2014-06-20 20:00:00 +01:00
|
|
|
/* Originally written by Bodo Moeller and Nils Larsch for the OpenSSL project.
|
|
|
|
* ====================================================================
|
|
|
|
* Copyright (c) 1998-2005 The OpenSSL Project. All rights reserved.
|
|
|
|
*
|
|
|
|
* Redistribution and use in source and binary forms, with or without
|
|
|
|
* modification, are permitted provided that the following conditions
|
|
|
|
* are met:
|
|
|
|
*
|
|
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
|
|
* notice, this list of conditions and the following disclaimer.
|
|
|
|
*
|
|
|
|
* 2. 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.
|
|
|
|
*
|
|
|
|
* 3. All advertising materials mentioning features or use of this
|
|
|
|
* software must display the following acknowledgment:
|
|
|
|
* "This product includes software developed by the OpenSSL Project
|
|
|
|
* for use in the OpenSSL Toolkit. (http://www.openssl.org/)"
|
|
|
|
*
|
|
|
|
* 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to
|
|
|
|
* endorse or promote products derived from this software without
|
|
|
|
* prior written permission. For written permission, please contact
|
|
|
|
* openssl-core@openssl.org.
|
|
|
|
*
|
|
|
|
* 5. Products derived from this software may not be called "OpenSSL"
|
|
|
|
* nor may "OpenSSL" appear in their names without prior written
|
|
|
|
* permission of the OpenSSL Project.
|
|
|
|
*
|
|
|
|
* 6. Redistributions of any form whatsoever must retain the following
|
|
|
|
* acknowledgment:
|
|
|
|
* "This product includes software developed by the OpenSSL Project
|
|
|
|
* for use in the OpenSSL Toolkit (http://www.openssl.org/)"
|
|
|
|
*
|
|
|
|
* THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY
|
|
|
|
* EXPRESSED 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 OpenSSL PROJECT OR
|
|
|
|
* ITS 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.
|
|
|
|
* ====================================================================
|
|
|
|
*
|
|
|
|
* This product includes cryptographic software written by Eric Young
|
|
|
|
* (eay@cryptsoft.com). This product includes software written by Tim
|
|
|
|
* Hudson (tjh@cryptsoft.com).
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
/* ====================================================================
|
|
|
|
* Copyright 2002 Sun Microsystems, Inc. ALL RIGHTS RESERVED.
|
|
|
|
*
|
|
|
|
* Portions of the attached software ("Contribution") are developed by
|
|
|
|
* SUN MICROSYSTEMS, INC., and are contributed to the OpenSSL project.
|
|
|
|
*
|
|
|
|
* The Contribution is licensed pursuant to the OpenSSL open source
|
|
|
|
* license provided above.
|
|
|
|
*
|
|
|
|
* The elliptic curve binary polynomial software is originally written by
|
|
|
|
* Sheueling Chang Shantz and Douglas Stebila of Sun Microsystems
|
|
|
|
* Laboratories. */
|
|
|
|
|
|
|
|
#include <openssl/ec.h>
|
|
|
|
