mirror of
https://github.com/nadoo/glider.git
synced 2026-11-20 07:29:42 +08:00
general: add vendor folder
This commit is contained in:
1 parent
621e8ed018
commit
3c766d0b68
103 files changed
+18061
-19
No files matched your search
+27
@@ -0,0 +1,27 @@
|
||||
Copyright (c) 2009 The Go Authors. 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.
|
||||
+22
@@ -0,0 +1,22 @@
|
||||
Additional IP Rights Grant (Patents)
|
||||
|
||||
"This implementation" means the copyrightable works distributed by
|
||||
Google as part of the Go project.
|
||||
|
||||
Google hereby grants to You a perpetual, worldwide, non-exclusive,
|
||||
no-charge, royalty-free, irrevocable (except as stated in this section)
|
||||
patent license to make, have made, use, offer to sell, sell, import,
|
||||
transfer and otherwise run, modify and propagate the contents of this
|
||||
implementation of Go, where such license applies only to those patent
|
||||
claims, both currently owned or controlled by Google and acquired in
|
||||
the future, licensable by Google that are necessarily infringed by this
|
||||
implementation of Go. This grant does not include claims that would be
|
||||
infringed only as a consequence of further modification of this
|
||||
implementation. If you or your agent or exclusive licensee institute or
|
||||
order or agree to the institution of patent litigation against any
|
||||
entity (including a cross-claim or counterclaim in a lawsuit) alleging
|
||||
that this implementation of Go or any code incorporated within this
|
||||
implementation of Go constitutes direct or contributory patent
|
||||
infringement, or inducement of patent infringement, then any patent
|
||||
rights granted to you under this License for this implementation of Go
|
||||
shall terminate as of the date such litigation is filed.
|
||||
+159
@@ -0,0 +1,159 @@
|
||||
// Copyright 2010 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
package blowfish
|
||||
|
||||
// getNextWord returns the next big-endian uint32 value from the byte slice
|
||||
// at the given position in a circular manner, updating the position.
|
||||
func getNextWord(b []byte, pos *int) uint32 {
|
||||
var w uint32
|
||||
j := *pos
|
||||
for i := 0; i < 4; i++ {
|
||||
w = w<<8 | uint32(b[j])
|
||||
j++
|
||||
if j >= len(b) {
|
||||
j = 0
|
||||
}
|
||||
}
|
||||
*pos = j
|
||||
return w
|
||||
}
|
||||
|
||||
// ExpandKey performs a key expansion on the given *Cipher. Specifically, it
|
||||
// performs the Blowfish algorithm's key schedule which sets up the *Cipher's
|
||||
// pi and substitution tables for calls to Encrypt. This is used, primarily,
|
||||
// by the bcrypt package to reuse the Blowfish key schedule during its
|
||||
// set up. It's unlikely that you need to use this directly.
|
||||
func ExpandKey(key []byte, c *Cipher) {
|
||||
j := 0
|
||||
for i := 0; i < 18; i++ {
|
||||
// Using inlined getNextWord for performance.
|
||||
var d uint32
|
||||
for k := 0; k < 4; k++ {
|
||||
d = d<<8 | uint32(key[j])
|
||||
j++
|
||||
if j >= len(key) {
|
||||
j = 0
|
||||
}
|
||||
}
|
||||
c.p[i] ^= d
|
||||
}
|
||||
|
||||
var l, r uint32
|
||||
for i := 0; i < 18; i += 2 {
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.p[i], c.p[i+1] = l, r
|
||||
}
|
||||
|
||||
for i := 0; i < 256; i += 2 {
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.s0[i], c.s0[i+1] = l, r
|
||||
}
|
||||
for i := 0; i < 256; i += 2 {
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.s1[i], c.s1[i+1] = l, r
|
||||
}
|
||||
for i := 0; i < 256; i += 2 {
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.s2[i], c.s2[i+1] = l, r
|
||||
}
|
||||
for i := 0; i < 256; i += 2 {
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.s3[i], c.s3[i+1] = l, r
|
||||
}
|
||||
}
|
||||
|
||||
// This is similar to ExpandKey, but folds the salt during the key
|
||||
// schedule. While ExpandKey is essentially expandKeyWithSalt with an all-zero
|
||||
// salt passed in, reusing ExpandKey turns out to be a place of inefficiency
|
||||
// and specializing it here is useful.
|
||||
func expandKeyWithSalt(key []byte, salt []byte, c *Cipher) {
|
||||
j := 0
|
||||
for i := 0; i < 18; i++ {
|
||||
c.p[i] ^= getNextWord(key, &j)
|
||||
}
|
||||
|
||||
j = 0
|
||||
var l, r uint32
|
||||
for i := 0; i < 18; i += 2 {
|
||||
l ^= getNextWord(salt, &j)
|
||||
r ^= getNextWord(salt, &j)
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.p[i], c.p[i+1] = l, r
|
||||
}
|
||||
|
||||
for i := 0; i < 256; i += 2 {
|
||||
l ^= getNextWord(salt, &j)
|
||||
r ^= getNextWord(salt, &j)
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.s0[i], c.s0[i+1] = l, r
|
||||
}
|
||||
|
||||
for i := 0; i < 256; i += 2 {
|
||||
l ^= getNextWord(salt, &j)
|
||||
r ^= getNextWord(salt, &j)
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.s1[i], c.s1[i+1] = l, r
|
||||
}
|
||||
|
||||
for i := 0; i < 256; i += 2 {
|
||||
l ^= getNextWord(salt, &j)
|
||||
r ^= getNextWord(salt, &j)
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.s2[i], c.s2[i+1] = l, r
|
||||
}
|
||||
|
||||
for i := 0; i < 256; i += 2 {
|
||||
l ^= getNextWord(salt, &j)
|
||||
r ^= getNextWord(salt, &j)
|
||||
l, r = encryptBlock(l, r, c)
|
||||
c.s3[i], c.s3[i+1] = l, r
|
||||
}
|
||||
}
|
||||
|
||||
func encryptBlock(l, r uint32, c *Cipher) (uint32, uint32) {
|
||||
xl, xr := l, r
|
||||
xl ^= c.p[0]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[1]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[2]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[3]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[4]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[5]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[6]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[7]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[8]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[9]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[10]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[11]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[12]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[13]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[14]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[15]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[16]
|
||||
xr ^= c.p[17]
|
||||
return xr, xl
|
||||
}
|
||||
|
||||
func decryptBlock(l, r uint32, c *Cipher) (uint32, uint32) {
|
||||
xl, xr := l, r
|
||||
xl ^= c.p[17]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[16]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[15]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[14]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[13]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[12]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[11]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[10]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[9]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[8]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[7]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[6]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[5]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[4]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[3]
|
||||
xr ^= ((c.s0[byte(xl>>24)] + c.s1[byte(xl>>16)]) ^ c.s2[byte(xl>>8)]) + c.s3[byte(xl)] ^ c.p[2]
|
||||
xl ^= ((c.s0[byte(xr>>24)] + c.s1[byte(xr>>16)]) ^ c.s2[byte(xr>>8)]) + c.s3[byte(xr)] ^ c.p[1]
|
||||
xr ^= c.p[0]
|
||||
return xr, xl
|
||||
}
|
||||
+91
@@ -0,0 +1,91 @@
|
||||
// Copyright 2010 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package blowfish implements Bruce Schneier's Blowfish encryption algorithm.
|
||||
package blowfish // import "golang.org/x/crypto/blowfish"
|
||||
|
||||
// The code is a port of Bruce Schneier's C implementation.
|
||||
// See https://www.schneier.com/blowfish.html.
|
||||
|
||||
import "strconv"
|
||||
|
||||
// The Blowfish block size in bytes.
|
||||
const BlockSize = 8
|
||||
|
||||
// A Cipher is an instance of Blowfish encryption using a particular key.
|
||||
type Cipher struct {
|
||||
p [18]uint32
|
||||
s0, s1, s2, s3 [256]uint32
|
||||
}
|
||||
|
||||
type KeySizeError int
|
||||
|
||||
func (k KeySizeError) Error() string {
|
||||
return "crypto/blowfish: invalid key size " + strconv.Itoa(int(k))
|
||||
}
|
||||
|
||||
// NewCipher creates and returns a Cipher.
|
||||
// The key argument should be the Blowfish key, from 1 to 56 bytes.
|
||||
func NewCipher(key []byte) (*Cipher, error) {
|
||||
var result Cipher
|
||||
if k := len(key); k < 1 || k > 56 {
|
||||
return nil, KeySizeError(k)
|
||||
}
|
||||
initCipher(&result)
|
||||
ExpandKey(key, &result)
|
||||
return &result, nil
|
||||
}
|
||||
|
||||
// NewSaltedCipher creates a returns a Cipher that folds a salt into its key
|
||||
// schedule. For most purposes, NewCipher, instead of NewSaltedCipher, is
|
||||
// sufficient and desirable. For bcrypt compatibility, the key can be over 56
|
||||
// bytes.
|
||||
func NewSaltedCipher(key, salt []byte) (*Cipher, error) {
|
||||
if len(salt) == 0 {
|
||||
return NewCipher(key)
|
||||
}
|
||||
var result Cipher
|
||||
if k := len(key); k < 1 {
|
||||
return nil, KeySizeError(k)
|
||||
}
|
||||
initCipher(&result)
|
||||
expandKeyWithSalt(key, salt, &result)
|
||||
return &result, nil
|
||||
}
|
||||
|
||||
// BlockSize returns the Blowfish block size, 8 bytes.
|
||||
// It is necessary to satisfy the Block interface in the
|
||||
// package "crypto/cipher".
|
||||
func (c *Cipher) BlockSize() int { return BlockSize }
|
||||
|
||||
// Encrypt encrypts the 8-byte buffer src using the key k
|
||||
// and stores the result in dst.
|
||||
// Note that for amounts of data larger than a block,
|
||||
// it is not safe to just call Encrypt on successive blocks;
|
||||
// instead, use an encryption mode like CBC (see crypto/cipher/cbc.go).
|
||||
func (c *Cipher) Encrypt(dst, src []byte) {
|
||||
l := uint32(src[0])<<24 | uint32(src[1])<<16 | uint32(src[2])<<8 | uint32(src[3])
|
||||
r := uint32(src[4])<<24 | uint32(src[5])<<16 | uint32(src[6])<<8 | uint32(src[7])
|
||||
l, r = encryptBlock(l, r, c)
|
||||
dst[0], dst[1], dst[2], dst[3] = byte(l>>24), byte(l>>16), byte(l>>8), byte(l)
|
||||
dst[4], dst[5], dst[6], dst[7] = byte(r>>24), byte(r>>16), byte(r>>8), byte(r)
|
||||
}
|
||||
|
||||
// Decrypt decrypts the 8-byte buffer src using the key k
|
||||
// and stores the result in dst.
|
||||
func (c *Cipher) Decrypt(dst, src []byte) {
|
||||
l := uint32(src[0])<<24 | uint32(src[1])<<16 | uint32(src[2])<<8 | uint32(src[3])
|
||||
r := uint32(src[4])<<24 | uint32(src[5])<<16 | uint32(src[6])<<8 | uint32(src[7])
|
||||
l, r = decryptBlock(l, r, c)
|
||||
dst[0], dst[1], dst[2], dst[3] = byte(l>>24), byte(l>>16), byte(l>>8), byte(l)
|
||||
dst[4], dst[5], dst[6], dst[7] = byte(r>>24), byte(r>>16), byte(r>>8), byte(r)
|
||||
}
|
||||
|
||||
func initCipher(c *Cipher) {
|
||||
copy(c.p[0:], p[0:])
|
||||
copy(c.s0[0:], s0[0:])
|
||||
copy(c.s1[0:], s1[0:])
|
||||
copy(c.s2[0:], s2[0:])
|
||||
copy(c.s3[0:], s3[0:])
|
||||
}
|
||||
+199
@@ -0,0 +1,199 @@
|
||||
// Copyright 2010 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// The startup permutation array and substitution boxes.
|
||||
// They are the hexadecimal digits of PI; see:
|
||||
// https://www.schneier.com/code/constants.txt.
|
||||
|
||||
package blowfish
|
||||
|
||||
var s0 = [256]uint32{
|
||||
0xd1310ba6, 0x98dfb5ac, 0x2ffd72db, 0xd01adfb7, 0xb8e1afed, 0x6a267e96,
|
||||
0xba7c9045, 0xf12c7f99, 0x24a19947, 0xb3916cf7, 0x0801f2e2, 0x858efc16,
|
||||
0x636920d8, 0x71574e69, 0xa458fea3, 0xf4933d7e, 0x0d95748f, 0x728eb658,
|
||||
0x718bcd58, 0x82154aee, 0x7b54a41d, 0xc25a59b5, 0x9c30d539, 0x2af26013,
|
||||
0xc5d1b023, 0x286085f0, 0xca417918, 0xb8db38ef, 0x8e79dcb0, 0x603a180e,
|
||||
0x6c9e0e8b, 0xb01e8a3e, 0xd71577c1, 0xbd314b27, 0x78af2fda, 0x55605c60,
|
||||
0xe65525f3, 0xaa55ab94, 0x57489862, 0x63e81440, 0x55ca396a, 0x2aab10b6,
|
||||
0xb4cc5c34, 0x1141e8ce, 0xa15486af, 0x7c72e993, 0xb3ee1411, 0x636fbc2a,
|
||||
0x2ba9c55d, 0x741831f6, 0xce5c3e16, 0x9b87931e, 0xafd6ba33, 0x6c24cf5c,
|
||||
0x7a325381, 0x28958677, 0x3b8f4898, 0x6b4bb9af, 0xc4bfe81b, 0x66282193,
|
||||
0x61d809cc, 0xfb21a991, 0x487cac60, 0x5dec8032, 0xef845d5d, 0xe98575b1,
|
||||
0xdc262302, 0xeb651b88, 0x23893e81, 0xd396acc5, 0x0f6d6ff3, 0x83f44239,
|
||||
0x2e0b4482, 0xa4842004, 0x69c8f04a, 0x9e1f9b5e, 0x21c66842, 0xf6e96c9a,
|
||||
0x670c9c61, 0xabd388f0, 0x6a51a0d2, 0xd8542f68, 0x960fa728, 0xab5133a3,
|
||||
0x6eef0b6c, 0x137a3be4, 0xba3bf050, 0x7efb2a98, 0xa1f1651d, 0x39af0176,
|
||||
0x66ca593e, 0x82430e88, 0x8cee8619, 0x456f9fb4, 0x7d84a5c3, 0x3b8b5ebe,
|
||||
0xe06f75d8, 0x85c12073, 0x401a449f, 0x56c16aa6, 0x4ed3aa62, 0x363f7706,
|
||||
0x1bfedf72, 0x429b023d, 0x37d0d724, 0xd00a1248, 0xdb0fead3, 0x49f1c09b,
|
||||
0x075372c9, 0x80991b7b, 0x25d479d8, 0xf6e8def7, 0xe3fe501a, 0xb6794c3b,
|
||||
0x976ce0bd, 0x04c006ba, 0xc1a94fb6, 0x409f60c4, 0x5e5c9ec2, 0x196a2463,
|
||||
0x68fb6faf, 0x3e6c53b5, 0x1339b2eb, 0x3b52ec6f, 0x6dfc511f, 0x9b30952c,
|
||||
0xcc814544, 0xaf5ebd09, 0xbee3d004, 0xde334afd, 0x660f2807, 0x192e4bb3,
|
||||
0xc0cba857, 0x45c8740f, 0xd20b5f39, 0xb9d3fbdb, 0x5579c0bd, 0x1a60320a,
|
||||
0xd6a100c6, 0x402c7279, 0x679f25fe, 0xfb1fa3cc, 0x8ea5e9f8, 0xdb3222f8,
|
||||
0x3c7516df, 0xfd616b15, 0x2f501ec8, 0xad0552ab, 0x323db5fa, 0xfd238760,
|
||||
0x53317b48, 0x3e00df82, 0x9e5c57bb, 0xca6f8ca0, 0x1a87562e, 0xdf1769db,
|
||||
0xd542a8f6, 0x287effc3, 0xac6732c6, 0x8c4f5573, 0x695b27b0, 0xbbca58c8,
|
||||
0xe1ffa35d, 0xb8f011a0, 0x10fa3d98, 0xfd2183b8, 0x4afcb56c, 0x2dd1d35b,
|
||||
0x9a53e479, 0xb6f84565, 0xd28e49bc, 0x4bfb9790, 0xe1ddf2da, 0xa4cb7e33,
|
||||
0x62fb1341, 0xcee4c6e8, 0xef20cada, 0x36774c01, 0xd07e9efe, 0x2bf11fb4,
|
||||
0x95dbda4d, 0xae909198, 0xeaad8e71, 0x6b93d5a0, 0xd08ed1d0, 0xafc725e0,
|
||||
0x8e3c5b2f, 0x8e7594b7, 0x8ff6e2fb, 0xf2122b64, 0x8888b812, 0x900df01c,
|
||||
0x4fad5ea0, 0x688fc31c, 0xd1cff191, 0xb3a8c1ad, 0x2f2f2218, 0xbe0e1777,
|
||||
0xea752dfe, 0x8b021fa1, 0xe5a0cc0f, 0xb56f74e8, 0x18acf3d6, 0xce89e299,
|
||||
0xb4a84fe0, 0xfd13e0b7, 0x7cc43b81, 0xd2ada8d9, 0x165fa266, 0x80957705,
|
||||
0x93cc7314, 0x211a1477, 0xe6ad2065, 0x77b5fa86, 0xc75442f5, 0xfb9d35cf,
|
||||
0xebcdaf0c, 0x7b3e89a0, 0xd6411bd3, 0xae1e7e49, 0x00250e2d, 0x2071b35e,
|
||||
0x226800bb, 0x57b8e0af, 0x2464369b, 0xf009b91e, 0x5563911d, 0x59dfa6aa,
|
||||
0x78c14389, 0xd95a537f, 0x207d5ba2, 0x02e5b9c5, 0x83260376, 0x6295cfa9,
|
||||
0x11c81968, 0x4e734a41, 0xb3472dca, 0x7b14a94a, 0x1b510052, 0x9a532915,
|
||||
0xd60f573f, 0xbc9bc6e4, 0x2b60a476, 0x81e67400, 0x08ba6fb5, 0x571be91f,
|
||||
0xf296ec6b, 0x2a0dd915, 0xb6636521, 0xe7b9f9b6, 0xff34052e, 0xc5855664,
|
||||
0x53b02d5d, 0xa99f8fa1, 0x08ba4799, 0x6e85076a,
|
||||
}
|
||||
|
||||
var s1 = [256]uint32{
|
||||
0x4b7a70e9, 0xb5b32944, 0xdb75092e, 0xc4192623, 0xad6ea6b0, 0x49a7df7d,
|
||||
0x9cee60b8, 0x8fedb266, 0xecaa8c71, 0x699a17ff, 0x5664526c, 0xc2b19ee1,
|
||||
0x193602a5, 0x75094c29, 0xa0591340, 0xe4183a3e, 0x3f54989a, 0x5b429d65,
|
||||
0x6b8fe4d6, 0x99f73fd6, 0xa1d29c07, 0xefe830f5, 0x4d2d38e6, 0xf0255dc1,
|
||||
0x4cdd2086, 0x8470eb26, 0x6382e9c6, 0x021ecc5e, 0x09686b3f, 0x3ebaefc9,
|
||||
0x3c971814, 0x6b6a70a1, 0x687f3584, 0x52a0e286, 0xb79c5305, 0xaa500737,
|
||||
0x3e07841c, 0x7fdeae5c, 0x8e7d44ec, 0x5716f2b8, 0xb03ada37, 0xf0500c0d,
|
||||
0xf01c1f04, 0x0200b3ff, 0xae0cf51a, 0x3cb574b2, 0x25837a58, 0xdc0921bd,
|
||||
0xd19113f9, 0x7ca92ff6, 0x94324773, 0x22f54701, 0x3ae5e581, 0x37c2dadc,
|
||||
0xc8b57634, 0x9af3dda7, 0xa9446146, 0x0fd0030e, 0xecc8c73e, 0xa4751e41,
|
||||
0xe238cd99, 0x3bea0e2f, 0x3280bba1, 0x183eb331, 0x4e548b38, 0x4f6db908,
|
||||
0x6f420d03, 0xf60a04bf, 0x2cb81290, 0x24977c79, 0x5679b072, 0xbcaf89af,
|
||||
0xde9a771f, 0xd9930810, 0xb38bae12, 0xdccf3f2e, 0x5512721f, 0x2e6b7124,
|
||||
0x501adde6, 0x9f84cd87, 0x7a584718, 0x7408da17, 0xbc9f9abc, 0xe94b7d8c,
|
||||
0xec7aec3a, 0xdb851dfa, 0x63094366, 0xc464c3d2, 0xef1c1847, 0x3215d908,
|
||||
0xdd433b37, 0x24c2ba16, 0x12a14d43, 0x2a65c451, 0x50940002, 0x133ae4dd,
|
||||
0x71dff89e, 0x10314e55, 0x81ac77d6, 0x5f11199b, 0x043556f1, 0xd7a3c76b,
|
||||
0x3c11183b, 0x5924a509, 0xf28fe6ed, 0x97f1fbfa, 0x9ebabf2c, 0x1e153c6e,
|
||||
0x86e34570, 0xeae96fb1, 0x860e5e0a, 0x5a3e2ab3, 0x771fe71c, 0x4e3d06fa,
|
||||
0x2965dcb9, 0x99e71d0f, 0x803e89d6, 0x5266c825, 0x2e4cc978, 0x9c10b36a,
|
||||
0xc6150eba, 0x94e2ea78, 0xa5fc3c53, 0x1e0a2df4, 0xf2f74ea7, 0x361d2b3d,
|
||||
0x1939260f, 0x19c27960, 0x5223a708, 0xf71312b6, 0xebadfe6e, 0xeac31f66,
|
||||
0xe3bc4595, 0xa67bc883, 0xb17f37d1, 0x018cff28, 0xc332ddef, 0xbe6c5aa5,
|
||||
0x65582185, 0x68ab9802, 0xeecea50f, 0xdb2f953b, 0x2aef7dad, 0x5b6e2f84,
|
||||
0x1521b628, 0x29076170, 0xecdd4775, 0x619f1510, 0x13cca830, 0xeb61bd96,
|
||||
0x0334fe1e, 0xaa0363cf, 0xb5735c90, 0x4c70a239, 0xd59e9e0b, 0xcbaade14,
|
||||
0xeecc86bc, 0x60622ca7, 0x9cab5cab, 0xb2f3846e, 0x648b1eaf, 0x19bdf0ca,
|
||||
0xa02369b9, 0x655abb50, 0x40685a32, 0x3c2ab4b3, 0x319ee9d5, 0xc021b8f7,
|
||||
0x9b540b19, 0x875fa099, 0x95f7997e, 0x623d7da8, 0xf837889a, 0x97e32d77,
|
||||
0x11ed935f, 0x16681281, 0x0e358829, 0xc7e61fd6, 0x96dedfa1, 0x7858ba99,
|
||||
0x57f584a5, 0x1b227263, 0x9b83c3ff, 0x1ac24696, 0xcdb30aeb, 0x532e3054,
|
||||
0x8fd948e4, 0x6dbc3128, 0x58ebf2ef, 0x34c6ffea, 0xfe28ed61, 0xee7c3c73,
|
||||
0x5d4a14d9, 0xe864b7e3, 0x42105d14, 0x203e13e0, 0x45eee2b6, 0xa3aaabea,
|
||||
0xdb6c4f15, 0xfacb4fd0, 0xc742f442, 0xef6abbb5, 0x654f3b1d, 0x41cd2105,
|
||||
0xd81e799e, 0x86854dc7, 0xe44b476a, 0x3d816250, 0xcf62a1f2, 0x5b8d2646,
|
||||
0xfc8883a0, 0xc1c7b6a3, 0x7f1524c3, 0x69cb7492, 0x47848a0b, 0x5692b285,
|
||||
0x095bbf00, 0xad19489d, 0x1462b174, 0x23820e00, 0x58428d2a, 0x0c55f5ea,
|
||||
0x1dadf43e, 0x233f7061, 0x3372f092, 0x8d937e41, 0xd65fecf1, 0x6c223bdb,
|
||||
0x7cde3759, 0xcbee7460, 0x4085f2a7, 0xce77326e, 0xa6078084, 0x19f8509e,
|
||||
0xe8efd855, 0x61d99735, 0xa969a7aa, 0xc50c06c2, 0x5a04abfc, 0x800bcadc,
|
||||
0x9e447a2e, 0xc3453484, 0xfdd56705, 0x0e1e9ec9, 0xdb73dbd3, 0x105588cd,
|
||||
0x675fda79, 0xe3674340, 0xc5c43465, 0x713e38d8, 0x3d28f89e, 0xf16dff20,
|
||||
0x153e21e7, 0x8fb03d4a, 0xe6e39f2b, 0xdb83adf7,
|
||||
}
|
||||
|
||||
var s2 = [256]uint32{
|
||||
0xe93d5a68, 0x948140f7, 0xf64c261c, 0x94692934, 0x411520f7, 0x7602d4f7,
|
||||
0xbcf46b2e, 0xd4a20068, 0xd4082471, 0x3320f46a, 0x43b7d4b7, 0x500061af,
|
||||
0x1e39f62e, 0x97244546, 0x14214f74, 0xbf8b8840, 0x4d95fc1d, 0x96b591af,
|
||||
0x70f4ddd3, 0x66a02f45, 0xbfbc09ec, 0x03bd9785, 0x7fac6dd0, 0x31cb8504,
|
||||
0x96eb27b3, 0x55fd3941, 0xda2547e6, 0xabca0a9a, 0x28507825, 0x530429f4,
|
||||
0x0a2c86da, 0xe9b66dfb, 0x68dc1462, 0xd7486900, 0x680ec0a4, 0x27a18dee,
|
||||
0x4f3ffea2, 0xe887ad8c, 0xb58ce006, 0x7af4d6b6, 0xaace1e7c, 0xd3375fec,
|
||||
0xce78a399, 0x406b2a42, 0x20fe9e35, 0xd9f385b9, 0xee39d7ab, 0x3b124e8b,
|
||||
0x1dc9faf7, 0x4b6d1856, 0x26a36631, 0xeae397b2, 0x3a6efa74, 0xdd5b4332,
|
||||
0x6841e7f7, 0xca7820fb, 0xfb0af54e, 0xd8feb397, 0x454056ac, 0xba489527,
|
||||
0x55533a3a, 0x20838d87, 0xfe6ba9b7, 0xd096954b, 0x55a867bc, 0xa1159a58,
|
||||
0xcca92963, 0x99e1db33, 0xa62a4a56, 0x3f3125f9, 0x5ef47e1c, 0x9029317c,
|
||||
0xfdf8e802, 0x04272f70, 0x80bb155c, 0x05282ce3, 0x95c11548, 0xe4c66d22,
|
||||
0x48c1133f, 0xc70f86dc, 0x07f9c9ee, 0x41041f0f, 0x404779a4, 0x5d886e17,
|
||||
0x325f51eb, 0xd59bc0d1, 0xf2bcc18f, 0x41113564, 0x257b7834, 0x602a9c60,
|
||||
0xdff8e8a3, 0x1f636c1b, 0x0e12b4c2, 0x02e1329e, 0xaf664fd1, 0xcad18115,
|
||||
0x6b2395e0, 0x333e92e1, 0x3b240b62, 0xeebeb922, 0x85b2a20e, 0xe6ba0d99,
|
||||
0xde720c8c, 0x2da2f728, 0xd0127845, 0x95b794fd, 0x647d0862, 0xe7ccf5f0,
|
||||
0x5449a36f, 0x877d48fa, 0xc39dfd27, 0xf33e8d1e, 0x0a476341, 0x992eff74,
|
||||
0x3a6f6eab, 0xf4f8fd37, 0xa812dc60, 0xa1ebddf8, 0x991be14c, 0xdb6e6b0d,
|
||||
0xc67b5510, 0x6d672c37, 0x2765d43b, 0xdcd0e804, 0xf1290dc7, 0xcc00ffa3,
|
||||
0xb5390f92, 0x690fed0b, 0x667b9ffb, 0xcedb7d9c, 0xa091cf0b, 0xd9155ea3,
|
||||
0xbb132f88, 0x515bad24, 0x7b9479bf, 0x763bd6eb, 0x37392eb3, 0xcc115979,
|
||||
0x8026e297, 0xf42e312d, 0x6842ada7, 0xc66a2b3b, 0x12754ccc, 0x782ef11c,
|
||||
0x6a124237, 0xb79251e7, 0x06a1bbe6, 0x4bfb6350, 0x1a6b1018, 0x11caedfa,
|
||||
0x3d25bdd8, 0xe2e1c3c9, 0x44421659, 0x0a121386, 0xd90cec6e, 0xd5abea2a,
|
||||
0x64af674e, 0xda86a85f, 0xbebfe988, 0x64e4c3fe, 0x9dbc8057, 0xf0f7c086,
|
||||
0x60787bf8, 0x6003604d, 0xd1fd8346, 0xf6381fb0, 0x7745ae04, 0xd736fccc,
|
||||
0x83426b33, 0xf01eab71, 0xb0804187, 0x3c005e5f, 0x77a057be, 0xbde8ae24,
|
||||
0x55464299, 0xbf582e61, 0x4e58f48f, 0xf2ddfda2, 0xf474ef38, 0x8789bdc2,
|
||||
0x5366f9c3, 0xc8b38e74, 0xb475f255, 0x46fcd9b9, 0x7aeb2661, 0x8b1ddf84,
|
||||
0x846a0e79, 0x915f95e2, 0x466e598e, 0x20b45770, 0x8cd55591, 0xc902de4c,
|
||||
0xb90bace1, 0xbb8205d0, 0x11a86248, 0x7574a99e, 0xb77f19b6, 0xe0a9dc09,
|
||||
0x662d09a1, 0xc4324633, 0xe85a1f02, 0x09f0be8c, 0x4a99a025, 0x1d6efe10,
|
||||
0x1ab93d1d, 0x0ba5a4df, 0xa186f20f, 0x2868f169, 0xdcb7da83, 0x573906fe,
|
||||
0xa1e2ce9b, 0x4fcd7f52, 0x50115e01, 0xa70683fa, 0xa002b5c4, 0x0de6d027,
|
||||
0x9af88c27, 0x773f8641, 0xc3604c06, 0x61a806b5, 0xf0177a28, 0xc0f586e0,
|
||||
0x006058aa, 0x30dc7d62, 0x11e69ed7, 0x2338ea63, 0x53c2dd94, 0xc2c21634,
|
||||
0xbbcbee56, 0x90bcb6de, 0xebfc7da1, 0xce591d76, 0x6f05e409, 0x4b7c0188,
|
||||
0x39720a3d, 0x7c927c24, 0x86e3725f, 0x724d9db9, 0x1ac15bb4, 0xd39eb8fc,
|
||||
0xed545578, 0x08fca5b5, 0xd83d7cd3, 0x4dad0fc4, 0x1e50ef5e, 0xb161e6f8,
|
||||
0xa28514d9, 0x6c51133c, 0x6fd5c7e7, 0x56e14ec4, 0x362abfce, 0xddc6c837,
|
||||
0xd79a3234, 0x92638212, 0x670efa8e, 0x406000e0,
|
||||
}
|
||||
|
||||
var s3 = [256]uint32{
|
||||
0x3a39ce37, 0xd3faf5cf, 0xabc27737, 0x5ac52d1b, 0x5cb0679e, 0x4fa33742,
|
||||
0xd3822740, 0x99bc9bbe, 0xd5118e9d, 0xbf0f7315, 0xd62d1c7e, 0xc700c47b,
|
||||
0xb78c1b6b, 0x21a19045, 0xb26eb1be, 0x6a366eb4, 0x5748ab2f, 0xbc946e79,
|
||||
0xc6a376d2, 0x6549c2c8, 0x530ff8ee, 0x468dde7d, 0xd5730a1d, 0x4cd04dc6,
|
||||
0x2939bbdb, 0xa9ba4650, 0xac9526e8, 0xbe5ee304, 0xa1fad5f0, 0x6a2d519a,
|
||||
0x63ef8ce2, 0x9a86ee22, 0xc089c2b8, 0x43242ef6, 0xa51e03aa, 0x9cf2d0a4,
|
||||
0x83c061ba, 0x9be96a4d, 0x8fe51550, 0xba645bd6, 0x2826a2f9, 0xa73a3ae1,
|
||||
0x4ba99586, 0xef5562e9, 0xc72fefd3, 0xf752f7da, 0x3f046f69, 0x77fa0a59,
|
||||
0x80e4a915, 0x87b08601, 0x9b09e6ad, 0x3b3ee593, 0xe990fd5a, 0x9e34d797,
|
||||
0x2cf0b7d9, 0x022b8b51, 0x96d5ac3a, 0x017da67d, 0xd1cf3ed6, 0x7c7d2d28,
|
||||
0x1f9f25cf, 0xadf2b89b, 0x5ad6b472, 0x5a88f54c, 0xe029ac71, 0xe019a5e6,
|
||||
0x47b0acfd, 0xed93fa9b, 0xe8d3c48d, 0x283b57cc, 0xf8d56629, 0x79132e28,
|
||||
0x785f0191, 0xed756055, 0xf7960e44, 0xe3d35e8c, 0x15056dd4, 0x88f46dba,
|
||||
0x03a16125, 0x0564f0bd, 0xc3eb9e15, 0x3c9057a2, 0x97271aec, 0xa93a072a,
|
||||
0x1b3f6d9b, 0x1e6321f5, 0xf59c66fb, 0x26dcf319, 0x7533d928, 0xb155fdf5,
|
||||
0x03563482, 0x8aba3cbb, 0x28517711, 0xc20ad9f8, 0xabcc5167, 0xccad925f,
|
||||
0x4de81751, 0x3830dc8e, 0x379d5862, 0x9320f991, 0xea7a90c2, 0xfb3e7bce,
|
||||
0x5121ce64, 0x774fbe32, 0xa8b6e37e, 0xc3293d46, 0x48de5369, 0x6413e680,
|
||||
0xa2ae0810, 0xdd6db224, 0x69852dfd, 0x09072166, 0xb39a460a, 0x6445c0dd,
|
||||
0x586cdecf, 0x1c20c8ae, 0x5bbef7dd, 0x1b588d40, 0xccd2017f, 0x6bb4e3bb,
|
||||
0xdda26a7e, 0x3a59ff45, 0x3e350a44, 0xbcb4cdd5, 0x72eacea8, 0xfa6484bb,
|
||||
0x8d6612ae, 0xbf3c6f47, 0xd29be463, 0x542f5d9e, 0xaec2771b, 0xf64e6370,
|
||||
0x740e0d8d, 0xe75b1357, 0xf8721671, 0xaf537d5d, 0x4040cb08, 0x4eb4e2cc,
|
||||
0x34d2466a, 0x0115af84, 0xe1b00428, 0x95983a1d, 0x06b89fb4, 0xce6ea048,
|
||||
0x6f3f3b82, 0x3520ab82, 0x011a1d4b, 0x277227f8, 0x611560b1, 0xe7933fdc,
|
||||
0xbb3a792b, 0x344525bd, 0xa08839e1, 0x51ce794b, 0x2f32c9b7, 0xa01fbac9,
|
||||
0xe01cc87e, 0xbcc7d1f6, 0xcf0111c3, 0xa1e8aac7, 0x1a908749, 0xd44fbd9a,
|
||||
0xd0dadecb, 0xd50ada38, 0x0339c32a, 0xc6913667, 0x8df9317c, 0xe0b12b4f,
|
||||
0xf79e59b7, 0x43f5bb3a, 0xf2d519ff, 0x27d9459c, 0xbf97222c, 0x15e6fc2a,
|
||||
0x0f91fc71, 0x9b941525, 0xfae59361, 0xceb69ceb, 0xc2a86459, 0x12baa8d1,
|
||||
0xb6c1075e, 0xe3056a0c, 0x10d25065, 0xcb03a442, 0xe0ec6e0e, 0x1698db3b,
|
||||
0x4c98a0be, 0x3278e964, 0x9f1f9532, 0xe0d392df, 0xd3a0342b, 0x8971f21e,
|
||||
0x1b0a7441, 0x4ba3348c, 0xc5be7120, 0xc37632d8, 0xdf359f8d, 0x9b992f2e,
|
||||
0xe60b6f47, 0x0fe3f11d, 0xe54cda54, 0x1edad891, 0xce6279cf, 0xcd3e7e6f,
|
||||
0x1618b166, 0xfd2c1d05, 0x848fd2c5, 0xf6fb2299, 0xf523f357, 0xa6327623,
|
||||
0x93a83531, 0x56cccd02, 0xacf08162, 0x5a75ebb5, 0x6e163697, 0x88d273cc,
|
||||
0xde966292, 0x81b949d0, 0x4c50901b, 0x71c65614, 0xe6c6c7bd, 0x327a140a,
|
||||
0x45e1d006, 0xc3f27b9a, 0xc9aa53fd, 0x62a80f00, 0xbb25bfe2, 0x35bdd2f6,
|
||||
0x71126905, 0xb2040222, 0xb6cbcf7c, 0xcd769c2b, 0x53113ec0, 0x1640e3d3,
|
||||
0x38abbd60, 0x2547adf0, 0xba38209c, 0xf746ce76, 0x77afa1c5, 0x20756060,
|
||||
0x85cbfe4e, 0x8ae88dd8, 0x7aaaf9b0, 0x4cf9aa7e, 0x1948c25c, 0x02fb8a8c,
|
||||
0x01c36ae4, 0xd6ebe1f9, 0x90d4f869, 0xa65cdea0, 0x3f09252d, 0xc208e69f,
|
||||
0xb74e6132, 0xce77e25b, 0x578fdfe3, 0x3ac372e6,
|
||||
}
|
||||
|
||||
var p = [18]uint32{
|
||||
0x243f6a88, 0x85a308d3, 0x13198a2e, 0x03707344, 0xa4093822, 0x299f31d0,
|
||||
0x082efa98, 0xec4e6c89, 0x452821e6, 0x38d01377, 0xbe5466cf, 0x34e90c6c,
|
||||
0xc0ac29b7, 0xc97c50dd, 0x3f84d5b5, 0xb5470917, 0x9216d5d9, 0x8979fb1b,
|
||||
}
|
||||
+526
@@ -0,0 +1,526 @@
|
||||
// Copyright 2010 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package cast5 implements CAST5, as defined in RFC 2144. CAST5 is a common
|
||||
// OpenPGP cipher.
