Commit 24d5d2ba authored by Dmitry Osipenko's avatar Dmitry Osipenko Committed by Mauro Carvalho Chehab
Browse files

media: staging: tegra-vde: Support V4L stateless video decoder API



Expose Tegra video decoder as a generic V4L M2M stateless video decoder.

Signed-off-by: default avatarDmitry Osipenko <digetx@gmail.com>
Signed-off-by: default avatarHans Verkuil <hverkuil-cisco@xs4all.nl>
Signed-off-by: default avatarMauro Carvalho Chehab <mchehab@kernel.org>
parent 9aa94a31
Loading
Loading
Loading
Loading
+7 −0
Original line number Diff line number Diff line
@@ -2,9 +2,16 @@
config TEGRA_VDE
	tristate "NVIDIA Tegra Video Decoder Engine driver"
	depends on ARCH_TEGRA || COMPILE_TEST
	depends on VIDEO_DEV && VIDEO_V4L2
	select DMA_SHARED_BUFFER
	select IOMMU_IOVA
	select MEDIA_CONTROLLER
	select MEDIA_CONTROLLER_REQUEST_API
	select SRAM
	select VIDEOBUF2_DMA_CONTIG
	select VIDEOBUF2_DMA_SG
	select V4L2_H264
	select V4L2_MEM2MEM_DEV
	help
	    Say Y here to enable support for the NVIDIA Tegra video decoder
	    driver.
+1 −1
Original line number Diff line number Diff line
# SPDX-License-Identifier: GPL-2.0
tegra-vde-y := vde.o iommu.o dmabuf-cache.o h264.o
tegra-vde-y := vde.o iommu.o dmabuf-cache.o h264.o v4l2.o
obj-$(CONFIG_TEGRA_VDE)	+= tegra-vde.o
+302 −2
Original line number Diff line number Diff line
@@ -11,10 +11,18 @@
#include <linux/reset.h>
#include <linux/slab.h>

#include <media/v4l2-h264.h>

#include "trace.h"
#include "uapi.h"
#include "vde.h"

struct h264_reflists {
	u8 p[V4L2_H264_NUM_DPB_ENTRIES];
	u8 b0[V4L2_H264_NUM_DPB_ENTRIES];
	u8 b1[V4L2_H264_NUM_DPB_ENTRIES];
};

static int tegra_vde_wait_mbe(struct tegra_vde *vde)
{
	u32 tmp;
@@ -125,8 +133,8 @@ static void tegra_vde_setup_frameid(struct tegra_vde *vde,
	u32 y_addr  = frame ? frame->y_addr  : 0x6CDEAD00;
	u32 cb_addr = frame ? frame->cb_addr : 0x6CDEAD00;
	u32 cr_addr = frame ? frame->cr_addr : 0x6CDEAD00;
	u32 value1 = frame ? ((mbs_width << 16) | mbs_height) : 0;
	u32 value2 = frame ? ((((mbs_width + 1) >> 1) << 6) | 1) : 0;
	u32 value1 = frame ? ((frame->luma_atoms_pitch << 16) | mbs_height) : 0;
	u32 value2 = frame ? ((frame->chroma_atoms_pitch << 6) | 1) : 0;

	tegra_vde_writel(vde, y_addr  >> 8, vde->frameid, 0x000 + frameid * 4);
	tegra_vde_writel(vde, cb_addr >> 8, vde->frameid, 0x100 + frameid * 4);
@@ -645,3 +653,295 @@ int tegra_vde_decode_h264(struct tegra_vde *vde,

	return tegra_vde_decode_end(vde);
}

static struct vb2_buffer *get_ref_buf(struct tegra_ctx *ctx,
				      struct vb2_v4l2_buffer *dst,
				      unsigned int dpb_idx)
{
	const struct v4l2_h264_dpb_entry *dpb = ctx->h264.decode_params->dpb;
	struct vb2_queue *cap_q = &ctx->fh.m2m_ctx->cap_q_ctx.q;
	int buf_idx = -1;

	if (dpb[dpb_idx].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)
		buf_idx = vb2_find_timestamp(cap_q,
					     dpb[dpb_idx].reference_ts, 0);

