Upload Kmake

deps/openssl/config/archs/linux-aarch64/asm/crypto/arm64cpuid.S

@@ -0,0 +1,129 @@
+#include "arm_arch.h"
+
+.text
+.arch	armv8-a+crypto
+
+.align	5
+.globl	_armv7_neon_probe
+.type	_armv7_neon_probe,%function
+_armv7_neon_probe:
+	orr	v15.16b, v15.16b, v15.16b
+	ret
+.size	_armv7_neon_probe,.-_armv7_neon_probe
+
+.globl	_armv7_tick
+.type	_armv7_tick,%function
+_armv7_tick:
+#ifdef	__APPLE__
+	mrs	x0, CNTPCT_EL0
+#else
+	mrs	x0, CNTVCT_EL0
+#endif
+	ret
+.size	_armv7_tick,.-_armv7_tick
+
+.globl	_armv8_aes_probe
+.type	_armv8_aes_probe,%function
+_armv8_aes_probe:
+	aese	v0.16b, v0.16b
+	ret
+.size	_armv8_aes_probe,.-_armv8_aes_probe
+
+.globl	_armv8_sha1_probe
+.type	_armv8_sha1_probe,%function
+_armv8_sha1_probe:
+	sha1h	s0, s0
+	ret
+.size	_armv8_sha1_probe,.-_armv8_sha1_probe
+
+.globl	_armv8_sha256_probe
+.type	_armv8_sha256_probe,%function
+_armv8_sha256_probe:
+	sha256su0	v0.4s, v0.4s
+	ret
+.size	_armv8_sha256_probe,.-_armv8_sha256_probe
+
+.globl	_armv8_pmull_probe
+.type	_armv8_pmull_probe,%function
+_armv8_pmull_probe:
+	pmull	v0.1q, v0.1d, v0.1d
+	ret
+.size	_armv8_pmull_probe,.-_armv8_pmull_probe
+
+.globl	_armv8_sha512_probe
+.type	_armv8_sha512_probe,%function
+_armv8_sha512_probe:
+.long	0xcec08000	// sha512su0	v0.2d,v0.2d
+	ret
+.size	_armv8_sha512_probe,.-_armv8_sha512_probe
+
+.globl	_armv8_cpuid_probe
+.type	_armv8_cpuid_probe,%function
+_armv8_cpuid_probe:
+	mrs	x0, midr_el1
+	ret
+.size	_armv8_cpuid_probe,.-_armv8_cpuid_probe
+
+.globl	OPENSSL_cleanse
+.type	OPENSSL_cleanse,%function
+.align	5
+OPENSSL_cleanse:
+	cbz	x1,.Lret	// len==0?
+	cmp	x1,#15
+	b.hi	.Lot		// len>15
+	nop
+.Little:
+	strb	wzr,[x0],#1	// store byte-by-byte
+	subs	x1,x1,#1
+	b.ne	.Little
+.Lret:	ret
+
+.align	4
+.Lot:	tst	x0,#7
+	b.eq	.Laligned	// inp is aligned
+	strb	wzr,[x0],#1	// store byte-by-byte
+	sub	x1,x1,#1
+	b	.Lot
+
+.align	4
+.Laligned:
+	str	xzr,[x0],#8	// store word-by-word
+	sub	x1,x1,#8
+	tst	x1,#-8
+	b.ne	.Laligned	// len>=8
+	cbnz	x1,.Little	// len!=0?
+	ret
+.size	OPENSSL_cleanse,.-OPENSSL_cleanse
+
+.globl	CRYPTO_memcmp
+.type	CRYPTO_memcmp,%function
+.align	4
+CRYPTO_memcmp:
+	eor	w3,w3,w3
+	cbz	x2,.Lno_data	// len==0?
+	cmp	x2,#16
+	b.ne	.Loop_cmp
+	ldp	x8,x9,[x0]
+	ldp	x10,x11,[x1]
+	eor	x8,x8,x10
+	eor	x9,x9,x11
+	orr	x8,x8,x9
+	mov	x0,#1
+	cmp	x8,#0
+	csel	x0,xzr,x0,eq
+	ret
+
+.align	4
+.Loop_cmp:
+	ldrb	w4,[x0],#1
+	ldrb	w5,[x1],#1
+	eor	w4,w4,w5
+	orr	w3,w3,w4
+	subs	x2,x2,#1
+	b.ne	.Loop_cmp
+
+.Lno_data:
+	neg	w0,w3
+	lsr	w0,w0,#31
+	ret
+.size	CRYPTO_memcmp,.-CRYPTO_memcmp

deps/openssl/config/archs/linux-aarch64/asm/crypto/buildinf.h

@@ -0,0 +1,31 @@
+/*
+ * WARNING: do not edit!
+ * Generated by util/mkbuildinf.pl
+ *
+ * Copyright 2014-2025 The OpenSSL Project Authors. All Rights Reserved.
+ *
+ * Licensed under the Apache License 2.0 (the "License").  You may not use
+ * this file except in compliance with the License.  You can obtain a copy
+ * in the file LICENSE in the source distribution or at
+ * https://www.openssl.org/source/license.html
+ */
+
+#define PLATFORM "platform: linux-aarch64"
+#define DATE "built on: Wed Mar  5 21:02:14 2025 UTC"
+
+/*
+ * Generate compiler_flags as an array of individual characters. This is a
+ * workaround for the situation where CFLAGS gets too long for a C90 string
+ * literal
+ */
+static const char compiler_flags[] = {
+    'c','o','m','p','i','l','e','r',':',' ','g','c','c',' ','-','f',
+    'P','I','C',' ','-','p','t','h','r','e','a','d',' ','-','W','a',
+    ',','-','-','n','o','e','x','e','c','s','t','a','c','k',' ','-',
+    'W','a','l','l',' ','-','O','3',' ','-','D','O','P','E','N','S',
+    'S','L','_','U','S','E','_','N','O','D','E','L','E','T','E',' ',
+    '-','D','O','P','E','N','S','S','L','_','P','I','C',' ','-','D',
+    'O','P','E','N','S','S','L','_','B','U','I','L','D','I','N','G',
+    '_','O','P','E','N','S','S','L',' ','-','D','N','D','E','B','U',
+    'G','\0'
+};

deps/openssl/config/archs/linux-aarch64/asm/crypto/modes/ghashv8-armx.S

@@ -0,0 +1,552 @@
+#include "arm_arch.h"
+
+#if __ARM_MAX_ARCH__>=7
+.arch	armv8-a+crypto
+.text
+.globl	gcm_init_v8
+.type	gcm_init_v8,%function
+.align	4
+gcm_init_v8:
+	ld1	{v17.2d},[x1]		//load input H
+	movi	v19.16b,#0xe1
+	shl	v19.2d,v19.2d,#57		//0xc2.0
+	ext	v3.16b,v17.16b,v17.16b,#8
+	ushr	v18.2d,v19.2d,#63
+	dup	v17.4s,v17.s[1]
+	ext	v16.16b,v18.16b,v19.16b,#8		//t0=0xc2....01
+	ushr	v18.2d,v3.2d,#63
+	sshr	v17.4s,v17.4s,#31		//broadcast carry bit
+	and	v18.16b,v18.16b,v16.16b
+	shl	v3.2d,v3.2d,#1
+	ext	v18.16b,v18.16b,v18.16b,#8
+	and	v16.16b,v16.16b,v17.16b
+	orr	v3.16b,v3.16b,v18.16b		//H<<<=1
+	eor	v20.16b,v3.16b,v16.16b		//twisted H
+	st1	{v20.2d},[x0],#16		//store Htable[0]
+