|
||||
package cast5 // import "golang.org/x/crypto/cast5"
|
||||
|
||||
import "errors"
|
||||
|
||||
const BlockSize = 8
|
||||
const KeySize = 16
|
||||
|
||||
type Cipher struct {
|
||||
masking [16]uint32
|
||||
rotate [16]uint8
|
||||
}
|
||||
|
||||
func NewCipher(key []byte) (c *Cipher, err error) {
|
||||
if len(key) != KeySize {
|
||||
return nil, errors.New("CAST5: keys must be 16 bytes")
|
||||
}
|
||||
|
||||
c = new(Cipher)
|
||||
c.keySchedule(key)
|
||||
return
|
||||
}
|
||||
|
||||
func (c *Cipher) BlockSize() int {
|
||||
return BlockSize
|
||||
}
|
||||
|
||||
func (c *Cipher) Encrypt(dst, src []byte) {
|
||||
l := uint32(src[0])<<24 | uint32(src[1])<<16 | uint32(src[2])<<8 | uint32(src[3])
|
||||
r := uint32(src[4])<<24 | uint32(src[5])<<16 | uint32(src[6])<<8 | uint32(src[7])
|
||||
|
||||
l, r = r, l^f1(r, c.masking[0], c.rotate[0])
|
||||
l, r = r, l^f2(r, c.masking[1], c.rotate[1])
|
||||
l, r = r, l^f3(r, c.masking[2], c.rotate[2])
|
||||
l, r = r, l^f1(r, c.masking[3], c.rotate[3])
|
||||
|
||||
l, r = r, l^f2(r, c.masking[4], c.rotate[4])
|
||||
l, r = r, l^f3(r, c.masking[5], c.rotate[5])
|
||||
l, r = r, l^f1(r, c.masking[6], c.rotate[6])
|
||||
l, r = r, l^f2(r, c.masking[7], c.rotate[7])
|
||||
|
||||
l, r = r, l^f3(r, c.masking[8], c.rotate[8])
|
||||
l, r = r, l^f1(r, c.masking[9], c.rotate[9])
|
||||
l, r = r, l^f2(r, c.masking[10], c.rotate[10])
|
||||
l, r = r, l^f3(r, c.masking[11], c.rotate[11])
|
||||
|
||||
l, r = r, l^f1(r, c.masking[12], c.rotate[12])
|
||||
l, r = r, l^f2(r, c.masking[13], c.rotate[13])
|
||||
l, r = r, l^f3(r, c.masking[14], c.rotate[14])
|
||||
l, r = r, l^f1(r, c.masking[15], c.rotate[15])
|
||||
|
||||
dst[0] = uint8(r >> 24)
|
||||
dst[1] = uint8(r >> 16)
|
||||
dst[2] = uint8(r >> 8)
|
||||
dst[3] = uint8(r)
|
||||
dst[4] = uint8(l >> 24)
|
||||
dst[5] = uint8(l >> 16)
|
||||
dst[6] = uint8(l >> 8)
|
||||
dst[7] = uint8(l)
|
||||
}
|
||||
|
||||
func (c *Cipher) Decrypt(dst, src []byte) {
|
||||
l := uint32(src[0])<<24 | uint32(src[1])<<16 | uint32(src[2])<<8 | uint32(src[3])
|
||||
r := uint32(src[4])<<24 | uint32(src[5])<<16 | uint32(src[6])<<8 | uint32(src[7])
|
||||
|
||||
l, r = r, l^f1(r, c.masking[15], c.rotate[15])
|
||||
l, r = r, l^f3(r, c.masking[14], c.rotate[14])
|
||||
l, r = r, l^f2(r, c.masking[13], c.rotate[13])
|
||||
l, r = r, l^f1(r, c.masking[12], c.rotate[12])
|
||||
|
||||
l, r = r, l^f3(r, c.masking[11], c.rotate[11])
|
||||
l, r = r, l^f2(r, c.masking[10], c.rotate[10])
|
||||
l, r = r, l^f1(r, c.masking[9], c.rotate[9])
|
||||
l, r = r, l^f3(r, c.masking[8], c.rotate[8])
|
||||
|
||||
l, r = r, l^f2(r, c.masking[7], c.rotate[7])
|
||||
l, r = r, l^f1(r, c.masking[6], c.rotate[6])
|
||||
l, r = r, l^f3(r, c.masking[5], c.rotate[5])
|
||||
l, r = r, l^f2(r, c.masking[4], c.rotate[4])
|
||||
|
||||
l, r = r, l^f1(r, c.masking[3], c.rotate[3])
|
||||
l, r = r, l^f3(r, c.masking[2], c.rotate[2])
|
||||
l, r = r, l^f2(r, c.masking[1], c.rotate[1])
|
||||
l, r = r, l^f1(r, c.masking[0], c.rotate[0])
|
||||
|
||||
dst[0] = uint8(r >> 24)
|
||||
dst[1] = uint8(r >> 16)
|
||||
dst[2] = uint8(r >> 8)
|
||||
dst[3] = uint8(r)
|
||||
dst[4] = uint8(l >> 24)
|
||||
dst[5] = uint8(l >> 16)
|
||||
dst[6] = uint8(l >> 8)
|
||||
dst[7] = uint8(l)
|
||||
}
|
||||
|
||||
type keyScheduleA [4][7]uint8
|
||||
type keyScheduleB [4][5]uint8
|
||||
|
||||
// keyScheduleRound contains the magic values for a round of the key schedule.
|
||||
// The keyScheduleA deals with the lines like:
|
||||
// z0z1z2z3 = x0x1x2x3 ^ S5[xD] ^ S6[xF] ^ S7[xC] ^ S8[xE] ^ S7[x8]
|
||||
// Conceptually, both x and z are in the same array, x first. The first
|
||||
// element describes which word of this array gets written to and the
|
||||
// second, which word gets read. So, for the line above, it's "4, 0", because
|
||||
// it's writing to the first word of z, which, being after x, is word 4, and
|
||||
// reading from the first word of x: word 0.
|
||||
//
|
||||
// Next are the indexes into the S-boxes. Now the array is treated as bytes. So
|
||||
// "xD" is 0xd. The first byte of z is written as "16 + 0", just to be clear
|
||||
// that it's z that we're indexing.
|
||||
//
|
||||
// keyScheduleB deals with lines like:
|
||||
// K1 = S5[z8] ^ S6[z9] ^ S7[z7] ^ S8[z6] ^ S5[z2]
|
||||
// "K1" is ignored because key words are always written in order. So the five
|
||||
// elements are the S-box indexes. They use the same form as in keyScheduleA,
|
||||
// above.
|
||||
|
||||
type keyScheduleRound struct{}
|
||||
type keySchedule []keyScheduleRound
|
||||
|
||||
var schedule = []struct {
|
||||
a keyScheduleA
|
||||
b keyScheduleB
|
||||
}{
|
||||
{
|
||||
keyScheduleA{
|
||||
{4, 0, 0xd, 0xf, 0xc, 0xe, 0x8},
|
||||
{5, 2, 16 + 0, 16 + 2, 16 + 1, 16 + 3, 0xa},
|
||||
{6, 3, 16 + 7, 16 + 6, 16 + 5, 16 + 4, 9},
|
||||
{7, 1, 16 + 0xa, 16 + 9, 16 + 0xb, 16 + 8, 0xb},
|
||||
},
|
||||
keyScheduleB{
|
||||
{16 + 8, 16 + 9, 16 + 7, 16 + 6, 16 + 2},
|
||||
{16 + 0xa, 16 + 0xb, 16 + 5, 16 + 4, 16 + 6},
|
||||
{16 + 0xc, 16 + 0xd, 16 + 3, 16 + 2, 16 + 9},
|
||||
{16 + 0xe, 16 + 0xf, 16 + 1, 16 + 0, 16 + 0xc},
|
||||
},
|
||||
},
|
||||
{
|
||||
keyScheduleA{
|
||||
{0, 6, 16 + 5, 16 + 7, 16 + 4, 16 + 6, 16 + 0},
|
||||
{1, 4, 0, 2, 1, 3, 16 + 2},
|
||||
{2, 5, 7, 6, 5, 4, 16 + 1},
|
||||
{3, 7, 0xa, 9, 0xb, 8, 16 + 3},
|
||||
},
|
||||
keyScheduleB{
|
||||
{3, 2, 0xc, 0xd, 8},
|
||||
{1, 0, 0xe, 0xf, 0xd},
|
||||
{7, 6, 8, 9, 3},
|
||||
{5, 4, 0xa, 0xb, 7},
|
||||
},
|
||||
},
|
||||
{
|
||||
keyScheduleA{
|
||||
{4, 0, 0xd, 0xf, 0xc, 0xe, 8},
|
||||
{5, 2, 16 + 0, 16 + 2, 16 + 1, 16 + 3, 0xa},
|
||||
{6, 3, 16 + 7, 16 + 6, 16 + 5, 16 + 4, 9},
|
||||
{7, 1, 16 + 0xa, 16 + 9, 16 + 0xb, 16 + 8, 0xb},
|
||||
},
|
||||
keyScheduleB{
|
||||
{16 + 3, 16 + 2, 16 + 0xc, 16 + 0xd, 16 + 9},
|
||||
{16 + 1, 16 + 0, 16 + 0xe, 16 + 0xf, 16 + 0xc},
|
||||
{16 + 7, 16 + 6, 16 + 8, 16 + 9, 16 + 2},
|
||||
{16 + 5, 16 + 4, 16 + 0xa, 16 + 0xb, 16 + 6},
|
||||
},
|
||||
},
|
||||
{
|
||||
keyScheduleA{
|
||||
{0, 6, 16 + 5, 16 + 7, 16 + 4, 16 + 6, 16 + 0},
|
||||
{1, 4, 0, 2, 1, 3, 16 + 2},
|
||||
{2, 5, 7, 6, 5, 4, 16 + 1},
|
||||
{3, 7, 0xa, 9, 0xb, 8, 16 + 3},
|
||||
},
|
||||
keyScheduleB{
|
||||
{8, 9, 7, 6, 3},
|
||||
{0xa, 0xb, 5, 4, 7},
|
||||
{0xc, 0xd, 3, 2, 8},
|
||||
{0xe, 0xf, 1, 0, 0xd},
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
func (c *Cipher) keySchedule(in []byte) {
|
||||
var t [8]uint32
|
||||
var k [32]uint32
|
||||
|
||||
for i := 0; i < 4; i++ {
|
||||
j := i * 4
|
||||
t[i] = uint32(in[j])<<24 | uint32(in[j+1])<<16 | uint32(in[j+2])<<8 | uint32(in[j+3])
|
||||
}
|
||||
|
||||
x := []byte{6, 7, 4, 5}
|
||||
ki := 0
|
||||
|
||||
for half := 0; half < 2; half++ {
|
||||
for _, round := range schedule {
|
||||
for j := 0; j < 4; j++ {
|
||||
var a [7]uint8
|
||||
copy(a[:], round.a[j][:])
|
||||
w := t[a[1]]
|
||||
w ^= sBox[4][(t[a[2]>>2]>>(24-8*(a[2]&3)))&0xff]
|
||||
w ^= sBox[5][(t[a[3]>>2]>>(24-8*(a[3]&3)))&0xff]
|
||||
w ^= sBox[6][(t[a[4]>>2]>>(24-8*(a[4]&3)))&0xff]
|
||||
w ^= sBox[7][(t[a[5]>>2]>>(24-8*(a[5]&3)))&0xff]
|
||||
w ^= sBox[x[j]][(t[a[6]>>2]>>(24-8*(a[6]&3)))&0xff]
|
||||
t[a[0]] = w
|
||||
}
|
||||
|
||||
for j := 0; j < 4; j++ {
|
||||
var b [5]uint8
|
||||
copy(b[:], round.b[j][:])
|
||||
w := sBox[4][(t[b[0]>>2]>>(24-8*(b[0]&3)))&0xff]
|
||||
w ^= sBox[5][(t[b[1]>>2]>>(24-8*(b[1]&3)))&0xff]
|
||||
w ^= sBox[6][(t[b[2]>>2]>>(24-8*(b[2]&3)))&0xff]
|
||||
w ^= sBox[7][(t[b[3]>>2]>>(24-8*(b[3]&3)))&0xff]
|
||||
w ^= sBox[4+j][(t[b[4]>>2]>>(24-8*(b[4]&3)))&0xff]
|
||||
k[ki] = w
|
||||
ki++
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for i := 0; i < 16; i++ {
|
||||
c.masking[i] = k[i]
|
||||
c.rotate[i] = uint8(k[16+i] & 0x1f)
|
||||
}
|
||||
}
|
||||
|
||||
// These are the three 'f' functions. See RFC 2144, section 2.2.
|
||||
func f1(d, m uint32, r uint8) uint32 {
|
||||
t := m + d
|
||||
I := (t << r) | (t >> (32 - r))
|
||||
return ((sBox[0][I>>24] ^ sBox[1][(I>>16)&0xff]) - sBox[2][(I>>8)&0xff]) + sBox[3][I&0xff]
|
||||
}
|
||||
|
||||
func f2(d, m uint32, r uint8) uint32 {
|
||||
t := m ^ d
|
||||
I := (t << r) | (t >> (32 - r))
|
||||
return ((sBox[0][I>>24] - sBox[1][(I>>16)&0xff]) + sBox[2][(I>>8)&0xff]) ^ sBox[3][I&0xff]
|
||||
}
|
||||
|
||||
func f3(d, m uint32, r uint8) uint32 {
|
||||
t := m - d
|
||||
I := (t << r) | (t >> (32 - r))
|
||||
return ((sBox[0][I>>24] + sBox[1][(I>>16)&0xff]) ^ sBox[2][(I>>8)&0xff]) - sBox[3][I&0xff]
|
||||
}
|
||||
|
||||
var sBox = [8][256]uint32{
|
||||
{
|
||||
0x30fb40d4, 0x9fa0ff0b, 0x6beccd2f, 0x3f258c7a, 0x1e213f2f, 0x9c004dd3, 0x6003e540, 0xcf9fc949,
|
||||
0xbfd4af27, 0x88bbbdb5, 0xe2034090, 0x98d09675, 0x6e63a0e0, 0x15c361d2, 0xc2e7661d, 0x22d4ff8e,
|
||||
0x28683b6f, 0xc07fd059, 0xff2379c8, 0x775f50e2, 0x43c340d3, 0xdf2f8656, 0x887ca41a, 0xa2d2bd2d,
|
||||
0xa1c9e0d6, 0x346c4819, 0x61b76d87, 0x22540f2f, 0x2abe32e1, 0xaa54166b, 0x22568e3a, 0xa2d341d0,
|
||||
0x66db40c8, 0xa784392f, 0x004dff2f, 0x2db9d2de, 0x97943fac, 0x4a97c1d8, 0x527644b7, 0xb5f437a7,
|
||||
0xb82cbaef, 0xd751d159, 0x6ff7f0ed, 0x5a097a1f, 0x827b68d0, 0x90ecf52e, 0x22b0c054, 0xbc8e5935,
|
||||
0x4b6d2f7f, 0x50bb64a2, 0xd2664910, 0xbee5812d, 0xb7332290, 0xe93b159f, 0xb48ee411, 0x4bff345d,
|
||||
0xfd45c240, 0xad31973f, 0xc4f6d02e, 0x55fc8165, 0xd5b1caad, 0xa1ac2dae, 0xa2d4b76d, 0xc19b0c50,
|
||||
0x882240f2, 0x0c6e4f38, 0xa4e4bfd7, 0x4f5ba272, 0x564c1d2f, 0xc59c5319, 0xb949e354, 0xb04669fe,
|
||||
0xb1b6ab8a, 0xc71358dd, 0x6385c545, 0x110f935d, 0x57538ad5, 0x6a390493, 0xe63d37e0, 0x2a54f6b3,
|
||||
0x3a787d5f, 0x6276a0b5, 0x19a6fcdf, 0x7a42206a, 0x29f9d4d5, 0xf61b1891, 0xbb72275e, 0xaa508167,
|
||||
0x38901091, 0xc6b505eb, 0x84c7cb8c, 0x2ad75a0f, 0x874a1427, 0xa2d1936b, 0x2ad286af, 0xaa56d291,
|
||||
0xd7894360, 0x425c750d, 0x93b39e26, 0x187184c9, 0x6c00b32d, 0x73e2bb14, 0xa0bebc3c, 0x54623779,
|
||||
0x64459eab, 0x3f328b82, 0x7718cf82, 0x59a2cea6, 0x04ee002e, 0x89fe78e6, 0x3fab0950, 0x325ff6c2,
|
||||
0x81383f05, 0x6963c5c8, 0x76cb5ad6, 0xd49974c9, 0xca180dcf, 0x380782d5, 0xc7fa5cf6, 0x8ac31511,
|
||||
0x35e79e13, 0x47da91d0, 0xf40f9086, 0xa7e2419e, 0x31366241, 0x051ef495, 0xaa573b04, 0x4a805d8d,
|
||||
0x548300d0, 0x00322a3c, 0xbf64cddf, 0xba57a68e, 0x75c6372b, 0x50afd341, 0xa7c13275, 0x915a0bf5,
|
||||
0x6b54bfab, 0x2b0b1426, 0xab4cc9d7, 0x449ccd82, 0xf7fbf265, 0xab85c5f3, 0x1b55db94, 0xaad4e324,
|
||||
0xcfa4bd3f, 0x2deaa3e2, 0x9e204d02, 0xc8bd25ac, 0xeadf55b3, 0xd5bd9e98, 0xe31231b2, 0x2ad5ad6c,
|
||||
0x954329de, 0xadbe4528, 0xd8710f69, 0xaa51c90f, 0xaa786bf6, 0x22513f1e, 0xaa51a79b, 0x2ad344cc,
|
||||
0x7b5a41f0, 0xd37cfbad, 0x1b069505, 0x41ece491, 0xb4c332e6, 0x032268d4, 0xc9600acc, 0xce387e6d,
|
||||
0xbf6bb16c, 0x6a70fb78, 0x0d03d9c9, 0xd4df39de, 0xe01063da, 0x4736f464, 0x5ad328d8, 0xb347cc96,
|
||||
0x75bb0fc3, 0x98511bfb, 0x4ffbcc35, 0xb58bcf6a, 0xe11f0abc, 0xbfc5fe4a, 0xa70aec10, 0xac39570a,
|
||||
0x3f04442f, 0x6188b153, 0xe0397a2e, 0x5727cb79, 0x9ceb418f, 0x1cacd68d, 0x2ad37c96, 0x0175cb9d,
|
||||
0xc69dff09, 0xc75b65f0, 0xd9db40d8, 0xec0e7779, 0x4744ead4, 0xb11c3274, 0xdd24cb9e, 0x7e1c54bd,
|
||||
0xf01144f9, 0xd2240eb1, 0x9675b3fd, 0xa3ac3755, 0xd47c27af, 0x51c85f4d, 0x56907596, 0xa5bb15e6,
|
||||
0x580304f0, 0xca042cf1, 0x011a37ea, 0x8dbfaadb, 0x35ba3e4a, 0x3526ffa0, 0xc37b4d09, 0xbc306ed9,
|
||||
0x98a52666, 0x5648f725, 0xff5e569d, 0x0ced63d0, 0x7c63b2cf, 0x700b45e1, 0xd5ea50f1, 0x85a92872,
|
||||
0xaf1fbda7, 0xd4234870, 0xa7870bf3, 0x2d3b4d79, 0x42e04198, 0x0cd0ede7, 0x26470db8, 0xf881814c,
|
||||
0x474d6ad7, 0x7c0c5e5c, 0xd1231959, 0x381b7298, 0xf5d2f4db, 0xab838653, 0x6e2f1e23, 0x83719c9e,
|
||||
0xbd91e046, 0x9a56456e, 0xdc39200c, 0x20c8c571, 0x962bda1c, 0xe1e696ff, 0xb141ab08, 0x7cca89b9,
|
||||
0x1a69e783, 0x02cc4843, 0xa2f7c579, 0x429ef47d, 0x427b169c, 0x5ac9f049, 0xdd8f0f00, 0x5c8165bf,
|
||||
},
|
||||
{
|
||||
0x1f201094, 0xef0ba75b, 0x69e3cf7e, 0x393f4380, 0xfe61cf7a, 0xeec5207a, 0x55889c94, 0x72fc0651,
|
||||
0xada7ef79, 0x4e1d7235, 0xd55a63ce, 0xde0436ba, 0x99c430ef, 0x5f0c0794, 0x18dcdb7d, 0xa1d6eff3,
|
||||
0xa0b52f7b, 0x59e83605, 0xee15b094, 0xe9ffd909, 0xdc440086, 0xef944459, 0xba83ccb3, 0xe0c3cdfb,
|
||||
0xd1da4181, 0x3b092ab1, 0xf997f1c1, 0xa5e6cf7b, 0x01420ddb, 0xe4e7ef5b, 0x25a1ff41, 0xe180f806,
|
||||
0x1fc41080, 0x179bee7a, 0xd37ac6a9, 0xfe5830a4, 0x98de8b7f, 0x77e83f4e, 0x79929269, 0x24fa9f7b,
|
||||
0xe113c85b, 0xacc40083, 0xd7503525, 0xf7ea615f, 0x62143154, 0x0d554b63, 0x5d681121, 0xc866c359,
|
||||
0x3d63cf73, 0xcee234c0, 0xd4d87e87, 0x5c672b21, 0x071f6181, 0x39f7627f, 0x361e3084, 0xe4eb573b,
|
||||
0x602f64a4, 0xd63acd9c, 0x1bbc4635, 0x9e81032d, 0x2701f50c, 0x99847ab4, 0xa0e3df79, 0xba6cf38c,
|
||||
0x10843094, 0x2537a95e, 0xf46f6ffe, 0xa1ff3b1f, 0x208cfb6a, 0x8f458c74, 0xd9e0a227, 0x4ec73a34,
|
||||
0xfc884f69, 0x3e4de8df, 0xef0e0088, 0x3559648d, 0x8a45388c, 0x1d804366, 0x721d9bfd, 0xa58684bb,
|
||||
0xe8256333, 0x844e8212, 0x128d8098, 0xfed33fb4, 0xce280ae1, 0x27e19ba5, 0xd5a6c252, 0xe49754bd,
|
||||
0xc5d655dd, 0xeb667064, 0x77840b4d, 0xa1b6a801, 0x84db26a9, 0xe0b56714, 0x21f043b7, 0xe5d05860,
|
||||
0x54f03084, 0x066ff472, 0xa31aa153, 0xdadc4755, 0xb5625dbf, 0x68561be6, 0x83ca6b94, 0x2d6ed23b,
|
||||
0xeccf01db, 0xa6d3d0ba, 0xb6803d5c, 0xaf77a709, 0x33b4a34c, 0x397bc8d6, 0x5ee22b95, 0x5f0e5304,
|
||||
0x81ed6f61, 0x20e74364, 0xb45e1378, 0xde18639b, 0x881ca122, 0xb96726d1, 0x8049a7e8, 0x22b7da7b,
|
||||
0x5e552d25, 0x5272d237, 0x79d2951c, 0xc60d894c, 0x488cb402, 0x1ba4fe5b, 0xa4b09f6b, 0x1ca815cf,
|
||||
0xa20c3005, 0x8871df63, 0xb9de2fcb, 0x0cc6c9e9, 0x0beeff53, 0xe3214517, 0xb4542835, 0x9f63293c,
|
||||
0xee41e729, 0x6e1d2d7c, 0x50045286, 0x1e6685f3, 0xf33401c6, 0x30a22c95, 0x31a70850, 0x60930f13,
|
||||
0x73f98417, 0xa1269859, 0xec645c44, 0x52c877a9, 0xcdff33a6, 0xa02b1741, 0x7cbad9a2, 0x2180036f,
|
||||
0x50d99c08, 0xcb3f4861, 0xc26bd765, 0x64a3f6ab, 0x80342676, 0x25a75e7b, 0xe4e6d1fc, 0x20c710e6,
|
||||
0xcdf0b680, 0x17844d3b, 0x31eef84d, 0x7e0824e4, 0x2ccb49eb, 0x846a3bae, 0x8ff77888, 0xee5d60f6,
|
||||
0x7af75673, 0x2fdd5cdb, 0xa11631c1, 0x30f66f43, 0xb3faec54, 0x157fd7fa, 0xef8579cc, 0xd152de58,
|
||||
0xdb2ffd5e, 0x8f32ce19, 0x306af97a, 0x02f03ef8, 0x99319ad5, 0xc242fa0f, 0xa7e3ebb0, 0xc68e4906,
|
||||
0xb8da230c, 0x80823028, 0xdcdef3c8, 0xd35fb171, 0x088a1bc8, 0xbec0c560, 0x61a3c9e8, 0xbca8f54d,
|
||||
0xc72feffa, 0x22822e99, 0x82c570b4, 0xd8d94e89, 0x8b1c34bc, 0x301e16e6, 0x273be979, 0xb0ffeaa6,
|
||||
0x61d9b8c6, 0x00b24869, 0xb7ffce3f, 0x08dc283b, 0x43daf65a, 0xf7e19798, 0x7619b72f, 0x8f1c9ba4,
|
||||
0xdc8637a0, 0x16a7d3b1, 0x9fc393b7, 0xa7136eeb, 0xc6bcc63e, 0x1a513742, 0xef6828bc, 0x520365d6,
|
||||
0x2d6a77ab, 0x3527ed4b, 0x821fd216, 0x095c6e2e, 0xdb92f2fb, 0x5eea29cb, 0x145892f5, 0x91584f7f,
|
||||
0x5483697b, 0x2667a8cc, 0x85196048, 0x8c4bacea, 0x833860d4, 0x0d23e0f9, 0x6c387e8a, 0x0ae6d249,
|
||||
0xb284600c, 0xd835731d, 0xdcb1c647, 0xac4c56ea, 0x3ebd81b3, 0x230eabb0, 0x6438bc87, 0xf0b5b1fa,
|
||||
0x8f5ea2b3, 0xfc184642, 0x0a036b7a, 0x4fb089bd, 0x649da589, 0xa345415e, 0x5c038323, 0x3e5d3bb9,
|
||||
0x43d79572, 0x7e6dd07c, 0x06dfdf1e, 0x6c6cc4ef, 0x7160a539, 0x73bfbe70, 0x83877605, 0x4523ecf1,
|
||||
},
|
||||
{
|
||||
0x8defc240, 0x25fa5d9f, 0xeb903dbf, 0xe810c907, 0x47607fff, 0x369fe44b, 0x8c1fc644, 0xaececa90,
|
||||
0xbeb1f9bf, 0xeefbcaea, 0xe8cf1950, 0x51df07ae, 0x920e8806, 0xf0ad0548, 0xe13c8d83, 0x927010d5,
|
||||
0x11107d9f, 0x07647db9, 0xb2e3e4d4, 0x3d4f285e, 0xb9afa820, 0xfade82e0, 0xa067268b, 0x8272792e,
|
||||
0x553fb2c0, 0x489ae22b, 0xd4ef9794, 0x125e3fbc, 0x21fffcee, 0x825b1bfd, 0x9255c5ed, 0x1257a240,
|
||||
0x4e1a8302, 0xbae07fff, 0x528246e7, 0x8e57140e, 0x3373f7bf, 0x8c9f8188, 0xa6fc4ee8, 0xc982b5a5,
|
||||
0xa8c01db7, 0x579fc264, 0x67094f31, 0xf2bd3f5f, 0x40fff7c1, 0x1fb78dfc, 0x8e6bd2c1, 0x437be59b,
|
||||
0x99b03dbf, 0xb5dbc64b, 0x638dc0e6, 0x55819d99, 0xa197c81c, 0x4a012d6e, 0xc5884a28, 0xccc36f71,
|
||||
0xb843c213, 0x6c0743f1, 0x8309893c, 0x0feddd5f, 0x2f7fe850, 0xd7c07f7e, 0x02507fbf, 0x5afb9a04,
|
||||
0xa747d2d0, 0x1651192e, 0xaf70bf3e, 0x58c31380, 0x5f98302e, 0x727cc3c4, 0x0a0fb402, 0x0f7fef82,
|
||||
0x8c96fdad, 0x5d2c2aae, 0x8ee99a49, 0x50da88b8, 0x8427f4a0, 0x1eac5790, 0x796fb449, 0x8252dc15,
|
||||
0xefbd7d9b, 0xa672597d, 0xada840d8, 0x45f54504, 0xfa5d7403, 0xe83ec305, 0x4f91751a, 0x925669c2,
|
||||
0x23efe941, 0xa903f12e, 0x60270df2, 0x0276e4b6, 0x94fd6574, 0x927985b2, 0x8276dbcb, 0x02778176,
|
||||
0xf8af918d, 0x4e48f79e, 0x8f616ddf, 0xe29d840e, 0x842f7d83, 0x340ce5c8, 0x96bbb682, 0x93b4b148,
|
||||
0xef303cab, 0x984faf28, 0x779faf9b, 0x92dc560d, 0x224d1e20, 0x8437aa88, 0x7d29dc96, 0x2756d3dc,
|
||||
0x8b907cee, 0xb51fd240, 0xe7c07ce3, 0xe566b4a1, 0xc3e9615e, 0x3cf8209d, 0x6094d1e3, 0xcd9ca341,
|
||||
0x5c76460e, 0x00ea983b, 0xd4d67881, 0xfd47572c, 0xf76cedd9, 0xbda8229c, 0x127dadaa, 0x438a074e,
|
||||
0x1f97c090, 0x081bdb8a, 0x93a07ebe, 0xb938ca15, 0x97b03cff, 0x3dc2c0f8, 0x8d1ab2ec, 0x64380e51,
|
||||
0x68cc7bfb, 0xd90f2788, 0x12490181, 0x5de5ffd4, 0xdd7ef86a, 0x76a2e214, 0xb9a40368, 0x925d958f,
|
||||
0x4b39fffa, 0xba39aee9, 0xa4ffd30b, 0xfaf7933b, 0x6d498623, 0x193cbcfa, 0x27627545, 0x825cf47a,
|
||||
0x61bd8ba0, 0xd11e42d1, 0xcead04f4, 0x127ea392, 0x10428db7, 0x8272a972, 0x9270c4a8, 0x127de50b,
|
||||
0x285ba1c8, 0x3c62f44f, 0x35c0eaa5, 0xe805d231, 0x428929fb, 0xb4fcdf82, 0x4fb66a53, 0x0e7dc15b,
|
||||
0x1f081fab, 0x108618ae, 0xfcfd086d, 0xf9ff2889, 0x694bcc11, 0x236a5cae, 0x12deca4d, 0x2c3f8cc5,
|
||||
0xd2d02dfe, 0xf8ef5896, 0xe4cf52da, 0x95155b67, 0x494a488c, 0xb9b6a80c, 0x5c8f82bc, 0x89d36b45,
|
||||
0x3a609437, 0xec00c9a9, 0x44715253, 0x0a874b49, 0xd773bc40, 0x7c34671c, 0x02717ef6, 0x4feb5536,
|
||||
0xa2d02fff, 0xd2bf60c4, 0xd43f03c0, 0x50b4ef6d, 0x07478cd1, 0x006e1888, 0xa2e53f55, 0xb9e6d4bc,
|
||||
0xa2048016, 0x97573833, 0xd7207d67, 0xde0f8f3d, 0x72f87b33, 0xabcc4f33, 0x7688c55d, 0x7b00a6b0,
|
||||
0x947b0001, 0x570075d2, 0xf9bb88f8, 0x8942019e, 0x4264a5ff, 0x856302e0, 0x72dbd92b, 0xee971b69,
|
||||
0x6ea22fde, 0x5f08ae2b, 0xaf7a616d, 0xe5c98767, 0xcf1febd2, 0x61efc8c2, 0xf1ac2571, 0xcc8239c2,
|
||||
0x67214cb8, 0xb1e583d1, 0xb7dc3e62, 0x7f10bdce, 0xf90a5c38, 0x0ff0443d, 0x606e6dc6, 0x60543a49,
|
||||
0x5727c148, 0x2be98a1d, 0x8ab41738, 0x20e1be24, 0xaf96da0f, 0x68458425, 0x99833be5, 0x600d457d,
|
||||
0x282f9350, 0x8334b362, 0xd91d1120, 0x2b6d8da0, 0x642b1e31, 0x9c305a00, 0x52bce688, 0x1b03588a,
|
||||
0xf7baefd5, 0x4142ed9c, 0xa4315c11, 0x83323ec5, 0xdfef4636, 0xa133c501, 0xe9d3531c, 0xee353783,
|
||||
},
|
||||
{
|
||||
0x9db30420, 0x1fb6e9de, 0xa7be7bef, 0xd273a298, 0x4a4f7bdb, 0x64ad8c57, 0x85510443, 0xfa020ed1,
|
||||
0x7e287aff, 0xe60fb663, 0x095f35a1, 0x79ebf120, 0xfd059d43, 0x6497b7b1, 0xf3641f63, 0x241e4adf,
|
||||
0x28147f5f, 0x4fa2b8cd, 0xc9430040, 0x0cc32220, 0xfdd30b30, 0xc0a5374f, 0x1d2d00d9, 0x24147b15,
|
||||
0xee4d111a, 0x0fca5167, 0x71ff904c, 0x2d195ffe, 0x1a05645f, 0x0c13fefe, 0x081b08ca, 0x05170121,
|
||||
0x80530100, 0xe83e5efe, 0xac9af4f8, 0x7fe72701, 0xd2b8ee5f, 0x06df4261, 0xbb9e9b8a, 0x7293ea25,
|
||||
0xce84ffdf, 0xf5718801, 0x3dd64b04, 0xa26f263b, 0x7ed48400, 0x547eebe6, 0x446d4ca0, 0x6cf3d6f5,
|
||||
0x2649abdf, 0xaea0c7f5, 0x36338cc1, 0x503f7e93, 0xd3772061, 0x11b638e1, 0x72500e03, 0xf80eb2bb,
|
||||
0xabe0502e, 0xec8d77de, 0x57971e81, 0xe14f6746, 0xc9335400, 0x6920318f, 0x081dbb99, 0xffc304a5,
|
||||
0x4d351805, 0x7f3d5ce3, 0xa6c866c6, 0x5d5bcca9, 0xdaec6fea, 0x9f926f91, 0x9f46222f, 0x3991467d,
|
||||
0xa5bf6d8e, 0x1143c44f, 0x43958302, 0xd0214eeb, 0x022083b8, 0x3fb6180c, 0x18f8931e, 0x281658e6,
|
||||
0x26486e3e, 0x8bd78a70, 0x7477e4c1, 0xb506e07c, 0xf32d0a25, 0x79098b02, 0xe4eabb81, 0x28123b23,
|
||||
0x69dead38, 0x1574ca16, 0xdf871b62, 0x211c40b7, 0xa51a9ef9, 0x0014377b, 0x041e8ac8, 0x09114003,
|
||||
0xbd59e4d2, 0xe3d156d5, 0x4fe876d5, 0x2f91a340, 0x557be8de, 0x00eae4a7, 0x0ce5c2ec, 0x4db4bba6,
|
||||
0xe756bdff, 0xdd3369ac, 0xec17b035, 0x06572327, 0x99afc8b0, 0x56c8c391, 0x6b65811c, 0x5e146119,
|
||||
0x6e85cb75, 0xbe07c002, 0xc2325577, 0x893ff4ec, 0x5bbfc92d, 0xd0ec3b25, 0xb7801ab7, 0x8d6d3b24,
|
||||
0x20c763ef, 0xc366a5fc, 0x9c382880, 0x0ace3205, 0xaac9548a, 0xeca1d7c7, 0x041afa32, 0x1d16625a,
|
||||
0x6701902c, 0x9b757a54, 0x31d477f7, 0x9126b031, 0x36cc6fdb, 0xc70b8b46, 0xd9e66a48, 0x56e55a79,
|
||||
0x026a4ceb, 0x52437eff, 0x2f8f76b4, 0x0df980a5, 0x8674cde3, 0xedda04eb, 0x17a9be04, 0x2c18f4df,
|
||||
0xb7747f9d, 0xab2af7b4, 0xefc34d20, 0x2e096b7c, 0x1741a254, 0xe5b6a035, 0x213d42f6, 0x2c1c7c26,
|
||||
0x61c2f50f, 0x6552daf9, 0xd2c231f8, 0x25130f69, 0xd8167fa2, 0x0418f2c8, 0x001a96a6, 0x0d1526ab,
|
||||
0x63315c21, 0x5e0a72ec, 0x49bafefd, 0x187908d9, 0x8d0dbd86, 0x311170a7, 0x3e9b640c, 0xcc3e10d7,
|
||||
0xd5cad3b6, 0x0caec388, 0xf73001e1, 0x6c728aff, 0x71eae2a1, 0x1f9af36e, 0xcfcbd12f, 0xc1de8417,
|
||||
0xac07be6b, 0xcb44a1d8, 0x8b9b0f56, 0x013988c3, 0xb1c52fca, 0xb4be31cd, 0xd8782806, 0x12a3a4e2,
|
||||
0x6f7de532, 0x58fd7eb6, 0xd01ee900, 0x24adffc2, 0xf4990fc5, 0x9711aac5, 0x001d7b95, 0x82e5e7d2,
|
||||
0x109873f6, 0x00613096, 0xc32d9521, 0xada121ff, 0x29908415, 0x7fbb977f, 0xaf9eb3db, 0x29c9ed2a,
|
||||
0x5ce2a465, 0xa730f32c, 0xd0aa3fe8, 0x8a5cc091, 0xd49e2ce7, 0x0ce454a9, 0xd60acd86, 0x015f1919,
|
||||
0x77079103, 0xdea03af6, 0x78a8565e, 0xdee356df, 0x21f05cbe, 0x8b75e387, 0xb3c50651, 0xb8a5c3ef,
|
||||
0xd8eeb6d2, 0xe523be77, 0xc2154529, 0x2f69efdf, 0xafe67afb, 0xf470c4b2, 0xf3e0eb5b, 0xd6cc9876,
|
||||
0x39e4460c, 0x1fda8538, 0x1987832f, 0xca007367, 0xa99144f8, 0x296b299e, 0x492fc295, 0x9266beab,
|
||||
0xb5676e69, 0x9bd3ddda, 0xdf7e052f, 0xdb25701c, 0x1b5e51ee, 0xf65324e6, 0x6afce36c, 0x0316cc04,
|
||||
0x8644213e, 0xb7dc59d0, 0x7965291f, 0xccd6fd43, 0x41823979, 0x932bcdf6, 0xb657c34d, 0x4edfd282,
|
||||
0x7ae5290c, 0x3cb9536b, 0x851e20fe, 0x9833557e, 0x13ecf0b0, 0xd3ffb372, 0x3f85c5c1, 0x0aef7ed2,
|
||||
},
|
||||
{
|
||||
0x7ec90c04, 0x2c6e74b9, 0x9b0e66df, 0xa6337911, 0xb86a7fff, 0x1dd358f5, 0x44dd9d44, 0x1731167f,
|
||||
0x08fbf1fa, 0xe7f511cc, 0xd2051b00, 0x735aba00, 0x2ab722d8, 0x386381cb, 0xacf6243a, 0x69befd7a,
|
||||
0xe6a2e77f, 0xf0c720cd, 0xc4494816, 0xccf5c180, 0x38851640, 0x15b0a848, 0xe68b18cb, 0x4caadeff,
|
||||
0x5f480a01, 0x0412b2aa, 0x259814fc, 0x41d0efe2, 0x4e40b48d, 0x248eb6fb, 0x8dba1cfe, 0x41a99b02,
|
||||
0x1a550a04, 0xba8f65cb, 0x7251f4e7, 0x95a51725, 0xc106ecd7, 0x97a5980a, 0xc539b9aa, 0x4d79fe6a,
|
||||
0xf2f3f763, 0x68af8040, 0xed0c9e56, 0x11b4958b, 0xe1eb5a88, 0x8709e6b0, 0xd7e07156, 0x4e29fea7,
|
||||
0x6366e52d, 0x02d1c000, 0xc4ac8e05, 0x9377f571, 0x0c05372a, 0x578535f2, 0x2261be02, 0xd642a0c9,
|
||||
0xdf13a280, 0x74b55bd2, 0x682199c0, 0xd421e5ec, 0x53fb3ce8, 0xc8adedb3, 0x28a87fc9, 0x3d959981,
|
||||
0x5c1ff900, 0xfe38d399, 0x0c4eff0b, 0x062407ea, 0xaa2f4fb1, 0x4fb96976, 0x90c79505, 0xb0a8a774,
|
||||
0xef55a1ff, 0xe59ca2c2, 0xa6b62d27, 0xe66a4263, 0xdf65001f, 0x0ec50966, 0xdfdd55bc, 0x29de0655,
|
||||
0x911e739a, 0x17af8975, 0x32c7911c, 0x89f89468, 0x0d01e980, 0x524755f4, 0x03b63cc9, 0x0cc844b2,
|
||||
0xbcf3f0aa, 0x87ac36e9, 0xe53a7426, 0x01b3d82b, 0x1a9e7449, 0x64ee2d7e, 0xcddbb1da, 0x01c94910,
|
||||
0xb868bf80, 0x0d26f3fd, 0x9342ede7, 0x04a5c284, 0x636737b6, 0x50f5b616, 0xf24766e3, 0x8eca36c1,
|
||||
0x136e05db, 0xfef18391, 0xfb887a37, 0xd6e7f7d4, 0xc7fb7dc9, 0x3063fcdf, 0xb6f589de, 0xec2941da,
|
||||
0x26e46695, 0xb7566419, 0xf654efc5, 0xd08d58b7, 0x48925401, 0xc1bacb7f, 0xe5ff550f, 0xb6083049,
