mirror of
https://github.com/rtlduino/RTL8710AF_GCC.git
synced 2026-07-12 06:15:42 +00:00
rtlduino rtl8710af gcc base version
This commit is contained in:
RtlduinoMan
parent
7675bdb95f
commit
9c0c9edf61
2097 changed files with 779974 additions and 2 deletions
121
tools/wigadget/iOS/WiGadget/WiGadget/Crypto/Crypto.swift
Normal file
121
tools/wigadget/iOS/WiGadget/WiGadget/Crypto/Crypto.swift
Normal file
|
|
@ -0,0 +1,121 @@
|
|||
//
|
||||
// Crypto.swift
|
||||
// WiGadget
|
||||
//
|
||||
// Created by WU JINZHOU on 27/8/15.
|
||||
// Copyright (c) 2015 WU JINZHOU. All rights reserved.
|
||||
//
|
||||
|
||||
import Foundation
|
||||
|
||||
class Crypto {
|
||||
|
||||
static var curve25519_private_key = [UInt8]()
|
||||
static var curve25519_base_point = R.curve25519_base_point
|
||||
static var curve25519_my_public_key = [UInt8](count: 32, repeatedValue: 0)
|
||||
static var curve25519_his_public_key = [UInt8]()
|
||||
static var curve25519_shared_key = [UInt8](count: 32, repeatedValue: 0)
|
||||
static var aes_128_key = [UInt8]()
|
||||
static var aes_iv = [UInt8](R.aes_iv.utf8)
|
||||
static var aes_block_size = aes_iv.count
|
||||
|
||||
//generate curve25519 public key
|
||||
class func makeCurve25519PublicKey() -> String {
|
||||
|
||||
for _ in 0 ..< 32 {
|
||||
curve25519_private_key.append(UInt8(arc4random() % 256))
|
||||
}
|
||||
|
||||
curve25519_donna(&curve25519_my_public_key, &curve25519_private_key, &curve25519_base_point)
|
||||
|
||||
return "\(curve25519_my_public_key)"
|
||||
}
|
||||
|
||||
//generate curve25519 shared key & AES shared key
|
||||
class func makePSK(hisCurve25519PublicKey:String) -> String {
|
||||
|
||||
let strArr = hisCurve25519PublicKey.characters.split { $0 == "," }.map { String($0) }
|
||||
|
||||
for item in strArr {
|
||||
let components = item.componentsSeparatedByCharactersInSet(NSCharacterSet.decimalDigitCharacterSet().invertedSet)
|
||||
let part = components.joinWithSeparator("")
|
||||
if let intVal = Int(part) {
|
||||
curve25519_his_public_key.append(UInt8(intVal))
|
||||
}
|
||||
}
|
||||
|
||||
curve25519_donna(&curve25519_shared_key, &curve25519_private_key, &curve25519_his_public_key)
|
||||
|
||||
aes_128_key = [UInt8](curve25519_shared_key[0...15])
|
||||
|
||||
return "\(aes_128_key)"
|
||||
}
|
||||
|
||||
//aes128 encryption
|
||||
class func encrypt(plainText:String,key:String) -> String {
|
||||
|
||||
var k8 = [UInt8]()
|
||||
|
||||
let strArr = key.characters.split { $0 == "," }.map { String($0) }
|
||||
|
||||
for item in strArr {
|
||||
let components = item.componentsSeparatedByCharactersInSet(NSCharacterSet.decimalDigitCharacterSet().invertedSet)
|
||||
let part = components.joinWithSeparator("")
|
||||
if let intVal = Int(part) {
|
||||
k8.append(UInt8(intVal))
|
||||
}
|
||||
}
|
||||
|
||||
var pt8 = [UInt8](plainText.utf8)
|
||||
|
||||
//zero padding
|
||||
let r = pt8.count % aes_block_size
|
||||
|
||||
for _ in 0 ..< (aes_block_size - r) {
|
||||
pt8.append(0)
|
||||
}
|
||||
|
||||
var ct8 = pt8 //allocate mem for ct8
|
||||
|
||||
AES128_CBC_encrypt_buffer(&ct8, &pt8, UInt32(pt8.count), &k8, &aes_iv)
|
||||
|
||||
return "\(ct8)"
|
||||
}
|
||||
|
||||
class func decrypt(cipherText:String,key:String) -> String {
|
||||
|
||||
var k8 = [UInt8]()
|
||||
|
||||
var strArr = key.characters.split { $0 == "," }.map { String($0) }
|
||||
|
||||
for item in strArr {
|
||||
let components = item.componentsSeparatedByCharactersInSet(NSCharacterSet.decimalDigitCharacterSet().invertedSet)
|
||||
let part = components.joinWithSeparator("")
|
||||
if let intVal = Int(part) {
|
||||
k8.append(UInt8(intVal))
|
||||
}
|
||||
}
|
||||
|
||||
var ct8 = [UInt8]()
|
||||
|
||||
strArr = cipherText.characters.split { $0 == "," }.map { String($0) }
|
||||
|
||||
for item in strArr {
|
||||
let components = item.componentsSeparatedByCharactersInSet(NSCharacterSet.decimalDigitCharacterSet().invertedSet)
|
||||
let part = components.joinWithSeparator("")
|
||||
if let intVal = Int(part) {
|
||||
ct8.append(UInt8(intVal))
|
||||
}
|
||||
}
|
||||
|
||||
var pt8 = ct8 //allocate mem for pt8
|
||||
|
||||
AES128_CBC_decrypt_buffer(&pt8, &ct8, UInt32(ct8.count), &k8, &aes_iv)
|
||||
|
||||
pt8 = pt8.filter({$0 != 0})
|
||||
|
||||
let pt = NSString(bytes: pt8, length: pt8.count, encoding: NSUTF8StringEncoding) as! String
|
||||
|
||||
return pt
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,860 @@
|
|||
/* Copyright 2008, Google Inc.
|
||||
* All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions are
|
||||
* met:
|
||||
*
|
||||
* * Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* * Redistributions in binary form must reproduce the above
|
||||
* copyright notice, this list of conditions and the following disclaimer
|
||||
* in the documentation and/or other materials provided with the
|
||||
* distribution.
|
||||
* * Neither the name of Google Inc. nor the names of its
|
||||
* contributors may be used to endorse or promote products derived from
|
||||
* this software without specific prior written permission.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
*
|
||||
* curve25519-donna: Curve25519 elliptic curve, public key function
|
||||
*
|
||||
* http://code.google.com/p/curve25519-donna/
|
||||
*
|
||||
* Adam Langley <agl@imperialviolet.org>
|
||||
*
|
||||
* Derived from public domain C code by Daniel J. Bernstein <djb@cr.yp.to>
|
||||
*
|
||||
* More information about curve25519 can be found here
|
||||
* http://cr.yp.to/ecdh.html
|
||||
*
|
||||
* djb's sample implementation of curve25519 is written in a special assembly
|
||||
* language called qhasm and uses the floating point registers.
|
||||
*
|
||||
* This is, almost, a clean room reimplementation from the curve25519 paper. It
|
||||
* uses many of the tricks described therein. Only the crecip function is taken
|
||||
* from the sample implementation. */
|
||||
|
||||
#include <string.h>
|
||||
#include <stdint.h>
|
||||
|
||||
#ifdef _MSC_VER
|
||||
#define inline __inline
|
||||
#endif
|
||||
|
||||
typedef uint8_t u8;
|
||||
typedef int32_t s32;
|
||||
typedef int64_t limb;
|
||||
|
||||
/* Field element representation:
|
||||
*
|
||||
* Field elements are written as an array of signed, 64-bit limbs, least
|
||||
* significant first. The value of the field element is:
|
||||
* x[0] + 2^26·x[1] + x^51·x[2] + 2^102·x[3] + ...
|
||||
*
|
||||
* i.e. the limbs are 26, 25, 26, 25, ... bits wide. */
|
||||
|
||||
/* Sum two numbers: output += in */
|
||||
static void fsum(limb *output, const limb *in) {
|
||||
unsigned i;
|
||||
for (i = 0; i < 10; i += 2) {
|
||||
output[0+i] = output[0+i] + in[0+i];
|
||||
output[1+i] = output[1+i] + in[1+i];
|
||||
}
|
||||
}
|
||||
|
||||
/* Find the difference of two numbers: output = in - output
|
||||
* (note the order of the arguments!). */
|
||||
static void fdifference(limb *output, const limb *in) {
|
||||
unsigned i;
|
||||
for (i = 0; i < 10; ++i) {
|
||||
output[i] = in[i] - output[i];
|
||||
}
|
||||
}
|
||||
|
||||
/* Multiply a number by a scalar: output = in * scalar */
|
||||
static void fscalar_product(limb *output, const limb *in, const limb scalar) {
|
||||
unsigned i;
|
||||
for (i = 0; i < 10; ++i) {
|
||||
output[i] = in[i] * scalar;
|
||||
}
|
||||
}
|
||||
|
||||
/* Multiply two numbers: output = in2 * in
|
||||
*
|
||||
* output must be distinct to both inputs. The inputs are reduced coefficient
|
||||
* form, the output is not.