|
|
|
|
#include <openssl/bn.h>
|
|
|
|
#include <openssl/err.h>
|
|
|
|
#include <openssl/mem.h>
|
|
|
|
|
2017-05-02 22:25:39 +01:00
|
|
|
#include "../bn/internal.h"
|
|
|
|
#include "../delocate.h"
|
2014-06-20 20:00:00 +01:00
|
|
|
#include "internal.h"
|
|
|
|
|
|
|
|
|
|
|
|
int ec_GFp_mont_group_init(EC_GROUP *group) {
|
|
|
|
int ok;
|
|
|
|
|
|
|
|
ok = ec_GFp_simple_group_init(group);
|
2015-04-08 22:11:16 +01:00
|
|
|
group->mont = NULL;
|
2014-06-20 20:00:00 +01:00
|
|
|
return ok;
|
|
|
|
}
|
|
|
|
|
|
|
|
void ec_GFp_mont_group_finish(EC_GROUP *group) {
|
2015-04-22 20:08:19 +01:00
|
|
|
BN_MONT_CTX_free(group->mont);
|
|
|
|
group->mont = NULL;
|
2014-06-20 20:00:00 +01:00
|
|
|
ec_GFp_simple_group_finish(group);
|
|
|
|
}
|
|
|
|
|
|
|
|
int ec_GFp_mont_group_set_curve(EC_GROUP *group, const BIGNUM *p,
|
|
|
|
const BIGNUM *a, const BIGNUM *b, BN_CTX *ctx) {
|
|
|
|
BN_CTX *new_ctx = NULL;
|
|
|
|
int ret = 0;
|
|
|
|
|
2015-04-22 20:08:19 +01:00
|
|
|
BN_MONT_CTX_free(group->mont);
|
|
|
|
group->mont = NULL;
|
2014-06-20 20:00:00 +01:00
|
|
|
|
|
|
|
if (ctx == NULL) {
|
|
|
|
ctx = new_ctx = BN_CTX_new();
|
2015-02-11 06:17:18 +00:00
|
|
|
if (ctx == NULL) {
|
2014-06-20 20:00:00 +01:00
|
|
|
return 0;
|
2015-02-11 06:17:18 +00:00
|
|
|
}
|
2014-06-20 20:00:00 +01:00
|
|
|
}
|
|
|
|
|
2018-01-23 22:03:26 +00:00
|
|
|
group->mont = BN_MONT_CTX_new_for_modulus(p, ctx);
|
|
|
|
if (group->mont == NULL) {
|
2015-06-29 05:28:17 +01:00
|
|
|
OPENSSL_PUT_ERROR(EC, ERR_R_BN_LIB);
|
2014-06-20 20:00:00 +01:00
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = ec_GFp_simple_group_set_curve(group, p, a, b, ctx);
|
|
|
|
|
|
|
|
if (!ret) {
|
2015-04-08 22:11:16 +01:00
|
|
|
BN_MONT_CTX_free(group->mont);
|
|
|
|
group->mont = NULL;
|
2014-06-20 20:00:00 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
err:
|
2015-04-22 20:08:19 +01:00
|
|
|
BN_CTX_free(new_ctx);
|
2014-06-20 20:00:00 +01:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int ec_GFp_mont_field_mul(const EC_GROUP *group, BIGNUM *r, const BIGNUM *a,
|
|
|
|
const BIGNUM *b, BN_CTX *ctx) {
|
2015-04-08 22:11:16 +01:00
|
|
|
if (group->mont == NULL) {
|
2015-06-29 05:28:17 +01:00
|
|
|
OPENSSL_PUT_ERROR(EC, EC_R_NOT_INITIALIZED);
|
2014-06-20 20:00:00 +01:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-04-08 22:11:16 +01:00
|
|
|
return BN_mod_mul_montgomery(r, a, b, group->mont, ctx);
|
2014-06-20 20:00:00 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
int ec_GFp_mont_field_sqr(const EC_GROUP *group, BIGNUM *r, const BIGNUM *a,
|
|
|
|
BN_CTX *ctx) {
|
2015-04-08 22:11:16 +01:00
|
|
|
if (group->mont == NULL) {
|
2015-06-29 05:28:17 +01:00
|
|
|
OPENSSL_PUT_ERROR(EC, EC_R_NOT_INITIALIZED);
|
2014-06-20 20:00:00 +01:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-04-08 22:11:16 +01:00
|
|
|
return BN_mod_mul_montgomery(r, a, a, group->mont, ctx);
|