|
||||
0x5bb5d0e8, 0x87d72e5a, 0xab6a6ee1, 0x223a66ce, 0xc62bf3cd, 0x9e0885f9, 0x68cb3e47, 0x086c010f,
|
||||
0xa21de820, 0xd18b69de, 0xf3f65777, 0xfa02c3f6, 0x407edac3, 0xcbb3d550, 0x1793084d, 0xb0d70eba,
|
||||
0x0ab378d5, 0xd951fb0c, 0xded7da56, 0x4124bbe4, 0x94ca0b56, 0x0f5755d1, 0xe0e1e56e, 0x6184b5be,
|
||||
0x580a249f, 0x94f74bc0, 0xe327888e, 0x9f7b5561, 0xc3dc0280, 0x05687715, 0x646c6bd7, 0x44904db3,
|
||||
0x66b4f0a3, 0xc0f1648a, 0x697ed5af, 0x49e92ff6, 0x309e374f, 0x2cb6356a, 0x85808573, 0x4991f840,
|
||||
0x76f0ae02, 0x083be84d, 0x28421c9a, 0x44489406, 0x736e4cb8, 0xc1092910, 0x8bc95fc6, 0x7d869cf4,
|
||||
0x134f616f, 0x2e77118d, 0xb31b2be1, 0xaa90b472, 0x3ca5d717, 0x7d161bba, 0x9cad9010, 0xaf462ba2,
|
||||
0x9fe459d2, 0x45d34559, 0xd9f2da13, 0xdbc65487, 0xf3e4f94e, 0x176d486f, 0x097c13ea, 0x631da5c7,
|
||||
0x445f7382, 0x175683f4, 0xcdc66a97, 0x70be0288, 0xb3cdcf72, 0x6e5dd2f3, 0x20936079, 0x459b80a5,
|
||||
0xbe60e2db, 0xa9c23101, 0xeba5315c, 0x224e42f2, 0x1c5c1572, 0xf6721b2c, 0x1ad2fff3, 0x8c25404e,
|
||||
0x324ed72f, 0x4067b7fd, 0x0523138e, 0x5ca3bc78, 0xdc0fd66e, 0x75922283, 0x784d6b17, 0x58ebb16e,
|
||||
0x44094f85, 0x3f481d87, 0xfcfeae7b, 0x77b5ff76, 0x8c2302bf, 0xaaf47556, 0x5f46b02a, 0x2b092801,
|
||||
0x3d38f5f7, 0x0ca81f36, 0x52af4a8a, 0x66d5e7c0, 0xdf3b0874, 0x95055110, 0x1b5ad7a8, 0xf61ed5ad,
|
||||
0x6cf6e479, 0x20758184, 0xd0cefa65, 0x88f7be58, 0x4a046826, 0x0ff6f8f3, 0xa09c7f70, 0x5346aba0,
|
||||
0x5ce96c28, 0xe176eda3, 0x6bac307f, 0x376829d2, 0x85360fa9, 0x17e3fe2a, 0x24b79767, 0xf5a96b20,
|
||||
0xd6cd2595, 0x68ff1ebf, 0x7555442c, 0xf19f06be, 0xf9e0659a, 0xeeb9491d, 0x34010718, 0xbb30cab8,
|
||||
0xe822fe15, 0x88570983, 0x750e6249, 0xda627e55, 0x5e76ffa8, 0xb1534546, 0x6d47de08, 0xefe9e7d4,
|
||||
},
|
||||
{
|
||||
0xf6fa8f9d, 0x2cac6ce1, 0x4ca34867, 0xe2337f7c, 0x95db08e7, 0x016843b4, 0xeced5cbc, 0x325553ac,
|
||||
0xbf9f0960, 0xdfa1e2ed, 0x83f0579d, 0x63ed86b9, 0x1ab6a6b8, 0xde5ebe39, 0xf38ff732, 0x8989b138,
|
||||
0x33f14961, 0xc01937bd, 0xf506c6da, 0xe4625e7e, 0xa308ea99, 0x4e23e33c, 0x79cbd7cc, 0x48a14367,
|
||||
0xa3149619, 0xfec94bd5, 0xa114174a, 0xeaa01866, 0xa084db2d, 0x09a8486f, 0xa888614a, 0x2900af98,
|
||||
0x01665991, 0xe1992863, 0xc8f30c60, 0x2e78ef3c, 0xd0d51932, 0xcf0fec14, 0xf7ca07d2, 0xd0a82072,
|
||||
0xfd41197e, 0x9305a6b0, 0xe86be3da, 0x74bed3cd, 0x372da53c, 0x4c7f4448, 0xdab5d440, 0x6dba0ec3,
|
||||
0x083919a7, 0x9fbaeed9, 0x49dbcfb0, 0x4e670c53, 0x5c3d9c01, 0x64bdb941, 0x2c0e636a, 0xba7dd9cd,
|
||||
0xea6f7388, 0xe70bc762, 0x35f29adb, 0x5c4cdd8d, 0xf0d48d8c, 0xb88153e2, 0x08a19866, 0x1ae2eac8,
|
||||
0x284caf89, 0xaa928223, 0x9334be53, 0x3b3a21bf, 0x16434be3, 0x9aea3906, 0xefe8c36e, 0xf890cdd9,
|
||||
0x80226dae, 0xc340a4a3, 0xdf7e9c09, 0xa694a807, 0x5b7c5ecc, 0x221db3a6, 0x9a69a02f, 0x68818a54,
|
||||
0xceb2296f, 0x53c0843a, 0xfe893655, 0x25bfe68a, 0xb4628abc, 0xcf222ebf, 0x25ac6f48, 0xa9a99387,
|
||||
0x53bddb65, 0xe76ffbe7, 0xe967fd78, 0x0ba93563, 0x8e342bc1, 0xe8a11be9, 0x4980740d, 0xc8087dfc,
|
||||
0x8de4bf99, 0xa11101a0, 0x7fd37975, 0xda5a26c0, 0xe81f994f, 0x9528cd89, 0xfd339fed, 0xb87834bf,
|
||||
0x5f04456d, 0x22258698, 0xc9c4c83b, 0x2dc156be, 0x4f628daa, 0x57f55ec5, 0xe2220abe, 0xd2916ebf,
|
||||
0x4ec75b95, 0x24f2c3c0, 0x42d15d99, 0xcd0d7fa0, 0x7b6e27ff, 0xa8dc8af0, 0x7345c106, 0xf41e232f,
|
||||
0x35162386, 0xe6ea8926, 0x3333b094, 0x157ec6f2, 0x372b74af, 0x692573e4, 0xe9a9d848, 0xf3160289,
|
||||
0x3a62ef1d, 0xa787e238, 0xf3a5f676, 0x74364853, 0x20951063, 0x4576698d, 0xb6fad407, 0x592af950,
|
||||
0x36f73523, 0x4cfb6e87, 0x7da4cec0, 0x6c152daa, 0xcb0396a8, 0xc50dfe5d, 0xfcd707ab, 0x0921c42f,
|
||||
0x89dff0bb, 0x5fe2be78, 0x448f4f33, 0x754613c9, 0x2b05d08d, 0x48b9d585, 0xdc049441, 0xc8098f9b,
|
||||
0x7dede786, 0xc39a3373, 0x42410005, 0x6a091751, 0x0ef3c8a6, 0x890072d6, 0x28207682, 0xa9a9f7be,
|
||||
0xbf32679d, 0xd45b5b75, 0xb353fd00, 0xcbb0e358, 0x830f220a, 0x1f8fb214, 0xd372cf08, 0xcc3c4a13,
|
||||
0x8cf63166, 0x061c87be, 0x88c98f88, 0x6062e397, 0x47cf8e7a, 0xb6c85283, 0x3cc2acfb, 0x3fc06976,
|
||||
0x4e8f0252, 0x64d8314d, 0xda3870e3, 0x1e665459, 0xc10908f0, 0x513021a5, 0x6c5b68b7, 0x822f8aa0,
|
||||
0x3007cd3e, 0x74719eef, 0xdc872681, 0x073340d4, 0x7e432fd9, 0x0c5ec241, 0x8809286c, 0xf592d891,
|
||||
0x08a930f6, 0x957ef305, 0xb7fbffbd, 0xc266e96f, 0x6fe4ac98, 0xb173ecc0, 0xbc60b42a, 0x953498da,
|
||||
0xfba1ae12, 0x2d4bd736, 0x0f25faab, 0xa4f3fceb, 0xe2969123, 0x257f0c3d, 0x9348af49, 0x361400bc,
|
||||
0xe8816f4a, 0x3814f200, 0xa3f94043, 0x9c7a54c2, 0xbc704f57, 0xda41e7f9, 0xc25ad33a, 0x54f4a084,
|
||||
0xb17f5505, 0x59357cbe, 0xedbd15c8, 0x7f97c5ab, 0xba5ac7b5, 0xb6f6deaf, 0x3a479c3a, 0x5302da25,
|
||||
0x653d7e6a, 0x54268d49, 0x51a477ea, 0x5017d55b, 0xd7d25d88, 0x44136c76, 0x0404a8c8, 0xb8e5a121,
|
||||
0xb81a928a, 0x60ed5869, 0x97c55b96, 0xeaec991b, 0x29935913, 0x01fdb7f1, 0x088e8dfa, 0x9ab6f6f5,
|
||||
0x3b4cbf9f, 0x4a5de3ab, 0xe6051d35, 0xa0e1d855, 0xd36b4cf1, 0xf544edeb, 0xb0e93524, 0xbebb8fbd,
|
||||
0xa2d762cf, 0x49c92f54, 0x38b5f331, 0x7128a454, 0x48392905, 0xa65b1db8, 0x851c97bd, 0xd675cf2f,
|
||||
},
|
||||
{
|
||||
0x85e04019, 0x332bf567, 0x662dbfff, 0xcfc65693, 0x2a8d7f6f, 0xab9bc912, 0xde6008a1, 0x2028da1f,
|
||||
0x0227bce7, 0x4d642916, 0x18fac300, 0x50f18b82, 0x2cb2cb11, 0xb232e75c, 0x4b3695f2, 0xb28707de,
|
||||
0xa05fbcf6, 0xcd4181e9, 0xe150210c, 0xe24ef1bd, 0xb168c381, 0xfde4e789, 0x5c79b0d8, 0x1e8bfd43,
|
||||
0x4d495001, 0x38be4341, 0x913cee1d, 0x92a79c3f, 0x089766be, 0xbaeeadf4, 0x1286becf, 0xb6eacb19,
|
||||
0x2660c200, 0x7565bde4, 0x64241f7a, 0x8248dca9, 0xc3b3ad66, 0x28136086, 0x0bd8dfa8, 0x356d1cf2,
|
||||
0x107789be, 0xb3b2e9ce, 0x0502aa8f, 0x0bc0351e, 0x166bf52a, 0xeb12ff82, 0xe3486911, 0xd34d7516,
|
||||
0x4e7b3aff, 0x5f43671b, 0x9cf6e037, 0x4981ac83, 0x334266ce, 0x8c9341b7, 0xd0d854c0, 0xcb3a6c88,
|
||||
0x47bc2829, 0x4725ba37, 0xa66ad22b, 0x7ad61f1e, 0x0c5cbafa, 0x4437f107, 0xb6e79962, 0x42d2d816,
|
||||
0x0a961288, 0xe1a5c06e, 0x13749e67, 0x72fc081a, 0xb1d139f7, 0xf9583745, 0xcf19df58, 0xbec3f756,
|
||||
0xc06eba30, 0x07211b24, 0x45c28829, 0xc95e317f, 0xbc8ec511, 0x38bc46e9, 0xc6e6fa14, 0xbae8584a,
|
||||
0xad4ebc46, 0x468f508b, 0x7829435f, 0xf124183b, 0x821dba9f, 0xaff60ff4, 0xea2c4e6d, 0x16e39264,
|
||||
0x92544a8b, 0x009b4fc3, 0xaba68ced, 0x9ac96f78, 0x06a5b79a, 0xb2856e6e, 0x1aec3ca9, 0xbe838688,
|
||||
0x0e0804e9, 0x55f1be56, 0xe7e5363b, 0xb3a1f25d, 0xf7debb85, 0x61fe033c, 0x16746233, 0x3c034c28,
|
||||
0xda6d0c74, 0x79aac56c, 0x3ce4e1ad, 0x51f0c802, 0x98f8f35a, 0x1626a49f, 0xeed82b29, 0x1d382fe3,
|
||||
0x0c4fb99a, 0xbb325778, 0x3ec6d97b, 0x6e77a6a9, 0xcb658b5c, 0xd45230c7, 0x2bd1408b, 0x60c03eb7,
|
||||
0xb9068d78, 0xa33754f4, 0xf430c87d, 0xc8a71302, 0xb96d8c32, 0xebd4e7be, 0xbe8b9d2d, 0x7979fb06,
|
||||
0xe7225308, 0x8b75cf77, 0x11ef8da4, 0xe083c858, 0x8d6b786f, 0x5a6317a6, 0xfa5cf7a0, 0x5dda0033,
|
||||
0xf28ebfb0, 0xf5b9c310, 0xa0eac280, 0x08b9767a, 0xa3d9d2b0, 0x79d34217, 0x021a718d, 0x9ac6336a,
|
||||
0x2711fd60, 0x438050e3, 0x069908a8, 0x3d7fedc4, 0x826d2bef, 0x4eeb8476, 0x488dcf25, 0x36c9d566,
|
||||
0x28e74e41, 0xc2610aca, 0x3d49a9cf, 0xbae3b9df, 0xb65f8de6, 0x92aeaf64, 0x3ac7d5e6, 0x9ea80509,
|
||||
0xf22b017d, 0xa4173f70, 0xdd1e16c3, 0x15e0d7f9, 0x50b1b887, 0x2b9f4fd5, 0x625aba82, 0x6a017962,
|
||||
0x2ec01b9c, 0x15488aa9, 0xd716e740, 0x40055a2c, 0x93d29a22, 0xe32dbf9a, 0x058745b9, 0x3453dc1e,
|
||||
0xd699296e, 0x496cff6f, 0x1c9f4986, 0xdfe2ed07, 0xb87242d1, 0x19de7eae, 0x053e561a, 0x15ad6f8c,
|
||||
0x66626c1c, 0x7154c24c, 0xea082b2a, 0x93eb2939, 0x17dcb0f0, 0x58d4f2ae, 0x9ea294fb, 0x52cf564c,
|
||||
0x9883fe66, 0x2ec40581, 0x763953c3, 0x01d6692e, 0xd3a0c108, 0xa1e7160e, 0xe4f2dfa6, 0x693ed285,
|
||||
0x74904698, 0x4c2b0edd, 0x4f757656, 0x5d393378, 0xa132234f, 0x3d321c5d, 0xc3f5e194, 0x4b269301,
|
||||
0xc79f022f, 0x3c997e7e, 0x5e4f9504, 0x3ffafbbd, 0x76f7ad0e, 0x296693f4, 0x3d1fce6f, 0xc61e45be,
|
||||
0xd3b5ab34, 0xf72bf9b7, 0x1b0434c0, 0x4e72b567, 0x5592a33d, 0xb5229301, 0xcfd2a87f, 0x60aeb767,
|
||||
0x1814386b, 0x30bcc33d, 0x38a0c07d, 0xfd1606f2, 0xc363519b, 0x589dd390, 0x5479f8e6, 0x1cb8d647,
|
||||
0x97fd61a9, 0xea7759f4, 0x2d57539d, 0x569a58cf, 0xe84e63ad, 0x462e1b78, 0x6580f87e, 0xf3817914,
|
||||
0x91da55f4, 0x40a230f3, 0xd1988f35, 0xb6e318d2, 0x3ffa50bc, 0x3d40f021, 0xc3c0bdae, 0x4958c24c,
|
||||
0x518f36b2, 0x84b1d370, 0x0fedce83, 0x878ddada, 0xf2a279c7, 0x94e01be8, 0x90716f4b, 0x954b8aa3,
|
||||
},
|
||||
{
|
||||
0xe216300d, 0xbbddfffc, 0xa7ebdabd, 0x35648095, 0x7789f8b7, 0xe6c1121b, 0x0e241600, 0x052ce8b5,
|
||||
0x11a9cfb0, 0xe5952f11, 0xece7990a, 0x9386d174, 0x2a42931c, 0x76e38111, 0xb12def3a, 0x37ddddfc,
|
||||
0xde9adeb1, 0x0a0cc32c, 0xbe197029, 0x84a00940, 0xbb243a0f, 0xb4d137cf, 0xb44e79f0, 0x049eedfd,
|
||||
0x0b15a15d, 0x480d3168, 0x8bbbde5a, 0x669ded42, 0xc7ece831, 0x3f8f95e7, 0x72df191b, 0x7580330d,
|
||||
0x94074251, 0x5c7dcdfa, 0xabbe6d63, 0xaa402164, 0xb301d40a, 0x02e7d1ca, 0x53571dae, 0x7a3182a2,
|
||||
0x12a8ddec, 0xfdaa335d, 0x176f43e8, 0x71fb46d4, 0x38129022, 0xce949ad4, 0xb84769ad, 0x965bd862,
|
||||
0x82f3d055, 0x66fb9767, 0x15b80b4e, 0x1d5b47a0, 0x4cfde06f, 0xc28ec4b8, 0x57e8726e, 0x647a78fc,
|
||||
0x99865d44, 0x608bd593, 0x6c200e03, 0x39dc5ff6, 0x5d0b00a3, 0xae63aff2, 0x7e8bd632, 0x70108c0c,
|
||||
0xbbd35049, 0x2998df04, 0x980cf42a, 0x9b6df491, 0x9e7edd53, 0x06918548, 0x58cb7e07, 0x3b74ef2e,
|
||||
0x522fffb1, 0xd24708cc, 0x1c7e27cd, 0xa4eb215b, 0x3cf1d2e2, 0x19b47a38, 0x424f7618, 0x35856039,
|
||||
0x9d17dee7, 0x27eb35e6, 0xc9aff67b, 0x36baf5b8, 0x09c467cd, 0xc18910b1, 0xe11dbf7b, 0x06cd1af8,
|
||||
0x7170c608, 0x2d5e3354, 0xd4de495a, 0x64c6d006, 0xbcc0c62c, 0x3dd00db3, 0x708f8f34, 0x77d51b42,
|
||||
0x264f620f, 0x24b8d2bf, 0x15c1b79e, 0x46a52564, 0xf8d7e54e, 0x3e378160, 0x7895cda5, 0x859c15a5,
|
||||
0xe6459788, 0xc37bc75f, 0xdb07ba0c, 0x0676a3ab, 0x7f229b1e, 0x31842e7b, 0x24259fd7, 0xf8bef472,
|
||||
0x835ffcb8, 0x6df4c1f2, 0x96f5b195, 0xfd0af0fc, 0xb0fe134c, 0xe2506d3d, 0x4f9b12ea, 0xf215f225,
|
||||
0xa223736f, 0x9fb4c428, 0x25d04979, 0x34c713f8, 0xc4618187, 0xea7a6e98, 0x7cd16efc, 0x1436876c,
|
||||
0xf1544107, 0xbedeee14, 0x56e9af27, 0xa04aa441, 0x3cf7c899, 0x92ecbae6, 0xdd67016d, 0x151682eb,
|
||||
0xa842eedf, 0xfdba60b4, 0xf1907b75, 0x20e3030f, 0x24d8c29e, 0xe139673b, 0xefa63fb8, 0x71873054,
|
||||
0xb6f2cf3b, 0x9f326442, 0xcb15a4cc, 0xb01a4504, 0xf1e47d8d, 0x844a1be5, 0xbae7dfdc, 0x42cbda70,
|
||||
0xcd7dae0a, 0x57e85b7a, 0xd53f5af6, 0x20cf4d8c, 0xcea4d428, 0x79d130a4, 0x3486ebfb, 0x33d3cddc,
|
||||
0x77853b53, 0x37effcb5, 0xc5068778, 0xe580b3e6, 0x4e68b8f4, 0xc5c8b37e, 0x0d809ea2, 0x398feb7c,
|
||||
0x132a4f94, 0x43b7950e, 0x2fee7d1c, 0x223613bd, 0xdd06caa2, 0x37df932b, 0xc4248289, 0xacf3ebc3,
|
||||
0x5715f6b7, 0xef3478dd, 0xf267616f, 0xc148cbe4, 0x9052815e, 0x5e410fab, 0xb48a2465, 0x2eda7fa4,
|
||||
0xe87b40e4, 0xe98ea084, 0x5889e9e1, 0xefd390fc, 0xdd07d35b, 0xdb485694, 0x38d7e5b2, 0x57720101,
|
||||
0x730edebc, 0x5b643113, 0x94917e4f, 0x503c2fba, 0x646f1282, 0x7523d24a, 0xe0779695, 0xf9c17a8f,
|
||||
0x7a5b2121, 0xd187b896, 0x29263a4d, 0xba510cdf, 0x81f47c9f, 0xad1163ed, 0xea7b5965, 0x1a00726e,
|
||||
0x11403092, 0x00da6d77, 0x4a0cdd61, 0xad1f4603, 0x605bdfb0, 0x9eedc364, 0x22ebe6a8, 0xcee7d28a,
|
||||
0xa0e736a0, 0x5564a6b9, 0x10853209, 0xc7eb8f37, 0x2de705ca, 0x8951570f, 0xdf09822b, 0xbd691a6c,
|
||||
0xaa12e4f2, 0x87451c0f, 0xe0f6a27a, 0x3ada4819, 0x4cf1764f, 0x0d771c2b, 0x67cdb156, 0x350d8384,
|
||||
0x5938fa0f, 0x42399ef3, 0x36997b07, 0x0e84093d, 0x4aa93e61, 0x8360d87b, 0x1fa98b0c, 0x1149382c,
|
||||
0xe97625a5, 0x0614d1b7, 0x0e25244b, 0x0c768347, 0x589e8d82, 0x0d2059d1, 0xa466bb1e, 0xf8da0a82,
|
||||
0x04f19130, 0xba6e4ec0, 0x99265164, 0x1ee7230d, 0x50b2ad80, 0xeaee6801, 0x8db2a283, 0xea8bf59e,
|
||||
},
|
||||
}
|
||||
+91
@@ -0,0 +1,91 @@
|
||||
// Copyright 2016 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package chacha20poly1305 implements the ChaCha20-Poly1305 AEAD as specified in RFC 7539.
|
||||
package chacha20poly1305 // import "golang.org/x/crypto/chacha20poly1305"
|
||||
|
||||
import (
|
||||
"crypto/cipher"
|
||||
"encoding/binary"
|
||||
"errors"
|
||||
)
|
||||
|
||||
const (
|
||||
// KeySize is the size of the key used by this AEAD, in bytes.
|
||||
KeySize = 32
|
||||
// NonceSize is the size of the nonce used with this AEAD, in bytes.
|
||||
NonceSize = 12
|
||||
)
|
||||
|
||||
type chacha20poly1305 struct {
|
||||
key [8]uint32
|
||||
}
|
||||
|
||||
// New returns a ChaCha20-Poly1305 AEAD that uses the given, 256-bit key.
|
||||
func New(key []byte) (cipher.AEAD, error) {
|
||||
if len(key) != KeySize {
|
||||
return nil, errors.New("chacha20poly1305: bad key length")
|
||||
}
|
||||
ret := new(chacha20poly1305)
|
||||
ret.key[0] = binary.LittleEndian.Uint32(key[0:4])
|
||||
ret.key[1] = binary.LittleEndian.Uint32(key[4:8])
|
||||
ret.key[2] = binary.LittleEndian.Uint32(key[8:12])
|
||||
ret.key[3] = binary.LittleEndian.Uint32(key[12:16])
|
||||
ret.key[4] = binary.LittleEndian.Uint32(key[16:20])
|
||||
ret.key[5] = binary.LittleEndian.Uint32(key[20:24])
|
||||
ret.key[6] = binary.LittleEndian.Uint32(key[24:28])
|
||||
ret.key[7] = binary.LittleEndian.Uint32(key[28:32])
|
||||
return ret, nil
|
||||
}
|
||||
|
||||
func (c *chacha20poly1305) NonceSize() int {
|
||||
return NonceSize
|
||||
}
|
||||
|
||||
func (c *chacha20poly1305) Overhead() int {
|
||||
return 16
|
||||
}
|
||||
|
||||
func (c *chacha20poly1305) Seal(dst, nonce, plaintext, additionalData []byte) []byte {
|
||||
if len(nonce) != NonceSize {
|
||||
panic("chacha20poly1305: bad nonce length passed to Seal")
|
||||
}
|
||||
|
||||
if uint64(len(plaintext)) > (1<<38)-64 {
|
||||
panic("chacha20poly1305: plaintext too large")
|
||||
}
|
||||
|
||||
return c.seal(dst, nonce, plaintext, additionalData)
|
||||
}
|
||||
|
||||
var errOpen = errors.New("chacha20poly1305: message authentication failed")
|
||||
|
||||
func (c *chacha20poly1305) Open(dst, nonce, ciphertext, additionalData []byte) ([]byte, error) {
|
||||
if len(nonce) != NonceSize {
|
||||
panic("chacha20poly1305: bad nonce length passed to Open")
|
||||
}
|
||||
if len(ciphertext) < 16 {
|
||||
return nil, errOpen
|
||||
}
|
||||
if uint64(len(ciphertext)) > (1<<38)-48 {
|
||||
panic("chacha20poly1305: ciphertext too large")
|
||||
}
|
||||
|
||||
return c.open(dst, nonce, ciphertext, additionalData)
|
||||
}
|
||||
|
||||
// sliceForAppend takes a slice and a requested number of bytes. It returns a
|
||||
// slice with the contents of the given slice followed by that many bytes and a
|
||||
// second slice that aliases into it and contains only the extra bytes. If the
|
||||
// original slice has sufficient capacity then no allocation is performed.
|
||||
func sliceForAppend(in []byte, n int) (head, tail []byte) {
|
||||
if total := len(in) + n; cap(in) >= total {
|
||||
head = in[:total]
|
||||
} else {
|
||||
head = make([]byte, total)
|
||||
copy(head, in)
|
||||
}
|
||||
tail = head[len(in):]
|
||||
return
|
||||
}
|
||||
+80
@@ -0,0 +1,80 @@
|
||||
// Copyright 2016 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build go1.7,amd64,!gccgo,!appengine
|
||||
|
||||
package chacha20poly1305
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
|
||||
"golang.org/x/sys/cpu"
|
||||
)
|
||||
|
||||
//go:noescape
|
||||
func chacha20Poly1305Open(dst []byte, key []uint32, src, ad []byte) bool
|
||||
|
||||
//go:noescape
|
||||
func chacha20Poly1305Seal(dst []byte, key []uint32, src, ad []byte)
|
||||
|
||||
var (
|
||||
useASM = cpu.X86.HasSSSE3
|
||||
useAVX2 = cpu.X86.HasAVX2 && cpu.X86.HasBMI2
|
||||
)
|
||||
|
||||
// setupState writes a ChaCha20 input matrix to state. See
|
||||
// https://tools.ietf.org/html/rfc7539#section-2.3.
|
||||
func setupState(state *[16]uint32, key *[8]uint32, nonce []byte) {
|
||||
state[0] = 0x61707865
|
||||
state[1] = 0x3320646e
|
||||
state[2] = 0x79622d32
|
||||
state[3] = 0x6b206574
|
||||
|
||||
state[4] = key[0]
|
||||
state[5] = key[1]
|
||||
state[6] = key[2]
|
||||
state[7] = key[3]
|
||||
state[8] = key[4]
|
||||
state[9] = key[5]
|
||||
state[10] = key[6]
|
||||
state[11] = key[7]
|
||||
|
||||
state[12] = 0
|
||||
state[13] = binary.LittleEndian.Uint32(nonce[:4])
|
||||
state[14] = binary.LittleEndian.Uint32(nonce[4:8])
|
||||
state[15] = binary.LittleEndian.Uint32(nonce[8:12])
|
||||
}
|
||||
|
||||
func (c *chacha20poly1305) seal(dst, nonce, plaintext, additionalData []byte) []byte {
|
||||
if !useASM {
|
||||
return c.sealGeneric(dst, nonce, plaintext, additionalData)
|
||||
}
|
||||
|
||||
var state [16]uint32
|
||||
setupState(&state, &c.key, nonce)
|
||||
|
||||
ret, out := sliceForAppend(dst, len(plaintext)+16)
|
||||
chacha20Poly1305Seal(out[:], state[:], plaintext, additionalData)
|
||||
return ret
|
||||
}
|
||||
|
||||
func (c *chacha20poly1305) open(dst, nonce, ciphertext, additionalData []byte) ([]byte, error) {
|
||||
if !useASM {
|
||||
return c.openGeneric(dst, nonce, ciphertext, additionalData)
|
||||
}
|
||||
|
||||
var state [16]uint32
|
||||
setupState(&state, &c.key, nonce)
|
||||
|
||||
ciphertext = ciphertext[:len(ciphertext)-16]
|
||||
ret, out := sliceForAppend(dst, len(ciphertext))
|
||||
if !chacha20Poly1305Open(out, state[:], ciphertext, additionalData) {
|
||||
for i := range out {
|
||||
out[i] = 0
|
||||
}
|
||||
return nil, errOpen
|
||||
}
|
||||
|
||||
return ret, nil
|
||||
}
|
||||
+2695
File diff suppressed because it is too large.
Load diff
+74
@@ -0,0 +1,74 @@
|
||||
// Copyright 2016 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
package chacha20poly1305
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
|
||||
"golang.org/x/crypto/internal/chacha20"
|
||||
"golang.org/x/crypto/poly1305"
|
||||
)
|
||||
|
||||
func roundTo16(n int) int {
|
||||
return 16 * ((n + 15) / 16)
|
||||
}
|
||||
|
||||
func (c *chacha20poly1305) sealGeneric(dst, nonce, plaintext, additionalData []byte) []byte {
|
||||
ret, out := sliceForAppend(dst, len(plaintext)+poly1305.TagSize)
|
||||
|
||||
var polyKey [32]byte
|
||||
s := chacha20.New(c.key, [3]uint32{
|
||||
binary.LittleEndian.Uint32(nonce[0:4]),
|
||||
binary.LittleEndian.Uint32(nonce[4:8]),
|
||||
binary.LittleEndian.Uint32(nonce[8:12]),
|
||||
})
|
||||
s.XORKeyStream(polyKey[:], polyKey[:])
|
||||
s.Advance() // skip the next 32 bytes
|
||||
s.XORKeyStream(out, plaintext)
|
||||
|
||||
polyInput := make([]byte, roundTo16(len(additionalData))+roundTo16(len(plaintext))+8+8)
|
||||
copy(polyInput, additionalData)
|
||||
copy(polyInput[roundTo16(len(additionalData)):], out[:len(plaintext)])
|
||||
binary.LittleEndian.PutUint64(polyInput[len(polyInput)-16:], uint64(len(additionalData)))
|
||||
binary.LittleEndian.PutUint64(polyInput[len(polyInput)-8:], uint64(len(plaintext)))
|
||||
|
||||
var tag [poly1305.TagSize]byte
|
||||
poly1305.Sum(&tag, polyInput, &polyKey)
|
||||
copy(out[len(plaintext):], tag[:])
|
||||
|
||||
return ret
|
||||
}
|
||||
|
||||
func (c *chacha20poly1305) openGeneric(dst, nonce, ciphertext, additionalData []byte) ([]byte, error) {
|
||||
var tag [poly1305.TagSize]byte
|
||||
copy(tag[:], ciphertext[len(ciphertext)-16:])
|
||||
ciphertext = ciphertext[:len(ciphertext)-16]
|
||||
|
||||
var polyKey [32]byte
|
||||
s := chacha20.New(c.key, [3]uint32{
|
||||
binary.LittleEndian.Uint32(nonce[0:4]),
|
||||
binary.LittleEndian.Uint32(nonce[4:8]),
|
||||
binary.LittleEndian.Uint32(nonce[8:12]),
|
||||
})
|
||||
s.XORKeyStream(polyKey[:], polyKey[:])
|
||||
s.Advance() // skip the next 32 bytes
|
||||
|
||||
polyInput := make([]byte, roundTo16(len(additionalData))+roundTo16(len(ciphertext))+8+8)
|
||||
copy(polyInput, additionalData)
|
||||
copy(polyInput[roundTo16(len(additionalData)):], ciphertext)
|
||||
binary.LittleEndian.PutUint64(polyInput[len(polyInput)-16:], uint64(len(additionalData)))
|
||||
binary.LittleEndian.PutUint64(polyInput[len(polyInput)-8:], uint64(len(ciphertext)))
|
||||
|
||||
ret, out := sliceForAppend(dst, len(ciphertext))
|
||||
if !poly1305.Verify(&tag, polyInput, &polyKey) {
|
||||
for i := range out {
|
||||
out[i] = 0
|
||||
}
|
||||
return nil, errOpen
|
||||
}
|
||||
|
||||
s.XORKeyStream(out, ciphertext)
|
||||
return ret, nil
|
||||
}
|
||||
+15
@@ -0,0 +1,15 @@
|
||||
// Copyright 2016 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build !amd64 !go1.7 gccgo appengine
|
||||
|
||||
package chacha20poly1305
|
||||
|
||||
func (c *chacha20poly1305) seal(dst, nonce, plaintext, additionalData []byte) []byte {
|
||||
return c.sealGeneric(dst, nonce, plaintext, additionalData)
|
||||
}
|
||||
|
||||
func (c *chacha20poly1305) open(dst, nonce, ciphertext, additionalData []byte) ([]byte, error) {
|
||||
return c.openGeneric(dst, nonce, ciphertext, additionalData)
|
||||
}
|
||||
+75
@@ -0,0 +1,75 @@
|
||||
// Copyright 2014 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package hkdf implements the HMAC-based Extract-and-Expand Key Derivation
|
||||
// Function (HKDF) as defined in RFC 5869.
|
||||
//
|
||||
// HKDF is a cryptographic key derivation function (KDF) with the goal of
|
||||
// expanding limited input keying material into one or more cryptographically
|
||||
// strong secret keys.
|
||||
//
|
||||
// RFC 5869: https://tools.ietf.org/html/rfc5869
|
||||
package hkdf // import "golang.org/x/crypto/hkdf"
|
||||
|
||||
import (
|
||||
"crypto/hmac"
|
||||
"errors"
|
||||
"hash"
|
||||
"io"
|
||||
)
|
||||
|
||||
type hkdf struct {
|
||||
expander hash.Hash
|
||||
size int
|
||||
|
||||
info []byte
|
||||
counter byte
|
||||
|
||||
prev []byte
|
||||
cache []byte
|
||||
}
|
||||
|
||||
func (f *hkdf) Read(p []byte) (int, error) {
|
||||
// Check whether enough data can be generated
|
||||
need := len(p)
|
||||
remains := len(f.cache) + int(255-f.counter+1)*f.size
|
||||
if remains < need {
|
||||
return 0, errors.New("hkdf: entropy limit reached")
|
||||
}
|
||||
// Read from the cache, if enough data is present
|
||||
n := copy(p, f.cache)
|
||||
p = p[n:]
|
||||
|
||||
// Fill the buffer
|
||||
for len(p) > 0 {
|
||||
f.expander.Reset()
|
||||
f.expander.Write(f.prev)
|
||||
f.expander.Write(f.info)
|
||||
f.expander.Write([]byte{f.counter})
|
||||
f.prev = f.expander.Sum(f.prev[:0])
|
||||
f.counter++
|
||||
|
||||
// Copy the new batch into p
|
||||
f.cache = f.prev
|
||||
n = copy(p, f.cache)
|
||||
p = p[n:]
|
||||
}
|
||||
// Save leftovers for next run
|
||||
f.cache = f.cache[n:]
|
||||
|
||||
return need, nil
|
||||
}
|
||||
|
||||
// New returns a new HKDF using the given hash, the secret keying material to expand
|
||||
// and optional salt and info fields.
|
||||
func New(hash func() hash.Hash, secret, salt, info []byte) io.Reader {
|
||||
if salt == nil {
|
||||
salt = make([]byte, hash().Size())
|
||||
}
|
||||
extractor := hmac.New(hash, salt)
|
||||
extractor.Write(secret)
|
||||
prk := extractor.Sum(nil)
|
||||
|
||||
return &hkdf{hmac.New(hash, prk), extractor.Size(), info, 1, nil, nil}
|
||||
}
|
||||
+283
@@ -0,0 +1,283 @@
|
||||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build s390x,!gccgo,!appengine
|
||||
|
||||
#include "go_asm.h"
|
||||
#include "textflag.h"
|
||||
|
||||
// This is an implementation of the ChaCha20 encryption algorithm as
|
||||
// specified in RFC 7539. It uses vector instructions to compute
|
||||
// 4 keystream blocks in parallel (256 bytes) which are then XORed
|
||||
// with the bytes in the input slice.
