/* SPDX-License-Identifier: BSD-2-Clause */
/*
 * test_m2m_decode — minimal V4L2 m2m stateless decoder client.
 *
 * Drives /dev/videoNN through one full QBUF/DQBUF round-trip:
 *   1. open the m2m device
 *   2. S_FMT on OUTPUT (VP9_FRAME) and CAPTURE (NV12M)
 *   3. REQBUFS 1 on both queues
 *   4. mmap the OUTPUT buffer, copy bitstream into it, QBUF
 *   5. QBUF the CAPTURE buffer
 *   6. STREAMON both queues
 *   7. poll for completion
 *   8. DQBUF capture
 *   9. mmap+dump the CAPTURE buffer to a file
 *
 * Phase 8.5 verification harness — confirms the kernel's m2m
 * wiring works end-to-end against a real bitstream.
 *
 * Usage:
 *   test_m2m_decode <keyframe.bin> <out.nv12> [w] [h] [codec]
 *     defaults: w=128 h=96 codec=vp9
 *     codec: vp9 | av1 | h264
 */
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <fcntl.h>
#include <unistd.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <poll.h>
#include <linux/videodev2.h>

#define V4L2_DEV		"/dev/video0"
#define POLL_TIMEOUT_MS		5000

static void die(const char *msg)
{
	perror(msg);
	exit(1);
}

static void *read_file(const char *path, size_t *out_len)
{
	struct stat st;
	void *buf;
	int fd;
	ssize_t n;

	fd = open(path, O_RDONLY);
	if (fd < 0)
		die("open bitstream");
	if (fstat(fd, &st) < 0)
		die("fstat");
	buf = malloc(st.st_size);
	if (!buf)
		die("malloc bitstream");
	n = read(fd, buf, st.st_size);
	if (n != st.st_size)
		die("read bitstream short");
	close(fd);
	*out_len = (size_t) st.st_size;
	return buf;
}

int main(int argc, char **argv)
{
	const char *bitstream_path, *out_path;
	const char *codec_name = "vp9";
	uint32_t output_fourcc = V4L2_PIX_FMT_VP9_FRAME;
	void *bitstream;
	size_t bs_len;
	uint32_t w = 128, h = 96;

	struct v4l2_format fmt;
	struct v4l2_requestbuffers reqbuf;
	struct v4l2_buffer buf;
	struct v4l2_plane planes[2];
	struct v4l2_exportbuffer expbuf;

	int fd, rc, i;
	void *out_map;
	void *cap_y, *cap_uv;
	size_t cap_y_size, cap_uv_size;
	uint32_t out_buf_offset;
	enum v4l2_buf_type t;

	if (argc < 3) {
		fprintf(stderr,
			"usage: %s <keyframe.bin> <out.nv12> [w] [h] [codec]\n"
			"  codec: vp9 | av1 | h264 (default vp9)\n",
			argv[0]);
		return 2;
	}
	bitstream_path = argv[1];
	out_path = argv[2];
	if (argc >= 5) {
		w = (uint32_t) atoi(argv[3]);
		h = (uint32_t) atoi(argv[4]);
	}
	if (argc >= 6) {
		codec_name = argv[5];
		if (!strcmp(codec_name, "vp9"))
			output_fourcc = V4L2_PIX_FMT_VP9_FRAME;
		else if (!strcmp(codec_name, "av1"))
			output_fourcc = V4L2_PIX_FMT_AV1_FRAME;
		else if (!strcmp(codec_name, "h264"))
			output_fourcc = V4L2_PIX_FMT_H264_SLICE;
		else {
			fprintf(stderr, "unknown codec '%s'\n", codec_name);
			return 2;
		}
	}
	printf("codec=%s fourcc='%c%c%c%c'\n", codec_name,
	       output_fourcc & 0xff, (output_fourcc >> 8) & 0xff,
	       (output_fourcc >> 16) & 0xff, (output_fourcc >> 24) & 0xff);

	bitstream = read_file(bitstream_path, &bs_len);
	printf("loaded bitstream: %zu bytes\n", bs_len);

	fd = open(V4L2_DEV, O_RDWR);
	if (fd < 0)
		die("open " V4L2_DEV);

