chacha20,poly1305: switch to perlasm originals on mips and arm

We also separate out Eric Biggers' Cortex A7 implementation into its own
file.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>

14 files changed, 5572 insertions, 6106 deletions

diff --git a/src/Makefile b/src/Makefile
index fcfa069..d26c6d1 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -52,7 +52,7 @@ install:
 	@$(MAKE) -C tools install
 
 rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
-DKMS_SOURCES := version.h Makefile Kbuild Kconfig dkms.conf $(filter-out version.h wireguard.mod.c tools/% tests/%,$(call rwildcard,,*.c *.h *.S *.include))
+DKMS_SOURCES := version.h Makefile Kbuild Kconfig dkms.conf $(filter-out version.h wireguard.mod.c tools/% tests/%,$(call rwildcard,,*.c *.h *.S *.pl *.include))
 dkms-install: $(DKMS_SOURCES)
 	@$(foreach f,$(DKMS_SOURCES),install -v -m0644 -D $(f) $(DESTDIR)$(DKMSDIR)/$(f);)
 
diff --git a/src/crypto/Kbuild.include b/src/crypto/Kbuild.include
index ab5ecea..5fb9445 100644
--- a/src/crypto/Kbuild.include
+++ b/src/crypto/Kbuild.include
@@ -16,7 +16,7 @@ endif
 
 zinc-y += chacha20/chacha20.o
 zinc-$(CONFIG_ZINC_ARCH_X86_64) += chacha20/chacha20-x86_64.o
-zinc-$(CONFIG_ZINC_ARCH_ARM) += chacha20/chacha20-arm.o
+zinc-$(CONFIG_ZINC_ARCH_ARM) += chacha20/chacha20-arm.o chacha20/chacha20-unrolled-arm.o
 zinc-$(CONFIG_ZINC_ARCH_ARM64) += chacha20/chacha20-arm64.o
 zinc-$(CONFIG_ZINC_ARCH_MIPS) += chacha20/chacha20-mips.o
 AFLAGS_chacha20-mips.o += -O2 # This is required to fill the branch delay slots
@@ -37,6 +37,12 @@ zinc-$(CONFIG_ZINC_ARCH_X86_64) += blake2s/blake2s-x86_64.o
 zinc-y += curve25519/curve25519.o
 zinc-$(CONFIG_ZINC_ARCH_ARM) += curve25519/curve25519-arm.o
 
+quiet_cmd_perlasm = PERLASM $@
+      cmd_perlasm = $(PERL) $< > $@
+%.S: %.pl
+	$(call cmd,perlasm)
+targets += $(patsubst %.o,crypto/zinc/%.S,$(zinc-y))
+
 wireguard-y += $(addprefix crypto/zinc/,$(zinc-y))
 ccflags-y += -I$(src)/crypto/include
 ccflags-$(CONFIG_ZINC_ARCH_X86_64) += -DCONFIG_ZINC_ARCH_X86_64
diff --git a/src/crypto/zinc/chacha20/chacha20-arm.S b/src/crypto/zinc/chacha20/chacha20-arm.S
deleted file mode 100644
index 79ed18f..0000000
--- a/src/crypto/zinc/chacha20/chacha20-arm.S
+++ /dev/null
@@ -1,1860 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
-/*
- * Copyright (C) 2018 Google, Inc.
- * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
-/*
- * The following scalar routine was written by Eric Biggers.
- *
- * Design notes:
- *
- * 16 registers would be needed to hold the state matrix, but only 14 are
- * available because 'sp' and 'pc' cannot be used.  So we spill the elements
- * (x8, x9) to the stack and swap them out with (x10, x11).  This adds one
- * 'ldrd' and one 'strd' instruction per round.
- *
- * All rotates are performed using the implicit rotate operand accepted by the
- * 'add' and 'eor' instructions.  This is faster than using explicit rotate
- * instructions.  To make this work, we allow the values in the second and last
- * rows of the ChaCha state matrix (rows 'b' and 'd') to temporarily have the
- * wrong rotation amount.  The rotation amount is then fixed up just in time
- * when the values are used.  'brot' is the number of bits the values in row 'b'
- * need to be rotated right to arrive at the correct values, and 'drot'
- * similarly for row 'd'.  (brot, drot) start out as (0, 0) but we make it such
- * that they end up as (25, 24) after every round.
- */
-
-	// ChaCha state registers
-	X0	.req	r0
-	X1	.req	r1
-	X2	.req	r2
-	X3	.req	r3
-	X4	.req	r4
-	X5	.req	r5
-	X6	.req	r6
-	X7	.req	r7
-	X8_X10	.req	r8	// shared by x8 and x10
-	X9_X11	.req	r9	// shared by x9 and x11
-	X12	.req	r10
-	X13	.req	r11
-	X14	.req	r12
-	X15	.req	r14
-
-.Lexpand_32byte_k:
-	// "expand 32-byte k"
-	.word	0x61707865, 0x3320646e, 0x79622d32, 0x6b206574
-
-#ifdef __thumb2__
-#  define adrl adr
-#endif
-
-.macro __rev		out, in,  t0, t1, t2
-.if __LINUX_ARM_ARCH__ >= 6
-	rev		\out, \in
-.else
-	lsl		\t0, \in, #24
-	and		\t1, \in, #0xff00
-	and		\t2, \in, #0xff0000
-	orr		\out, \t0, \in, lsr #24
-	orr		\out, \out, \t1, lsl #8
-	orr		\out, \out, \t2, lsr #8
-.endif
-.endm
-
-.macro _le32_bswap	x,  t0, t1, t2
-#ifdef __ARMEB__
-	__rev		\x, \x,  \t0, \t1, \t2
-#endif
-.endm
-
-.macro _le32_bswap_4x	a, b, c, d,  t0, t1, t2
-	_le32_bswap	\a,  \t0, \t1, \t2
-	_le32_bswap	\b,  \t0, \t1, \t2
-	_le32_bswap	\c,  \t0, \t1, \t2
-	_le32_bswap	\d,  \t0, \t1, \t2
-.endm
-
-.macro __ldrd		a, b, src, offset
-#if __LINUX_ARM_ARCH__ >= 6
-	ldrd		\a, \b, [\src, #\offset]
-#else
-	ldr		\a, [\src, #\offset]
-	ldr		\b, [\src, #\offset + 4]
-#endif
-.endm
-
-.macro __strd		a, b, dst, offset
-#if __LINUX_ARM_ARCH__ >= 6
-	strd		\a, \b, [\dst, #\offset]
-#else
-	str		\a, [\dst, #\offset]
-	str		\b, [\dst, #\offset + 4]
-#endif
-.endm
-
-.macro _halfround	a1, b1, c1, d1,  a2, b2, c2, d2
-
-	// a += b; d ^= a; d = rol(d, 16);
-	add		\a1, \a1, \b1, ror #brot
-	add		\a2, \a2, \b2, ror #brot
-	eor		\d1, \a1, \d1, ror #drot
-	eor		\d2, \a2, \d2, ror #drot
-	// drot == 32 - 16 == 16
-
-	// c += d; b ^= c; b = rol(b, 12);
-	add		\c1, \c1, \d1, ror #16
-	add		\c2, \c2, \d2, ror #16
-	eor		\b1, \c1, \b1, ror #brot
-	eor		\b2, \c2, \b2, ror #brot
-	// brot == 32 - 12 == 20
-
-	// a += b; d ^= a; d = rol(d, 8);
-	add		\a1, \a1, \b1, ror #20
-	add		\a2, \a2, \b2, ror #20
-	eor		\d1, \a1, \d1, ror #16
-	eor		\d2, \a2, \d2, ror #16
-	// drot == 32 - 8 == 24
-
-	// c += d; b ^= c; b = rol(b, 7);
-	add		\c1, \c1, \d1, ror #24
-	add		\c2, \c2, \d2, ror #24
-	eor		\b1, \c1, \b1, ror #20
-	eor		\b2, \c2, \b2, ror #20
-	// brot == 32 - 7 == 25
-.endm
-
-.macro _doubleround
-
-	// column round
-
-	// quarterrounds: (x0, x4, x8, x12) and (x1, x5, x9, x13)
-	_halfround	X0, X4, X8_X10, X12,  X1, X5, X9_X11, X13
-
-	// save (x8, x9); restore (x10, x11)
-	__strd		X8_X10, X9_X11, sp, 0
-	__ldrd		X8_X10, X9_X11, sp, 8
-
-	// quarterrounds: (x2, x6, x10, x14) and (x3, x7, x11, x15)
-	_halfround	X2, X6, X8_X10, X14,  X3, X7, X9_X11, X15
-
-	.set brot, 25
-	.set drot, 24
-
-	// diagonal round
-
-	// quarterrounds: (x0, x5, x10, x15) and (x1, x6, x11, x12)
-	_halfround	X0, X5, X8_X10, X15,  X1, X6, X9_X11, X12
-
-	// save (x10, x11); restore (x8, x9)
-	__strd		X8_X10, X9_X11, sp, 8
-	__ldrd		X8_X10, X9_X11, sp, 0
-
-	// quarterrounds: (x2, x7, x8, x13) and (x3, x4, x9, x14)
-	_halfround	X2, X7, X8_X10, X13,  X3, X4, X9_X11, X14
-.endm
-
-.macro _chacha_permute	nrounds
-	.set brot, 0
-	.set drot, 0
-	.rept \nrounds / 2
-	 _doubleround
-	.endr
-.endm
-
-.macro _chacha		nrounds
-
-.Lnext_block\@:
-	// Stack: unused0-unused1 x10-x11 x0-x15 OUT IN LEN
-	// Registers contain x0-x9,x12-x15.
-
-	// Do the core ChaCha permutation to update x0-x15.
-	_chacha_permute	\nrounds
-
-	add		sp, #8
-	// Stack: x10-x11 orig_x0-orig_x15 OUT IN LEN
-	// Registers contain x0-x9,x12-x15.
-	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
-
-	// Free up some registers (r8-r12,r14) by pushing (x8-x9,x12-x15).
-	push		{X8_X10, X9_X11, X12, X13, X14, X15}
-
-	// Load (OUT, IN, LEN).
-	ldr		r14, [sp, #96]
-	ldr		r12, [sp, #100]
-	ldr		r11, [sp, #104]
-
-	orr		r10, r14, r12
-
-	// Use slow path if fewer than 64 bytes remain.
-	cmp		r11, #64
-	blt		.Lxor_slowpath\@
-
-	// Use slow path if IN and/or OUT isn't 4-byte aligned.  Needed even on
-	// ARMv6+, since ldmia and stmia (used below) still require alignment.
-	tst		r10, #3
-	bne		.Lxor_slowpath\@
-
-	// Fast path: XOR 64 bytes of aligned data.
-
-	// Stack: x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
-	// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is OUT.
-	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
-
-	// x0-x3
-	__ldrd		r8, r9, sp, 32
-	__ldrd		r10, r11, sp, 40
-	add		X0, X0, r8
-	add		X1, X1, r9
-	add		X2, X2, r10
-	add		X3, X3, r11
-	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
-	ldmia		r12!, {r8-r11}
-	eor		X0, X0, r8
-	eor		X1, X1, r9
-	eor		X2, X2, r10
-	eor		X3, X3, r11
-	stmia		r14!, {X0-X3}
-
-	// x4-x7
-	__ldrd		r8, r9, sp, 48
-	__ldrd		r10, r11, sp, 56
-	add		X4, r8, X4, ror #brot
-	add		X5, r9, X5, ror #brot
-	ldmia		r12!, {X0-X3}
-	add		X6, r10, X6, ror #brot
-	add		X7, r11, X7, ror #brot
-	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
-	eor		X4, X4, X0
-	eor		X5, X5, X1
-	eor		X6, X6, X2
-	eor		X7, X7, X3
-	stmia		r14!, {X4-X7}
-
-	// x8-x15
-	pop		{r0-r7}			// (x8-x9,x12-x15,x10-x11)
-	__ldrd		r8, r9, sp, 32
-	__ldrd		r10, r11, sp, 40
-	add		r0, r0, r8		// x8
-	add		r1, r1, r9		// x9
-	add		r6, r6, r10		// x10
-	add		r7, r7, r11		// x11
-	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
-	ldmia		r12!, {r8-r11}
-	eor		r0, r0, r8		// x8
-	eor		r1, r1, r9		// x9
-	eor		r6, r6, r10		// x10
-	eor		r7, r7, r11		// x11
-	stmia		r14!, {r0,r1,r6,r7}
-	ldmia		r12!, {r0,r1,r6,r7}
-	__ldrd		r8, r9, sp, 48
-	__ldrd		r10, r11, sp, 56
-	add		r2, r8, r2, ror #drot	// x12
-	add		r3, r9, r3, ror #drot	// x13
-	add		r4, r10, r4, ror #drot	// x14
-	add		r5, r11, r5, ror #drot	// x15
-	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
-	  ldr		r9, [sp, #72]		// load LEN
-	eor		r2, r2, r0		// x12
-	eor		r3, r3, r1		// x13
-	eor		r4, r4, r6		// x14
-	eor		r5, r5, r7		// x15
-	  subs		r9, #64			// decrement and check LEN
-	stmia		r14!, {r2-r5}
-
-	beq		.Ldone\@
-
-.Lprepare_for_next_block\@:
-
-	// Stack: x0-x15 OUT IN LEN
-
-	// Increment block counter (x12)
-	add		r8, #1
-
-	// Store updated (OUT, IN, LEN)
-	str		r14, [sp, #64]
-	str		r12, [sp, #68]
-	str		r9, [sp, #72]
-
-	  mov		r14, sp
-
-	// Store updated block counter (x12)
-	str		r8, [sp, #48]
-
-	  sub		sp, #16
-
-	// Reload state and do next block
-	ldmia		r14!, {r0-r11}		// load x0-x11
-	__strd		r10, r11, sp, 8		// store x10-x11 before state
-	ldmia		r14, {r10-r12,r14}	// load x12-x15
-	b		.Lnext_block\@
-
-.Lxor_slowpath\@:
-	// Slow path: < 64 bytes remaining, or unaligned input or output buffer.
-	// We handle it by storing the 64 bytes of keystream to the stack, then
-	// XOR-ing the needed portion with the data.
-
-	// Allocate keystream buffer
-	sub		sp, #64
-	mov		r14, sp
-
-	// Stack: ks0-ks15 x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
-	// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is &ks0.
-	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
-
-	// Save keystream for x0-x3
-	__ldrd		r8, r9, sp, 96
-	__ldrd		r10, r11, sp, 104
-	add		X0, X0, r8
-	add		X1, X1, r9
-	add		X2, X2, r10
-	add		X3, X3, r11
-	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
-	stmia		r14!, {X0-X3}
-
-	// Save keystream for x4-x7
-	__ldrd		r8, r9, sp, 112
-	__ldrd		r10, r11, sp, 120
-	add		X4, r8, X4, ror #brot
-	add		X5, r9, X5, ror #brot
-	add		X6, r10, X6, ror #brot
-	add		X7, r11, X7, ror #brot
-	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
-	  add		r8, sp, #64
-	stmia		r14!, {X4-X7}
-
-	// Save keystream for x8-x15
-	ldm		r8, {r0-r7}		// (x8-x9,x12-x15,x10-x11)
-	__ldrd		r8, r9, sp, 128
-	__ldrd		r10, r11, sp, 136
-	add		r0, r0, r8		// x8
-	add		r1, r1, r9		// x9
-	add		r6, r6, r10		// x10
-	add		r7, r7, r11		// x11
-	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
-	stmia		r14!, {r0,r1,r6,r7}
-	__ldrd		r8, r9, sp, 144
-	__ldrd		r10, r11, sp, 152
-	add		r2, r8, r2, ror #drot	// x12
-	add		r3, r9, r3, ror #drot	// x13
-	add		r4, r10, r4, ror #drot	// x14
-	add		r5, r11, r5, ror #drot	// x15
-	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
-	stmia		r14, {r2-r5}
-
-	// Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
-	// Registers: r8 is block counter, r12 is IN.
-
-	ldr		r9, [sp, #168]		// LEN
-	ldr		r14, [sp, #160]		// OUT
-	cmp		r9, #64
-	  mov		r0, sp
-	movle		r1, r9
-	movgt		r1, #64
-	// r1 is number of bytes to XOR, in range [1, 64]
-
-.if __LINUX_ARM_ARCH__ < 6
-	orr		r2, r12, r14
-	tst		r2, #3			// IN or OUT misaligned?
-	bne		.Lxor_next_byte\@
-.endif
-
-	// XOR a word at a time
-.rept 16
-	subs		r1, #4
-	blt		.Lxor_words_done\@
-	ldr		r2, [r12], #4
-	ldr		r3, [r0], #4
-	eor		r2, r2, r3
-	str		r2, [r14], #4
-.endr
-	b		.Lxor_slowpath_done\@
-.Lxor_words_done\@:
-	ands		r1, r1, #3
-	beq		.Lxor_slowpath_done\@
-
-	// XOR a byte at a time
-.Lxor_next_byte\@:
-	ldrb		r2, [r12], #1
-	ldrb		r3, [r0], #1
-	eor		r2, r2, r3
-	strb		r2, [r14], #1
-	subs		r1, #1
-	bne		.Lxor_next_byte\@
-
-.Lxor_slowpath_done\@:
-	subs		r9, #64
-	add		sp, #96
-	bgt		.Lprepare_for_next_block\@
-
-.Ldone\@:
-.endm	// _chacha
-
-/*
- * void chacha20_arm(u8 *out, const u8 *in, size_t len, const u32 key[8],
- *		     const u32 iv[4]);
- */
-ENTRY(chacha20_arm)
-	cmp		r2, #0			// len == 0?
-	reteq		lr
-
-	push		{r0-r2,r4-r11,lr}
-
-	// Push state x0-x15 onto stack.
-	// Also store an extra copy of x10-x11 just before the state.
-
-	ldr		r4, [sp, #48]		// iv
-	mov		r0, sp
-	sub		sp, #80
-
-	// iv: x12-x15
-	ldm		r4, {X12,X13,X14,X15}
-	stmdb		r0!, {X12,X13,X14,X15}
-
-	// key: x4-x11
-	__ldrd		X8_X10, X9_X11, r3, 24
-	__strd		X8_X10, X9_X11, sp, 8
-	stmdb		r0!, {X8_X10, X9_X11}
-	ldm		r3, {X4-X9_X11}
-	stmdb		r0!, {X4-X9_X11}
-
-	// constants: x0-x3
-	adrl		X3, .Lexpand_32byte_k
-	ldm		X3, {X0-X3}
-	__strd		X0, X1, sp, 16
-	__strd		X2, X3, sp, 24
-
-	_chacha		20
-
-	add		sp, #76
-	pop		{r4-r11, pc}
-ENDPROC(chacha20_arm)
-
-/*
- * void hchacha20_arm(const u32 state[16], u32 out[8]);
- */
-ENTRY(hchacha20_arm)
-	push		{r1,r4-r11,lr}
-
-	mov		r14, r0
-	ldmia		r14!, {r0-r11}		// load x0-x11
-	push		{r10-r11}		// store x10-x11 to stack
-	ldm		r14, {r10-r12,r14}	// load x12-x15
-	sub		sp, #8
-
-	_chacha_permute	20
-
-	// Skip over (unused0-unused1, x10-x11)
-	add		sp, #16
-
-	// Fix up rotations of x12-x15
-	ror		X12, X12, #drot
-	ror		X13, X13, #drot
-	  pop		{r4}			// load 'out'
-	ror		X14, X14, #drot
-	ror		X15, X15, #drot
-
-	// Store (x0-x3,x12-x15) to 'out'
-	stm		r4, {X0,X1,X2,X3,X12,X13,X14,X15}
-
-	pop		{r4-r11,pc}
-ENDPROC(hchacha20_arm)
-
-#ifdef CONFIG_KERNEL_MODE_NEON
-/*
- * This following NEON routine was ported from Andy Polyakov's implementation
- * from CRYPTOGAMS. It begins with parts of the CRYPTOGAMS scalar routine,
- * since certain NEON code paths actually branch to it.
