/*
 * Cryptographic API.
 *
 * SHA-256, as specified in
 * http://csrc.nist.gov/cryptval/shs/sha256-384-512.pdf
 *
 * SHA-256 code by Jean-Luc Cooke <jlcooke@certainkey.com>.
 *
 * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com>
 * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
 * Copyright (c) 2002 James Morris <jmorris@intercode.com.au>
 * SHA224 Support Copyright 2007 Intel Corporation <jonathan.lynch@intel.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the Free
 * Software Foundation; either version 2 of the License, or (at your option) 
 * any later version.
 *
 */
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/crypto.h>
#include <linux/types.h>
#include <crypto/sha.h>
#include <asm/byteorder.h>

struct sha256_ctx {
	u32 count[2];
	u32 state[8];
	u8 buf[128];
};

static inline u32 Ch(u32 x, u32 y, u32 z)
{
	return z ^ (x & (y ^ z));
}

static inline u32 Maj(u32 x, u32 y, u32 z)
{
	return (x & y) | (z & (x | y));
}

#define e0(x)       (ror32(x, 2) ^ ror32(x,13) ^ ror32(x,22))
#define e1(x)       (ror32(x, 6) ^ ror32(x,11) ^ ror32(x,25))
#define s0(x)       (ror32(x, 7) ^ ror32(x,18) ^ (x >> 3))
#define s1(x)       (ror32(x,17) ^ ror32(x,19) ^ (x >> 10))

static inline void LOAD_OP(int I, u32 *W, const u8 *input)
{
	W[I] = __be32_to_cpu( ((__be32*)(input))[I] );
}

static inline void BLEND_OP(int I, u32 *W)
{
	W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16];
}

static void sha256_transform(u32 *state, const u8 *input)
{
	u32 a, b, c, d, e, f, g, h, t1, t2;
	u32 W[64];
	int i;

	/* load the input */
	for (i = 0; i < 16; i++)
		LOAD_OP(i, W, input);

	/* now blend */
	for (i = 16; i < 64; i++)
		BLEND_OP(i, W);
    
	/* load the state into our registers */
	a=state[0];  b=state[1];  c=state[2];  d=state[3];
	e=state[4];  f=state[5];  g=state[6];  h=state[7];

	/* now iterate */
	t1 = h + e1(e) + Ch(e,f,g) + 0x428a2f98 + W[ 0];
	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
	t1 = g + e1(d) + Ch(d,e,f) + 0x71374491 + W[ 1];
	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
	t1 = f + e1(c) + Ch(c,d,e) + 0xb5c0fbcf + W[ 2];
	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
	t1 = e + e1(b) + Ch(b,c,d) + 0xe9b5dba5 + W[ 3];
	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
	t1 = d + e1(a) + Ch(a,b,c) + 0x3956c25b + W[ 4];
	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
	t1 = c + e1(h) + Ch(h,a,b) + 0x59f111f1 + W[ 5];
	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
	t1 = b + e1(g) + Ch(g,h,a) + 0x923f82a4 + W[ 6];
	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
	t1 = a + e1(f) + Ch(f,g,h) + 0xab1c5ed5 + W[ 7];
	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;

	t1 = h + e1(e) + Ch(e,f,g) + 0xd807aa98 + W[ 8];
	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
	t1 = g + e1(d) + Ch(d,e,f) + 0x12835b01 + W[ 9];
	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
	t1 = f + e1(c) + Ch(c,d,e) + 0x243185be + W[10];
	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
	t1 = e + e1(b) + Ch(b,c,d) + 0x550c7dc3 + W[11];
	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
	t1 = d + e1(a) + Ch(a,b,c) + 0x72be5d74 + W[12];
	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
	t1 = c + e1(h) + Ch(h,a,b) + 0x80deb1fe + W[13];
	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
	t1 = b + e1(g) + Ch(g,h,a) + 0x9bdc06a7 + W[14];
	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
	t1 = a + e1(f) + Ch(f,g,h) + 0xc19bf174 + W[15];
	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;