	/* --- S_FMT OUTPUT (compressed) --- */
	memset(&fmt, 0, sizeof(fmt));
	fmt.type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
	fmt.fmt.pix_mp.width	   = w;
	fmt.fmt.pix_mp.height	   = h;
	fmt.fmt.pix_mp.pixelformat = output_fourcc;
	if (ioctl(fd, VIDIOC_S_FMT, &fmt) < 0)
		die("S_FMT OUTPUT");
	printf("OUTPUT sizeimage = %u\n", fmt.fmt.pix_mp.plane_fmt[0].sizeimage);

	/* --- S_FMT CAPTURE (NV12M) --- */
	memset(&fmt, 0, sizeof(fmt));
	fmt.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
	fmt.fmt.pix_mp.width	   = w;
	fmt.fmt.pix_mp.height	   = h;
	fmt.fmt.pix_mp.pixelformat = V4L2_PIX_FMT_NV12M;
	if (ioctl(fd, VIDIOC_S_FMT, &fmt) < 0)
		die("S_FMT CAPTURE");
	printf("CAPTURE planes = %u, [0].sizeimage=%u [1].sizeimage=%u\n",
	       fmt.fmt.pix_mp.num_planes,
	       fmt.fmt.pix_mp.plane_fmt[0].sizeimage,
	       fmt.fmt.pix_mp.plane_fmt[1].sizeimage);
	cap_y_size  = fmt.fmt.pix_mp.plane_fmt[0].sizeimage;
	cap_uv_size = fmt.fmt.pix_mp.plane_fmt[1].sizeimage;

	/* --- REQBUFS OUTPUT --- */
	memset(&reqbuf, 0, sizeof(reqbuf));
	reqbuf.type	= V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
	reqbuf.memory	= V4L2_MEMORY_MMAP;
	reqbuf.count	= 1;
	if (ioctl(fd, VIDIOC_REQBUFS, &reqbuf) < 0)
		die("REQBUFS OUTPUT");
	printf("OUTPUT REQBUFS -> %u\n", reqbuf.count);

	/* --- REQBUFS CAPTURE --- */
	memset(&reqbuf, 0, sizeof(reqbuf));
	reqbuf.type	= V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
	reqbuf.memory	= V4L2_MEMORY_MMAP;
	reqbuf.count	= 1;
	if (ioctl(fd, VIDIOC_REQBUFS, &reqbuf) < 0)
		die("REQBUFS CAPTURE");
	printf("CAPTURE REQBUFS -> %u\n", reqbuf.count);

	/* --- QUERYBUF OUTPUT[0] + mmap + fill --- */
	memset(&buf, 0, sizeof(buf));
	memset(planes, 0, sizeof(planes));
	buf.type	= V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
	buf.memory	= V4L2_MEMORY_MMAP;
	buf.index	= 0;
	buf.m.planes	= planes;
	buf.length	= 1;
	if (ioctl(fd, VIDIOC_QUERYBUF, &buf) < 0)
		die("QUERYBUF OUTPUT");
	out_buf_offset = planes[0].m.mem_offset;
	out_map = mmap(NULL, planes[0].length, PROT_READ | PROT_WRITE,
		       MAP_SHARED, fd, out_buf_offset);
	if (out_map == MAP_FAILED)
		die("mmap OUTPUT");
	if (bs_len > planes[0].length) {
		fprintf(stderr, "bitstream too big: %zu > %u\n",
			bs_len, planes[0].length);
		return 1;
	}
	memcpy(out_map, bitstream, bs_len);
	planes[0].bytesused = (uint32_t) bs_len;

	if (ioctl(fd, VIDIOC_QBUF, &buf) < 0)
		die("QBUF OUTPUT");
	printf("QBUF OUTPUT[0] bytesused=%zu\n", bs_len);

	/* --- QBUF CAPTURE[0] --- */
	memset(&buf, 0, sizeof(buf));
	memset(planes, 0, sizeof(planes));
	buf.type	= V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
	buf.memory	= V4L2_MEMORY_MMAP;
	buf.index	= 0;
	buf.m.planes	= planes;
	buf.length	= 2;
	if (ioctl(fd, VIDIOC_QBUF, &buf) < 0)
		die("QBUF CAPTURE");
	printf("QBUF CAPTURE[0]\n");