- */
-
-.text
-#if defined(__thumb2__) || defined(__clang__)
-.syntax	unified
-#endif
-#if defined(__thumb2__)
-.thumb
-#else
-.code	32
-#endif
-
-#if defined(__thumb2__) || defined(__clang__)
-#define ldrhsb	ldrbhs
-#endif
-
-.align	4
-.Loop_outer:
-	ldmia	sp,{r0-r9}		@ load key material
-	str	r11,[sp,#4*(32+2)]	@ save len
-	str	r12,  [sp,#4*(32+1)]	@ save inp
-	str	r14,  [sp,#4*(32+0)]	@ save out
-.Loop_outer_enter:
-	ldr	r11, [sp,#4*(15)]
-	 mov	r4,r4,ror#19	@ twist b[0..3]
-	ldr	r12,[sp,#4*(12)]	@ modulo-scheduled load
-	 mov	r5,r5,ror#19
-	ldr	r10, [sp,#4*(13)]
-	 mov	r6,r6,ror#19
-	ldr	r14,[sp,#4*(14)]
-	 mov	r7,r7,ror#19
-	mov	r11,r11,ror#8	@ twist d[0..3]
-	mov	r12,r12,ror#8
-	mov	r10,r10,ror#8
-	mov	r14,r14,ror#8
-	str	r11, [sp,#4*(16+15)]
-	mov	r11,#10
-	b	.Loop
-
-.align	4
-.Loop:
-	subs	r11,r11,#1
-	add	r0,r0,r4,ror#13
-	add	r1,r1,r5,ror#13
-	eor	r12,r0,r12,ror#24
-	eor	r10,r1,r10,ror#24
-	add	r8,r8,r12,ror#16
-	add	r9,r9,r10,ror#16
-	eor	r4,r8,r4,ror#13
-	eor	r5,r9,r5,ror#13
-	add	r0,r0,r4,ror#20
-	add	r1,r1,r5,ror#20
-	eor	r12,r0,r12,ror#16
-	eor	r10,r1,r10,ror#16
-	add	r8,r8,r12,ror#24
-	str	r10,[sp,#4*(16+13)]
-	add	r9,r9,r10,ror#24
-	ldr	r10,[sp,#4*(16+15)]
-	str	r8,[sp,#4*(16+8)]
-	eor	r4,r4,r8,ror#12
-	str	r9,[sp,#4*(16+9)]
-	eor	r5,r5,r9,ror#12
-	ldr	r8,[sp,#4*(16+10)]
-	add	r2,r2,r6,ror#13
-	ldr	r9,[sp,#4*(16+11)]
-	add	r3,r3,r7,ror#13
-	eor	r14,r2,r14,ror#24
-	eor	r10,r3,r10,ror#24
-	add	r8,r8,r14,ror#16
-	add	r9,r9,r10,ror#16
-	eor	r6,r8,r6,ror#13
-	eor	r7,r9,r7,ror#13
-	add	r2,r2,r6,ror#20
-	add	r3,r3,r7,ror#20
-	eor	r14,r2,r14,ror#16
-	eor	r10,r3,r10,ror#16
-	add	r8,r8,r14,ror#24
-	add	r9,r9,r10,ror#24
-	eor	r6,r6,r8,ror#12
-	eor	r7,r7,r9,ror#12
-	add	r0,r0,r5,ror#13
-	add	r1,r1,r6,ror#13
-	eor	r10,r0,r10,ror#24
-	eor	r12,r1,r12,ror#24
-	add	r8,r8,r10,ror#16
-	add	r9,r9,r12,ror#16
-	eor	r5,r8,r5,ror#13
-	eor	r6,r9,r6,ror#13
-	add	r0,r0,r5,ror#20
-	add	r1,r1,r6,ror#20
-	eor	r10,r0,r10,ror#16
-	eor	r12,r1,r12,ror#16
-	str	r10,[sp,#4*(16+15)]
-	add	r8,r8,r10,ror#24
-	ldr	r10,[sp,#4*(16+13)]
-	add	r9,r9,r12,ror#24
-	str	r8,[sp,#4*(16+10)]
-	eor	r5,r5,r8,ror#12
-	str	r9,[sp,#4*(16+11)]
-	eor	r6,r6,r9,ror#12
-	ldr	r8,[sp,#4*(16+8)]
-	add	r2,r2,r7,ror#13
-	ldr	r9,[sp,#4*(16+9)]
-	add	r3,r3,r4,ror#13
-	eor	r10,r2,r10,ror#24
-	eor	r14,r3,r14,ror#24
-	add	r8,r8,r10,ror#16
-	add	r9,r9,r14,ror#16
-	eor	r7,r8,r7,ror#13
-	eor	r4,r9,r4,ror#13
-	add	r2,r2,r7,ror#20
-	add	r3,r3,r4,ror#20
-	eor	r10,r2,r10,ror#16
-	eor	r14,r3,r14,ror#16
-	add	r8,r8,r10,ror#24
-	add	r9,r9,r14,ror#24
-	eor	r7,r7,r8,ror#12
-	eor	r4,r4,r9,ror#12
-	bne	.Loop
-
-	ldr	r11,[sp,#4*(32+2)]	@ load len
-
-	str	r8, [sp,#4*(16+8)]	@ modulo-scheduled store
-	str	r9, [sp,#4*(16+9)]
-	str	r12,[sp,#4*(16+12)]
-	str	r10, [sp,#4*(16+13)]
-	str	r14,[sp,#4*(16+14)]
-
-	@ at this point we have first half of 512-bit result in
-	@ rx and second half at sp+4*(16+8)
-
-	cmp	r11,#64		@ done yet?
-#ifdef __thumb2__
-	itete	lo
-#endif
-	addlo	r12,sp,#4*(0)		@ shortcut or ...
-	ldrhs	r12,[sp,#4*(32+1)]	@ ... load inp
-	addlo	r14,sp,#4*(0)		@ shortcut or ...
-	ldrhs	r14,[sp,#4*(32+0)]	@ ... load out
-
-	ldr	r8,[sp,#4*(0)]	@ load key material
-	ldr	r9,[sp,#4*(1)]
-
-#if __LINUX_ARM_ARCH__ >= 6 || !defined(__ARMEB__)
-#if __LINUX_ARM_ARCH__ < 7
-	orr	r10,r12,r14
-	tst	r10,#3		@ are input and output aligned?
-	ldr	r10,[sp,#4*(2)]
-	bne	.Lunaligned
-	cmp	r11,#64		@ restore flags
-#else
-	ldr	r10,[sp,#4*(2)]
-#endif
-	ldr	r11,[sp,#4*(3)]
-
-	add	r0,r0,r8	@ accumulate key material
-	add	r1,r1,r9
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhs	r8,[r12],#16		@ load input
-	ldrhs	r9,[r12,#-12]
-
-	add	r2,r2,r10
-	add	r3,r3,r11
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhs	r10,[r12,#-8]
-	ldrhs	r11,[r12,#-4]
-#if __LINUX_ARM_ARCH__ >= 6 && defined(__ARMEB__)
-	rev	r0,r0
-	rev	r1,r1
-	rev	r2,r2
-	rev	r3,r3
-#endif
-#ifdef __thumb2__
-	itt	hs
-#endif
-	eorhs	r0,r0,r8	@ xor with input
-	eorhs	r1,r1,r9
-	 add	r8,sp,#4*(4)
-	str	r0,[r14],#16		@ store output
-#ifdef __thumb2__
-	itt	hs
-#endif
-	eorhs	r2,r2,r10
-	eorhs	r3,r3,r11
-	 ldmia	r8,{r8-r11}	@ load key material
-	str	r1,[r14,#-12]
-	str	r2,[r14,#-8]
-	str	r3,[r14,#-4]
-
-	add	r4,r8,r4,ror#13 @ accumulate key material
-	add	r5,r9,r5,ror#13
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhs	r8,[r12],#16		@ load input
-	ldrhs	r9,[r12,#-12]
-	add	r6,r10,r6,ror#13
-	add	r7,r11,r7,ror#13
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhs	r10,[r12,#-8]
-	ldrhs	r11,[r12,#-4]
-#if __LINUX_ARM_ARCH__ >= 6 && defined(__ARMEB__)
-	rev	r4,r4
-	rev	r5,r5
-	rev	r6,r6
-	rev	r7,r7
-#endif
-#ifdef __thumb2__
-	itt	hs
-#endif
-	eorhs	r4,r4,r8
-	eorhs	r5,r5,r9
-	 add	r8,sp,#4*(8)
-	str	r4,[r14],#16		@ store output
-#ifdef __thumb2__
-	itt	hs
-#endif
-	eorhs	r6,r6,r10
-	eorhs	r7,r7,r11
-	str	r5,[r14,#-12]
-	 ldmia	r8,{r8-r11}	@ load key material
-	str	r6,[r14,#-8]
-	 add	r0,sp,#4*(16+8)
-	str	r7,[r14,#-4]
-
-	ldmia	r0,{r0-r7}	@ load second half
-
-	add	r0,r0,r8	@ accumulate key material
-	add	r1,r1,r9
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhs	r8,[r12],#16		@ load input
-	ldrhs	r9,[r12,#-12]
-#ifdef __thumb2__
-	itt	hi
-#endif
-	 strhi	r10,[sp,#4*(16+10)]	@ copy "rx" while at it
-	 strhi	r11,[sp,#4*(16+11)]	@ copy "rx" while at it
-	add	r2,r2,r10
-	add	r3,r3,r11
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhs	r10,[r12,#-8]
-	ldrhs	r11,[r12,#-4]
-#if __LINUX_ARM_ARCH__ >= 6 && defined(__ARMEB__)
-	rev	r0,r0
-	rev	r1,r1
-	rev	r2,r2
-	rev	r3,r3
-#endif
-#ifdef __thumb2__
-	itt	hs
-#endif
-	eorhs	r0,r0,r8
-	eorhs	r1,r1,r9
-	 add	r8,sp,#4*(12)
-	str	r0,[r14],#16		@ store output
-#ifdef __thumb2__
-	itt	hs
-#endif
-	eorhs	r2,r2,r10
-	eorhs	r3,r3,r11
-	str	r1,[r14,#-12]
-	 ldmia	r8,{r8-r11}	@ load key material
-	str	r2,[r14,#-8]
-	str	r3,[r14,#-4]
-
-	add	r4,r8,r4,ror#24 @ accumulate key material
-	add	r5,r9,r5,ror#24
-#ifdef __thumb2__
-	itt	hi
-#endif
-	 addhi	r8,r8,#1		@ next counter value
-	 strhi	r8,[sp,#4*(12)]	@ save next counter value
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhs	r8,[r12],#16		@ load input
-	ldrhs	r9,[r12,#-12]
-	add	r6,r10,r6,ror#24
-	add	r7,r11,r7,ror#24
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhs	r10,[r12,#-8]
-	ldrhs	r11,[r12,#-4]
-#if __LINUX_ARM_ARCH__ >= 6 && defined(__ARMEB__)
-	rev	r4,r4
-	rev	r5,r5
-	rev	r6,r6
-	rev	r7,r7
-#endif
-#ifdef __thumb2__
-	itt	hs
-#endif
-	eorhs	r4,r4,r8
-	eorhs	r5,r5,r9
-#ifdef __thumb2__
-	 it	ne
-#endif
-	 ldrne	r8,[sp,#4*(32+2)]	@ re-load len
-#ifdef __thumb2__
-	itt	hs
-#endif
-	eorhs	r6,r6,r10
-	eorhs	r7,r7,r11
-	str	r4,[r14],#16		@ store output
-	str	r5,[r14,#-12]
-#ifdef __thumb2__
-	it	hs
-#endif
-	 subhs	r11,r8,#64		@ len-=64
-	str	r6,[r14,#-8]
-	str	r7,[r14,#-4]
-	bhi	.Loop_outer
-
-	beq	.Ldone
-#if __LINUX_ARM_ARCH__ < 7
-	b	.Ltail
-
-.align	4
-.Lunaligned:				@ unaligned endian-neutral path
-	cmp	r11,#64		@ restore flags
-#endif
-#endif
-#if __LINUX_ARM_ARCH__ < 7
-	ldr	r11,[sp,#4*(3)]
-	add	r0,r8,r0	@ accumulate key material
-	add	r1,r9,r1
-	add	r2,r10,r2
-#ifdef __thumb2__
-	itete	lo
-#endif
-	eorlo	r8,r8,r8		@ zero or ...
-	ldrhsb	r8,[r12],#16			@ ... load input
-	eorlo	r9,r9,r9
-	ldrhsb	r9,[r12,#-12]
-
-	add	r3,r11,r3
-#ifdef __thumb2__
-	itete	lo
-#endif
-	eorlo	r10,r10,r10
-	ldrhsb	r10,[r12,#-8]
-	eorlo	r11,r11,r11
-	ldrhsb	r11,[r12,#-4]
-
-	eor	r0,r8,r0		@ xor with input (or zero)
-	eor	r1,r9,r1
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-15]		@ load more input
-	ldrhsb	r9,[r12,#-11]
-	eor	r2,r10,r2
-	 strb	r0,[r14],#16		@ store output
-	eor	r3,r11,r3
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-7]
-	ldrhsb	r11,[r12,#-3]
-	 strb	r1,[r14,#-12]
-	eor	r0,r8,r0,lsr#8
-	 strb	r2,[r14,#-8]
-	eor	r1,r9,r1,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-14]		@ load more input
-	ldrhsb	r9,[r12,#-10]
-	 strb	r3,[r14,#-4]
-	eor	r2,r10,r2,lsr#8
-	 strb	r0,[r14,#-15]
-	eor	r3,r11,r3,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-6]
-	ldrhsb	r11,[r12,#-2]
-	 strb	r1,[r14,#-11]
-	eor	r0,r8,r0,lsr#8
-	 strb	r2,[r14,#-7]
-	eor	r1,r9,r1,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-13]		@ load more input
-	ldrhsb	r9,[r12,#-9]
-	 strb	r3,[r14,#-3]
-	eor	r2,r10,r2,lsr#8
-	 strb	r0,[r14,#-14]
-	eor	r3,r11,r3,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-5]
-	ldrhsb	r11,[r12,#-1]
-	 strb	r1,[r14,#-10]
-	 strb	r2,[r14,#-6]
-	eor	r0,r8,r0,lsr#8
-	 strb	r3,[r14,#-2]
-	eor	r1,r9,r1,lsr#8
-	 strb	r0,[r14,#-13]
-	eor	r2,r10,r2,lsr#8
-	 strb	r1,[r14,#-9]
-	eor	r3,r11,r3,lsr#8
-	 strb	r2,[r14,#-5]
-	 strb	r3,[r14,#-1]
-	add	r8,sp,#4*(4+0)
-	ldmia	r8,{r8-r11}		@ load key material
-	add	r0,sp,#4*(16+8)
-	add	r4,r8,r4,ror#13	@ accumulate key material
-	add	r5,r9,r5,ror#13
-	add	r6,r10,r6,ror#13
-#ifdef __thumb2__
-	itete	lo
-#endif
-	eorlo	r8,r8,r8		@ zero or ...
-	ldrhsb	r8,[r12],#16			@ ... load input
-	eorlo	r9,r9,r9
-	ldrhsb	r9,[r12,#-12]
-
-	add	r7,r11,r7,ror#13
-#ifdef __thumb2__
-	itete	lo
-#endif
-	eorlo	r10,r10,r10
-	ldrhsb	r10,[r12,#-8]
-	eorlo	r11,r11,r11
-	ldrhsb	r11,[r12,#-4]
-
-	eor	r4,r8,r4		@ xor with input (or zero)
-	eor	r5,r9,r5
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-15]		@ load more input
-	ldrhsb	r9,[r12,#-11]
-	eor	r6,r10,r6
-	 strb	r4,[r14],#16		@ store output
-	eor	r7,r11,r7
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-7]
-	ldrhsb	r11,[r12,#-3]
-	 strb	r5,[r14,#-12]
-	eor	r4,r8,r4,lsr#8
-	 strb	r6,[r14,#-8]
-	eor	r5,r9,r5,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-14]		@ load more input
-	ldrhsb	r9,[r12,#-10]
-	 strb	r7,[r14,#-4]
-	eor	r6,r10,r6,lsr#8
-	 strb	r4,[r14,#-15]
-	eor	r7,r11,r7,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-6]
-	ldrhsb	r11,[r12,#-2]
-	 strb	r5,[r14,#-11]
-	eor	r4,r8,r4,lsr#8
-	 strb	r6,[r14,#-7]
-	eor	r5,r9,r5,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-13]		@ load more input
-	ldrhsb	r9,[r12,#-9]
-	 strb	r7,[r14,#-3]
-	eor	r6,r10,r6,lsr#8
-	 strb	r4,[r14,#-14]
-	eor	r7,r11,r7,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-5]
-	ldrhsb	r11,[r12,#-1]
-	 strb	r5,[r14,#-10]
-	 strb	r6,[r14,#-6]
-	eor	r4,r8,r4,lsr#8
-	 strb	r7,[r14,#-2]
-	eor	r5,r9,r5,lsr#8
-	 strb	r4,[r14,#-13]
-	eor	r6,r10,r6,lsr#8
-	 strb	r5,[r14,#-9]
-	eor	r7,r11,r7,lsr#8
-	 strb	r6,[r14,#-5]
-	 strb	r7,[r14,#-1]
-	add	r8,sp,#4*(4+4)
-	ldmia	r8,{r8-r11}		@ load key material
-	ldmia	r0,{r0-r7}		@ load second half
-#ifdef __thumb2__
-	itt	hi
-#endif
-	strhi	r10,[sp,#4*(16+10)]		@ copy "rx"
-	strhi	r11,[sp,#4*(16+11)]		@ copy "rx"
-	add	r0,r8,r0	@ accumulate key material
-	add	r1,r9,r1
-	add	r2,r10,r2
-#ifdef __thumb2__
-	itete	lo
-#endif
-	eorlo	r8,r8,r8		@ zero or ...