|
||||
|
||||
GLOBL ·constants<>(SB), RODATA|NOPTR, $32
|
||||
// BSWAP: swap bytes in each 4-byte element
|
||||
DATA ·constants<>+0x00(SB)/4, $0x03020100
|
||||
DATA ·constants<>+0x04(SB)/4, $0x07060504
|
||||
DATA ·constants<>+0x08(SB)/4, $0x0b0a0908
|
||||
DATA ·constants<>+0x0c(SB)/4, $0x0f0e0d0c
|
||||
// J0: [j0, j1, j2, j3]
|
||||
DATA ·constants<>+0x10(SB)/4, $0x61707865
|
||||
DATA ·constants<>+0x14(SB)/4, $0x3320646e
|
||||
DATA ·constants<>+0x18(SB)/4, $0x79622d32
|
||||
DATA ·constants<>+0x1c(SB)/4, $0x6b206574
|
||||
|
||||
// EXRL targets:
|
||||
TEXT ·mvcSrcToBuf(SB), NOFRAME|NOSPLIT, $0
|
||||
MVC $1, (R1), (R8)
|
||||
RET
|
||||
|
||||
TEXT ·mvcBufToDst(SB), NOFRAME|NOSPLIT, $0
|
||||
MVC $1, (R8), (R9)
|
||||
RET
|
||||
|
||||
#define BSWAP V5
|
||||
#define J0 V6
|
||||
#define KEY0 V7
|
||||
#define KEY1 V8
|
||||
#define NONCE V9
|
||||
#define CTR V10
|
||||
#define M0 V11
|
||||
#define M1 V12
|
||||
#define M2 V13
|
||||
#define M3 V14
|
||||
#define INC V15
|
||||
#define X0 V16
|
||||
#define X1 V17
|
||||
#define X2 V18
|
||||
#define X3 V19
|
||||
#define X4 V20
|
||||
#define X5 V21
|
||||
#define X6 V22
|
||||
#define X7 V23
|
||||
#define X8 V24
|
||||
#define X9 V25
|
||||
#define X10 V26
|
||||
#define X11 V27
|
||||
#define X12 V28
|
||||
#define X13 V29
|
||||
#define X14 V30
|
||||
#define X15 V31
|
||||
|
||||
#define NUM_ROUNDS 20
|
||||
|
||||
#define ROUND4(a0, a1, a2, a3, b0, b1, b2, b3, c0, c1, c2, c3, d0, d1, d2, d3) \
|
||||
VAF a1, a0, a0 \
|
||||
VAF b1, b0, b0 \
|
||||
VAF c1, c0, c0 \
|
||||
VAF d1, d0, d0 \
|
||||
VX a0, a2, a2 \
|
||||
VX b0, b2, b2 \
|
||||
VX c0, c2, c2 \
|
||||
VX d0, d2, d2 \
|
||||
VERLLF $16, a2, a2 \
|
||||
VERLLF $16, b2, b2 \
|
||||
VERLLF $16, c2, c2 \
|
||||
VERLLF $16, d2, d2 \
|
||||
VAF a2, a3, a3 \
|
||||
VAF b2, b3, b3 \
|
||||
VAF c2, c3, c3 \
|
||||
VAF d2, d3, d3 \
|
||||
VX a3, a1, a1 \
|
||||
VX b3, b1, b1 \
|
||||
VX c3, c1, c1 \
|
||||
VX d3, d1, d1 \
|
||||
VERLLF $12, a1, a1 \
|
||||
VERLLF $12, b1, b1 \
|
||||
VERLLF $12, c1, c1 \
|
||||
VERLLF $12, d1, d1 \
|
||||
VAF a1, a0, a0 \
|
||||
VAF b1, b0, b0 \
|
||||
VAF c1, c0, c0 \
|
||||
VAF d1, d0, d0 \
|
||||
VX a0, a2, a2 \
|
||||
VX b0, b2, b2 \
|
||||
VX c0, c2, c2 \
|
||||
VX d0, d2, d2 \
|
||||
VERLLF $8, a2, a2 \
|
||||
VERLLF $8, b2, b2 \
|
||||
VERLLF $8, c2, c2 \
|
||||
VERLLF $8, d2, d2 \
|
||||
VAF a2, a3, a3 \
|
||||
VAF b2, b3, b3 \
|
||||
VAF c2, c3, c3 \
|
||||
VAF d2, d3, d3 \
|
||||
VX a3, a1, a1 \
|
||||
VX b3, b1, b1 \
|
||||
VX c3, c1, c1 \
|
||||
VX d3, d1, d1 \
|
||||
VERLLF $7, a1, a1 \
|
||||
VERLLF $7, b1, b1 \
|
||||
VERLLF $7, c1, c1 \
|
||||
VERLLF $7, d1, d1
|
||||
|
||||
#define PERMUTE(mask, v0, v1, v2, v3) \
|
||||
VPERM v0, v0, mask, v0 \
|
||||
VPERM v1, v1, mask, v1 \
|
||||
VPERM v2, v2, mask, v2 \
|
||||
VPERM v3, v3, mask, v3
|
||||
|
||||
#define ADDV(x, v0, v1, v2, v3) \
|
||||
VAF x, v0, v0 \
|
||||
VAF x, v1, v1 \
|
||||
VAF x, v2, v2 \
|
||||
VAF x, v3, v3
|
||||
|
||||
#define XORV(off, dst, src, v0, v1, v2, v3) \
|
||||
VLM off(src), M0, M3 \
|
||||
PERMUTE(BSWAP, v0, v1, v2, v3) \
|
||||
VX v0, M0, M0 \
|
||||
VX v1, M1, M1 \
|
||||
VX v2, M2, M2 \
|
||||
VX v3, M3, M3 \
|
||||
VSTM M0, M3, off(dst)
|
||||
|
||||
#define SHUFFLE(a, b, c, d, t, u, v, w) \
|
||||
VMRHF a, c, t \ // t = {a[0], c[0], a[1], c[1]}
|
||||
VMRHF b, d, u \ // u = {b[0], d[0], b[1], d[1]}
|
||||
VMRLF a, c, v \ // v = {a[2], c[2], a[3], c[3]}
|
||||
VMRLF b, d, w \ // w = {b[2], d[2], b[3], d[3]}
|
||||
VMRHF t, u, a \ // a = {a[0], b[0], c[0], d[0]}
|
||||
VMRLF t, u, b \ // b = {a[1], b[1], c[1], d[1]}
|
||||
VMRHF v, w, c \ // c = {a[2], b[2], c[2], d[2]}
|
||||
VMRLF v, w, d // d = {a[3], b[3], c[3], d[3]}
|
||||
|
||||
// func xorKeyStreamVX(dst, src []byte, key *[8]uint32, nonce *[3]uint32, counter *uint32, buf *[256]byte, len *int)
|
||||
TEXT ·xorKeyStreamVX(SB), NOSPLIT, $0
|
||||
MOVD $·constants<>(SB), R1
|
||||
MOVD dst+0(FP), R2 // R2=&dst[0]
|
||||
LMG src+24(FP), R3, R4 // R3=&src[0] R4=len(src)
|
||||
MOVD key+48(FP), R5 // R5=key
|
||||
MOVD nonce+56(FP), R6 // R6=nonce
|
||||
MOVD counter+64(FP), R7 // R7=counter
|
||||
MOVD buf+72(FP), R8 // R8=buf
|
||||
MOVD len+80(FP), R9 // R9=len
|
||||
|
||||
// load BSWAP and J0
|
||||
VLM (R1), BSWAP, J0
|
||||
|
||||
// set up tail buffer
|
||||
ADD $-1, R4, R12
|
||||
MOVBZ R12, R12
|
||||
CMPUBEQ R12, $255, aligned
|
||||
MOVD R4, R1
|
||||
AND $~255, R1
|
||||
MOVD $(R3)(R1*1), R1
|
||||
EXRL $·mvcSrcToBuf(SB), R12
|
||||
MOVD $255, R0
|
||||
SUB R12, R0
|
||||
MOVD R0, (R9) // update len
|
||||
|
||||
aligned:
|
||||
// setup
|
||||
MOVD $95, R0
|
||||
VLM (R5), KEY0, KEY1
|
||||
VLL R0, (R6), NONCE
|
||||
VZERO M0
|
||||
VLEIB $7, $32, M0
|
||||
VSRLB M0, NONCE, NONCE
|
||||
|
||||
// initialize counter values
|
||||
VLREPF (R7), CTR
|
||||
VZERO INC
|
||||
VLEIF $1, $1, INC
|
||||
VLEIF $2, $2, INC
|
||||
VLEIF $3, $3, INC
|
||||
VAF INC, CTR, CTR
|
||||
VREPIF $4, INC
|
||||
|
||||
chacha:
|
||||
VREPF $0, J0, X0
|
||||
VREPF $1, J0, X1
|
||||
VREPF $2, J0, X2
|
||||
VREPF $3, J0, X3
|
||||
VREPF $0, KEY0, X4
|
||||
VREPF $1, KEY0, X5
|
||||
VREPF $2, KEY0, X6
|
||||
VREPF $3, KEY0, X7
|
||||
VREPF $0, KEY1, X8
|
||||
VREPF $1, KEY1, X9
|
||||
VREPF $2, KEY1, X10
|
||||
VREPF $3, KEY1, X11
|
||||
VLR CTR, X12
|
||||
VREPF $1, NONCE, X13
|
||||
VREPF $2, NONCE, X14
|
||||
VREPF $3, NONCE, X15
|
||||
|
||||
MOVD $(NUM_ROUNDS/2), R1
|
||||
|
||||
loop:
|
||||
ROUND4(X0, X4, X12, X8, X1, X5, X13, X9, X2, X6, X14, X10, X3, X7, X15, X11)
|
||||
ROUND4(X0, X5, X15, X10, X1, X6, X12, X11, X2, X7, X13, X8, X3, X4, X14, X9)
|
||||
|
||||
ADD $-1, R1
|
||||
BNE loop
|
||||
|
||||
// decrement length
|
||||
ADD $-256, R4
|
||||
BLT tail
|
||||
|
||||
continue:
|
||||
// rearrange vectors
|
||||
SHUFFLE(X0, X1, X2, X3, M0, M1, M2, M3)
|
||||
ADDV(J0, X0, X1, X2, X3)
|
||||
SHUFFLE(X4, X5, X6, X7, M0, M1, M2, M3)
|
||||
ADDV(KEY0, X4, X5, X6, X7)
|
||||
SHUFFLE(X8, X9, X10, X11, M0, M1, M2, M3)
|
||||
ADDV(KEY1, X8, X9, X10, X11)
|
||||
VAF CTR, X12, X12
|
||||
SHUFFLE(X12, X13, X14, X15, M0, M1, M2, M3)
|
||||
ADDV(NONCE, X12, X13, X14, X15)
|
||||
|
||||
// increment counters
|
||||
VAF INC, CTR, CTR
|
||||
|
||||
// xor keystream with plaintext
|
||||
XORV(0*64, R2, R3, X0, X4, X8, X12)
|
||||
XORV(1*64, R2, R3, X1, X5, X9, X13)
|
||||
XORV(2*64, R2, R3, X2, X6, X10, X14)
|
||||
XORV(3*64, R2, R3, X3, X7, X11, X15)
|
||||
|
||||
// increment pointers
|
||||
MOVD $256(R2), R2
|
||||
MOVD $256(R3), R3
|
||||
|
||||
CMPBNE R4, $0, chacha
|
||||
CMPUBEQ R12, $255, return
|
||||
EXRL $·mvcBufToDst(SB), R12 // len was updated during setup
|
||||
|
||||
return:
|
||||
VSTEF $0, CTR, (R7)
|
||||
RET
|
||||
|
||||
tail:
|
||||
MOVD R2, R9
|
||||
MOVD R8, R2
|
||||
MOVD R8, R3
|
||||
MOVD $0, R4
|
||||
JMP continue
|
||||
|
||||
// func hasVectorFacility() bool
|
||||
TEXT ·hasVectorFacility(SB), NOSPLIT, $24-1
|
||||
MOVD $x-24(SP), R1
|
||||
XC $24, 0(R1), 0(R1) // clear the storage
|
||||
MOVD $2, R0 // R0 is the number of double words stored -1
|
||||
WORD $0xB2B01000 // STFLE 0(R1)
|
||||
XOR R0, R0 // reset the value of R0
|
||||
MOVBZ z-8(SP), R1
|
||||
AND $0x40, R1
|
||||
BEQ novector
|
||||
|
||||
vectorinstalled:
|
||||
// check if the vector instruction has been enabled
|
||||
VLEIB $0, $0xF, V16
|
||||
VLGVB $0, V16, R1
|
||||
CMPBNE R1, $0xF, novector
|
||||
MOVB $1, ret+0(FP) // have vx
|
||||
RET
|
||||
|
||||
novector:
|
||||
MOVB $0, ret+0(FP) // no vx
|
||||
RET
|
||||
+227
@@ -0,0 +1,227 @@
|
||||
// Copyright 2016 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package ChaCha20 implements the core ChaCha20 function as specified
|
||||
// in https://tools.ietf.org/html/rfc7539#section-2.3.
|
||||
package chacha20
|
||||
|
||||
import (
|
||||
"crypto/cipher"
|
||||
"encoding/binary"
|
||||
)
|
||||
|
||||
// assert that *Cipher implements cipher.Stream
|
||||
var _ cipher.Stream = (*Cipher)(nil)
|
||||
|
||||
// Cipher is a stateful instance of ChaCha20 using a particular key
|
||||
// and nonce. A *Cipher implements the cipher.Stream interface.
|
||||
type Cipher struct {
|
||||
key [8]uint32
|
||||
counter uint32 // incremented after each block
|
||||
nonce [3]uint32
|
||||
buf [bufSize]byte // buffer for unused keystream bytes
|
||||
len int // number of unused keystream bytes at end of buf
|
||||
}
|
||||
|
||||
// New creates a new ChaCha20 stream cipher with the given key and nonce.
|
||||
// The initial counter value is set to 0.
|
||||
func New(key [8]uint32, nonce [3]uint32) *Cipher {
|
||||
return &Cipher{key: key, nonce: nonce}
|
||||
}
|
||||
|
||||
// XORKeyStream XORs each byte in the given slice with a byte from the
|
||||
// cipher's key stream. Dst and src must overlap entirely or not at all.
|
||||
//
|
||||
// If len(dst) < len(src), XORKeyStream will panic. It is acceptable
|
||||
// to pass a dst bigger than src, and in that case, XORKeyStream will
|
||||
// only update dst[:len(src)] and will not touch the rest of dst.
|
||||
//
|
||||
// Multiple calls to XORKeyStream behave as if the concatenation of
|
||||
// the src buffers was passed in a single run. That is, Cipher
|
||||
// maintains state and does not reset at each XORKeyStream call.
|
||||
func (s *Cipher) XORKeyStream(dst, src []byte) {
|
||||
// xor src with buffered keystream first
|
||||
if s.len != 0 {
|
||||
buf := s.buf[len(s.buf)-s.len:]
|
||||
if len(src) < len(buf) {
|
||||
buf = buf[:len(src)]
|
||||
}
|
||||
td, ts := dst[:len(buf)], src[:len(buf)] // BCE hint
|
||||
for i, b := range buf {
|
||||
td[i] = ts[i] ^ b
|
||||
}
|
||||
s.len -= len(buf)
|
||||
if s.len != 0 {
|
||||
return
|
||||
}
|
||||
s.buf = [len(s.buf)]byte{} // zero the empty buffer
|
||||
src = src[len(buf):]
|
||||
dst = dst[len(buf):]
|
||||
}
|
||||
|
||||
if len(src) == 0 {
|
||||
return
|
||||
}
|
||||
if haveAsm {
|
||||
s.xorKeyStreamAsm(dst, src)
|
||||
return
|
||||
}
|
||||
|
||||
// set up a 64-byte buffer to pad out the final block if needed
|
||||
// (hoisted out of the main loop to avoid spills)
|
||||
rem := len(src) % 64 // length of final block
|
||||
fin := len(src) - rem // index of final block
|
||||
if rem > 0 {
|
||||
copy(s.buf[len(s.buf)-64:], src[fin:])
|
||||
}
|
||||
|
||||
// qr calculates a quarter round
|
||||
qr := func(a, b, c, d uint32) (uint32, uint32, uint32, uint32) {
|
||||
a += b
|
||||
d ^= a
|
||||
d = (d << 16) | (d >> 16)
|
||||
c += d
|
||||
b ^= c
|
||||
b = (b << 12) | (b >> 20)
|
||||
a += b
|
||||
d ^= a
|
||||
d = (d << 8) | (d >> 24)
|
||||
c += d
|
||||
b ^= c
|
||||
b = (b << 7) | (b >> 25)
|
||||
return a, b, c, d
|
||||
}
|
||||
|
||||
// ChaCha20 constants
|
||||
const (
|
||||
j0 = 0x61707865
|
||||
j1 = 0x3320646e
|
||||
j2 = 0x79622d32
|
||||
j3 = 0x6b206574
|
||||
)
|
||||
|
||||
// pre-calculate most of the first round
|
||||
s1, s5, s9, s13 := qr(j1, s.key[1], s.key[5], s.nonce[0])
|
||||
s2, s6, s10, s14 := qr(j2, s.key[2], s.key[6], s.nonce[1])
|
||||
s3, s7, s11, s15 := qr(j3, s.key[3], s.key[7], s.nonce[2])
|
||||
|
||||
n := len(src)
|
||||
src, dst = src[:n:n], dst[:n:n] // BCE hint
|
||||
for i := 0; i < n; i += 64 {
|
||||
// calculate the remainder of the first round
|
||||
s0, s4, s8, s12 := qr(j0, s.key[0], s.key[4], s.counter)
|
||||
|
||||
// execute the second round
|
||||
x0, x5, x10, x15 := qr(s0, s5, s10, s15)
|
||||
x1, x6, x11, x12 := qr(s1, s6, s11, s12)
|
||||
x2, x7, x8, x13 := qr(s2, s7, s8, s13)
|
||||
x3, x4, x9, x14 := qr(s3, s4, s9, s14)
|
||||
|
||||
// execute the remaining 18 rounds
|
||||
for i := 0; i < 9; i++ {
|
||||
x0, x4, x8, x12 = qr(x0, x4, x8, x12)
|
||||
x1, x5, x9, x13 = qr(x1, x5, x9, x13)
|
||||
x2, x6, x10, x14 = qr(x2, x6, x10, x14)
|
||||
x3, x7, x11, x15 = qr(x3, x7, x11, x15)
|
||||
|
||||
x0, x5, x10, x15 = qr(x0, x5, x10, x15)
|
||||
x1, x6, x11, x12 = qr(x1, x6, x11, x12)
|
||||
x2, x7, x8, x13 = qr(x2, x7, x8, x13)
|
||||
x3, x4, x9, x14 = qr(x3, x4, x9, x14)
|
||||
}
|
||||
|
||||
x0 += j0
|
||||
x1 += j1
|
||||
x2 += j2
|
||||
x3 += j3
|
||||
|
||||
x4 += s.key[0]
|
||||
x5 += s.key[1]
|
||||
x6 += s.key[2]
|
||||
x7 += s.key[3]
|
||||
x8 += s.key[4]
|
||||
x9 += s.key[5]
|
||||
x10 += s.key[6]
|
||||
x11 += s.key[7]
|
||||
|
||||
x12 += s.counter
|
||||
x13 += s.nonce[0]
|
||||
x14 += s.nonce[1]
|
||||
x15 += s.nonce[2]
|
||||
|
||||
// increment the counter
|
||||
s.counter += 1
|
||||
if s.counter == 0 {
|
||||
panic("chacha20: counter overflow")
|
||||
}
|
||||
|
||||
// pad to 64 bytes if needed
|
||||
in, out := src[i:], dst[i:]
|
||||
if i == fin {
|
||||
// src[fin:] has already been copied into s.buf before
|
||||
// the main loop
|
||||
in, out = s.buf[len(s.buf)-64:], s.buf[len(s.buf)-64:]
|
||||
}
|
||||
in, out = in[:64], out[:64] // BCE hint
|
||||
|
||||
// XOR the key stream with the source and write out the result
|
||||
xor(out[0:], in[0:], x0)
|
||||
xor(out[4:], in[4:], x1)
|
||||
xor(out[8:], in[8:], x2)
|
||||
xor(out[12:], in[12:], x3)
|
||||
xor(out[16:], in[16:], x4)
|
||||
xor(out[20:], in[20:], x5)
|
||||
xor(out[24:], in[24:], x6)
|
||||
xor(out[28:], in[28:], x7)
|
||||
xor(out[32:], in[32:], x8)
|
||||
xor(out[36:], in[36:], x9)
|
||||
xor(out[40:], in[40:], x10)
|
||||
xor(out[44:], in[44:], x11)
|
||||
xor(out[48:], in[48:], x12)
|
||||
xor(out[52:], in[52:], x13)
|
||||
xor(out[56:], in[56:], x14)
|
||||
xor(out[60:], in[60:], x15)
|
||||
}
|
||||
// copy any trailing bytes out of the buffer and into dst
|
||||
if rem != 0 {
|
||||
s.len = 64 - rem
|
||||
copy(dst[fin:], s.buf[len(s.buf)-64:])
|
||||
}
|
||||
}
|
||||
|
||||
// Advance discards bytes in the key stream until the next 64 byte block
|
||||
// boundary is reached and updates the counter accordingly. If the key
|
||||
// stream is already at a block boundary no bytes will be discarded and
|
||||
// the counter will be unchanged.
|
||||
func (s *Cipher) Advance() {
|
||||
s.len -= s.len % 64
|
||||
if s.len == 0 {
|
||||
s.buf = [len(s.buf)]byte{}
|
||||
}
|
||||
}
|
||||
|
||||
// XORKeyStream crypts bytes from in to out using the given key and counters.
|
||||
// In and out must overlap entirely or not at all. Counter contains the raw
|
||||
// ChaCha20 counter bytes (i.e. block counter followed by nonce).
|
||||
func XORKeyStream(out, in []byte, counter *[16]byte, key *[32]byte) {
|
||||
s := Cipher{
|
||||
key: [8]uint32{
|
||||
binary.LittleEndian.Uint32(key[0:4]),
|
||||
binary.LittleEndian.Uint32(key[4:8]),
|
||||
binary.LittleEndian.Uint32(key[8:12]),
|
||||
binary.LittleEndian.Uint32(key[12:16]),
|
||||
binary.LittleEndian.Uint32(key[16:20]),
|
||||
binary.LittleEndian.Uint32(key[20:24]),
|
||||
binary.LittleEndian.Uint32(key[24:28]),
|
||||
binary.LittleEndian.Uint32(key[28:32]),
|
||||
},
|
||||
nonce: [3]uint32{
|
||||
binary.LittleEndian.Uint32(counter[4:8]),
|
||||
binary.LittleEndian.Uint32(counter[8:12]),
|
||||
binary.LittleEndian.Uint32(counter[12:16]),
|
||||
},
|
||||
counter: binary.LittleEndian.Uint32(counter[0:4]),
|
||||
}
|
||||
s.XORKeyStream(out, in)
|
||||
}
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build !s390x gccgo appengine
|
||||
|
||||
package chacha20
|
||||
|
||||
const (
|
||||
bufSize = 64
|
||||
haveAsm = false
|
||||
)
|
||||
|
||||
func (*Cipher) xorKeyStreamAsm(dst, src []byte) {
|
||||
panic("not implemented")
|
||||
}
|
||||
+30
@@ -0,0 +1,30 @@
|
||||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build s390x,!gccgo,!appengine
|
||||
|
||||
package chacha20
|
||||
|
||||
var haveAsm = hasVectorFacility()
|
||||
|
||||
const bufSize = 256
|
||||
|
||||
// hasVectorFacility reports whether the machine supports the vector
|
||||
// facility (vx).
|
||||
// Implementation in asm_s390x.s.
|
||||
func hasVectorFacility() bool
|
||||
|
||||
// xorKeyStreamVX is an assembly implementation of XORKeyStream. It must only
|
||||
// be called when the vector facility is available.
|
||||
// Implementation in asm_s390x.s.
|
||||
//go:noescape
|
||||
func xorKeyStreamVX(dst, src []byte, key *[8]uint32, nonce *[3]uint32, counter *uint32, buf *[256]byte, len *int)
|
||||
|
||||
func (c *Cipher) xorKeyStreamAsm(dst, src []byte) {
|
||||
xorKeyStreamVX(dst, src, &c.key, &c.nonce, &c.counter, &c.buf, &c.len)
|
||||
}
|
||||
|
||||
// EXRL targets, DO NOT CALL!
|
||||
func mvcSrcToBuf()
|
||||
func mvcBufToDst()
|
||||
+43
@@ -0,0 +1,43 @@
|
||||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found src the LICENSE file.
|
||||
|
||||
package chacha20
|
||||
|
||||
import (
|
||||
"runtime"
|
||||
)
|
||||
|
||||
// Platforms that have fast unaligned 32-bit little endian accesses.
|
||||
const unaligned = runtime.GOARCH == "386" ||
|
||||
runtime.GOARCH == "amd64" ||
|
||||
runtime.GOARCH == "arm64" ||
|
||||
runtime.GOARCH == "ppc64le" ||
|
||||
runtime.GOARCH == "s390x"
|
||||
|
||||
// xor reads a little endian uint32 from src, XORs it with u and
|
||||
// places the result in little endian byte order in dst.
|
||||
func xor(dst, src []byte, u uint32) {
|
||||
_, _ = src[3], dst[3] // eliminate bounds checks
|
||||
if unaligned {
|
||||
// The compiler should optimize this code into
|
||||
// 32-bit unaligned little endian loads and stores.
|
||||
// TODO: delete once the compiler does a reliably
|
||||
// good job with the generic code below.
|
||||
// See issue #25111 for more details.
|
||||
v := uint32(src[0])
|
||||
v |= uint32(src[1]) << 8
|
||||
v |= uint32(src[2]) << 16
|
||||
v |= uint32(src[3]) << 24
|
||||
v ^= u
|
||||
dst[0] = byte(v)
|
||||
dst[1] = byte(v >> 8)
|
||||
dst[2] = byte(v >> 16)
|
||||
dst[3] = byte(v >> 24)
|
||||
} else {
|
||||
dst[0] = src[0] ^ byte(u)
|
||||
dst[1] = src[1] ^ byte(u>>8)
|
||||
dst[2] = src[2] ^ byte(u>>16)
|
||||
dst[3] = src[3] ^ byte(u>>24)
|
||||
}
|
||||
}
|
||||
+33
@@ -0,0 +1,33 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
/*
|
||||
Package poly1305 implements Poly1305 one-time message authentication code as
|
||||
specified in https://cr.yp.to/mac/poly1305-20050329.pdf.
|
||||
|
||||
Poly1305 is a fast, one-time authentication function. It is infeasible for an
|
||||
attacker to generate an authenticator for a message without the key. However, a
|
||||
key must only be used for a single message. Authenticating two different
|
||||
messages with the same key allows an attacker to forge authenticators for other
|
||||
messages with the same key.
|
||||
|
||||
Poly1305 was originally coupled with AES in order to make Poly1305-AES. AES was
|
||||
used with a fixed key in order to generate one-time keys from an nonce.
|
||||
However, in this package AES isn't used and the one-time key is specified
|
||||
directly.
|
||||
*/
|
||||
package poly1305 // import "golang.org/x/crypto/poly1305"
|
||||
|
||||
import "crypto/subtle"
|
||||
|
||||
// TagSize is the size, in bytes, of a poly1305 authenticator.
|
||||
const TagSize = 16
|
||||
|
||||
// Verify returns true if mac is a valid authenticator for m with the given
|
||||
// key.
|
||||
func Verify(mac *[16]byte, m []byte, key *[32]byte) bool {
|
||||
var tmp [16]byte
|
||||
Sum(&tmp, m, key)
|
||||
return subtle.ConstantTimeCompare(tmp[:], mac[:]) == 1
|
||||
}
|
||||
+22
@@ -0,0 +1,22 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build amd64,!gccgo,!appengine
|
||||
|
||||
package poly1305
|
||||
|
||||
// This function is implemented in sum_amd64.s
|
||||
//go:noescape
|
||||
func poly1305(out *[16]byte, m *byte, mlen uint64, key *[32]byte)
|
||||
|
||||
// Sum generates an authenticator for m using a one-time key and puts the
|
||||
// 16-byte result into out. Authenticating two different messages with the same
|
||||
// key allows an attacker to forge messages at will.
|
||||
func Sum(out *[16]byte, m []byte, key *[32]byte) {
|
||||
var mPtr *byte
|
||||
if len(m) > 0 {
|
||||
mPtr = &m[0]
|
||||
}
|
||||
poly1305(out, mPtr, uint64(len(m)), key)
|
||||
}
|
||||
+125
@@ -0,0 +1,125 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build amd64,!gccgo,!appengine
|
||||
|
||||
#include "textflag.h"
|
||||
|
||||
#define POLY1305_ADD(msg, h0, h1, h2) \
|
||||
ADDQ 0(msg), h0; \
|
||||
ADCQ 8(msg), h1; \
|
||||
ADCQ $1, h2; \
|
||||
LEAQ 16(msg), msg
|
||||
|
||||
#define POLY1305_MUL(h0, h1, h2, r0, r1, t0, t1, t2, t3) \
|
||||
MOVQ r0, AX; \
|
||||
MULQ h0; \
|
||||
MOVQ AX, t0; \
|
||||
MOVQ DX, t1; \
|
||||
MOVQ r0, AX; \
|
||||
MULQ h1; \
|
||||
ADDQ AX, t1; \
|
||||
ADCQ $0, DX; \
|
||||
MOVQ r0, t2; \
|
||||
IMULQ h2, t2; \
|
||||
ADDQ DX, t2; \
|
||||
\
|
||||
MOVQ r1, AX; \
|
||||
MULQ h0; \
|
||||
ADDQ AX, t1; \
|
||||
ADCQ $0, DX; \
|
||||
MOVQ DX, h0; \
|
||||
MOVQ r1, t3; \
|
||||
IMULQ h2, t3; \
|
||||
MOVQ r1, AX; \
|
||||
MULQ h1; \
|
||||
ADDQ AX, t2; \
|
||||
ADCQ DX, t3; \
|
||||
ADDQ h0, t2; \
|
||||
ADCQ $0, t3; \
|
||||
\
|
||||
MOVQ t0, h0; \
|
||||
MOVQ t1, h1; \
|
||||
MOVQ t2, h2; \
|
||||
ANDQ $3, h2; \
|
||||
MOVQ t2, t0; \
|
||||
ANDQ $0xFFFFFFFFFFFFFFFC, t0; \
|
||||
ADDQ t0, h0; \
|
||||
ADCQ t3, h1; \
|
||||
ADCQ $0, h2; \
|
||||
SHRQ $2, t3, t2; \
|
||||
SHRQ $2, t3; \
|
||||
ADDQ t2, h0; \
|
||||
ADCQ t3, h1; \
|
||||
ADCQ $0, h2
|
||||
|
||||
DATA ·poly1305Mask<>+0x00(SB)/8, $0x0FFFFFFC0FFFFFFF
|
||||
DATA ·poly1305Mask<>+0x08(SB)/8, $0x0FFFFFFC0FFFFFFC
|
||||
GLOBL ·poly1305Mask<>(SB), RODATA, $16
|
||||
|
||||
// func poly1305(out *[16]byte, m *byte, mlen uint64, key *[32]key)
|
||||
TEXT ·poly1305(SB), $0-32
|
||||
MOVQ out+0(FP), DI
|
||||
MOVQ m+8(FP), SI
|
||||
MOVQ mlen+16(FP), R15
|
||||
MOVQ key+24(FP), AX
|
||||
|
||||
MOVQ 0(AX), R11
|
||||
MOVQ 8(AX), R12
|
||||
ANDQ ·poly1305Mask<>(SB), R11 // r0
|
||||
ANDQ ·poly1305Mask<>+8(SB), R12 // r1
|
||||
XORQ R8, R8 // h0
|
||||
XORQ R9, R9 // h1
|
||||
XORQ R10, R10 // h2
|
||||
|
||||
CMPQ R15, $16
|
||||
JB bytes_between_0_and_15
|
||||
|
||||
loop:
|
||||
POLY1305_ADD(SI, R8, R9, R10)
|
||||
|
||||
multiply:
|
||||
POLY1305_MUL(R8, R9, R10, R11, R12, BX, CX, R13, R14)
|
||||
SUBQ $16, R15
|
||||
CMPQ R15, $16
|
||||
JAE loop
|
||||
|
||||
bytes_between_0_and_15:
|
||||
TESTQ R15, R15
|
||||
JZ done
|
||||
MOVQ $1, BX
|
||||
XORQ CX, CX
|
||||
XORQ R13, R13
|
||||
ADDQ R15, SI
|
||||
|
||||
flush_buffer:
|
||||
SHLQ $8, BX, CX
|
||||
SHLQ $8, BX
|
||||
MOVB -1(SI), R13
|
||||
XORQ R13, BX
|
||||
DECQ SI
|
||||
DECQ R15
|
||||
JNZ flush_buffer
|
||||
|
||||
ADDQ BX, R8
|
||||
ADCQ CX, R9
|
||||
ADCQ $0, R10
|
||||
MOVQ $16, R15
|
||||
JMP multiply
|
||||
|
||||
done:
|
||||
MOVQ R8, AX
|
||||
MOVQ R9, BX
|
||||
SUBQ $0xFFFFFFFFFFFFFFFB, AX
|
||||
SBBQ $0xFFFFFFFFFFFFFFFF, BX
|
||||
SBBQ $3, R10
|
||||
CMOVQCS R8, AX
|
||||
CMOVQCS R9, BX
|
||||
MOVQ key+24(FP), R8
|
||||
ADDQ 16(R8), AX
|
||||
ADCQ 24(R8), BX
|
||||
|
||||
MOVQ AX, 0(DI)
|
||||
MOVQ BX, 8(DI)
|
||||
RET
|
||||
+22
@@ -0,0 +1,22 @@
|
||||
// Copyright 2015 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build arm,!gccgo,!appengine,!nacl
|
||||
|
||||
package poly1305
|
||||
|
||||
// This function is implemented in sum_arm.s
|
||||
//go:noescape
|
||||
func poly1305_auth_armv6(out *[16]byte, m *byte, mlen uint32, key *[32]byte)
|
||||
|
||||
// Sum generates an authenticator for m using a one-time key and puts the
|
||||
// 16-byte result into out. Authenticating two different messages with the same
|
||||
// key allows an attacker to forge messages at will.
|
||||
func Sum(out *[16]byte, m []byte, key *[32]byte) {
|
||||
var mPtr *byte
|
||||
if len(m) > 0 {
|
||||
mPtr = &m[0]
|
||||
}
|
||||
poly1305_auth_armv6(out, mPtr, uint32(len(m)), key)
|
||||
}
|
||||
+427
@@ -0,0 +1,427 @@
|
||||
// Copyright 2015 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build arm,!gccgo,!appengine,!nacl
|
||||
|
||||
#include "textflag.h"
|
||||
|
||||
// This code was translated into a form compatible with 5a from the public
|
||||
// domain source by Andrew Moon: github.com/floodyberry/poly1305-opt/blob/master/app/extensions/poly1305.
|
||||
|
||||
DATA ·poly1305_init_constants_armv6<>+0x00(SB)/4, $0x3ffffff
|
||||
DATA ·poly1305_init_constants_armv6<>+0x04(SB)/4, $0x3ffff03
|
||||
DATA ·poly1305_init_constants_armv6<>+0x08(SB)/4, $0x3ffc0ff
|
||||
DATA ·poly1305_init_constants_armv6<>+0x0c(SB)/4, $0x3f03fff
|
||||
DATA ·poly1305_init_constants_armv6<>+0x10(SB)/4, $0x00fffff
|
||||
GLOBL ·poly1305_init_constants_armv6<>(SB), 8, $20
|
||||
|
||||
// Warning: the linker may use R11 to synthesize certain instructions. Please
|
||||
// take care and verify that no synthetic instructions use it.
|
||||
|
||||
TEXT poly1305_init_ext_armv6<>(SB), NOSPLIT, $0
|
||||
// Needs 16 bytes of stack and 64 bytes of space pointed to by R0. (It
|
||||
// might look like it's only 60 bytes of space but the final four bytes
|
||||
// will be written by another function.) We need to skip over four
|
||||
// bytes of stack because that's saving the value of 'g'.
|
||||
ADD $4, R13, R8
|
||||
MOVM.IB [R4-R7], (R8)
|
||||
MOVM.IA.W (R1), [R2-R5]
|
||||
MOVW $·poly1305_init_constants_armv6<>(SB), R7
|
||||
MOVW R2, R8
|
||||
MOVW R2>>26, R9
|
||||
MOVW R3>>20, g
|
||||
MOVW R4>>14, R11
|
||||
MOVW R5>>8, R12
|
||||
ORR R3<<6, R9, R9
|
||||
ORR R4<<12, g, g
|
||||
ORR R5<<18, R11, R11
|
||||
MOVM.IA (R7), [R2-R6]
|
||||
AND R8, R2, R2
|
||||
AND R9, R3, R3
|
||||
AND g, R4, R4
|
||||
AND R11, R5, R5
|
||||
AND R12, R6, R6
|
||||
MOVM.IA.W [R2-R6], (R0)
|
||||
EOR R2, R2, R2
|
||||
EOR R3, R3, R3
|
||||
EOR R4, R4, R4
|
||||
EOR R5, R5, R5
|
||||
EOR R6, R6, R6
|
||||
MOVM.IA.W [R2-R6], (R0)
|
||||
MOVM.IA.W (R1), [R2-R5]
|
||||
MOVM.IA [R2-R6], (R0)
|
||||
ADD $20, R13, R0
|
||||
MOVM.DA (R0), [R4-R7]
|
||||
RET
|
||||
|
||||
#define MOVW_UNALIGNED(Rsrc, Rdst, Rtmp, offset) \
|
||||
MOVBU (offset+0)(Rsrc), Rtmp; \
|
||||
MOVBU Rtmp, (offset+0)(Rdst); \
|
||||
MOVBU (offset+1)(Rsrc), Rtmp; \
|
||||
MOVBU Rtmp, (offset+1)(Rdst); \
|
||||
MOVBU (offset+2)(Rsrc), Rtmp; \
|
||||
MOVBU Rtmp, (offset+2)(Rdst); \
|
||||
MOVBU (offset+3)(Rsrc), Rtmp; \
|
||||
MOVBU Rtmp, (offset+3)(Rdst)
|
||||
|
||||
TEXT poly1305_blocks_armv6<>(SB), NOSPLIT, $0
|
||||
// Needs 24 bytes of stack for saved registers and then 88 bytes of
|
||||
// scratch space after that. We assume that 24 bytes at (R13) have
|
||||
// already been used: four bytes for the link register saved in the
|
||||
// prelude of poly1305_auth_armv6, four bytes for saving the value of g
|
||||
// in that function and 16 bytes of scratch space used around
|
||||
// poly1305_finish_ext_armv6_skip1.