+	//calculate H^2
+	ext	v16.16b,v20.16b,v20.16b,#8		//Karatsuba pre-processing
+	pmull	v0.1q,v20.1d,v20.1d
+	eor	v16.16b,v16.16b,v20.16b
+	pmull2	v2.1q,v20.2d,v20.2d
+	pmull	v1.1q,v16.1d,v16.1d
+
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v17.16b
+	eor	v1.16b,v1.16b,v18.16b
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase
+
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	eor	v0.16b,v1.16b,v18.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase
+	pmull	v0.1q,v0.1d,v19.1d
+	eor	v18.16b,v18.16b,v2.16b
+	eor	v22.16b,v0.16b,v18.16b
+
+	ext	v17.16b,v22.16b,v22.16b,#8		//Karatsuba pre-processing
+	eor	v17.16b,v17.16b,v22.16b
+	ext	v21.16b,v16.16b,v17.16b,#8		//pack Karatsuba pre-processed
+	st1	{v21.2d,v22.2d},[x0],#32	//store Htable[1..2]
+	//calculate H^3 and H^4
+	pmull	v0.1q,v20.1d, v22.1d
+	pmull	v5.1q,v22.1d,v22.1d
+	pmull2	v2.1q,v20.2d, v22.2d
+	pmull2	v7.1q,v22.2d,v22.2d
+	pmull	v1.1q,v16.1d,v17.1d
+	pmull	v6.1q,v17.1d,v17.1d
+
+	ext	v16.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	ext	v17.16b,v5.16b,v7.16b,#8
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v16.16b
+	eor	v4.16b,v5.16b,v7.16b
+	eor	v6.16b,v6.16b,v17.16b
+	eor	v1.16b,v1.16b,v18.16b
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase
+	eor	v6.16b,v6.16b,v4.16b
+	pmull	v4.1q,v5.1d,v19.1d
+
+	ins	v2.d[0],v1.d[1]
+	ins	v7.d[0],v6.d[1]
+	ins	v1.d[1],v0.d[0]
+	ins	v6.d[1],v5.d[0]
+	eor	v0.16b,v1.16b,v18.16b
+	eor	v5.16b,v6.16b,v4.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase
+	ext	v4.16b,v5.16b,v5.16b,#8
+	pmull	v0.1q,v0.1d,v19.1d
+	pmull	v5.1q,v5.1d,v19.1d
+	eor	v18.16b,v18.16b,v2.16b
+	eor	v4.16b,v4.16b,v7.16b
+	eor	v20.16b, v0.16b,v18.16b		//H^3
+	eor	v22.16b,v5.16b,v4.16b		//H^4
+
+	ext	v16.16b,v20.16b, v20.16b,#8		//Karatsuba pre-processing
+	ext	v17.16b,v22.16b,v22.16b,#8
+	eor	v16.16b,v16.16b,v20.16b
+	eor	v17.16b,v17.16b,v22.16b
+	ext	v21.16b,v16.16b,v17.16b,#8		//pack Karatsuba pre-processed
+	st1	{v20.2d,v21.2d,v22.2d},[x0]		//store Htable[3..5]
+	ret
+.size	gcm_init_v8,.-gcm_init_v8
+.globl	gcm_gmult_v8
+.type	gcm_gmult_v8,%function
+.align	4
+gcm_gmult_v8:
+	ld1	{v17.2d},[x0]		//load Xi
+	movi	v19.16b,#0xe1
+	ld1	{v20.2d,v21.2d},[x1]	//load twisted H, ...
+	shl	v19.2d,v19.2d,#57
+#ifndef __AARCH64EB__
+	rev64	v17.16b,v17.16b
+#endif
+	ext	v3.16b,v17.16b,v17.16b,#8
+
+	pmull	v0.1q,v20.1d,v3.1d		//H.lo·Xi.lo
+	eor	v17.16b,v17.16b,v3.16b		//Karatsuba pre-processing
+	pmull2	v2.1q,v20.2d,v3.2d		//H.hi·Xi.hi
+	pmull	v1.1q,v21.1d,v17.1d		//(H.lo+H.hi)·(Xi.lo+Xi.hi)
+
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v17.16b
+	eor	v1.16b,v1.16b,v18.16b
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase of reduction
+
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	eor	v0.16b,v1.16b,v18.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
+	pmull	v0.1q,v0.1d,v19.1d
+	eor	v18.16b,v18.16b,v2.16b
+	eor	v0.16b,v0.16b,v18.16b
+
+#ifndef __AARCH64EB__
+	rev64	v0.16b,v0.16b
+#endif
+	ext	v0.16b,v0.16b,v0.16b,#8
+	st1	{v0.2d},[x0]		//write out Xi
+
+	ret
+.size	gcm_gmult_v8,.-gcm_gmult_v8
+.globl	gcm_ghash_v8
+.type	gcm_ghash_v8,%function
+.align	4
+gcm_ghash_v8:
+	cmp	x3,#64
+	b.hs	.Lgcm_ghash_v8_4x
+	ld1	{v0.2d},[x0]		//load [rotated] Xi
+						//"[rotated]" means that
+						//loaded value would have
+						//to be rotated in order to
+						//make it appear as in
+						//algorithm specification
+	subs	x3,x3,#32		//see if x3 is 32 or larger
+	mov	x12,#16		//x12 is used as post-
+						//increment for input pointer;
+						//as loop is modulo-scheduled
+						//x12 is zeroed just in time
+						//to preclude overstepping
+						//inp[len], which means that
+						//last block[s] are actually
+						//loaded twice, but last
+						//copy is not processed
+	ld1	{v20.2d,v21.2d},[x1],#32	//load twisted H, ..., H^2
+	movi	v19.16b,#0xe1
+	ld1	{v22.2d},[x1]
+	csel	x12,xzr,x12,eq			//is it time to zero x12?
+	ext	v0.16b,v0.16b,v0.16b,#8		//rotate Xi
+	ld1	{v16.2d},[x2],#16	//load [rotated] I[0]
+	shl	v19.2d,v19.2d,#57		//compose 0xc2.0 constant
+#ifndef __AARCH64EB__
+	rev64	v16.16b,v16.16b
+	rev64	v0.16b,v0.16b
+#endif
+	ext	v3.16b,v16.16b,v16.16b,#8		//rotate I[0]
+	b.lo	.Lodd_tail_v8		//x3 was less than 32
+	ld1	{v17.2d},[x2],x12	//load [rotated] I[1]
+#ifndef __AARCH64EB__
+	rev64	v17.16b,v17.16b
+#endif
+	ext	v7.16b,v17.16b,v17.16b,#8
+	eor	v3.16b,v3.16b,v0.16b		//I[i]^=Xi
+	pmull	v4.1q,v20.1d,v7.1d		//H·Ii+1
+	eor	v17.16b,v17.16b,v7.16b		//Karatsuba pre-processing
+	pmull2	v6.1q,v20.2d,v7.2d
+	b	.Loop_mod2x_v8
+
+.align	4
+.Loop_mod2x_v8:
+	ext	v18.16b,v3.16b,v3.16b,#8
+	subs	x3,x3,#32		//is there more data?
+	pmull	v0.1q,v22.1d,v3.1d		//H^2.lo·Xi.lo
+	csel	x12,xzr,x12,lo			//is it time to zero x12?