|
||||
*
|
||||
* output[x] <= 14 * the largest product of the input limbs. */
|
||||
static void fproduct(limb *output, const limb *in2, const limb *in) {
|
||||
output[0] = ((limb) ((s32) in2[0])) * ((s32) in[0]);
|
||||
output[1] = ((limb) ((s32) in2[0])) * ((s32) in[1]) +
|
||||
((limb) ((s32) in2[1])) * ((s32) in[0]);
|
||||
output[2] = 2 * ((limb) ((s32) in2[1])) * ((s32) in[1]) +
|
||||
((limb) ((s32) in2[0])) * ((s32) in[2]) +
|
||||
((limb) ((s32) in2[2])) * ((s32) in[0]);
|
||||
output[3] = ((limb) ((s32) in2[1])) * ((s32) in[2]) +
|
||||
((limb) ((s32) in2[2])) * ((s32) in[1]) +
|
||||
((limb) ((s32) in2[0])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[3])) * ((s32) in[0]);
|
||||
output[4] = ((limb) ((s32) in2[2])) * ((s32) in[2]) +
|
||||
2 * (((limb) ((s32) in2[1])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[3])) * ((s32) in[1])) +
|
||||
((limb) ((s32) in2[0])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in2[4])) * ((s32) in[0]);
|
||||
output[5] = ((limb) ((s32) in2[2])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[3])) * ((s32) in[2]) +
|
||||
((limb) ((s32) in2[1])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in2[4])) * ((s32) in[1]) +
|
||||
((limb) ((s32) in2[0])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[5])) * ((s32) in[0]);
|
||||
output[6] = 2 * (((limb) ((s32) in2[3])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[1])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[5])) * ((s32) in[1])) +
|
||||
((limb) ((s32) in2[2])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in2[4])) * ((s32) in[2]) +
|
||||
((limb) ((s32) in2[0])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in2[6])) * ((s32) in[0]);
|
||||
output[7] = ((limb) ((s32) in2[3])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in2[4])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[2])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[5])) * ((s32) in[2]) +
|
||||
((limb) ((s32) in2[1])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in2[6])) * ((s32) in[1]) +
|
||||
((limb) ((s32) in2[0])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[7])) * ((s32) in[0]);
|
||||
output[8] = ((limb) ((s32) in2[4])) * ((s32) in[4]) +
|
||||
2 * (((limb) ((s32) in2[3])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[5])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[1])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[7])) * ((s32) in[1])) +
|
||||
((limb) ((s32) in2[2])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in2[6])) * ((s32) in[2]) +
|
||||
((limb) ((s32) in2[0])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in2[8])) * ((s32) in[0]);
|
||||
output[9] = ((limb) ((s32) in2[4])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[5])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in2[3])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in2[6])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[2])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[7])) * ((s32) in[2]) +
|
||||
((limb) ((s32) in2[1])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in2[8])) * ((s32) in[1]) +
|
||||
((limb) ((s32) in2[0])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[0]);
|
||||
output[10] = 2 * (((limb) ((s32) in2[5])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[3])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[7])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[1])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[1])) +
|
||||
((limb) ((s32) in2[4])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in2[6])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in2[2])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in2[8])) * ((s32) in[2]);
|
||||
output[11] = ((limb) ((s32) in2[5])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in2[6])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[4])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[7])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in2[3])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in2[8])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in2[2])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[2]);
|
||||
output[12] = ((limb) ((s32) in2[6])) * ((s32) in[6]) +
|
||||
2 * (((limb) ((s32) in2[5])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[7])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[3])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[3])) +
|
||||
((limb) ((s32) in2[4])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in2[8])) * ((s32) in[4]);
|
||||
output[13] = ((limb) ((s32) in2[6])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[7])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in2[5])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in2[8])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in2[4])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[4]);
|
||||
output[14] = 2 * (((limb) ((s32) in2[7])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[5])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[5])) +
|
||||
((limb) ((s32) in2[6])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in2[8])) * ((s32) in[6]);
|
||||
output[15] = ((limb) ((s32) in2[7])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in2[8])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in2[6])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[6]);
|
||||
output[16] = ((limb) ((s32) in2[8])) * ((s32) in[8]) +
|
||||
2 * (((limb) ((s32) in2[7])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[7]));
|
||||
output[17] = ((limb) ((s32) in2[8])) * ((s32) in[9]) +
|
||||
((limb) ((s32) in2[9])) * ((s32) in[8]);
|
||||
output[18] = 2 * ((limb) ((s32) in2[9])) * ((s32) in[9]);
|
||||
}
|
||||
|
||||
/* Reduce a long form to a short form by taking the input mod 2^255 - 19.
|
||||
*
|
||||
* On entry: |output[i]| < 14*2^54
|
||||
* On exit: |output[0..8]| < 280*2^54 */
|
||||
static void freduce_degree(limb *output) {
|
||||
/* Each of these shifts and adds ends up multiplying the value by 19.
|
||||
*
|
||||
* For output[0..8], the absolute entry value is < 14*2^54 and we add, at
|
||||
* most, 19*14*2^54 thus, on exit, |output[0..8]| < 280*2^54. */
|
||||
output[8] += output[18] << 4;
|
||||
output[8] += output[18] << 1;
|
||||
output[8] += output[18];
|
||||
output[7] += output[17] << 4;
|
||||
output[7] += output[17] << 1;
|
||||
output[7] += output[17];
|
||||
output[6] += output[16] << 4;
|
||||
output[6] += output[16] << 1;
|
||||
output[6] += output[16];
|
||||
output[5] += output[15] << 4;
|
||||
output[5] += output[15] << 1;
|
||||
output[5] += output[15];
|
||||
output[4] += output[14] << 4;
|
||||
output[4] += output[14] << 1;
|
||||
output[4] += output[14];
|
||||
output[3] += output[13] << 4;
|
||||
output[3] += output[13] << 1;
|
||||
output[3] += output[13];
|
||||
output[2] += output[12] << 4;
|
||||
output[2] += output[12] << 1;
|
||||
output[2] += output[12];
|
||||
output[1] += output[11] << 4;
|
||||
output[1] += output[11] << 1;
|
||||
output[1] += output[11];
|
||||
output[0] += output[10] << 4;
|
||||
output[0] += output[10] << 1;
|
||||
output[0] += output[10];
|
||||
}
|
||||
|
||||
#if (-1 & 3) != 3
|
||||
#error "This code only works on a two's complement system"
|
||||
#endif
|
||||
|
||||
/* return v / 2^26, using only shifts and adds.
|
||||
*
|
||||
* On entry: v can take any value. */
|
||||
static inline limb
|
||||
div_by_2_26(const limb v)
|
||||
{
|
||||
/* High word of v; no shift needed. */
|
||||
const uint32_t highword = (uint32_t) (((uint64_t) v) >> 32);
|
||||
/* Set to all 1s if v was negative; else set to 0s. */
|
||||
const int32_t sign = ((int32_t) highword) >> 31;
|
||||
/* Set to 0x3ffffff if v was negative; else set to 0. */
|
||||
const int32_t roundoff = ((uint32_t) sign) >> 6;
|
||||
/* Should return v / (1<<26) */
|
||||
return (v + roundoff) >> 26;
|
||||
}
|
||||
|
||||
/* return v / (2^25), using only shifts and adds.
|
||||
*
|
||||
* On entry: v can take any value. */
|
||||
static inline limb
|
||||
div_by_2_25(const limb v)
|
||||
{
|
||||
/* High word of v; no shift needed*/
|
||||
const uint32_t highword = (uint32_t) (((uint64_t) v) >> 32);
|
||||
/* Set to all 1s if v was negative; else set to 0s. */
|
||||
const int32_t sign = ((int32_t) highword) >> 31;
|
||||
/* Set to 0x1ffffff if v was negative; else set to 0. */
|
||||
const int32_t roundoff = ((uint32_t) sign) >> 7;
|
||||
/* Should return v / (1<<25) */
|
||||
return (v + roundoff) >> 25;
|
||||
}
|
||||
|
||||
/* Reduce all coefficients of the short form input so that |x| < 2^26.
|
||||
*
|
||||
* On entry: |output[i]| < 280*2^54 */
|
||||
static void freduce_coefficients(limb *output) {
|
||||
unsigned i;
|
||||
|
||||
output[10] = 0;
|
||||
|
||||
for (i = 0; i < 10; i += 2) {
|
||||
limb over = div_by_2_26(output[i]);
|
||||
/* The entry condition (that |output[i]| < 280*2^54) means that over is, at
|
||||
* most, 280*2^28 in the first iteration of this loop. This is added to the
|
||||
* next limb and we can approximate the resulting bound of that limb by
|
||||
* 281*2^54. */
|
||||
output[i] -= over << 26;
|
||||
output[i+1] += over;
|
||||
|
||||
/* For the first iteration, |output[i+1]| < 281*2^54, thus |over| <
|
||||
* 281*2^29. When this is added to the next limb, the resulting bound can
|
||||
* be approximated as 281*2^54.
|
||||
*
|
||||
* For subsequent iterations of the loop, 281*2^54 remains a conservative
|
||||
* bound and no overflow occurs. */
|
||||
over = div_by_2_25(output[i+1]);
|
||||
output[i+1] -= over << 25;
|
||||
output[i+2] += over;
|
||||
}
|
||||
/* Now |output[10]| < 281*2^29 and all other coefficients are reduced. */
|
||||
output[0] += output[10] << 4;
|
||||
output[0] += output[10] << 1;
|
||||
output[0] += output[10];
|
||||
|
||||
output[10] = 0;
|
||||
|
||||
/* Now output[1..9] are reduced, and |output[0]| < 2^26 + 19*281*2^29
|
||||
* So |over| will be no more than 2^16. */
|
||||
{
|
||||
limb over = div_by_2_26(output[0]);
|
||||
output[0] -= over << 26;
|
||||
output[1] += over;
|
||||
}
|
||||
|
||||
/* Now output[0,2..9] are reduced, and |output[1]| < 2^25 + 2^16 < 2^26. The
|
||||
* bound on |output[1]| is sufficient to meet our needs. */
|
||||
}
|
||||
|
||||
/* A helpful wrapper around fproduct: output = in * in2.
