// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) Collabora, Ltd.
 *
 * Based on GSPCA and CODA drivers:
 * Copyright (C) Jean-Francois Moine (http://moinejf.free.fr)
 * Copyright (C) 2014 Philipp Zabel, Pengutronix
 */

#include <linux/align.h>
#include <linux/build_bug.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include "hantro_jpeg.h"
#include "hantro.h"

#define LUMA_QUANT_OFF		25
#define CHROMA_QUANT_OFF	90
#define HEIGHT_OFF		159
#define WIDTH_OFF		161

#define HUFF_LUMA_DC_OFF	178
#define HUFF_LUMA_AC_OFF	211
#define HUFF_CHROMA_DC_OFF	394
#define HUFF_CHROMA_AC_OFF	427

/* Default tables from JPEG ITU-T.81
 * (ISO/IEC 10918-1) Annex K, tables K.1 and K.2
 */
static const unsigned char luma_q_table[] = {
	0x10, 0x0b, 0x0a, 0x10, 0x18, 0x28, 0x33, 0x3d,
	0x0c, 0x0c, 0x0e, 0x13, 0x1a, 0x3a, 0x3c, 0x37,
	0x0e, 0x0d, 0x10, 0x18, 0x28, 0x39, 0x45, 0x38,
	0x0e, 0x11, 0x16, 0x1d, 0x33, 0x57, 0x50, 0x3e,
	0x12, 0x16, 0x25, 0x38, 0x44, 0x6d, 0x67, 0x4d,
	0x18, 0x23, 0x37, 0x40, 0x51, 0x68, 0x71, 0x5c,
	0x31, 0x40, 0x4e, 0x57, 0x67, 0x79, 0x78, 0x65,
	0x48, 0x5c, 0x5f, 0x62, 0x70, 0x64, 0x67, 0x63
};

static const unsigned char chroma_q_table[] = {
	0x11, 0x12, 0x18, 0x2f, 0x63, 0x63, 0x63, 0x63,
	0x12, 0x15, 0x1a, 0x42, 0x63, 0x63, 0x63, 0x63,
	0x18, 0x1a, 0x38, 0x63, 0x63, 0x63, 0x63, 0x63,
	0x2f, 0x42, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63,
	0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63,
	0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63,
	0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63,
	0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63, 0x63
};

static const unsigned char zigzag[] = {
	 0,  1,  8, 16,  9,  2,  3, 10,
	17, 24, 32, 25, 18, 11,  4,  5,
	12, 19, 26, 33, 40, 48, 41, 34,
	27, 20, 13,  6,  7, 14, 21, 28,
	35, 42, 49, 56, 57, 50, 43, 36,
	29, 22, 15, 23, 30, 37, 44, 51,
	58, 59, 52, 45, 38, 31, 39, 46,
	53, 60, 61, 54, 47, 55, 62, 63
};

static const u32 hw_reorder[] = {
	 0,  8, 16, 24,  1,  9, 17, 25,
	32, 40, 48, 56, 33, 41, 49, 57,
	 2, 10, 18, 26,  3, 11, 19, 27,
	34, 42, 50, 58, 35, 43, 51, 59,
	 4, 12, 20, 28,  5, 13, 21, 29,
	36, 44, 52, 60, 37, 45, 53, 61,
	 6, 14, 22, 30,  7, 15, 23, 31,
	38, 46, 54, 62, 39, 47, 55, 63
};

/* Huffman tables are shared with CODA */
static const unsigned char luma_dc_table[] = {
	0x00, 0x01, 0x05, 0x01, 0x01, 0x01, 0x01, 0x01,
	0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
	0x08, 0x09, 0x0a, 0x0b,
};

static const unsigned char chroma_dc_table[] = {
	0x00, 0x03, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
	0x01, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
	0x08, 0x09, 0x0a, 0x0b,
};