+
+	pmull	v5.1q,v21.1d,v17.1d
+	eor	v18.16b,v18.16b,v3.16b		//Karatsuba pre-processing
+	pmull2	v2.1q,v22.2d,v3.2d		//H^2.hi·Xi.hi
+	eor	v0.16b,v0.16b,v4.16b		//accumulate
+	pmull2	v1.1q,v21.2d,v18.2d		//(H^2.lo+H^2.hi)·(Xi.lo+Xi.hi)
+	ld1	{v16.2d},[x2],x12	//load [rotated] I[i+2]
+
+	eor	v2.16b,v2.16b,v6.16b
+	csel	x12,xzr,x12,eq			//is it time to zero x12?
+	eor	v1.16b,v1.16b,v5.16b
+
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v17.16b
+	ld1	{v17.2d},[x2],x12	//load [rotated] I[i+3]
+#ifndef __AARCH64EB__
+	rev64	v16.16b,v16.16b
+#endif
+	eor	v1.16b,v1.16b,v18.16b
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase of reduction
+
+#ifndef __AARCH64EB__
+	rev64	v17.16b,v17.16b
+#endif
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	ext	v7.16b,v17.16b,v17.16b,#8
+	ext	v3.16b,v16.16b,v16.16b,#8
+	eor	v0.16b,v1.16b,v18.16b
+	pmull	v4.1q,v20.1d,v7.1d		//H·Ii+1
+	eor	v3.16b,v3.16b,v2.16b		//accumulate v3.16b early
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
+	pmull	v0.1q,v0.1d,v19.1d
+	eor	v3.16b,v3.16b,v18.16b
+	eor	v17.16b,v17.16b,v7.16b		//Karatsuba pre-processing
+	eor	v3.16b,v3.16b,v0.16b
+	pmull2	v6.1q,v20.2d,v7.2d
+	b.hs	.Loop_mod2x_v8		//there was at least 32 more bytes
+
+	eor	v2.16b,v2.16b,v18.16b
+	ext	v3.16b,v16.16b,v16.16b,#8		//re-construct v3.16b
+	adds	x3,x3,#32		//re-construct x3
+	eor	v0.16b,v0.16b,v2.16b		//re-construct v0.16b
+	b.eq	.Ldone_v8		//is x3 zero?
+.Lodd_tail_v8:
+	ext	v18.16b,v0.16b,v0.16b,#8
+	eor	v3.16b,v3.16b,v0.16b		//inp^=Xi
+	eor	v17.16b,v16.16b,v18.16b		//v17.16b is rotated inp^Xi
+
+	pmull	v0.1q,v20.1d,v3.1d		//H.lo·Xi.lo
+	eor	v17.16b,v17.16b,v3.16b		//Karatsuba pre-processing
+	pmull2	v2.1q,v20.2d,v3.2d		//H.hi·Xi.hi
+	pmull	v1.1q,v21.1d,v17.1d		//(H.lo+H.hi)·(Xi.lo+Xi.hi)
+
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v17.16b
+	eor	v1.16b,v1.16b,v18.16b
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase of reduction
+
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	eor	v0.16b,v1.16b,v18.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
+	pmull	v0.1q,v0.1d,v19.1d
+	eor	v18.16b,v18.16b,v2.16b
+	eor	v0.16b,v0.16b,v18.16b
+
+.Ldone_v8:
+#ifndef __AARCH64EB__
+	rev64	v0.16b,v0.16b
+#endif
+	ext	v0.16b,v0.16b,v0.16b,#8
+	st1	{v0.2d},[x0]		//write out Xi
+
+	ret
+.size	gcm_ghash_v8,.-gcm_ghash_v8
+.type	gcm_ghash_v8_4x,%function
+.align	4
+gcm_ghash_v8_4x:
+.Lgcm_ghash_v8_4x:
+	ld1	{v0.2d},[x0]		//load [rotated] Xi
+	ld1	{v20.2d,v21.2d,v22.2d},[x1],#48	//load twisted H, ..., H^2
+	movi	v19.16b,#0xe1
+	ld1	{v26.2d,v27.2d,v28.2d},[x1]	//load twisted H^3, ..., H^4
+	shl	v19.2d,v19.2d,#57		//compose 0xc2.0 constant
+
+	ld1	{v4.2d,v5.2d,v6.2d,v7.2d},[x2],#64
+#ifndef __AARCH64EB__
+	rev64	v0.16b,v0.16b
+	rev64	v5.16b,v5.16b
+	rev64	v6.16b,v6.16b
+	rev64	v7.16b,v7.16b
+	rev64	v4.16b,v4.16b
+#endif
+	ext	v25.16b,v7.16b,v7.16b,#8
+	ext	v24.16b,v6.16b,v6.16b,#8
+	ext	v23.16b,v5.16b,v5.16b,#8
+
+	pmull	v29.1q,v20.1d,v25.1d		//H·Ii+3
+	eor	v7.16b,v7.16b,v25.16b
+	pmull2	v31.1q,v20.2d,v25.2d
+	pmull	v30.1q,v21.1d,v7.1d
+
+	pmull	v16.1q,v22.1d,v24.1d		//H^2·Ii+2
+	eor	v6.16b,v6.16b,v24.16b
+	pmull2	v24.1q,v22.2d,v24.2d
+	pmull2	v6.1q,v21.2d,v6.2d
+
+	eor	v29.16b,v29.16b,v16.16b
+	eor	v31.16b,v31.16b,v24.16b
+	eor	v30.16b,v30.16b,v6.16b
+
+	pmull	v7.1q,v26.1d,v23.1d		//H^3·Ii+1
+	eor	v5.16b,v5.16b,v23.16b
+	pmull2	v23.1q,v26.2d,v23.2d
+	pmull	v5.1q,v27.1d,v5.1d
+
+	eor	v29.16b,v29.16b,v7.16b
+	eor	v31.16b,v31.16b,v23.16b
+	eor	v30.16b,v30.16b,v5.16b
+
+	subs	x3,x3,#128
+	b.lo	.Ltail4x
+
+	b	.Loop4x
+
+.align	4
+.Loop4x:
+	eor	v16.16b,v4.16b,v0.16b
+	ld1	{v4.2d,v5.2d,v6.2d,v7.2d},[x2],#64
+	ext	v3.16b,v16.16b,v16.16b,#8
+#ifndef __AARCH64EB__
+	rev64	v5.16b,v5.16b
+	rev64	v6.16b,v6.16b
+	rev64	v7.16b,v7.16b
+	rev64	v4.16b,v4.16b
+#endif
+
+	pmull	v0.1q,v28.1d,v3.1d		//H^4·(Xi+Ii)
+	eor	v16.16b,v16.16b,v3.16b
+	pmull2	v2.1q,v28.2d,v3.2d
+	ext	v25.16b,v7.16b,v7.16b,#8
+	pmull2	v1.1q,v27.2d,v16.2d
+
+	eor	v0.16b,v0.16b,v29.16b
+	eor	v2.16b,v2.16b,v31.16b
+	ext	v24.16b,v6.16b,v6.16b,#8
+	eor	v1.16b,v1.16b,v30.16b
+	ext	v23.16b,v5.16b,v5.16b,#8
+
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	pmull	v29.1q,v20.1d,v25.1d		//H·Ii+3
+	eor	v7.16b,v7.16b,v25.16b
+	eor	v1.16b,v1.16b,v17.16b
+	pmull2	v31.1q,v20.2d,v25.2d
+	eor	v1.16b,v1.16b,v18.16b
+	pmull	v30.1q,v21.1d,v7.1d
+
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase of reduction
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	pmull	v16.1q,v22.1d,v24.1d		//H^2·Ii+2
