f->type) ? "OUTPUT" : "CAPTURE",
+		  &frm->fmt->fourcc, frm->width, frm->height,
+		  frm->stride, frm->size);
+
+	for (i = 0; i < pix_fmt->num_planes; i++) {
+		v4l2_dbg(debug, 1, &rga->v4l2_dev,
+			 "plane[%d]: size %d, bytesperline %d\n",
+			 i, pix_fmt->plane_fmt[i].sizeimage,
+			 pix_fmt->plane_fmt[i].bytesperline);
+	}
+
 	return 0;
 }
 
@@ -560,21 +570,21 @@ static int vidioc_g_selection(struct file *file, void *prv,
 	switch (s->target) {
 	case V4L2_SEL_TGT_COMPOSE_DEFAULT:
 	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
-		if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		if (!V4L2_TYPE_IS_CAPTURE(s->type))
 			return -EINVAL;
 		break;
 	case V4L2_SEL_TGT_CROP_DEFAULT:
 	case V4L2_SEL_TGT_CROP_BOUNDS:
-		if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
+		if (!V4L2_TYPE_IS_OUTPUT(s->type))
 			return -EINVAL;
 		break;
 	case V4L2_SEL_TGT_COMPOSE:
-		if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		if (!V4L2_TYPE_IS_CAPTURE(s->type))
 			return -EINVAL;
 		use_frame = true;
 		break;
 	case V4L2_SEL_TGT_CROP:
-		if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
+		if (!V4L2_TYPE_IS_OUTPUT(s->type))
 			return -EINVAL;
 		use_frame = true;
 		break;
@@ -612,7 +622,7 @@ static int vidioc_s_selection(struct file *file, void *prv,
 		 * COMPOSE target is only valid for capture buffer type, return
 		 * error for output buffer type
 		 */
-		if (s->type != V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		if (!V4L2_TYPE_IS_CAPTURE(s->type))
 			return -EINVAL;
 		break;
 	case V4L2_SEL_TGT_CROP:
@@ -620,7 +630,7 @@ static int vidioc_s_selection(struct file *file, void *prv,
 		 * CROP target is only valid for output buffer type, return
 		 * error for capture buffer type
 		 */
-		if (s->type != V4L2_BUF_TYPE_VIDEO_OUTPUT)
+		if (!V4L2_TYPE_IS_OUTPUT(s->type))
 			return -EINVAL;
 		break;
 	/*
@@ -653,14 +663,14 @@ static const struct v4l2_ioctl_ops rga_ioctl_ops = {
 	.vidioc_querycap = vidioc_querycap,
 
 	.vidioc_enum_fmt_vid_cap = vidioc_enum_fmt,
-	.vidioc_g_fmt_vid_cap = vidioc_g_fmt,
-	.vidioc_try_fmt_vid_cap = vidioc_try_fmt,
-	.vidioc_s_fmt_vid_cap = vidioc_s_fmt,
+	.vidioc_g_fmt_vid_cap_mplane = vidioc_g_fmt,
+	.vidioc_try_fmt_vid_cap_mplane = vidioc_try_fmt,
+	.vidioc_s_fmt_vid_cap_mplane = vidioc_s_fmt,
 
 	.vidioc_enum_fmt_vid_out = vidioc_enum_fmt,
-	.vidioc_g_fmt_vid_out = vidioc_g_fmt,
-	.vidioc_try_fmt_vid_out = vidioc_try_fmt,
-	.vidioc_s_fmt_vid_out = vidioc_s_fmt,
+	.vidioc_g_fmt_vid_out_mplane = vidioc_g_fmt,
+	.vidioc_try_fmt_vid_out_mplane = vidioc_try_fmt,
+	.vidioc_s_fmt_vid_out_mplane = vidioc_s_fmt,
 
 	.vidioc_reqbufs = v4l2_m2m_ioctl_reqbufs,
 	.vidioc_querybuf = v4l2_m2m_ioctl_querybuf,
@@ -687,7 +697,7 @@ static const struct video_device rga_videodev = {
 	.minor = -1,
 	.release = video_device_release,
 	.vfl_dir = VFL_DIR_M2M,
-	.device_caps = V4L2_CAP_VIDEO_M2M | V4L2_CAP_STREAMING,
+	.device_caps = V4L2_CAP_VIDEO_M2M_MPLANE | V4L2_CAP_STREAMING,
 };
 
 static int rga_enable_clocks(struct rockchip_rga *rga)
@@ -827,6 +837,12 @@ static int rga_probe(struct platform_device *pdev)
 		goto err_put_clk;
 	}
 
+	ret = dma_set_mask_and_coherent(rga->dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(rga->dev, "32-bit DMA not supported");
+		goto err_put_clk;
+	}
+
 	ret = v4l2_device_register(&pdev->dev, &rga->v4l2_dev);
 	if (ret)
 		goto err_put_clk;
@@ -872,26 +888,13 @@ static int rga_probe(struct platform_device *pdev)
 		goto rel_m2m;
 	}
 