|
||||
*
|
||||
* On entry: |in[i]| < 2^27 and |in2[i]| < 2^27.
|
||||
*
|
||||
* output must be distinct to both inputs. The output is reduced degree
|
||||
* (indeed, one need only provide storage for 10 limbs) and |output[i]| < 2^26. */
|
||||
static void
|
||||
fmul(limb *output, const limb *in, const limb *in2) {
|
||||
limb t[19];
|
||||
fproduct(t, in, in2);
|
||||
/* |t[i]| < 14*2^54 */
|
||||
freduce_degree(t);
|
||||
freduce_coefficients(t);
|
||||
/* |t[i]| < 2^26 */
|
||||
memcpy(output, t, sizeof(limb) * 10);
|
||||
}
|
||||
|
||||
/* Square a number: output = in**2
|
||||
*
|
||||
* output must be distinct from the input. The inputs are reduced coefficient
|
||||
* form, the output is not.
|
||||
*
|
||||
* output[x] <= 14 * the largest product of the input limbs. */
|
||||
static void fsquare_inner(limb *output, const limb *in) {
|
||||
output[0] = ((limb) ((s32) in[0])) * ((s32) in[0]);
|
||||
output[1] = 2 * ((limb) ((s32) in[0])) * ((s32) in[1]);
|
||||
output[2] = 2 * (((limb) ((s32) in[1])) * ((s32) in[1]) +
|
||||
((limb) ((s32) in[0])) * ((s32) in[2]));
|
||||
output[3] = 2 * (((limb) ((s32) in[1])) * ((s32) in[2]) +
|
||||
((limb) ((s32) in[0])) * ((s32) in[3]));
|
||||
output[4] = ((limb) ((s32) in[2])) * ((s32) in[2]) +
|
||||
4 * ((limb) ((s32) in[1])) * ((s32) in[3]) +
|
||||
2 * ((limb) ((s32) in[0])) * ((s32) in[4]);
|
||||
output[5] = 2 * (((limb) ((s32) in[2])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in[1])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in[0])) * ((s32) in[5]));
|
||||
output[6] = 2 * (((limb) ((s32) in[3])) * ((s32) in[3]) +
|
||||
((limb) ((s32) in[2])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in[0])) * ((s32) in[6]) +
|
||||
2 * ((limb) ((s32) in[1])) * ((s32) in[5]));
|
||||
output[7] = 2 * (((limb) ((s32) in[3])) * ((s32) in[4]) +
|
||||
((limb) ((s32) in[2])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in[1])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in[0])) * ((s32) in[7]));
|
||||
output[8] = ((limb) ((s32) in[4])) * ((s32) in[4]) +
|
||||
2 * (((limb) ((s32) in[2])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in[0])) * ((s32) in[8]) +
|
||||
2 * (((limb) ((s32) in[1])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in[3])) * ((s32) in[5])));
|
||||
output[9] = 2 * (((limb) ((s32) in[4])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in[3])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in[2])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in[1])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in[0])) * ((s32) in[9]));
|
||||
output[10] = 2 * (((limb) ((s32) in[5])) * ((s32) in[5]) +
|
||||
((limb) ((s32) in[4])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in[2])) * ((s32) in[8]) +
|
||||
2 * (((limb) ((s32) in[3])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in[1])) * ((s32) in[9])));
|
||||
output[11] = 2 * (((limb) ((s32) in[5])) * ((s32) in[6]) +
|
||||
((limb) ((s32) in[4])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in[3])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in[2])) * ((s32) in[9]));
|
||||
output[12] = ((limb) ((s32) in[6])) * ((s32) in[6]) +
|
||||
2 * (((limb) ((s32) in[4])) * ((s32) in[8]) +
|
||||
2 * (((limb) ((s32) in[5])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in[3])) * ((s32) in[9])));
|
||||
output[13] = 2 * (((limb) ((s32) in[6])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in[5])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in[4])) * ((s32) in[9]));
|
||||
output[14] = 2 * (((limb) ((s32) in[7])) * ((s32) in[7]) +
|
||||
((limb) ((s32) in[6])) * ((s32) in[8]) +
|
||||
2 * ((limb) ((s32) in[5])) * ((s32) in[9]));
|
||||
output[15] = 2 * (((limb) ((s32) in[7])) * ((s32) in[8]) +
|
||||
((limb) ((s32) in[6])) * ((s32) in[9]));
|
||||
output[16] = ((limb) ((s32) in[8])) * ((s32) in[8]) +
|
||||
4 * ((limb) ((s32) in[7])) * ((s32) in[9]);
|
||||
output[17] = 2 * ((limb) ((s32) in[8])) * ((s32) in[9]);
|
||||
output[18] = 2 * ((limb) ((s32) in[9])) * ((s32) in[9]);
|
||||
}
|
||||
|
||||
/* fsquare sets output = in^2.
|
||||
*
|
||||
* On entry: The |in| argument is in reduced coefficients form and |in[i]| <
|
||||
* 2^27.
|
||||
*
|
||||
* On exit: The |output| argument is in reduced coefficients form (indeed, one
|
||||
* need only provide storage for 10 limbs) and |out[i]| < 2^26. */
|
||||
static void
|
||||
fsquare(limb *output, const limb *in) {
|
||||
limb t[19];
|
||||
fsquare_inner(t, in);
|
||||
/* |t[i]| < 14*2^54 because the largest product of two limbs will be <
|
||||
* 2^(27+27) and fsquare_inner adds together, at most, 14 of those
|
||||
* products. */
|
||||
freduce_degree(t);
|
||||
freduce_coefficients(t);
|
||||
/* |t[i]| < 2^26 */
|
||||
memcpy(output, t, sizeof(limb) * 10);
|
||||
}
|
||||
|
||||
/* Take a little-endian, 32-byte number and expand it into polynomial form */
|
||||
static void
|
||||
fexpand(limb *output, const u8 *input) {
|
||||
#define F(n,start,shift,mask) \
|
||||
output[n] = ((((limb) input[start + 0]) | \
|
||||
((limb) input[start + 1]) << 8 | \
|
||||
((limb) input[start + 2]) << 16 | \
|
||||
((limb) input[start + 3]) << 24) >> shift) & mask;
|
||||
F(0, 0, 0, 0x3ffffff);
|
||||
F(1, 3, 2, 0x1ffffff);
|
||||
F(2, 6, 3, 0x3ffffff);
|
||||
F(3, 9, 5, 0x1ffffff);
|
||||
F(4, 12, 6, 0x3ffffff);
|
||||
F(5, 16, 0, 0x1ffffff);
|
||||
F(6, 19, 1, 0x3ffffff);
|
||||
F(7, 22, 3, 0x1ffffff);
|
||||
F(8, 25, 4, 0x3ffffff);
|
||||
F(9, 28, 6, 0x1ffffff);
|
||||
#undef F
|
||||
}
|
||||
|
||||
#if (-32 >> 1) != -16
|
||||
#error "This code only works when >> does sign-extension on negative numbers"
|
||||
#endif
|
||||
|
||||
/* s32_eq returns 0xffffffff iff a == b and zero otherwise. */
|
||||
static s32 s32_eq(s32 a, s32 b) {
|
||||
a = ~(a ^ b);
|
||||
a &= a << 16;
|
||||
a &= a << 8;
|
||||
a &= a << 4;
|
||||
a &= a << 2;
|
||||
a &= a << 1;
|
||||
return a >> 31;
|
||||
}
|
||||
|
||||
/* s32_gte returns 0xffffffff if a >= b and zero otherwise, where a and b are
|
||||
* both non-negative. */
|
||||
static s32 s32_gte(s32 a, s32 b) {
|
||||
a -= b;
|
||||
/* a >= 0 iff a >= b. */
|
||||
return ~(a >> 31);
|
||||
}
|
||||
|
||||
/* Take a fully reduced polynomial form number and contract it into a
|
||||
* little-endian, 32-byte array.