+	eor	v6.16b,v6.16b,v24.16b
+	pmull2	v24.1q,v22.2d,v24.2d
+	eor	v0.16b,v1.16b,v18.16b
+	pmull2	v6.1q,v21.2d,v6.2d
+
+	eor	v29.16b,v29.16b,v16.16b
+	eor	v31.16b,v31.16b,v24.16b
+	eor	v30.16b,v30.16b,v6.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
+	pmull	v0.1q,v0.1d,v19.1d
+	pmull	v7.1q,v26.1d,v23.1d		//H^3·Ii+1
+	eor	v5.16b,v5.16b,v23.16b
+	eor	v18.16b,v18.16b,v2.16b
+	pmull2	v23.1q,v26.2d,v23.2d
+	pmull	v5.1q,v27.1d,v5.1d
+
+	eor	v0.16b,v0.16b,v18.16b
+	eor	v29.16b,v29.16b,v7.16b
+	eor	v31.16b,v31.16b,v23.16b
+	ext	v0.16b,v0.16b,v0.16b,#8
+	eor	v30.16b,v30.16b,v5.16b
+
+	subs	x3,x3,#64
+	b.hs	.Loop4x
+
+.Ltail4x:
+	eor	v16.16b,v4.16b,v0.16b
+	ext	v3.16b,v16.16b,v16.16b,#8
+
+	pmull	v0.1q,v28.1d,v3.1d		//H^4·(Xi+Ii)
+	eor	v16.16b,v16.16b,v3.16b
+	pmull2	v2.1q,v28.2d,v3.2d
+	pmull2	v1.1q,v27.2d,v16.2d
+
+	eor	v0.16b,v0.16b,v29.16b
+	eor	v2.16b,v2.16b,v31.16b
+	eor	v1.16b,v1.16b,v30.16b
+
+	adds	x3,x3,#64
+	b.eq	.Ldone4x
+
+	cmp	x3,#32
+	b.lo	.Lone
+	b.eq	.Ltwo
+.Lthree:
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v17.16b
+	ld1	{v4.2d,v5.2d,v6.2d},[x2]
+	eor	v1.16b,v1.16b,v18.16b
+#ifndef	__AARCH64EB__
+	rev64	v5.16b,v5.16b
+	rev64	v6.16b,v6.16b
+	rev64	v4.16b,v4.16b
+#endif
+
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase of reduction
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	ext	v24.16b,v6.16b,v6.16b,#8
+	ext	v23.16b,v5.16b,v5.16b,#8
+	eor	v0.16b,v1.16b,v18.16b
+
+	pmull	v29.1q,v20.1d,v24.1d		//H·Ii+2
+	eor	v6.16b,v6.16b,v24.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
+	pmull	v0.1q,v0.1d,v19.1d
+	eor	v18.16b,v18.16b,v2.16b
+	pmull2	v31.1q,v20.2d,v24.2d
+	pmull	v30.1q,v21.1d,v6.1d
+	eor	v0.16b,v0.16b,v18.16b
+	pmull	v7.1q,v22.1d,v23.1d		//H^2·Ii+1
+	eor	v5.16b,v5.16b,v23.16b
+	ext	v0.16b,v0.16b,v0.16b,#8
+
+	pmull2	v23.1q,v22.2d,v23.2d
+	eor	v16.16b,v4.16b,v0.16b
+	pmull2	v5.1q,v21.2d,v5.2d
+	ext	v3.16b,v16.16b,v16.16b,#8
+
+	eor	v29.16b,v29.16b,v7.16b
+	eor	v31.16b,v31.16b,v23.16b
+	eor	v30.16b,v30.16b,v5.16b
+
+	pmull	v0.1q,v26.1d,v3.1d		//H^3·(Xi+Ii)
+	eor	v16.16b,v16.16b,v3.16b
+	pmull2	v2.1q,v26.2d,v3.2d
+	pmull	v1.1q,v27.1d,v16.1d
+
+	eor	v0.16b,v0.16b,v29.16b
+	eor	v2.16b,v2.16b,v31.16b
+	eor	v1.16b,v1.16b,v30.16b
+	b	.Ldone4x
+
+.align	4
+.Ltwo:
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v17.16b
+	ld1	{v4.2d,v5.2d},[x2]
+	eor	v1.16b,v1.16b,v18.16b
+#ifndef	__AARCH64EB__
+	rev64	v5.16b,v5.16b
+	rev64	v4.16b,v4.16b
+#endif
+
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase of reduction
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	ext	v23.16b,v5.16b,v5.16b,#8
+	eor	v0.16b,v1.16b,v18.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
+	pmull	v0.1q,v0.1d,v19.1d
+	eor	v18.16b,v18.16b,v2.16b
+	eor	v0.16b,v0.16b,v18.16b
+	ext	v0.16b,v0.16b,v0.16b,#8
+
+	pmull	v29.1q,v20.1d,v23.1d		//H·Ii+1
+	eor	v5.16b,v5.16b,v23.16b
+
+	eor	v16.16b,v4.16b,v0.16b
+	ext	v3.16b,v16.16b,v16.16b,#8
+
+	pmull2	v31.1q,v20.2d,v23.2d
+	pmull	v30.1q,v21.1d,v5.1d
+
+	pmull	v0.1q,v22.1d,v3.1d		//H^2·(Xi+Ii)
+	eor	v16.16b,v16.16b,v3.16b
+	pmull2	v2.1q,v22.2d,v3.2d
+	pmull2	v1.1q,v21.2d,v16.2d
+
+	eor	v0.16b,v0.16b,v29.16b
+	eor	v2.16b,v2.16b,v31.16b
+	eor	v1.16b,v1.16b,v30.16b
+	b	.Ldone4x
+
+.align	4
+.Lone:
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v17.16b
+	ld1	{v4.2d},[x2]
+	eor	v1.16b,v1.16b,v18.16b
+#ifndef	__AARCH64EB__
+	rev64	v4.16b,v4.16b
+#endif
+
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase of reduction
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	eor	v0.16b,v1.16b,v18.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
+	pmull	v0.1q,v0.1d,v19.1d
+	eor	v18.16b,v18.16b,v2.16b
+	eor	v0.16b,v0.16b,v18.16b
+	ext	v0.16b,v0.16b,v0.16b,#8
+
+	eor	v16.16b,v4.16b,v0.16b
+	ext	v3.16b,v16.16b,v16.16b,#8
+
+	pmull	v0.1q,v20.1d,v3.1d
+	eor	v16.16b,v16.16b,v3.16b
+	pmull2	v2.1q,v20.2d,v3.2d
+	pmull	v1.1q,v21.1d,v16.1d
+
+.Ldone4x:
+	ext	v17.16b,v0.16b,v2.16b,#8		//Karatsuba post-processing
+	eor	v18.16b,v0.16b,v2.16b
+	eor	v1.16b,v1.16b,v17.16b
+	eor	v1.16b,v1.16b,v18.16b
+
+	pmull	v18.1q,v0.1d,v19.1d		//1st phase of reduction
+	ins	v2.d[0],v1.d[1]
+	ins	v1.d[1],v0.d[0]
+	eor	v0.16b,v1.16b,v18.16b
+
+	ext	v18.16b,v0.16b,v0.16b,#8		//2nd phase of reduction
+	pmull	v0.1q,v0.1d,v19.1d
+	eor	v18.16b,v18.16b,v2.16b
+	eor	v0.16b,v0.16b,v18.16b
+	ext	v0.16b,v0.16b,v0.16b,#8
+
+#ifndef __AARCH64EB__
+	rev64	v0.16b,v0.16b
+#endif
+	st1	{v0.2d},[x0]		//write out Xi
+
+	ret
+.size	gcm_ghash_v8_4x,.-gcm_ghash_v8_4x