-	ldrhsb	r8,[r12],#16			@ ... load input
-	eorlo	r9,r9,r9
-	ldrhsb	r9,[r12,#-12]
-
-	add	r3,r11,r3
-#ifdef __thumb2__
-	itete	lo
-#endif
-	eorlo	r10,r10,r10
-	ldrhsb	r10,[r12,#-8]
-	eorlo	r11,r11,r11
-	ldrhsb	r11,[r12,#-4]
-
-	eor	r0,r8,r0		@ xor with input (or zero)
-	eor	r1,r9,r1
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-15]		@ load more input
-	ldrhsb	r9,[r12,#-11]
-	eor	r2,r10,r2
-	 strb	r0,[r14],#16		@ store output
-	eor	r3,r11,r3
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-7]
-	ldrhsb	r11,[r12,#-3]
-	 strb	r1,[r14,#-12]
-	eor	r0,r8,r0,lsr#8
-	 strb	r2,[r14,#-8]
-	eor	r1,r9,r1,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-14]		@ load more input
-	ldrhsb	r9,[r12,#-10]
-	 strb	r3,[r14,#-4]
-	eor	r2,r10,r2,lsr#8
-	 strb	r0,[r14,#-15]
-	eor	r3,r11,r3,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-6]
-	ldrhsb	r11,[r12,#-2]
-	 strb	r1,[r14,#-11]
-	eor	r0,r8,r0,lsr#8
-	 strb	r2,[r14,#-7]
-	eor	r1,r9,r1,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-13]		@ load more input
-	ldrhsb	r9,[r12,#-9]
-	 strb	r3,[r14,#-3]
-	eor	r2,r10,r2,lsr#8
-	 strb	r0,[r14,#-14]
-	eor	r3,r11,r3,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-5]
-	ldrhsb	r11,[r12,#-1]
-	 strb	r1,[r14,#-10]
-	 strb	r2,[r14,#-6]
-	eor	r0,r8,r0,lsr#8
-	 strb	r3,[r14,#-2]
-	eor	r1,r9,r1,lsr#8
-	 strb	r0,[r14,#-13]
-	eor	r2,r10,r2,lsr#8
-	 strb	r1,[r14,#-9]
-	eor	r3,r11,r3,lsr#8
-	 strb	r2,[r14,#-5]
-	 strb	r3,[r14,#-1]
-	add	r8,sp,#4*(4+8)
-	ldmia	r8,{r8-r11}		@ load key material
-	add	r4,r8,r4,ror#24	@ accumulate key material
-#ifdef __thumb2__
-	itt	hi
-#endif
-	addhi	r8,r8,#1			@ next counter value
-	strhi	r8,[sp,#4*(12)]		@ save next counter value
-	add	r5,r9,r5,ror#24
-	add	r6,r10,r6,ror#24
-#ifdef __thumb2__
-	itete	lo
-#endif
-	eorlo	r8,r8,r8		@ zero or ...
-	ldrhsb	r8,[r12],#16			@ ... load input
-	eorlo	r9,r9,r9
-	ldrhsb	r9,[r12,#-12]
-
-	add	r7,r11,r7,ror#24
-#ifdef __thumb2__
-	itete	lo
-#endif
-	eorlo	r10,r10,r10
-	ldrhsb	r10,[r12,#-8]
-	eorlo	r11,r11,r11
-	ldrhsb	r11,[r12,#-4]
-
-	eor	r4,r8,r4		@ xor with input (or zero)
-	eor	r5,r9,r5
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-15]		@ load more input
-	ldrhsb	r9,[r12,#-11]
-	eor	r6,r10,r6
-	 strb	r4,[r14],#16		@ store output
-	eor	r7,r11,r7
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-7]
-	ldrhsb	r11,[r12,#-3]
-	 strb	r5,[r14,#-12]
-	eor	r4,r8,r4,lsr#8
-	 strb	r6,[r14,#-8]
-	eor	r5,r9,r5,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-14]		@ load more input
-	ldrhsb	r9,[r12,#-10]
-	 strb	r7,[r14,#-4]
-	eor	r6,r10,r6,lsr#8
-	 strb	r4,[r14,#-15]
-	eor	r7,r11,r7,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-6]
-	ldrhsb	r11,[r12,#-2]
-	 strb	r5,[r14,#-11]
-	eor	r4,r8,r4,lsr#8
-	 strb	r6,[r14,#-7]
-	eor	r5,r9,r5,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r8,[r12,#-13]		@ load more input
-	ldrhsb	r9,[r12,#-9]
-	 strb	r7,[r14,#-3]
-	eor	r6,r10,r6,lsr#8
-	 strb	r4,[r14,#-14]
-	eor	r7,r11,r7,lsr#8
-#ifdef __thumb2__
-	itt	hs
-#endif
-	ldrhsb	r10,[r12,#-5]
-	ldrhsb	r11,[r12,#-1]
-	 strb	r5,[r14,#-10]
-	 strb	r6,[r14,#-6]
-	eor	r4,r8,r4,lsr#8
-	 strb	r7,[r14,#-2]
-	eor	r5,r9,r5,lsr#8
-	 strb	r4,[r14,#-13]
-	eor	r6,r10,r6,lsr#8
-	 strb	r5,[r14,#-9]
-	eor	r7,r11,r7,lsr#8
-	 strb	r6,[r14,#-5]
-	 strb	r7,[r14,#-1]
-#ifdef __thumb2__
-	it	ne
-#endif
-	ldrne	r8,[sp,#4*(32+2)]		@ re-load len
-#ifdef __thumb2__
-	it	hs
-#endif
-	subhs	r11,r8,#64			@ len-=64
-	bhi	.Loop_outer
-
-	beq	.Ldone
-#endif
-
-.Ltail:
-	ldr	r12,[sp,#4*(32+1)]	@ load inp
-	add	r9,sp,#4*(0)
-	ldr	r14,[sp,#4*(32+0)]	@ load out
-
-.Loop_tail:
-	ldrb	r10,[r9],#1	@ read buffer on stack
-	ldrb	r11,[r12],#1		@ read input
-	subs	r8,r8,#1
-	eor	r11,r11,r10
-	strb	r11,[r14],#1		@ store output
-	bne	.Loop_tail
-
-.Ldone:
-	add	sp,sp,#4*(32+3)
-	ldmia	sp!,{r4-r11,pc}
-
-.align	5
-.Lsigma2:
-.long	0x61707865,0x3320646e,0x79622d32,0x6b206574	@ endian-neutral
-.Lone2:
-.long	1,0,0,0
-.word	-1
-
-.arch	armv7-a
-.fpu	neon
-
-.align	5
-ENTRY(chacha20_neon)
-	ldr		r12,[sp,#0]		@ pull pointer to counter and nonce
-	stmdb		sp!,{r0-r2,r4-r11,lr}
-	cmp		r2,#0			@ len==0?
-#ifdef	__thumb2__
-	itt		eq
-#endif
-	addeq		sp,sp,#4*3
-	beq		.Lno_data_neon
-.Lchacha20_neon_begin:
-	adr		r14,.Lsigma2
-	vstmdb		sp!,{d8-d15}		@ ABI spec says so
-	stmdb		sp!,{r0-r3}
-
-	vld1.32		{q1-q2},[r3]		@ load key
-	ldmia		r3,{r4-r11}		@ load key
-
-	sub		sp,sp,#4*(16+16)
-	vld1.32		{q3},[r12]		@ load counter and nonce
-	add		r12,sp,#4*8
-	ldmia		r14,{r0-r3}		@ load sigma
-	vld1.32		{q0},[r14]!		@ load sigma
-	vld1.32		{q12},[r14]!		@ one
-	@ vld1.32	{d30},[r14]		@ rot8
-	vst1.32		{q2-q3},[r12]		@ copy 1/2key|counter|nonce
-	vst1.32		{q0-q1},[sp]		@ copy sigma|1/2key
-
-	str		r10,[sp,#4*(16+10)]	@ off-load "rx"
-	str		r11,[sp,#4*(16+11)]	@ off-load "rx"
-	vshl.i32	d26,d24,#1	@ two
-	vstr		d24,[sp,#4*(16+0)]
-	vshl.i32	d28,d24,#2	@ four
-	vstr		d26,[sp,#4*(16+2)]
-	vmov		q4,q0
-	vstr		d28,[sp,#4*(16+4)]
-	vmov		q8,q0
-	@ vstr		d30,[sp,#4*(16+6)]
-	vmov		q5,q1
-	vmov		q9,q1
-	b		.Loop_neon_enter
-
-.align	4
-.Loop_neon_outer:
-	ldmia		sp,{r0-r9}		@ load key material
-	cmp		r11,#64*2		@ if len<=64*2
-	bls		.Lbreak_neon		@ switch to integer-only
-	@ vldr		d30,[sp,#4*(16+6)]	@ rot8
-	vmov		q4,q0
-	str		r11,[sp,#4*(32+2)]	@ save len
-	vmov		q8,q0
-	str		r12,  [sp,#4*(32+1)]	@ save inp
-	vmov		q5,q1
-	str		r14,  [sp,#4*(32+0)]	@ save out
-	vmov		q9,q1
-.Loop_neon_enter:
-	ldr		r11, [sp,#4*(15)]
-	 mov		r4,r4,ror#19	@ twist b[0..3]
-	vadd.i32	q7,q3,q12		@ counter+1
-	ldr		r12,[sp,#4*(12)]	@ modulo-scheduled load
-	 mov		r5,r5,ror#19
-	vmov		q6,q2
-	ldr		r10, [sp,#4*(13)]
-	 mov		r6,r6,ror#19
-	vmov		q10,q2
-	ldr		r14,[sp,#4*(14)]
-	 mov		r7,r7,ror#19
-	vadd.i32	q11,q7,q12		@ counter+2
-	add		r12,r12,#3	@ counter+3
-	mov		r11,r11,ror#8	@ twist d[0..3]
-	mov		r12,r12,ror#8
-	mov		r10,r10,ror#8
-	mov		r14,r14,ror#8
-	str		r11, [sp,#4*(16+15)]
-	mov		r11,#10
-	b		.Loop_neon
-
-.align	4
-.Loop_neon:
-	subs		r11,r11,#1
-	vadd.i32	q0,q0,q1
-	add	r0,r0,r4,ror#13
-	vadd.i32	q4,q4,q5
-	add	r1,r1,r5,ror#13
-	vadd.i32	q8,q8,q9
-	eor	r12,r0,r12,ror#24
-	veor	q3,q3,q0
-	eor	r10,r1,r10,ror#24
-	veor	q7,q7,q4
-	add	r8,r8,r12,ror#16
-	veor	q11,q11,q8
-	add	r9,r9,r10,ror#16
-	vrev32.16	q3,q3
-	eor	r4,r8,r4,ror#13
-	vrev32.16	q7,q7
-	eor	r5,r9,r5,ror#13
-	vrev32.16	q11,q11
-	add	r0,r0,r4,ror#20
-	vadd.i32	q2,q2,q3
-	add	r1,r1,r5,ror#20
-	vadd.i32	q6,q6,q7
-	eor	r12,r0,r12,ror#16
-	vadd.i32	q10,q10,q11
-	eor	r10,r1,r10,ror#16
-	veor	q12,q1,q2
-	add	r8,r8,r12,ror#24
-	veor	q13,q5,q6
-	str	r10,[sp,#4*(16+13)]
-	veor	q14,q9,q10
-	add	r9,r9,r10,ror#24
-	vshr.u32	q1,q12,#20
-	ldr	r10,[sp,#4*(16+15)]
-	vshr.u32	q5,q13,#20
-	str	r8,[sp,#4*(16+8)]
-	vshr.u32	q9,q14,#20
-	eor	r4,r4,r8,ror#12
-	vsli.32	q1,q12,#12
-	str	r9,[sp,#4*(16+9)]
-	vsli.32	q5,q13,#12
-	eor	r5,r5,r9,ror#12
-	vsli.32	q9,q14,#12
-	ldr	r8,[sp,#4*(16+10)]
-	vadd.i32	q0,q0,q1
-	add	r2,r2,r6,ror#13
-	vadd.i32	q4,q4,q5
-	ldr	r9,[sp,#4*(16+11)]
-	vadd.i32	q8,q8,q9
-	add	r3,r3,r7,ror#13
-	veor	q12,q3,q0
-	eor	r14,r2,r14,ror#24
-	veor	q13,q7,q4
-	eor	r10,r3,r10,ror#24
-	veor	q14,q11,q8
-	add	r8,r8,r14,ror#16
-	vshr.u32	q3,q12,#24
-	add	r9,r9,r10,ror#16
-	vshr.u32	q7,q13,#24
-	eor	r6,r8,r6,ror#13
-	vshr.u32	q11,q14,#24
-	eor	r7,r9,r7,ror#13
-	vsli.32	q3,q12,#8
-	add	r2,r2,r6,ror#20
-	vsli.32	q7,q13,#8
-	add	r3,r3,r7,ror#20
-	vsli.32	q11,q14,#8
-	eor	r14,r2,r14,ror#16
-	vadd.i32	q2,q2,q3
-	eor	r10,r3,r10,ror#16
-	vadd.i32	q6,q6,q7
-	add	r8,r8,r14,ror#24
-	vadd.i32	q10,q10,q11
-	add	r9,r9,r10,ror#24
-	veor	q12,q1,q2
-	eor	r6,r6,r8,ror#12
-	veor	q13,q5,q6
-	eor	r7,r7,r9,ror#12
-	veor	q14,q9,q10
-	vshr.u32	q1,q12,#25
-	vshr.u32	q5,q13,#25
-	vshr.u32	q9,q14,#25
-	vsli.32	q1,q12,#7
-	vsli.32	q5,q13,#7
-	vsli.32	q9,q14,#7
-	vext.8	q2,q2,q2,#8
-	vext.8	q6,q6,q6,#8
-	vext.8	q10,q10,q10,#8
-	vext.8	q1,q1,q1,#4
-	vext.8	q5,q5,q5,#4
-	vext.8	q9,q9,q9,#4
-	vext.8	q3,q3,q3,#12
-	vext.8	q7,q7,q7,#12
-	vext.8	q11,q11,q11,#12
-	vadd.i32	q0,q0,q1
-	add	r0,r0,r5,ror#13
-	vadd.i32	q4,q4,q5
-	add	r1,r1,r6,ror#13
-	vadd.i32	q8,q8,q9
-	eor	r10,r0,r10,ror#24
-	veor	q3,q3,q0
-	eor	r12,r1,r12,ror#24
-	veor	q7,q7,q4
-	add	r8,r8,r10,ror#16
-	veor	q11,q11,q8
-	add	r9,r9,r12,ror#16
-	vrev32.16	q3,q3
-	eor	r5,r8,r5,ror#13
-	vrev32.16	q7,q7
-	eor	r6,r9,r6,ror#13
-	vrev32.16	q11,q11
-	add	r0,r0,r5,ror#20
-	vadd.i32	q2,q2,q3
-	add	r1,r1,r6,ror#20
-	vadd.i32	q6,q6,q7
-	eor	r10,r0,r10,ror#16
-	vadd.i32	q10,q10,q11
-	eor	r12,r1,r12,ror#16
-	veor	q12,q1,q2
-	str	r10,[sp,#4*(16+15)]
-	veor	q13,q5,q6
-	add	r8,r8,r10,ror#24
-	veor	q14,q9,q10
-	ldr	r10,[sp,#4*(16+13)]
-	vshr.u32	q1,q12,#20
-	add	r9,r9,r12,ror#24
-	vshr.u32	q5,q13,#20
-	str	r8,[sp,#4*(16+10)]
-	vshr.u32	q9,q14,#20
-	eor	r5,r5,r8,ror#12
-	vsli.32	q1,q12,#12
-	str	r9,[sp,#4*(16+11)]
-	vsli.32	q5,q13,#12
-	eor	r6,r6,r9,ror#12
-	vsli.32	q9,q14,#12
-	ldr	r8,[sp,#4*(16+8)]
-	vadd.i32	q0,q0,q1
-	add	r2,r2,r7,ror#13
-	vadd.i32	q4,q4,q5
-	ldr	r9,[sp,#4*(16+9)]
-	vadd.i32	q8,q8,q9
-	add	r3,r3,r4,ror#13
-	veor	q12,q3,q0
-	eor	r10,r2,r10,ror#24
-	veor	q13,q7,q4
-	eor	r14,r3,r14,ror#24
-	veor	q14,q11,q8
-	add	r8,r8,r10,ror#16
-	vshr.u32	q3,q12,#24
-	add	r9,r9,r14,ror#16
-	vshr.u32	q7,q13,#24
-	eor	r7,r8,r7,ror#13
-	vshr.u32	q11,q14,#24
-	eor	r4,r9,r4,ror#13
-	vsli.32	q3,q12,#8
-	add	r2,r2,r7,ror#20
-	vsli.32	q7,q13,#8
-	add	r3,r3,r4,ror#20
-	vsli.32	q11,q14,#8
-	eor	r10,r2,r10,ror#16
-	vadd.i32	q2,q2,q3
-	eor	r14,r3,r14,ror#16
-	vadd.i32	q6,q6,q7
-	add	r8,r8,r10,ror#24
-	vadd.i32	q10,q10,q11
-	add	r9,r9,r14,ror#24
-	veor	q12,q1,q2
-	eor	r7,r7,r8,ror#12
-	veor	q13,q5,q6
-	eor	r4,r4,r9,ror#12
-	veor	q14,q9,q10
-	vshr.u32	q1,q12,#25
-	vshr.u32	q5,q13,#25
-	vshr.u32	q9,q14,#25
-	vsli.32	q1,q12,#7
-	vsli.32	q5,q13,#7
-	vsli.32	q9,q14,#7
-	vext.8	q2,q2,q2,#8
-	vext.8	q6,q6,q6,#8
-	vext.8	q10,q10,q10,#8
-	vext.8	q1,q1,q1,#12
-	vext.8	q5,q5,q5,#12
-	vext.8	q9,q9,q9,#12
-	vext.8	q3,q3,q3,#4
-	vext.8	q7,q7,q7,#4
-	vext.8	q11,q11,q11,#4
-	bne		.Loop_neon
-
-	add		r11,sp,#32
-	vld1.32		{q12-q13},[sp]		@ load key material
-	vld1.32		{q14-q15},[r11]
-
-	ldr		r11,[sp,#4*(32+2)]	@ load len
-
-	str		r8, [sp,#4*(16+8)]	@ modulo-scheduled store
-	str		r9, [sp,#4*(16+9)]
-	str		r12,[sp,#4*(16+12)]
-	str		r10, [sp,#4*(16+13)]
-	str		r14,[sp,#4*(16+14)]
-
-	@ at this point we have first half of 512-bit result in
-	@ rx and second half at sp+4*(16+8)
-
-	ldr		r12,[sp,#4*(32+1)]	@ load inp
-	ldr		r14,[sp,#4*(32+0)]	@ load out
-
-	vadd.i32	q0,q0,q12		@ accumulate key material
-	vadd.i32	q4,q4,q12
-	vadd.i32	q8,q8,q12
-	vldr		d24,[sp,#4*(16+0)]	@ one
-
-	vadd.i32	q1,q1,q13
-	vadd.i32	q5,q5,q13
-	vadd.i32	q9,q9,q13
-	vldr		d26,[sp,#4*(16+2)]	@ two
-
-	vadd.i32	q2,q2,q14
-	vadd.i32	q6,q6,q14
-	vadd.i32	q10,q10,q14
-	vadd.i32	d14,d14,d24	@ counter+1
-	vadd.i32	d22,d22,d26	@ counter+2
-
-	vadd.i32	q3,q3,q15
-	vadd.i32	q7,q7,q15
-	vadd.i32	q11,q11,q15
-
-	cmp		r11,#64*4
-	blo		.Ltail_neon
-
-	vld1.8		{q12-q13},[r12]!	@ load input
-	 mov		r11,sp
-	vld1.8		{q14-q15},[r12]!
-	veor		q0,q0,q12		@ xor with input
-	veor		q1,q1,q13
-	vld1.8		{q12-q13},[r12]!
-	veor		q2,q2,q14
-	veor		q3,q3,q15
-	vld1.8		{q14-q15},[r12]!