|
||||
*
|
||||
* On entry: |input_limbs[i]| < 2^26 */
|
||||
static void
|
||||
fcontract(u8 *output, limb *input_limbs) {
|
||||
int i;
|
||||
int j;
|
||||
s32 input[10];
|
||||
s32 mask;
|
||||
|
||||
/* |input_limbs[i]| < 2^26, so it's valid to convert to an s32. */
|
||||
for (i = 0; i < 10; i++) {
|
||||
input[i] = (s32)input_limbs[i];
|
||||
}
|
||||
|
||||
for (j = 0; j < 2; ++j) {
|
||||
for (i = 0; i < 9; ++i) {
|
||||
if ((i & 1) == 1) {
|
||||
/* This calculation is a time-invariant way to make input[i]
|
||||
* non-negative by borrowing from the next-larger limb. */
|
||||
const s32 mask = input[i] >> 31;
|
||||
const s32 carry = -((input[i] & mask) >> 25);
|
||||
input[i] = input[i] + (carry << 25);
|
||||
input[i+1] = input[i+1] - carry;
|
||||
} else {
|
||||
const s32 mask = input[i] >> 31;
|
||||
const s32 carry = -((input[i] & mask) >> 26);
|
||||
input[i] = input[i] + (carry << 26);
|
||||
input[i+1] = input[i+1] - carry;
|
||||
}
|
||||
}
|
||||
|
||||
/* There's no greater limb for input[9] to borrow from, but we can multiply
|
||||
* by 19 and borrow from input[0], which is valid mod 2^255-19. */
|
||||
{
|
||||
const s32 mask = input[9] >> 31;
|
||||
const s32 carry = -((input[9] & mask) >> 25);
|
||||
input[9] = input[9] + (carry << 25);
|
||||
input[0] = input[0] - (carry * 19);
|
||||
}
|
||||
|
||||
/* After the first iteration, input[1..9] are non-negative and fit within
|
||||
* 25 or 26 bits, depending on position. However, input[0] may be
|
||||
* negative. */
|
||||
}
|
||||
|
||||
/* The first borrow-propagation pass above ended with every limb
|
||||
except (possibly) input[0] non-negative.
|
||||
|
||||
If input[0] was negative after the first pass, then it was because of a
|
||||
carry from input[9]. On entry, input[9] < 2^26 so the carry was, at most,
|
||||
one, since (2**26-1) >> 25 = 1. Thus input[0] >= -19.
|
||||
|
||||
In the second pass, each limb is decreased by at most one. Thus the second
|
||||
borrow-propagation pass could only have wrapped around to decrease
|
||||
input[0] again if the first pass left input[0] negative *and* input[1]
|
||||
through input[9] were all zero. In that case, input[1] is now 2^25 - 1,
|
||||
and this last borrow-propagation step will leave input[1] non-negative. */
|
||||
{
|
||||
const s32 mask = input[0] >> 31;
|
||||
const s32 carry = -((input[0] & mask) >> 26);
|
||||
input[0] = input[0] + (carry << 26);
|
||||
input[1] = input[1] - carry;
|
||||
}
|
||||
|
||||
/* All input[i] are now non-negative. However, there might be values between
|
||||
* 2^25 and 2^26 in a limb which is, nominally, 25 bits wide. */
|
||||
for (j = 0; j < 2; j++) {
|
||||
for (i = 0; i < 9; i++) {
|
||||
if ((i & 1) == 1) {
|
||||
const s32 carry = input[i] >> 25;
|
||||
input[i] &= 0x1ffffff;
|
||||
input[i+1] += carry;
|
||||
} else {
|
||||
const s32 carry = input[i] >> 26;
|
||||
input[i] &= 0x3ffffff;
|
||||
input[i+1] += carry;
|
||||
}
|
||||
}
|
||||
|
||||
{
|
||||
const s32 carry = input[9] >> 25;
|
||||
input[9] &= 0x1ffffff;
|
||||
input[0] += 19*carry;
|
||||
}
|
||||
}
|
||||
|
||||
/* If the first carry-chain pass, just above, ended up with a carry from
|
||||
* input[9], and that caused input[0] to be out-of-bounds, then input[0] was
|
||||
* < 2^26 + 2*19, because the carry was, at most, two.
|
||||
*
|
||||
* If the second pass carried from input[9] again then input[0] is < 2*19 and
|
||||
* the input[9] -> input[0] carry didn't push input[0] out of bounds. */
|
||||
|
||||
/* It still remains the case that input might be between 2^255-19 and 2^255.
|
||||
* In this case, input[1..9] must take their maximum value and input[0] must
|
||||
* be >= (2^255-19) & 0x3ffffff, which is 0x3ffffed. */
|
||||
mask = s32_gte(input[0], 0x3ffffed);
|
||||
for (i = 1; i < 10; i++) {
|
||||
if ((i & 1) == 1) {
|
||||
mask &= s32_eq(input[i], 0x1ffffff);
|
||||
} else {
|
||||
mask &= s32_eq(input[i], 0x3ffffff);
|
||||
}
|
||||
}
|
||||
|
||||
/* mask is either 0xffffffff (if input >= 2^255-19) and zero otherwise. Thus
|
||||
* this conditionally subtracts 2^255-19. */
|
||||
input[0] -= mask & 0x3ffffed;
|
||||
|
||||
for (i = 1; i < 10; i++) {
|
||||
if ((i & 1) == 1) {
|
||||
input[i] -= mask & 0x1ffffff;
|
||||
} else {
|
||||
input[i] -= mask & 0x3ffffff;
|
||||
}
|
||||
}
|
||||
|
||||
input[1] <<= 2;
|
||||
input[2] <<= 3;
|
||||
input[3] <<= 5;
|
||||
input[4] <<= 6;
|
||||
input[6] <<= 1;
|
||||
input[7] <<= 3;
|
||||
input[8] <<= 4;
|
||||
input[9] <<= 6;
|
||||
#define F(i, s) \
|
||||
output[s+0] |= input[i] & 0xff; \
|
||||
output[s+1] = (input[i] >> 8) & 0xff; \
|
||||
output[s+2] = (input[i] >> 16) & 0xff; \
|
||||
output[s+3] = (input[i] >> 24) & 0xff;
|
||||
output[0] = 0;
|
||||
output[16] = 0;
|
||||
F(0,0);
|
||||
F(1,3);
|
||||
F(2,6);
|
||||
F(3,9);
|
||||
F(4,12);
|
||||
F(5,16);
|
||||
F(6,19);
|
||||
F(7,22);
|
||||
F(8,25);
|
||||
F(9,28);
|
||||
#undef F
|
||||
}
|
||||
|
||||
/* Input: Q, Q', Q-Q'
|
||||
* Output: 2Q, Q+Q'
|
||||
*
|
||||
* x2 z3: long form
|
||||
* x3 z3: long form
|
||||
* x z: short form, destroyed
|
||||
* xprime zprime: short form, destroyed
|
||||
* qmqp: short form, preserved
|
||||
*
|
||||
* On entry and exit, the absolute value of the limbs of all inputs and outputs
|
||||
* are < 2^26. */
|
||||
static void fmonty(limb *x2, limb *z2, /* output 2Q */
|
||||
limb *x3, limb *z3, /* output Q + Q' */
|
||||
limb *x, limb *z, /* input Q */
|
||||
limb *xprime, limb *zprime, /* input Q' */
|
||||
const limb *qmqp /* input Q - Q' */) {
|
||||
limb origx[10], origxprime[10], zzz[19], xx[19], zz[19], xxprime[19],
|
||||
zzprime[19], zzzprime[19], xxxprime[19];
|
||||
|
||||
memcpy(origx, x, 10 * sizeof(limb));
|
||||
fsum(x, z);
|
||||
/* |x[i]| < 2^27 */
|
||||
fdifference(z, origx); /* does x - z */
|
||||
/* |z[i]| < 2^27 */
|
||||
|
||||
memcpy(origxprime, xprime, sizeof(limb) * 10);
|
||||
fsum(xprime, zprime);
|
||||
/* |xprime[i]| < 2^27 */
|
||||
fdifference(zprime, origxprime);
|
||||
/* |zprime[i]| < 2^27 */
|
||||
fproduct(xxprime, xprime, z);
|
||||
/* |xxprime[i]| < 14*2^54: the largest product of two limbs will be <
|
||||
* 2^(27+27) and fproduct adds together, at most, 14 of those products.
|
||||
* (Approximating that to 2^58 doesn't work out.) */
|
||||
fproduct(zzprime, x, zprime);
|
||||
/* |zzprime[i]| < 14*2^54 */
|
||||
freduce_degree(xxprime);
|
||||
freduce_coefficients(xxprime);
|
||||
/* |xxprime[i]| < 2^26 */
|
||||
freduce_degree(zzprime);
|
||||
freduce_coefficients(zzprime);
|
||||
/* |zzprime[i]| < 2^26 */
|
||||
memcpy(origxprime, xxprime, sizeof(limb) * 10);
|
||||
fsum(xxprime, zzprime);
|
||||
/* |xxprime[i]| < 2^27 */
|
||||
fdifference(zzprime, origxprime);
|
||||
/* |zzprime[i]| < 2^27 */
|
||||
fsquare(xxxprime, xxprime);
|
||||
/* |xxxprime[i]| < 2^26 */
|
||||
fsquare(zzzprime, zzprime);
|
||||
/* |zzzprime[i]| < 2^26 */
|
||||
fproduct(zzprime, zzzprime, qmqp);
|
||||
/* |zzprime[i]| < 14*2^52 */
|
||||
freduce_degree(zzprime);
|
||||
freduce_coefficients(zzprime);
|
||||
/* |zzprime[i]| < 2^26 */
|
||||
memcpy(x3, xxxprime, sizeof(limb) * 10);
|
||||
memcpy(z3, zzprime, sizeof(limb) * 10);
|
||||
|
||||
fsquare(xx, x);
|
||||
/* |xx[i]| < 2^26 */
|
||||
fsquare(zz, z);
|
||||
/* |zz[i]| < 2^26 */
|
||||
fproduct(x2, xx, zz);
|
||||
/* |x2[i]| < 14*2^52 */
|
||||
freduce_degree(x2);
|
||||
freduce_coefficients(x2);
|
||||
/* |x2[i]| < 2^26 */
|
||||
fdifference(zz, xx); // does zz = xx - zz
|
||||
/* |zz[i]| < 2^27 */
|
||||
memset(zzz + 10, 0, sizeof(limb) * 9);
|
||||
fscalar_product(zzz, zz, 121665);
|
||||
/* |zzz[i]| < 2^(27+17) */
|
||||
/* No need to call freduce_degree here:
|
||||
fscalar_product doesn't increase the degree of its input. */
|
||||
freduce_coefficients(zzz);
|
||||
/* |zzz[i]| < 2^26 */
|
||||
fsum(zzz, xx);
|
||||
/* |zzz[i]| < 2^27 */
|
||||
fproduct(z2, zz, zzz);
|
||||
/* |z2[i]| < 14*2^(26+27) */
|
||||
freduce_degree(z2);
|
||||
freduce_coefficients(z2);
|
||||
/* |z2|i| < 2^26 */
|
||||
}
|
||||
|
||||
/* Conditionally swap two reduced-form limb arrays if 'iswap' is 1, but leave
|
||||
* them unchanged if 'iswap' is 0. Runs in data-invariant time to avoid
|
||||
* side-channel attacks.