2014-06-20 20:00:00 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
int ec_GFp_mont_field_encode(const EC_GROUP *group, BIGNUM *r, const BIGNUM *a,
|
|
|
|
BN_CTX *ctx) {
|
2015-04-08 22:11:16 +01:00
|
|
|
if (group->mont == NULL) {
|
2015-06-29 05:28:17 +01:00
|
|
|
OPENSSL_PUT_ERROR(EC, EC_R_NOT_INITIALIZED);
|
2014-06-20 20:00:00 +01:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-04-08 22:11:16 +01:00
|
|
|
return BN_to_montgomery(r, a, group->mont, ctx);
|
2014-06-20 20:00:00 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
int ec_GFp_mont_field_decode(const EC_GROUP *group, BIGNUM *r, const BIGNUM *a,
|
|
|
|
BN_CTX *ctx) {
|
2015-04-08 22:11:16 +01:00
|
|
|
if (group->mont == NULL) {
|
2015-06-29 05:28:17 +01:00
|
|
|
OPENSSL_PUT_ERROR(EC, EC_R_NOT_INITIALIZED);
|
2014-06-20 20:00:00 +01:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-04-08 22:11:16 +01:00
|
|
|
return BN_from_montgomery(r, a, group->mont, ctx);
|
2014-06-20 20:00:00 +01:00
|
|
|
}
|
|
|
|
|
2016-03-11 23:12:11 +00:00
|
|
|
static int ec_GFp_mont_point_get_affine_coordinates(const EC_GROUP *group,
|
|
|
|
const EC_POINT *point,
|
|
|
|
BIGNUM *x, BIGNUM *y,
|
|
|
|
BN_CTX *ctx) {
|
|
|
|
if (EC_POINT_is_at_infinity(group, point)) {
|
|
|
|
OPENSSL_PUT_ERROR(EC, EC_R_POINT_AT_INFINITY);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2016-03-12 00:04:14 +00:00
|
|
|
BN_CTX *new_ctx = NULL;
|
2016-03-11 23:12:11 +00:00
|
|
|
if (ctx == NULL) {
|
|
|
|
ctx = new_ctx = BN_CTX_new();
|
|
|
|
if (ctx == NULL) {
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-03-12 00:04:14 +00:00
|
|
|
int ret = 0;
|
2016-03-11 23:12:11 +00:00
|
|
|
|
2016-03-12 00:04:14 +00:00
|
|
|
BN_CTX_start(ctx);
|
2016-03-11 23:12:11 +00:00
|
|
|
|
2016-03-12 00:04:14 +00:00
|
|
|
if (BN_cmp(&point->Z, &group->one) == 0) {
|
2017-08-18 19:06:02 +01:00
|
|
|
// |point| is already affine.
|
2016-03-12 00:04:14 +00:00
|
|
|
if (x != NULL && !BN_from_montgomery(x, &point->X, group->mont, ctx)) {
|
2016-03-11 23:19:14 +00:00
|
|
|
goto err;
|
|
|
|
}
|
2016-03-12 00:04:14 +00:00
|
|
|
if (y != NULL && !BN_from_montgomery(y, &point->Y, group->mont, ctx)) {
|
2016-03-11 23:19:14 +00:00
|
|
|
goto err;
|
2016-03-11 23:12:11 +00:00
|
|
|
}
|
|
|
|
} else {
|
2017-08-18 19:06:02 +01:00
|
|
|
// transform (X, Y, Z) into (x, y) := (X/Z^2, Y/Z^3)
|
2016-03-12 00:04:14 +00:00
|
|
|
|
|
|
|
BIGNUM *Z_1 = BN_CTX_get(ctx);
|
|
|
|
BIGNUM *Z_2 = BN_CTX_get(ctx);
|
|
|
|
BIGNUM *Z_3 = BN_CTX_get(ctx);
|
|
|
|
if (Z_1 == NULL ||
|
|
|
|
Z_2 == NULL ||
|
2016-12-17 19:27:16 +00:00
|
|
|
Z_3 == NULL) {
|
2016-03-11 23:12:11 +00:00
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
|
2017-08-18 19:06:02 +01:00
|
|
|
// The straightforward way to calculate the inverse of a Montgomery-encoded
|
|
|
|
// value where the result is Montgomery-encoded is:
|
|
|
|
//
|
|
|
|
// |BN_from_montgomery| + invert + |BN_to_montgomery|.