-
-	veor		q4,q4,q12
-	 vst1.8		{q0-q1},[r14]!	@ store output
-	veor		q5,q5,q13
-	vld1.8		{q12-q13},[r12]!
-	veor		q6,q6,q14
-	 vst1.8		{q2-q3},[r14]!
-	veor		q7,q7,q15
-	vld1.8		{q14-q15},[r12]!
-
-	veor		q8,q8,q12
-	 vld1.32	{q0-q1},[r11]!	@ load for next iteration
-	 veor		d25,d25,d25
-	 vldr		d24,[sp,#4*(16+4)]	@ four
-	veor		q9,q9,q13
-	 vld1.32	{q2-q3},[r11]
-	veor		q10,q10,q14
-	 vst1.8		{q4-q5},[r14]!
-	veor		q11,q11,q15
-	 vst1.8		{q6-q7},[r14]!
-
-	vadd.i32	d6,d6,d24	@ next counter value
-	vldr		d24,[sp,#4*(16+0)]	@ one
-
-	ldmia		sp,{r8-r11}	@ load key material
-	add		r0,r0,r8	@ accumulate key material
-	ldr		r8,[r12],#16		@ load input
-	 vst1.8		{q8-q9},[r14]!
-	add		r1,r1,r9
-	ldr		r9,[r12,#-12]
-	 vst1.8		{q10-q11},[r14]!
-	add		r2,r2,r10
-	ldr		r10,[r12,#-8]
-	add		r3,r3,r11
-	ldr		r11,[r12,#-4]
-#ifdef	__ARMEB__
-	rev		r0,r0
-	rev		r1,r1
-	rev		r2,r2
-	rev		r3,r3
-#endif
-	eor		r0,r0,r8	@ xor with input
-	 add		r8,sp,#4*(4)
-	eor		r1,r1,r9
-	str		r0,[r14],#16		@ store output
-	eor		r2,r2,r10
-	str		r1,[r14,#-12]
-	eor		r3,r3,r11
-	 ldmia		r8,{r8-r11}	@ load key material
-	str		r2,[r14,#-8]
-	str		r3,[r14,#-4]
-
-	add		r4,r8,r4,ror#13 @ accumulate key material
-	ldr		r8,[r12],#16		@ load input
-	add		r5,r9,r5,ror#13
-	ldr		r9,[r12,#-12]
-	add		r6,r10,r6,ror#13
-	ldr		r10,[r12,#-8]
-	add		r7,r11,r7,ror#13
-	ldr		r11,[r12,#-4]
-#ifdef	__ARMEB__
-	rev		r4,r4
-	rev		r5,r5
-	rev		r6,r6
-	rev		r7,r7
-#endif
-	eor		r4,r4,r8
-	 add		r8,sp,#4*(8)
-	eor		r5,r5,r9
-	str		r4,[r14],#16		@ store output
-	eor		r6,r6,r10
-	str		r5,[r14,#-12]
-	eor		r7,r7,r11
-	 ldmia		r8,{r8-r11}	@ load key material
-	str		r6,[r14,#-8]
-	 add		r0,sp,#4*(16+8)
-	str		r7,[r14,#-4]
-
-	ldmia		r0,{r0-r7}	@ load second half
-
-	add		r0,r0,r8	@ accumulate key material
-	ldr		r8,[r12],#16		@ load input
-	add		r1,r1,r9
-	ldr		r9,[r12,#-12]
-#ifdef __thumb2__
-	it	hi
-#endif
-	 strhi		r10,[sp,#4*(16+10)]	@ copy "rx" while at it
-	add		r2,r2,r10
-	ldr		r10,[r12,#-8]
-#ifdef __thumb2__
-	it	hi
-#endif
-	 strhi		r11,[sp,#4*(16+11)]	@ copy "rx" while at it
-	add		r3,r3,r11
-	ldr		r11,[r12,#-4]
-#ifdef	__ARMEB__
-	rev		r0,r0
-	rev		r1,r1
-	rev		r2,r2
-	rev		r3,r3
-#endif
-	eor		r0,r0,r8
-	 add		r8,sp,#4*(12)
-	eor		r1,r1,r9
-	str		r0,[r14],#16		@ store output
-	eor		r2,r2,r10
-	str		r1,[r14,#-12]
-	eor		r3,r3,r11
-	 ldmia		r8,{r8-r11}	@ load key material
-	str		r2,[r14,#-8]
-	str		r3,[r14,#-4]
-
-	add		r4,r8,r4,ror#24 @ accumulate key material
-	 add		r8,r8,#4		@ next counter value
-	add		r5,r9,r5,ror#24
-	 str		r8,[sp,#4*(12)]	@ save next counter value
-	ldr		r8,[r12],#16		@ load input
-	add		r6,r10,r6,ror#24
-	 add		r4,r4,#3		@ counter+3
-	ldr		r9,[r12,#-12]
-	add		r7,r11,r7,ror#24
-	ldr		r10,[r12,#-8]
-	ldr		r11,[r12,#-4]
-#ifdef	__ARMEB__
-	rev		r4,r4
-	rev		r5,r5
-	rev		r6,r6
-	rev		r7,r7
-#endif
-	eor		r4,r4,r8
-#ifdef __thumb2__
-	it	hi
-#endif
-	 ldrhi		r8,[sp,#4*(32+2)]	@ re-load len
-	eor		r5,r5,r9
-	eor		r6,r6,r10
-	str		r4,[r14],#16		@ store output
-	eor		r7,r7,r11
-	str		r5,[r14,#-12]
-	 sub		r11,r8,#64*4	@ len-=64*4
-	str		r6,[r14,#-8]
-	str		r7,[r14,#-4]
-	bhi		.Loop_neon_outer
-
-	b		.Ldone_neon
-
-.align	4
-.Lbreak_neon:
-	@ harmonize NEON and integer-only stack frames: load data
-	@ from NEON frame, but save to integer-only one; distance
-	@ between the two is 4*(32+4+16-32)=4*(20).
-
-	str		r11, [sp,#4*(20+32+2)]	@ save len
-	 add		r11,sp,#4*(32+4)
-	str		r12,   [sp,#4*(20+32+1)]	@ save inp
-	str		r14,   [sp,#4*(20+32+0)]	@ save out
-
-	ldr		r12,[sp,#4*(16+10)]
-	ldr		r14,[sp,#4*(16+11)]
-	 vldmia		r11,{d8-d15}			@ fulfill ABI requirement
-	str		r12,[sp,#4*(20+16+10)]	@ copy "rx"
-	str		r14,[sp,#4*(20+16+11)]	@ copy "rx"
-
-	ldr		r11, [sp,#4*(15)]
-	 mov		r4,r4,ror#19		@ twist b[0..3]
-	ldr		r12,[sp,#4*(12)]		@ modulo-scheduled load
-	 mov		r5,r5,ror#19
-	ldr		r10, [sp,#4*(13)]
-	 mov		r6,r6,ror#19
-	ldr		r14,[sp,#4*(14)]
-	 mov		r7,r7,ror#19
-	mov		r11,r11,ror#8		@ twist d[0..3]
-	mov		r12,r12,ror#8
-	mov		r10,r10,ror#8
-	mov		r14,r14,ror#8
-	str		r11, [sp,#4*(20+16+15)]
-	add		r11,sp,#4*(20)
-	vst1.32		{q0-q1},[r11]!		@ copy key
-	add		sp,sp,#4*(20)			@ switch frame
-	vst1.32		{q2-q3},[r11]
-	mov		r11,#10
-	b		.Loop				@ go integer-only
-
-.align	4
-.Ltail_neon:
-	cmp		r11,#64*3
-	bhs		.L192_or_more_neon
-	cmp		r11,#64*2
-	bhs		.L128_or_more_neon
-	cmp		r11,#64*1
-	bhs		.L64_or_more_neon
-
-	add		r8,sp,#4*(8)
-	vst1.8		{q0-q1},[sp]
-	add		r10,sp,#4*(0)
-	vst1.8		{q2-q3},[r8]
-	b		.Loop_tail_neon
-
-.align	4
-.L64_or_more_neon:
-	vld1.8		{q12-q13},[r12]!
-	vld1.8		{q14-q15},[r12]!
-	veor		q0,q0,q12
-	veor		q1,q1,q13
-	veor		q2,q2,q14
-	veor		q3,q3,q15
-	vst1.8		{q0-q1},[r14]!
-	vst1.8		{q2-q3},[r14]!
-
-	beq		.Ldone_neon
-
-	add		r8,sp,#4*(8)
-	vst1.8		{q4-q5},[sp]
-	add		r10,sp,#4*(0)
-	vst1.8		{q6-q7},[r8]
-	sub		r11,r11,#64*1	@ len-=64*1
-	b		.Loop_tail_neon
-
-.align	4
-.L128_or_more_neon:
-	vld1.8		{q12-q13},[r12]!
-	vld1.8		{q14-q15},[r12]!
-	veor		q0,q0,q12
-	veor		q1,q1,q13
-	vld1.8		{q12-q13},[r12]!
-	veor		q2,q2,q14
-	veor		q3,q3,q15
-	vld1.8		{q14-q15},[r12]!
-
-	veor		q4,q4,q12
-	veor		q5,q5,q13
-	 vst1.8		{q0-q1},[r14]!
-	veor		q6,q6,q14
-	 vst1.8		{q2-q3},[r14]!
-	veor		q7,q7,q15
-	vst1.8		{q4-q5},[r14]!
-	vst1.8		{q6-q7},[r14]!
-
-	beq		.Ldone_neon
-
-	add		r8,sp,#4*(8)
-	vst1.8		{q8-q9},[sp]
-	add		r10,sp,#4*(0)
-	vst1.8		{q10-q11},[r8]
-	sub		r11,r11,#64*2	@ len-=64*2
-	b		.Loop_tail_neon
-
-.align	4
-.L192_or_more_neon:
-	vld1.8		{q12-q13},[r12]!
-	vld1.8		{q14-q15},[r12]!
-	veor		q0,q0,q12
-	veor		q1,q1,q13
-	vld1.8		{q12-q13},[r12]!
-	veor		q2,q2,q14
-	veor		q3,q3,q15
-	vld1.8		{q14-q15},[r12]!
-
-	veor		q4,q4,q12
-	veor		q5,q5,q13
-	vld1.8		{q12-q13},[r12]!
-	veor		q6,q6,q14
-	 vst1.8		{q0-q1},[r14]!
-	veor		q7,q7,q15
-	vld1.8		{q14-q15},[r12]!
-
-	veor		q8,q8,q12
-	 vst1.8		{q2-q3},[r14]!
-	veor		q9,q9,q13
-	 vst1.8		{q4-q5},[r14]!
-	veor		q10,q10,q14
-	 vst1.8		{q6-q7},[r14]!
-	veor		q11,q11,q15
-	vst1.8		{q8-q9},[r14]!
-	vst1.8		{q10-q11},[r14]!
-
-	beq		.Ldone_neon
-
-	ldmia		sp,{r8-r11}	@ load key material
-	add		r0,r0,r8	@ accumulate key material
-	 add		r8,sp,#4*(4)
-	add		r1,r1,r9
-	add		r2,r2,r10
-	add		r3,r3,r11
-	 ldmia		r8,{r8-r11}	@ load key material
-
-	add		r4,r8,r4,ror#13 @ accumulate key material
-	 add		r8,sp,#4*(8)
-	add		r5,r9,r5,ror#13
-	add		r6,r10,r6,ror#13
-	add		r7,r11,r7,ror#13
-	 ldmia		r8,{r8-r11}	@ load key material
-#ifdef	__ARMEB__
-	rev		r0,r0
-	rev		r1,r1
-	rev		r2,r2
-	rev		r3,r3
-	rev		r4,r4
-	rev		r5,r5
-	rev		r6,r6
-	rev		r7,r7
-#endif
-	stmia		sp,{r0-r7}
-	 add		r0,sp,#4*(16+8)
-
-	ldmia		r0,{r0-r7}	@ load second half
-
-	add		r0,r0,r8	@ accumulate key material
-	 add		r8,sp,#4*(12)
-	add		r1,r1,r9
-	add		r2,r2,r10
-	add		r3,r3,r11
-	 ldmia		r8,{r8-r11}	@ load key material
-
-	add		r4,r8,r4,ror#24 @ accumulate key material
-	 add		r8,sp,#4*(8)
-	add		r5,r9,r5,ror#24
-	 add		r4,r4,#3		@ counter+3
-	add		r6,r10,r6,ror#24
-	add		r7,r11,r7,ror#24
-	 ldr		r11,[sp,#4*(32+2)]	@ re-load len
-#ifdef	__ARMEB__
-	rev		r0,r0
-	rev		r1,r1
-	rev		r2,r2
-	rev		r3,r3
-	rev		r4,r4
-	rev		r5,r5
-	rev		r6,r6
-	rev		r7,r7
-#endif
-	stmia		r8,{r0-r7}
-	 add		r10,sp,#4*(0)
-	 sub		r11,r11,#64*3	@ len-=64*3
-
-.Loop_tail_neon:
-	ldrb		r8,[r10],#1	@ read buffer on stack
-	ldrb		r9,[r12],#1		@ read input
-	subs		r11,r11,#1
-	eor		r8,r8,r9
-	strb		r8,[r14],#1		@ store output
-	bne		.Loop_tail_neon
-
-.Ldone_neon:
-	add		sp,sp,#4*(32+4)
-	vldmia		sp,{d8-d15}
-	add		sp,sp,#4*(16+3)
-.Lno_data_neon:
-	ldmia		sp!,{r4-r11,pc}
-ENDPROC(chacha20_neon)
-#endif
diff --git a/src/crypto/zinc/chacha20/chacha20-arm.pl b/src/crypto/zinc/chacha20/chacha20-arm.pl
new file mode 100644
index 0000000..3621957
--- /dev/null
+++ b/src/crypto/zinc/chacha20/chacha20-arm.pl
@@ -0,0 +1,1227 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+#
+# This code is taken from the OpenSSL project but the author, Andy Polyakov,
+# has relicensed it under the licenses specified in the SPDX header above.
+# The original headers, including the original license headers, are
+# included below for completeness.
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# December 2014
+#
+# ChaCha20 for ARMv4.
+#
+# September 2018
+#
+# Improve scalar performance per Eric Biggers' suggestion to eliminate
+# separate rotates. This requires b[0..3] and d[0..3] to be maintained
+# pre-rotated, hence odd twists prior inner loop and when accumulating
+# key material. Since amount of instructions is reduced as result, even
+# NEON performance is improved somewhat, most notably by ~9% on low-end
+# Cortex-A5/A7. Full unroll was shown to provide even better scalar
+# performance on Cortex-A5/A7, naturally at the cost of manyfold size
+# increase. We let it be. Oversized code works in benchmarks, but is not
+# necessarily optimal in real life, when it's likely to be out-of-cache
+# upon entry and evict significant part of cache upon completion.
+#
+# Performance in cycles per byte out of large buffer.
+#
+#			IALU/gcc-4.4    1xNEON      3xNEON+1xIALU
+#
+# Cortex-A5		14.2(*)/+160%   21.8        12.9(**)
+# Cortex-A8		10.2(*)/+190%   13.9        6.10
+# Cortex-A9		10.8(*)/+150%   14.3        6.50
+# Cortex-A15		11.0/+40%       16.0        4.90
+# Snapdragon S4		13.9(***)/+90%  13.6        4.90
+#
+# (*)	most "favourable" result for aligned data on little-endian
+#	processor, result for misaligned data is 10-15% lower;
+# (**)	pure 4xNEON [with "vertical" layout] was shown to provide ~8%
+#	better performance on Cortex-A5/A7, but not on others;
+# (***)	it's 17% slower than original, trade-off is considered
+#	acceptable, because of improvement on others, specifically
+#	+36% on Cortex-A5/A7 and +20% on Cortex-A9;
+
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
+
+sub AUTOLOAD()		# thunk [simplified] x86-style perlasm
+{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./;
+  my $arg = pop;
+    $arg = "#$arg" if ($arg*1 eq $arg);
+    $code .= "\t$opcode\t".join(',',@_,$arg)."\n";
+}
+
+my @x=map("r$_",(0..7,"x","x","x","x",12,"x",14,"x"));
+my @t=map("r$_",(8..11));
+
+sub ROUND {
+my ($a0,$b0,$c0,$d0)=@_;
+my ($a1,$b1,$c1,$d1)=map(($_&~3)+(($_+1)&3),($a0,$b0,$c0,$d0));
+my ($a2,$b2,$c2,$d2)=map(($_&~3)+(($_+1)&3),($a1,$b1,$c1,$d1));
+my ($a3,$b3,$c3,$d3)=map(($_&~3)+(($_+1)&3),($a2,$b2,$c2,$d2));
+my $odd = $d0&1;
+my ($xc,$xc_) = (@t[0..1]);
+my ($xd,$xd_) = $odd ? (@t[2],@x[$d1]) : (@x[$d0],@t[2]);
+my @ret;
+
+	# Consider order in which variables are addressed by their
+	# index:
+	#
+	#       a   b   c   d
+	#
+	#       0   4   8  12 < even round
+	#       1   5   9  13
+	#       2   6  10  14
+	#       3   7  11  15
+	#       0   5  10  15 < odd round
+	#       1   6  11  12
+	#       2   7   8  13
+	#       3   4   9  14
+	#
+	# 'a', 'b' are permanently allocated in registers, @x[0..7],
+	# while 'c's and pair of 'd's are maintained in memory. If
+	# you observe 'c' column, you'll notice that pair of 'c's is
+	# invariant between rounds. This means that we have to reload
+	# them once per round, in the middle. This is why you'll see
+	# bunch of 'c' stores and loads in the middle, but none in
+	# the beginning or end. If you observe 'd' column, you'll
+	# notice that 15 and 13 are reused in next pair of rounds.
+	# This is why these two are chosen for offloading to memory,
+	# to make loads count more.