	/*
	 * If a DPB entry is unused or invalid, address of current destination
	 * buffer is returned.
	 */
	if (buf_idx < 0)
		return &dst->vb2_buf;

	return vb2_get_buffer(cap_q, buf_idx);
}

static int tegra_vde_validate_vb_size(struct tegra_ctx *ctx,
				      struct vb2_buffer *vb,
				      unsigned int plane_id,
				      size_t min_size)
{
	u64 offset = vb->planes[plane_id].data_offset;
	struct device *dev = ctx->vde->dev;

	if (offset + min_size > vb2_plane_size(vb, plane_id)) {
		dev_err(dev, "Too small plane[%u] size %lu @0x%llX, should be at least %zu\n",
			plane_id, vb2_plane_size(vb, plane_id), offset, min_size);
		return -EINVAL;
	}

	return 0;
}

static int tegra_vde_h264_setup_frame(struct tegra_ctx *ctx,
				      struct tegra_vde_h264_decoder_ctx *h264,
				      struct v4l2_h264_reflist_builder *b,
				      struct vb2_buffer *vb,
				      unsigned int ref_id,
				      unsigned int id)
{
	struct v4l2_pix_format_mplane *pixfmt = &ctx->decoded_fmt.fmt.pix_mp;
	struct tegra_m2m_buffer *tb = vb_to_tegra_buf(vb);
	struct tegra_ctx_h264 *h = &ctx->h264;
	struct tegra_vde *vde = ctx->vde;
	struct device *dev = vde->dev;
	unsigned int cstride, lstride;
	unsigned int flags = 0;
	size_t lsize, csize;
	int err, frame_num;

	lsize = h264->pic_width_in_mbs * 16 * h264->pic_height_in_mbs * 16;
	csize = h264->pic_width_in_mbs *  8 * h264->pic_height_in_mbs *  8;
	lstride = pixfmt->plane_fmt[0].bytesperline;
	cstride = pixfmt->plane_fmt[1].bytesperline;

	err = tegra_vde_validate_vb_size(ctx, vb, 0, lsize);
	if (err)
		return err;

	err = tegra_vde_validate_vb_size(ctx, vb, 1, csize);
	if (err)
		return err;

	err = tegra_vde_validate_vb_size(ctx, vb, 2, csize);
	if (err)
		return err;

	if (!tb->aux || tb->aux->size < csize) {
		dev_err(dev, "Too small aux size %zd, should be at least %zu\n",
			tb->aux ? tb->aux->size : -1, csize);
		return -EINVAL;
	}

	if (id == 0) {
		frame_num = h->decode_params->frame_num;

		if (h->decode_params->nal_ref_idc)
			flags |= FLAG_REFERENCE;
	} else {
		frame_num = b->refs[ref_id].frame_num;
	}

	if (tb->b_frame)
		flags |= FLAG_B_FRAME;

	vde->frames[id].flags = flags;
	vde->frames[id].y_addr = tb->dma_addr[0];
	vde->frames[id].cb_addr = tb->dma_addr[1];
	vde->frames[id].cr_addr = tb->dma_addr[2];
	vde->frames[id].aux_addr = tb->aux->dma_addr;
	vde->frames[id].frame_num = frame_num & 0x7fffff;
	vde->frames[id].luma_atoms_pitch = lstride / VDE_ATOM;
	vde->frames[id].chroma_atoms_pitch = cstride / VDE_ATOM;

	return 0;
}

static int tegra_vde_h264_setup_frames(struct tegra_ctx *ctx,
				       struct tegra_vde_h264_decoder_ctx *h264)
{
	struct vb2_v4l2_buffer *src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
	struct vb2_v4l2_buffer *dst = v4l2_m2m_next_dst_buf(ctx->fh.m2m_ctx);
	const struct v4l2_h264_dpb_entry *dpb = ctx->h264.decode_params->dpb;
	struct tegra_m2m_buffer *tb = vb_to_tegra_buf(&dst->vb2_buf);
	struct tegra_ctx_h264 *h = &ctx->h264;
	struct v4l2_h264_reflist_builder b;
	struct h264_reflists reflists;
	struct vb2_buffer *ref;
	unsigned int i;
	u8 *dpb_id;
	int err;