|
||||
*
|
||||
* NOTE that this function requires that 'iswap' be 1 or 0; other values give
|
||||
* wrong results. Also, the two limb arrays must be in reduced-coefficient,
|
||||
* reduced-degree form: the values in a[10..19] or b[10..19] aren't swapped,
|
||||
* and all all values in a[0..9],b[0..9] must have magnitude less than
|
||||
* INT32_MAX. */
|
||||
static void
|
||||
swap_conditional(limb a[19], limb b[19], limb iswap) {
|
||||
unsigned i;
|
||||
const s32 swap = (s32) -iswap;
|
||||
|
||||
for (i = 0; i < 10; ++i) {
|
||||
const s32 x = swap & ( ((s32)a[i]) ^ ((s32)b[i]) );
|
||||
a[i] = ((s32)a[i]) ^ x;
|
||||
b[i] = ((s32)b[i]) ^ x;
|
||||
}
|
||||
}
|
||||
|
||||
/* Calculates nQ where Q is the x-coordinate of a point on the curve
|
||||
*
|
||||
* resultx/resultz: the x coordinate of the resulting curve point (short form)
|
||||
* n: a little endian, 32-byte number
|
||||
* q: a point of the curve (short form) */
|
||||
static void
|
||||
cmult(limb *resultx, limb *resultz, const u8 *n, const limb *q) {
|
||||
limb a[19] = {0}, b[19] = {1}, c[19] = {1}, d[19] = {0};
|
||||
limb *nqpqx = a, *nqpqz = b, *nqx = c, *nqz = d, *t;
|
||||
limb e[19] = {0}, f[19] = {1}, g[19] = {0}, h[19] = {1};
|
||||
limb *nqpqx2 = e, *nqpqz2 = f, *nqx2 = g, *nqz2 = h;
|
||||
|
||||
unsigned i, j;
|
||||
|
||||
memcpy(nqpqx, q, sizeof(limb) * 10);
|
||||
|
||||
for (i = 0; i < 32; ++i) {
|
||||
u8 byte = n[31 - i];
|
||||
for (j = 0; j < 8; ++j) {
|
||||
const limb bit = byte >> 7;
|
||||
|
||||
swap_conditional(nqx, nqpqx, bit);
|
||||
swap_conditional(nqz, nqpqz, bit);
|
||||
fmonty(nqx2, nqz2,
|
||||
nqpqx2, nqpqz2,
|
||||
nqx, nqz,
|
||||
nqpqx, nqpqz,
|
||||
q);
|
||||
swap_conditional(nqx2, nqpqx2, bit);
|
||||
swap_conditional(nqz2, nqpqz2, bit);
|
||||
|
||||
t = nqx;
|
||||
nqx = nqx2;
|
||||
nqx2 = t;
|
||||
t = nqz;
|
||||
nqz = nqz2;
|
||||
nqz2 = t;
|
||||
t = nqpqx;
|
||||
nqpqx = nqpqx2;
|
||||
nqpqx2 = t;
|
||||
t = nqpqz;
|
||||
nqpqz = nqpqz2;
|
||||
nqpqz2 = t;
|
||||
|
||||
byte <<= 1;
|
||||
}
|
||||
}
|
||||
|
||||
memcpy(resultx, nqx, sizeof(limb) * 10);
|
||||
memcpy(resultz, nqz, sizeof(limb) * 10);
|
||||
}
|
||||
|
||||
// -----------------------------------------------------------------------------
|
||||
// Shamelessly copied from djb's code
|
||||
// -----------------------------------------------------------------------------
|
||||
static void
|
||||
crecip(limb *out, const limb *z) {
|
||||
limb z2[10];
|
||||
limb z9[10];
|
||||
limb z11[10];
|
||||
limb z2_5_0[10];
|
||||
limb z2_10_0[10];
|
||||
limb z2_20_0[10];
|
||||
limb z2_50_0[10];
|
||||
limb z2_100_0[10];
|
||||
limb t0[10];
|
||||
limb t1[10];
|
||||
int i;
|
||||
|
||||
/* 2 */ fsquare(z2,z);
|
||||
/* 4 */ fsquare(t1,z2);
|
||||
/* 8 */ fsquare(t0,t1);
|
||||
/* 9 */ fmul(z9,t0,z);
|
||||
/* 11 */ fmul(z11,z9,z2);
|
||||
/* 22 */ fsquare(t0,z11);
|
||||
/* 2^5 - 2^0 = 31 */ fmul(z2_5_0,t0,z9);
|
||||
|
||||
/* 2^6 - 2^1 */ fsquare(t0,z2_5_0);
|
||||
/* 2^7 - 2^2 */ fsquare(t1,t0);
|
||||
/* 2^8 - 2^3 */ fsquare(t0,t1);
|
||||
/* 2^9 - 2^4 */ fsquare(t1,t0);
|
||||
/* 2^10 - 2^5 */ fsquare(t0,t1);
|
||||
/* 2^10 - 2^0 */ fmul(z2_10_0,t0,z2_5_0);
|
||||
|
||||
/* 2^11 - 2^1 */ fsquare(t0,z2_10_0);
|
||||
/* 2^12 - 2^2 */ fsquare(t1,t0);
|
||||
/* 2^20 - 2^10 */ for (i = 2;i < 10;i += 2) { fsquare(t0,t1); fsquare(t1,t0); }
|
||||
/* 2^20 - 2^0 */ fmul(z2_20_0,t1,z2_10_0);
|
||||
|
||||
/* 2^21 - 2^1 */ fsquare(t0,z2_20_0);
|
||||
/* 2^22 - 2^2 */ fsquare(t1,t0);
|
||||
/* 2^40 - 2^20 */ for (i = 2;i < 20;i += 2) { fsquare(t0,t1); fsquare(t1,t0); }
|
||||
/* 2^40 - 2^0 */ fmul(t0,t1,z2_20_0);
|
||||
|
||||
/* 2^41 - 2^1 */ fsquare(t1,t0);
|
||||
/* 2^42 - 2^2 */ fsquare(t0,t1);
|
||||
/* 2^50 - 2^10 */ for (i = 2;i < 10;i += 2) { fsquare(t1,t0); fsquare(t0,t1); }
|
||||
/* 2^50 - 2^0 */ fmul(z2_50_0,t0,z2_10_0);
|
||||
|
||||
/* 2^51 - 2^1 */ fsquare(t0,z2_50_0);
|
||||
/* 2^52 - 2^2 */ fsquare(t1,t0);
|
||||
/* 2^100 - 2^50 */ for (i = 2;i < 50;i += 2) { fsquare(t0,t1); fsquare(t1,t0); }
|
||||
/* 2^100 - 2^0 */ fmul(z2_100_0,t1,z2_50_0);
|
||||
|
||||
/* 2^101 - 2^1 */ fsquare(t1,z2_100_0);
|
||||
/* 2^102 - 2^2 */ fsquare(t0,t1);
|
||||
/* 2^200 - 2^100 */ for (i = 2;i < 100;i += 2) { fsquare(t1,t0); fsquare(t0,t1); }
|
||||
/* 2^200 - 2^0 */ fmul(t1,t0,z2_100_0);
|
||||
|
||||
/* 2^201 - 2^1 */ fsquare(t0,t1);
|
||||
/* 2^202 - 2^2 */ fsquare(t1,t0);
|
||||
/* 2^250 - 2^50 */ for (i = 2;i < 50;i += 2) { fsquare(t0,t1); fsquare(t1,t0); }
|
||||
/* 2^250 - 2^0 */ fmul(t0,t1,z2_50_0);
|
||||
|
||||
/* 2^251 - 2^1 */ fsquare(t1,t0);
|
||||
/* 2^252 - 2^2 */ fsquare(t0,t1);
|
||||
/* 2^253 - 2^3 */ fsquare(t1,t0);
|
||||
/* 2^254 - 2^4 */ fsquare(t0,t1);
|
||||
/* 2^255 - 2^5 */ fsquare(t1,t0);
|
||||
/* 2^255 - 21 */ fmul(out,t1,z11);
|
||||
}
|
||||
|
||||
int
|
||||
curve25519_donna(u8 *mypublic, const u8 *secret, const u8 *basepoint) {
|
||||
limb bp[10], x[10], z[11], zmone[10];
|
||||
uint8_t e[32];
|
||||
int i;
|
||||
|
||||
for (i = 0; i < 32; ++i) e[i] = secret[i];
|
||||
e[0] &= 248;
|
||||
e[31] &= 127;
|
||||
e[31] |= 64;
|
||||
|
||||
fexpand(bp, basepoint);
|
||||
cmult(x, z, e, bp);
|
||||
crecip(zmone, z);
|
||||
fmul(z, x, zmone);
|
||||
fcontract(mypublic, z);
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
#ifndef __curve25519_donnaDotH__
|
||||
#define __curve25519_donnaDotH__
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
void curve25519_donna( unsigned char *outKey, const unsigned char *inSecret, const unsigned char *inBasePoint );
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif // __curve25519_donnaDotH__
|
||||
583
tools/wigadget/iOS/WiGadget/WiGadget/Crypto/TinyAES128/aes.c
Normal file
583
tools/wigadget/iOS/WiGadget/WiGadget/Crypto/TinyAES128/aes.c
Normal file
|
|
@ -0,0 +1,583 @@
|
|||
/*
|
||||
|
||||
This is an implementation of the AES128 algorithm, specifically ECB and CBC mode.