|
||||
ADD $24, R13, R12
|
||||
MOVM.IB [R4-R8, R14], (R12)
|
||||
MOVW R0, 88(R13)
|
||||
MOVW R1, 92(R13)
|
||||
MOVW R2, 96(R13)
|
||||
MOVW R1, R14
|
||||
MOVW R2, R12
|
||||
MOVW 56(R0), R8
|
||||
WORD $0xe1180008 // TST R8, R8 not working see issue 5921
|
||||
EOR R6, R6, R6
|
||||
MOVW.EQ $(1<<24), R6
|
||||
MOVW R6, 84(R13)
|
||||
ADD $116, R13, g
|
||||
MOVM.IA (R0), [R0-R9]
|
||||
MOVM.IA [R0-R4], (g)
|
||||
CMP $16, R12
|
||||
BLO poly1305_blocks_armv6_done
|
||||
|
||||
poly1305_blocks_armv6_mainloop:
|
||||
WORD $0xe31e0003 // TST R14, #3 not working see issue 5921
|
||||
BEQ poly1305_blocks_armv6_mainloop_aligned
|
||||
ADD $100, R13, g
|
||||
MOVW_UNALIGNED(R14, g, R0, 0)
|
||||
MOVW_UNALIGNED(R14, g, R0, 4)
|
||||
MOVW_UNALIGNED(R14, g, R0, 8)
|
||||
MOVW_UNALIGNED(R14, g, R0, 12)
|
||||
MOVM.IA (g), [R0-R3]
|
||||
ADD $16, R14
|
||||
B poly1305_blocks_armv6_mainloop_loaded
|
||||
|
||||
poly1305_blocks_armv6_mainloop_aligned:
|
||||
MOVM.IA.W (R14), [R0-R3]
|
||||
|
||||
poly1305_blocks_armv6_mainloop_loaded:
|
||||
MOVW R0>>26, g
|
||||
MOVW R1>>20, R11
|
||||
MOVW R2>>14, R12
|
||||
MOVW R14, 92(R13)
|
||||
MOVW R3>>8, R4
|
||||
ORR R1<<6, g, g
|
||||
ORR R2<<12, R11, R11
|
||||
ORR R3<<18, R12, R12
|
||||
BIC $0xfc000000, R0, R0
|
||||
BIC $0xfc000000, g, g
|
||||
MOVW 84(R13), R3
|
||||
BIC $0xfc000000, R11, R11
|
||||
BIC $0xfc000000, R12, R12
|
||||
ADD R0, R5, R5
|
||||
ADD g, R6, R6
|
||||
ORR R3, R4, R4
|
||||
ADD R11, R7, R7
|
||||
ADD $116, R13, R14
|
||||
ADD R12, R8, R8
|
||||
ADD R4, R9, R9
|
||||
MOVM.IA (R14), [R0-R4]
|
||||
MULLU R4, R5, (R11, g)
|
||||
MULLU R3, R5, (R14, R12)
|
||||
MULALU R3, R6, (R11, g)
|
||||
MULALU R2, R6, (R14, R12)
|
||||
MULALU R2, R7, (R11, g)
|
||||
MULALU R1, R7, (R14, R12)
|
||||
ADD R4<<2, R4, R4
|
||||
ADD R3<<2, R3, R3
|
||||
MULALU R1, R8, (R11, g)
|
||||
MULALU R0, R8, (R14, R12)
|
||||
MULALU R0, R9, (R11, g)
|
||||
MULALU R4, R9, (R14, R12)
|
||||
MOVW g, 76(R13)
|
||||
MOVW R11, 80(R13)
|
||||
MOVW R12, 68(R13)
|
||||
MOVW R14, 72(R13)
|
||||
MULLU R2, R5, (R11, g)
|
||||
MULLU R1, R5, (R14, R12)
|
||||
MULALU R1, R6, (R11, g)
|
||||
MULALU R0, R6, (R14, R12)
|
||||
MULALU R0, R7, (R11, g)
|
||||
MULALU R4, R7, (R14, R12)
|
||||
ADD R2<<2, R2, R2
|
||||
ADD R1<<2, R1, R1
|
||||
MULALU R4, R8, (R11, g)
|
||||
MULALU R3, R8, (R14, R12)
|
||||
MULALU R3, R9, (R11, g)
|
||||
MULALU R2, R9, (R14, R12)
|
||||
MOVW g, 60(R13)
|
||||
MOVW R11, 64(R13)
|
||||
MOVW R12, 52(R13)
|
||||
MOVW R14, 56(R13)
|
||||
MULLU R0, R5, (R11, g)
|
||||
MULALU R4, R6, (R11, g)
|
||||
MULALU R3, R7, (R11, g)
|
||||
MULALU R2, R8, (R11, g)
|
||||
MULALU R1, R9, (R11, g)
|
||||
ADD $52, R13, R0
|
||||
MOVM.IA (R0), [R0-R7]
|
||||
MOVW g>>26, R12
|
||||
MOVW R4>>26, R14
|
||||
ORR R11<<6, R12, R12
|
||||
ORR R5<<6, R14, R14
|
||||
BIC $0xfc000000, g, g
|
||||
BIC $0xfc000000, R4, R4
|
||||
ADD.S R12, R0, R0
|
||||
ADC $0, R1, R1
|
||||
ADD.S R14, R6, R6
|
||||
ADC $0, R7, R7
|
||||
MOVW R0>>26, R12
|
||||
MOVW R6>>26, R14
|
||||
ORR R1<<6, R12, R12
|
||||
ORR R7<<6, R14, R14
|
||||
BIC $0xfc000000, R0, R0
|
||||
BIC $0xfc000000, R6, R6
|
||||
ADD R14<<2, R14, R14
|
||||
ADD.S R12, R2, R2
|
||||
ADC $0, R3, R3
|
||||
ADD R14, g, g
|
||||
MOVW R2>>26, R12
|
||||
MOVW g>>26, R14
|
||||
ORR R3<<6, R12, R12
|
||||
BIC $0xfc000000, g, R5
|
||||
BIC $0xfc000000, R2, R7
|
||||
ADD R12, R4, R4
|
||||
ADD R14, R0, R0
|
||||
MOVW R4>>26, R12
|
||||
BIC $0xfc000000, R4, R8
|
||||
ADD R12, R6, R9
|
||||
MOVW 96(R13), R12
|
||||
MOVW 92(R13), R14
|
||||
MOVW R0, R6
|
||||
CMP $32, R12
|
||||
SUB $16, R12, R12
|
||||
MOVW R12, 96(R13)
|
||||
BHS poly1305_blocks_armv6_mainloop
|
||||
|
||||
poly1305_blocks_armv6_done:
|
||||
MOVW 88(R13), R12
|
||||
MOVW R5, 20(R12)
|
||||
MOVW R6, 24(R12)
|
||||
MOVW R7, 28(R12)
|
||||
MOVW R8, 32(R12)
|
||||
MOVW R9, 36(R12)
|
||||
ADD $48, R13, R0
|
||||
MOVM.DA (R0), [R4-R8, R14]
|
||||
RET
|
||||
|
||||
#define MOVHUP_UNALIGNED(Rsrc, Rdst, Rtmp) \
|
||||
MOVBU.P 1(Rsrc), Rtmp; \
|
||||
MOVBU.P Rtmp, 1(Rdst); \
|
||||
MOVBU.P 1(Rsrc), Rtmp; \
|
||||
MOVBU.P Rtmp, 1(Rdst)
|
||||
|
||||
#define MOVWP_UNALIGNED(Rsrc, Rdst, Rtmp) \
|
||||
MOVHUP_UNALIGNED(Rsrc, Rdst, Rtmp); \
|
||||
MOVHUP_UNALIGNED(Rsrc, Rdst, Rtmp)
|
||||
|
||||
// func poly1305_auth_armv6(out *[16]byte, m *byte, mlen uint32, key *[32]key)
|
||||
TEXT ·poly1305_auth_armv6(SB), $196-16
|
||||
// The value 196, just above, is the sum of 64 (the size of the context
|
||||
// structure) and 132 (the amount of stack needed).
|
||||
//
|
||||
// At this point, the stack pointer (R13) has been moved down. It
|
||||
// points to the saved link register and there's 196 bytes of free
|
||||
// space above it.
|
||||
//
|
||||
// The stack for this function looks like:
|
||||
//
|
||||
// +---------------------
|
||||
// |
|
||||
// | 64 bytes of context structure
|
||||
// |
|
||||
// +---------------------
|
||||
// |
|
||||
// | 112 bytes for poly1305_blocks_armv6
|
||||
// |
|
||||
// +---------------------
|
||||
// | 16 bytes of final block, constructed at
|
||||
// | poly1305_finish_ext_armv6_skip8
|
||||
// +---------------------
|
||||
// | four bytes of saved 'g'
|
||||
// +---------------------
|
||||
// | lr, saved by prelude <- R13 points here
|
||||
// +---------------------
|
||||
MOVW g, 4(R13)
|
||||
|
||||
MOVW out+0(FP), R4
|
||||
MOVW m+4(FP), R5
|
||||
MOVW mlen+8(FP), R6
|
||||
MOVW key+12(FP), R7
|
||||
|
||||
ADD $136, R13, R0 // 136 = 4 + 4 + 16 + 112
|
||||
MOVW R7, R1
|
||||
|
||||
// poly1305_init_ext_armv6 will write to the stack from R13+4, but
|
||||
// that's ok because none of the other values have been written yet.
|
||||
BL poly1305_init_ext_armv6<>(SB)
|
||||
BIC.S $15, R6, R2
|
||||
BEQ poly1305_auth_armv6_noblocks
|
||||
ADD $136, R13, R0
|
||||
MOVW R5, R1
|
||||
ADD R2, R5, R5
|
||||
SUB R2, R6, R6
|
||||
BL poly1305_blocks_armv6<>(SB)
|
||||
|
||||
poly1305_auth_armv6_noblocks:
|
||||
ADD $136, R13, R0
|
||||
MOVW R5, R1
|
||||
MOVW R6, R2
|
||||
MOVW R4, R3
|
||||
|
||||
MOVW R0, R5
|
||||
MOVW R1, R6
|
||||
MOVW R2, R7
|
||||
MOVW R3, R8
|
||||
AND.S R2, R2, R2
|
||||
BEQ poly1305_finish_ext_armv6_noremaining
|
||||
EOR R0, R0
|
||||
ADD $8, R13, R9 // 8 = offset to 16 byte scratch space
|
||||
MOVW R0, (R9)
|
||||
MOVW R0, 4(R9)
|
||||
MOVW R0, 8(R9)
|
||||
MOVW R0, 12(R9)
|
||||
WORD $0xe3110003 // TST R1, #3 not working see issue 5921
|
||||
BEQ poly1305_finish_ext_armv6_aligned
|
||||
WORD $0xe3120008 // TST R2, #8 not working see issue 5921
|
||||
BEQ poly1305_finish_ext_armv6_skip8
|
||||
MOVWP_UNALIGNED(R1, R9, g)
|
||||
MOVWP_UNALIGNED(R1, R9, g)
|
||||
|
||||
poly1305_finish_ext_armv6_skip8:
|
||||
WORD $0xe3120004 // TST $4, R2 not working see issue 5921
|
||||
BEQ poly1305_finish_ext_armv6_skip4
|
||||
MOVWP_UNALIGNED(R1, R9, g)
|
||||
|
||||
poly1305_finish_ext_armv6_skip4:
|
||||
WORD $0xe3120002 // TST $2, R2 not working see issue 5921
|
||||
BEQ poly1305_finish_ext_armv6_skip2
|
||||
MOVHUP_UNALIGNED(R1, R9, g)
|
||||
B poly1305_finish_ext_armv6_skip2
|
||||
|
||||
poly1305_finish_ext_armv6_aligned:
|
||||
WORD $0xe3120008 // TST R2, #8 not working see issue 5921
|
||||
BEQ poly1305_finish_ext_armv6_skip8_aligned
|
||||
MOVM.IA.W (R1), [g-R11]
|
||||
MOVM.IA.W [g-R11], (R9)
|
||||
|
||||
poly1305_finish_ext_armv6_skip8_aligned:
|
||||
WORD $0xe3120004 // TST $4, R2 not working see issue 5921
|
||||
BEQ poly1305_finish_ext_armv6_skip4_aligned
|
||||
MOVW.P 4(R1), g
|
||||
MOVW.P g, 4(R9)
|
||||
|
||||
poly1305_finish_ext_armv6_skip4_aligned:
|
||||
WORD $0xe3120002 // TST $2, R2 not working see issue 5921
|
||||
BEQ poly1305_finish_ext_armv6_skip2
|
||||
MOVHU.P 2(R1), g
|
||||
MOVH.P g, 2(R9)
|
||||
|
||||
poly1305_finish_ext_armv6_skip2:
|
||||
WORD $0xe3120001 // TST $1, R2 not working see issue 5921
|
||||
BEQ poly1305_finish_ext_armv6_skip1
|
||||
MOVBU.P 1(R1), g
|
||||
MOVBU.P g, 1(R9)
|
||||
|
||||
poly1305_finish_ext_armv6_skip1:
|
||||
MOVW $1, R11
|
||||
MOVBU R11, 0(R9)
|
||||
MOVW R11, 56(R5)
|
||||
MOVW R5, R0
|
||||
ADD $8, R13, R1
|
||||
MOVW $16, R2
|
||||
BL poly1305_blocks_armv6<>(SB)
|
||||
|
||||
poly1305_finish_ext_armv6_noremaining:
|
||||
MOVW 20(R5), R0
|
||||
MOVW 24(R5), R1
|
||||
MOVW 28(R5), R2
|
||||
MOVW 32(R5), R3
|
||||
MOVW 36(R5), R4
|
||||
MOVW R4>>26, R12
|
||||
BIC $0xfc000000, R4, R4
|
||||
ADD R12<<2, R12, R12
|
||||
ADD R12, R0, R0
|
||||
MOVW R0>>26, R12
|
||||
BIC $0xfc000000, R0, R0
|
||||
ADD R12, R1, R1
|
||||
MOVW R1>>26, R12
|
||||
BIC $0xfc000000, R1, R1
|
||||
ADD R12, R2, R2
|
||||
MOVW R2>>26, R12
|
||||
BIC $0xfc000000, R2, R2
|
||||
ADD R12, R3, R3
|
||||
MOVW R3>>26, R12
|
||||
BIC $0xfc000000, R3, R3
|
||||
ADD R12, R4, R4
|
||||
ADD $5, R0, R6
|
||||
MOVW R6>>26, R12
|
||||
BIC $0xfc000000, R6, R6
|
||||
ADD R12, R1, R7
|
||||
MOVW R7>>26, R12
|
||||
BIC $0xfc000000, R7, R7
|
||||
ADD R12, R2, g
|
||||
MOVW g>>26, R12
|
||||
BIC $0xfc000000, g, g
|
||||
ADD R12, R3, R11
|
||||
MOVW $-(1<<26), R12
|
||||
ADD R11>>26, R12, R12
|
||||
BIC $0xfc000000, R11, R11
|
||||
ADD R12, R4, R9
|
||||
MOVW R9>>31, R12
|
||||
SUB $1, R12
|
||||
AND R12, R6, R6
|
||||
AND R12, R7, R7
|
||||
AND R12, g, g
|
||||
AND R12, R11, R11
|
||||
AND R12, R9, R9
|
||||
MVN R12, R12
|
||||
AND R12, R0, R0
|
||||
AND R12, R1, R1
|
||||
AND R12, R2, R2
|
||||
AND R12, R3, R3
|
||||
AND R12, R4, R4
|
||||
ORR R6, R0, R0
|
||||
ORR R7, R1, R1
|
||||
ORR g, R2, R2
|
||||
ORR R11, R3, R3
|
||||
ORR R9, R4, R4
|
||||
ORR R1<<26, R0, R0
|
||||
MOVW R1>>6, R1
|
||||
ORR R2<<20, R1, R1
|
||||
MOVW R2>>12, R2
|
||||
ORR R3<<14, R2, R2
|
||||
MOVW R3>>18, R3
|
||||
ORR R4<<8, R3, R3
|
||||
MOVW 40(R5), R6
|
||||
MOVW 44(R5), R7
|
||||
MOVW 48(R5), g
|
||||
MOVW 52(R5), R11
|
||||
ADD.S R6, R0, R0
|
||||
ADC.S R7, R1, R1
|
||||
ADC.S g, R2, R2
|
||||
ADC.S R11, R3, R3
|
||||
MOVM.IA [R0-R3], (R8)
|
||||
MOVW R5, R12
|
||||
EOR R0, R0, R0
|
||||
EOR R1, R1, R1
|
||||
EOR R2, R2, R2
|
||||
EOR R3, R3, R3
|
||||
EOR R4, R4, R4
|
||||
EOR R5, R5, R5
|
||||
EOR R6, R6, R6
|
||||
EOR R7, R7, R7
|
||||
MOVM.IA.W [R0-R7], (R12)
|
||||
MOVM.IA [R0-R7], (R12)
|
||||
MOVW 4(R13), g
|
||||
RET
|
||||
+14
@@ -0,0 +1,14 @@
|
||||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build s390x,!go1.11 !arm,!amd64,!s390x gccgo appengine nacl
|
||||
|
||||
package poly1305
|
||||
|
||||
// Sum generates an authenticator for msg using a one-time key and puts the
|
||||
// 16-byte result into out. Authenticating two different messages with the same
|
||||
// key allows an attacker to forge messages at will.
|
||||
func Sum(out *[TagSize]byte, msg []byte, key *[32]byte) {
|
||||
sumGeneric(out, msg, key)
|
||||
}
|
||||
+139
@@ -0,0 +1,139 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
package poly1305
|
||||
|
||||
import "encoding/binary"
|
||||
|
||||
// sumGeneric generates an authenticator for msg using a one-time key and
|
||||
// puts the 16-byte result into out. This is the generic implementation of
|
||||
// Sum and should be called if no assembly implementation is available.
|
||||
func sumGeneric(out *[TagSize]byte, msg []byte, key *[32]byte) {
|
||||
var (
|
||||
h0, h1, h2, h3, h4 uint32 // the hash accumulators
|
||||
r0, r1, r2, r3, r4 uint64 // the r part of the key
|
||||
)
|
||||
|
||||
r0 = uint64(binary.LittleEndian.Uint32(key[0:]) & 0x3ffffff)
|
||||
r1 = uint64((binary.LittleEndian.Uint32(key[3:]) >> 2) & 0x3ffff03)
|
||||
r2 = uint64((binary.LittleEndian.Uint32(key[6:]) >> 4) & 0x3ffc0ff)
|
||||
r3 = uint64((binary.LittleEndian.Uint32(key[9:]) >> 6) & 0x3f03fff)
|
||||
r4 = uint64((binary.LittleEndian.Uint32(key[12:]) >> 8) & 0x00fffff)
|
||||
|
||||
R1, R2, R3, R4 := r1*5, r2*5, r3*5, r4*5
|
||||
|
||||
for len(msg) >= TagSize {
|
||||
// h += msg
|
||||
h0 += binary.LittleEndian.Uint32(msg[0:]) & 0x3ffffff
|
||||
h1 += (binary.LittleEndian.Uint32(msg[3:]) >> 2) & 0x3ffffff
|
||||
h2 += (binary.LittleEndian.Uint32(msg[6:]) >> 4) & 0x3ffffff
|
||||
h3 += (binary.LittleEndian.Uint32(msg[9:]) >> 6) & 0x3ffffff
|
||||
h4 += (binary.LittleEndian.Uint32(msg[12:]) >> 8) | (1 << 24)
|
||||
|
||||
// h *= r
|
||||
d0 := (uint64(h0) * r0) + (uint64(h1) * R4) + (uint64(h2) * R3) + (uint64(h3) * R2) + (uint64(h4) * R1)
|
||||
d1 := (d0 >> 26) + (uint64(h0) * r1) + (uint64(h1) * r0) + (uint64(h2) * R4) + (uint64(h3) * R3) + (uint64(h4) * R2)
|
||||
d2 := (d1 >> 26) + (uint64(h0) * r2) + (uint64(h1) * r1) + (uint64(h2) * r0) + (uint64(h3) * R4) + (uint64(h4) * R3)
|
||||
d3 := (d2 >> 26) + (uint64(h0) * r3) + (uint64(h1) * r2) + (uint64(h2) * r1) + (uint64(h3) * r0) + (uint64(h4) * R4)
|
||||
d4 := (d3 >> 26) + (uint64(h0) * r4) + (uint64(h1) * r3) + (uint64(h2) * r2) + (uint64(h3) * r1) + (uint64(h4) * r0)
|
||||
|
||||
// h %= p
|
||||
h0 = uint32(d0) & 0x3ffffff
|
||||
h1 = uint32(d1) & 0x3ffffff
|
||||
h2 = uint32(d2) & 0x3ffffff
|
||||
h3 = uint32(d3) & 0x3ffffff
|
||||
h4 = uint32(d4) & 0x3ffffff
|
||||
|
||||
h0 += uint32(d4>>26) * 5
|
||||
h1 += h0 >> 26
|
||||
h0 = h0 & 0x3ffffff
|
||||
|
||||
msg = msg[TagSize:]
|
||||
}
|
||||
|
||||
if len(msg) > 0 {
|
||||
var block [TagSize]byte
|
||||
off := copy(block[:], msg)
|
||||
block[off] = 0x01
|
||||
|
||||
// h += msg
|
||||
h0 += binary.LittleEndian.Uint32(block[0:]) & 0x3ffffff
|
||||
h1 += (binary.LittleEndian.Uint32(block[3:]) >> 2) & 0x3ffffff
|
||||
h2 += (binary.LittleEndian.Uint32(block[6:]) >> 4) & 0x3ffffff
|
||||
h3 += (binary.LittleEndian.Uint32(block[9:]) >> 6) & 0x3ffffff
|
||||
h4 += (binary.LittleEndian.Uint32(block[12:]) >> 8)
|
||||
|
||||
// h *= r
|
||||
d0 := (uint64(h0) * r0) + (uint64(h1) * R4) + (uint64(h2) * R3) + (uint64(h3) * R2) + (uint64(h4) * R1)
|
||||
d1 := (d0 >> 26) + (uint64(h0) * r1) + (uint64(h1) * r0) + (uint64(h2) * R4) + (uint64(h3) * R3) + (uint64(h4) * R2)
|
||||
d2 := (d1 >> 26) + (uint64(h0) * r2) + (uint64(h1) * r1) + (uint64(h2) * r0) + (uint64(h3) * R4) + (uint64(h4) * R3)
|
||||
d3 := (d2 >> 26) + (uint64(h0) * r3) + (uint64(h1) * r2) + (uint64(h2) * r1) + (uint64(h3) * r0) + (uint64(h4) * R4)
|
||||
d4 := (d3 >> 26) + (uint64(h0) * r4) + (uint64(h1) * r3) + (uint64(h2) * r2) + (uint64(h3) * r1) + (uint64(h4) * r0)
|
||||
|
||||
// h %= p
|
||||
h0 = uint32(d0) & 0x3ffffff
|
||||
h1 = uint32(d1) & 0x3ffffff
|
||||
h2 = uint32(d2) & 0x3ffffff
|
||||
h3 = uint32(d3) & 0x3ffffff
|
||||
h4 = uint32(d4) & 0x3ffffff
|
||||
|
||||
h0 += uint32(d4>>26) * 5
|
||||
h1 += h0 >> 26
|
||||
h0 = h0 & 0x3ffffff
|
||||
}
|
||||
|
||||
// h %= p reduction
|
||||
h2 += h1 >> 26
|
||||
h1 &= 0x3ffffff
|
||||
h3 += h2 >> 26
|
||||
h2 &= 0x3ffffff
|
||||
h4 += h3 >> 26
|
||||
h3 &= 0x3ffffff
|
||||
h0 += 5 * (h4 >> 26)
|
||||
h4 &= 0x3ffffff
|
||||
h1 += h0 >> 26
|
||||
h0 &= 0x3ffffff
|
||||
|
||||
// h - p
|
||||
t0 := h0 + 5
|
||||
t1 := h1 + (t0 >> 26)
|
||||
t2 := h2 + (t1 >> 26)
|
||||
t3 := h3 + (t2 >> 26)
|
||||
t4 := h4 + (t3 >> 26) - (1 << 26)
|
||||
t0 &= 0x3ffffff
|
||||
t1 &= 0x3ffffff
|
||||
t2 &= 0x3ffffff
|
||||
t3 &= 0x3ffffff
|
||||
|
||||
// select h if h < p else h - p
|
||||
t_mask := (t4 >> 31) - 1
|
||||
h_mask := ^t_mask
|
||||
h0 = (h0 & h_mask) | (t0 & t_mask)
|
||||
h1 = (h1 & h_mask) | (t1 & t_mask)
|
||||
h2 = (h2 & h_mask) | (t2 & t_mask)
|
||||
h3 = (h3 & h_mask) | (t3 & t_mask)
|
||||
h4 = (h4 & h_mask) | (t4 & t_mask)
|
||||
|
||||
// h %= 2^128
|
||||
h0 |= h1 << 26
|
||||
h1 = ((h1 >> 6) | (h2 << 20))
|
||||
h2 = ((h2 >> 12) | (h3 << 14))
|
||||
h3 = ((h3 >> 18) | (h4 << 8))
|
||||
|
||||
// s: the s part of the key
|
||||
// tag = (h + s) % (2^128)
|
||||
t := uint64(h0) + uint64(binary.LittleEndian.Uint32(key[16:]))
|
||||
h0 = uint32(t)
|
||||
t = uint64(h1) + uint64(binary.LittleEndian.Uint32(key[20:])) + (t >> 32)
|
||||
h1 = uint32(t)
|
||||
t = uint64(h2) + uint64(binary.LittleEndian.Uint32(key[24:])) + (t >> 32)
|
||||
h2 = uint32(t)
|
||||
t = uint64(h3) + uint64(binary.LittleEndian.Uint32(key[28:])) + (t >> 32)
|
||||
h3 = uint32(t)
|
||||
|
||||
binary.LittleEndian.PutUint32(out[0:], h0)
|
||||
binary.LittleEndian.PutUint32(out[4:], h1)
|
||||
binary.LittleEndian.PutUint32(out[8:], h2)
|
||||
binary.LittleEndian.PutUint32(out[12:], h3)
|
||||
}
|
||||
+49
@@ -0,0 +1,49 @@
|
||||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build s390x,go1.11,!gccgo,!appengine
|
||||
|
||||
package poly1305
|
||||
|
||||
// hasVectorFacility reports whether the machine supports
|
||||
// the vector facility (vx).
|
||||
func hasVectorFacility() bool
|
||||
|
||||
// hasVMSLFacility reports whether the machine supports
|
||||
// Vector Multiply Sum Logical (VMSL).
|
||||
func hasVMSLFacility() bool
|
||||
|
||||
var hasVX = hasVectorFacility()
|
||||
var hasVMSL = hasVMSLFacility()
|
||||
|
||||
// poly1305vx is an assembly implementation of Poly1305 that uses vector
|
||||
// instructions. It must only be called if the vector facility (vx) is
|
||||
// available.
|
||||
//go:noescape
|
||||
func poly1305vx(out *[16]byte, m *byte, mlen uint64, key *[32]byte)
|
||||
|
||||
// poly1305vmsl is an assembly implementation of Poly1305 that uses vector
|
||||
// instructions, including VMSL. It must only be called if the vector facility (vx) is
|
||||
// available and if VMSL is supported.
|
||||
//go:noescape
|
||||
func poly1305vmsl(out *[16]byte, m *byte, mlen uint64, key *[32]byte)
|
||||
|
||||
// Sum generates an authenticator for m using a one-time key and puts the
|
||||
// 16-byte result into out. Authenticating two different messages with the same
|
||||
// key allows an attacker to forge messages at will.
|
||||
func Sum(out *[16]byte, m []byte, key *[32]byte) {
|
||||
if hasVX {
|
||||
var mPtr *byte
|
||||
if len(m) > 0 {
|
||||
mPtr = &m[0]
|
||||
}
|
||||
if hasVMSL && len(m) > 256 {
|
||||
poly1305vmsl(out, mPtr, uint64(len(m)), key)
|
||||
} else {
|
||||
poly1305vx(out, mPtr, uint64(len(m)), key)
|
||||
}
|
||||
} else {
|
||||
sumGeneric(out, m, key)
|
||||
}
|
||||
}
|
||||
+400
@@ -0,0 +1,400 @@
|
||||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build s390x,go1.11,!gccgo,!appengine
|
||||
|
||||
#include "textflag.h"
|
||||
|
||||
// Implementation of Poly1305 using the vector facility (vx).
|
||||
|
||||
// constants
|
||||
#define MOD26 V0
|
||||
#define EX0 V1
|
||||
#define EX1 V2
|
||||
#define EX2 V3
|
||||
|
||||
// temporaries
|
||||
#define T_0 V4
|
||||
#define T_1 V5
|
||||
#define T_2 V6
|
||||
#define T_3 V7
|
||||
#define T_4 V8
|
||||
|
||||
// key (r)
|
||||
#define R_0 V9
|
||||
#define R_1 V10
|
||||
#define R_2 V11
|
||||
#define R_3 V12
|
||||
#define R_4 V13
|
||||
#define R5_1 V14
|
||||
#define R5_2 V15
|
||||
#define R5_3 V16
|
||||
#define R5_4 V17
|
||||
#define RSAVE_0 R5
|
||||
#define RSAVE_1 R6
|
||||
#define RSAVE_2 R7
|
||||
#define RSAVE_3 R8
|
||||
#define RSAVE_4 R9
|
||||
#define R5SAVE_1 V28
|
||||
#define R5SAVE_2 V29
|
||||
#define R5SAVE_3 V30
|
||||
#define R5SAVE_4 V31
|
||||
|
||||
// message block
|
||||
#define F_0 V18
|
||||
#define F_1 V19
|
||||
#define F_2 V20
|
||||
#define F_3 V21
|
||||
#define F_4 V22
|
||||
|
||||
// accumulator
|
||||
#define H_0 V23
|
||||
#define H_1 V24
|
||||
#define H_2 V25
|
||||
#define H_3 V26
|
||||
#define H_4 V27
|
||||
|
||||
GLOBL ·keyMask<>(SB), RODATA, $16
|
||||
DATA ·keyMask<>+0(SB)/8, $0xffffff0ffcffff0f
|
||||
DATA ·keyMask<>+8(SB)/8, $0xfcffff0ffcffff0f
|
||||
|
||||
GLOBL ·bswapMask<>(SB), RODATA, $16
|
||||
DATA ·bswapMask<>+0(SB)/8, $0x0f0e0d0c0b0a0908
|
||||
DATA ·bswapMask<>+8(SB)/8, $0x0706050403020100
|
||||
|
||||
GLOBL ·constants<>(SB), RODATA, $64
|
||||
// MOD26
|
||||
DATA ·constants<>+0(SB)/8, $0x3ffffff
|
||||
DATA ·constants<>+8(SB)/8, $0x3ffffff
|
||||
// EX0
|
||||
DATA ·constants<>+16(SB)/8, $0x0006050403020100
|
||||
DATA ·constants<>+24(SB)/8, $0x1016151413121110
|
||||
// EX1
|
||||
DATA ·constants<>+32(SB)/8, $0x060c0b0a09080706
|
||||
DATA ·constants<>+40(SB)/8, $0x161c1b1a19181716
|
||||
// EX2
|
||||
DATA ·constants<>+48(SB)/8, $0x0d0d0d0d0d0f0e0d
|
||||
DATA ·constants<>+56(SB)/8, $0x1d1d1d1d1d1f1e1d
|
||||
|
||||
// h = (f*g) % (2**130-5) [partial reduction]
|
||||
#define MULTIPLY(f0, f1, f2, f3, f4, g0, g1, g2, g3, g4, g51, g52, g53, g54, h0, h1, h2, h3, h4) \
|
||||
VMLOF f0, g0, h0 \
|
||||
VMLOF f0, g1, h1 \
|
||||
VMLOF f0, g2, h2 \
|
||||
VMLOF f0, g3, h3 \
|
||||
VMLOF f0, g4, h4 \
|
||||
VMLOF f1, g54, T_0 \
|
||||
VMLOF f1, g0, T_1 \
|
||||
VMLOF f1, g1, T_2 \
|
||||
VMLOF f1, g2, T_3 \
|
||||
VMLOF f1, g3, T_4 \
|
||||
VMALOF f2, g53, h0, h0 \
|
||||
VMALOF f2, g54, h1, h1 \
|
||||
VMALOF f2, g0, h2, h2 \
|
||||
VMALOF f2, g1, h3, h3 \
|
||||
VMALOF f2, g2, h4, h4 \
|
||||
VMALOF f3, g52, T_0, T_0 \
|
||||
VMALOF f3, g53, T_1, T_1 \
|
||||
VMALOF f3, g54, T_2, T_2 \
|
||||
VMALOF f3, g0, T_3, T_3 \
|
||||
VMALOF f3, g1, T_4, T_4 \
|
||||
VMALOF f4, g51, h0, h0 \
|
||||
VMALOF f4, g52, h1, h1 \
|
||||
VMALOF f4, g53, h2, h2 \
|
||||
VMALOF f4, g54, h3, h3 \
|
||||
VMALOF f4, g0, h4, h4 \
|
||||
VAG T_0, h0, h0 \
|
||||
VAG T_1, h1, h1 \
|
||||
VAG T_2, h2, h2 \
|
||||
VAG T_3, h3, h3 \
|
||||
VAG T_4, h4, h4
|
||||
|
||||
// carry h0->h1 h3->h4, h1->h2 h4->h0, h0->h1 h2->h3, h3->h4
|
||||
#define REDUCE(h0, h1, h2, h3, h4) \
|
||||
VESRLG $26, h0, T_0 \
|
||||
VESRLG $26, h3, T_1 \
|
||||
VN MOD26, h0, h0 \
|
||||
VN MOD26, h3, h3 \
|
||||
VAG T_0, h1, h1 \
|
||||
VAG T_1, h4, h4 \
|
||||
VESRLG $26, h1, T_2 \
|
||||
VESRLG $26, h4, T_3 \
|
||||
VN MOD26, h1, h1 \
|
||||
VN MOD26, h4, h4 \
|
||||
VESLG $2, T_3, T_4 \
|
||||
VAG T_3, T_4, T_4 \
|
||||
VAG T_2, h2, h2 \
|
||||
VAG T_4, h0, h0 \
|
||||
VESRLG $26, h2, T_0 \
|
||||
VESRLG $26, h0, T_1 \
|
||||
VN MOD26, h2, h2 \
|
||||
VN MOD26, h0, h0 \
|
||||
VAG T_0, h3, h3 \
|
||||
VAG T_1, h1, h1 \
|
||||
VESRLG $26, h3, T_2 \
|
||||
VN MOD26, h3, h3 \
|
||||
VAG T_2, h4, h4
|
||||
|
||||
// expand in0 into d[0] and in1 into d[1]
|
||||
#define EXPAND(in0, in1, d0, d1, d2, d3, d4) \
|
||||
VGBM $0x0707, d1 \ // d1=tmp
|
||||
VPERM in0, in1, EX2, d4 \
|
||||
VPERM in0, in1, EX0, d0 \
|
||||
VPERM in0, in1, EX1, d2 \
|
||||
VN d1, d4, d4 \
|
||||
VESRLG $26, d0, d1 \
|
||||
VESRLG $30, d2, d3 \
|
||||
VESRLG $4, d2, d2 \
|
||||
VN MOD26, d0, d0 \
|
||||
VN MOD26, d1, d1 \
|
||||
VN MOD26, d2, d2 \
|
||||
VN MOD26, d3, d3
|
||||
|
||||
// pack h4:h0 into h1:h0 (no carry)
|
||||
#define PACK(h0, h1, h2, h3, h4) \
|
||||
VESLG $26, h1, h1 \
|
||||
VESLG $26, h3, h3 \
|
||||
VO h0, h1, h0 \
|
||||
VO h2, h3, h2 \
|
||||
VESLG $4, h2, h2 \
|
||||
VLEIB $7, $48, h1 \
|
||||
VSLB h1, h2, h2 \
|
||||
VO h0, h2, h0 \
|
||||
VLEIB $7, $104, h1 \
|
||||
VSLB h1, h4, h3 \
|
||||
VO h3, h0, h0 \
|
||||
VLEIB $7, $24, h1 \
|
||||
VSRLB h1, h4, h1
|
||||
|
||||
// if h > 2**130-5 then h -= 2**130-5
|
||||
#define MOD(h0, h1, t0, t1, t2) \
|
||||
VZERO t0 \
|
||||
VLEIG $1, $5, t0 \
|
||||
VACCQ h0, t0, t1 \
|
||||
VAQ h0, t0, t0 \
|
||||
VONE t2 \
|
||||
VLEIG $1, $-4, t2 \
|
||||
VAQ t2, t1, t1 \
|
||||
VACCQ h1, t1, t1 \
|
||||
VONE t2 \
|
||||
VAQ t2, t1, t1 \
|
||||
VN h0, t1, t2 \
|
||||
VNC t0, t1, t1 \
|
||||
VO t1, t2, h0
|
||||
|
||||
// func poly1305vx(out *[16]byte, m *byte, mlen uint64, key *[32]key)
|
||||
TEXT ·poly1305vx(SB), $0-32
|
||||
// This code processes up to 2 blocks (32 bytes) per iteration
|
||||
// using the algorithm described in:
|
||||
// NEON crypto, Daniel J. Bernstein & Peter Schwabe
|
||||
// https://cryptojedi.org/papers/neoncrypto-20120320.pdf
|
||||
LMG out+0(FP), R1, R4 // R1=out, R2=m, R3=mlen, R4=key
|
||||
|
||||
// load MOD26, EX0, EX1 and EX2
|
||||
MOVD $·constants<>(SB), R5
|
||||
VLM (R5), MOD26, EX2
|
||||
|
||||
// setup r
|
||||
VL (R4), T_0
|
||||
MOVD $·keyMask<>(SB), R6
|
||||
VL (R6), T_1
|
||||
VN T_0, T_1, T_0
|
||||
EXPAND(T_0, T_0, R_0, R_1, R_2, R_3, R_4)
|
||||
|
||||
// setup r*5
|
||||
VLEIG $0, $5, T_0
|
||||
VLEIG $1, $5, T_0
|
||||
|
||||
// store r (for final block)
|
||||
VMLOF T_0, R_1, R5SAVE_1
|
||||
VMLOF T_0, R_2, R5SAVE_2
|
||||
VMLOF T_0, R_3, R5SAVE_3
|
||||
VMLOF T_0, R_4, R5SAVE_4
|
||||
VLGVG $0, R_0, RSAVE_0
|
||||
VLGVG $0, R_1, RSAVE_1
|
||||
VLGVG $0, R_2, RSAVE_2
|
||||
VLGVG $0, R_3, RSAVE_3
|
||||
VLGVG $0, R_4, RSAVE_4
|
||||
|
||||
// skip r**2 calculation
|
||||
CMPBLE R3, $16, skip
|
||||
|
||||
// calculate r**2
|
||||
MULTIPLY(R_0, R_1, R_2, R_3, R_4, R_0, R_1, R_2, R_3, R_4, R5SAVE_1, R5SAVE_2, R5SAVE_3, R5SAVE_4, H_0, H_1, H_2, H_3, H_4)
|
||||
REDUCE(H_0, H_1, H_2, H_3, H_4)
|
||||
VLEIG $0, $5, T_0
|
||||
VLEIG $1, $5, T_0
|
||||
VMLOF T_0, H_1, R5_1
|
||||
VMLOF T_0, H_2, R5_2
|
||||
VMLOF T_0, H_3, R5_3
|
||||
VMLOF T_0, H_4, R5_4
|
||||
VLR H_0, R_0
|
||||
VLR H_1, R_1
|
||||
VLR H_2, R_2
|
||||
VLR H_3, R_3
|
||||
VLR H_4, R_4
|
||||
|
||||
// initialize h
|
||||
VZERO H_0
|
||||
VZERO H_1
|
||||
VZERO H_2
|
||||
VZERO H_3
|
||||
VZERO H_4
|
||||
|
||||
loop:
|
||||
CMPBLE R3, $32, b2
|
||||
VLM (R2), T_0, T_1
|
||||
SUB $32, R3
|
||||
MOVD $32(R2), R2
|
||||
EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4)
|
||||
VLEIB $4, $1, F_4
|
||||
VLEIB $12, $1, F_4
|
||||
|
||||
multiply:
|
||||
VAG H_0, F_0, F_0
|
||||
VAG H_1, F_1, F_1
|
||||
VAG H_2, F_2, F_2
|
||||
VAG H_3, F_3, F_3
|
||||
VAG H_4, F_4, F_4
|
||||
MULTIPLY(F_0, F_1, F_2, F_3, F_4, R_0, R_1, R_2, R_3, R_4, R5_1, R5_2, R5_3, R5_4, H_0, H_1, H_2, H_3, H_4)
|
||||
REDUCE(H_0, H_1, H_2, H_3, H_4)
|
||||
CMPBNE R3, $0, loop
|
||||
|
||||
finish:
|
||||
// sum vectors
|
||||
VZERO T_0
|
||||
VSUMQG H_0, T_0, H_0
|
||||
VSUMQG H_1, T_0, H_1
|
||||
VSUMQG H_2, T_0, H_2
|
||||
VSUMQG H_3, T_0, H_3
|
||||
VSUMQG H_4, T_0, H_4
|
||||
|
||||
// h may be >= 2*(2**130-5) so we need to reduce it again
|
||||
REDUCE(H_0, H_1, H_2, H_3, H_4)
|
||||
|
||||
// carry h1->h4
|
||||
VESRLG $26, H_1, T_1
|
||||
VN MOD26, H_1, H_1
|
||||
VAQ T_1, H_2, H_2
|
||||
VESRLG $26, H_2, T_2
|
||||
VN MOD26, H_2, H_2
|
||||
VAQ T_2, H_3, H_3
|
||||
VESRLG $26, H_3, T_3
|
||||
VN MOD26, H_3, H_3
|
||||
VAQ T_3, H_4, H_4
|
||||
|
||||
// h is now < 2*(2**130-5)
|
||||
// pack h into h1 (hi) and h0 (lo)
|
||||
PACK(H_0, H_1, H_2, H_3, H_4)
|
||||
|
||||
// if h > 2**130-5 then h -= 2**130-5
|
||||
MOD(H_0, H_1, T_0, T_1, T_2)
|
||||
|
||||
// h += s
|
||||
MOVD $·bswapMask<>(SB), R5
|
||||
VL (R5), T_1
|
||||
VL 16(R4), T_0
|
||||
VPERM T_0, T_0, T_1, T_0 // reverse bytes (to big)
|
||||
VAQ T_0, H_0, H_0
|
||||
VPERM H_0, H_0, T_1, H_0 // reverse bytes (to little)
|
||||
VST H_0, (R1)
|
||||
|
||||
RET
|
||||
|
||||
b2:
|
||||
CMPBLE R3, $16, b1
|
||||
|
||||
// 2 blocks remaining
|
||||
SUB $17, R3
|
||||
VL (R2), T_0
|
||||
VLL R3, 16(R2), T_1
|
||||
ADD $1, R3
|
||||
MOVBZ $1, R0
|
||||
CMPBEQ R3, $16, 2(PC)
|
||||
VLVGB R3, R0, T_1
|
||||
EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4)
|
||||
CMPBNE R3, $16, 2(PC)
|
||||
VLEIB $12, $1, F_4
|
||||
VLEIB $4, $1, F_4
|
||||
|
||||
// setup [r²,r]
|
||||
VLVGG $1, RSAVE_0, R_0
|
||||
VLVGG $1, RSAVE_1, R_1
|
||||
VLVGG $1, RSAVE_2, R_2
|
||||
VLVGG $1, RSAVE_3, R_3
|
||||
VLVGG $1, RSAVE_4, R_4
|
||||
VPDI $0, R5_1, R5SAVE_1, R5_1
|
||||
VPDI $0, R5_2, R5SAVE_2, R5_2
|
||||
VPDI $0, R5_3, R5SAVE_3, R5_3
|
||||
VPDI $0, R5_4, R5SAVE_4, R5_4
|
||||
|
||||
MOVD $0, R3
|
||||
BR multiply
|
||||
|
||||
skip:
|
||||
VZERO H_0
|
||||
VZERO H_1
|
||||
VZERO H_2
|
||||
VZERO H_3
|
||||
VZERO H_4
|
||||
|
||||
CMPBEQ R3, $0, finish
|
||||
|
||||
b1:
|
||||
// 1 block remaining
|
||||
SUB $1, R3
|
||||
VLL R3, (R2), T_0
|
||||
ADD $1, R3
|
||||
MOVBZ $1, R0
|
||||
CMPBEQ R3, $16, 2(PC)
|
||||
VLVGB R3, R0, T_0
|
||||
VZERO T_1
|
||||
EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4)
|
||||
CMPBNE R3, $16, 2(PC)
|
||||
VLEIB $4, $1, F_4
|
||||
VLEIG $1, $1, R_0
|
||||
VZERO R_1
|
||||
VZERO R_2
|
||||
VZERO R_3
|
||||
VZERO R_4
|
||||
VZERO R5_1
|
||||
VZERO R5_2
|
||||
VZERO R5_3
|
||||
VZERO R5_4
|
||||
|
||||
// setup [r, 1]
|
||||
VLVGG $0, RSAVE_0, R_0
|
||||
VLVGG $0, RSAVE_1, R_1
|
||||
VLVGG $0, RSAVE_2, R_2
|
||||
VLVGG $0, RSAVE_3, R_3
|
||||
VLVGG $0, RSAVE_4, R_4
|
||||
VPDI $0, R5SAVE_1, R5_1, R5_1
|
||||
VPDI $0, R5SAVE_2, R5_2, R5_2
|
||||
VPDI $0, R5SAVE_3, R5_3, R5_3
|
||||
VPDI $0, R5SAVE_4, R5_4, R5_4
|
||||
|
||||
MOVD $0, R3
|
||||
BR multiply
|
||||
|
||||
TEXT ·hasVectorFacility(SB), NOSPLIT, $24-1
|
||||
MOVD $x-24(SP), R1
|
||||
XC $24, 0(R1), 0(R1) // clear the storage
|
||||
MOVD $2, R0 // R0 is the number of double words stored -1
|
||||
WORD $0xB2B01000 // STFLE 0(R1)
|
||||
XOR R0, R0 // reset the value of R0
|
||||
MOVBZ z-8(SP), R1
|
||||
AND $0x40, R1
|
||||
BEQ novector
|
||||
|
||||
vectorinstalled:
|
||||
// check if the vector instruction has been enabled
|
||||
VLEIB $0, $0xF, V16
|
||||
VLGVB $0, V16, R1
|
||||
CMPBNE R1, $0xF, novector
|
||||
MOVB $1, ret+0(FP) // have vx
|
||||
RET
|
||||
|
||||
novector:
|
||||
MOVB $0, ret+0(FP) // no vx
|
||||
RET
|
||||
+931
@@ -0,0 +1,931 @@
|
||||
// Copyright 2018 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build s390x,go1.11,!gccgo,!appengine
|
||||
|
||||
#include "textflag.h"
|
||||
|
||||
// Implementation of Poly1305 using the vector facility (vx) and the VMSL instruction.