|
|
|
|
//
|
|
|
|
// This is equivalent, but more efficient, because |BN_from_montgomery|
|
|
|
|
// is more efficient (at least in theory) than |BN_to_montgomery|, since it
|
|
|
|
// doesn't have to do the multiplication before the reduction.
|
|
|
|
//
|
|
|
|
// Use Fermat's Little Theorem instead of |BN_mod_inverse_odd| since this
|
|
|
|
// inversion may be done as the final step of private key operations.
|
|
|
|
// Unfortunately, this is suboptimal for ECDSA verification.
|
2016-03-12 00:04:14 +00:00
|
|
|
if (!BN_from_montgomery(Z_1, &point->Z, group->mont, ctx) ||
|
|
|
|
!BN_from_montgomery(Z_1, Z_1, group->mont, ctx) ||
|
2016-12-17 19:27:16 +00:00
|
|
|
!bn_mod_inverse_prime(Z_1, Z_1, &group->field, ctx, group->mont)) {
|
2016-03-11 23:12:11 +00:00
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
|
2016-03-12 00:04:14 +00:00
|
|
|
if (!BN_mod_mul_montgomery(Z_2, Z_1, Z_1, group->mont, ctx)) {
|
2016-03-11 23:12:11 +00:00
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
|
2017-08-18 19:06:02 +01:00
|
|
|
// Instead of using |BN_from_montgomery| to convert the |x| coordinate
|
|
|
|
// and then calling |BN_from_montgomery| again to convert the |y|
|
|
|
|
// coordinate below, convert the common factor |Z_2| once now, saving one
|
|
|
|
// reduction.
|
2016-03-12 00:04:14 +00:00
|
|
|
if (!BN_from_montgomery(Z_2, Z_2, group->mont, ctx)) {
|
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (x != NULL) {
|
|
|
|
if (!BN_mod_mul_montgomery(x, &point->X, Z_2, group->mont, ctx)) {
|
2016-03-11 23:12:11 +00:00
|
|
|
goto err;
|
|
|
|
}
|
2016-03-12 00:04:14 +00:00
|
|
|
}
|
2016-03-11 23:12:11 +00:00
|
|
|
|
2016-03-12 00:04:14 +00:00
|
|
|
if (y != NULL) {
|
|
|
|
if (!BN_mod_mul_montgomery(Z_3, Z_2, Z_1, group->mont, ctx) ||
|
|
|
|
!BN_mod_mul_montgomery(y, &point->Y, Z_3, group->mont, ctx)) {
|
2016-03-11 23:12:11 +00:00
|
|
|
goto err;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = 1;
|
|
|
|
|
|
|
|
err:
|
|
|
|
BN_CTX_end(ctx);
|
|
|
|
BN_CTX_free(new_ctx);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2017-05-02 22:25:39 +01:00
|
|
|
DEFINE_METHOD_FUNCTION(EC_METHOD, EC_GFp_mont_method) {
|
|
|
|
out->group_init = ec_GFp_mont_group_init;
|
|
|
|
out->group_finish = ec_GFp_mont_group_finish;
|
|
|
|
out->group_set_curve = ec_GFp_mont_group_set_curve;
|
|
|
|
out->point_get_affine_coordinates = ec_GFp_mont_point_get_affine_coordinates;
|
|
|
|
out->mul = ec_wNAF_mul /* XXX: Not constant time. */;
|
ec/p256.c: fiat-crypto field arithmetic (64, 32)
The fiat-crypto-generated code uses the Montgomery form implementation
strategy, for both 32-bit and 64-bit code.
64-bit throughput seems slower, but the difference is smaller than noise between repetitions (-2%?)
32-bit throughput has decreased significantly for ECDH (-40%). I am
attributing this to the change from varibale-time scalar multiplication
to constant-time scalar multiplication. Due to the same bottleneck,
ECDSA verification still uses the old code (otherwise there would have
been a 60% throughput decrease). On the other hand, ECDSA signing
throughput has increased slightly (+10%), perhaps due to the use of a
precomputed table of multiples of the base point.