|
||||
|
||||
The implementation is verified against the test vectors in:
|
||||
National Institute of Standards and Technology Special Publication 800-38A 2001 ED
|
||||
|
||||
ECB-AES128
|
||||
----------
|
||||
|
||||
plain-text:
|
||||
6bc1bee22e409f96e93d7e117393172a
|
||||
ae2d8a571e03ac9c9eb76fac45af8e51
|
||||
30c81c46a35ce411e5fbc1191a0a52ef
|
||||
f69f2445df4f9b17ad2b417be66c3710
|
||||
|
||||
key:
|
||||
2b7e151628aed2a6abf7158809cf4f3c
|
||||
|
||||
resulting cipher
|
||||
3ad77bb40d7a3660a89ecaf32466ef97
|
||||
f5d3d58503b9699de785895a96fdbaaf
|
||||
43b1cd7f598ece23881b00e3ed030688
|
||||
7b0c785e27e8ad3f8223207104725dd4
|
||||
|
||||
|
||||
NOTE: String length must be evenly divisible by 16byte (str_len % 16 == 0)
|
||||
You should pad the end of the string with zeros if this is not the case.
|
||||
|
||||
*/
|
||||
|
||||
|
||||
/*****************************************************************************/
|
||||
/* Includes: */
|
||||
/*****************************************************************************/
|
||||
#include <stdint.h>
|
||||
#include <string.h> // CBC mode, for memset
|
||||
#include "aes.h"
|
||||
|
||||
|
||||
/*****************************************************************************/
|
||||
/* Defines: */
|
||||
/*****************************************************************************/
|
||||
// The number of columns comprising a state in AES. This is a constant in AES. Value=4
|
||||
#define Nb 4
|
||||
// The number of 32 bit words in a key.
|
||||
#define Nk 4
|
||||
// Key length in bytes [128 bit]
|
||||
#define KEYLEN 16
|
||||
// The number of rounds in AES Cipher.
|
||||
#define Nr 10
|
||||
|
||||
// jcallan@github points out that declaring Multiply as a function
|
||||
// reduces code size considerably with the Keil ARM compiler.
|
||||
// See this link for more information: https://github.com/kokke/tiny-AES128-C/pull/3
|
||||
#ifndef MULTIPLY_AS_A_FUNCTION
|
||||
#define MULTIPLY_AS_A_FUNCTION 0
|
||||
#endif
|
||||
|
||||
|
||||
/*****************************************************************************/
|
||||
/* Private variables: */
|
||||
/*****************************************************************************/
|
||||
// state - array holding the intermediate results during decryption.
|
||||
typedef uint8_t state_t[4][4];
|
||||
static state_t* state;
|
||||
|
||||
// The array that stores the round keys.
|
||||
static uint8_t RoundKey[176];
|
||||
|
||||
// The Key input to the AES Program
|
||||
static const uint8_t* Key;
|
||||
|
||||
#if defined(CBC) && CBC
|
||||
// Initial Vector used only for CBC mode
|
||||
static uint8_t* Iv;
|
||||
#endif
|
||||
|
||||
// The lookup-tables are marked const so they can be placed in read-only storage instead of RAM
|
||||
// The numbers below can be computed dynamically trading ROM for RAM -
|
||||
// This can be useful in (embedded) bootloader applications, where ROM is often limited.
|
||||
static const uint8_t sbox[256] = {
|
||||
//0 1 2 3 4 5 6 7 8 9 A B C D E F
|
||||
0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5, 0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76,
|
||||
0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0, 0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0,
|
||||
0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc, 0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15,
|
||||
0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a, 0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75,
|
||||
0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0, 0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84,
|
||||
0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b, 0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf,
|
||||
0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85, 0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8,
|
||||
0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5, 0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2,
|
||||
0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17, 0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73,
|
||||
0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88, 0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb,
|
||||
0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c, 0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79,
|
||||
0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9, 0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08,
|
||||
0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6, 0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a,
|
||||
0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e, 0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e,
|
||||
0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf,
|
||||
0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16 };
|
||||
|
||||
static const uint8_t rsbox[256] =
|
||||
{ 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb,
|
||||
0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87, 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb,
|
||||
0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d, 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e,
|
||||
0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2, 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25,
|
||||
0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16, 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92,
|
||||
0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda, 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84,
|
||||
0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a, 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06,
|
||||
0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02, 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b,
|
||||
0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea, 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73,
|
||||
0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85, 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e,
|
||||
0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89, 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b,
|
||||
0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20, 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4,
|
||||
0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31, 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f,
|
||||
0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
|
||||
0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
|
||||
0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d };
|
||||
|
||||
|
||||
// The round constant word array, Rcon[i], contains the values given by
|
||||
// x to th e power (i-1) being powers of x (x is denoted as {02}) in the field GF(2^8)
|
||||
// Note that i starts at 1, not 0).
|
||||
static const uint8_t Rcon[255] = {
|
||||
0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a,
|
||||
0x2f, 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35, 0x6a, 0xd4, 0xb3, 0x7d, 0xfa, 0xef, 0xc5, 0x91, 0x39,
|
||||
0x72, 0xe4, 0xd3, 0xbd, 0x61, 0xc2, 0x9f, 0x25, 0x4a, 0x94, 0x33, 0x66, 0xcc, 0x83, 0x1d, 0x3a,
|
||||
0x74, 0xe8, 0xcb, 0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36, 0x6c, 0xd8,
|
||||
0xab, 0x4d, 0x9a, 0x2f, 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35, 0x6a, 0xd4, 0xb3, 0x7d, 0xfa, 0xef,
|
||||
0xc5, 0x91, 0x39, 0x72, 0xe4, 0xd3, 0xbd, 0x61, 0xc2, 0x9f, 0x25, 0x4a, 0x94, 0x33, 0x66, 0xcc,
|
||||
0x83, 0x1d, 0x3a, 0x74, 0xe8, 0xcb, 0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b,
|
||||
0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a, 0x2f, 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35, 0x6a, 0xd4, 0xb3,
|
||||
0x7d, 0xfa, 0xef, 0xc5, 0x91, 0x39, 0x72, 0xe4, 0xd3, 0xbd, 0x61, 0xc2, 0x9f, 0x25, 0x4a, 0x94,
|
||||
0x33, 0x66, 0xcc, 0x83, 0x1d, 0x3a, 0x74, 0xe8, 0xcb, 0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20,
|
||||
0x40, 0x80, 0x1b, 0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a, 0x2f, 0x5e, 0xbc, 0x63, 0xc6, 0x97, 0x35,
|
||||
0x6a, 0xd4, 0xb3, 0x7d, 0xfa, 0xef, 0xc5, 0x91, 0x39, 0x72, 0xe4, 0xd3, 0xbd, 0x61, 0xc2, 0x9f,
|
||||
0x25, 0x4a, 0x94, 0x33, 0x66, 0xcc, 0x83, 0x1d, 0x3a, 0x74, 0xe8, 0xcb, 0x8d, 0x01, 0x02, 0x04,
|
||||
0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36, 0x6c, 0xd8, 0xab, 0x4d, 0x9a, 0x2f, 0x5e, 0xbc, 0x63,
|
||||
0xc6, 0x97, 0x35, 0x6a, 0xd4, 0xb3, 0x7d, 0xfa, 0xef, 0xc5, 0x91, 0x39, 0x72, 0xe4, 0xd3, 0xbd,
|
||||
0x61, 0xc2, 0x9f, 0x25, 0x4a, 0x94, 0x33, 0x66, 0xcc, 0x83, 0x1d, 0x3a, 0x74, 0xe8, 0xcb };
|
||||
|
||||
|
||||
/*****************************************************************************/
|
||||
/* Private functions: */
|
||||
/*****************************************************************************/
|
||||
static uint8_t getSBoxValue(uint8_t num)
|
||||
{
|
||||
return sbox[num];
|
||||
}
|
||||
|
||||
static uint8_t getSBoxInvert(uint8_t num)
|
||||
{
|
||||
return rsbox[num];
|
||||
}
|
||||
|
||||
// This function produces Nb(Nr+1) round keys. The round keys are used in each round to decrypt the states.
|
||||
static void KeyExpansion(void)
|
||||
{
|
||||
uint32_t i, j, k;
|
||||
uint8_t tempa[4]; // Used for the column/row operations
|
||||
|
||||
// The first round key is the key itself.