+.byte	71,72,65,83,72,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.align	2
+.align	2
+#endif

deps/openssl/config/archs/linux-aarch64/asm/crypto/poly1305/poly1305-armv8.S

@@ -0,0 +1,863 @@
+#include "arm_arch.h"
+
+.text
+
+// forward "declarations" are required for Apple
+
+.hidden	OPENSSL_armcap_P
+.globl	poly1305_init
+.hidden	poly1305_init
+.globl	poly1305_blocks
+.hidden	poly1305_blocks
+.globl	poly1305_emit
+.hidden	poly1305_emit
+
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+	cmp	x1,xzr
+	stp	xzr,xzr,[x0]		// zero hash value
+	stp	xzr,xzr,[x0,#16]	// [along with is_base2_26]
+
+	csel	x0,xzr,x0,eq
+	b.eq	.Lno_key
+
+	adrp	x17,OPENSSL_armcap_P
+	ldr	w17,[x17,#:lo12:OPENSSL_armcap_P]
+
+	ldp	x7,x8,[x1]		// load key
+	mov	x9,#0xfffffffc0fffffff
+	movk	x9,#0x0fff,lsl#48
+#ifdef	__AARCH64EB__
+	rev	x7,x7			// flip bytes
+	rev	x8,x8
+#endif
+	and	x7,x7,x9		// &=0ffffffc0fffffff
+	and	x9,x9,#-4
+	and	x8,x8,x9		// &=0ffffffc0ffffffc
+	stp	x7,x8,[x0,#32]	// save key value
+
+	tst	w17,#ARMV7_NEON
+
+	adr	x12,.Lpoly1305_blocks
+	adr	x7,.Lpoly1305_blocks_neon
+	adr	x13,.Lpoly1305_emit
+	adr	x8,.Lpoly1305_emit_neon
+
+	csel	x12,x12,x7,eq
+	csel	x13,x13,x8,eq
+
+#ifdef	__ILP32__
+	stp	w12,w13,[x2]
+#else
+	stp	x12,x13,[x2]
+#endif
+
+	mov	x0,#1
+.Lno_key:
+	ret
+.size	poly1305_init,.-poly1305_init
+
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	ands	x2,x2,#-16
+	b.eq	.Lno_data
+
+	ldp	x4,x5,[x0]		// load hash value
+	ldp	x7,x8,[x0,#32]	// load key value
+	ldr	x6,[x0,#16]
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+	b	.Loop
+
+.align	5
+.Loop:
+	ldp	x10,x11,[x1],#16	// load input
+	sub	x2,x2,#16
+#ifdef	__AARCH64EB__
+	rev	x10,x10
+	rev	x11,x11
+#endif
+	adds	x4,x4,x10		// accumulate input
+	adcs	x5,x5,x11
+
+	mul	x12,x4,x7		// h0*r0
+	adc	x6,x6,x3
+	umulh	x13,x4,x7
+
+	mul	x10,x5,x9		// h1*5*r1
+	umulh	x11,x5,x9
+
+	adds	x12,x12,x10
+	mul	x10,x4,x8		// h0*r1
+	adc	x13,x13,x11
+	umulh	x14,x4,x8
+
+	adds	x13,x13,x10
+	mul	x10,x5,x7		// h1*r0
+	adc	x14,x14,xzr
+	umulh	x11,x5,x7
+
+	adds	x13,x13,x10
+	mul	x10,x6,x9		// h2*5*r1
+	adc	x14,x14,x11
+	mul	x11,x6,x7		// h2*r0
+
+	adds	x13,x13,x10
+	adc	x14,x14,x11
+
+	and	x10,x14,#-4		// final reduction
+	and	x6,x14,#3
+	add	x10,x10,x14,lsr#2
+	adds	x4,x12,x10
+	adcs	x5,x13,xzr
+	adc	x6,x6,xzr
+
+	cbnz	x2,.Loop
+
+	stp	x4,x5,[x0]		// store hash value
+	str	x6,[x0,#16]
+
+.Lno_data:
+	ret
+.size	poly1305_blocks,.-poly1305_blocks
+
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	ldp	x4,x5,[x0]		// load hash base 2^64
+	ldr	x6,[x0,#16]
+	ldp	x10,x11,[x2]	// load nonce
+
+	adds	x12,x4,#5		// compare to modulus
+	adcs	x13,x5,xzr
+	adc	x14,x6,xzr
+
+	tst	x14,#-4			// see if it's carried/borrowed
+
+	csel	x4,x4,x12,eq
+	csel	x5,x5,x13,eq
+
+#ifdef	__AARCH64EB__
+	ror	x10,x10,#32		// flip nonce words
+	ror	x11,x11,#32
+#endif
+	adds	x4,x4,x10		// accumulate nonce
+	adc	x5,x5,x11
+#ifdef	__AARCH64EB__
+	rev	x4,x4			// flip output bytes
+	rev	x5,x5
+#endif
+	stp	x4,x5,[x1]		// write result
+
+	ret
+.size	poly1305_emit,.-poly1305_emit
+.type	poly1305_mult,%function
+.align	5
+poly1305_mult:
+	mul	x12,x4,x7		// h0*r0
+	umulh	x13,x4,x7
+
+	mul	x10,x5,x9		// h1*5*r1
+	umulh	x11,x5,x9
+
+	adds	x12,x12,x10
+	mul	x10,x4,x8		// h0*r1
+	adc	x13,x13,x11
+	umulh	x14,x4,x8
+
+	adds	x13,x13,x10
+	mul	x10,x5,x7		// h1*r0
+	adc	x14,x14,xzr
+	umulh	x11,x5,x7
+
+	adds	x13,x13,x10
+	mul	x10,x6,x9		// h2*5*r1
+	adc	x14,x14,x11
+	mul	x11,x6,x7		// h2*r0
+
+	adds	x13,x13,x10
+	adc	x14,x14,x11
+
+	and	x10,x14,#-4		// final reduction
+	and	x6,x14,#3
+	add	x10,x10,x14,lsr#2
+	adds	x4,x12,x10
+	adcs	x5,x13,xzr
+	adc	x6,x6,xzr
+
+	ret
+.size	poly1305_mult,.-poly1305_mult
+
+.type	poly1305_splat,%function
+.align	5
+poly1305_splat:
+	and	x12,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x13,x4,#26,#26
+	extr	x14,x5,x4,#52
+	and	x14,x14,#0x03ffffff
+	ubfx	x15,x5,#14,#26
+	extr	x16,x6,x5,#40
+
+	str	w12,[x0,#16*0]	// r0
+	add	w12,w13,w13,lsl#2	// r1*5
+	str	w13,[x0,#16*1]	// r1
+	add	w13,w14,w14,lsl#2	// r2*5
+	str	w12,[x0,#16*2]	// s1
+	str	w14,[x0,#16*3]	// r2
+	add	w14,w15,w15,lsl#2	// r3*5
+	str	w13,[x0,#16*4]	// s2
+	str	w15,[x0,#16*5]	// r3
+	add	w15,w16,w16,lsl#2	// r4*5
+	str	w14,[x0,#16*6]	// s3
+	str	w16,[x0,#16*7]	// r4
+	str	w15,[x0,#16*8]	// s4
+
+	ret
+.size	poly1305_splat,.-poly1305_splat
+
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	x17,[x0,#24]
+	cmp	x2,#128
+	b.hs	.Lblocks_neon
+	cbz	x17,.Lpoly1305_blocks
+
+.Lblocks_neon:
+.inst	0xd503233f		// paciasp
+	stp	x29,x30,[sp,#-80]!