static const unsigned char luma_ac_table[] = {
	0x00, 0x02, 0x01, 0x03, 0x03, 0x02, 0x04, 0x03,
	0x05, 0x05, 0x04, 0x04, 0x00, 0x00, 0x01, 0x7d,
	0x01, 0x02, 0x03, 0x00, 0x04, 0x11, 0x05, 0x12,
	0x21, 0x31, 0x41, 0x06, 0x13, 0x51, 0x61, 0x07,
	0x22, 0x71, 0x14, 0x32, 0x81, 0x91, 0xa1, 0x08,
	0x23, 0x42, 0xb1, 0xc1, 0x15, 0x52, 0xd1, 0xf0,
	0x24, 0x33, 0x62, 0x72, 0x82, 0x09, 0x0a, 0x16,
	0x17, 0x18, 0x19, 0x1a, 0x25, 0x26, 0x27, 0x28,
	0x29, 0x2a, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39,
	0x3a, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49,
	0x4a, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59,
	0x5a, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69,
	0x6a, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79,
	0x7a, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89,
	0x8a, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98,
	0x99, 0x9a, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7,
	0xa8, 0xa9, 0xaa, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6,
	0xb7, 0xb8, 0xb9, 0xba, 0xc2, 0xc3, 0xc4, 0xc5,
	0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xd2, 0xd3, 0xd4,
	0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xe1, 0xe2,
	0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea,
	0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8,
	0xf9, 0xfa,
};

static const unsigned char chroma_ac_table[] = {
	0x00, 0x02, 0x01, 0x02, 0x04, 0x04, 0x03, 0x04,
	0x07, 0x05, 0x04, 0x04, 0x00, 0x01, 0x02, 0x77,
	0x00, 0x01, 0x02, 0x03, 0x11, 0x04, 0x05, 0x21,
	0x31, 0x06, 0x12, 0x41, 0x51, 0x07, 0x61, 0x71,
	0x13, 0x22, 0x32, 0x81, 0x08, 0x14, 0x42, 0x91,
	0xa1, 0xb1, 0xc1, 0x09, 0x23, 0x33, 0x52, 0xf0,
	0x15, 0x62, 0x72, 0xd1, 0x0a, 0x16, 0x24, 0x34,
	0xe1, 0x25, 0xf1, 0x17, 0x18, 0x19, 0x1a, 0x26,
	0x27, 0x28, 0x29, 0x2a, 0x35, 0x36, 0x37, 0x38,
	0x39, 0x3a, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48,
	0x49, 0x4a, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58,
	0x59, 0x5a, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68,
	0x69, 0x6a, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78,
	0x79, 0x7a, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87,
	0x88, 0x89, 0x8a, 0x92, 0x93, 0x94, 0x95, 0x96,
	0x97, 0x98, 0x99, 0x9a, 0xa2, 0xa3, 0xa4, 0xa5,
	0xa6, 0xa7, 0xa8, 0xa9, 0xaa, 0xb2, 0xb3, 0xb4,
	0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xc2, 0xc3,
	0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xd2,
	0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda,
	0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9,
	0xea, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8,
	0xf9, 0xfa,
};

/* For simplicity, we keep a pre-formatted JPEG header,
 * and we'll use fixed offsets to change the width, height
 * quantization tables, etc.
 */
static const unsigned char hantro_jpeg_header[] = {
	/* SOI */
	0xff, 0xd8,

	/* JFIF-APP0 */
	0xff, 0xe0, 0x00, 0x10, 0x4a, 0x46, 0x49, 0x46,
	0x00, 0x01, 0x01, 0x00, 0x00, 0x01, 0x00, 0x01,
	0x00, 0x00,

	/* DQT */
	0xff, 0xdb, 0x00, 0x84,

	0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,

	0x01,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,

	/* SOF */
	0xff, 0xc0, 0x00, 0x11, 0x08, 0x00, 0xf0, 0x01,
	0x40, 0x03, 0x01, 0x22, 0x00, 0x02, 0x11, 0x01,
	0x03, 0x11, 0x01,

	/* DHT */
	0xff, 0xc4, 0x00, 0x1f, 0x00,

	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00,

	/* DHT */
	0xff, 0xc4, 0x00, 0xb5, 0x10,

	0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,

	/* DHT */
	0xff, 0xc4, 0x00, 0x1f, 0x01,

	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00,

	/* DHT */
	0xff, 0xc4, 0x00, 0xb5, 0x11,

	0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,

	/* COM */
	0xff, 0xfe, 0x00, 0x03, 0x00,

	/* SOS */
	0xff, 0xda, 0x00, 0x0c, 0x03, 0x01, 0x00, 0x02,
	0x11, 0x03, 0x11, 0x00, 0x3f, 0x00,
};

