/*
 * Cryptographic API.
 *
 * SHA1 Secure Hash Algorithm.
 *
 * Derived from cryptoapi implementation, adapted for in-place
 * scatterlist interface.
 *
 * Copyright (c) Alan Smithee.
 * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
 * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
 *
 * 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 <common.h>
#include <digest.h>
#include <init.h>
#include <linux/string.h>
#include <asm/unaligned.h>
#include <asm/byteorder.h>

#include <crypto/sha.h>
#include <crypto/internal.h>

#define SHA_WORKSPACE_WORDS 16

static int sha1_init(struct digest *desc)
{
	struct sha1_state *ctx = digest_ctx(desc);

	ctx->count = 0;

	ctx->state[0] = SHA1_H0;
	ctx->state[1] = SHA1_H1;
	ctx->state[2] = SHA1_H2;
	ctx->state[3] = SHA1_H3;
	ctx->state[4] = SHA1_H4;

	return 0;
}

/*
 * If you have 32 registers or more, the compiler can (and should)
 * try to change the array[] accesses into registers. However, on
 * machines with less than ~25 registers, that won't really work,
 * and at least gcc will make an unholy mess of it.
 *
 * So to avoid that mess which just slows things down, we force
 * the stores to memory to actually happen (we might be better off
 * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as
 * suggested by Artur Skawina - that will also make gcc unable to
 * try to do the silly "optimize away loads" part because it won't
 * see what the value will be).
 *
 * Ben Herrenschmidt reports that on PPC, the C version comes close
 * to the optimized asm with this (ie on PPC you don't want that
 * 'volatile', since there are lots of registers).
 *
 * On ARM we get the best code generation by forcing a full memory barrier
 * between each SHA_ROUND, otherwise gcc happily get wild with spilling and
 * the stack frame size simply explode and performance goes down the drain.
 */

#ifdef CONFIG_X86
  #define setW(x, val) (*(volatile __u32 *)&W(x) = (val))
#elif defined(CONFIG_ARM)
  #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0)
#else
  #define setW(x, val) (W(x) = (val))
#endif

/* This "rolls" over the 512-bit array */
#define W(x) (array[(x)&15])

/*
 * Where do we get the source from? The first 16 iterations get it from
 * the input data, the next mix it from the 512-bit array.
 */
#define SHA_SRC(t) get_unaligned_be32((__u32 *)data + t)
#define SHA_MIX(t) rol32(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1)

#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \
	__u32 TEMP = input(t); setW(t, TEMP); \
	E += TEMP + rol32(A,5) + (fn) + (constant); \
	B = ror32(B, 2); } while (0)

#define T_0_15(t, A, B, C, D, E)  SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E )
#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E )
#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) ,  0xca62c1d6, A, B, C, D, E )

/**
 * sha_transform - single block SHA1 transform
 *
 * @digest: 160 bit digest to update
 * @data:   512 bits of data to hash
 * @array:  16 words of workspace (see note)
 *
 * This function generates a SHA1 digest for a single 512-bit block.
 * Be warned, it does not handle padding and message digest, do not
 * confuse it with the full FIPS 180-1 digest algorithm for variable
 * length messages.
 *
 * Note: If the hash is security sensitive, the caller should be sure
 * to clear the workspace. This is left to the caller to avoid
 * unnecessary clears between chained hashing operations.
 */
static void sha_transform(__u32 *digest, const char *data, __u32 *array)
{
	__u32 A, B, C, D, E;

	A = digest[0];
	B = digest[1];
	C = digest[2];
	D = digest[3];
	E = digest[4];

	/* Round 1 - iterations 0-16 take their input from 'data' */
	T_0_15( 0, A, B, C, D, E);
	T_0_15( 1, E, A, B, C, D);
	T_0_15( 2, D, E, A, B, C);
	T_0_15( 3, C, D, E, A, B);
	T_0_15( 4, B, C, D, E, A);
	T_0_15( 5, A, B, C, D, E);
	T_0_15( 6, E, A, B, C, D);
	T_0_15( 7, D, E, A, B, C);
	T_0_15( 8, C, D, E, A, B);
	T_0_15( 9, B, C, D, E, A);
	T_0_15(10, A, B, C, D, E);
	T_0_15(11, E, A, B, C, D);
	T_0_15(12, D, E, A, B, C);
	T_0_15(13, C, D, E, A, B);
	T_0_15(14, B, C, D, E, A);
	T_0_15(15, A, B, C, D, E);

	/* Round 1 - tail. Input from 512-bit mixing array */
	T_16_19(16, E, A, B, C, D);
	T_16_19(17, D, E, A, B, C);
	T_16_19(18, C, D, E, A, B);
	T_16_19(19, B, C, D, E, A);