	t1 = h + e1(e) + Ch(e,f,g) + 0xe49b69c1 + W[16];
	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
	t1 = g + e1(d) + Ch(d,e,f) + 0xefbe4786 + W[17];
	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
	t1 = f + e1(c) + Ch(c,d,e) + 0x0fc19dc6 + W[18];
	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
	t1 = e + e1(b) + Ch(b,c,d) + 0x240ca1cc + W[19];
	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
	t1 = d + e1(a) + Ch(a,b,c) + 0x2de92c6f + W[20];
	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
	t1 = c + e1(h) + Ch(h,a,b) + 0x4a7484aa + W[21];
	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
	t1 = b + e1(g) + Ch(g,h,a) + 0x5cb0a9dc + W[22];
	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
	t1 = a + e1(f) + Ch(f,g,h) + 0x76f988da + W[23];
	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;

	t1 = h + e1(e) + Ch(e,f,g) + 0x983e5152 + W[24];
	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
	t1 = g + e1(d) + Ch(d,e,f) + 0xa831c66d + W[25];
	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
	t1 = f + e1(c) + Ch(c,d,e) + 0xb00327c8 + W[26];
	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
	t1 = e + e1(b) + Ch(b,c,d) + 0xbf597fc7 + W[27];
	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
	t1 = d + e1(a) + Ch(a,b,c) + 0xc6e00bf3 + W[28];
	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
	t1 = c + e1(h) + Ch(h,a,b) + 0xd5a79147 + W[29];
	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
	t1 = b + e1(g) + Ch(g,h,a) + 0x06ca6351 + W[30];
	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
	t1 = a + e1(f) + Ch(f,g,h) + 0x14292967 + W[31];
	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;

	t1 = h + e1(e) + Ch(e,f,g) + 0x27b70a85 + W[32];
	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
	t1 = g + e1(d) + Ch(d,e,f) + 0x2e1b2138 + W[33];
	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
	t1 = f + e1(c) + Ch(c,d,e) + 0x4d2c6dfc + W[34];
	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
	t1 = e + e1(b) + Ch(b,c,d) + 0x53380d13 + W[35];
	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
	t1 = d + e1(a) + Ch(a,b,c) + 0x650a7354 + W[36];
	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
	t1 = c + e1(h) + Ch(h,a,b) + 0x766a0abb + W[37];
	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
	t1 = b + e1(g) + Ch(g,h,a) + 0x81c2c92e + W[38];
	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
	t1 = a + e1(f) + Ch(f,g,h) + 0x92722c85 + W[39];
	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;

	t1 = h + e1(e) + Ch(e,f,g) + 0xa2bfe8a1 + W[40];
	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
	t1 = g + e1(d) + Ch(d,e,f) + 0xa81a664b + W[41];
	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
	t1 = f + e1(c) + Ch(c,d,e) + 0xc24b8b70 + W[42];
	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
	t1 = e + e1(b) + Ch(b,c,d) + 0xc76c51a3 + W[43];
	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
	t1 = d + e1(a) + Ch(a,b,c) + 0xd192e819 + W[44];
	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
	t1 = c + e1(h) + Ch(h,a,b) + 0xd6990624 + W[45];
	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
	t1 = b + e1(g) + Ch(g,h,a) + 0xf40e3585 + W[46];
	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
	t1 = a + e1(f) + Ch(f,g,h) + 0x106aa070 + W[47];
	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;

	t1 = h + e1(e) + Ch(e,f,g) + 0x19a4c116 + W[48];
	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
	t1 = g + e1(d) + Ch(d,e,f) + 0x1e376c08 + W[49];
	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
	t1 = f + e1(c) + Ch(c,d,e) + 0x2748774c + W[50];
	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
	t1 = e + e1(b) + Ch(b,c,d) + 0x34b0bcb5 + W[51];
	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
	t1 = d + e1(a) + Ch(a,b,c) + 0x391c0cb3 + W[52];
	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
	t1 = c + e1(h) + Ch(h,a,b) + 0x4ed8aa4a + W[53];
	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
	t1 = b + e1(g) + Ch(g,h,a) + 0x5b9cca4f + W[54];
	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
	t1 = a + e1(f) + Ch(f,g,h) + 0x682e6ff3 + W[55];
	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;