+	add	x29,sp,#0
+
+	ands	x2,x2,#-16
+	b.eq	.Lno_data_neon
+
+	cbz	x17,.Lbase2_64_neon
+
+	ldp	w10,w11,[x0]		// load hash value base 2^26
+	ldp	w12,w13,[x0,#8]
+	ldr	w14,[x0,#16]
+
+	tst	x2,#31
+	b.eq	.Leven_neon
+
+	ldp	x7,x8,[x0,#32]	// load key value
+
+	add	x4,x10,x11,lsl#26	// base 2^26 -> base 2^64
+	lsr	x5,x12,#12
+	adds	x4,x4,x12,lsl#52
+	add	x5,x5,x13,lsl#14
+	adc	x5,x5,xzr
+	lsr	x6,x14,#24
+	adds	x5,x5,x14,lsl#40
+	adc	x14,x6,xzr		// can be partially reduced...
+
+	ldp	x12,x13,[x1],#16	// load input
+	sub	x2,x2,#16
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+
+	and	x10,x14,#-4		// ... so reduce
+	and	x6,x14,#3
+	add	x10,x10,x14,lsr#2
+	adds	x4,x4,x10
+	adcs	x5,x5,xzr
+	adc	x6,x6,xzr
+
+#ifdef	__AARCH64EB__
+	rev	x12,x12
+	rev	x13,x13
+#endif
+	adds	x4,x4,x12		// accumulate input
+	adcs	x5,x5,x13
+	adc	x6,x6,x3
+
+	bl	poly1305_mult
+	ldr	x30,[sp,#8]
+
+	cbz	x3,.Lstore_base2_64_neon
+
+	and	x10,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,x4,#26,#26
+	extr	x12,x5,x4,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,x5,#14,#26
+	extr	x14,x6,x5,#40
+
+	cbnz	x2,.Leven_neon
+
+	stp	w10,w11,[x0]		// store hash value base 2^26
+	stp	w12,w13,[x0,#8]
+	str	w14,[x0,#16]
+	b	.Lno_data_neon
+
+.align	4
+.Lstore_base2_64_neon:
+	stp	x4,x5,[x0]		// store hash value base 2^64
+	stp	x6,xzr,[x0,#16]	// note that is_base2_26 is zeroed
+	b	.Lno_data_neon
+
+.align	4
+.Lbase2_64_neon:
+	ldp	x7,x8,[x0,#32]	// load key value
+
+	ldp	x4,x5,[x0]		// load hash value base 2^64
+	ldr	x6,[x0,#16]
+
+	tst	x2,#31
+	b.eq	.Linit_neon
+
+	ldp	x12,x13,[x1],#16	// load input
+	sub	x2,x2,#16
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+#ifdef	__AARCH64EB__
+	rev	x12,x12
+	rev	x13,x13
+#endif
+	adds	x4,x4,x12		// accumulate input
+	adcs	x5,x5,x13
+	adc	x6,x6,x3
+
+	bl	poly1305_mult
+
+.Linit_neon:
+	and	x10,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,x4,#26,#26
+	extr	x12,x5,x4,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,x5,#14,#26
+	extr	x14,x6,x5,#40
+
+	stp	d8,d9,[sp,#16]		// meet ABI requirements
+	stp	d10,d11,[sp,#32]
+	stp	d12,d13,[sp,#48]
+	stp	d14,d15,[sp,#64]
+
+	fmov	d24,x10
+	fmov	d25,x11
+	fmov	d26,x12
+	fmov	d27,x13
+	fmov	d28,x14
+
+	////////////////////////////////// initialize r^n table
+	mov	x4,x7			// r^1
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+	mov	x5,x8
+	mov	x6,xzr
+	add	x0,x0,#48+12
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^2
+	sub	x0,x0,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^3
+	sub	x0,x0,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^4
+	sub	x0,x0,#4
+	bl	poly1305_splat
+	ldr	x30,[sp,#8]
+
+	add	x16,x1,#32
+	adr	x17,.Lzeros
+	subs	x2,x2,#64
+	csel	x16,x17,x16,lo
+
+	mov	x4,#1
+	stur	x4,[x0,#-24]		// set is_base2_26
+	sub	x0,x0,#48		// restore original x0
+	b	.Ldo_neon
+
+.align	4
+.Leven_neon:
+	add	x16,x1,#32
+	adr	x17,.Lzeros
+	subs	x2,x2,#64
+	csel	x16,x17,x16,lo
+
+	stp	d8,d9,[sp,#16]		// meet ABI requirements
+	stp	d10,d11,[sp,#32]
+	stp	d12,d13,[sp,#48]
+	stp	d14,d15,[sp,#64]
+
+	fmov	d24,x10
+	fmov	d25,x11
+	fmov	d26,x12
+	fmov	d27,x13
+	fmov	d28,x14
+
+.Ldo_neon:
+	ldp	x8,x12,[x16],#16	// inp[2:3] (or zero)
+	ldp	x9,x13,[x16],#48
+
+	lsl	x3,x3,#24
+	add	x15,x0,#48
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	d14,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,x3,x12,lsr#40
+	add	x13,x3,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	d15,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	fmov	d16,x8
+	fmov	d17,x10
+	fmov	d18,x12
+
+	ldp	x8,x12,[x1],#16	// inp[0:1]
+	ldp	x9,x13,[x1],#48
+
+	ld1	{v0.4s,v1.4s,v2.4s,v3.4s},[x15],#64
+	ld1	{v4.4s,v5.4s,v6.4s,v7.4s},[x15],#64
+	ld1	{v8.4s},[x15]
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	d9,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,x3,x12,lsr#40
+	add	x13,x3,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	d10,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	movi	v31.2d,#-1
+	fmov	d11,x8
+	fmov	d12,x10
+	fmov	d13,x12
+	ushr	v31.2d,v31.2d,#38
+
+	b.ls	.Lskip_loop
+
+.align	4
+.Loop_neon:
+	////////////////////////////////////////////////////////////////
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	//   ___________________/
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	//   ___________________/ ____________________/
+	//
+	// Note that we start with inp[2:3]*r^2. This is because it
+	// doesn't depend on reduction in previous iteration.