+							push @ret,(
+	"&add	(@x[$a0],@x[$a0],@x[$b0],'ror#13')",
+	 "&add	(@x[$a1],@x[$a1],@x[$b1],'ror#13')",
+	"&eor	($xd,@x[$a0],$xd,'ror#24')",
+	 "&eor	($xd_,@x[$a1],$xd_,'ror#24')",
+
+	"&add	($xc,$xc,$xd,'ror#16')",
+	 "&add	($xc_,$xc_,$xd_,'ror#16')",
+	"&eor	(@x[$b0],$xc, @x[$b0],'ror#13')",
+	 "&eor	(@x[$b1],$xc_,@x[$b1],'ror#13')",
+
+	"&add	(@x[$a0],@x[$a0],@x[$b0],'ror#20')",
+	 "&add	(@x[$a1],@x[$a1],@x[$b1],'ror#20')",
+	"&eor	($xd,@x[$a0],$xd,'ror#16')",
+	 "&eor	($xd_,@x[$a1],$xd_,'ror#16')"		);
+							push @ret,(
+	"&str	($xd,'[sp,#4*(16+$d0)]')"		) if ($odd);
+							push @ret,(
+	"&add	($xc,$xc,$xd,'ror#24')"			);
+							push @ret,(
+	"&ldr	($xd,'[sp,#4*(16+$d2)]')"		) if ($odd);
+							push @ret,(
+	 "&str	($xd_,'[sp,#4*(16+$d1)]')"		) if (!$odd);
+							push @ret,(
+	 "&add	($xc_,$xc_,$xd_,'ror#24')"		);
+							push @ret,(
+	 "&ldr	($xd_,'[sp,#4*(16+$d3)]')"		) if (!$odd);
+							push @ret,(
+	"&str	($xc,'[sp,#4*(16+$c0)]')",
+	"&eor	(@x[$b0],@x[$b0],$xc,'ror#12')",
+	 "&str	($xc_,'[sp,#4*(16+$c1)]')",
+	 "&eor	(@x[$b1],@x[$b1],$xc_,'ror#12')"	);
+
+	$xd=@x[$d2]					if (!$odd);
+	$xd_=@x[$d3]					if ($odd);
+							push @ret,(
+	"&ldr	($xc,'[sp,#4*(16+$c2)]')",
+	"&add	(@x[$a2],@x[$a2],@x[$b2],'ror#13')",
+	 "&ldr	($xc_,'[sp,#4*(16+$c3)]')",
+	 "&add	(@x[$a3],@x[$a3],@x[$b3],'ror#13')",
+	"&eor	($xd,@x[$a2],$xd,'ror#24')",
+	 "&eor	($xd_,@x[$a3],$xd_,'ror#24')",
+
+	"&add	($xc,$xc,$xd,'ror#16')",
+	 "&add	($xc_,$xc_,$xd_,'ror#16')",
+	"&eor	(@x[$b2],$xc, @x[$b2],'ror#13')",
+	 "&eor	(@x[$b3],$xc_,@x[$b3],'ror#13')",
+
+	"&add	(@x[$a2],@x[$a2],@x[$b2],'ror#20')",
+	 "&add	(@x[$a3],@x[$a3],@x[$b3],'ror#20')",
+	"&eor	($xd,@x[$a2],$xd,'ror#16')",
+	 "&eor	($xd_,@x[$a3],$xd_,'ror#16')",
+
+	"&add	($xc,$xc,$xd,'ror#24')",
+	 "&add	($xc_,$xc_,$xd_,'ror#24')",
+	"&eor	(@x[$b2],@x[$b2],$xc,'ror#12')",
+	 "&eor	(@x[$b3],@x[$b3],$xc_,'ror#12')"	);
+
+	@ret;
+}
+
+$code.=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
+# define ChaCha20_ctr32 chacha20_arm_cryptogams
+# define ChaCha20_neon  chacha20_neon
+#endif
+
+.text
+#if defined(__thumb2__) || defined(__clang__)
+.syntax	unified
+# define ldrhsb	ldrbhs
+#endif
+#if defined(__thumb2__)
+.thumb
+#else
+.code	32
+#endif
+
+.align	5
+.Lsigma:
+.long	0x61707865,0x3320646e,0x79622d32,0x6b206574	@ endian-neutral
+.Lone:
+.long	1,0,0,0
+.Lrot8:
+.long	0x02010003,0x06050407
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word   OPENSSL_armcap_P-.LChaCha20_ctr32
+#else
+.word	-1
+#endif
+
+.globl	ChaCha20_ctr32
+.type	ChaCha20_ctr32,%function
+.align	5
+ChaCha20_ctr32:
+.LChaCha20_ctr32:
+	ldr	r12,[sp,#0]		@ pull pointer to counter and nonce
+	stmdb	sp!,{r0-r2,r4-r11,lr}
+#if __ARM_ARCH__<7 && !defined(__thumb2__)
+	sub	r14,pc,#16		@ ChaCha20_ctr32
+#else
+	adr	r14,.LChaCha20_ctr32
+#endif
+	cmp	r2,#0			@ len==0?
+#ifdef	__thumb2__
+	itt	eq
+#endif
+	addeq	sp,sp,#4*3
+	beq	.Lno_data
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	cmp	r2,#192			@ test len
+	bls	.Lshort
+	ldr	r4,[r14,#-24]
+	ldr	r4,[r14,r4]
+# ifdef	__APPLE__
+	ldr	r4,[r4]
+# endif
+	tst	r4,#ARMV7_NEON
+	bne	.LChaCha20_neon
+.Lshort:
+#endif
+	ldmia	r12,{r4-r7}		@ load counter and nonce
+	sub	sp,sp,#4*(16)		@ off-load area
+	sub	r14,r14,#64		@ .Lsigma
+	stmdb	sp!,{r4-r7}		@ copy counter and nonce
+	ldmia	r3,{r4-r11}		@ load key
+	ldmia	r14,{r0-r3}		@ load sigma
+	stmdb	sp!,{r4-r11}		@ copy key
+	stmdb	sp!,{r0-r3}		@ copy sigma
+	str	r10,[sp,#4*(16+10)]	@ off-load "@x[10]"
+	str	r11,[sp,#4*(16+11)]	@ off-load "@x[11]"
+	b	.Loop_outer_enter
+
+.align	4
+.Loop_outer:
+	ldmia	sp,{r0-r9}		@ load key material
+	str	@t[3],[sp,#4*(32+2)]	@ save len
+	str	r12,  [sp,#4*(32+1)]	@ save inp
+	str	r14,  [sp,#4*(32+0)]	@ save out
+.Loop_outer_enter:
+	ldr	@t[3], [sp,#4*(15)]
+	 mov	@x[4],@x[4],ror#19	@ twist b[0..3]
+	ldr	@x[12],[sp,#4*(12)]	@ modulo-scheduled load
+	 mov	@x[5],@x[5],ror#19
+	ldr	@t[2], [sp,#4*(13)]
+	 mov	@x[6],@x[6],ror#19
+	ldr	@x[14],[sp,#4*(14)]
+	 mov	@x[7],@x[7],ror#19
+	mov	@t[3],@t[3],ror#8	@ twist d[0..3]
+	mov	@x[12],@x[12],ror#8
+	mov	@t[2],@t[2],ror#8
+	mov	@x[14],@x[14],ror#8
+	str	@t[3], [sp,#4*(16+15)]
+	mov	@t[3],#10
+	b	.Loop
+
+.align	4
+.Loop:
+	subs	@t[3],@t[3],#1
+___
+	foreach (&ROUND(0, 4, 8,12)) { eval; }
+	foreach (&ROUND(0, 5,10,15)) { eval; }
+$code.=<<___;
+	bne	.Loop
+
+	ldr	@t[3],[sp,#4*(32+2)]	@ load len
+
+	str	@t[0], [sp,#4*(16+8)]	@ modulo-scheduled store
+	str	@t[1], [sp,#4*(16+9)]
+	str	@x[12],[sp,#4*(16+12)]
+	str	@t[2], [sp,#4*(16+13)]
+	str	@x[14],[sp,#4*(16+14)]
+
+	@ at this point we have first half of 512-bit result in
+	@ @x[0-7] and second half at sp+4*(16+8)
+
+	cmp	@t[3],#64		@ done yet?
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	addlo	r12,sp,#4*(0)		@ shortcut or ...
+	ldrhs	r12,[sp,#4*(32+1)]	@ ... load inp
+	addlo	r14,sp,#4*(0)		@ shortcut or ...
+	ldrhs	r14,[sp,#4*(32+0)]	@ ... load out
+
+	ldr	@t[0],[sp,#4*(0)]	@ load key material
+	ldr	@t[1],[sp,#4*(1)]
+
+#if __ARM_ARCH__>=6 || !defined(__ARMEB__)
+# if __ARM_ARCH__<7
+	orr	@t[2],r12,r14
+	tst	@t[2],#3		@ are input and output aligned?
+	ldr	@t[2],[sp,#4*(2)]
+	bne	.Lunaligned
+	cmp	@t[3],#64		@ restore flags
+# else
+	ldr	@t[2],[sp,#4*(2)]
+# endif
+	ldr	@t[3],[sp,#4*(3)]
+
+	add	@x[0],@x[0],@t[0]	@ accumulate key material
+	add	@x[1],@x[1],@t[1]
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	@t[0],[r12],#16		@ load input
+	ldrhs	@t[1],[r12,#-12]
+
+	add	@x[2],@x[2],@t[2]
+	add	@x[3],@x[3],@t[3]
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	@t[2],[r12,#-8]
+	ldrhs	@t[3],[r12,#-4]
+# if __ARM_ARCH__>=6 && defined(__ARMEB__)
+	rev	@x[0],@x[0]
+	rev	@x[1],@x[1]
+	rev	@x[2],@x[2]
+	rev	@x[3],@x[3]
+# endif
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	@x[0],@x[0],@t[0]	@ xor with input
+	eorhs	@x[1],@x[1],@t[1]
+	 add	@t[0],sp,#4*(4)
+	str	@x[0],[r14],#16		@ store output
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	@x[2],@x[2],@t[2]
+	eorhs	@x[3],@x[3],@t[3]
+	 ldmia	@t[0],{@t[0]-@t[3]}	@ load key material
+	str	@x[1],[r14,#-12]
+	str	@x[2],[r14,#-8]
+	str	@x[3],[r14,#-4]
+
+	add	@x[4],@t[0],@x[4],ror#13 @ accumulate key material
+	add	@x[5],@t[1],@x[5],ror#13
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	@t[0],[r12],#16		@ load input
+	ldrhs	@t[1],[r12,#-12]
+	add	@x[6],@t[2],@x[6],ror#13
+	add	@x[7],@t[3],@x[7],ror#13
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	@t[2],[r12,#-8]
+	ldrhs	@t[3],[r12,#-4]
+# if __ARM_ARCH__>=6 && defined(__ARMEB__)
+	rev	@x[4],@x[4]
+	rev	@x[5],@x[5]
+	rev	@x[6],@x[6]
+	rev	@x[7],@x[7]
+# endif
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	@x[4],@x[4],@t[0]
+	eorhs	@x[5],@x[5],@t[1]
+	 add	@t[0],sp,#4*(8)
+	str	@x[4],[r14],#16		@ store output
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	@x[6],@x[6],@t[2]
+	eorhs	@x[7],@x[7],@t[3]
+	str	@x[5],[r14,#-12]
+	 ldmia	@t[0],{@t[0]-@t[3]}	@ load key material
+	str	@x[6],[r14,#-8]
+	 add	@x[0],sp,#4*(16+8)
+	str	@x[7],[r14,#-4]
+
+	ldmia	@x[0],{@x[0]-@x[7]}	@ load second half
+
+	add	@x[0],@x[0],@t[0]	@ accumulate key material
+	add	@x[1],@x[1],@t[1]
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	@t[0],[r12],#16		@ load input
+	ldrhs	@t[1],[r12,#-12]
+# ifdef	__thumb2__
+	itt	hi
+# endif
+	 strhi	@t[2],[sp,#4*(16+10)]	@ copy "@x[10]" while at it
+	 strhi	@t[3],[sp,#4*(16+11)]	@ copy "@x[11]" while at it
+	add	@x[2],@x[2],@t[2]
+	add	@x[3],@x[3],@t[3]
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	@t[2],[r12,#-8]
+	ldrhs	@t[3],[r12,#-4]
+# if __ARM_ARCH__>=6 && defined(__ARMEB__)
+	rev	@x[0],@x[0]
+	rev	@x[1],@x[1]
+	rev	@x[2],@x[2]
+	rev	@x[3],@x[3]
+# endif
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	@x[0],@x[0],@t[0]
+	eorhs	@x[1],@x[1],@t[1]
+	 add	@t[0],sp,#4*(12)
+	str	@x[0],[r14],#16		@ store output
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	@x[2],@x[2],@t[2]
+	eorhs	@x[3],@x[3],@t[3]
+	str	@x[1],[r14,#-12]
+	 ldmia	@t[0],{@t[0]-@t[3]}	@ load key material
+	str	@x[2],[r14,#-8]
+	str	@x[3],[r14,#-4]
+
+	add	@x[4],@t[0],@x[4],ror#24 @ accumulate key material
+	add	@x[5],@t[1],@x[5],ror#24
+# ifdef	__thumb2__
+	itt	hi
+# endif
+	 addhi	@t[0],@t[0],#1		@ next counter value
+	 strhi	@t[0],[sp,#4*(12)]	@ save next counter value
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	@t[0],[r12],#16		@ load input
+	ldrhs	@t[1],[r12,#-12]
+	add	@x[6],@t[2],@x[6],ror#24
+	add	@x[7],@t[3],@x[7],ror#24
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhs	@t[2],[r12,#-8]
+	ldrhs	@t[3],[r12,#-4]
+# if __ARM_ARCH__>=6 && defined(__ARMEB__)
+	rev	@x[4],@x[4]
+	rev	@x[5],@x[5]
+	rev	@x[6],@x[6]
+	rev	@x[7],@x[7]
+# endif
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	@x[4],@x[4],@t[0]
+	eorhs	@x[5],@x[5],@t[1]
+# ifdef	__thumb2__
+	 it	ne
+# endif
+	 ldrne	@t[0],[sp,#4*(32+2)]	@ re-load len
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	eorhs	@x[6],@x[6],@t[2]
+	eorhs	@x[7],@x[7],@t[3]
+	str	@x[4],[r14],#16		@ store output
+	str	@x[5],[r14,#-12]
+# ifdef	__thumb2__
+	it	hs
+# endif
+	 subhs	@t[3],@t[0],#64		@ len-=64
+	str	@x[6],[r14,#-8]
+	str	@x[7],[r14,#-4]
+	bhi	.Loop_outer
+
+	beq	.Ldone
+# if __ARM_ARCH__<7
+	b	.Ltail
+
+.align	4
+.Lunaligned:				@ unaligned endian-neutral path
+	cmp	@t[3],#64		@ restore flags
+# endif
+#endif
+#if __ARM_ARCH__<7
+	ldr	@t[3],[sp,#4*(3)]
+___
+for ($i=0;$i<16;$i+=4) {
+my $j=$i&0x7;
+my $twist="";
+if ($i==4)     { $twist = ",ror#13"; }
+elsif ($i==12) { $twist = ",ror#24"; }
+
+$code.=<<___	if ($i==4);
+	add	@x[0],sp,#4*(16+8)
+___
+$code.=<<___	if ($i==8);
+	ldmia	@x[0],{@x[0]-@x[7]}		@ load second half
+# ifdef	__thumb2__
+	itt	hi
+# endif
+	strhi	@t[2],[sp,#4*(16+10)]		@ copy "@x[10]"
+	strhi	@t[3],[sp,#4*(16+11)]		@ copy "@x[11]"
+___
+$code.=<<___;
+	add	@x[$j+0],@t[0],@x[$j+0]$twist	@ accumulate key material
+___
+$code.=<<___	if ($i==12);
+# ifdef	__thumb2__
+	itt	hi
+# endif
+	addhi	@t[0],@t[0],#1			@ next counter value
+	strhi	@t[0],[sp,#4*(12)]		@ save next counter value
+___
+$code.=<<___;
+	add	@x[$j+1],@t[1],@x[$j+1]$twist
+	add	@x[$j+2],@t[2],@x[$j+2]$twist
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	@t[0],@t[0],@t[0]		@ zero or ...
+	ldrhsb	@t[0],[r12],#16			@ ... load input
+	eorlo	@t[1],@t[1],@t[1]
+	ldrhsb	@t[1],[r12,#-12]
+
+	add	@x[$j+3],@t[3],@x[$j+3]$twist
+# ifdef	__thumb2__
+	itete	lo
+# endif
+	eorlo	@t[2],@t[2],@t[2]
+	ldrhsb	@t[2],[r12,#-8]
+	eorlo	@t[3],@t[3],@t[3]
+	ldrhsb	@t[3],[r12,#-4]
+
+	eor	@x[$j+0],@t[0],@x[$j+0]		@ xor with input (or zero)
+	eor	@x[$j+1],@t[1],@x[$j+1]
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	@t[0],[r12,#-15]		@ load more input
+	ldrhsb	@t[1],[r12,#-11]
+	eor	@x[$j+2],@t[2],@x[$j+2]
+	 strb	@x[$j+0],[r14],#16		@ store output
+	eor	@x[$j+3],@t[3],@x[$j+3]
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	@t[2],[r12,#-7]
+	ldrhsb	@t[3],[r12,#-3]
+	 strb	@x[$j+1],[r14,#-12]
+	eor	@x[$j+0],@t[0],@x[$j+0],lsr#8
+	 strb	@x[$j+2],[r14,#-8]
+	eor	@x[$j+1],@t[1],@x[$j+1],lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	@t[0],[r12,#-14]		@ load more input
+	ldrhsb	@t[1],[r12,#-10]
+	 strb	@x[$j+3],[r14,#-4]
+	eor	@x[$j+2],@t[2],@x[$j+2],lsr#8
+	 strb	@x[$j+0],[r14,#-15]
+	eor	@x[$j+3],@t[3],@x[$j+3],lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	@t[2],[r12,#-6]
+	ldrhsb	@t[3],[r12,#-2]
+	 strb	@x[$j+1],[r14,#-11]
+	eor	@x[$j+0],@t[0],@x[$j+0],lsr#8
+	 strb	@x[$j+2],[r14,#-7]
+	eor	@x[$j+1],@t[1],@x[$j+1],lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	@t[0],[r12,#-13]		@ load more input
+	ldrhsb	@t[1],[r12,#-9]
+	 strb	@x[$j+3],[r14,#-3]
+	eor	@x[$j+2],@t[2],@x[$j+2],lsr#8
+	 strb	@x[$j+0],[r14,#-14]
+	eor	@x[$j+3],@t[3],@x[$j+3],lsr#8
+# ifdef	__thumb2__
+	itt	hs
+# endif
+	ldrhsb	@t[2],[r12,#-5]
+	ldrhsb	@t[3],[r12,#-1]
+	 strb	@x[$j+1],[r14,#-10]
+	 strb	@x[$j+2],[r14,#-6]
+	eor	@x[$j+0],@t[0],@x[$j+0],lsr#8
+	 strb	@x[$j+3],[r14,#-2]
+	eor	@x[$j+1],@t[1],@x[$j+1],lsr#8
+	 strb	@x[$j+0],[r14,#-13]
+	eor	@x[$j+2],@t[2],@x[$j+2],lsr#8
+	 strb	@x[$j+1],[r14,#-9]
+	eor	@x[$j+3],@t[3],@x[$j+3],lsr#8
+	 strb	@x[$j+2],[r14,#-5]
+	 strb	@x[$j+3],[r14,#-1]
+___
+$code.=<<___	if ($i<12);
+	add	@t[0],sp,#4*(4+$i)
+	ldmia	@t[0],{@t[0]-@t[3]}		@ load key material
+___
+}
+$code.=<<___;
+# ifdef	__thumb2__
+	it	ne
+# endif
+	ldrne	@t[0],[sp,#4*(32+2)]		@ re-load len
+# ifdef	__thumb2__
+	it	hs
+# endif
+	subhs	@t[3],@t[0],#64			@ len-=64
+	bhi	.Loop_outer
+
+	beq	.Ldone
+#endif
+
+.Ltail:
+	ldr	r12,[sp,#4*(32+1)]	@ load inp
+	add	@t[1],sp,#4*(0)
+	ldr	r14,[sp,#4*(32+0)]	@ load out
+
+.Loop_tail:
+	ldrb	@t[2],[@t[1]],#1	@ read buffer on stack
+	ldrb	@t[3],[r12],#1		@ read input
+	subs	@t[0],@t[0],#1
+	eor	@t[3],@t[3],@t[2]
+	strb	@t[3],[r14],#1		@ store output
+	bne	.Loop_tail
+
+.Ldone:
+	add	sp,sp,#4*(32+3)
+.Lno_data:
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r11,pc}
+#else
+	ldmia	sp!,{r4-r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.long	0xe12fff1e		@ interoperable with Thumb ISA:-)
+#endif
+.size	ChaCha20_ctr32,.-ChaCha20_ctr32
+___
+
+{{{
+my ($a0,$b0,$c0,$d0,$a1,$b1,$c1,$d1,$a2,$b2,$c2,$d2,$t0,$t1,$t2,$t3) =
+    map("q$_",(0..15));
+
+# This can replace vshr-by-24+vsli-by-8. It gives ~3% improvement on
+# Cortex-A5/A7, but hurts Cortex-A9 by 5% and Snapdragon S4 by 14%!