	/* --- STREAMON both --- */
	t = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
	if (ioctl(fd, VIDIOC_STREAMON, &t) < 0)
		die("STREAMON OUTPUT");
	t = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
	if (ioctl(fd, VIDIOC_STREAMON, &t) < 0)
		die("STREAMON CAPTURE");
	printf("STREAMON both\n");

	/* --- poll for CAPTURE completion --- */
	{
		struct pollfd p = { .fd = fd, .events = POLLIN | POLLOUT };
		rc = poll(&p, 1, POLL_TIMEOUT_MS);
		if (rc < 0)
			die("poll");
		if (rc == 0) {
			fprintf(stderr, "poll timeout\n");
			return 1;
		}
		printf("poll revents=0x%x\n", p.revents);
	}

	/* --- DQBUF OUTPUT (return the bitstream buffer) --- */
	memset(&buf, 0, sizeof(buf));
	memset(planes, 0, sizeof(planes));
	buf.type	= V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
	buf.memory	= V4L2_MEMORY_MMAP;
	buf.m.planes	= planes;
	buf.length	= 1;
	if (ioctl(fd, VIDIOC_DQBUF, &buf) < 0)
		die("DQBUF OUTPUT");
	printf("DQBUF OUTPUT[%u] flags=0x%x\n", buf.index, buf.flags);

	/* --- DQBUF CAPTURE (get the decoded frame) --- */
	memset(&buf, 0, sizeof(buf));
	memset(planes, 0, sizeof(planes));
	buf.type	= V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
	buf.memory	= V4L2_MEMORY_MMAP;
	buf.m.planes	= planes;
	buf.length	= 2;
	if (ioctl(fd, VIDIOC_DQBUF, &buf) < 0)
		die("DQBUF CAPTURE");
	printf("DQBUF CAPTURE[%u] flags=0x%x payloads=[%u, %u]\n",
	       buf.index, buf.flags,
	       planes[0].bytesused, planes[1].bytesused);
	if (buf.flags & V4L2_BUF_FLAG_ERROR) {
		fprintf(stderr, "CAPTURE buffer flagged ERROR\n");
		return 1;
	}

	/* --- mmap CAPTURE plane 0 + 1 and dump --- */
	{
		struct v4l2_buffer qb;
		struct v4l2_plane pl[2];

		memset(&qb, 0, sizeof(qb));
		memset(pl, 0, sizeof(pl));
		qb.type		= V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
		qb.memory	= V4L2_MEMORY_MMAP;
		qb.index	= 0;
		qb.m.planes	= pl;
		qb.length	= 2;
		if (ioctl(fd, VIDIOC_QUERYBUF, &qb) < 0)
			die("QUERYBUF CAPTURE");
		cap_y = mmap(NULL, pl[0].length, PROT_READ, MAP_SHARED, fd,
			     pl[0].m.mem_offset);
		if (cap_y == MAP_FAILED)
			die("mmap cap Y");
		cap_uv = mmap(NULL, pl[1].length, PROT_READ, MAP_SHARED, fd,
			      pl[1].m.mem_offset);
		if (cap_uv == MAP_FAILED)
			die("mmap cap UV");
	}

	{
		FILE *of = fopen(out_path, "wb");
		size_t y_actual  = planes[0].bytesused
				 ? planes[0].bytesused : cap_y_size;
		size_t uv_actual = planes[1].bytesused
				 ? planes[1].bytesused : cap_uv_size;
		if (!of)
			die("fopen out");
		fwrite(cap_y, 1, y_actual, of);
		fwrite(cap_uv, 1, uv_actual, of);
		fclose(of);
		printf("wrote %zu Y + %zu UV bytes to %s\n",
		       y_actual, uv_actual, out_path);
	}

	/* --- STREAMOFF, cleanup --- */
	t = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE;
	ioctl(fd, VIDIOC_STREAMOFF, &t);
	t = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
	ioctl(fd, VIDIOC_STREAMOFF, &t);

	close(fd);
	free(bitstream);
	printf("OK\n");
	(void) expbuf;
	(void) i;
	return 0;
}