/*
 * JPEG_HEADER_SIZE is used in other parts of the driver in lieu of
 * "sizeof(hantro_jpeg_header)". The two must be equal.
 */
static_assert(sizeof(hantro_jpeg_header) == JPEG_HEADER_SIZE);

/*
 * hantro_jpeg_header is padded with a COM segment, so that the payload
 * of the SOS segment (the entropy-encoded image scan), which should
 * trail the whole header, is 8-byte aligned for the hardware to write
 * to directly.
 */
static_assert(IS_ALIGNED(sizeof(hantro_jpeg_header), 8),
	      "Hantro JPEG header size needs to be 8-byte aligned.");

static unsigned char jpeg_scale_qp(const unsigned char qp, int scale)
{
	unsigned int temp;

	temp = DIV_ROUND_CLOSEST((unsigned int)qp * scale, 100);
	if (temp <= 0)
		temp = 1;
	if (temp > 255)
		temp = 255;

	return (unsigned char)temp;
}

static void
jpeg_scale_quant_table(unsigned char *file_q_tab,
		       unsigned char *reordered_q_tab,
		       const unsigned char *tab, int scale)
{
	int i;

	BUILD_BUG_ON(ARRAY_SIZE(zigzag) != JPEG_QUANT_SIZE);
	BUILD_BUG_ON(ARRAY_SIZE(hw_reorder) != JPEG_QUANT_SIZE);

	for (i = 0; i < JPEG_QUANT_SIZE; i++) {
		file_q_tab[i] = jpeg_scale_qp(tab[zigzag[i]], scale);
		reordered_q_tab[i] = jpeg_scale_qp(tab[hw_reorder[i]], scale);
	}
}

static void jpeg_set_quality(struct hantro_jpeg_ctx *ctx)
{
	int scale;

	/*
	 * Non-linear scaling factor:
	 * [5,50] -> [1000..100], [51,100] -> [98..0]
	 */
	if (ctx->quality < 50)
		scale = 5000 / ctx->quality;
	else
		scale = 200 - 2 * ctx->quality;

	BUILD_BUG_ON(ARRAY_SIZE(luma_q_table) != JPEG_QUANT_SIZE);
	BUILD_BUG_ON(ARRAY_SIZE(chroma_q_table) != JPEG_QUANT_SIZE);
	BUILD_BUG_ON(ARRAY_SIZE(ctx->hw_luma_qtable) != JPEG_QUANT_SIZE);
	BUILD_BUG_ON(ARRAY_SIZE(ctx->hw_chroma_qtable) != JPEG_QUANT_SIZE);

	jpeg_scale_quant_table(ctx->buffer + LUMA_QUANT_OFF,
			       ctx->hw_luma_qtable, luma_q_table, scale);
	jpeg_scale_quant_table(ctx->buffer + CHROMA_QUANT_OFF,
			       ctx->hw_chroma_qtable, chroma_q_table, scale);
}

void hantro_jpeg_header_assemble(struct hantro_jpeg_ctx *ctx)
{
	char *buf = ctx->buffer;

	memcpy(buf, hantro_jpeg_header,
	       sizeof(hantro_jpeg_header));

	buf[HEIGHT_OFF + 0] = ctx->height >> 8;
	buf[HEIGHT_OFF + 1] = ctx->height;
	buf[WIDTH_OFF + 0] = ctx->width >> 8;
	buf[WIDTH_OFF + 1] = ctx->width;

	memcpy(buf + HUFF_LUMA_DC_OFF, luma_dc_table, sizeof(luma_dc_table));
	memcpy(buf + HUFF_LUMA_AC_OFF, luma_ac_table, sizeof(luma_ac_table));
	memcpy(buf + HUFF_CHROMA_DC_OFF, chroma_dc_table,
	       sizeof(chroma_dc_table));
	memcpy(buf + HUFF_CHROMA_AC_OFF, chroma_ac_table,
	       sizeof(chroma_ac_table));

	jpeg_set_quality(ctx);
}