64-bit benchmarks (Google Cloud Haswell):
with this change:
Did 9126 ECDH P-256 operations in 1009572us (9039.5 ops/sec)
Did 23000 ECDSA P-256 signing operations in 1039832us (22119.0 ops/sec)
Did 8820 ECDSA P-256 verify operations in 1024242us (8611.2 ops/sec)
master (40e8c921cab5cce2bc10722ecf4ebe0e380cf6c8):
Did 9340 ECDH P-256 operations in 1017975us (9175.1 ops/sec)
Did 23000 ECDSA P-256 signing operations in 1039820us (22119.2 ops/sec)
Did 8688 ECDSA P-256 verify operations in 1021108us (8508.4 ops/sec)
benchmarks on ARMv7 (LG Nexus 4):
with this change:
Did 150 ECDH P-256 operations in 1029726us (145.7 ops/sec)
Did 506 ECDSA P-256 signing operations in 1065192us (475.0 ops/sec)
Did 363 ECDSA P-256 verify operations in 1033298us (351.3 ops/sec)
master (2fce1beda0f7e74e2d687860f807cf0b8d8056a4):
Did 245 ECDH P-256 operations in 1017518us (240.8 ops/sec)
Did 473 ECDSA P-256 signing operations in 1086281us (435.4 ops/sec)
Did 360 ECDSA P-256 verify operations in 1003846us (358.6 ops/sec)
64-bit tables converted as follows:
import re, sys, math
p = 2**256 - 2**224 + 2**192 + 2**96 - 1
R = 2**256
def convert(t):
x0, s1, x1, s2, x2, s3, x3 = t.groups()
v = int(x0, 0) + 2**64 * (int(x1, 0) + 2**64*(int(x2,0) + 2**64*(int(x3, 0)) ))
w = v*R%p
y0 = hex(w%(2**64))
y1 = hex((w>>64)%(2**64))
y2 = hex((w>>(2*64))%(2**64))
y3 = hex((w>>(3*64))%(2**64))
ww = int(y0, 0) + 2**64 * (int(y1, 0) + 2**64*(int(y2,0) + 2**64*(int(y3, 0)) ))
if ww != v*R%p:
print(x0,x1,x2,x3)
print(hex(v))
print(y0,y1,y2,y3)
print(hex(w))
print(hex(ww))
assert 0
return '{'+y0+s1+y1+s2+y2+s3+y3+'}'
fe_re = re.compile('{'+r'(\s*,\s*)'.join(r'(\d+|0x[abcdefABCDEF0123456789]+)' for i in range(4)) + '}')
print (re.sub(fe_re, convert, sys.stdin.read()).rstrip('\n'))
32-bit tables converted from 64-bit tables
Change-Id: I52d6e5504fcb6ca2e8b0ee13727f4500c80c1799
Reviewed-on: https://boringssl-review.googlesource.com/23244
Commit-Queue: Adam Langley <agl@google.com>
Reviewed-by: Adam Langley <agl@google.com>
CQ-Verified: CQ bot account: commit-bot@chromium.org <commit-bot@chromium.org>
2017-11-08 20:32:38 +00:00
|
|
|
out->mul_public = ec_wNAF_mul;
|
2017-05-02 22:25:39 +01:00
|
|
|
out->field_mul = ec_GFp_mont_field_mul;
|
|
|
|
out->field_sqr = ec_GFp_mont_field_sqr;
|
|
|
|
out->field_encode = ec_GFp_mont_field_encode;
|
|
|
|
out->field_decode = ec_GFp_mont_field_decode;
|
2018-04-07 00:43:29 +01:00
|
|
|
out->scalar_inv_montgomery = ec_simple_scalar_inv_montgomery;
|
2017-05-02 22:25:39 +01:00
|
|
|
}
|