From: Niels Möller <nisse@lysator.liu.se>
Date: Sun, 5 Dec 2021 16:06:58 +0000 (+0100)
Subject: arm64: Implement ecc_secp256r1_redc.
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=5ee0839bb28c092044fce09534651b78640518c4;p=thirdparty%2Fnettle.git

arm64: Implement ecc_secp256r1_redc.
---

diff --git a/ChangeLog b/ChangeLog
index 45259369..9f8012c3 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,7 @@
+2021-12-05  Niels Möller  <nisse@lysator.liu.se>
+
+	* arm64/ecc-secp256r1-redc.asm: New file.
+
 2021-11-19  Niels Möller  <nisse@lysator.liu.se>
 
 	* gmp-glue.c (mpz_limbs_cmp): Deleted function. Usage replaced
diff --git a/arm64/ecc-secp256r1-redc.asm b/arm64/ecc-secp256r1-redc.asm
new file mode 100644
index 00000000..47df9de3
--- /dev/null
+++ b/arm64/ecc-secp256r1-redc.asm
@@ -0,0 +1,120 @@
+C arm64/ecc-secp256r1-redc.asm
+
+ifelse(`
+   Copyright (C) 2013, 2021 Niels Möller
+
+   This file is part of GNU Nettle.
+
+   GNU Nettle is free software: you can redistribute it and/or
+   modify it under the terms of either:
+
+     * the GNU Lesser General Public License as published by the Free
+       Software Foundation; either version 3 of the License, or (at your
+       option) any later version.
+
+   or
+
+     * the GNU General Public License as published by the Free
+       Software Foundation; either version 2 of the License, or (at your
+       option) any later version.
+
+   or both in parallel, as here.
+
+   GNU Nettle is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   You should have received copies of the GNU General Public License and
+   the GNU Lesser General Public License along with this program.  If
+   not, see http://www.gnu.org/licenses/.
+')
+
+	.file "ecc-secp256r1-redc.asm"
+
+define(`RP', `x1')
+define(`XP', `x2')
+
+define(`U0', `x0') C Overlaps unused modulo input
+define(`U1', `x3')
+define(`U2', `x4')
+define(`U3', `x5')
+define(`U4', `x6')
+define(`U5', `x7')
+define(`U6', `x8')
+define(`U7', `x9')
+define(`F0', `x10')
+define(`F1', `x11')
+define(`F2', `x12')
+define(`F3', `x13')
+define(`ZERO', `x14')
+
+C FOLD(x), sets (F3, F2,F1,F0 )  <--  (x << 192) - (x << 160) + (x << 128) + (x << 32)
+define(`FOLD', `
+	lsl	F0, $1, #32
+	lsr	F1, $1, #32
+	subs	F2, $1, F0
+	sbc	F3, $1, F1
+')
+PROLOGUE(_nettle_ecc_secp256r1_redc)
+	ldr	U0, [XP]
+	ldr	U1, [XP, #8]
+	ldr	U2, [XP, #16]
+	ldr	U3, [XP, #24]
+	ldr	U4, [XP, #32]
+	ldr	U5, [XP, #40]
+	ldr	U6, [XP, #48]
+	ldr	U7, [XP, #56]
+	mov	ZERO, #0
+
+	FOLD(U0)
+	adds	U1, U1, F0
+	adcs	U2, U2, F1
+	adcs	U3, U3, F2
+	adc	U0, ZERO, F3
+
+	FOLD(U1)
+	adds	U2, U2, F0
+	adcs	U3, U3, F1
+	adcs	U4, U4, F2
+	adc	U1, ZERO, F3
+
+	FOLD(U2)
+	adds	U3, U3, F0
+	adcs	U4, U4, F1
+	adcs	U5, U5, F2
+	adc	U2, ZERO, F3
+
+	FOLD(U3)
+	adds	U4, U4, F0
+	adcs	U5, U5, F1
+	adcs	U6, U6, F2
+	adc	U3, ZERO, F3
+
+	adds	U0, U4, U0
+	adcs	U1, U5, U1
+	adcs	U2, U6, U2
+	adcs	U3, U7, U3
+
+	C Sum, including carry, is < 2^{256} + p.
+	C If carry, we need to add in 2^{256} mod p = 2^{256} - p
+	C     = <0xfffffffe, 0xff..ff, 0xffffffff00000000, 1>
+	C and this addition can not overflow.
+	adc	F0, ZERO, ZERO
+	neg	F2, F0
+	lsl	F1, F2, #32
+	lsr	F3, F2, #32
+	and	F3, F3, #-2
+
+	adds	U0, F0, U0
+	adcs	U1, F1, U1
+	adcs	U2, F2, U2
+	adc	U3, F3, U3
+
+	str	U0, [RP]
+	str	U1, [RP, #8]
+	str	U2, [RP, #16]
+	str	U3, [RP, #24]
+
+	ret
+EPILOGUE(_nettle_ecc_secp256r1_redc)