	/*
	 * Tegra hardware requires information about frame's type, assuming
	 * that frame consists of the same type slices. Userspace must tag
	 * frame's type appropriately.
	 *
	 * Decoding of a non-uniform frames isn't supported by hardware and
	 * require software preprocessing that we don't implement. Decoding
	 * is expected to fail in this case. Such video streams are rare in
	 * practice, so not a big deal.
	 *
	 * If userspace doesn't tell us frame's type, then we will try decode
	 * as-is.
	 */
	v4l2_m2m_buf_copy_metadata(src, dst, true);

	if (h->decode_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BFRAME)
		tb->b_frame = true;
	else
		tb->b_frame = false;

	err = tegra_vde_h264_setup_frame(ctx, h264, NULL, &dst->vb2_buf, 0,
					 h264->dpb_frames_nb++);
	if (err)
		return err;

	if (!(h->decode_params->flags & (V4L2_H264_DECODE_PARAM_FLAG_PFRAME |
					 V4L2_H264_DECODE_PARAM_FLAG_BFRAME)))
		return 0;

	v4l2_h264_init_reflist_builder(&b, h->decode_params, h->sps, dpb);

	if (h->decode_params->flags & V4L2_H264_DECODE_PARAM_FLAG_BFRAME) {
		v4l2_h264_build_b_ref_lists(&b, reflists.b0, reflists.b1);
		dpb_id = reflists.b0;
	} else {
		v4l2_h264_build_p_ref_list(&b, reflists.p);
		dpb_id = reflists.p;
	}

	for (i = 0; i < b.num_valid; i++) {
		ref = get_ref_buf(ctx, dst, dpb_id[i]);

		err = tegra_vde_h264_setup_frame(ctx, h264, &b, ref, dpb_id[i],
						 h264->dpb_frames_nb++);
		if (err)
			return err;

		if (b.refs[dpb_id[i]].pic_order_count < b.cur_pic_order_count)
			h264->dpb_ref_frames_with_earlier_poc_nb++;
	}

	return 0;
}

static unsigned int to_tegra_vde_h264_level_idc(unsigned int level_idc)
{
	switch (level_idc) {
	case 11:
		return 2;
	case 12:
		return 3;
	case 13:
		return 4;
	case 20:
		return 5;
	case 21:
		return 6;
	case 22:
		return 7;
	case 30:
		return 8;
	case 31:
		return 9;
	case 32:
		return 10;
	case 40:
		return 11;
	case 41:
		return 12;
	case 42:
		return 13;
	case 50:
		return 14;
	default:
		break;
	}

	return 15;
}

static int tegra_vde_h264_setup_context(struct tegra_ctx *ctx,
					struct tegra_vde_h264_decoder_ctx *h264)
{
	struct tegra_ctx_h264 *h = &ctx->h264;
	struct tegra_vde *vde = ctx->vde;
	struct device *dev = vde->dev;
	int err;

	memset(h264, 0, sizeof(*h264));
	memset(vde->frames, 0, sizeof(vde->frames));

	tegra_vde_prepare_control_data(ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS);
	tegra_vde_prepare_control_data(ctx, V4L2_CID_STATELESS_H264_SPS);
	tegra_vde_prepare_control_data(ctx, V4L2_CID_STATELESS_H264_PPS);