|
||||
|
||||
// constants
|
||||
#define EX0 V1
|
||||
#define EX1 V2
|
||||
#define EX2 V3
|
||||
|
||||
// temporaries
|
||||
#define T_0 V4
|
||||
#define T_1 V5
|
||||
#define T_2 V6
|
||||
#define T_3 V7
|
||||
#define T_4 V8
|
||||
#define T_5 V9
|
||||
#define T_6 V10
|
||||
#define T_7 V11
|
||||
#define T_8 V12
|
||||
#define T_9 V13
|
||||
#define T_10 V14
|
||||
|
||||
// r**2 & r**4
|
||||
#define R_0 V15
|
||||
#define R_1 V16
|
||||
#define R_2 V17
|
||||
#define R5_1 V18
|
||||
#define R5_2 V19
|
||||
// key (r)
|
||||
#define RSAVE_0 R7
|
||||
#define RSAVE_1 R8
|
||||
#define RSAVE_2 R9
|
||||
#define R5SAVE_1 R10
|
||||
#define R5SAVE_2 R11
|
||||
|
||||
// message block
|
||||
#define M0 V20
|
||||
#define M1 V21
|
||||
#define M2 V22
|
||||
#define M3 V23
|
||||
#define M4 V24
|
||||
#define M5 V25
|
||||
|
||||
// accumulator
|
||||
#define H0_0 V26
|
||||
#define H1_0 V27
|
||||
#define H2_0 V28
|
||||
#define H0_1 V29
|
||||
#define H1_1 V30
|
||||
#define H2_1 V31
|
||||
|
||||
GLOBL ·keyMask<>(SB), RODATA, $16
|
||||
DATA ·keyMask<>+0(SB)/8, $0xffffff0ffcffff0f
|
||||
DATA ·keyMask<>+8(SB)/8, $0xfcffff0ffcffff0f
|
||||
|
||||
GLOBL ·bswapMask<>(SB), RODATA, $16
|
||||
DATA ·bswapMask<>+0(SB)/8, $0x0f0e0d0c0b0a0908
|
||||
DATA ·bswapMask<>+8(SB)/8, $0x0706050403020100
|
||||
|
||||
GLOBL ·constants<>(SB), RODATA, $48
|
||||
// EX0
|
||||
DATA ·constants<>+0(SB)/8, $0x18191a1b1c1d1e1f
|
||||
DATA ·constants<>+8(SB)/8, $0x0000050403020100
|
||||
// EX1
|
||||
DATA ·constants<>+16(SB)/8, $0x18191a1b1c1d1e1f
|
||||
DATA ·constants<>+24(SB)/8, $0x00000a0908070605
|
||||
// EX2
|
||||
DATA ·constants<>+32(SB)/8, $0x18191a1b1c1d1e1f
|
||||
DATA ·constants<>+40(SB)/8, $0x0000000f0e0d0c0b
|
||||
|
||||
GLOBL ·c<>(SB), RODATA, $48
|
||||
// EX0
|
||||
DATA ·c<>+0(SB)/8, $0x0000050403020100
|
||||
DATA ·c<>+8(SB)/8, $0x0000151413121110
|
||||
// EX1
|
||||
DATA ·c<>+16(SB)/8, $0x00000a0908070605
|
||||
DATA ·c<>+24(SB)/8, $0x00001a1918171615
|
||||
// EX2
|
||||
DATA ·c<>+32(SB)/8, $0x0000000f0e0d0c0b
|
||||
DATA ·c<>+40(SB)/8, $0x0000001f1e1d1c1b
|
||||
|
||||
GLOBL ·reduce<>(SB), RODATA, $32
|
||||
// 44 bit
|
||||
DATA ·reduce<>+0(SB)/8, $0x0
|
||||
DATA ·reduce<>+8(SB)/8, $0xfffffffffff
|
||||
// 42 bit
|
||||
DATA ·reduce<>+16(SB)/8, $0x0
|
||||
DATA ·reduce<>+24(SB)/8, $0x3ffffffffff
|
||||
|
||||
// h = (f*g) % (2**130-5) [partial reduction]
|
||||
// uses T_0...T_9 temporary registers
|
||||
// input: m02_0, m02_1, m02_2, m13_0, m13_1, m13_2, r_0, r_1, r_2, r5_1, r5_2, m4_0, m4_1, m4_2, m5_0, m5_1, m5_2
|
||||
// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8, t9
|
||||
// output: m02_0, m02_1, m02_2, m13_0, m13_1, m13_2
|
||||
#define MULTIPLY(m02_0, m02_1, m02_2, m13_0, m13_1, m13_2, r_0, r_1, r_2, r5_1, r5_2, m4_0, m4_1, m4_2, m5_0, m5_1, m5_2, t0, t1, t2, t3, t4, t5, t6, t7, t8, t9) \
|
||||
\ // Eliminate the dependency for the last 2 VMSLs
|
||||
VMSLG m02_0, r_2, m4_2, m4_2 \
|
||||
VMSLG m13_0, r_2, m5_2, m5_2 \ // 8 VMSLs pipelined
|
||||
VMSLG m02_0, r_0, m4_0, m4_0 \
|
||||
VMSLG m02_1, r5_2, V0, T_0 \
|
||||
VMSLG m02_0, r_1, m4_1, m4_1 \
|
||||
VMSLG m02_1, r_0, V0, T_1 \
|
||||
VMSLG m02_1, r_1, V0, T_2 \
|
||||
VMSLG m02_2, r5_1, V0, T_3 \
|
||||
VMSLG m02_2, r5_2, V0, T_4 \
|
||||
VMSLG m13_0, r_0, m5_0, m5_0 \
|
||||
VMSLG m13_1, r5_2, V0, T_5 \
|
||||
VMSLG m13_0, r_1, m5_1, m5_1 \
|
||||
VMSLG m13_1, r_0, V0, T_6 \
|
||||
VMSLG m13_1, r_1, V0, T_7 \
|
||||
VMSLG m13_2, r5_1, V0, T_8 \
|
||||
VMSLG m13_2, r5_2, V0, T_9 \
|
||||
VMSLG m02_2, r_0, m4_2, m4_2 \
|
||||
VMSLG m13_2, r_0, m5_2, m5_2 \
|
||||
VAQ m4_0, T_0, m02_0 \
|
||||
VAQ m4_1, T_1, m02_1 \
|
||||
VAQ m5_0, T_5, m13_0 \
|
||||
VAQ m5_1, T_6, m13_1 \
|
||||
VAQ m02_0, T_3, m02_0 \
|
||||
VAQ m02_1, T_4, m02_1 \
|
||||
VAQ m13_0, T_8, m13_0 \
|
||||
VAQ m13_1, T_9, m13_1 \
|
||||
VAQ m4_2, T_2, m02_2 \
|
||||
VAQ m5_2, T_7, m13_2 \
|
||||
|
||||
// SQUARE uses three limbs of r and r_2*5 to output square of r
|
||||
// uses T_1, T_5 and T_7 temporary registers
|
||||
// input: r_0, r_1, r_2, r5_2
|
||||
// temp: TEMP0, TEMP1, TEMP2
|
||||
// output: p0, p1, p2
|
||||
#define SQUARE(r_0, r_1, r_2, r5_2, p0, p1, p2, TEMP0, TEMP1, TEMP2) \
|
||||
VMSLG r_0, r_0, p0, p0 \
|
||||
VMSLG r_1, r5_2, V0, TEMP0 \
|
||||
VMSLG r_2, r5_2, p1, p1 \
|
||||
VMSLG r_0, r_1, V0, TEMP1 \
|
||||
VMSLG r_1, r_1, p2, p2 \
|
||||
VMSLG r_0, r_2, V0, TEMP2 \
|
||||
VAQ TEMP0, p0, p0 \
|
||||
VAQ TEMP1, p1, p1 \
|
||||
VAQ TEMP2, p2, p2 \
|
||||
VAQ TEMP0, p0, p0 \
|
||||
VAQ TEMP1, p1, p1 \
|
||||
VAQ TEMP2, p2, p2 \
|
||||
|
||||
// carry h0->h1->h2->h0 || h3->h4->h5->h3
|
||||
// uses T_2, T_4, T_5, T_7, T_8, T_9
|
||||
// t6, t7, t8, t9, t10, t11
|
||||
// input: h0, h1, h2, h3, h4, h5
|
||||
// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11
|
||||
// output: h0, h1, h2, h3, h4, h5
|
||||
#define REDUCE(h0, h1, h2, h3, h4, h5, t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11) \
|
||||
VLM (R12), t6, t7 \ // 44 and 42 bit clear mask
|
||||
VLEIB $7, $0x28, t10 \ // 5 byte shift mask
|
||||
VREPIB $4, t8 \ // 4 bit shift mask
|
||||
VREPIB $2, t11 \ // 2 bit shift mask
|
||||
VSRLB t10, h0, t0 \ // h0 byte shift
|
||||
VSRLB t10, h1, t1 \ // h1 byte shift
|
||||
VSRLB t10, h2, t2 \ // h2 byte shift
|
||||
VSRLB t10, h3, t3 \ // h3 byte shift
|
||||
VSRLB t10, h4, t4 \ // h4 byte shift
|
||||
VSRLB t10, h5, t5 \ // h5 byte shift
|
||||
VSRL t8, t0, t0 \ // h0 bit shift
|
||||
VSRL t8, t1, t1 \ // h2 bit shift
|
||||
VSRL t11, t2, t2 \ // h2 bit shift
|
||||
VSRL t8, t3, t3 \ // h3 bit shift
|
||||
VSRL t8, t4, t4 \ // h4 bit shift
|
||||
VESLG $2, t2, t9 \ // h2 carry x5
|
||||
VSRL t11, t5, t5 \ // h5 bit shift
|
||||
VN t6, h0, h0 \ // h0 clear carry
|
||||
VAQ t2, t9, t2 \ // h2 carry x5
|
||||
VESLG $2, t5, t9 \ // h5 carry x5
|
||||
VN t6, h1, h1 \ // h1 clear carry
|
||||
VN t7, h2, h2 \ // h2 clear carry
|
||||
VAQ t5, t9, t5 \ // h5 carry x5
|
||||
VN t6, h3, h3 \ // h3 clear carry
|
||||
VN t6, h4, h4 \ // h4 clear carry
|
||||
VN t7, h5, h5 \ // h5 clear carry
|
||||
VAQ t0, h1, h1 \ // h0->h1
|
||||
VAQ t3, h4, h4 \ // h3->h4
|
||||
VAQ t1, h2, h2 \ // h1->h2
|
||||
VAQ t4, h5, h5 \ // h4->h5
|
||||
VAQ t2, h0, h0 \ // h2->h0
|
||||
VAQ t5, h3, h3 \ // h5->h3
|
||||
VREPG $1, t6, t6 \ // 44 and 42 bit masks across both halves
|
||||
VREPG $1, t7, t7 \
|
||||
VSLDB $8, h0, h0, h0 \ // set up [h0/1/2, h3/4/5]
|
||||
VSLDB $8, h1, h1, h1 \
|
||||
VSLDB $8, h2, h2, h2 \
|
||||
VO h0, h3, h3 \
|
||||
VO h1, h4, h4 \
|
||||
VO h2, h5, h5 \
|
||||
VESRLG $44, h3, t0 \ // 44 bit shift right
|
||||
VESRLG $44, h4, t1 \
|
||||
VESRLG $42, h5, t2 \
|
||||
VN t6, h3, h3 \ // clear carry bits
|
||||
VN t6, h4, h4 \
|
||||
VN t7, h5, h5 \
|
||||
VESLG $2, t2, t9 \ // multiply carry by 5
|
||||
VAQ t9, t2, t2 \
|
||||
VAQ t0, h4, h4 \
|
||||
VAQ t1, h5, h5 \
|
||||
VAQ t2, h3, h3 \
|
||||
|
||||
// carry h0->h1->h2->h0
|
||||
// input: h0, h1, h2
|
||||
// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8
|
||||
// output: h0, h1, h2
|
||||
#define REDUCE2(h0, h1, h2, t0, t1, t2, t3, t4, t5, t6, t7, t8) \
|
||||
VLEIB $7, $0x28, t3 \ // 5 byte shift mask
|
||||
VREPIB $4, t4 \ // 4 bit shift mask
|
||||
VREPIB $2, t7 \ // 2 bit shift mask
|
||||
VGBM $0x003F, t5 \ // mask to clear carry bits
|
||||
VSRLB t3, h0, t0 \
|
||||
VSRLB t3, h1, t1 \
|
||||
VSRLB t3, h2, t2 \
|
||||
VESRLG $4, t5, t5 \ // 44 bit clear mask
|
||||
VSRL t4, t0, t0 \
|
||||
VSRL t4, t1, t1 \
|
||||
VSRL t7, t2, t2 \
|
||||
VESRLG $2, t5, t6 \ // 42 bit clear mask
|
||||
VESLG $2, t2, t8 \
|
||||
VAQ t8, t2, t2 \
|
||||
VN t5, h0, h0 \
|
||||
VN t5, h1, h1 \
|
||||
VN t6, h2, h2 \
|
||||
VAQ t0, h1, h1 \
|
||||
VAQ t1, h2, h2 \
|
||||
VAQ t2, h0, h0 \
|
||||
VSRLB t3, h0, t0 \
|
||||
VSRLB t3, h1, t1 \
|
||||
VSRLB t3, h2, t2 \
|
||||
VSRL t4, t0, t0 \
|
||||
VSRL t4, t1, t1 \
|
||||
VSRL t7, t2, t2 \
|
||||
VN t5, h0, h0 \
|
||||
VN t5, h1, h1 \
|
||||
VESLG $2, t2, t8 \
|
||||
VN t6, h2, h2 \
|
||||
VAQ t0, h1, h1 \
|
||||
VAQ t8, t2, t2 \
|
||||
VAQ t1, h2, h2 \
|
||||
VAQ t2, h0, h0 \
|
||||
|
||||
// expands two message blocks into the lower halfs of the d registers
|
||||
// moves the contents of the d registers into upper halfs
|
||||
// input: in1, in2, d0, d1, d2, d3, d4, d5
|
||||
// temp: TEMP0, TEMP1, TEMP2, TEMP3
|
||||
// output: d0, d1, d2, d3, d4, d5
|
||||
#define EXPACC(in1, in2, d0, d1, d2, d3, d4, d5, TEMP0, TEMP1, TEMP2, TEMP3) \
|
||||
VGBM $0xff3f, TEMP0 \
|
||||
VGBM $0xff1f, TEMP1 \
|
||||
VESLG $4, d1, TEMP2 \
|
||||
VESLG $4, d4, TEMP3 \
|
||||
VESRLG $4, TEMP0, TEMP0 \
|
||||
VPERM in1, d0, EX0, d0 \
|
||||
VPERM in2, d3, EX0, d3 \
|
||||
VPERM in1, d2, EX2, d2 \
|
||||
VPERM in2, d5, EX2, d5 \
|
||||
VPERM in1, TEMP2, EX1, d1 \
|
||||
VPERM in2, TEMP3, EX1, d4 \
|
||||
VN TEMP0, d0, d0 \
|
||||
VN TEMP0, d3, d3 \
|
||||
VESRLG $4, d1, d1 \
|
||||
VESRLG $4, d4, d4 \
|
||||
VN TEMP1, d2, d2 \
|
||||
VN TEMP1, d5, d5 \
|
||||
VN TEMP0, d1, d1 \
|
||||
VN TEMP0, d4, d4 \
|
||||
|
||||
// expands one message block into the lower halfs of the d registers
|
||||
// moves the contents of the d registers into upper halfs
|
||||
// input: in, d0, d1, d2
|
||||
// temp: TEMP0, TEMP1, TEMP2
|
||||
// output: d0, d1, d2
|
||||
#define EXPACC2(in, d0, d1, d2, TEMP0, TEMP1, TEMP2) \
|
||||
VGBM $0xff3f, TEMP0 \
|
||||
VESLG $4, d1, TEMP2 \
|
||||
VGBM $0xff1f, TEMP1 \
|
||||
VPERM in, d0, EX0, d0 \
|
||||
VESRLG $4, TEMP0, TEMP0 \
|
||||
VPERM in, d2, EX2, d2 \
|
||||
VPERM in, TEMP2, EX1, d1 \
|
||||
VN TEMP0, d0, d0 \
|
||||
VN TEMP1, d2, d2 \
|
||||
VESRLG $4, d1, d1 \
|
||||
VN TEMP0, d1, d1 \
|
||||
|
||||
// pack h2:h0 into h1:h0 (no carry)
|
||||
// input: h0, h1, h2
|
||||
// output: h0, h1, h2
|
||||
#define PACK(h0, h1, h2) \
|
||||
VMRLG h1, h2, h2 \ // copy h1 to upper half h2
|
||||
VESLG $44, h1, h1 \ // shift limb 1 44 bits, leaving 20
|
||||
VO h0, h1, h0 \ // combine h0 with 20 bits from limb 1
|
||||
VESRLG $20, h2, h1 \ // put top 24 bits of limb 1 into h1
|
||||
VLEIG $1, $0, h1 \ // clear h2 stuff from lower half of h1
|
||||
VO h0, h1, h0 \ // h0 now has 88 bits (limb 0 and 1)
|
||||
VLEIG $0, $0, h2 \ // clear upper half of h2
|
||||
VESRLG $40, h2, h1 \ // h1 now has upper two bits of result
|
||||
VLEIB $7, $88, h1 \ // for byte shift (11 bytes)
|
||||
VSLB h1, h2, h2 \ // shift h2 11 bytes to the left
|
||||
VO h0, h2, h0 \ // combine h0 with 20 bits from limb 1
|
||||
VLEIG $0, $0, h1 \ // clear upper half of h1
|
||||
|
||||
// if h > 2**130-5 then h -= 2**130-5
|
||||
// input: h0, h1
|
||||
// temp: t0, t1, t2
|
||||
// output: h0
|
||||
#define MOD(h0, h1, t0, t1, t2) \
|
||||
VZERO t0 \
|
||||
VLEIG $1, $5, t0 \
|
||||
VACCQ h0, t0, t1 \
|
||||
VAQ h0, t0, t0 \
|
||||
VONE t2 \
|
||||
VLEIG $1, $-4, t2 \
|
||||
VAQ t2, t1, t1 \
|
||||
VACCQ h1, t1, t1 \
|
||||
VONE t2 \
|
||||
VAQ t2, t1, t1 \
|
||||
VN h0, t1, t2 \
|
||||
VNC t0, t1, t1 \
|
||||
VO t1, t2, h0 \
|
||||
|
||||
// func poly1305vmsl(out *[16]byte, m *byte, mlen uint64, key *[32]key)
|
||||
TEXT ·poly1305vmsl(SB), $0-32
|
||||
// This code processes 6 + up to 4 blocks (32 bytes) per iteration
|
||||
// using the algorithm described in:
|
||||
// NEON crypto, Daniel J. Bernstein & Peter Schwabe
|
||||
// https://cryptojedi.org/papers/neoncrypto-20120320.pdf
|
||||
// And as moddified for VMSL as described in
|
||||
// Accelerating Poly1305 Cryptographic Message Authentication on the z14
|
||||
// O'Farrell et al, CASCON 2017, p48-55
|
||||
// https://ibm.ent.box.com/s/jf9gedj0e9d2vjctfyh186shaztavnht
|
||||
|
||||
LMG out+0(FP), R1, R4 // R1=out, R2=m, R3=mlen, R4=key
|
||||
VZERO V0 // c
|
||||
|
||||
// load EX0, EX1 and EX2
|
||||
MOVD $·constants<>(SB), R5
|
||||
VLM (R5), EX0, EX2 // c
|
||||
|
||||
// setup r
|
||||
VL (R4), T_0
|
||||
MOVD $·keyMask<>(SB), R6
|
||||
VL (R6), T_1
|
||||
VN T_0, T_1, T_0
|
||||
VZERO T_2 // limbs for r
|
||||
VZERO T_3
|
||||
VZERO T_4
|
||||
EXPACC2(T_0, T_2, T_3, T_4, T_1, T_5, T_7)
|
||||
|
||||
// T_2, T_3, T_4: [0, r]
|
||||
|
||||
// setup r*20
|
||||
VLEIG $0, $0, T_0
|
||||
VLEIG $1, $20, T_0 // T_0: [0, 20]
|
||||
VZERO T_5
|
||||
VZERO T_6
|
||||
VMSLG T_0, T_3, T_5, T_5
|
||||
VMSLG T_0, T_4, T_6, T_6
|
||||
|
||||
// store r for final block in GR
|
||||
VLGVG $1, T_2, RSAVE_0 // c
|
||||
VLGVG $1, T_3, RSAVE_1 // c
|
||||
VLGVG $1, T_4, RSAVE_2 // c
|
||||
VLGVG $1, T_5, R5SAVE_1 // c
|
||||
VLGVG $1, T_6, R5SAVE_2 // c
|
||||
|
||||
// initialize h
|
||||
VZERO H0_0
|
||||
VZERO H1_0
|
||||
VZERO H2_0
|
||||
VZERO H0_1
|
||||
VZERO H1_1
|
||||
VZERO H2_1
|
||||
|
||||
// initialize pointer for reduce constants
|
||||
MOVD $·reduce<>(SB), R12
|
||||
|
||||
// calculate r**2 and 20*(r**2)
|
||||
VZERO R_0
|
||||
VZERO R_1
|
||||
VZERO R_2
|
||||
SQUARE(T_2, T_3, T_4, T_6, R_0, R_1, R_2, T_1, T_5, T_7)
|
||||
REDUCE2(R_0, R_1, R_2, M0, M1, M2, M3, M4, R5_1, R5_2, M5, T_1)
|
||||
VZERO R5_1
|
||||
VZERO R5_2
|
||||
VMSLG T_0, R_1, R5_1, R5_1
|
||||
VMSLG T_0, R_2, R5_2, R5_2
|
||||
|
||||
// skip r**4 calculation if 3 blocks or less
|
||||
CMPBLE R3, $48, b4
|
||||
|
||||
// calculate r**4 and 20*(r**4)
|
||||
VZERO T_8
|
||||
VZERO T_9
|
||||
VZERO T_10
|
||||
SQUARE(R_0, R_1, R_2, R5_2, T_8, T_9, T_10, T_1, T_5, T_7)
|
||||
REDUCE2(T_8, T_9, T_10, M0, M1, M2, M3, M4, T_2, T_3, M5, T_1)
|
||||
VZERO T_2
|
||||
VZERO T_3
|
||||
VMSLG T_0, T_9, T_2, T_2
|
||||
VMSLG T_0, T_10, T_3, T_3
|
||||
|
||||
// put r**2 to the right and r**4 to the left of R_0, R_1, R_2
|
||||
VSLDB $8, T_8, T_8, T_8
|
||||
VSLDB $8, T_9, T_9, T_9
|
||||
VSLDB $8, T_10, T_10, T_10
|
||||
VSLDB $8, T_2, T_2, T_2
|
||||
VSLDB $8, T_3, T_3, T_3
|
||||
|
||||
VO T_8, R_0, R_0
|
||||
VO T_9, R_1, R_1
|
||||
VO T_10, R_2, R_2
|
||||
VO T_2, R5_1, R5_1
|
||||
VO T_3, R5_2, R5_2
|
||||
|
||||
CMPBLE R3, $80, load // less than or equal to 5 blocks in message
|
||||
|
||||
// 6(or 5+1) blocks
|
||||
SUB $81, R3
|
||||
VLM (R2), M0, M4
|
||||
VLL R3, 80(R2), M5
|
||||
ADD $1, R3
|
||||
MOVBZ $1, R0
|
||||
CMPBGE R3, $16, 2(PC)
|
||||
VLVGB R3, R0, M5
|
||||
MOVD $96(R2), R2
|
||||
EXPACC(M0, M1, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3)
|
||||
EXPACC(M2, M3, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3)
|
||||
VLEIB $2, $1, H2_0
|
||||
VLEIB $2, $1, H2_1
|
||||
VLEIB $10, $1, H2_0
|
||||
VLEIB $10, $1, H2_1
|
||||
|
||||
VZERO M0
|
||||
VZERO M1
|
||||
VZERO M2
|
||||
VZERO M3
|
||||
VZERO T_4
|
||||
VZERO T_10
|
||||
EXPACC(M4, M5, M0, M1, M2, M3, T_4, T_10, T_0, T_1, T_2, T_3)
|
||||
VLR T_4, M4
|
||||
VLEIB $10, $1, M2
|
||||
CMPBLT R3, $16, 2(PC)
|
||||
VLEIB $10, $1, T_10
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M2, M3, M4, T_4, T_5, T_2, T_7, T_8, T_9)
|
||||
VMRHG V0, H0_1, H0_0
|
||||
VMRHG V0, H1_1, H1_0
|
||||
VMRHG V0, H2_1, H2_0
|
||||
VMRLG V0, H0_1, H0_1
|
||||
VMRLG V0, H1_1, H1_1
|
||||
VMRLG V0, H2_1, H2_1
|
||||
|
||||
SUB $16, R3
|
||||
CMPBLE R3, $0, square
|
||||
|
||||
load:
|
||||
// load EX0, EX1 and EX2
|
||||
MOVD $·c<>(SB), R5
|
||||
VLM (R5), EX0, EX2
|
||||
|
||||
loop:
|
||||
CMPBLE R3, $64, add // b4 // last 4 or less blocks left
|
||||
|
||||
// next 4 full blocks
|
||||
VLM (R2), M2, M5
|
||||
SUB $64, R3
|
||||
MOVD $64(R2), R2
|
||||
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, T_0, T_1, T_3, T_4, T_5, T_2, T_7, T_8, T_9)
|
||||
|
||||
// expacc in-lined to create [m2, m3] limbs
|
||||
VGBM $0x3f3f, T_0 // 44 bit clear mask
|
||||
VGBM $0x1f1f, T_1 // 40 bit clear mask
|
||||
VPERM M2, M3, EX0, T_3
|
||||
VESRLG $4, T_0, T_0 // 44 bit clear mask ready
|
||||
VPERM M2, M3, EX1, T_4
|
||||
VPERM M2, M3, EX2, T_5
|
||||
VN T_0, T_3, T_3
|
||||
VESRLG $4, T_4, T_4
|
||||
VN T_1, T_5, T_5
|
||||
VN T_0, T_4, T_4
|
||||
VMRHG H0_1, T_3, H0_0
|
||||
VMRHG H1_1, T_4, H1_0
|
||||
VMRHG H2_1, T_5, H2_0
|
||||
VMRLG H0_1, T_3, H0_1
|
||||
VMRLG H1_1, T_4, H1_1
|
||||
VMRLG H2_1, T_5, H2_1
|
||||
VLEIB $10, $1, H2_0
|
||||
VLEIB $10, $1, H2_1
|
||||
VPERM M4, M5, EX0, T_3
|
||||
VPERM M4, M5, EX1, T_4
|
||||
VPERM M4, M5, EX2, T_5
|
||||
VN T_0, T_3, T_3
|
||||
VESRLG $4, T_4, T_4
|
||||
VN T_1, T_5, T_5
|
||||
VN T_0, T_4, T_4
|
||||
VMRHG V0, T_3, M0
|
||||
VMRHG V0, T_4, M1
|
||||
VMRHG V0, T_5, M2
|
||||
VMRLG V0, T_3, M3
|
||||
VMRLG V0, T_4, M4
|
||||
VMRLG V0, T_5, M5
|
||||
VLEIB $10, $1, M2
|
||||
VLEIB $10, $1, M5
|
||||
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
CMPBNE R3, $0, loop
|
||||
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9)
|
||||
VMRHG V0, H0_1, H0_0
|
||||
VMRHG V0, H1_1, H1_0
|
||||
VMRHG V0, H2_1, H2_0
|
||||
VMRLG V0, H0_1, H0_1
|
||||
VMRLG V0, H1_1, H1_1
|
||||
VMRLG V0, H2_1, H2_1
|
||||
|
||||
// load EX0, EX1, EX2
|
||||
MOVD $·constants<>(SB), R5
|
||||
VLM (R5), EX0, EX2
|
||||
|
||||
// sum vectors
|
||||
VAQ H0_0, H0_1, H0_0
|
||||
VAQ H1_0, H1_1, H1_0
|
||||
VAQ H2_0, H2_1, H2_0
|
||||
|
||||
// h may be >= 2*(2**130-5) so we need to reduce it again
|
||||
// M0...M4 are used as temps here
|
||||
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5)
|
||||
|
||||
next: // carry h1->h2
|
||||
VLEIB $7, $0x28, T_1
|
||||
VREPIB $4, T_2
|
||||
VGBM $0x003F, T_3
|
||||
VESRLG $4, T_3
|
||||
|
||||
// byte shift
|
||||
VSRLB T_1, H1_0, T_4
|
||||
|
||||
// bit shift
|
||||
VSRL T_2, T_4, T_4
|
||||
|
||||
// clear h1 carry bits
|
||||
VN T_3, H1_0, H1_0
|
||||
|
||||
// add carry
|
||||
VAQ T_4, H2_0, H2_0
|
||||
|
||||
// h is now < 2*(2**130-5)
|
||||
// pack h into h1 (hi) and h0 (lo)
|
||||
PACK(H0_0, H1_0, H2_0)
|
||||
|
||||
// if h > 2**130-5 then h -= 2**130-5
|
||||
MOD(H0_0, H1_0, T_0, T_1, T_2)
|
||||
|
||||
// h += s
|
||||
MOVD $·bswapMask<>(SB), R5
|
||||
VL (R5), T_1
|
||||
VL 16(R4), T_0
|
||||
VPERM T_0, T_0, T_1, T_0 // reverse bytes (to big)
|
||||
VAQ T_0, H0_0, H0_0
|
||||
VPERM H0_0, H0_0, T_1, H0_0 // reverse bytes (to little)
|
||||
VST H0_0, (R1)
|
||||
RET
|
||||
|
||||
add:
|
||||
// load EX0, EX1, EX2
|
||||
MOVD $·constants<>(SB), R5
|
||||
VLM (R5), EX0, EX2
|
||||
|
||||
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9)
|
||||
VMRHG V0, H0_1, H0_0
|
||||
VMRHG V0, H1_1, H1_0
|
||||
VMRHG V0, H2_1, H2_0
|
||||
VMRLG V0, H0_1, H0_1
|
||||
VMRLG V0, H1_1, H1_1
|
||||
VMRLG V0, H2_1, H2_1
|
||||
CMPBLE R3, $64, b4
|
||||
|
||||
b4:
|
||||
CMPBLE R3, $48, b3 // 3 blocks or less
|
||||
|
||||
// 4(3+1) blocks remaining
|
||||
SUB $49, R3
|
||||
VLM (R2), M0, M2
|
||||
VLL R3, 48(R2), M3
|
||||
ADD $1, R3
|
||||
MOVBZ $1, R0
|
||||
CMPBEQ R3, $16, 2(PC)
|
||||
VLVGB R3, R0, M3
|
||||
MOVD $64(R2), R2
|
||||
EXPACC(M0, M1, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3)
|
||||
VLEIB $10, $1, H2_0
|
||||
VLEIB $10, $1, H2_1
|
||||
VZERO M0
|
||||
VZERO M1
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
VZERO T_4
|
||||
VZERO T_10
|
||||
EXPACC(M2, M3, M0, M1, M4, M5, T_4, T_10, T_0, T_1, T_2, T_3)
|
||||
VLR T_4, M2
|
||||
VLEIB $10, $1, M4
|
||||
CMPBNE R3, $16, 2(PC)
|
||||
VLEIB $10, $1, T_10
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M4, M5, M2, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9)
|
||||
VMRHG V0, H0_1, H0_0
|
||||
VMRHG V0, H1_1, H1_0
|
||||
VMRHG V0, H2_1, H2_0
|
||||
VMRLG V0, H0_1, H0_1
|
||||
VMRLG V0, H1_1, H1_1
|
||||
VMRLG V0, H2_1, H2_1
|
||||
SUB $16, R3
|
||||
CMPBLE R3, $0, square // this condition must always hold true!