|
||||
for(i = 0; i < Nk; ++i)
|
||||
{
|
||||
RoundKey[(i * 4) + 0] = Key[(i * 4) + 0];
|
||||
RoundKey[(i * 4) + 1] = Key[(i * 4) + 1];
|
||||
RoundKey[(i * 4) + 2] = Key[(i * 4) + 2];
|
||||
RoundKey[(i * 4) + 3] = Key[(i * 4) + 3];
|
||||
}
|
||||
|
||||
// All other round keys are found from the previous round keys.
|
||||
for(; (i < (Nb * (Nr + 1))); ++i)
|
||||
{
|
||||
for(j = 0; j < 4; ++j)
|
||||
{
|
||||
tempa[j]=RoundKey[(i-1) * 4 + j];
|
||||
}
|
||||
if (i % Nk == 0)
|
||||
{
|
||||
// This function rotates the 4 bytes in a word to the left once.
|
||||
// [a0,a1,a2,a3] becomes [a1,a2,a3,a0]
|
||||
|
||||
// Function RotWord()
|
||||
{
|
||||
k = tempa[0];
|
||||
tempa[0] = tempa[1];
|
||||
tempa[1] = tempa[2];
|
||||
tempa[2] = tempa[3];
|
||||
tempa[3] = k;
|
||||
}
|
||||
|
||||
// SubWord() is a function that takes a four-byte input word and
|
||||
// applies the S-box to each of the four bytes to produce an output word.
|
||||
|
||||
// Function Subword()
|
||||
{
|
||||
tempa[0] = getSBoxValue(tempa[0]);
|
||||
tempa[1] = getSBoxValue(tempa[1]);
|
||||
tempa[2] = getSBoxValue(tempa[2]);
|
||||
tempa[3] = getSBoxValue(tempa[3]);
|
||||
}
|
||||
|
||||
tempa[0] = tempa[0] ^ Rcon[i/Nk];
|
||||
}
|
||||
else if (Nk > 6 && i % Nk == 4)
|
||||
{
|
||||
// Function Subword()
|
||||
{
|
||||
tempa[0] = getSBoxValue(tempa[0]);
|
||||
tempa[1] = getSBoxValue(tempa[1]);
|
||||
tempa[2] = getSBoxValue(tempa[2]);
|
||||
tempa[3] = getSBoxValue(tempa[3]);
|
||||
}
|
||||
}
|
||||
RoundKey[i * 4 + 0] = RoundKey[(i - Nk) * 4 + 0] ^ tempa[0];
|
||||
RoundKey[i * 4 + 1] = RoundKey[(i - Nk) * 4 + 1] ^ tempa[1];
|
||||
RoundKey[i * 4 + 2] = RoundKey[(i - Nk) * 4 + 2] ^ tempa[2];
|
||||
RoundKey[i * 4 + 3] = RoundKey[(i - Nk) * 4 + 3] ^ tempa[3];
|
||||
}
|
||||
}
|
||||
|
||||
// This function adds the round key to state.
|
||||
// The round key is added to the state by an XOR function.
|
||||
static void AddRoundKey(uint8_t round)
|
||||
{
|
||||
uint8_t i,j;
|
||||
for(i=0;i<4;++i)
|
||||
{
|
||||
for(j = 0; j < 4; ++j)
|
||||
{
|
||||
(*state)[i][j] ^= RoundKey[round * Nb * 4 + i * Nb + j];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The SubBytes Function Substitutes the values in the
|
||||
// state matrix with values in an S-box.
|
||||
static void SubBytes(void)
|
||||
{
|
||||
uint8_t i, j;
|
||||
for(i = 0; i < 4; ++i)
|
||||
{
|
||||
for(j = 0; j < 4; ++j)
|
||||
{
|
||||
(*state)[j][i] = getSBoxValue((*state)[j][i]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// The ShiftRows() function shifts the rows in the state to the left.
|
||||
// Each row is shifted with different offset.
|
||||
// Offset = Row number. So the first row is not shifted.
|
||||
static void ShiftRows(void)
|
||||
{
|
||||
uint8_t temp;
|
||||
|
||||
// Rotate first row 1 columns to left
|
||||
temp = (*state)[0][1];
|
||||
(*state)[0][1] = (*state)[1][1];
|
||||
(*state)[1][1] = (*state)[2][1];
|
||||
(*state)[2][1] = (*state)[3][1];
|
||||
(*state)[3][1] = temp;
|
||||
|
||||
// Rotate second row 2 columns to left
|
||||
temp = (*state)[0][2];
|
||||
(*state)[0][2] = (*state)[2][2];
|
||||
(*state)[2][2] = temp;
|
||||
|
||||
temp = (*state)[1][2];
|
||||
(*state)[1][2] = (*state)[3][2];
|
||||
(*state)[3][2] = temp;
|
||||
|
||||
// Rotate third row 3 columns to left
|
||||
temp = (*state)[0][3];
|
||||
(*state)[0][3] = (*state)[3][3];
|
||||
(*state)[3][3] = (*state)[2][3];
|
||||
(*state)[2][3] = (*state)[1][3];
|
||||
(*state)[1][3] = temp;
|
||||
}
|
||||
|
||||
static uint8_t xtime(uint8_t x)
|
||||
{
|
||||
return ((x<<1) ^ (((x>>7) & 1) * 0x1b));
|
||||
}
|
||||
|
||||
// MixColumns function mixes the columns of the state matrix
|
||||
static void MixColumns(void)
|
||||
{
|
||||
uint8_t i;
|
||||
uint8_t Tmp,Tm,t;
|
||||
for(i = 0; i < 4; ++i)
|
||||
{
|
||||
t = (*state)[i][0];
|
||||
Tmp = (*state)[i][0] ^ (*state)[i][1] ^ (*state)[i][2] ^ (*state)[i][3] ;
|
||||
Tm = (*state)[i][0] ^ (*state)[i][1] ; Tm = xtime(Tm); (*state)[i][0] ^= Tm ^ Tmp ;
|
||||
Tm = (*state)[i][1] ^ (*state)[i][2] ; Tm = xtime(Tm); (*state)[i][1] ^= Tm ^ Tmp ;
|
||||
Tm = (*state)[i][2] ^ (*state)[i][3] ; Tm = xtime(Tm); (*state)[i][2] ^= Tm ^ Tmp ;
|
||||
Tm = (*state)[i][3] ^ t ; Tm = xtime(Tm); (*state)[i][3] ^= Tm ^ Tmp ;
|
||||
}
|
||||
}
|
||||
|
||||
// Multiply is used to multiply numbers in the field GF(2^8)
|
||||
#if MULTIPLY_AS_A_FUNCTION
|
||||
static uint8_t Multiply(uint8_t x, uint8_t y)
|
||||
{
|
||||
return (((y & 1) * x) ^
|
||||
((y>>1 & 1) * xtime(x)) ^
|
||||
((y>>2 & 1) * xtime(xtime(x))) ^
|
||||
((y>>3 & 1) * xtime(xtime(xtime(x)))) ^
|
||||
((y>>4 & 1) * xtime(xtime(xtime(xtime(x))))));
|
||||
}
|
||||
#else
|
||||
#define Multiply(x, y) \
|
||||
( ((y & 1) * x) ^ \
|
||||
((y>>1 & 1) * xtime(x)) ^ \
|
||||
((y>>2 & 1) * xtime(xtime(x))) ^ \
|
||||
((y>>3 & 1) * xtime(xtime(xtime(x)))) ^ \
|
||||
((y>>4 & 1) * xtime(xtime(xtime(xtime(x)))))) \
|
||||
|
||||
#endif
|
||||
|
||||
// MixColumns function mixes the columns of the state matrix.
|
||||
// The method used to multiply may be difficult to understand for the inexperienced.
|
||||
// Please use the references to gain more information.
|
||||
static void InvMixColumns(void)
|
||||
{
|
||||
int i;
|
||||
uint8_t a,b,c,d;
|
||||
for(i=0;i<4;++i)
|
||||
{
|
||||
a = (*state)[i][0];
|
||||
b = (*state)[i][1];
|
||||
c = (*state)[i][2];
|
||||
d = (*state)[i][3];
|
||||
|
||||
(*state)[i][0] = Multiply(a, 0x0e) ^ Multiply(b, 0x0b) ^ Multiply(c, 0x0d) ^ Multiply(d, 0x09);
|
||||
(*state)[i][1] = Multiply(a, 0x09) ^ Multiply(b, 0x0e) ^ Multiply(c, 0x0b) ^ Multiply(d, 0x0d);
|
||||
(*state)[i][2] = Multiply(a, 0x0d) ^ Multiply(b, 0x09) ^ Multiply(c, 0x0e) ^ Multiply(d, 0x0b);
|
||||
(*state)[i][3] = Multiply(a, 0x0b) ^ Multiply(b, 0x0d) ^ Multiply(c, 0x09) ^ Multiply(d, 0x0e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// The SubBytes Function Substitutes the values in the
|
||||
// state matrix with values in an S-box.