+sub vperm()
+{ my ($dst,$src,$tbl) = @_;
+    $code .= "	vtbl.8	$dst#lo,{$src#lo},$tbl#lo\n";
+    $code .= "	vtbl.8	$dst#hi,{$src#hi},$tbl#lo\n";
+}
+
+sub NEONROUND {
+my $odd = pop;
+my ($a,$b,$c,$d,$t)=@_;
+
+	(
+	"&vadd_i32	($a,$a,$b)",
+	"&veor		($d,$d,$a)",
+	"&vrev32_16	($d,$d)",	# vrot ($d,16)
+
+	"&vadd_i32	($c,$c,$d)",
+	"&veor		($t,$b,$c)",
+	"&vshr_u32	($b,$t,20)",
+	"&vsli_32	($b,$t,12)",
+
+	"&vadd_i32	($a,$a,$b)",
+	"&veor		($t,$d,$a)",
+	"&vshr_u32	($d,$t,24)",
+	"&vsli_32	($d,$t,8)",
+	#"&vperm	($d,$t,$t3)",
+
+	"&vadd_i32	($c,$c,$d)",
+	"&veor		($t,$b,$c)",
+	"&vshr_u32	($b,$t,25)",
+	"&vsli_32	($b,$t,7)",
+
+	"&vext_8	($c,$c,$c,8)",
+	"&vext_8	($b,$b,$b,$odd?12:4)",
+	"&vext_8	($d,$d,$d,$odd?4:12)"
+	);
+}
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+# ifdef __KERNEL__
+.globl	ChaCha20_neon
+@ For optimal performance it's appropriate for caller to enforce
+@ minimum input length, 193 bytes is suggested.
+# endif
+.type	ChaCha20_neon,%function
+.align	5
+ChaCha20_neon:
+	ldr		r12,[sp,#0]		@ pull pointer to counter and nonce
+	stmdb		sp!,{r0-r2,r4-r11,lr}
+.LChaCha20_neon:
+	adr		r14,.Lsigma
+	vstmdb		sp!,{d8-d15}		@ ABI spec says so
+	stmdb		sp!,{r0-r3}
+
+	vld1.32		{$b0-$c0},[r3]		@ load key
+	ldmia		r3,{r4-r11}		@ load key
+
+	sub		sp,sp,#4*(16+16)
+	vld1.32		{$d0},[r12]		@ load counter and nonce
+	add		r12,sp,#4*8
+	ldmia		r14,{r0-r3}		@ load sigma
+	vld1.32		{$a0},[r14]!		@ load sigma
+	vld1.32		{$t0},[r14]!		@ one
+	@ vld1.32	{$t3#lo},[r14]		@ rot8
+	vst1.32		{$c0-$d0},[r12]		@ copy 1/2key|counter|nonce
+	vst1.32		{$a0-$b0},[sp]		@ copy sigma|1/2key
+
+	str		r10,[sp,#4*(16+10)]	@ off-load "@x[10]"
+	str		r11,[sp,#4*(16+11)]	@ off-load "@x[11]"
+	vshl.i32	$t1#lo,$t0#lo,#1	@ two
+	vstr		$t0#lo,[sp,#4*(16+0)]
+	vshl.i32	$t2#lo,$t0#lo,#2	@ four
+	vstr		$t1#lo,[sp,#4*(16+2)]
+	vmov		$a1,$a0
+	vstr		$t2#lo,[sp,#4*(16+4)]
+	vmov		$a2,$a0
+	@ vstr		$t3#lo,[sp,#4*(16+6)]
+	vmov		$b1,$b0
+	vmov		$b2,$b0
+	b		.Loop_neon_enter
+
+.align	4
+.Loop_neon_outer:
+	ldmia		sp,{r0-r9}		@ load key material
+	cmp		@t[3],#64*2		@ if len<=64*2
+	bls		.Lbreak_neon		@ switch to integer-only
+	@ vldr		$t3#lo,[sp,#4*(16+6)]	@ rot8
+	vmov		$a1,$a0
+	str		@t[3],[sp,#4*(32+2)]	@ save len
+	vmov		$a2,$a0
+	str		r12,  [sp,#4*(32+1)]	@ save inp
+	vmov		$b1,$b0
+	str		r14,  [sp,#4*(32+0)]	@ save out
+	vmov		$b2,$b0
+.Loop_neon_enter:
+	ldr		@t[3], [sp,#4*(15)]
+	 mov		@x[4],@x[4],ror#19	@ twist b[0..3]
+	vadd.i32	$d1,$d0,$t0		@ counter+1
+	ldr		@x[12],[sp,#4*(12)]	@ modulo-scheduled load
+	 mov		@x[5],@x[5],ror#19
+	vmov		$c1,$c0
+	ldr		@t[2], [sp,#4*(13)]
+	 mov		@x[6],@x[6],ror#19
+	vmov		$c2,$c0
+	ldr		@x[14],[sp,#4*(14)]
+	 mov		@x[7],@x[7],ror#19
+	vadd.i32	$d2,$d1,$t0		@ counter+2
+	add		@x[12],@x[12],#3	@ counter+3
+	mov		@t[3],@t[3],ror#8	@ twist d[0..3]
+	mov		@x[12],@x[12],ror#8
+	mov		@t[2],@t[2],ror#8
+	mov		@x[14],@x[14],ror#8
+	str		@t[3], [sp,#4*(16+15)]
+	mov		@t[3],#10
+	b		.Loop_neon
+
+.align	4
+.Loop_neon:
+	subs		@t[3],@t[3],#1
+___
+	my @thread0=&NEONROUND($a0,$b0,$c0,$d0,$t0,0);
+	my @thread1=&NEONROUND($a1,$b1,$c1,$d1,$t1,0);
+	my @thread2=&NEONROUND($a2,$b2,$c2,$d2,$t2,0);
+	my @thread3=&ROUND(0,4,8,12);
+
+	foreach (@thread0) {
+		eval;			eval(shift(@thread3));
+		eval(shift(@thread1));	eval(shift(@thread3));
+		eval(shift(@thread2));	eval(shift(@thread3));
+	}
+
+	@thread0=&NEONROUND($a0,$b0,$c0,$d0,$t0,1);
+	@thread1=&NEONROUND($a1,$b1,$c1,$d1,$t1,1);
+	@thread2=&NEONROUND($a2,$b2,$c2,$d2,$t2,1);
+	@thread3=&ROUND(0,5,10,15);
+
+	foreach (@thread0) {
+		eval;			eval(shift(@thread3));
+		eval(shift(@thread1));	eval(shift(@thread3));
+		eval(shift(@thread2));	eval(shift(@thread3));
+	}
+$code.=<<___;
+	bne		.Loop_neon
+
+	add		@t[3],sp,#32
+	vld1.32		{$t0-$t1},[sp]		@ load key material
+	vld1.32		{$t2-$t3},[@t[3]]
+
+	ldr		@t[3],[sp,#4*(32+2)]	@ load len
+
+	str		@t[0], [sp,#4*(16+8)]	@ modulo-scheduled store
+	str		@t[1], [sp,#4*(16+9)]
+	str		@x[12],[sp,#4*(16+12)]
+	str		@t[2], [sp,#4*(16+13)]
+	str		@x[14],[sp,#4*(16+14)]
+
+	@ at this point we have first half of 512-bit result in
+	@ @x[0-7] and second half at sp+4*(16+8)
+
+	ldr		r12,[sp,#4*(32+1)]	@ load inp
+	ldr		r14,[sp,#4*(32+0)]	@ load out
+
+	vadd.i32	$a0,$a0,$t0		@ accumulate key material
+	vadd.i32	$a1,$a1,$t0
+	vadd.i32	$a2,$a2,$t0
+	vldr		$t0#lo,[sp,#4*(16+0)]	@ one
+
+	vadd.i32	$b0,$b0,$t1
+	vadd.i32	$b1,$b1,$t1
+	vadd.i32	$b2,$b2,$t1
+	vldr		$t1#lo,[sp,#4*(16+2)]	@ two
+
+	vadd.i32	$c0,$c0,$t2
+	vadd.i32	$c1,$c1,$t2
+	vadd.i32	$c2,$c2,$t2
+	vadd.i32	$d1#lo,$d1#lo,$t0#lo	@ counter+1
+	vadd.i32	$d2#lo,$d2#lo,$t1#lo	@ counter+2
+
+	vadd.i32	$d0,$d0,$t3
+	vadd.i32	$d1,$d1,$t3
+	vadd.i32	$d2,$d2,$t3
+
+	cmp		@t[3],#64*4
+	blo		.Ltail_neon
+
+	vld1.8		{$t0-$t1},[r12]!	@ load input
+	 mov		@t[3],sp
+	vld1.8		{$t2-$t3},[r12]!
+	veor		$a0,$a0,$t0		@ xor with input
+	veor		$b0,$b0,$t1
+	vld1.8		{$t0-$t1},[r12]!
+	veor		$c0,$c0,$t2
+	veor		$d0,$d0,$t3
+	vld1.8		{$t2-$t3},[r12]!
+
+	veor		$a1,$a1,$t0
+	 vst1.8		{$a0-$b0},[r14]!	@ store output
+	veor		$b1,$b1,$t1
+	vld1.8		{$t0-$t1},[r12]!
+	veor		$c1,$c1,$t2
+	 vst1.8		{$c0-$d0},[r14]!
+	veor		$d1,$d1,$t3
+	vld1.8		{$t2-$t3},[r12]!
+
+	veor		$a2,$a2,$t0
+	 vld1.32	{$a0-$b0},[@t[3]]!	@ load for next iteration
+	 veor		$t0#hi,$t0#hi,$t0#hi
+	 vldr		$t0#lo,[sp,#4*(16+4)]	@ four
+	veor		$b2,$b2,$t1
+	 vld1.32	{$c0-$d0},[@t[3]]
+	veor		$c2,$c2,$t2
+	 vst1.8		{$a1-$b1},[r14]!
+	veor		$d2,$d2,$t3
+	 vst1.8		{$c1-$d1},[r14]!
+
+	vadd.i32	$d0#lo,$d0#lo,$t0#lo	@ next counter value
+	vldr		$t0#lo,[sp,#4*(16+0)]	@ one
+
+	ldmia		sp,{@t[0]-@t[3]}	@ load key material
+	add		@x[0],@x[0],@t[0]	@ accumulate key material
+	ldr		@t[0],[r12],#16		@ load input
+	 vst1.8		{$a2-$b2},[r14]!
+	add		@x[1],@x[1],@t[1]
+	ldr		@t[1],[r12,#-12]
+	 vst1.8		{$c2-$d2},[r14]!
+	add		@x[2],@x[2],@t[2]
+	ldr		@t[2],[r12,#-8]
+	add		@x[3],@x[3],@t[3]
+	ldr		@t[3],[r12,#-4]
+# ifdef	__ARMEB__
+	rev		@x[0],@x[0]
+	rev		@x[1],@x[1]
+	rev		@x[2],@x[2]
+	rev		@x[3],@x[3]
+# endif
+	eor		@x[0],@x[0],@t[0]	@ xor with input
+	 add		@t[0],sp,#4*(4)
+	eor		@x[1],@x[1],@t[1]
+	str		@x[0],[r14],#16		@ store output
+	eor		@x[2],@x[2],@t[2]
+	str		@x[1],[r14,#-12]
+	eor		@x[3],@x[3],@t[3]
+	 ldmia		@t[0],{@t[0]-@t[3]}	@ load key material
+	str		@x[2],[r14,#-8]
+	str		@x[3],[r14,#-4]
+
+	add		@x[4],@t[0],@x[4],ror#13 @ accumulate key material
+	ldr		@t[0],[r12],#16		@ load input
+	add		@x[5],@t[1],@x[5],ror#13
+	ldr		@t[1],[r12,#-12]
+	add		@x[6],@t[2],@x[6],ror#13
+	ldr		@t[2],[r12,#-8]
+	add		@x[7],@t[3],@x[7],ror#13
+	ldr		@t[3],[r12,#-4]
+# ifdef	__ARMEB__
+	rev		@x[4],@x[4]
+	rev		@x[5],@x[5]
+	rev		@x[6],@x[6]
+	rev		@x[7],@x[7]
+# endif
+	eor		@x[4],@x[4],@t[0]
+	 add		@t[0],sp,#4*(8)
+	eor		@x[5],@x[5],@t[1]
+	str		@x[4],[r14],#16		@ store output
+	eor		@x[6],@x[6],@t[2]
+	str		@x[5],[r14,#-12]
+	eor		@x[7],@x[7],@t[3]
+	 ldmia		@t[0],{@t[0]-@t[3]}	@ load key material
+	str		@x[6],[r14,#-8]
+	 add		@x[0],sp,#4*(16+8)
+	str		@x[7],[r14,#-4]
+
+	ldmia		@x[0],{@x[0]-@x[7]}	@ load second half
+
+	add		@x[0],@x[0],@t[0]	@ accumulate key material
+	ldr		@t[0],[r12],#16		@ load input
+	add		@x[1],@x[1],@t[1]
+	ldr		@t[1],[r12,#-12]
+# ifdef	__thumb2__
+	it	hi
+# endif
+	 strhi		@t[2],[sp,#4*(16+10)]	@ copy "@x[10]" while at it
+	add		@x[2],@x[2],@t[2]
+	ldr		@t[2],[r12,#-8]
+# ifdef	__thumb2__
+	it	hi
+# endif
+	 strhi		@t[3],[sp,#4*(16+11)]	@ copy "@x[11]" while at it
+	add		@x[3],@x[3],@t[3]
+	ldr		@t[3],[r12,#-4]
+# ifdef	__ARMEB__
+	rev		@x[0],@x[0]
+	rev		@x[1],@x[1]
+	rev		@x[2],@x[2]
+	rev		@x[3],@x[3]
+# endif
+	eor		@x[0],@x[0],@t[0]
+	 add		@t[0],sp,#4*(12)
+	eor		@x[1],@x[1],@t[1]
+	str		@x[0],[r14],#16		@ store output
+	eor		@x[2],@x[2],@t[2]
+	str		@x[1],[r14,#-12]
+	eor		@x[3],@x[3],@t[3]
+	 ldmia		@t[0],{@t[0]-@t[3]}	@ load key material
+	str		@x[2],[r14,#-8]
+	str		@x[3],[r14,#-4]
+
+	add		@x[4],@t[0],@x[4],ror#24 @ accumulate key material
+	 add		@t[0],@t[0],#4		@ next counter value
+	add		@x[5],@t[1],@x[5],ror#24
+	 str		@t[0],[sp,#4*(12)]	@ save next counter value
+	ldr		@t[0],[r12],#16		@ load input
+	add		@x[6],@t[2],@x[6],ror#24
+	 add		@x[4],@x[4],#3		@ counter+3
+	ldr		@t[1],[r12,#-12]
+	add		@x[7],@t[3],@x[7],ror#24
+	ldr		@t[2],[r12,#-8]
+	ldr		@t[3],[r12,#-4]
+# ifdef	__ARMEB__
+	rev		@x[4],@x[4]
+	rev		@x[5],@x[5]
+	rev		@x[6],@x[6]
+	rev		@x[7],@x[7]
+# endif
+	eor		@x[4],@x[4],@t[0]
+# ifdef	__thumb2__
+	it	hi
+# endif
+	 ldrhi		@t[0],[sp,#4*(32+2)]	@ re-load len
+	eor		@x[5],@x[5],@t[1]
+	eor		@x[6],@x[6],@t[2]
+	str		@x[4],[r14],#16		@ store output
+	eor		@x[7],@x[7],@t[3]
+	str		@x[5],[r14,#-12]
+	 sub		@t[3],@t[0],#64*4	@ len-=64*4
+	str		@x[6],[r14,#-8]
+	str		@x[7],[r14,#-4]
+	bhi		.Loop_neon_outer
+
+	b		.Ldone_neon
+
+.align	4
+.Lbreak_neon:
+	@ harmonize NEON and integer-only stack frames: load data
+	@ from NEON frame, but save to integer-only one; distance
+	@ between the two is 4*(32+4+16-32)=4*(20).
+
+	str		@t[3], [sp,#4*(20+32+2)]	@ save len
+	 add		@t[3],sp,#4*(32+4)
+	str		r12,   [sp,#4*(20+32+1)]	@ save inp
+	str		r14,   [sp,#4*(20+32+0)]	@ save out
+
+	ldr		@x[12],[sp,#4*(16+10)]
+	ldr		@x[14],[sp,#4*(16+11)]
+	 vldmia		@t[3],{d8-d15}			@ fulfill ABI requirement
+	str		@x[12],[sp,#4*(20+16+10)]	@ copy "@x[10]"
+	str		@x[14],[sp,#4*(20+16+11)]	@ copy "@x[11]"
+
+	ldr		@t[3], [sp,#4*(15)]
+	 mov		@x[4],@x[4],ror#19		@ twist b[0..3]
+	ldr		@x[12],[sp,#4*(12)]		@ modulo-scheduled load
+	 mov		@x[5],@x[5],ror#19
+	ldr		@t[2], [sp,#4*(13)]
+	 mov		@x[6],@x[6],ror#19
+	ldr		@x[14],[sp,#4*(14)]
+	 mov		@x[7],@x[7],ror#19
+	mov		@t[3],@t[3],ror#8		@ twist d[0..3]
+	mov		@x[12],@x[12],ror#8
+	mov		@t[2],@t[2],ror#8
+	mov		@x[14],@x[14],ror#8
+	str		@t[3], [sp,#4*(20+16+15)]
+	add		@t[3],sp,#4*(20)
+	vst1.32		{$a0-$b0},[@t[3]]!		@ copy key
+	add		sp,sp,#4*(20)			@ switch frame
+	vst1.32		{$c0-$d0},[@t[3]]
+	mov		@t[3],#10
+	b		.Loop				@ go integer-only
+
+.align	4
+.Ltail_neon:
+	cmp		@t[3],#64*3
+	bhs		.L192_or_more_neon
+	cmp		@t[3],#64*2
+	bhs		.L128_or_more_neon
+	cmp		@t[3],#64*1
+	bhs		.L64_or_more_neon
+
+	add		@t[0],sp,#4*(8)
+	vst1.8		{$a0-$b0},[sp]
+	add		@t[2],sp,#4*(0)
+	vst1.8		{$c0-$d0},[@t[0]]
+	b		.Loop_tail_neon
+
+.align	4
+.L64_or_more_neon:
+	vld1.8		{$t0-$t1},[r12]!
+	vld1.8		{$t2-$t3},[r12]!
+	veor		$a0,$a0,$t0
+	veor		$b0,$b0,$t1
+	veor		$c0,$c0,$t2
+	veor		$d0,$d0,$t3
+	vst1.8		{$a0-$b0},[r14]!