	/* CABAC unsupported by hardware, requires software preprocessing */
	if (h->pps->flags & V4L2_H264_PPS_FLAG_ENTROPY_CODING_MODE)
		return -EOPNOTSUPP;

	if (h->sps->profile_idc == 66)
		h264->baseline_profile = 1;

	if (h->sps->flags & V4L2_H264_SPS_FLAG_DIRECT_8X8_INFERENCE)
		h264->direct_8x8_inference_flag = 1;

	if (h->pps->flags & V4L2_H264_PPS_FLAG_CONSTRAINED_INTRA_PRED)
		h264->constrained_intra_pred_flag = 1;

	if (h->pps->flags & V4L2_H264_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT)
		h264->deblocking_filter_control_present_flag = 1;

	if (h->pps->flags & V4L2_H264_PPS_FLAG_BOTTOM_FIELD_PIC_ORDER_IN_FRAME_PRESENT)
		h264->pic_order_present_flag = 1;

	h264->level_idc				= to_tegra_vde_h264_level_idc(h->sps->level_idc);
	h264->log2_max_pic_order_cnt_lsb	= h->sps->log2_max_pic_order_cnt_lsb_minus4 + 4;
	h264->log2_max_frame_num		= h->sps->log2_max_frame_num_minus4 + 4;
	h264->pic_order_cnt_type		= h->sps->pic_order_cnt_type;
	h264->pic_width_in_mbs			= h->sps->pic_width_in_mbs_minus1 + 1;
	h264->pic_height_in_mbs			= h->sps->pic_height_in_map_units_minus1 + 1;

	h264->num_ref_idx_l0_active_minus1	= h->pps->num_ref_idx_l0_default_active_minus1;
	h264->num_ref_idx_l1_active_minus1	= h->pps->num_ref_idx_l1_default_active_minus1;
	h264->chroma_qp_index_offset		= h->pps->chroma_qp_index_offset & 0x1f;
	h264->pic_init_qp			= h->pps->pic_init_qp_minus26 + 26;

	err = tegra_vde_h264_setup_frames(ctx, h264);
	if (err)
		return err;

	err = tegra_vde_validate_h264_ctx(dev, h264);
	if (err)
		return err;

	return 0;
}

int tegra_vde_h264_decode_run(struct tegra_ctx *ctx)
{
	struct vb2_v4l2_buffer *src = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
	struct tegra_m2m_buffer *bitstream = vb_to_tegra_buf(&src->vb2_buf);
	size_t bitstream_size = vb2_get_plane_payload(&src->vb2_buf, 0);
	struct tegra_vde_h264_decoder_ctx h264;
	struct tegra_vde *vde = ctx->vde;
	int err;

	err = tegra_vde_h264_setup_context(ctx, &h264);
	if (err)
		return err;

	err = tegra_vde_decode_begin(vde, &h264, vde->frames,
				     bitstream->dma_addr[0],
				     bitstream_size);
	if (err)
		return err;

	return 0;
}

int tegra_vde_h264_decode_wait(struct tegra_ctx *ctx)
{
	return tegra_vde_decode_end(ctx->vde);
}
+1018 −0

File added.

Preview size limit exceeded, changes collapsed.

+69 −5
Original line number Diff line number Diff line
@@ -53,7 +53,7 @@ void tegra_vde_set_bits(struct tegra_vde *vde, u32 mask,
	tegra_vde_writel(vde, value | mask, base, offset);
}

static int tegra_vde_alloc_bo(struct tegra_vde *vde,
int tegra_vde_alloc_bo(struct tegra_vde *vde,
		       struct tegra_vde_bo **ret_bo,
		       enum dma_data_direction dma_dir,
		       size_t size)
@@ -126,7 +126,7 @@ static int tegra_vde_alloc_bo(struct tegra_vde *vde,
	return err;
}

static void tegra_vde_free_bo(struct tegra_vde_bo *bo)
void tegra_vde_free_bo(struct tegra_vde_bo *bo)
{
	struct tegra_vde *vde = bo->vde;
	struct device *dev = vde->miscdev.parent;
@@ -332,6 +332,8 @@ static int tegra_vde_ioctl_decode_h264(struct tegra_vde *vde,

		dpb_frames[i].flags = frames[i].flags;
		dpb_frames[i].frame_num = frames[i].frame_num;
		dpb_frames[i].luma_atoms_pitch = ctx.pic_width_in_mbs;
		dpb_frames[i].chroma_atoms_pitch = cstride / VDE_ATOM;

		dma_dir = (i == 0) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;

