media: cedrus: h264: Support multiple slices per frame

With recent changes, support for decoding multi-slice frames can be
easily added now.

Signal VPU if current slice is first in frame or not and add information
about first macroblock coordinates.

When frame contains multiple slices and driver works in slice mode, it's
more efficient to hold capture buffer in queue until all slices of a
same frame are decoded.

Add support for that to Cedrus driver by exposing and implementing
V4L2_BUF_CAP_SUPPORTS_M2M_HOLD_CAPTURE_BUF capability.
Signed-off-by: NJernej Skrabec <jernej.skrabec@siol.net>
[hverkuil-cisco@xs4all.nl: rewritten to use v4l2_m2m_buf_done_and_job_finish]
[hverkuil-cisco@xs4all.nl: removed unnecessary (u32) cast]
[hverkuil-cisco@xs4all.nl: use new_frame v4l2_m2m_ctx bool]
Signed-off-by: NHans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: NMauro Carvalho Chehab <mchehab+samsung@kernel.org>

drivers/staging/media/sunxi/cedrus/cedrus_h264.c

@@ -301,6 +301,8 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 	dma_addr_t src_buf_addr;
 	u32 offset = slice->header_bit_size;
 	u32 len = (slice->size * 8) - offset;
+	unsigned int pic_width_in_mbs;
+	bool mbaff_pic;
 	u32 reg;
 
 	cedrus_write(dev, VE_H264_VLD_LEN, len);
@@ -370,12 +372,20 @@ static void cedrus_set_params(struct cedrus_ctx *ctx,
 		reg |= VE_H264_SPS_DIRECT_8X8_INFERENCE;
 	cedrus_write(dev, VE_H264_SPS, reg);
 
+	mbaff_pic = !(slice->flags & V4L2_H264_SLICE_FLAG_FIELD_PIC) &&
+		    (sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD);
+	pic_width_in_mbs = sps->pic_width_in_mbs_minus1 + 1;
+
 	// slice parameters
 	reg = 0;
+	reg |= ((slice->first_mb_in_slice % pic_width_in_mbs) & 0xff) << 24;
+	reg |= (((slice->first_mb_in_slice / pic_width_in_mbs) *
+		 (mbaff_pic + 1)) & 0xff) << 16;
 	reg |= decode->nal_ref_idc ? BIT(12) : 0;
 	reg |= (slice->slice_type & 0xf) << 8;
 	reg |= slice->cabac_init_idc & 0x3;
-	reg |= VE_H264_SHS_FIRST_SLICE_IN_PIC;
+	if (ctx->fh.m2m_ctx->new_frame)
+		reg |= VE_H264_SHS_FIRST_SLICE_IN_PIC;
 	if (slice->flags & V4L2_H264_SLICE_FLAG_FIELD_PIC)
 		reg |= VE_H264_SHS_FIELD_PIC;
 	if (slice->flags & V4L2_H264_SLICE_FLAG_BOTTOM_FIELD)

drivers/staging/media/sunxi/cedrus/cedrus_hw.c

@@ -103,7 +103,6 @@ static irqreturn_t cedrus_irq(int irq, void *data)
 {
 	struct cedrus_dev *dev = data;
 	struct cedrus_ctx *ctx;
-	struct vb2_v4l2_buffer *src_buf, *dst_buf;
 	enum vb2_buffer_state state;
 	enum cedrus_irq_status status;
 
@@ -121,24 +120,13 @@ static irqreturn_t cedrus_irq(int irq, void *data)
 	dev->dec_ops[ctx->current_codec]->irq_disable(ctx);
 	dev->dec_ops[ctx->current_codec]->irq_clear(ctx);
 
-	src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
-	dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
-
-	if (!src_buf || !dst_buf) {
-		v4l2_err(&dev->v4l2_dev,
-			 "Missing source and/or destination buffers\n");
-		return IRQ_HANDLED;
-	}
-
 	if (status == CEDRUS_IRQ_ERROR)
 		state = VB2_BUF_STATE_ERROR;
 	else
 		state = VB2_BUF_STATE_DONE;
 
-	v4l2_m2m_buf_done(src_buf, state);
-	v4l2_m2m_buf_done(dst_buf, state);
-
-	v4l2_m2m_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx);
+	v4l2_m2m_buf_done_and_job_finish(ctx->dev->m2m_dev, ctx->fh.m2m_ctx,
+					 state);
 
 	return IRQ_HANDLED;
 }

drivers/staging/media/sunxi/cedrus/cedrus_video.c

@@ -303,6 +303,17 @@ static int cedrus_s_fmt_vid_out(struct file *file, void *priv,
 
 	ctx->src_fmt = f->fmt.pix;
 
+	switch (ctx->src_fmt.pixelformat) {
+	case V4L2_PIX_FMT_H264_SLICE:
+		vq->subsystem_flags |=
+			VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF;
+		break;
+	default:
+		vq->subsystem_flags &=
+			~VB2_V4L2_FL_SUPPORTS_M2M_HOLD_CAPTURE_BUF;
+		break;
+	}
+
 	/* Propagate colorspace information to capture. */
 	ctx->dst_fmt.colorspace = f->fmt.pix.colorspace;
 	ctx->dst_fmt.xfer_func = f->fmt.pix.xfer_func;
@@ -336,6 +347,9 @@ const struct v4l2_ioctl_ops cedrus_ioctl_ops = {
 	.vidioc_streamon		= v4l2_m2m_ioctl_streamon,
 	.vidioc_streamoff		= v4l2_m2m_ioctl_streamoff,
 
+	.vidioc_try_decoder_cmd		= v4l2_m2m_ioctl_stateless_try_decoder_cmd,
+	.vidioc_decoder_cmd		= v4l2_m2m_ioctl_stateless_decoder_cmd,
+
 	.vidioc_subscribe_event		= v4l2_ctrl_subscribe_event,
 	.vidioc_unsubscribe_event	= v4l2_event_unsubscribe,
 };