|
||||
|
||||
b3:
|
||||
CMPBLE R3, $32, b2
|
||||
|
||||
// 3 blocks remaining
|
||||
|
||||
// setup [r²,r]
|
||||
VSLDB $8, R_0, R_0, R_0
|
||||
VSLDB $8, R_1, R_1, R_1
|
||||
VSLDB $8, R_2, R_2, R_2
|
||||
VSLDB $8, R5_1, R5_1, R5_1
|
||||
VSLDB $8, R5_2, R5_2, R5_2
|
||||
|
||||
VLVGG $1, RSAVE_0, R_0
|
||||
VLVGG $1, RSAVE_1, R_1
|
||||
VLVGG $1, RSAVE_2, R_2
|
||||
VLVGG $1, R5SAVE_1, R5_1
|
||||
VLVGG $1, R5SAVE_2, R5_2
|
||||
|
||||
// setup [h0, h1]
|
||||
VSLDB $8, H0_0, H0_0, H0_0
|
||||
VSLDB $8, H1_0, H1_0, H1_0
|
||||
VSLDB $8, H2_0, H2_0, H2_0
|
||||
VO H0_1, H0_0, H0_0
|
||||
VO H1_1, H1_0, H1_0
|
||||
VO H2_1, H2_0, H2_0
|
||||
VZERO H0_1
|
||||
VZERO H1_1
|
||||
VZERO H2_1
|
||||
|
||||
VZERO M0
|
||||
VZERO M1
|
||||
VZERO M2
|
||||
VZERO M3
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
|
||||
// H*[r**2, r]
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, H0_1, H1_1, T_10, M5)
|
||||
|
||||
SUB $33, R3
|
||||
VLM (R2), M0, M1
|
||||
VLL R3, 32(R2), M2
|
||||
ADD $1, R3
|
||||
MOVBZ $1, R0
|
||||
CMPBEQ R3, $16, 2(PC)
|
||||
VLVGB R3, R0, M2
|
||||
|
||||
// H += m0
|
||||
VZERO T_1
|
||||
VZERO T_2
|
||||
VZERO T_3
|
||||
EXPACC2(M0, T_1, T_2, T_3, T_4, T_5, T_6)
|
||||
VLEIB $10, $1, T_3
|
||||
VAG H0_0, T_1, H0_0
|
||||
VAG H1_0, T_2, H1_0
|
||||
VAG H2_0, T_3, H2_0
|
||||
|
||||
VZERO M0
|
||||
VZERO M3
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
VZERO T_10
|
||||
|
||||
// (H+m0)*r
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M3, M4, M5, V0, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE2(H0_0, H1_0, H2_0, M0, M3, M4, M5, T_10, H0_1, H1_1, H2_1, T_9)
|
||||
|
||||
// H += m1
|
||||
VZERO V0
|
||||
VZERO T_1
|
||||
VZERO T_2
|
||||
VZERO T_3
|
||||
EXPACC2(M1, T_1, T_2, T_3, T_4, T_5, T_6)
|
||||
VLEIB $10, $1, T_3
|
||||
VAQ H0_0, T_1, H0_0
|
||||
VAQ H1_0, T_2, H1_0
|
||||
VAQ H2_0, T_3, H2_0
|
||||
REDUCE2(H0_0, H1_0, H2_0, M0, M3, M4, M5, T_9, H0_1, H1_1, H2_1, T_10)
|
||||
|
||||
// [H, m2] * [r**2, r]
|
||||
EXPACC2(M2, H0_0, H1_0, H2_0, T_1, T_2, T_3)
|
||||
CMPBNE R3, $16, 2(PC)
|
||||
VLEIB $10, $1, H2_0
|
||||
VZERO M0
|
||||
VZERO M1
|
||||
VZERO M2
|
||||
VZERO M3
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, H0_1, H1_1, M5, T_10)
|
||||
SUB $16, R3
|
||||
CMPBLE R3, $0, next // this condition must always hold true!
|
||||
|
||||
b2:
|
||||
CMPBLE R3, $16, b1
|
||||
|
||||
// 2 blocks remaining
|
||||
|
||||
// setup [r²,r]
|
||||
VSLDB $8, R_0, R_0, R_0
|
||||
VSLDB $8, R_1, R_1, R_1
|
||||
VSLDB $8, R_2, R_2, R_2
|
||||
VSLDB $8, R5_1, R5_1, R5_1
|
||||
VSLDB $8, R5_2, R5_2, R5_2
|
||||
|
||||
VLVGG $1, RSAVE_0, R_0
|
||||
VLVGG $1, RSAVE_1, R_1
|
||||
VLVGG $1, RSAVE_2, R_2
|
||||
VLVGG $1, R5SAVE_1, R5_1
|
||||
VLVGG $1, R5SAVE_2, R5_2
|
||||
|
||||
// setup [h0, h1]
|
||||
VSLDB $8, H0_0, H0_0, H0_0
|
||||
VSLDB $8, H1_0, H1_0, H1_0
|
||||
VSLDB $8, H2_0, H2_0, H2_0
|
||||
VO H0_1, H0_0, H0_0
|
||||
VO H1_1, H1_0, H1_0
|
||||
VO H2_1, H2_0, H2_0
|
||||
VZERO H0_1
|
||||
VZERO H1_1
|
||||
VZERO H2_1
|
||||
|
||||
VZERO M0
|
||||
VZERO M1
|
||||
VZERO M2
|
||||
VZERO M3
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
|
||||
// H*[r**2, r]
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M2, M3, M4, T_4, T_5, T_2, T_7, T_8, T_9)
|
||||
VMRHG V0, H0_1, H0_0
|
||||
VMRHG V0, H1_1, H1_0
|
||||
VMRHG V0, H2_1, H2_0
|
||||
VMRLG V0, H0_1, H0_1
|
||||
VMRLG V0, H1_1, H1_1
|
||||
VMRLG V0, H2_1, H2_1
|
||||
|
||||
// move h to the left and 0s at the right
|
||||
VSLDB $8, H0_0, H0_0, H0_0
|
||||
VSLDB $8, H1_0, H1_0, H1_0
|
||||
VSLDB $8, H2_0, H2_0, H2_0
|
||||
|
||||
// get message blocks and append 1 to start
|
||||
SUB $17, R3
|
||||
VL (R2), M0
|
||||
VLL R3, 16(R2), M1
|
||||
ADD $1, R3
|
||||
MOVBZ $1, R0
|
||||
CMPBEQ R3, $16, 2(PC)
|
||||
VLVGB R3, R0, M1
|
||||
VZERO T_6
|
||||
VZERO T_7
|
||||
VZERO T_8
|
||||
EXPACC2(M0, T_6, T_7, T_8, T_1, T_2, T_3)
|
||||
EXPACC2(M1, T_6, T_7, T_8, T_1, T_2, T_3)
|
||||
VLEIB $2, $1, T_8
|
||||
CMPBNE R3, $16, 2(PC)
|
||||
VLEIB $10, $1, T_8
|
||||
|
||||
// add [m0, m1] to h
|
||||
VAG H0_0, T_6, H0_0
|
||||
VAG H1_0, T_7, H1_0
|
||||
VAG H2_0, T_8, H2_0
|
||||
|
||||
VZERO M2
|
||||
VZERO M3
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
VZERO T_10
|
||||
VZERO M0
|
||||
|
||||
// at this point R_0 .. R5_2 look like [r**2, r]
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M2, M3, M4, M5, T_10, M0, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE2(H0_0, H1_0, H2_0, M2, M3, M4, M5, T_9, H0_1, H1_1, H2_1, T_10)
|
||||
SUB $16, R3, R3
|
||||
CMPBLE R3, $0, next
|
||||
|
||||
b1:
|
||||
CMPBLE R3, $0, next
|
||||
|
||||
// 1 block remaining
|
||||
|
||||
// setup [r²,r]
|
||||
VSLDB $8, R_0, R_0, R_0
|
||||
VSLDB $8, R_1, R_1, R_1
|
||||
VSLDB $8, R_2, R_2, R_2
|
||||
VSLDB $8, R5_1, R5_1, R5_1
|
||||
VSLDB $8, R5_2, R5_2, R5_2
|
||||
|
||||
VLVGG $1, RSAVE_0, R_0
|
||||
VLVGG $1, RSAVE_1, R_1
|
||||
VLVGG $1, RSAVE_2, R_2
|
||||
VLVGG $1, R5SAVE_1, R5_1
|
||||
VLVGG $1, R5SAVE_2, R5_2
|
||||
|
||||
// setup [h0, h1]
|
||||
VSLDB $8, H0_0, H0_0, H0_0
|
||||
VSLDB $8, H1_0, H1_0, H1_0
|
||||
VSLDB $8, H2_0, H2_0, H2_0
|
||||
VO H0_1, H0_0, H0_0
|
||||
VO H1_1, H1_0, H1_0
|
||||
VO H2_1, H2_0, H2_0
|
||||
VZERO H0_1
|
||||
VZERO H1_1
|
||||
VZERO H2_1
|
||||
|
||||
VZERO M0
|
||||
VZERO M1
|
||||
VZERO M2
|
||||
VZERO M3
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
|
||||
// H*[r**2, r]
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5)
|
||||
|
||||
// set up [0, m0] limbs
|
||||
SUB $1, R3
|
||||
VLL R3, (R2), M0
|
||||
ADD $1, R3
|
||||
MOVBZ $1, R0
|
||||
CMPBEQ R3, $16, 2(PC)
|
||||
VLVGB R3, R0, M0
|
||||
VZERO T_1
|
||||
VZERO T_2
|
||||
VZERO T_3
|
||||
EXPACC2(M0, T_1, T_2, T_3, T_4, T_5, T_6)// limbs: [0, m]
|
||||
CMPBNE R3, $16, 2(PC)
|
||||
VLEIB $10, $1, T_3
|
||||
|
||||
// h+m0
|
||||
VAQ H0_0, T_1, H0_0
|
||||
VAQ H1_0, T_2, H1_0
|
||||
VAQ H2_0, T_3, H2_0
|
||||
|
||||
VZERO M0
|
||||
VZERO M1
|
||||
VZERO M2
|
||||
VZERO M3
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5)
|
||||
|
||||
BR next
|
||||
|
||||
square:
|
||||
// setup [r²,r]
|
||||
VSLDB $8, R_0, R_0, R_0
|
||||
VSLDB $8, R_1, R_1, R_1
|
||||
VSLDB $8, R_2, R_2, R_2
|
||||
VSLDB $8, R5_1, R5_1, R5_1
|
||||
VSLDB $8, R5_2, R5_2, R5_2
|
||||
|
||||
VLVGG $1, RSAVE_0, R_0
|
||||
VLVGG $1, RSAVE_1, R_1
|
||||
VLVGG $1, RSAVE_2, R_2
|
||||
VLVGG $1, R5SAVE_1, R5_1
|
||||
VLVGG $1, R5SAVE_2, R5_2
|
||||
|
||||
// setup [h0, h1]
|
||||
VSLDB $8, H0_0, H0_0, H0_0
|
||||
VSLDB $8, H1_0, H1_0, H1_0
|
||||
VSLDB $8, H2_0, H2_0, H2_0
|
||||
VO H0_1, H0_0, H0_0
|
||||
VO H1_1, H1_0, H1_0
|
||||
VO H2_1, H2_0, H2_0
|
||||
VZERO H0_1
|
||||
VZERO H1_1
|
||||
VZERO H2_1
|
||||
|
||||
VZERO M0
|
||||
VZERO M1
|
||||
VZERO M2
|
||||
VZERO M3
|
||||
VZERO M4
|
||||
VZERO M5
|
||||
|
||||
// (h0*r**2) + (h1*r)
|
||||
MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9)
|
||||
REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5)
|
||||
BR next
|
||||
|
||||
TEXT ·hasVMSLFacility(SB), NOSPLIT, $24-1
|
||||
MOVD $x-24(SP), R1
|
||||
XC $24, 0(R1), 0(R1) // clear the storage
|
||||
MOVD $2, R0 // R0 is the number of double words stored -1
|
||||
WORD $0xB2B01000 // STFLE 0(R1)
|
||||
XOR R0, R0 // reset the value of R0
|
||||
MOVBZ z-8(SP), R1
|
||||
AND $0x01, R1
|
||||
BEQ novmsl
|
||||
|
||||
vectorinstalled:
|
||||
// check if the vector instruction has been enabled
|
||||
VLEIB $0, $0xF, V16
|
||||
VLGVB $0, V16, R1
|
||||
CMPBNE R1, $0xF, novmsl
|
||||
MOVB $1, ret+0(FP) // have vx
|
||||
RET
|
||||
|
||||
novmsl:
|
||||
MOVB $0, ret+0(FP) // no vx
|
||||
RET
|
||||
+144
@@ -0,0 +1,144 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// Package salsa provides low-level access to functions in the Salsa family.
|
||||
package salsa // import "golang.org/x/crypto/salsa20/salsa"
|
||||
|
||||
// Sigma is the Salsa20 constant for 256-bit keys.
|
||||
var Sigma = [16]byte{'e', 'x', 'p', 'a', 'n', 'd', ' ', '3', '2', '-', 'b', 'y', 't', 'e', ' ', 'k'}
|
||||
|
||||
// HSalsa20 applies the HSalsa20 core function to a 16-byte input in, 32-byte
|
||||
// key k, and 16-byte constant c, and puts the result into the 32-byte array
|
||||
// out.
|
||||
func HSalsa20(out *[32]byte, in *[16]byte, k *[32]byte, c *[16]byte) {
|
||||
x0 := uint32(c[0]) | uint32(c[1])<<8 | uint32(c[2])<<16 | uint32(c[3])<<24
|
||||
x1 := uint32(k[0]) | uint32(k[1])<<8 | uint32(k[2])<<16 | uint32(k[3])<<24
|
||||
x2 := uint32(k[4]) | uint32(k[5])<<8 | uint32(k[6])<<16 | uint32(k[7])<<24
|
||||
x3 := uint32(k[8]) | uint32(k[9])<<8 | uint32(k[10])<<16 | uint32(k[11])<<24
|
||||
x4 := uint32(k[12]) | uint32(k[13])<<8 | uint32(k[14])<<16 | uint32(k[15])<<24
|
||||
x5 := uint32(c[4]) | uint32(c[5])<<8 | uint32(c[6])<<16 | uint32(c[7])<<24
|
||||
x6 := uint32(in[0]) | uint32(in[1])<<8 | uint32(in[2])<<16 | uint32(in[3])<<24
|
||||
x7 := uint32(in[4]) | uint32(in[5])<<8 | uint32(in[6])<<16 | uint32(in[7])<<24
|
||||
x8 := uint32(in[8]) | uint32(in[9])<<8 | uint32(in[10])<<16 | uint32(in[11])<<24
|
||||
x9 := uint32(in[12]) | uint32(in[13])<<8 | uint32(in[14])<<16 | uint32(in[15])<<24
|
||||
x10 := uint32(c[8]) | uint32(c[9])<<8 | uint32(c[10])<<16 | uint32(c[11])<<24
|
||||
x11 := uint32(k[16]) | uint32(k[17])<<8 | uint32(k[18])<<16 | uint32(k[19])<<24
|
||||
x12 := uint32(k[20]) | uint32(k[21])<<8 | uint32(k[22])<<16 | uint32(k[23])<<24
|
||||
x13 := uint32(k[24]) | uint32(k[25])<<8 | uint32(k[26])<<16 | uint32(k[27])<<24
|
||||
x14 := uint32(k[28]) | uint32(k[29])<<8 | uint32(k[30])<<16 | uint32(k[31])<<24
|
||||
x15 := uint32(c[12]) | uint32(c[13])<<8 | uint32(c[14])<<16 | uint32(c[15])<<24
|
||||
|
||||
for i := 0; i < 20; i += 2 {
|
||||
u := x0 + x12
|
||||
x4 ^= u<<7 | u>>(32-7)
|
||||
u = x4 + x0
|
||||
x8 ^= u<<9 | u>>(32-9)
|
||||
u = x8 + x4
|
||||
x12 ^= u<<13 | u>>(32-13)
|
||||
u = x12 + x8
|
||||
x0 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x5 + x1
|
||||
x9 ^= u<<7 | u>>(32-7)
|
||||
u = x9 + x5
|
||||
x13 ^= u<<9 | u>>(32-9)
|
||||
u = x13 + x9
|
||||
x1 ^= u<<13 | u>>(32-13)
|
||||
u = x1 + x13
|
||||
x5 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x10 + x6
|
||||
x14 ^= u<<7 | u>>(32-7)
|
||||
u = x14 + x10
|
||||
x2 ^= u<<9 | u>>(32-9)
|
||||
u = x2 + x14
|
||||
x6 ^= u<<13 | u>>(32-13)
|
||||
u = x6 + x2
|
||||
x10 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x15 + x11
|
||||
x3 ^= u<<7 | u>>(32-7)
|
||||
u = x3 + x15
|
||||
x7 ^= u<<9 | u>>(32-9)
|
||||
u = x7 + x3
|
||||
x11 ^= u<<13 | u>>(32-13)
|
||||
u = x11 + x7
|
||||
x15 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x0 + x3
|
||||
x1 ^= u<<7 | u>>(32-7)
|
||||
u = x1 + x0
|
||||
x2 ^= u<<9 | u>>(32-9)
|
||||
u = x2 + x1
|
||||
x3 ^= u<<13 | u>>(32-13)
|
||||
u = x3 + x2
|
||||
x0 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x5 + x4
|
||||
x6 ^= u<<7 | u>>(32-7)
|
||||
u = x6 + x5
|
||||
x7 ^= u<<9 | u>>(32-9)
|
||||
u = x7 + x6
|
||||
x4 ^= u<<13 | u>>(32-13)
|
||||
u = x4 + x7
|
||||
x5 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x10 + x9
|
||||
x11 ^= u<<7 | u>>(32-7)
|
||||
u = x11 + x10
|
||||
x8 ^= u<<9 | u>>(32-9)
|
||||
u = x8 + x11
|
||||
x9 ^= u<<13 | u>>(32-13)
|
||||
u = x9 + x8
|
||||
x10 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x15 + x14
|
||||
x12 ^= u<<7 | u>>(32-7)
|
||||
u = x12 + x15
|
||||
x13 ^= u<<9 | u>>(32-9)
|
||||
u = x13 + x12
|
||||
x14 ^= u<<13 | u>>(32-13)
|
||||
u = x14 + x13
|
||||
x15 ^= u<<18 | u>>(32-18)
|
||||
}
|
||||
out[0] = byte(x0)
|
||||
out[1] = byte(x0 >> 8)
|
||||
out[2] = byte(x0 >> 16)
|
||||
out[3] = byte(x0 >> 24)
|
||||
|
||||
out[4] = byte(x5)
|
||||
out[5] = byte(x5 >> 8)
|
||||
out[6] = byte(x5 >> 16)
|
||||
out[7] = byte(x5 >> 24)
|
||||
|
||||
out[8] = byte(x10)
|
||||
out[9] = byte(x10 >> 8)
|
||||
out[10] = byte(x10 >> 16)
|
||||
out[11] = byte(x10 >> 24)
|
||||
|
||||
out[12] = byte(x15)
|
||||
out[13] = byte(x15 >> 8)
|
||||
out[14] = byte(x15 >> 16)
|
||||
out[15] = byte(x15 >> 24)
|
||||
|
||||
out[16] = byte(x6)
|
||||
out[17] = byte(x6 >> 8)
|
||||
out[18] = byte(x6 >> 16)
|
||||
out[19] = byte(x6 >> 24)
|
||||
|
||||
out[20] = byte(x7)
|
||||
out[21] = byte(x7 >> 8)
|
||||
out[22] = byte(x7 >> 16)
|
||||
out[23] = byte(x7 >> 24)
|
||||
|
||||
out[24] = byte(x8)
|
||||
out[25] = byte(x8 >> 8)
|
||||
out[26] = byte(x8 >> 16)
|
||||
out[27] = byte(x8 >> 24)
|
||||
|
||||
out[28] = byte(x9)
|
||||
out[29] = byte(x9 >> 8)
|
||||
out[30] = byte(x9 >> 16)
|
||||
out[31] = byte(x9 >> 24)
|
||||
}
|
||||
+889
@@ -0,0 +1,889 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build amd64,!appengine,!gccgo
|
||||
|
||||
// This code was translated into a form compatible with 6a from the public
|
||||
// domain sources in SUPERCOP: https://bench.cr.yp.to/supercop.html
|
||||
|
||||
// func salsa2020XORKeyStream(out, in *byte, n uint64, nonce, key *byte)
|
||||
// This needs up to 64 bytes at 360(SP); hence the non-obvious frame size.
|
||||
TEXT ·salsa2020XORKeyStream(SB),0,$456-40 // frame = 424 + 32 byte alignment
|
||||
MOVQ out+0(FP),DI
|
||||
MOVQ in+8(FP),SI
|
||||
MOVQ n+16(FP),DX
|
||||
MOVQ nonce+24(FP),CX
|
||||
MOVQ key+32(FP),R8
|
||||
|
||||
MOVQ SP,R12
|
||||
MOVQ SP,R9
|
||||
ADDQ $31, R9
|
||||
ANDQ $~31, R9
|
||||
MOVQ R9, SP
|
||||
|
||||
MOVQ DX,R9
|
||||
MOVQ CX,DX
|
||||
MOVQ R8,R10
|
||||
CMPQ R9,$0
|
||||
JBE DONE
|
||||
START:
|
||||
MOVL 20(R10),CX
|
||||
MOVL 0(R10),R8
|
||||
MOVL 0(DX),AX
|
||||
MOVL 16(R10),R11
|
||||
MOVL CX,0(SP)
|
||||
MOVL R8, 4 (SP)
|
||||
MOVL AX, 8 (SP)
|
||||
MOVL R11, 12 (SP)
|
||||
MOVL 8(DX),CX
|
||||
MOVL 24(R10),R8
|
||||
MOVL 4(R10),AX
|
||||
MOVL 4(DX),R11
|
||||
MOVL CX,16(SP)
|
||||
MOVL R8, 20 (SP)
|
||||
MOVL AX, 24 (SP)
|
||||
MOVL R11, 28 (SP)
|
||||
MOVL 12(DX),CX
|
||||
MOVL 12(R10),DX
|
||||
MOVL 28(R10),R8
|
||||
MOVL 8(R10),AX
|
||||
MOVL DX,32(SP)
|
||||
MOVL CX, 36 (SP)
|
||||
MOVL R8, 40 (SP)
|
||||
MOVL AX, 44 (SP)
|
||||
MOVQ $1634760805,DX
|
||||
MOVQ $857760878,CX
|
||||
MOVQ $2036477234,R8
|
||||
MOVQ $1797285236,AX
|
||||
MOVL DX,48(SP)
|
||||
MOVL CX, 52 (SP)
|
||||
MOVL R8, 56 (SP)
|
||||
MOVL AX, 60 (SP)
|
||||
CMPQ R9,$256
|
||||
JB BYTESBETWEEN1AND255
|
||||
MOVOA 48(SP),X0
|
||||
PSHUFL $0X55,X0,X1
|
||||
PSHUFL $0XAA,X0,X2
|
||||
PSHUFL $0XFF,X0,X3
|
||||
PSHUFL $0X00,X0,X0
|
||||
MOVOA X1,64(SP)
|
||||
MOVOA X2,80(SP)
|
||||
MOVOA X3,96(SP)
|
||||
MOVOA X0,112(SP)
|
||||
MOVOA 0(SP),X0
|
||||
PSHUFL $0XAA,X0,X1
|
||||
PSHUFL $0XFF,X0,X2
|
||||
PSHUFL $0X00,X0,X3
|
||||
PSHUFL $0X55,X0,X0
|
||||
MOVOA X1,128(SP)
|
||||
MOVOA X2,144(SP)
|
||||
MOVOA X3,160(SP)
|
||||
MOVOA X0,176(SP)
|
||||
MOVOA 16(SP),X0
|
||||
PSHUFL $0XFF,X0,X1
|
||||
PSHUFL $0X55,X0,X2
|
||||
PSHUFL $0XAA,X0,X0
|
||||
MOVOA X1,192(SP)
|
||||
MOVOA X2,208(SP)
|
||||
MOVOA X0,224(SP)
|
||||
MOVOA 32(SP),X0
|
||||
PSHUFL $0X00,X0,X1
|
||||
PSHUFL $0XAA,X0,X2
|
||||
PSHUFL $0XFF,X0,X0
|
||||
MOVOA X1,240(SP)
|
||||
MOVOA X2,256(SP)
|
||||
MOVOA X0,272(SP)
|
||||
BYTESATLEAST256:
|
||||
MOVL 16(SP),DX
|
||||
MOVL 36 (SP),CX
|
||||
MOVL DX,288(SP)
|
||||
MOVL CX,304(SP)
|
||||
ADDQ $1,DX
|
||||
SHLQ $32,CX
|
||||
ADDQ CX,DX
|
||||
MOVQ DX,CX
|
||||
SHRQ $32,CX
|
||||
MOVL DX, 292 (SP)
|
||||
MOVL CX, 308 (SP)
|
||||
ADDQ $1,DX
|
||||
SHLQ $32,CX
|
||||
ADDQ CX,DX
|
||||
MOVQ DX,CX
|
||||
SHRQ $32,CX
|
||||
MOVL DX, 296 (SP)
|
||||
MOVL CX, 312 (SP)
|
||||
ADDQ $1,DX
|
||||
SHLQ $32,CX
|
||||
ADDQ CX,DX
|
||||
MOVQ DX,CX
|
||||
SHRQ $32,CX
|
||||
MOVL DX, 300 (SP)
|
||||
MOVL CX, 316 (SP)
|
||||
ADDQ $1,DX
|
||||
SHLQ $32,CX
|
||||
ADDQ CX,DX
|
||||
MOVQ DX,CX
|
||||
SHRQ $32,CX
|
||||
MOVL DX,16(SP)
|
||||
MOVL CX, 36 (SP)
|
||||
MOVQ R9,352(SP)
|
||||
MOVQ $20,DX
|
||||
MOVOA 64(SP),X0
|
||||
MOVOA 80(SP),X1
|
||||
MOVOA 96(SP),X2
|
||||
MOVOA 256(SP),X3
|
||||
MOVOA 272(SP),X4
|
||||
MOVOA 128(SP),X5
|
||||
MOVOA 144(SP),X6
|
||||
MOVOA 176(SP),X7
|
||||
MOVOA 192(SP),X8
|
||||
MOVOA 208(SP),X9
|
||||
MOVOA 224(SP),X10
|
||||
MOVOA 304(SP),X11
|
||||
MOVOA 112(SP),X12
|
||||
MOVOA 160(SP),X13
|
||||
MOVOA 240(SP),X14
|
||||
MOVOA 288(SP),X15
|
||||
MAINLOOP1:
|
||||
MOVOA X1,320(SP)
|
||||
MOVOA X2,336(SP)
|
||||
MOVOA X13,X1
|
||||
PADDL X12,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $7,X1
|
||||
PXOR X1,X14
|
||||
PSRLL $25,X2
|
||||
PXOR X2,X14
|
||||
MOVOA X7,X1
|
||||
PADDL X0,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $7,X1
|
||||
PXOR X1,X11
|
||||
PSRLL $25,X2
|
||||
PXOR X2,X11
|
||||
MOVOA X12,X1
|
||||
PADDL X14,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $9,X1
|
||||
PXOR X1,X15
|
||||
PSRLL $23,X2
|
||||
PXOR X2,X15
|
||||
MOVOA X0,X1
|
||||
PADDL X11,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $9,X1
|
||||
PXOR X1,X9
|
||||
PSRLL $23,X2
|
||||
PXOR X2,X9
|
||||
MOVOA X14,X1
|
||||
PADDL X15,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $13,X1
|
||||
PXOR X1,X13
|
||||
PSRLL $19,X2
|
||||
PXOR X2,X13
|
||||
MOVOA X11,X1
|
||||
PADDL X9,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $13,X1
|
||||
PXOR X1,X7
|
||||
PSRLL $19,X2
|
||||
PXOR X2,X7
|
||||
MOVOA X15,X1
|
||||
PADDL X13,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $18,X1
|
||||
PXOR X1,X12
|
||||
PSRLL $14,X2
|
||||
PXOR X2,X12
|
||||
MOVOA 320(SP),X1
|
||||
MOVOA X12,320(SP)
|
||||
MOVOA X9,X2
|
||||
PADDL X7,X2
|
||||
MOVOA X2,X12
|
||||
PSLLL $18,X2
|
||||
PXOR X2,X0
|
||||
PSRLL $14,X12
|
||||
PXOR X12,X0
|
||||
MOVOA X5,X2
|
||||
PADDL X1,X2
|
||||
MOVOA X2,X12
|
||||
PSLLL $7,X2
|
||||
PXOR X2,X3
|
||||
PSRLL $25,X12
|
||||
PXOR X12,X3
|
||||
MOVOA 336(SP),X2
|
||||
MOVOA X0,336(SP)
|
||||
MOVOA X6,X0
|
||||
PADDL X2,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $7,X0
|
||||
PXOR X0,X4
|
||||
PSRLL $25,X12
|
||||
PXOR X12,X4
|
||||
MOVOA X1,X0
|
||||
PADDL X3,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $9,X0
|
||||
PXOR X0,X10
|
||||
PSRLL $23,X12
|
||||
PXOR X12,X10
|
||||
MOVOA X2,X0
|
||||
PADDL X4,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $9,X0
|
||||
PXOR X0,X8
|
||||
PSRLL $23,X12
|
||||
PXOR X12,X8
|
||||
MOVOA X3,X0
|
||||
PADDL X10,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $13,X0
|
||||
PXOR X0,X5
|
||||
PSRLL $19,X12
|
||||
PXOR X12,X5
|
||||
MOVOA X4,X0
|
||||
PADDL X8,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $13,X0
|
||||
PXOR X0,X6
|
||||
PSRLL $19,X12
|
||||
PXOR X12,X6
|
||||
MOVOA X10,X0
|
||||
PADDL X5,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $18,X0
|
||||
PXOR X0,X1
|
||||
PSRLL $14,X12
|
||||
PXOR X12,X1
|
||||
MOVOA 320(SP),X0
|
||||
MOVOA X1,320(SP)
|
||||
MOVOA X4,X1
|
||||
PADDL X0,X1
|
||||
MOVOA X1,X12
|
||||
PSLLL $7,X1
|
||||
PXOR X1,X7
|
||||
PSRLL $25,X12
|
||||
PXOR X12,X7
|
||||
MOVOA X8,X1
|
||||
PADDL X6,X1
|
||||
MOVOA X1,X12
|
||||
PSLLL $18,X1
|
||||
PXOR X1,X2
|
||||
PSRLL $14,X12
|
||||
PXOR X12,X2
|
||||
MOVOA 336(SP),X12
|
||||
MOVOA X2,336(SP)
|
||||
MOVOA X14,X1
|
||||
PADDL X12,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $7,X1
|
||||
PXOR X1,X5
|
||||
PSRLL $25,X2
|
||||
PXOR X2,X5
|
||||
MOVOA X0,X1
|
||||
PADDL X7,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $9,X1
|
||||
PXOR X1,X10
|
||||
PSRLL $23,X2
|
||||
PXOR X2,X10
|
||||
MOVOA X12,X1
|
||||
PADDL X5,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $9,X1
|
||||
PXOR X1,X8
|
||||
PSRLL $23,X2
|
||||
PXOR X2,X8
|
||||
MOVOA X7,X1
|
||||
PADDL X10,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $13,X1
|
||||
PXOR X1,X4
|
||||
PSRLL $19,X2
|
||||
PXOR X2,X4
|
||||
MOVOA X5,X1
|
||||
PADDL X8,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $13,X1
|
||||
PXOR X1,X14
|
||||
PSRLL $19,X2
|
||||
PXOR X2,X14
|
||||
MOVOA X10,X1
|
||||
PADDL X4,X1
|
||||
MOVOA X1,X2
|
||||
PSLLL $18,X1
|
||||
PXOR X1,X0
|
||||
PSRLL $14,X2
|
||||
PXOR X2,X0
|
||||
MOVOA 320(SP),X1
|
||||
MOVOA X0,320(SP)
|
||||
MOVOA X8,X0
|
||||
PADDL X14,X0
|
||||
MOVOA X0,X2
|
||||
PSLLL $18,X0
|
||||
PXOR X0,X12
|
||||
PSRLL $14,X2
|
||||
PXOR X2,X12
|
||||
MOVOA X11,X0
|
||||
PADDL X1,X0
|
||||
MOVOA X0,X2
|
||||
PSLLL $7,X0
|
||||
PXOR X0,X6
|
||||
PSRLL $25,X2
|
||||
PXOR X2,X6
|
||||
MOVOA 336(SP),X2
|
||||
MOVOA X12,336(SP)
|
||||
MOVOA X3,X0
|
||||
PADDL X2,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $7,X0
|
||||
PXOR X0,X13
|
||||
PSRLL $25,X12
|
||||
PXOR X12,X13
|
||||
MOVOA X1,X0
|
||||
PADDL X6,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $9,X0
|
||||
PXOR X0,X15
|
||||
PSRLL $23,X12
|
||||
PXOR X12,X15
|
||||
MOVOA X2,X0
|
||||
PADDL X13,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $9,X0
|
||||
PXOR X0,X9
|
||||
PSRLL $23,X12
|
||||
PXOR X12,X9
|
||||
MOVOA X6,X0
|
||||
PADDL X15,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $13,X0
|
||||
PXOR X0,X11
|
||||
PSRLL $19,X12
|
||||
PXOR X12,X11
|
||||
MOVOA X13,X0
|
||||
PADDL X9,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $13,X0
|
||||
PXOR X0,X3
|
||||
PSRLL $19,X12
|
||||
PXOR X12,X3
|
||||
MOVOA X15,X0
|
||||
PADDL X11,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $18,X0
|
||||
PXOR X0,X1
|
||||
PSRLL $14,X12
|
||||
PXOR X12,X1
|
||||
MOVOA X9,X0
|
||||
PADDL X3,X0
|
||||
MOVOA X0,X12
|
||||
PSLLL $18,X0
|
||||
PXOR X0,X2
|
||||
PSRLL $14,X12
|
||||
PXOR X12,X2
|
||||
MOVOA 320(SP),X12
|
||||
MOVOA 336(SP),X0
|
||||
SUBQ $2,DX
|
||||
JA MAINLOOP1
|
||||
PADDL 112(SP),X12
|
||||
PADDL 176(SP),X7
|
||||
PADDL 224(SP),X10
|
||||
PADDL 272(SP),X4
|
||||
MOVD X12,DX
|
||||
MOVD X7,CX
|
||||
MOVD X10,R8
|
||||
MOVD X4,R9
|
||||
PSHUFL $0X39,X12,X12
|
||||
PSHUFL $0X39,X7,X7
|
||||
PSHUFL $0X39,X10,X10
|
||||
PSHUFL $0X39,X4,X4
|
||||
XORL 0(SI),DX
|
||||
XORL 4(SI),CX
|
||||
XORL 8(SI),R8
|
||||
XORL 12(SI),R9
|
||||
MOVL DX,0(DI)
|
||||
MOVL CX,4(DI)
|
||||
MOVL R8,8(DI)
|
||||
MOVL R9,12(DI)
|
||||
MOVD X12,DX
|
||||
MOVD X7,CX
|
||||
MOVD X10,R8
|
||||
MOVD X4,R9
|
||||
PSHUFL $0X39,X12,X12
|
||||
PSHUFL $0X39,X7,X7
|
||||
PSHUFL $0X39,X10,X10
|
||||
PSHUFL $0X39,X4,X4
|
||||
XORL 64(SI),DX
|
||||
XORL 68(SI),CX
|
||||
XORL 72(SI),R8
|
||||
XORL 76(SI),R9
|
||||
MOVL DX,64(DI)
|
||||
MOVL CX,68(DI)
|
||||
MOVL R8,72(DI)
|
||||
MOVL R9,76(DI)
|
||||
MOVD X12,DX
|
||||
MOVD X7,CX
|
||||
MOVD X10,R8
|
||||
MOVD X4,R9
|
||||
PSHUFL $0X39,X12,X12
|
||||
PSHUFL $0X39,X7,X7
|
||||
PSHUFL $0X39,X10,X10
|
||||
PSHUFL $0X39,X4,X4
|
||||
XORL 128(SI),DX
|
||||
XORL 132(SI),CX
|
||||
XORL 136(SI),R8
|
||||
XORL 140(SI),R9
|
||||
MOVL DX,128(DI)
|
||||
MOVL CX,132(DI)
|
||||
MOVL R8,136(DI)
|
||||
MOVL R9,140(DI)
|
||||
MOVD X12,DX
|
||||
MOVD X7,CX
|
||||
MOVD X10,R8
|
||||
MOVD X4,R9
|
||||
XORL 192(SI),DX
|
||||
XORL 196(SI),CX
|
||||
XORL 200(SI),R8
|
||||
XORL 204(SI),R9
|
||||
MOVL DX,192(DI)
|
||||
MOVL CX,196(DI)
|
||||
MOVL R8,200(DI)
|
||||
MOVL R9,204(DI)
|
||||
PADDL 240(SP),X14
|
||||
PADDL 64(SP),X0
|
||||
PADDL 128(SP),X5
|
||||
PADDL 192(SP),X8
|
||||
MOVD X14,DX
|
||||
MOVD X0,CX
|
||||
MOVD X5,R8
|
||||
MOVD X8,R9
|
||||
PSHUFL $0X39,X14,X14
|
||||
PSHUFL $0X39,X0,X0
|
||||
PSHUFL $0X39,X5,X5
|
||||
PSHUFL $0X39,X8,X8
|
||||
XORL 16(SI),DX
|
||||