@@ -626,8 +628,16 @@ static int tegra_vde_probe(struct platform_device *pdev)
		goto err_free_secure_bo;
	}

	err = tegra_vde_v4l2_init(vde);
	if (err) {
		dev_err(dev, "Failed to initialize V4L2: %d\n", err);
		goto misc_unreg;
	}

	return 0;

misc_unreg:
	misc_deregister(&vde->miscdev);
err_free_secure_bo:
	tegra_vde_free_bo(vde->secure_bo);
err_pm_runtime:
@@ -648,6 +658,7 @@ static int tegra_vde_remove(struct platform_device *pdev)
	struct tegra_vde *vde = platform_get_drvdata(pdev);
	struct device *dev = &pdev->dev;

	tegra_vde_v4l2_deinit(vde);
	misc_deregister(&vde->miscdev);

	tegra_vde_free_bo(vde->secure_bo);
@@ -722,20 +733,73 @@ static const struct dev_pm_ops tegra_vde_pm_ops = {
				tegra_vde_pm_resume)
};

static const u32 tegra124_decoded_fmts[] = {
	/* TBD: T124 supports only a non-standard Tegra tiled format */
};

static const struct tegra_coded_fmt_desc tegra124_coded_fmts[] = {
	{
		.fourcc = V4L2_PIX_FMT_H264_SLICE,
		.frmsize = {
			.min_width = 16,
			.max_width = 1920,
			.step_width = 16,
			.min_height = 16,
			.max_height = 2032,
			.step_height = 16,
		},
		.num_decoded_fmts = ARRAY_SIZE(tegra124_decoded_fmts),
		.decoded_fmts = tegra124_decoded_fmts,
		.decode_run = tegra_vde_h264_decode_run,
		.decode_wait = tegra_vde_h264_decode_wait,
	},
};

static const u32 tegra20_decoded_fmts[] = {
	V4L2_PIX_FMT_YUV420M,
	V4L2_PIX_FMT_YVU420M,
};

static const struct tegra_coded_fmt_desc tegra20_coded_fmts[] = {
	{
		.fourcc = V4L2_PIX_FMT_H264_SLICE,
		.frmsize = {
			.min_width = 16,
			.max_width = 1920,
			.step_width = 16,
			.min_height = 16,
			.max_height = 2032,
			.step_height = 16,
		},
		.num_decoded_fmts = ARRAY_SIZE(tegra20_decoded_fmts),
		.decoded_fmts = tegra20_decoded_fmts,
		.decode_run = tegra_vde_h264_decode_run,
		.decode_wait = tegra_vde_h264_decode_wait,
	},
};

static const struct tegra_vde_soc tegra124_vde_soc = {
	.supports_ref_pic_marking = true,
	.coded_fmts = tegra124_coded_fmts,
	.num_coded_fmts = ARRAY_SIZE(tegra124_coded_fmts),
};

static const struct tegra_vde_soc tegra114_vde_soc = {
	.supports_ref_pic_marking = true,
	.coded_fmts = tegra20_coded_fmts,
	.num_coded_fmts = ARRAY_SIZE(tegra20_coded_fmts),
};

static const struct tegra_vde_soc tegra30_vde_soc = {
	.supports_ref_pic_marking = false,
	.coded_fmts = tegra20_coded_fmts,
	.num_coded_fmts = ARRAY_SIZE(tegra20_coded_fmts),
};

static const struct tegra_vde_soc tegra20_vde_soc = {
	.supports_ref_pic_marking = false,
	.coded_fmts = tegra20_coded_fmts,
	.num_coded_fmts = ARRAY_SIZE(tegra20_coded_fmts),
};

static const struct of_device_id tegra_vde_of_match[] = {
Loading