+	vst1.8		{$c0-$d0},[r14]!
+
+	beq		.Ldone_neon
+
+	add		@t[0],sp,#4*(8)
+	vst1.8		{$a1-$b1},[sp]
+	add		@t[2],sp,#4*(0)
+	vst1.8		{$c1-$d1},[@t[0]]
+	sub		@t[3],@t[3],#64*1	@ len-=64*1
+	b		.Loop_tail_neon
+
+.align	4
+.L128_or_more_neon:
+	vld1.8		{$t0-$t1},[r12]!
+	vld1.8		{$t2-$t3},[r12]!
+	veor		$a0,$a0,$t0
+	veor		$b0,$b0,$t1
+	vld1.8		{$t0-$t1},[r12]!
+	veor		$c0,$c0,$t2
+	veor		$d0,$d0,$t3
+	vld1.8		{$t2-$t3},[r12]!
+
+	veor		$a1,$a1,$t0
+	veor		$b1,$b1,$t1
+	 vst1.8		{$a0-$b0},[r14]!
+	veor		$c1,$c1,$t2
+	 vst1.8		{$c0-$d0},[r14]!
+	veor		$d1,$d1,$t3
+	vst1.8		{$a1-$b1},[r14]!
+	vst1.8		{$c1-$d1},[r14]!
+
+	beq		.Ldone_neon
+
+	add		@t[0],sp,#4*(8)
+	vst1.8		{$a2-$b2},[sp]
+	add		@t[2],sp,#4*(0)
+	vst1.8		{$c2-$d2},[@t[0]]
+	sub		@t[3],@t[3],#64*2	@ len-=64*2
+	b		.Loop_tail_neon
+
+.align	4
+.L192_or_more_neon:
+	vld1.8		{$t0-$t1},[r12]!
+	vld1.8		{$t2-$t3},[r12]!
+	veor		$a0,$a0,$t0
+	veor		$b0,$b0,$t1
+	vld1.8		{$t0-$t1},[r12]!
+	veor		$c0,$c0,$t2
+	veor		$d0,$d0,$t3
+	vld1.8		{$t2-$t3},[r12]!
+
+	veor		$a1,$a1,$t0
+	veor		$b1,$b1,$t1
+	vld1.8		{$t0-$t1},[r12]!
+	veor		$c1,$c1,$t2
+	 vst1.8		{$a0-$b0},[r14]!
+	veor		$d1,$d1,$t3
+	vld1.8		{$t2-$t3},[r12]!
+
+	veor		$a2,$a2,$t0
+	 vst1.8		{$c0-$d0},[r14]!
+	veor		$b2,$b2,$t1
+	 vst1.8		{$a1-$b1},[r14]!
+	veor		$c2,$c2,$t2
+	 vst1.8		{$c1-$d1},[r14]!
+	veor		$d2,$d2,$t3
+	vst1.8		{$a2-$b2},[r14]!
+	vst1.8		{$c2-$d2},[r14]!
+
+	beq		.Ldone_neon
+
+	ldmia		sp,{@t[0]-@t[3]}	@ load key material
+	add		@x[0],@x[0],@t[0]	@ accumulate key material
+	 add		@t[0],sp,#4*(4)
+	add		@x[1],@x[1],@t[1]
+	add		@x[2],@x[2],@t[2]
+	add		@x[3],@x[3],@t[3]
+	 ldmia		@t[0],{@t[0]-@t[3]}	@ load key material
+
+	add		@x[4],@t[0],@x[4],ror#13 @ accumulate key material
+	 add		@t[0],sp,#4*(8)
+	add		@x[5],@t[1],@x[5],ror#13
+	add		@x[6],@t[2],@x[6],ror#13
+	add		@x[7],@t[3],@x[7],ror#13
+	 ldmia		@t[0],{@t[0]-@t[3]}	@ load key material
+# ifdef	__ARMEB__
+	rev		@x[0],@x[0]
+	rev		@x[1],@x[1]
+	rev		@x[2],@x[2]
+	rev		@x[3],@x[3]
+	rev		@x[4],@x[4]
+	rev		@x[5],@x[5]
+	rev		@x[6],@x[6]
+	rev		@x[7],@x[7]
+# endif
+	stmia		sp,{@x[0]-@x[7]}
+	 add		@x[0],sp,#4*(16+8)
+
+	ldmia		@x[0],{@x[0]-@x[7]}	@ load second half
+
+	add		@x[0],@x[0],@t[0]	@ accumulate key material
+	 add		@t[0],sp,#4*(12)
+	add		@x[1],@x[1],@t[1]
+	add		@x[2],@x[2],@t[2]
+	add		@x[3],@x[3],@t[3]
+	 ldmia		@t[0],{@t[0]-@t[3]}	@ load key material
+
+	add		@x[4],@t[0],@x[4],ror#24 @ accumulate key material
+	 add		@t[0],sp,#4*(8)
+	add		@x[5],@t[1],@x[5],ror#24
+	 add		@x[4],@x[4],#3		@ counter+3
+	add		@x[6],@t[2],@x[6],ror#24
+	add		@x[7],@t[3],@x[7],ror#24
+	 ldr		@t[3],[sp,#4*(32+2)]	@ re-load len
+# ifdef	__ARMEB__
+	rev		@x[0],@x[0]
+	rev		@x[1],@x[1]
+	rev		@x[2],@x[2]
+	rev		@x[3],@x[3]
+	rev		@x[4],@x[4]
+	rev		@x[5],@x[5]
+	rev		@x[6],@x[6]
+	rev		@x[7],@x[7]
+# endif
+	stmia		@t[0],{@x[0]-@x[7]}
+	 add		@t[2],sp,#4*(0)
+	 sub		@t[3],@t[3],#64*3	@ len-=64*3
+
+.Loop_tail_neon:
+	ldrb		@t[0],[@t[2]],#1	@ read buffer on stack
+	ldrb		@t[1],[r12],#1		@ read input
+	subs		@t[3],@t[3],#1
+	eor		@t[0],@t[0],@t[1]
+	strb		@t[0],[r14],#1		@ store output
+	bne		.Loop_tail_neon
+
+.Ldone_neon:
+	add		sp,sp,#4*(32+4)
+	vldmia		sp,{d8-d15}
+	add		sp,sp,#4*(16+3)
+	ldmia		sp!,{r4-r11,pc}
+.size	ChaCha20_neon,.-ChaCha20_neon
+# ifndef __KERNEL__
+.comm	OPENSSL_armcap_P,4,4
+# endif
+#endif
+___
+}}}
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/@/ and !/^$/);
+	print;
+}
+close SELF;
+
+foreach (split("\n",$code)) {
+	s/\`([^\`]*)\`/eval $1/geo;
+
+	s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo;
+
+	print $_,"\n";
+}
+close STDOUT;
diff --git a/src/crypto/zinc/chacha20/chacha20-arm64.S b/src/crypto/zinc/chacha20/chacha20-arm64.S
deleted file mode 100644
index 1ae11a5..0000000
--- a/src/crypto/zinc/chacha20/chacha20-arm64.S
+++ /dev/null
@@ -1,1942 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
-/*
- * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
- *
- * This is based in part on Andy Polyakov's implementation from CRYPTOGAMS.
- */
-
-#include <linux/linkage.h>
-
-.text
-.align	5
-.Lsigma:
-.quad	0x3320646e61707865,0x6b20657479622d32		// endian-neutral
-.Lone:
-.long	1,0,0,0
-
-.align	5
-ENTRY(chacha20_arm)
-	cbz	x2,.Labort
-
-	stp	x29,x30,[sp,#-96]!
-	add	x29,sp,#0
-
-	adr	x5,.Lsigma
-	stp	x19,x20,[sp,#16]
-	stp	x21,x22,[sp,#32]
-	stp	x23,x24,[sp,#48]
-	stp	x25,x26,[sp,#64]
-	stp	x27,x28,[sp,#80]
-	sub	sp,sp,#64
-
-	ldp	x22,x23,[x5]		// load sigma
-	ldp	x24,x25,[x3]		// load key
-	ldp	x26,x27,[x3,#16]
-	ldp	x28,x30,[x4]		// load counter
-#ifdef	__AARCH64EB__
-	ror	x24,x24,#32
-	ror	x25,x25,#32
-	ror	x26,x26,#32
-	ror	x27,x27,#32
-	ror	x28,x28,#32
-	ror	x30,x30,#32
-#endif
-
-.Loop_outer:
-	mov	w5,w22			// unpack key block
-	lsr	x6,x22,#32
-	mov	w7,w23
-	lsr	x8,x23,#32
-	mov	w9,w24
-	lsr	x10,x24,#32
-	mov	w11,w25
-	lsr	x12,x25,#32
-	mov	w13,w26
-	lsr	x14,x26,#32
-	mov	w15,w27
-	lsr	x16,x27,#32
-	mov	w17,w28
-	lsr	x19,x28,#32
-	mov	w20,w30
-	lsr	x21,x30,#32
-
-	mov	x4,#10
-	subs	x2,x2,#64
-.Loop:
-	sub	x4,x4,#1
-	add	w5,w5,w9
-	add	w6,w6,w10
-	add	w7,w7,w11
-	add	w8,w8,w12
-	eor	w17,w17,w5
-	eor	w19,w19,w6
-	eor	w20,w20,w7
-	eor	w21,w21,w8
-	ror	w17,w17,#16
-	ror	w19,w19,#16
-	ror	w20,w20,#16
-	ror	w21,w21,#16
-	add	w13,w13,w17
-	add	w14,w14,w19
-	add	w15,w15,w20
-	add	w16,w16,w21
-	eor	w9,w9,w13
-	eor	w10,w10,w14
-	eor	w11,w11,w15
-	eor	w12,w12,w16
-	ror	w9,w9,#20
-	ror	w10,w10,#20
-	ror	w11,w11,#20
-	ror	w12,w12,#20
-	add	w5,w5,w9
-	add	w6,w6,w10
-	add	w7,w7,w11
-	add	w8,w8,w12
-	eor	w17,w17,w5
-	eor	w19,w19,w6
-	eor	w20,w20,w7
-	eor	w21,w21,w8
-	ror	w17,w17,#24
-	ror	w19,w19,#24
-	ror	w20,w20,#24
-	ror	w21,w21,#24
-	add	w13,w13,w17
-	add	w14,w14,w19
-	add	w15,w15,w20
-	add	w16,w16,w21
-	eor	w9,w9,w13
-	eor	w10,w10,w14
-	eor	w11,w11,w15
-	eor	w12,w12,w16
-	ror	w9,w9,#25
-	ror	w10,w10,#25
-	ror	w11,w11,#25
-	ror	w12,w12,#25
-	add	w5,w5,w10
-	add	w6,w6,w11
-	add	w7,w7,w12
-	add	w8,w8,w9
-	eor	w21,w21,w5
-	eor	w17,w17,w6
-	eor	w19,w19,w7
-	eor	w20,w20,w8
-	ror	w21,w21,#16
-	ror	w17,w17,#16
-	ror	w19,w19,#16
-	ror	w20,w20,#16
-	add	w15,w15,w21
-	add	w16,w16,w17
-	add	w13,w13,w19
-	add	w14,w14,w20
-	eor	w10,w10,w15
-	eor	w11,w11,w16
-	eor	w12,w12,w13
-	eor	w9,w9,w14
-	ror	w10,w10,#20
-	ror	w11,w11,#20
-	ror	w12,w12,#20
-	ror	w9,w9,#20
-	add	w5,w5,w10
-	add	w6,w6,w11
-	add	w7,w7,w12
-	add	w8,w8,w9
-	eor	w21,w21,w5
-	eor	w17,w17,w6
-	eor	w19,w19,w7
-	eor	w20,w20,w8
-	ror	w21,w21,#24
-	ror	w17,w17,#24
-	ror	w19,w19,#24
-	ror	w20,w20,#24
-	add	w15,w15,w21
-	add	w16,w16,w17
-	add	w13,w13,w19
-	add	w14,w14,w20
-	eor	w10,w10,w15
-	eor	w11,w11,w16
-	eor	w12,w12,w13
-	eor	w9,w9,w14
-	ror	w10,w10,#25
-	ror	w11,w11,#25
-	ror	w12,w12,#25
-	ror	w9,w9,#25
-	cbnz	x4,.Loop
-
-	add	w5,w5,w22		// accumulate key block
-	add	x6,x6,x22,lsr#32
-	add	w7,w7,w23
-	add	x8,x8,x23,lsr#32
-	add	w9,w9,w24
-	add	x10,x10,x24,lsr#32
-	add	w11,w11,w25
-	add	x12,x12,x25,lsr#32
-	add	w13,w13,w26
-	add	x14,x14,x26,lsr#32
-	add	w15,w15,w27
-	add	x16,x16,x27,lsr#32
-	add	w17,w17,w28
-	add	x19,x19,x28,lsr#32
-	add	w20,w20,w30
-	add	x21,x21,x30,lsr#32
-
-	b.lo	.Ltail
-
-	add	x5,x5,x6,lsl#32	// pack
-	add	x7,x7,x8,lsl#32
-	ldp	x6,x8,[x1,#0]		// load input
-	add	x9,x9,x10,lsl#32
-	add	x11,x11,x12,lsl#32
-	ldp	x10,x12,[x1,#16]
-	add	x13,x13,x14,lsl#32
-	add	x15,x15,x16,lsl#32
-	ldp	x14,x16,[x1,#32]
-	add	x17,x17,x19,lsl#32
-	add	x20,x20,x21,lsl#32
-	ldp	x19,x21,[x1,#48]
-	add	x1,x1,#64
-#ifdef	__AARCH64EB__
-	rev	x5,x5
-	rev	x7,x7
-	rev	x9,x9
-	rev	x11,x11
-	rev	x13,x13
-	rev	x15,x15
-	rev	x17,x17
-	rev	x20,x20
-#endif
-	eor	x5,x5,x6
-	eor	x7,x7,x8
-	eor	x9,x9,x10
-	eor	x11,x11,x12
-	eor	x13,x13,x14
-	eor	x15,x15,x16
-	eor	x17,x17,x19
-	eor	x20,x20,x21
-
-	stp	x5,x7,[x0,#0]		// store output
-	add	x28,x28,#1			// increment counter
-	stp	x9,x11,[x0,#16]
-	stp	x13,x15,[x0,#32]
-	stp	x17,x20,[x0,#48]
-	add	x0,x0,#64
-
-	b.hi	.Loop_outer
-
-	ldp	x19,x20,[x29,#16]
-	add	sp,sp,#64
-	ldp	x21,x22,[x29,#32]
-	ldp	x23,x24,[x29,#48]
-	ldp	x25,x26,[x29,#64]
-	ldp	x27,x28,[x29,#80]
-	ldp	x29,x30,[sp],#96
-.Labort:
-	ret
-
-.align	4
-.Ltail:
-	add	x2,x2,#64
-.Less_than_64:
-	sub	x0,x0,#1
-	add	x1,x1,x2
-	add	x0,x0,x2
-	add	x4,sp,x2
-	neg	x2,x2
-
-	add	x5,x5,x6,lsl#32	// pack
-	add	x7,x7,x8,lsl#32
-	add	x9,x9,x10,lsl#32
-	add	x11,x11,x12,lsl#32
-	add	x13,x13,x14,lsl#32
-	add	x15,x15,x16,lsl#32
-	add	x17,x17,x19,lsl#32
-	add	x20,x20,x21,lsl#32
-#ifdef	__AARCH64EB__
-	rev	x5,x5
-	rev	x7,x7
-	rev	x9,x9
-	rev	x11,x11
-	rev	x13,x13
-	rev	x15,x15
-	rev	x17,x17
-	rev	x20,x20
-#endif
-	stp	x5,x7,[sp,#0]
-	stp	x9,x11,[sp,#16]
-	stp	x13,x15,[sp,#32]
-	stp	x17,x20,[sp,#48]
-
-.Loop_tail:
-	ldrb	w10,[x1,x2]
-	ldrb	w11,[x4,x2]
-	add	x2,x2,#1
-	eor	w10,w10,w11
-	strb	w10,[x0,x2]
-	cbnz	x2,.Loop_tail
-
-	stp	xzr,xzr,[sp,#0]
-	stp	xzr,xzr,[sp,#16]
-	stp	xzr,xzr,[sp,#32]
-	stp	xzr,xzr,[sp,#48]
-
-	ldp	x19,x20,[x29,#16]
-	add	sp,sp,#64
-	ldp	x21,x22,[x29,#32]
-	ldp	x23,x24,[x29,#48]
-	ldp	x25,x26,[x29,#64]
-	ldp	x27,x28,[x29,#80]
-	ldp	x29,x30,[sp],#96
-	ret
-ENDPROC(chacha20_arm)
-
-#ifdef CONFIG_KERNEL_MODE_NEON
-.align	5
-ENTRY(chacha20_neon)
-	cbz	x2,.Labort_neon
-
-	stp	x29,x30,[sp,#-96]!