	t1 = h + e1(e) + Ch(e,f,g) + 0x748f82ee + W[56];
	t2 = e0(a) + Maj(a,b,c);    d+=t1;    h=t1+t2;
	t1 = g + e1(d) + Ch(d,e,f) + 0x78a5636f + W[57];
	t2 = e0(h) + Maj(h,a,b);    c+=t1;    g=t1+t2;
	t1 = f + e1(c) + Ch(c,d,e) + 0x84c87814 + W[58];
	t2 = e0(g) + Maj(g,h,a);    b+=t1;    f=t1+t2;
	t1 = e + e1(b) + Ch(b,c,d) + 0x8cc70208 + W[59];
	t2 = e0(f) + Maj(f,g,h);    a+=t1;    e=t1+t2;
	t1 = d + e1(a) + Ch(a,b,c) + 0x90befffa + W[60];
	t2 = e0(e) + Maj(e,f,g);    h+=t1;    d=t1+t2;
	t1 = c + e1(h) + Ch(h,a,b) + 0xa4506ceb + W[61];
	t2 = e0(d) + Maj(d,e,f);    g+=t1;    c=t1+t2;
	t1 = b + e1(g) + Ch(g,h,a) + 0xbef9a3f7 + W[62];
	t2 = e0(c) + Maj(c,d,e);    f+=t1;    b=t1+t2;
	t1 = a + e1(f) + Ch(f,g,h) + 0xc67178f2 + W[63];
	t2 = e0(b) + Maj(b,c,d);    e+=t1;    a=t1+t2;

	state[0] += a; state[1] += b; state[2] += c; state[3] += d;
	state[4] += e; state[5] += f; state[6] += g; state[7] += h;

	/* clear any sensitive info... */
	a = b = c = d = e = f = g = h = t1 = t2 = 0;
	memset(W, 0, 64 * sizeof(u32));
}


static void sha224_init(struct crypto_tfm *tfm)
{
	struct sha256_ctx *sctx = crypto_tfm_ctx(tfm);
	sctx->state[0] = SHA224_H0;
	sctx->state[1] = SHA224_H1;
	sctx->state[2] = SHA224_H2;
	sctx->state[3] = SHA224_H3;
	sctx->state[4] = SHA224_H4;
	sctx->state[5] = SHA224_H5;
	sctx->state[6] = SHA224_H6;
	sctx->state[7] = SHA224_H7;
	sctx->count[0] = 0;
	sctx->count[1] = 0;
}

static void sha256_init(struct crypto_tfm *tfm)
{
	struct sha256_ctx *sctx = crypto_tfm_ctx(tfm);
	sctx->state[0] = SHA256_H0;
	sctx->state[1] = SHA256_H1;
	sctx->state[2] = SHA256_H2;
	sctx->state[3] = SHA256_H3;
	sctx->state[4] = SHA256_H4;
	sctx->state[5] = SHA256_H5;
	sctx->state[6] = SHA256_H6;
	sctx->state[7] = SHA256_H7;
	sctx->count[0] = sctx->count[1] = 0;
}

static void sha256_update(struct crypto_tfm *tfm, const u8 *data,
			  unsigned int len)
{
	struct sha256_ctx *sctx = crypto_tfm_ctx(tfm);
	unsigned int i, index, part_len;

	/* Compute number of bytes mod 128 */
	index = (unsigned int)((sctx->count[0] >> 3) & 0x3f);

	/* Update number of bits */
	if ((sctx->count[0] += (len << 3)) < (len << 3)) {
		sctx->count[1]++;
		sctx->count[1] += (len >> 29);
	}

	part_len = 64 - index;