XORL 20(SI),CX
|
||||
XORL 24(SI),R8
|
||||
XORL 28(SI),R9
|
||||
MOVL DX,16(DI)
|
||||
MOVL CX,20(DI)
|
||||
MOVL R8,24(DI)
|
||||
MOVL R9,28(DI)
|
||||
MOVD X14,DX
|
||||
MOVD X0,CX
|
||||
MOVD X5,R8
|
||||
MOVD X8,R9
|
||||
PSHUFL $0X39,X14,X14
|
||||
PSHUFL $0X39,X0,X0
|
||||
PSHUFL $0X39,X5,X5
|
||||
PSHUFL $0X39,X8,X8
|
||||
XORL 80(SI),DX
|
||||
XORL 84(SI),CX
|
||||
XORL 88(SI),R8
|
||||
XORL 92(SI),R9
|
||||
MOVL DX,80(DI)
|
||||
MOVL CX,84(DI)
|
||||
MOVL R8,88(DI)
|
||||
MOVL R9,92(DI)
|
||||
MOVD X14,DX
|
||||
MOVD X0,CX
|
||||
MOVD X5,R8
|
||||
MOVD X8,R9
|
||||
PSHUFL $0X39,X14,X14
|
||||
PSHUFL $0X39,X0,X0
|
||||
PSHUFL $0X39,X5,X5
|
||||
PSHUFL $0X39,X8,X8
|
||||
XORL 144(SI),DX
|
||||
XORL 148(SI),CX
|
||||
XORL 152(SI),R8
|
||||
XORL 156(SI),R9
|
||||
MOVL DX,144(DI)
|
||||
MOVL CX,148(DI)
|
||||
MOVL R8,152(DI)
|
||||
MOVL R9,156(DI)
|
||||
MOVD X14,DX
|
||||
MOVD X0,CX
|
||||
MOVD X5,R8
|
||||
MOVD X8,R9
|
||||
XORL 208(SI),DX
|
||||
XORL 212(SI),CX
|
||||
XORL 216(SI),R8
|
||||
XORL 220(SI),R9
|
||||
MOVL DX,208(DI)
|
||||
MOVL CX,212(DI)
|
||||
MOVL R8,216(DI)
|
||||
MOVL R9,220(DI)
|
||||
PADDL 288(SP),X15
|
||||
PADDL 304(SP),X11
|
||||
PADDL 80(SP),X1
|
||||
PADDL 144(SP),X6
|
||||
MOVD X15,DX
|
||||
MOVD X11,CX
|
||||
MOVD X1,R8
|
||||
MOVD X6,R9
|
||||
PSHUFL $0X39,X15,X15
|
||||
PSHUFL $0X39,X11,X11
|
||||
PSHUFL $0X39,X1,X1
|
||||
PSHUFL $0X39,X6,X6
|
||||
XORL 32(SI),DX
|
||||
XORL 36(SI),CX
|
||||
XORL 40(SI),R8
|
||||
XORL 44(SI),R9
|
||||
MOVL DX,32(DI)
|
||||
MOVL CX,36(DI)
|
||||
MOVL R8,40(DI)
|
||||
MOVL R9,44(DI)
|
||||
MOVD X15,DX
|
||||
MOVD X11,CX
|
||||
MOVD X1,R8
|
||||
MOVD X6,R9
|
||||
PSHUFL $0X39,X15,X15
|
||||
PSHUFL $0X39,X11,X11
|
||||
PSHUFL $0X39,X1,X1
|
||||
PSHUFL $0X39,X6,X6
|
||||
XORL 96(SI),DX
|
||||
XORL 100(SI),CX
|
||||
XORL 104(SI),R8
|
||||
XORL 108(SI),R9
|
||||
MOVL DX,96(DI)
|
||||
MOVL CX,100(DI)
|
||||
MOVL R8,104(DI)
|
||||
MOVL R9,108(DI)
|
||||
MOVD X15,DX
|
||||
MOVD X11,CX
|
||||
MOVD X1,R8
|
||||
MOVD X6,R9
|
||||
PSHUFL $0X39,X15,X15
|
||||
PSHUFL $0X39,X11,X11
|
||||
PSHUFL $0X39,X1,X1
|
||||
PSHUFL $0X39,X6,X6
|
||||
XORL 160(SI),DX
|
||||
XORL 164(SI),CX
|
||||
XORL 168(SI),R8
|
||||
XORL 172(SI),R9
|
||||
MOVL DX,160(DI)
|
||||
MOVL CX,164(DI)
|
||||
MOVL R8,168(DI)
|
||||
MOVL R9,172(DI)
|
||||
MOVD X15,DX
|
||||
MOVD X11,CX
|
||||
MOVD X1,R8
|
||||
MOVD X6,R9
|
||||
XORL 224(SI),DX
|
||||
XORL 228(SI),CX
|
||||
XORL 232(SI),R8
|
||||
XORL 236(SI),R9
|
||||
MOVL DX,224(DI)
|
||||
MOVL CX,228(DI)
|
||||
MOVL R8,232(DI)
|
||||
MOVL R9,236(DI)
|
||||
PADDL 160(SP),X13
|
||||
PADDL 208(SP),X9
|
||||
PADDL 256(SP),X3
|
||||
PADDL 96(SP),X2
|
||||
MOVD X13,DX
|
||||
MOVD X9,CX
|
||||
MOVD X3,R8
|
||||
MOVD X2,R9
|
||||
PSHUFL $0X39,X13,X13
|
||||
PSHUFL $0X39,X9,X9
|
||||
PSHUFL $0X39,X3,X3
|
||||
PSHUFL $0X39,X2,X2
|
||||
XORL 48(SI),DX
|
||||
XORL 52(SI),CX
|
||||
XORL 56(SI),R8
|
||||
XORL 60(SI),R9
|
||||
MOVL DX,48(DI)
|
||||
MOVL CX,52(DI)
|
||||
MOVL R8,56(DI)
|
||||
MOVL R9,60(DI)
|
||||
MOVD X13,DX
|
||||
MOVD X9,CX
|
||||
MOVD X3,R8
|
||||
MOVD X2,R9
|
||||
PSHUFL $0X39,X13,X13
|
||||
PSHUFL $0X39,X9,X9
|
||||
PSHUFL $0X39,X3,X3
|
||||
PSHUFL $0X39,X2,X2
|
||||
XORL 112(SI),DX
|
||||
XORL 116(SI),CX
|
||||
XORL 120(SI),R8
|
||||
XORL 124(SI),R9
|
||||
MOVL DX,112(DI)
|
||||
MOVL CX,116(DI)
|
||||
MOVL R8,120(DI)
|
||||
MOVL R9,124(DI)
|
||||
MOVD X13,DX
|
||||
MOVD X9,CX
|
||||
MOVD X3,R8
|
||||
MOVD X2,R9
|
||||
PSHUFL $0X39,X13,X13
|
||||
PSHUFL $0X39,X9,X9
|
||||
PSHUFL $0X39,X3,X3
|
||||
PSHUFL $0X39,X2,X2
|
||||
XORL 176(SI),DX
|
||||
XORL 180(SI),CX
|
||||
XORL 184(SI),R8
|
||||
XORL 188(SI),R9
|
||||
MOVL DX,176(DI)
|
||||
MOVL CX,180(DI)
|
||||
MOVL R8,184(DI)
|
||||
MOVL R9,188(DI)
|
||||
MOVD X13,DX
|
||||
MOVD X9,CX
|
||||
MOVD X3,R8
|
||||
MOVD X2,R9
|
||||
XORL 240(SI),DX
|
||||
XORL 244(SI),CX
|
||||
XORL 248(SI),R8
|
||||
XORL 252(SI),R9
|
||||
MOVL DX,240(DI)
|
||||
MOVL CX,244(DI)
|
||||
MOVL R8,248(DI)
|
||||
MOVL R9,252(DI)
|
||||
MOVQ 352(SP),R9
|
||||
SUBQ $256,R9
|
||||
ADDQ $256,SI
|
||||
ADDQ $256,DI
|
||||
CMPQ R9,$256
|
||||
JAE BYTESATLEAST256
|
||||
CMPQ R9,$0
|
||||
JBE DONE
|
||||
BYTESBETWEEN1AND255:
|
||||
CMPQ R9,$64
|
||||
JAE NOCOPY
|
||||
MOVQ DI,DX
|
||||
LEAQ 360(SP),DI
|
||||
MOVQ R9,CX
|
||||
REP; MOVSB
|
||||
LEAQ 360(SP),DI
|
||||
LEAQ 360(SP),SI
|
||||
NOCOPY:
|
||||
MOVQ R9,352(SP)
|
||||
MOVOA 48(SP),X0
|
||||
MOVOA 0(SP),X1
|
||||
MOVOA 16(SP),X2
|
||||
MOVOA 32(SP),X3
|
||||
MOVOA X1,X4
|
||||
MOVQ $20,CX
|
||||
MAINLOOP2:
|
||||
PADDL X0,X4
|
||||
MOVOA X0,X5
|
||||
MOVOA X4,X6
|
||||
PSLLL $7,X4
|
||||
PSRLL $25,X6
|
||||
PXOR X4,X3
|
||||
PXOR X6,X3
|
||||
PADDL X3,X5
|
||||
MOVOA X3,X4
|
||||
MOVOA X5,X6
|
||||
PSLLL $9,X5
|
||||
PSRLL $23,X6
|
||||
PXOR X5,X2
|
||||
PSHUFL $0X93,X3,X3
|
||||
PXOR X6,X2
|
||||
PADDL X2,X4
|
||||
MOVOA X2,X5
|
||||
MOVOA X4,X6
|
||||
PSLLL $13,X4
|
||||
PSRLL $19,X6
|
||||
PXOR X4,X1
|
||||
PSHUFL $0X4E,X2,X2
|
||||
PXOR X6,X1
|
||||
PADDL X1,X5
|
||||
MOVOA X3,X4
|
||||
MOVOA X5,X6
|
||||
PSLLL $18,X5
|
||||
PSRLL $14,X6
|
||||
PXOR X5,X0
|
||||
PSHUFL $0X39,X1,X1
|
||||
PXOR X6,X0
|
||||
PADDL X0,X4
|
||||
MOVOA X0,X5
|
||||
MOVOA X4,X6
|
||||
PSLLL $7,X4
|
||||
PSRLL $25,X6
|
||||
PXOR X4,X1
|
||||
PXOR X6,X1
|
||||
PADDL X1,X5
|
||||
MOVOA X1,X4
|
||||
MOVOA X5,X6
|
||||
PSLLL $9,X5
|
||||
PSRLL $23,X6
|
||||
PXOR X5,X2
|
||||
PSHUFL $0X93,X1,X1
|
||||
PXOR X6,X2
|
||||
PADDL X2,X4
|
||||
MOVOA X2,X5
|
||||
MOVOA X4,X6
|
||||
PSLLL $13,X4
|
||||
PSRLL $19,X6
|
||||
PXOR X4,X3
|
||||
PSHUFL $0X4E,X2,X2
|
||||
PXOR X6,X3
|
||||
PADDL X3,X5
|
||||
MOVOA X1,X4
|
||||
MOVOA X5,X6
|
||||
PSLLL $18,X5
|
||||
PSRLL $14,X6
|
||||
PXOR X5,X0
|
||||
PSHUFL $0X39,X3,X3
|
||||
PXOR X6,X0
|
||||
PADDL X0,X4
|
||||
MOVOA X0,X5
|
||||
MOVOA X4,X6
|
||||
PSLLL $7,X4
|
||||
PSRLL $25,X6
|
||||
PXOR X4,X3
|
||||
PXOR X6,X3
|
||||
PADDL X3,X5
|
||||
MOVOA X3,X4
|
||||
MOVOA X5,X6
|
||||
PSLLL $9,X5
|
||||
PSRLL $23,X6
|
||||
PXOR X5,X2
|
||||
PSHUFL $0X93,X3,X3
|
||||
PXOR X6,X2
|
||||
PADDL X2,X4
|
||||
MOVOA X2,X5
|
||||
MOVOA X4,X6
|
||||
PSLLL $13,X4
|
||||
PSRLL $19,X6
|
||||
PXOR X4,X1
|
||||
PSHUFL $0X4E,X2,X2
|
||||
PXOR X6,X1
|
||||
PADDL X1,X5
|
||||
MOVOA X3,X4
|
||||
MOVOA X5,X6
|
||||
PSLLL $18,X5
|
||||
PSRLL $14,X6
|
||||
PXOR X5,X0
|
||||
PSHUFL $0X39,X1,X1
|
||||
PXOR X6,X0
|
||||
PADDL X0,X4
|
||||
MOVOA X0,X5
|
||||
MOVOA X4,X6
|
||||
PSLLL $7,X4
|
||||
PSRLL $25,X6
|
||||
PXOR X4,X1
|
||||
PXOR X6,X1
|
||||
PADDL X1,X5
|
||||
MOVOA X1,X4
|
||||
MOVOA X5,X6
|
||||
PSLLL $9,X5
|
||||
PSRLL $23,X6
|
||||
PXOR X5,X2
|
||||
PSHUFL $0X93,X1,X1
|
||||
PXOR X6,X2
|
||||
PADDL X2,X4
|
||||
MOVOA X2,X5
|
||||
MOVOA X4,X6
|
||||
PSLLL $13,X4
|
||||
PSRLL $19,X6
|
||||
PXOR X4,X3
|
||||
PSHUFL $0X4E,X2,X2
|
||||
PXOR X6,X3
|
||||
SUBQ $4,CX
|
||||
PADDL X3,X5
|
||||
MOVOA X1,X4
|
||||
MOVOA X5,X6
|
||||
PSLLL $18,X5
|
||||
PXOR X7,X7
|
||||
PSRLL $14,X6
|
||||
PXOR X5,X0
|
||||
PSHUFL $0X39,X3,X3
|
||||
PXOR X6,X0
|
||||
JA MAINLOOP2
|
||||
PADDL 48(SP),X0
|
||||
PADDL 0(SP),X1
|
||||
PADDL 16(SP),X2
|
||||
PADDL 32(SP),X3
|
||||
MOVD X0,CX
|
||||
MOVD X1,R8
|
||||
MOVD X2,R9
|
||||
MOVD X3,AX
|
||||
PSHUFL $0X39,X0,X0
|
||||
PSHUFL $0X39,X1,X1
|
||||
PSHUFL $0X39,X2,X2
|
||||
PSHUFL $0X39,X3,X3
|
||||
XORL 0(SI),CX
|
||||
XORL 48(SI),R8
|
||||
XORL 32(SI),R9
|
||||
XORL 16(SI),AX
|
||||
MOVL CX,0(DI)
|
||||
MOVL R8,48(DI)
|
||||
MOVL R9,32(DI)
|
||||
MOVL AX,16(DI)
|
||||
MOVD X0,CX
|
||||
MOVD X1,R8
|
||||
MOVD X2,R9
|
||||
MOVD X3,AX
|
||||
PSHUFL $0X39,X0,X0
|
||||
PSHUFL $0X39,X1,X1
|
||||
PSHUFL $0X39,X2,X2
|
||||
PSHUFL $0X39,X3,X3
|
||||
XORL 20(SI),CX
|
||||
XORL 4(SI),R8
|
||||
XORL 52(SI),R9
|
||||
XORL 36(SI),AX
|
||||
MOVL CX,20(DI)
|
||||
MOVL R8,4(DI)
|
||||
MOVL R9,52(DI)
|
||||
MOVL AX,36(DI)
|
||||
MOVD X0,CX
|
||||
MOVD X1,R8
|
||||
MOVD X2,R9
|
||||
MOVD X3,AX
|
||||
PSHUFL $0X39,X0,X0
|
||||
PSHUFL $0X39,X1,X1
|
||||
PSHUFL $0X39,X2,X2
|
||||
PSHUFL $0X39,X3,X3
|
||||
XORL 40(SI),CX
|
||||
XORL 24(SI),R8
|
||||
XORL 8(SI),R9
|
||||
XORL 56(SI),AX
|
||||
MOVL CX,40(DI)
|
||||
MOVL R8,24(DI)
|
||||
MOVL R9,8(DI)
|
||||
MOVL AX,56(DI)
|
||||
MOVD X0,CX
|
||||
MOVD X1,R8
|
||||
MOVD X2,R9
|
||||
MOVD X3,AX
|
||||
XORL 60(SI),CX
|
||||
XORL 44(SI),R8
|
||||
XORL 28(SI),R9
|
||||
XORL 12(SI),AX
|
||||
MOVL CX,60(DI)
|
||||
MOVL R8,44(DI)
|
||||
MOVL R9,28(DI)
|
||||
MOVL AX,12(DI)
|
||||
MOVQ 352(SP),R9
|
||||
MOVL 16(SP),CX
|
||||
MOVL 36 (SP),R8
|
||||
ADDQ $1,CX
|
||||
SHLQ $32,R8
|
||||
ADDQ R8,CX
|
||||
MOVQ CX,R8
|
||||
SHRQ $32,R8
|
||||
MOVL CX,16(SP)
|
||||
MOVL R8, 36 (SP)
|
||||
CMPQ R9,$64
|
||||
JA BYTESATLEAST65
|
||||
JAE BYTESATLEAST64
|
||||
MOVQ DI,SI
|
||||
MOVQ DX,DI
|
||||
MOVQ R9,CX
|
||||
REP; MOVSB
|
||||
BYTESATLEAST64:
|
||||
DONE:
|
||||
MOVQ R12,SP
|
||||
RET
|
||||
BYTESATLEAST65:
|
||||
SUBQ $64,R9
|
||||
ADDQ $64,DI
|
||||
ADDQ $64,SI
|
||||
JMP BYTESBETWEEN1AND255
|
||||
+199
@@ -0,0 +1,199 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
package salsa
|
||||
|
||||
// Core208 applies the Salsa20/8 core function to the 64-byte array in and puts
|
||||
// the result into the 64-byte array out. The input and output may be the same array.
|
||||
func Core208(out *[64]byte, in *[64]byte) {
|
||||
j0 := uint32(in[0]) | uint32(in[1])<<8 | uint32(in[2])<<16 | uint32(in[3])<<24
|
||||
j1 := uint32(in[4]) | uint32(in[5])<<8 | uint32(in[6])<<16 | uint32(in[7])<<24
|
||||
j2 := uint32(in[8]) | uint32(in[9])<<8 | uint32(in[10])<<16 | uint32(in[11])<<24
|
||||
j3 := uint32(in[12]) | uint32(in[13])<<8 | uint32(in[14])<<16 | uint32(in[15])<<24
|
||||
j4 := uint32(in[16]) | uint32(in[17])<<8 | uint32(in[18])<<16 | uint32(in[19])<<24
|
||||
j5 := uint32(in[20]) | uint32(in[21])<<8 | uint32(in[22])<<16 | uint32(in[23])<<24
|
||||
j6 := uint32(in[24]) | uint32(in[25])<<8 | uint32(in[26])<<16 | uint32(in[27])<<24
|
||||
j7 := uint32(in[28]) | uint32(in[29])<<8 | uint32(in[30])<<16 | uint32(in[31])<<24
|
||||
j8 := uint32(in[32]) | uint32(in[33])<<8 | uint32(in[34])<<16 | uint32(in[35])<<24
|
||||
j9 := uint32(in[36]) | uint32(in[37])<<8 | uint32(in[38])<<16 | uint32(in[39])<<24
|
||||
j10 := uint32(in[40]) | uint32(in[41])<<8 | uint32(in[42])<<16 | uint32(in[43])<<24
|
||||
j11 := uint32(in[44]) | uint32(in[45])<<8 | uint32(in[46])<<16 | uint32(in[47])<<24
|
||||
j12 := uint32(in[48]) | uint32(in[49])<<8 | uint32(in[50])<<16 | uint32(in[51])<<24
|
||||
j13 := uint32(in[52]) | uint32(in[53])<<8 | uint32(in[54])<<16 | uint32(in[55])<<24
|
||||
j14 := uint32(in[56]) | uint32(in[57])<<8 | uint32(in[58])<<16 | uint32(in[59])<<24
|
||||
j15 := uint32(in[60]) | uint32(in[61])<<8 | uint32(in[62])<<16 | uint32(in[63])<<24
|
||||
|
||||
x0, x1, x2, x3, x4, x5, x6, x7, x8 := j0, j1, j2, j3, j4, j5, j6, j7, j8
|
||||
x9, x10, x11, x12, x13, x14, x15 := j9, j10, j11, j12, j13, j14, j15
|
||||
|
||||
for i := 0; i < 8; i += 2 {
|
||||
u := x0 + x12
|
||||
x4 ^= u<<7 | u>>(32-7)
|
||||
u = x4 + x0
|
||||
x8 ^= u<<9 | u>>(32-9)
|
||||
u = x8 + x4
|
||||
x12 ^= u<<13 | u>>(32-13)
|
||||
u = x12 + x8
|
||||
x0 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x5 + x1
|
||||
x9 ^= u<<7 | u>>(32-7)
|
||||
u = x9 + x5
|
||||
x13 ^= u<<9 | u>>(32-9)
|
||||
u = x13 + x9
|
||||
x1 ^= u<<13 | u>>(32-13)
|
||||
u = x1 + x13
|
||||
x5 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x10 + x6
|
||||
x14 ^= u<<7 | u>>(32-7)
|
||||
u = x14 + x10
|
||||
x2 ^= u<<9 | u>>(32-9)
|
||||
u = x2 + x14
|
||||
x6 ^= u<<13 | u>>(32-13)
|
||||
u = x6 + x2
|
||||
x10 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x15 + x11
|
||||
x3 ^= u<<7 | u>>(32-7)
|
||||
u = x3 + x15
|
||||
x7 ^= u<<9 | u>>(32-9)
|
||||
u = x7 + x3
|
||||
x11 ^= u<<13 | u>>(32-13)
|
||||
u = x11 + x7
|
||||
x15 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x0 + x3
|
||||
x1 ^= u<<7 | u>>(32-7)
|
||||
u = x1 + x0
|
||||
x2 ^= u<<9 | u>>(32-9)
|
||||
u = x2 + x1
|
||||
x3 ^= u<<13 | u>>(32-13)
|
||||
u = x3 + x2
|
||||
x0 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x5 + x4
|
||||
x6 ^= u<<7 | u>>(32-7)
|
||||
u = x6 + x5
|
||||
x7 ^= u<<9 | u>>(32-9)
|
||||
u = x7 + x6
|
||||
x4 ^= u<<13 | u>>(32-13)
|
||||
u = x4 + x7
|
||||
x5 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x10 + x9
|
||||
x11 ^= u<<7 | u>>(32-7)
|
||||
u = x11 + x10
|
||||
x8 ^= u<<9 | u>>(32-9)
|
||||
u = x8 + x11
|
||||
x9 ^= u<<13 | u>>(32-13)
|
||||
u = x9 + x8
|
||||
x10 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x15 + x14
|
||||
x12 ^= u<<7 | u>>(32-7)
|
||||
u = x12 + x15
|
||||
x13 ^= u<<9 | u>>(32-9)
|
||||
u = x13 + x12
|
||||
x14 ^= u<<13 | u>>(32-13)
|
||||
u = x14 + x13
|
||||
x15 ^= u<<18 | u>>(32-18)
|
||||
}
|
||||
x0 += j0
|
||||
x1 += j1
|
||||
x2 += j2
|
||||
x3 += j3
|
||||
x4 += j4
|
||||
x5 += j5
|
||||
x6 += j6
|
||||
x7 += j7
|
||||
x8 += j8
|
||||
x9 += j9
|
||||
x10 += j10
|
||||
x11 += j11
|
||||
x12 += j12
|
||||
x13 += j13
|
||||
x14 += j14
|
||||
x15 += j15
|
||||
|
||||
out[0] = byte(x0)
|
||||
out[1] = byte(x0 >> 8)
|
||||
out[2] = byte(x0 >> 16)
|
||||
out[3] = byte(x0 >> 24)
|
||||
|
||||
out[4] = byte(x1)
|
||||
out[5] = byte(x1 >> 8)
|
||||
out[6] = byte(x1 >> 16)
|
||||
out[7] = byte(x1 >> 24)
|
||||
|
||||
out[8] = byte(x2)
|
||||
out[9] = byte(x2 >> 8)
|
||||
out[10] = byte(x2 >> 16)
|
||||
out[11] = byte(x2 >> 24)
|
||||
|
||||
out[12] = byte(x3)
|
||||
out[13] = byte(x3 >> 8)
|
||||
out[14] = byte(x3 >> 16)
|
||||
out[15] = byte(x3 >> 24)
|
||||
|
||||
out[16] = byte(x4)
|
||||
out[17] = byte(x4 >> 8)
|
||||
out[18] = byte(x4 >> 16)
|
||||
out[19] = byte(x4 >> 24)
|
||||
|
||||
out[20] = byte(x5)
|
||||
out[21] = byte(x5 >> 8)
|
||||
out[22] = byte(x5 >> 16)
|
||||
out[23] = byte(x5 >> 24)
|
||||
|
||||
out[24] = byte(x6)
|
||||
out[25] = byte(x6 >> 8)
|
||||
out[26] = byte(x6 >> 16)
|
||||
out[27] = byte(x6 >> 24)
|
||||
|
||||
out[28] = byte(x7)
|
||||
out[29] = byte(x7 >> 8)
|
||||
out[30] = byte(x7 >> 16)
|
||||
out[31] = byte(x7 >> 24)
|
||||
|
||||
out[32] = byte(x8)
|
||||
out[33] = byte(x8 >> 8)
|
||||
out[34] = byte(x8 >> 16)
|
||||
out[35] = byte(x8 >> 24)
|
||||
|
||||
out[36] = byte(x9)
|
||||
out[37] = byte(x9 >> 8)
|
||||
out[38] = byte(x9 >> 16)
|
||||
out[39] = byte(x9 >> 24)
|
||||
|
||||
out[40] = byte(x10)
|
||||
out[41] = byte(x10 >> 8)
|
||||
out[42] = byte(x10 >> 16)
|
||||
out[43] = byte(x10 >> 24)
|
||||
|
||||
out[44] = byte(x11)
|
||||
out[45] = byte(x11 >> 8)
|
||||
out[46] = byte(x11 >> 16)
|
||||
out[47] = byte(x11 >> 24)
|
||||
|
||||
out[48] = byte(x12)
|
||||
out[49] = byte(x12 >> 8)
|
||||
out[50] = byte(x12 >> 16)
|
||||
out[51] = byte(x12 >> 24)
|
||||
|
||||
out[52] = byte(x13)
|
||||
out[53] = byte(x13 >> 8)
|
||||
out[54] = byte(x13 >> 16)
|
||||
out[55] = byte(x13 >> 24)
|
||||
|
||||
out[56] = byte(x14)
|
||||
out[57] = byte(x14 >> 8)
|
||||
out[58] = byte(x14 >> 16)
|
||||
out[59] = byte(x14 >> 24)
|
||||
|
||||
out[60] = byte(x15)
|
||||
out[61] = byte(x15 >> 8)
|
||||
out[62] = byte(x15 >> 16)
|
||||
out[63] = byte(x15 >> 24)
|
||||
}
|
||||
+24
@@ -0,0 +1,24 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build amd64,!appengine,!gccgo
|
||||
|
||||
package salsa
|
||||
|
||||
// This function is implemented in salsa2020_amd64.s.
|
||||
|
||||
//go:noescape
|
||||
|
||||
func salsa2020XORKeyStream(out, in *byte, n uint64, nonce, key *byte)
|
||||
|
||||
// XORKeyStream crypts bytes from in to out using the given key and counters.
|
||||
// In and out must overlap entirely or not at all. Counter
|
||||
// contains the raw salsa20 counter bytes (both nonce and block counter).
|
||||
func XORKeyStream(out, in []byte, counter *[16]byte, key *[32]byte) {
|
||||
if len(in) == 0 {
|
||||
return
|
||||
}
|
||||
_ = out[len(in)-1]
|
||||
salsa2020XORKeyStream(&out[0], &in[0], uint64(len(in)), &counter[0], &key[0])
|
||||
}
|
||||
+234
@@ -0,0 +1,234 @@
|
||||
// Copyright 2012 The Go Authors. All rights reserved.
|
||||
// Use of this source code is governed by a BSD-style
|
||||
// license that can be found in the LICENSE file.
|
||||
|
||||
// +build !amd64 appengine gccgo
|
||||
|
||||
package salsa
|
||||
|
||||
const rounds = 20
|
||||
|
||||
// core applies the Salsa20 core function to 16-byte input in, 32-byte key k,
|
||||
// and 16-byte constant c, and puts the result into 64-byte array out.
|
||||
func core(out *[64]byte, in *[16]byte, k *[32]byte, c *[16]byte) {
|
||||
j0 := uint32(c[0]) | uint32(c[1])<<8 | uint32(c[2])<<16 | uint32(c[3])<<24
|
||||
j1 := uint32(k[0]) | uint32(k[1])<<8 | uint32(k[2])<<16 | uint32(k[3])<<24
|
||||
j2 := uint32(k[4]) | uint32(k[5])<<8 | uint32(k[6])<<16 | uint32(k[7])<<24
|
||||
j3 := uint32(k[8]) | uint32(k[9])<<8 | uint32(k[10])<<16 | uint32(k[11])<<24
|
||||
j4 := uint32(k[12]) | uint32(k[13])<<8 | uint32(k[14])<<16 | uint32(k[15])<<24
|
||||
j5 := uint32(c[4]) | uint32(c[5])<<8 | uint32(c[6])<<16 | uint32(c[7])<<24
|
||||
j6 := uint32(in[0]) | uint32(in[1])<<8 | uint32(in[2])<<16 | uint32(in[3])<<24
|
||||
j7 := uint32(in[4]) | uint32(in[5])<<8 | uint32(in[6])<<16 | uint32(in[7])<<24
|
||||
j8 := uint32(in[8]) | uint32(in[9])<<8 | uint32(in[10])<<16 | uint32(in[11])<<24
|
||||
j9 := uint32(in[12]) | uint32(in[13])<<8 | uint32(in[14])<<16 | uint32(in[15])<<24
|
||||
j10 := uint32(c[8]) | uint32(c[9])<<8 | uint32(c[10])<<16 | uint32(c[11])<<24
|
||||
j11 := uint32(k[16]) | uint32(k[17])<<8 | uint32(k[18])<<16 | uint32(k[19])<<24
|
||||
j12 := uint32(k[20]) | uint32(k[21])<<8 | uint32(k[22])<<16 | uint32(k[23])<<24
|
||||
j13 := uint32(k[24]) | uint32(k[25])<<8 | uint32(k[26])<<16 | uint32(k[27])<<24
|
||||
j14 := uint32(k[28]) | uint32(k[29])<<8 | uint32(k[30])<<16 | uint32(k[31])<<24
|
||||
j15 := uint32(c[12]) | uint32(c[13])<<8 | uint32(c[14])<<16 | uint32(c[15])<<24
|
||||
|
||||
x0, x1, x2, x3, x4, x5, x6, x7, x8 := j0, j1, j2, j3, j4, j5, j6, j7, j8
|
||||
x9, x10, x11, x12, x13, x14, x15 := j9, j10, j11, j12, j13, j14, j15
|
||||
|
||||
for i := 0; i < rounds; i += 2 {
|
||||
u := x0 + x12
|
||||
x4 ^= u<<7 | u>>(32-7)
|
||||
u = x4 + x0
|
||||
x8 ^= u<<9 | u>>(32-9)
|
||||
u = x8 + x4
|
||||
x12 ^= u<<13 | u>>(32-13)
|
||||
u = x12 + x8
|
||||
x0 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x5 + x1
|
||||
x9 ^= u<<7 | u>>(32-7)
|
||||
u = x9 + x5
|
||||
x13 ^= u<<9 | u>>(32-9)
|
||||
u = x13 + x9
|
||||
x1 ^= u<<13 | u>>(32-13)
|
||||
u = x1 + x13
|
||||
x5 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x10 + x6
|
||||
x14 ^= u<<7 | u>>(32-7)
|
||||
u = x14 + x10
|
||||
x2 ^= u<<9 | u>>(32-9)
|
||||
u = x2 + x14
|
||||
x6 ^= u<<13 | u>>(32-13)
|
||||
u = x6 + x2
|
||||
x10 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x15 + x11
|
||||
x3 ^= u<<7 | u>>(32-7)
|
||||
u = x3 + x15
|
||||
x7 ^= u<<9 | u>>(32-9)
|
||||
u = x7 + x3
|
||||
x11 ^= u<<13 | u>>(32-13)
|
||||
u = x11 + x7
|
||||
x15 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x0 + x3
|
||||
x1 ^= u<<7 | u>>(32-7)
|
||||
u = x1 + x0
|
||||
x2 ^= u<<9 | u>>(32-9)
|
||||
u = x2 + x1
|
||||
x3 ^= u<<13 | u>>(32-13)
|
||||
u = x3 + x2
|
||||
x0 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x5 + x4
|
||||
x6 ^= u<<7 | u>>(32-7)
|
||||
u = x6 + x5
|
||||
x7 ^= u<<9 | u>>(32-9)
|
||||
u = x7 + x6
|
||||
x4 ^= u<<13 | u>>(32-13)
|
||||
u = x4 + x7
|
||||
x5 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x10 + x9
|
||||
x11 ^= u<<7 | u>>(32-7)
|
||||
u = x11 + x10
|
||||
x8 ^= u<<9 | u>>(32-9)
|
||||
u = x8 + x11
|
||||
x9 ^= u<<13 | u>>(32-13)
|
||||
u = x9 + x8
|
||||
x10 ^= u<<18 | u>>(32-18)
|
||||
|
||||
u = x15 + x14
|
||||
x12 ^= u<<7 | u>>(32-7)
|
||||
u = x12 + x15
|
||||
x13 ^= u<<9 | u>>(32-9)
|
||||
u = x13 + x12
|
||||
x14 ^= u<<13 | u>>(32-13)
|
||||
u = x14 + x13
|
||||
x15 ^= u<<18 | u>>(32-18)
|
||||
}
|
||||
x0 += j0
|
||||
x1 += j1
|
||||
x2 += j2
|
||||
x3 += j3
|
||||
x4 += j4
|
||||
x5 += j5
|
||||
x6 += j6
|
||||
x7 += j7
|
||||
x8 += j8
|
||||
x9 += j9
|
||||
x10 += j10
|
||||
x11 += j11
|
||||
x12 += j12
|
||||
x13 += j13
|
||||
x14 += j14
|
||||
x15 += j15
|
||||
|
||||
out[0] = byte(x0)
|
||||
out[1] = byte(x0 >> 8)
|
||||
out[2] = byte(x0 >> 16)
|
||||
out[3] = byte(x0 >> 24)
|
||||
|
||||
out[4] = byte(x1)
|
||||
out[5] = byte(x1 >> 8)
|
||||
out[6] = byte(x1 >> 16)
|
||||
out[7] = byte(x1 >> 24)
|
||||
|
||||
out[8] = byte(x2)
|
||||
out[9] = byte(x2 >> 8)
|
||||
out[10] = byte(x2 >> 16)
|
||||
out[11] = byte(x2 >> 24)
|
||||
|
||||
out[12] = byte(x3)
|
||||
out[13] = byte(x3 >> 8)
|
||||
out[14] = byte(x3 >> 16)
|
||||
out[15] = byte(x3 >> 24)
|
||||
|
||||
out[16] = byte(x4)
|
||||
out[17] = byte(x4 >> 8)
|
||||
out[18] = byte(x4 >> 16)
|
||||
out[19] = byte(x4 >> 24)
|
||||
|
||||
out[20] = byte(x5)
|
||||
out[21] = byte(x5 >> 8)
|
||||
out[22] = byte(x5 >> 16)
|
||||
out[23] = byte(x5 >> 24)
|
||||
|
||||
out[24] = byte(x6)
|
||||
out[25] = byte(x6 >> 8)
|
||||
out[26] = byte(x6 >> 16)
|
||||
out[27] = byte(x6 >> 24)
|
||||
|
||||
out[28] = byte(x7)
|
||||
out[29] = byte(x7 >> 8)
|
||||
out[30] = byte(x7 >> 16)
|
||||
out[31] = byte(x7 >> 24)
|
||||
|
||||
out[32] = byte(x8)
|
||||
out[33] = byte(x8 >> 8)
|
||||
out[34] = byte(x8 >> 16)
|
||||
out[35] = byte(x8 >> 24)
|
||||
|
||||
out[36] = byte(x9)
|
||||
out[37] = byte(x9 >> 8)
|
||||
out[38] = byte(x9 >> 16)
|
||||
out[39] = byte(x9 >> 24)
|
||||
|
||||
out[40] = byte(x10)
|
||||
out[41] = byte(x10 >> 8)
|
||||
out[42] = byte(x10 >> 16)
|
||||
out[43] = byte(x10 >> 24)
|
||||
|
||||
out[44] = byte(x11)
|
||||
out[45] = byte(x11 >> 8)
|
||||
out[46] = byte(x11 >> 16)
|
||||
out[47] = byte(x11 >> 24)
|
||||
|
||||
out[48] = byte(x12)
|
||||
out[49] = byte(x12 >> 8)
|
||||
out[50] = byte(x12 >> 16)
|
||||
out[51] = byte(x12 >> 24)
|
||||
|
||||
out[52] = byte(x13)
|
||||
out[53] = byte(x13 >> 8)
|
||||
out[54] = byte(x13 >> 16)
|
||||
out[55] = byte(x13 >> 24)
|
||||
|
||||
out[56] = byte(x14)
|
||||
out[57] = byte(x14 >> 8)
|
||||
out[58] = byte(x14 >> 16)
|
||||
out[59] = byte(x14 >> 24)
|
||||
|
||||
out[60] = byte(x15)
|
||||
out[61] = byte(x15 >> 8)
|
||||
out[62] = byte(x15 >> 16)
|
||||
out[63] = byte(x15 >> 24)
|
||||
}
|
||||
|
||||
// XORKeyStream crypts bytes from in to out using the given key and counters.
|
||||
// In and out must overlap entirely or not at all. Counter
|
||||
// contains the raw salsa20 counter bytes (both nonce and block counter).
|
||||
func XORKeyStream(out, in []byte, counter *[16]byte, key *[32]byte) {
|
||||
var block [64]byte
|
||||
var counterCopy [16]byte
|
||||
copy(counterCopy[:], counter[:])
|
||||
|
||||
for len(in) >= 64 {
|
||||
core(&block, &counterCopy, key, &Sigma)
|
||||
for i, x := range block {
|
||||
out[i] = in[i] ^ x
|
||||
}
|
||||
u := uint32(1)
|
||||
for i := 8; i < 16; i++ {
|
||||
u += uint32(counterCopy[i])
|
||||
counterCopy[i] = byte(u)
|
||||
u >>= 8
|
||||
}
|
||||
in = in[64:]
|
||||
out = out[64:]
|
||||
}
|
||||
|
||||
if len(in) > 0 {
|
||||
core(&block, &counterCopy, key, &Sigma)
|
||||
for i, v := range in {
|
||||
out[i] = v ^ block[i]
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user