	/* Round 2 */
	T_20_39(20, A, B, C, D, E);
	T_20_39(21, E, A, B, C, D);
	T_20_39(22, D, E, A, B, C);
	T_20_39(23, C, D, E, A, B);
	T_20_39(24, B, C, D, E, A);
	T_20_39(25, A, B, C, D, E);
	T_20_39(26, E, A, B, C, D);
	T_20_39(27, D, E, A, B, C);
	T_20_39(28, C, D, E, A, B);
	T_20_39(29, B, C, D, E, A);
	T_20_39(30, A, B, C, D, E);
	T_20_39(31, E, A, B, C, D);
	T_20_39(32, D, E, A, B, C);
	T_20_39(33, C, D, E, A, B);
	T_20_39(34, B, C, D, E, A);
	T_20_39(35, A, B, C, D, E);
	T_20_39(36, E, A, B, C, D);
	T_20_39(37, D, E, A, B, C);
	T_20_39(38, C, D, E, A, B);
	T_20_39(39, B, C, D, E, A);

	/* Round 3 */
	T_40_59(40, A, B, C, D, E);
	T_40_59(41, E, A, B, C, D);
	T_40_59(42, D, E, A, B, C);
	T_40_59(43, C, D, E, A, B);
	T_40_59(44, B, C, D, E, A);
	T_40_59(45, A, B, C, D, E);
	T_40_59(46, E, A, B, C, D);
	T_40_59(47, D, E, A, B, C);
	T_40_59(48, C, D, E, A, B);
	T_40_59(49, B, C, D, E, A);
	T_40_59(50, A, B, C, D, E);
	T_40_59(51, E, A, B, C, D);
	T_40_59(52, D, E, A, B, C);
	T_40_59(53, C, D, E, A, B);
	T_40_59(54, B, C, D, E, A);
	T_40_59(55, A, B, C, D, E);
	T_40_59(56, E, A, B, C, D);
	T_40_59(57, D, E, A, B, C);
	T_40_59(58, C, D, E, A, B);
	T_40_59(59, B, C, D, E, A);

	/* Round 4 */
	T_60_79(60, A, B, C, D, E);
	T_60_79(61, E, A, B, C, D);
	T_60_79(62, D, E, A, B, C);
	T_60_79(63, C, D, E, A, B);
	T_60_79(64, B, C, D, E, A);
	T_60_79(65, A, B, C, D, E);
	T_60_79(66, E, A, B, C, D);
	T_60_79(67, D, E, A, B, C);
	T_60_79(68, C, D, E, A, B);
	T_60_79(69, B, C, D, E, A);
	T_60_79(70, A, B, C, D, E);
	T_60_79(71, E, A, B, C, D);
	T_60_79(72, D, E, A, B, C);
	T_60_79(73, C, D, E, A, B);
	T_60_79(74, B, C, D, E, A);
	T_60_79(75, A, B, C, D, E);
	T_60_79(76, E, A, B, C, D);
	T_60_79(77, D, E, A, B, C);
	T_60_79(78, C, D, E, A, B);
	T_60_79(79, B, C, D, E, A);

	digest[0] += A;
	digest[1] += B;
	digest[2] += C;
	digest[3] += D;
	digest[4] += E;
}

static int sha1_update(struct digest *desc, const void *data,
			     unsigned long len)
{
	struct sha1_state *sctx = digest_ctx(desc);
	unsigned int partial, done;
	const u8 *src;

	partial = sctx->count % SHA1_BLOCK_SIZE;
	sctx->count += len;
	done = 0;
	src = data;

	if ((partial + len) >= SHA1_BLOCK_SIZE) {
		u32 temp[SHA_WORKSPACE_WORDS];

		if (partial) {
			done = -partial;
			memcpy(sctx->buffer + partial, data,
			       done + SHA1_BLOCK_SIZE);
			src = sctx->buffer;
		}

		do {
			sha_transform(sctx->state, src, temp);
			done += SHA1_BLOCK_SIZE;
			src = data + done;
		} while (done + SHA1_BLOCK_SIZE <= len);

		memset(temp, 0, sizeof(temp));
		partial = 0;
	}
	memcpy(sctx->buffer + partial, src, len - done);

	return 0;
}

static int sha1_final(struct digest *desc, unsigned char *md)
{
	struct sha1_state *sctx = digest_ctx(desc);
	__be32 *dst = (__be32 *)md;
	u32 i, index, padlen;
	__be64 bits;
	static const u8 padding[64] = { 0x80, };

	bits = cpu_to_be64(sctx->count << 3);

	/* Pad out to 56 mod 64 */
	index = sctx->count & 0x3f;
	padlen = (index < 56) ? (56 - index) : ((64+56) - index);
	sha1_update(desc, padding, padlen);

	/* Append length */
	sha1_update(desc, (const u8 *)&bits, sizeof(bits));

	/* Store state in digest */
	for (i = 0; i < 5; i++)
		dst[i] = cpu_to_be32(sctx->state[i]);

	/* Wipe context */
	memset(sctx, 0, sizeof *sctx);

	return 0;
}

static struct digest_algo m = {
	.base = {
		.name		=	"sha1",
		.driver_name	=	"sha1-generic",
		.priority	=	0,
		.algo		=	HASH_ALGO_SHA1,
	},

	.init		= sha1_init,
	.update		= sha1_update,
	.final		= sha1_final,
	.digest		= digest_generic_digest,
	.verify		= digest_generic_verify,
	.length		= SHA1_DIGEST_SIZE,
	.ctx_length = sizeof(struct sha1_state),
};

static int sha1_digest_register(void)
{
	return digest_algo_register(&m);
}
device_initcall(sha1_digest_register);