[PATCH 10/10] staging: media: cedrus: vp8: support frames wider than 2048 pixels

[Jernej Skrabec]

Above 2048 pixels, the deblocking and intra prediction row buffers don't
fit into the internal SRAM anymore. Put them into DRAM like H.264 does.
The vendor library sizes the deblocking buffer as 24 bytes per column.

Tested on H616 with 2560x1440 and 3840x2160 libvpx streams, which are
bit-exact with the FFmpeg software decoder.

Signed-off-by: Jernej Skrabec <jernej.skrabec at gmail.com>
---
 drivers/staging/media/sunxi/cedrus/cedrus.h   |  7 ++
 .../staging/media/sunxi/cedrus/cedrus_vp8.c   | 64 +++++++++++++++++++
 2 files changed, 71 insertions(+)

diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.h b/drivers/staging/media/sunxi/cedrus/cedrus.h
index d28fe91562d1..ca4efa9302fc 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus.h
+++ b/drivers/staging/media/sunxi/cedrus/cedrus.h
@@ -156,6 +156,13 @@ struct cedrus_ctx {
 
 			u8		*entropy_probs_buf;
 			dma_addr_t	entropy_probs_buf_dma;
+
+			void		*deblk_buf;
+			dma_addr_t	deblk_buf_dma;
+			ssize_t		deblk_buf_size;
+			void		*intra_pred_buf;
+			dma_addr_t	intra_pred_buf_dma;
+			ssize_t		intra_pred_buf_size;
 		} vp8;
 	} codec;
 };
diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_vp8.c b/drivers/staging/media/sunxi/cedrus/cedrus_vp8.c
index 6b00efa77c22..954c0ceb98ed 100644
--- a/drivers/staging/media/sunxi/cedrus/cedrus_vp8.c
+++ b/drivers/staging/media/sunxi/cedrus/cedrus_vp8.c
@@ -666,6 +666,20 @@ static int cedrus_vp8_setup(struct cedrus_ctx *ctx, struct cedrus_run *run)
 
 	cedrus_write(dev, VE_H264_CTRL, VE_H264_CTRL_VP8);
 
+	if (ctx->codec.vp8.deblk_buf_size) {
+		cedrus_write(dev, VE_BUF_CTRL,
+			     VE_BUF_CTRL_INTRAPRED_MIXED_RAM |
+			     VE_BUF_CTRL_DBLK_MIXED_RAM);
+		cedrus_write(dev, VE_DBLK_DRAM_BUF_ADDR,
+			     ctx->codec.vp8.deblk_buf_dma);
+		cedrus_write(dev, VE_INTRAPRED_DRAM_BUF_ADDR,
+			     ctx->codec.vp8.intra_pred_buf_dma);
+	} else {
+		cedrus_write(dev, VE_BUF_CTRL,
+			     VE_BUF_CTRL_INTRAPRED_INT_SRAM |
+			     VE_BUF_CTRL_DBLK_INT_SRAM);
+	}
+
 	cedrus_vp8_update_probs(slice, ctx->codec.vp8.entropy_probs_buf);
 
 	reg = slice->first_part_size * 8;
@@ -849,7 +863,44 @@ static int cedrus_vp8_start(struct cedrus_ctx *ctx)
 	memcpy(&ctx->codec.vp8.entropy_probs_buf[2048],
 	       prob_table_init, sizeof(prob_table_init));
 
+	/*
+	 * Above 2048 pixels the deblocking and intra prediction row buffers
+	 * no longer fit into the internal SRAM. The vendor library sizes the
+	 * deblocking buffer as 24 bytes per (32 aligned) column.
+	 */
+	if (ctx->src_fmt.width > 2048) {
+		ctx->codec.vp8.deblk_buf_size =
+			ALIGN(ctx->src_fmt.width, 32) * 24;
+		ctx->codec.vp8.deblk_buf =
+			dma_alloc_attrs(dev->dev, ctx->codec.vp8.deblk_buf_size,
+					&ctx->codec.vp8.deblk_buf_dma,
+					GFP_KERNEL, DMA_ATTR_NO_KERNEL_MAPPING);
+		if (!ctx->codec.vp8.deblk_buf)
+			goto err_probs;
+
+		ctx->codec.vp8.intra_pred_buf_size =
+			ALIGN(ctx->src_fmt.width, 64) * 5 * 2;
+		ctx->codec.vp8.intra_pred_buf =
+			dma_alloc_attrs(dev->dev,
+					ctx->codec.vp8.intra_pred_buf_size,
+					&ctx->codec.vp8.intra_pred_buf_dma,
+					GFP_KERNEL, DMA_ATTR_NO_KERNEL_MAPPING);
+		if (!ctx->codec.vp8.intra_pred_buf)
+			goto err_deblk;
+	}
+
 	return 0;
+
+err_deblk:
+	dma_free_attrs(dev->dev, ctx->codec.vp8.deblk_buf_size,
+		       ctx->codec.vp8.deblk_buf, ctx->codec.vp8.deblk_buf_dma,
+		       DMA_ATTR_NO_KERNEL_MAPPING);
+	ctx->codec.vp8.deblk_buf_size = 0;
+err_probs:
+	dma_free_coherent(dev->dev, CEDRUS_ENTROPY_PROBS_SIZE,
+			  ctx->codec.vp8.entropy_probs_buf,
+			  ctx->codec.vp8.entropy_probs_buf_dma);
+	return -ENOMEM;
 }
 
 static void cedrus_vp8_stop(struct cedrus_ctx *ctx)
@@ -861,6 +912,19 @@ static void cedrus_vp8_stop(struct cedrus_ctx *ctx)
 	dma_free_coherent(dev->dev, CEDRUS_ENTROPY_PROBS_SIZE,
 			  ctx->codec.vp8.entropy_probs_buf,
 			  ctx->codec.vp8.entropy_probs_buf_dma);
+
+	if (ctx->codec.vp8.deblk_buf_size) {
+		dma_free_attrs(dev->dev, ctx->codec.vp8.deblk_buf_size,
+			       ctx->codec.vp8.deblk_buf,
+			       ctx->codec.vp8.deblk_buf_dma,
+			       DMA_ATTR_NO_KERNEL_MAPPING);
+		dma_free_attrs(dev->dev, ctx->codec.vp8.intra_pred_buf_size,
+			       ctx->codec.vp8.intra_pred_buf,
+			       ctx->codec.vp8.intra_pred_buf_dma,
+			       DMA_ATTR_NO_KERNEL_MAPPING);
+		ctx->codec.vp8.deblk_buf_size = 0;
+		ctx->codec.vp8.intra_pred_buf_size = 0;
+	}
 }
 
 static void cedrus_vp8_trigger(struct cedrus_ctx *ctx)
-- 
2.43.0