|
||||
static void InvSubBytes(void)
|
||||
{
|
||||
uint8_t i,j;
|
||||
for(i=0;i<4;++i)
|
||||
{
|
||||
for(j=0;j<4;++j)
|
||||
{
|
||||
(*state)[j][i] = getSBoxInvert((*state)[j][i]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static void InvShiftRows(void)
|
||||
{
|
||||
uint8_t temp;
|
||||
|
||||
// Rotate first row 1 columns to right
|
||||
temp=(*state)[3][1];
|
||||
(*state)[3][1]=(*state)[2][1];
|
||||
(*state)[2][1]=(*state)[1][1];
|
||||
(*state)[1][1]=(*state)[0][1];
|
||||
(*state)[0][1]=temp;
|
||||
|
||||
// Rotate second row 2 columns to right
|
||||
temp=(*state)[0][2];
|
||||
(*state)[0][2]=(*state)[2][2];
|
||||
(*state)[2][2]=temp;
|
||||
|
||||
temp=(*state)[1][2];
|
||||
(*state)[1][2]=(*state)[3][2];
|
||||
(*state)[3][2]=temp;
|
||||
|
||||
// Rotate third row 3 columns to right
|
||||
temp=(*state)[0][3];
|
||||
(*state)[0][3]=(*state)[1][3];
|
||||
(*state)[1][3]=(*state)[2][3];
|
||||
(*state)[2][3]=(*state)[3][3];
|
||||
(*state)[3][3]=temp;
|
||||
}
|
||||
|
||||
|
||||
// Cipher is the main function that encrypts the PlainText.
|
||||
static void Cipher(void)
|
||||
{
|
||||
uint8_t round = 0;
|
||||
|
||||
// Add the First round key to the state before starting the rounds.
|
||||
AddRoundKey(0);
|
||||
|
||||
// There will be Nr rounds.
|
||||
// The first Nr-1 rounds are identical.
|
||||
// These Nr-1 rounds are executed in the loop below.
|
||||
for(round = 1; round < Nr; ++round)
|
||||
{
|
||||
SubBytes();
|
||||
ShiftRows();
|
||||
MixColumns();
|
||||
AddRoundKey(round);
|
||||
}
|
||||
|
||||
// The last round is given below.
|
||||
// The MixColumns function is not here in the last round.
|
||||
SubBytes();
|
||||
ShiftRows();
|
||||
AddRoundKey(Nr);
|
||||
}
|
||||
|
||||
static void InvCipher(void)
|
||||
{
|
||||
uint8_t round=0;
|
||||
|
||||
// Add the First round key to the state before starting the rounds.
|
||||
AddRoundKey(Nr);
|
||||
|
||||
// There will be Nr rounds.
|
||||
// The first Nr-1 rounds are identical.
|
||||
// These Nr-1 rounds are executed in the loop below.
|
||||
for(round=Nr-1;round>0;round--)
|
||||
{
|
||||
InvShiftRows();
|
||||
InvSubBytes();
|
||||
AddRoundKey(round);
|
||||
InvMixColumns();
|
||||
}
|
||||
|
||||
// The last round is given below.
|
||||
// The MixColumns function is not here in the last round.
|
||||
InvShiftRows();
|
||||
InvSubBytes();
|
||||
AddRoundKey(0);
|
||||
}
|
||||
|
||||
static void BlockCopy(uint8_t* output, uint8_t* input)
|
||||
{
|
||||
uint8_t i;
|
||||
for (i=0;i<KEYLEN;++i)
|
||||
{
|
||||
output[i] = input[i];
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
/*****************************************************************************/
|
||||
/* Public functions: */
|
||||
/*****************************************************************************/
|
||||
#if defined(ECB) && ECB
|
||||
|
||||
|
||||
void AES128_ECB_encrypt(uint8_t* input, const uint8_t* key, uint8_t* output)
|
||||
{
|
||||
// Copy input to output, and work in-memory on output
|
||||
BlockCopy(output, input);
|
||||
state = (state_t*)output;
|
||||
|
||||
Key = key;
|
||||
KeyExpansion();
|
||||
|
||||
// The next function call encrypts the PlainText with the Key using AES algorithm.
|
||||
Cipher();
|
||||
}
|
||||
|
||||
void AES128_ECB_decrypt(uint8_t* input, const uint8_t* key, uint8_t *output)
|
||||
{
|
||||
// Copy input to output, and work in-memory on output
|
||||
BlockCopy(output, input);
|
||||
state = (state_t*)output;
|
||||
|
||||
// The KeyExpansion routine must be called before encryption.
|
||||
Key = key;
|
||||
KeyExpansion();
|
||||
|
||||
InvCipher();
|
||||
}
|
||||
|
||||
|
||||
#endif // #if defined(ECB) && ECB
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
#if defined(CBC) && CBC
|
||||
|
||||
|
||||
static void XorWithIv(uint8_t* buf)
|
||||
{
|
||||
uint8_t i;
|
||||
for(i = 0; i < KEYLEN; ++i)
|
||||
{
|
||||
buf[i] ^= Iv[i];
|
||||
}
|
||||
}
|
||||
|
||||
void AES128_CBC_encrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length, const uint8_t* key, const uint8_t* iv)
|
||||
{
|
||||
uintptr_t i;
|
||||
uint8_t remainders = length % KEYLEN; /* Remaining bytes in the last non-full block */
|
||||
|
||||
BlockCopy(output, input);
|
||||
state = (state_t*)output;
|
||||
|
||||
// Skip the key expansion if key is passed as 0
|
||||
if(0 != key)
|
||||
{
|
||||
Key = key;
|
||||
KeyExpansion();
|
||||
}
|
||||
|
||||
if(iv != 0)
|
||||
{
|
||||
Iv = (uint8_t*)iv;
|
||||
}
|
||||
|
||||
for(i = 0; i < length; i += KEYLEN)
|
||||
{
|
||||
XorWithIv(input);
|
||||
BlockCopy(output, input);
|
||||
state = (state_t*)output;
|
||||
Cipher();
|
||||
Iv = output;
|
||||
input += KEYLEN;
|
||||
output += KEYLEN;
|
||||
}
|
||||
|
||||
if(remainders)
|
||||
{
|
||||
BlockCopy(output, input);
|
||||
memset(output + remainders, 0, KEYLEN - remainders); /* add 0-padding */
|
||||
state = (state_t*)output;
|
||||
Cipher();
|
||||
}
|
||||
}
|
||||
|
||||
void AES128_CBC_decrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length, const uint8_t* key, const uint8_t* iv)
|
||||
{
|
||||
uintptr_t i;
|
||||
uint8_t remainders = length % KEYLEN; /* Remaining bytes in the last non-full block */
|
||||
|
||||
BlockCopy(output, input);
|
||||
state = (state_t*)output;
|
||||
|
||||
// Skip the key expansion if key is passed as 0
|
||||
if(0 != key)
|
||||
{
|
||||
Key = key;
|
||||
KeyExpansion();
|
||||
}
|
||||
|
||||
// If iv is passed as 0, we continue to encrypt without re-setting the Iv
|
||||
if(iv != 0)
|
||||
{
|
||||
Iv = (uint8_t*)iv;
|
||||
}
|
||||
|
||||
for(i = 0; i < length; i += KEYLEN)
|
||||
{
|
||||
BlockCopy(output, input);
|
||||
state = (state_t*)output;
|
||||
InvCipher();
|
||||
XorWithIv(output);
|
||||
Iv = input;
|
||||
input += KEYLEN;
|
||||
output += KEYLEN;
|
||||
}
|
||||
|
||||
if(remainders)
|
||||
{
|
||||
BlockCopy(output, input);
|
||||
memset(output+remainders, 0, KEYLEN - remainders); /* add 0-padding */
|
||||
state = (state_t*)output;
|
||||
InvCipher();
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
#endif // #if defined(CBC) && CBC
|
||||
|
||||
|
||||
40
tools/wigadget/iOS/WiGadget/WiGadget/Crypto/TinyAES128/aes.h
Normal file
40
tools/wigadget/iOS/WiGadget/WiGadget/Crypto/TinyAES128/aes.h
Normal file
|
|
@ -0,0 +1,40 @@
|
|||
#ifndef _AES_H_
|
||||
#define _AES_H_
|
||||
|
||||
#include <stdint.h>
|
||||
|
||||
|
||||
// #define the macros below to 1/0 to enable/disable the mode of operation.
|
||||
//
|
||||
// CBC enables AES128 encryption in CBC-mode of operation and handles 0-padding.
|
||||
// ECB enables the basic ECB 16-byte block algorithm. Both can be enabled simultaneously.
|
||||
|
||||
// The #ifndef-guard allows it to be configured before #include'ing or at compile time.
|
||||
#ifndef CBC
|
||||
#define CBC 1
|
||||
#endif
|
||||
|
||||
#ifndef ECB
|
||||
#define ECB 1
|
||||
#endif
|
||||
|
||||
|
||||
|
||||
#if defined(ECB) && ECB
|
||||
|
||||
void AES128_ECB_encrypt(uint8_t* input, const uint8_t* key, uint8_t *output);
|
||||
void AES128_ECB_decrypt(uint8_t* input, const uint8_t* key, uint8_t *output);
|
||||
|
||||
#endif // #if defined(ECB) && ECB
|
||||
|
||||
|
||||
#if defined(CBC) && CBC
|
||||
|
||||
void AES128_CBC_encrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length, const uint8_t* key, const uint8_t* iv);
|
||||
void AES128_CBC_decrypt_buffer(uint8_t* output, uint8_t* input, uint32_t length, const uint8_t* key, const uint8_t* iv);
|
||||
|
||||
#endif // #if defined(CBC) && CBC
|
||||
|
||||
|
||||
|
||||
#endif //_AES_H_
|
||||
Loading…
Add table
Add a link
Reference in a new issue