	/* Transform as many times as possible. */
	if (len >= part_len) {
		memcpy(&sctx->buf[index], data, part_len);
		sha256_transform(sctx->state, sctx->buf);

		for (i = part_len; i + 63 < len; i += 64)
			sha256_transform(sctx->state, &data[i]);
		index = 0;
	} else {
		i = 0;
	}
	
	/* Buffer remaining input */
	memcpy(&sctx->buf[index], &data[i], len-i);
}

static void sha256_final(struct crypto_tfm *tfm, u8 *out)
{
	struct sha256_ctx *sctx = crypto_tfm_ctx(tfm);
	__be32 *dst = (__be32 *)out;
	__be32 bits[2];
	unsigned int index, pad_len;
	int i;
	static const u8 padding[64] = { 0x80, };

	/* Save number of bits */
	bits[1] = cpu_to_be32(sctx->count[0]);
	bits[0] = cpu_to_be32(sctx->count[1]);

	/* Pad out to 56 mod 64. */
	index = (sctx->count[0] >> 3) & 0x3f;
	pad_len = (index < 56) ? (56 - index) : ((64+56) - index);
	sha256_update(tfm, padding, pad_len);

	/* Append length (before padding) */
	sha256_update(tfm, (const u8 *)bits, sizeof(bits));

	/* Store state in digest */
	for (i = 0; i < 8; i++)
		dst[i] = cpu_to_be32(sctx->state[i]);

	/* Zeroize sensitive information. */
	memset(sctx, 0, sizeof(*sctx));
}

static void sha224_final(struct crypto_tfm *tfm, u8 *hash)
{
	u8 D[SHA256_DIGEST_SIZE];

	sha256_final(tfm, D);

	memcpy(hash, D, SHA224_DIGEST_SIZE);
	memset(D, 0, SHA256_DIGEST_SIZE);
}

static struct crypto_alg sha256 = {
	.cra_name	=	"sha256",
	.cra_driver_name=	"sha256-generic",
	.cra_flags	=	CRYPTO_ALG_TYPE_DIGEST,
	.cra_blocksize	=	SHA256_BLOCK_SIZE,
	.cra_ctxsize	=	sizeof(struct sha256_ctx),
	.cra_module	=	THIS_MODULE,
	.cra_alignmask	=	3,
	.cra_list	=	LIST_HEAD_INIT(sha256.cra_list),
	.cra_u		=	{ .digest = {
	.dia_digestsize	=	SHA256_DIGEST_SIZE,
	.dia_init	=	sha256_init,
	.dia_update	=	sha256_update,
	.dia_final	=	sha256_final } }
};

static struct crypto_alg sha224 = {
	.cra_name	= "sha224",
	.cra_driver_name = "sha224-generic",
	.cra_flags	= CRYPTO_ALG_TYPE_DIGEST,
	.cra_blocksize	= SHA224_BLOCK_SIZE,
	.cra_ctxsize	= sizeof(struct sha256_ctx),
	.cra_module	= THIS_MODULE,
	.cra_alignmask	= 3,
	.cra_list	= LIST_HEAD_INIT(sha224.cra_list),
	.cra_u		= { .digest = {
	.dia_digestsize = SHA224_DIGEST_SIZE,
	.dia_init	= sha224_init,
	.dia_update	= sha256_update,
	.dia_final	= sha224_final } }
};

static int __init sha256_generic_mod_init(void)
{
	int ret = 0;

	ret = crypto_register_alg(&sha224);

	if (ret < 0)
		return ret;

	ret = crypto_register_alg(&sha256);

	if (ret < 0)
		crypto_unregister_alg(&sha224);

	return ret;
}

static void __exit sha256_generic_mod_fini(void)
{
	crypto_unregister_alg(&sha224);
	crypto_unregister_alg(&sha256);
}

module_init(sha256_generic_mod_init);
module_exit(sha256_generic_mod_fini);

MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA-224 and SHA-256 Secure Hash Algorithm");

MODULE_ALIAS("sha224");
MODULE_ALIAS("sha256");