+	////////////////////////////////////////////////////////////////
+	// d4 = h0*r4 + h1*r3   + h2*r2   + h3*r1   + h4*r0
+	// d3 = h0*r3 + h1*r2   + h2*r1   + h3*r0   + h4*5*r4
+	// d2 = h0*r2 + h1*r1   + h2*r0   + h3*5*r4 + h4*5*r3
+	// d1 = h0*r1 + h1*r0   + h2*5*r4 + h3*5*r3 + h4*5*r2
+	// d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1
+
+	subs	x2,x2,#64
+	umull	v23.2d,v14.2s,v7.s[2]
+	csel	x16,x17,x16,lo
+	umull	v22.2d,v14.2s,v5.s[2]
+	umull	v21.2d,v14.2s,v3.s[2]
+	ldp	x8,x12,[x16],#16	// inp[2:3] (or zero)
+	umull	v20.2d,v14.2s,v1.s[2]
+	ldp	x9,x13,[x16],#48
+	umull	v19.2d,v14.2s,v0.s[2]
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+
+	umlal	v23.2d,v15.2s,v5.s[2]
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	v22.2d,v15.2s,v3.s[2]
+	and	x5,x9,#0x03ffffff
+	umlal	v21.2d,v15.2s,v1.s[2]
+	ubfx	x6,x8,#26,#26
+	umlal	v20.2d,v15.2s,v0.s[2]
+	ubfx	x7,x9,#26,#26
+	umlal	v19.2d,v15.2s,v8.s[2]
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+
+	umlal	v23.2d,v16.2s,v3.s[2]
+	extr	x8,x12,x8,#52
+	umlal	v22.2d,v16.2s,v1.s[2]
+	extr	x9,x13,x9,#52
+	umlal	v21.2d,v16.2s,v0.s[2]
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	v20.2d,v16.2s,v8.s[2]
+	fmov	d14,x4
+	umlal	v19.2d,v16.2s,v6.s[2]
+	and	x8,x8,#0x03ffffff
+
+	umlal	v23.2d,v17.2s,v1.s[2]
+	and	x9,x9,#0x03ffffff
+	umlal	v22.2d,v17.2s,v0.s[2]
+	ubfx	x10,x12,#14,#26
+	umlal	v21.2d,v17.2s,v8.s[2]
+	ubfx	x11,x13,#14,#26
+	umlal	v20.2d,v17.2s,v6.s[2]
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	v19.2d,v17.2s,v4.s[2]
+	fmov	d15,x6
+
+	add	v11.2s,v11.2s,v26.2s
+	add	x12,x3,x12,lsr#40
+	umlal	v23.2d,v18.2s,v0.s[2]
+	add	x13,x3,x13,lsr#40
+	umlal	v22.2d,v18.2s,v8.s[2]
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	v21.2d,v18.2s,v6.s[2]
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	v20.2d,v18.2s,v4.s[2]
+	fmov	d16,x8
+	umlal	v19.2d,v18.2s,v2.s[2]
+	fmov	d17,x10
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4 and accumulate
+
+	add	v9.2s,v9.2s,v24.2s
+	fmov	d18,x12
+	umlal	v22.2d,v11.2s,v1.s[0]
+	ldp	x8,x12,[x1],#16	// inp[0:1]
+	umlal	v19.2d,v11.2s,v6.s[0]
+	ldp	x9,x13,[x1],#48
+	umlal	v23.2d,v11.2s,v3.s[0]
+	umlal	v20.2d,v11.2s,v8.s[0]
+	umlal	v21.2d,v11.2s,v0.s[0]
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+
+	add	v10.2s,v10.2s,v25.2s
+	umlal	v22.2d,v9.2s,v5.s[0]
+	umlal	v23.2d,v9.2s,v7.s[0]
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	v21.2d,v9.2s,v3.s[0]
+	and	x5,x9,#0x03ffffff
+	umlal	v19.2d,v9.2s,v0.s[0]
+	ubfx	x6,x8,#26,#26
+	umlal	v20.2d,v9.2s,v1.s[0]
+	ubfx	x7,x9,#26,#26
+
+	add	v12.2s,v12.2s,v27.2s
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	umlal	v22.2d,v10.2s,v3.s[0]
+	extr	x8,x12,x8,#52
+	umlal	v23.2d,v10.2s,v5.s[0]
+	extr	x9,x13,x9,#52
+	umlal	v19.2d,v10.2s,v8.s[0]
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	v21.2d,v10.2s,v1.s[0]
+	fmov	d9,x4
+	umlal	v20.2d,v10.2s,v0.s[0]
+	and	x8,x8,#0x03ffffff
+
+	add	v13.2s,v13.2s,v28.2s
+	and	x9,x9,#0x03ffffff
+	umlal	v22.2d,v12.2s,v0.s[0]
+	ubfx	x10,x12,#14,#26
+	umlal	v19.2d,v12.2s,v4.s[0]
+	ubfx	x11,x13,#14,#26
+	umlal	v23.2d,v12.2s,v1.s[0]
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	v20.2d,v12.2s,v6.s[0]
+	fmov	d10,x6
+	umlal	v21.2d,v12.2s,v8.s[0]
+	add	x12,x3,x12,lsr#40
+
+	umlal	v22.2d,v13.2s,v8.s[0]
+	add	x13,x3,x13,lsr#40
+	umlal	v19.2d,v13.2s,v2.s[0]
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	v23.2d,v13.2s,v0.s[0]
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	v20.2d,v13.2s,v4.s[0]
+	fmov	d11,x8
+	umlal	v21.2d,v13.2s,v6.s[0]
+	fmov	d12,x10
+	fmov	d13,x12
+
+	/////////////////////////////////////////////////////////////////
+	// lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	// and P. Schwabe
+	//
+	// [see discussion in poly1305-armv4 module]
+
+	ushr	v29.2d,v22.2d,#26
+	xtn	v27.2s,v22.2d
+	ushr	v30.2d,v19.2d,#26
+	and	v19.16b,v19.16b,v31.16b
+	add	v23.2d,v23.2d,v29.2d	// h3 -> h4
+	bic	v27.2s,#0xfc,lsl#24	// &=0x03ffffff
+	add	v20.2d,v20.2d,v30.2d	// h0 -> h1
+
+	ushr	v29.2d,v23.2d,#26
+	xtn	v28.2s,v23.2d
+	ushr	v30.2d,v20.2d,#26
+	xtn	v25.2s,v20.2d
+	bic	v28.2s,#0xfc,lsl#24
+	add	v21.2d,v21.2d,v30.2d	// h1 -> h2
+
+	add	v19.2d,v19.2d,v29.2d
+	shl	v29.2d,v29.2d,#2
+	shrn	v30.2s,v21.2d,#26
+	xtn	v26.2s,v21.2d
+	add	v19.2d,v19.2d,v29.2d	// h4 -> h0
+	bic	v25.2s,#0xfc,lsl#24
+	add	v27.2s,v27.2s,v30.2s		// h2 -> h3
+	bic	v26.2s,#0xfc,lsl#24
+
+	shrn	v29.2s,v19.2d,#26
+	xtn	v24.2s,v19.2d
+	ushr	v30.2s,v27.2s,#26
+	bic	v27.2s,#0xfc,lsl#24
+	bic	v24.2s,#0xfc,lsl#24
+	add	v25.2s,v25.2s,v29.2s		// h0 -> h1
+	add	v28.2s,v28.2s,v30.2s		// h3 -> h4
+
+	b.hi	.Loop_neon
+
+.Lskip_loop:
+	dup	v16.2d,v16.d[0]
+	add	v11.2s,v11.2s,v26.2s
+
+	////////////////////////////////////////////////////////////////