-	rga->src_mmu_pages =
-		(unsigned int *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 3);
-	if (!rga->src_mmu_pages) {
-		ret = -ENOMEM;
-		goto free_dma;
-	}
-	rga->dst_mmu_pages =
-		(unsigned int *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 3);
-	if (!rga->dst_mmu_pages) {
-		ret = -ENOMEM;
-		goto free_src_pages;
-	}
-
 	def_frame.stride = (def_frame.width * def_frame.fmt->depth) >> 3;
 	def_frame.size = def_frame.stride * def_frame.height;
 
 	ret = video_register_device(vfd, VFL_TYPE_VIDEO, -1);
 	if (ret) {
 		v4l2_err(&rga->v4l2_dev, "Failed to register video device\n");
-		goto free_dst_pages;
+		goto free_dma;
 	}
 
 	v4l2_info(&rga->v4l2_dev, "Registered %s as /dev/%s\n",
@@ -899,10 +902,6 @@ static int rga_probe(struct platform_device *pdev)
 
 	return 0;
 
-free_dst_pages:
-	free_pages((unsigned long)rga->dst_mmu_pages, 3);
-free_src_pages:
-	free_pages((unsigned long)rga->src_mmu_pages, 3);
 free_dma:
 	dma_free_attrs(rga->dev, RGA_CMDBUF_SIZE, rga->cmdbuf_virt,
 		       rga->cmdbuf_phy, DMA_ATTR_WRITE_COMBINE);
@@ -925,9 +924,6 @@ static void rga_remove(struct platform_device *pdev)
 	dma_free_attrs(rga->dev, RGA_CMDBUF_SIZE, rga->cmdbuf_virt,
 		       rga->cmdbuf_phy, DMA_ATTR_WRITE_COMBINE);
 
-	free_pages((unsigned long)rga->src_mmu_pages, 3);
-	free_pages((unsigned long)rga->dst_mmu_pages, 3);
-
 	v4l2_info(&rga->v4l2_dev, "Removing\n");
 
 	v4l2_m2m_release(rga->m2m_dev);
diff --git a/drivers/media/platform/rockchip/rga/rga.h b/drivers/media/platform/rockchip/rga/rga.h
index 5fa9d2f366..3502dff605 100644
--- a/drivers/media/platform/rockchip/rga/rga.h
+++ b/drivers/media/platform/rockchip/rga/rga.h
@@ -34,12 +34,17 @@ struct rga_frame {
 
 	/* Image format */
 	struct rga_fmt *fmt;
+	struct v4l2_pix_format_mplane pix;
 
 	/* Variables that can calculated once and reused */
 	u32 stride;
 	u32 size;
 };
 
+struct rga_dma_desc {
+	u32 addr;
+};
+
 struct rockchip_rga_version {
 	u32 major;
 	u32 minor;
@@ -81,15 +86,36 @@ struct rockchip_rga {
 	struct rga_ctx *curr;
 	dma_addr_t cmdbuf_phy;
 	void *cmdbuf_virt;
-	unsigned int *src_mmu_pages;
-	unsigned int *dst_mmu_pages;
 };
 
+struct rga_addr_offset {
+	unsigned int y_off;
+	unsigned int u_off;
+	unsigned int v_off;
+};
+
+struct rga_vb_buffer {
+	struct vb2_v4l2_buffer vb_buf;
+	struct list_head queue;
+
+	/* RGA MMU mapping for this buffer */
+	struct rga_dma_desc *dma_desc;
+	dma_addr_t dma_desc_pa;
+	size_t n_desc;
+
+	/* Plane offsets of this buffer into the mapping */
+	struct rga_addr_offset offset;
+};
+
+static inline struct rga_vb_buffer *vb_to_rga(struct vb2_v4l2_buffer *vb)
+{
+	return container_of(vb, struct rga_vb_buffer, vb_buf);
+}
+
 struct rga_frame *rga_get_frame(struct rga_ctx *ctx, enum v4l2_buf_type type);
 
 /* RGA Buffers Manage */
 extern const struct vb2_ops rga_qops;
-void rga_buf_map(struct vb2_buffer *vb);
 
 /* RGA Hardware */
 static inline void rga_write(struct rockchip_rga *rga, u32 reg, u32 value)
@@ -110,6 +136,7 @@ static inline void rga_mod(struct rockchip_rga *rga, u32 reg, u32 val, u32 mask)
 	rga_write(rga, reg, temp);
 };
 
-void rga_hw_start(struct rockchip_rga *rga);
+void rga_hw_start(struct rockchip_rga *rga,
+		  struct rga_vb_buffer *src, struct rga_vb_buffer *dst);
 
 #endif