+	// multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	adds	x2,x2,#32
+	b.ne	.Long_tail
+
+	dup	v16.2d,v11.d[0]
+	add	v14.2s,v9.2s,v24.2s
+	add	v17.2s,v12.2s,v27.2s
+	add	v15.2s,v10.2s,v25.2s
+	add	v18.2s,v13.2s,v28.2s
+
+.Long_tail:
+	dup	v14.2d,v14.d[0]
+	umull2	v19.2d,v16.4s,v6.4s
+	umull2	v22.2d,v16.4s,v1.4s
+	umull2	v23.2d,v16.4s,v3.4s
+	umull2	v21.2d,v16.4s,v0.4s
+	umull2	v20.2d,v16.4s,v8.4s
+
+	dup	v15.2d,v15.d[0]
+	umlal2	v19.2d,v14.4s,v0.4s
+	umlal2	v21.2d,v14.4s,v3.4s
+	umlal2	v22.2d,v14.4s,v5.4s
+	umlal2	v23.2d,v14.4s,v7.4s
+	umlal2	v20.2d,v14.4s,v1.4s
+
+	dup	v17.2d,v17.d[0]
+	umlal2	v19.2d,v15.4s,v8.4s
+	umlal2	v22.2d,v15.4s,v3.4s
+	umlal2	v21.2d,v15.4s,v1.4s
+	umlal2	v23.2d,v15.4s,v5.4s
+	umlal2	v20.2d,v15.4s,v0.4s
+
+	dup	v18.2d,v18.d[0]
+	umlal2	v22.2d,v17.4s,v0.4s
+	umlal2	v23.2d,v17.4s,v1.4s
+	umlal2	v19.2d,v17.4s,v4.4s
+	umlal2	v20.2d,v17.4s,v6.4s
+	umlal2	v21.2d,v17.4s,v8.4s
+
+	umlal2	v22.2d,v18.4s,v8.4s
+	umlal2	v19.2d,v18.4s,v2.4s
+	umlal2	v23.2d,v18.4s,v0.4s
+	umlal2	v20.2d,v18.4s,v4.4s
+	umlal2	v21.2d,v18.4s,v6.4s
+
+	b.eq	.Lshort_tail
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	add	v9.2s,v9.2s,v24.2s
+	umlal	v22.2d,v11.2s,v1.2s
+	umlal	v19.2d,v11.2s,v6.2s
+	umlal	v23.2d,v11.2s,v3.2s
+	umlal	v20.2d,v11.2s,v8.2s
+	umlal	v21.2d,v11.2s,v0.2s
+
+	add	v10.2s,v10.2s,v25.2s
+	umlal	v22.2d,v9.2s,v5.2s
+	umlal	v19.2d,v9.2s,v0.2s
+	umlal	v23.2d,v9.2s,v7.2s
+	umlal	v20.2d,v9.2s,v1.2s
+	umlal	v21.2d,v9.2s,v3.2s
+
+	add	v12.2s,v12.2s,v27.2s
+	umlal	v22.2d,v10.2s,v3.2s
+	umlal	v19.2d,v10.2s,v8.2s
+	umlal	v23.2d,v10.2s,v5.2s
+	umlal	v20.2d,v10.2s,v0.2s
+	umlal	v21.2d,v10.2s,v1.2s
+
+	add	v13.2s,v13.2s,v28.2s
+	umlal	v22.2d,v12.2s,v0.2s
+	umlal	v19.2d,v12.2s,v4.2s
+	umlal	v23.2d,v12.2s,v1.2s
+	umlal	v20.2d,v12.2s,v6.2s
+	umlal	v21.2d,v12.2s,v8.2s
+
+	umlal	v22.2d,v13.2s,v8.2s
+	umlal	v19.2d,v13.2s,v2.2s
+	umlal	v23.2d,v13.2s,v0.2s
+	umlal	v20.2d,v13.2s,v4.2s
+	umlal	v21.2d,v13.2s,v6.2s
+
+.Lshort_tail:
+	////////////////////////////////////////////////////////////////
+	// horizontal add
+
+	addp	v22.2d,v22.2d,v22.2d
+	ldp	d8,d9,[sp,#16]		// meet ABI requirements
+	addp	v19.2d,v19.2d,v19.2d
+	ldp	d10,d11,[sp,#32]
+	addp	v23.2d,v23.2d,v23.2d
+	ldp	d12,d13,[sp,#48]
+	addp	v20.2d,v20.2d,v20.2d
+	ldp	d14,d15,[sp,#64]
+	addp	v21.2d,v21.2d,v21.2d
+
+	////////////////////////////////////////////////////////////////
+	// lazy reduction, but without narrowing
+
+	ushr	v29.2d,v22.2d,#26
+	and	v22.16b,v22.16b,v31.16b
+	ushr	v30.2d,v19.2d,#26
+	and	v19.16b,v19.16b,v31.16b
+
+	add	v23.2d,v23.2d,v29.2d	// h3 -> h4
+	add	v20.2d,v20.2d,v30.2d	// h0 -> h1
+
+	ushr	v29.2d,v23.2d,#26
+	and	v23.16b,v23.16b,v31.16b
+	ushr	v30.2d,v20.2d,#26
+	and	v20.16b,v20.16b,v31.16b
+	add	v21.2d,v21.2d,v30.2d	// h1 -> h2
+
+	add	v19.2d,v19.2d,v29.2d
+	shl	v29.2d,v29.2d,#2
+	ushr	v30.2d,v21.2d,#26
+	and	v21.16b,v21.16b,v31.16b
+	add	v19.2d,v19.2d,v29.2d	// h4 -> h0
+	add	v22.2d,v22.2d,v30.2d	// h2 -> h3
+
+	ushr	v29.2d,v19.2d,#26
+	and	v19.16b,v19.16b,v31.16b
+	ushr	v30.2d,v22.2d,#26
+	and	v22.16b,v22.16b,v31.16b
+	add	v20.2d,v20.2d,v29.2d	// h0 -> h1
+	add	v23.2d,v23.2d,v30.2d	// h3 -> h4
+
+	////////////////////////////////////////////////////////////////
+	// write the result, can be partially reduced
+
+	st4	{v19.s,v20.s,v21.s,v22.s}[0],[x0],#16
+	st1	{v23.s}[0],[x0]
+
+.Lno_data_neon:
+	ldr	x29,[sp],#80
+.inst	0xd50323bf		// autiasp
+	ret
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.type	poly1305_emit_neon,%function
+.align	5
+poly1305_emit_neon:
+.Lpoly1305_emit_neon:
+	ldr	x17,[x0,#24]
+	cbz	x17,poly1305_emit
+
+	ldp	w10,w11,[x0]		// load hash value base 2^26
+	ldp	w12,w13,[x0,#8]
+	ldr	w14,[x0,#16]
+
+	add	x4,x10,x11,lsl#26	// base 2^26 -> base 2^64
+	lsr	x5,x12,#12
+	adds	x4,x4,x12,lsl#52
+	add	x5,x5,x13,lsl#14
+	adc	x5,x5,xzr
+	lsr	x6,x14,#24
+	adds	x5,x5,x14,lsl#40
+	adc	x6,x6,xzr		// can be partially reduced...
+
+	ldp	x10,x11,[x2]	// load nonce
+
+	and	x12,x6,#-4		// ... so reduce
+	add	x12,x12,x6,lsr#2
+	and	x6,x6,#3
+	adds	x4,x4,x12
+	adcs	x5,x5,xzr
+	adc	x6,x6,xzr
+
+	adds	x12,x4,#5		// compare to modulus
+	adcs	x13,x5,xzr
+	adc	x14,x6,xzr
+
+	tst	x14,#-4			// see if it's carried/borrowed
+
+	csel	x4,x4,x12,eq
+	csel	x5,x5,x13,eq
+
+#ifdef	__AARCH64EB__
+	ror	x10,x10,#32		// flip nonce words
+	ror	x11,x11,#32
+#endif
+	adds	x4,x4,x10		// accumulate nonce
+	adc	x5,x5,x11
+#ifdef	__AARCH64EB__
+	rev	x4,x4			// flip output bytes
+	rev	x5,x5
+#endif
+	stp	x4,x5,[x1]		// write result
+
+	ret
+.size	poly1305_emit_neon,.-poly1305_emit_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0
+.byte	80,111,108,121,49,51,48,53,32,102,111,114,32,65,82,77,118,56,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
+.align	2
+.align	2