-	add	x29,sp,#0
-
-	adr	x5,.Lsigma
-	stp	x19,x20,[sp,#16]
-	stp	x21,x22,[sp,#32]
-	stp	x23,x24,[sp,#48]
-	stp	x25,x26,[sp,#64]
-	stp	x27,x28,[sp,#80]
-	cmp	x2,#512
-	b.hs	.L512_or_more_neon
-
-	sub	sp,sp,#64
-
-	ldp	x22,x23,[x5]		// load sigma
-	ld1	{v24.4s},[x5],#16
-	ldp	x24,x25,[x3]		// load key
-	ldp	x26,x27,[x3,#16]
-	ld1	{v25.4s,v26.4s},[x3]
-	ldp	x28,x30,[x4]		// load counter
-	ld1	{v27.4s},[x4]
-	ld1	{v31.4s},[x5]
-#ifdef	__AARCH64EB__
-	rev64	v24.4s,v24.4s
-	ror	x24,x24,#32
-	ror	x25,x25,#32
-	ror	x26,x26,#32
-	ror	x27,x27,#32
-	ror	x28,x28,#32
-	ror	x30,x30,#32
-#endif
-	add	v27.4s,v27.4s,v31.4s		// += 1
-	add	v28.4s,v27.4s,v31.4s
-	add	v29.4s,v28.4s,v31.4s
-	shl	v31.4s,v31.4s,#2			// 1 -> 4
-
-.Loop_outer_neon:
-	mov	w5,w22			// unpack key block
-	lsr	x6,x22,#32
-	mov	v0.16b,v24.16b
-	mov	w7,w23
-	lsr	x8,x23,#32
-	mov	v4.16b,v24.16b
-	mov	w9,w24
-	lsr	x10,x24,#32
-	mov	v16.16b,v24.16b
-	mov	w11,w25
-	mov	v1.16b,v25.16b
-	lsr	x12,x25,#32
-	mov	v5.16b,v25.16b
-	mov	w13,w26
-	mov	v17.16b,v25.16b
-	lsr	x14,x26,#32
-	mov	v3.16b,v27.16b
-	mov	w15,w27
-	mov	v7.16b,v28.16b
-	lsr	x16,x27,#32
-	mov	v19.16b,v29.16b
-	mov	w17,w28
-	mov	v2.16b,v26.16b
-	lsr	x19,x28,#32
-	mov	v6.16b,v26.16b
-	mov	w20,w30
-	mov	v18.16b,v26.16b
-	lsr	x21,x30,#32
-
-	mov	x4,#10
-	subs	x2,x2,#256
-.Loop_neon:
-	sub	x4,x4,#1
-	add	v0.4s,v0.4s,v1.4s
-	add	w5,w5,w9
-	add	v4.4s,v4.4s,v5.4s
-	add	w6,w6,w10
-	add	v16.4s,v16.4s,v17.4s
-	add	w7,w7,w11
-	eor	v3.16b,v3.16b,v0.16b
-	add	w8,w8,w12
-	eor	v7.16b,v7.16b,v4.16b
-	eor	w17,w17,w5
-	eor	v19.16b,v19.16b,v16.16b
-	eor	w19,w19,w6
-	rev32	v3.8h,v3.8h
-	eor	w20,w20,w7
-	rev32	v7.8h,v7.8h
-	eor	w21,w21,w8
-	rev32	v19.8h,v19.8h
-	ror	w17,w17,#16
-	add	v2.4s,v2.4s,v3.4s
-	ror	w19,w19,#16
-	add	v6.4s,v6.4s,v7.4s
-	ror	w20,w20,#16
-	add	v18.4s,v18.4s,v19.4s
-	ror	w21,w21,#16
-	eor	v20.16b,v1.16b,v2.16b
-	add	w13,w13,w17
-	eor	v21.16b,v5.16b,v6.16b
-	add	w14,w14,w19
-	eor	v22.16b,v17.16b,v18.16b
-	add	w15,w15,w20
-	ushr	v1.4s,v20.4s,#20
-	add	w16,w16,w21
-	ushr	v5.4s,v21.4s,#20
-	eor	w9,w9,w13
-	ushr	v17.4s,v22.4s,#20
-	eor	w10,w10,w14
-	sli	v1.4s,v20.4s,#12
-	eor	w11,w11,w15
-	sli	v5.4s,v21.4s,#12
-	eor	w12,w12,w16
-	sli	v17.4s,v22.4s,#12
-	ror	w9,w9,#20
-	add	v0.4s,v0.4s,v1.4s
-	ror	w10,w10,#20
-	add	v4.4s,v4.4s,v5.4s
-	ror	w11,w11,#20
-	add	v16.4s,v16.4s,v17.4s
-	ror	w12,w12,#20
-	eor	v20.16b,v3.16b,v0.16b
-	add	w5,w5,w9
-	eor	v21.16b,v7.16b,v4.16b
-	add	w6,w6,w10
-	eor	v22.16b,v19.16b,v16.16b
-	add	w7,w7,w11
-	ushr	v3.4s,v20.4s,#24
-	add	w8,w8,w12
-	ushr	v7.4s,v21.4s,#24
-	eor	w17,w17,w5
-	ushr	v19.4s,v22.4s,#24
-	eor	w19,w19,w6
-	sli	v3.4s,v20.4s,#8
-	eor	w20,w20,w7
-	sli	v7.4s,v21.4s,#8
-	eor	w21,w21,w8
-	sli	v19.4s,v22.4s,#8
-	ror	w17,w17,#24
-	add	v2.4s,v2.4s,v3.4s
-	ror	w19,w19,#24
-	add	v6.4s,v6.4s,v7.4s
-	ror	w20,w20,#24
-	add	v18.4s,v18.4s,v19.4s
-	ror	w21,w21,#24
-	eor	v20.16b,v1.16b,v2.16b
-	add	w13,w13,w17
-	eor	v21.16b,v5.16b,v6.16b
-	add	w14,w14,w19
-	eor	v22.16b,v17.16b,v18.16b
-	add	w15,w15,w20
-	ushr	v1.4s,v20.4s,#25
-	add	w16,w16,w21
-	ushr	v5.4s,v21.4s,#25
-	eor	w9,w9,w13
-	ushr	v17.4s,v22.4s,#25
-	eor	w10,w10,w14
-	sli	v1.4s,v20.4s,#7
-	eor	w11,w11,w15
-	sli	v5.4s,v21.4s,#7
-	eor	w12,w12,w16
-	sli	v17.4s,v22.4s,#7
-	ror	w9,w9,#25
-	ext	v2.16b,v2.16b,v2.16b,#8
-	ror	w10,w10,#25
-	ext	v6.16b,v6.16b,v6.16b,#8
-	ror	w11,w11,#25
-	ext	v18.16b,v18.16b,v18.16b,#8
-	ror	w12,w12,#25
-	ext	v3.16b,v3.16b,v3.16b,#12
-	ext	v7.16b,v7.16b,v7.16b,#12
-	ext	v19.16b,v19.16b,v19.16b,#12
-	ext	v1.16b,v1.16b,v1.16b,#4
-	ext	v5.16b,v5.16b,v5.16b,#4
-	ext	v17.16b,v17.16b,v17.16b,#4
-	add	v0.4s,v0.4s,v1.4s
-	add	w5,w5,w10
-	add	v4.4s,v4.4s,v5.4s
-	add	w6,w6,w11
-	add	v16.4s,v16.4s,v17.4s
-	add	w7,w7,w12
-	eor	v3.16b,v3.16b,v0.16b
-	add	w8,w8,w9
-	eor	v7.16b,v7.16b,v4.16b
-	eor	w21,w21,w5
-	eor	v19.16b,v19.16b,v16.16b
-	eor	w17,w17,w6
-	rev32	v3.8h,v3.8h
-	eor	w19,w19,w7
-	rev32	v7.8h,v7.8h
-	eor	w20,w20,w8
-	rev32	v19.8h,v19.8h
-	ror	w21,w21,#16
-	add	v2.4s,v2.4s,v3.4s
-	ror	w17,w17,#16
-	add	v6.4s,v6.4s,v7.4s
-	ror	w19,w19,#16
-	add	v18.4s,v18.4s,v19.4s
-	ror	w20,w20,#16
-	eor	v20.16b,v1.16b,v2.16b
-	add	w15,w15,w21
-	eor	v21.16b,v5.16b,v6.16b
-	add	w16,w16,w17
-	eor	v22.16b,v17.16b,v18.16b
-	add	w13,w13,w19
-	ushr	v1.4s,v20.4s,#20
-	add	w14,w14,w20
-	ushr	v5.4s,v21.4s,#20
-	eor	w10,w10,w15
-	ushr	v17.4s,v22.4s,#20
-	eor	w11,w11,w16
-	sli	v1.4s,v20.4s,#12
-	eor	w12,w12,w13
-	sli	v5.4s,v21.4s,#12
-	eor	w9,w9,w14
-	sli	v17.4s,v22.4s,#12
-	ror	w10,w10,#20
-	add	v0.4s,v0.4s,v1.4s
-	ror	w11,w11,#20
-	add	v4.4s,v4.4s,v5.4s
-	ror	w12,w12,#20
-	add	v16.4s,v16.4s,v17.4s
-	ror	w9,w9,#20
-	eor	v20.16b,v3.16b,v0.16b
-	add	w5,w5,w10
-	eor	v21.16b,v7.16b,v4.16b
-	add	w6,w6,w11
-	eor	v22.16b,v19.16b,v16.16b
-	add	w7,w7,w12
-	ushr	v3.4s,v20.4s,#24
-	add	w8,w8,w9
-	ushr	v7.4s,v21.4s,#24
-	eor	w21,w21,w5
-	ushr	v19.4s,v22.4s,#24
-	eor	w17,w17,w6
-	sli	v3.4s,v20.4s,#8
-	eor	w19,w19,w7
-	sli	v7.4s,v21.4s,#8
-	eor	w20,w20,w8
-	sli	v19.4s,v22.4s,#8
-	ror	w21,w21,#24
-	add	v2.4s,v2.4s,v3.4s
-	ror	w17,w17,#24
-	add	v6.4s,v6.4s,v7.4s
-	ror	w19,w19,#24
-	add	v18.4s,v18.4s,v19.4s
-	ror	w20,w20,#24
-	eor	v20.16b,v1.16b,v2.16b
-	add	w15,w15,w21
-	eor	v21.16b,v5.16b,v6.16b
-	add	w16,w16,w17
-	eor	v22.16b,v17.16b,v18.16b
-	add	w13,w13,w19
-	ushr	v1.4s,v20.4s,#25
-	add	w14,w14,w20
-	ushr	v5.4s,v21.4s,#25
-	eor	w10,w10,w15
-	ushr	v17.4s,v22.4s,#25
-	eor	w11,w11,w16
-	sli	v1.4s,v20.4s,#7
-	eor	w12,w12,w13
-	sli	v5.4s,v21.4s,#7
-	eor	w9,w9,w14
-	sli	v17.4s,v22.4s,#7
-	ror	w10,w10,#25
-	ext	v2.16b,v2.16b,v2.16b,#8
-	ror	w11,w11,#25
-	ext	v6.16b,v6.16b,v6.16b,#8
-	ror	w12,w12,#25
-	ext	v18.16b,v18.16b,v18.16b,#8
-	ror	w9,w9,#25
-	ext	v3.16b,v3.16b,v3.16b,#4
-	ext	v7.16b,v7.16b,v7.16b,#4
-	ext	v19.16b,v19.16b,v19.16b,#4
-	ext	v1.16b,v1.16b,v1.16b,#12
-	ext	v5.16b,v5.16b,v5.16b,#12
-	ext	v17.16b,v17.16b,v17.16b,#12
-	cbnz	x4,.Loop_neon
-
-	add	w5,w5,w22		// accumulate key block
-	add	v0.4s,v0.4s,v24.4s
-	add	x6,x6,x22,lsr#32
-	add	v4.4s,v4.4s,v24.4s
-	add	w7,w7,w23
-	add	v16.4s,v16.4s,v24.4s
-	add	x8,x8,x23,lsr#32
-	add	v2.4s,v2.4s,v26.4s
-	add	w9,w9,w24
-	add	v6.4s,v6.4s,v26.4s
-	add	x10,x10,x24,lsr#32
-	add	v18.4s,v18.4s,v26.4s
-	add	w11,w11,w25
-	add	v3.4s,v3.4s,v27.4s
-	add	x12,x12,x25,lsr#32
-	add	w13,w13,w26
-	add	v7.4s,v7.4s,v28.4s
-	add	x14,x14,x26,lsr#32
-	add	w15,w15,w27
-	add	v19.4s,v19.4s,v29.4s
-	add	x16,x16,x27,lsr#32
-	add	w17,w17,w28
-	add	v1.4s,v1.4s,v25.4s
-	add	x19,x19,x28,lsr#32
-	add	w20,w20,w30
-	add	v5.4s,v5.4s,v25.4s
-	add	x21,x21,x30,lsr#32
-	add	v17.4s,v17.4s,v25.4s
-
-	b.lo	.Ltail_neon
-
-	add	x5,x5,x6,lsl#32	// pack
-	add	x7,x7,x8,lsl#32
-	ldp	x6,x8,[x1,#0]		// load input
-	add	x9,x9,x10,lsl#32
-	add	x11,x11,x12,lsl#32
-	ldp	x10,x12,[x1,#16]
-	add	x13,x13,x14,lsl#32
-	add	x15,x15,x16,lsl#32
-	ldp	x14,x16,[x1,#32]
-	add	x17,x17,x19,lsl#32
-	add	x20,x20,x21,lsl#32
-	ldp	x19,x21,[x1,#48]
-	add	x1,x1,#64
-#ifdef	__AARCH64EB__
-	rev	x5,x5
-	rev	x7,x7
-	rev	x9,x9
-	rev	x11,x11
-	rev	x13,x13
-	rev	x15,x15
-	rev	x17,x17
-	rev	x20,x20
-#endif
-	ld1	{v20.16b,v21.16b,v22.16b,v23.16b},[x1],#64
-	eor	x5,x5,x6
-	eor	x7,x7,x8
-	eor	x9,x9,x10
-	eor	x11,x11,x12
-	eor	x13,x13,x14
-	eor	v0.16b,v0.16b,v20.16b
-	eor	x15,x15,x16
-	eor	v1.16b,v1.16b,v21.16b
-	eor	x17,x17,x19
-	eor	v2.16b,v2.16b,v22.16b
-	eor	x20,x20,x21
-	eor	v3.16b,v3.16b,v23.16b
-	ld1	{v20.16b,v21.16b,v22.16b,v23.16b},[x1],#64
-
-	stp	x5,x7,[x0,#0]		// store output
-	add	x28,x28,#4			// increment counter
-	stp	x9,x11,[x0,#16]
-	add	v27.4s,v27.4s,v31.4s		// += 4
-	stp	x13,x15,[x0,#32]
-	add	v28.4s,v28.4s,v31.4s
-	stp	x17,x20,[x0,#48]
-	add	v29.4s,v29.4s,v31.4s
-	add	x0,x0,#64
-
-	st1	{v0.16b,v1.16b,v2.16b,v3.16b},[x0],#64
-	ld1	{v0.16b,v1.16b,v2.16b,v3.16b},[x1],#64
-
-	eor	v4.16b,v4.16b,v20.16b
-	eor	v5.16b,v5.16b,v21.16b
-	eor	v6.16b,v6.16b,v22.16b
-	eor	v7.16b,v7.16b,v23.16b
-	st1	{v4.16b,v5.16b,v6.16b,v7.16b},[x0],#64
-
-	eor	v16.16b,v16.16b,v0.16b
-	eor	v17.16b,v17.16b,v1.16b
-	eor	v18.16b,v18.16b,v2.16b
-	eor	v19.16b,v19.16b,v3.16b
-	st1	{v16.16b,v17.16b,v18.16b,v19.16b},[x0],#64
-
-	b.hi	.Loop_outer_neon
-
-	ldp	x19,x20,[x29,#16]
-	add	sp,sp,#64
-	ldp	x21,x22,[x29,#32]
-	ldp	x23,x24,[x29,#48]
-	ldp	x25,x26,[x29,#64]
-	ldp	x27,x28,[x29,#80]
-	ldp	x29,x30,[sp],#96
-	ret
-
-.Ltail_neon:
-	add	x2,x2,#256
-	cmp	x2,#64
-	b.lo	.Less_than_64
-
-	add	x5,x5,x6,lsl#32	// pack
-	add	x7,x7,x8,lsl#32
-	ldp	x6,x8,[x1,#0]		// load input
-	add	x9,x9,x10,lsl#32
-	add	x11,x11,x12,lsl#32
-	ldp	x10,x12,[x1,#16]
-	add	x13,x13,x14,lsl#32
-	add	x15,x15,x16,lsl#32
-	ldp	x14,x16,[x1,#32]
-	add	x17,x17,x19,lsl#32
-	add	x20,x20,x21,lsl#32
-	ldp	x19,x21,[x1,#48]
-	add	x1,x1,#64
-#ifdef	__AARCH64EB__
-	rev	x5,x5
-	rev	x7,x7
-	rev	x9,x9
-	rev	x11,x11
-	rev	x13,x13
-	rev	x15,x15
-	rev	x17,x17
-	rev	x20,x20
-#endif
-	eor	x5,x5,x6
-	eor	x7,x7,x8
-	eor	x9,x9,x10
-	eor	x11,x11,x12
-	eor	x13,x13,x14
-	eor	x15,x15,x16
-	eor	x17,x17,x19
-	eor	x20,x20,x21
-
-	stp	x5,x7,[x0,#0]		// store output
-	add	x28,x28,#4			// increment counter
-	stp	x9,x11,[x0,#16]
-	stp	x13,x15,[x0,#32]
-	stp	x17,x20,[x0,#48]
-	add	x0,x0,#64
-	b.eq	.Ldone_neon
-	sub	x2,x2,#64
-	cmp	x2,#64
-	b.lo	.Less_than_128
-
-	ld1	{v20.16b,v21.16b,v22.16b,v23.16b},[x1],#64
-	eor	v0.16b,v0.16b,v20.16b
-	eor	v1.16b,v1.16b,v21.16b
-	eor	v2.16b,v2.16b,v22.16b
-	eor	v3.16b,v3.16b,v23.16b
-	st1	{v0.16b,v1.16b,v2.16b,v3.16b},[x0],#64
-	b.eq	.Ldone_neon
-	sub	x2,x2,#64
-	cmp	x2,#64
-	b.lo	.Less_than_192
-
-	ld1	{v20.16b,v21.16b,v22.16b,v23.16b},[x1],#64
-	eor	v4.16b,v4.16b,v20.16b
-	eor	v5.16b,v5.16b,v21.16b
-	eor	v6.16b,v6.16b,v22.16b
-	eor	v7.16b,v7.16b,v23.16b
-	st1	{v4.16b,v5.16b,v6.16b,v7.16b},[x0],#64
-	b.eq	.Ldone_neon
-	sub	x2,x2,#64
-
-	st1	{v16.16b,v17.16b,v18.16b,v19.16b},[sp]
-	b	.Last_neon
-
-.Less_than_128:
-	st1	{v0.16b,v1.16b,v2.16b,v3.16b},[sp]
-	b	.Last_neon
-.Less_than_192:
-	st1	{v4.16b,v5.16b,v6.16b,v7.16b},[sp]
-	b	.Last_neon
-
-.align	4
-.Last_neon:
-	sub	x0,x0,#1
-	add	x1,x1,x2
-	add	x0,x0,x2
-	add	x4,sp,x2
-	neg	x2,x2
-
-.Loop_tail_neon:
-	ldrb	w10,[x1,x2]
-	ldrb	w11,[x4,x2]
-	add	x2,x2,#1
-	eor	w10,w10,w11
-	strb	w10,[x0,x2]
-	cbnz	x2,.Loop_tail_neon
-
-	stp	xzr,xzr,[sp,#0]
-	stp	xzr,xzr,[sp,#16]
-	stp	xzr,xzr,[sp,#32]
-	stp	xzr,xzr,[sp,#48]
-
-.Ldone_neon:
-	ldp	x19,x20,[x29,#16]
-	add	sp,sp,#64
-	ldp	x21,x22,[x29,#32]
-	ldp	x23,x24,[x29,#48]
-	ldp	x25,x26,[x29,#64]
-	ldp	x27,x28,[x29,#80]
-	ldp	x29,x30,[sp],#96
-	ret
-
-.L512_or_more_neon:
-	sub	sp,sp,#128+64
-
-	ldp	x22,x23,[x5]		// load sigma
-	ld1	{v24.4s},[x5],#16
-	ldp	x24,x25,[x3]		// load key
-	ldp	x26,x27,[x3,#16]
-	ld1	{v25.4s,v26.4s},[x3]
-	ldp	x28,x30,[x4]		// load counter
-	ld1	{v27.4s},[x4]
-	ld1	{v31.4s},[x5]
-#ifdef	__AARCH64EB__
-	rev64	v24.4s,v24.4s
-	ror	x24,x24,#32
-	ror	x25,x25,#32
-	ror	x26,x26,#32
-	ror	x27,x27,#32
-	ror	x28,x28,#32
-	ror	x30,x30,#32
-#endif
-	add	v27.4s,v27.4s,v31.4s		// += 1
-	stp	q24,q25,[sp,#0]		// off-load key block, invariant part
-	add	v27.4s,v27.4s,v31.4s		// not typo
-	str	q26,[sp,#32]
-	add	v28.4s,v27.4s,v31.4s
-	add	v29.4s,v28.4s,v31.4s
-	add	v30.4s,v29.4s,v31.4s
-	shl	v31.4s,v31.4s,#2			// 1 -> 4
-
-	stp	d8,d9,[sp,#128+0]		// meet ABI requirements
-	stp	d10,d11,[sp,#128+16]
-	stp	d12,d13,[sp,#128+32]
-	stp	d14,d15,[sp,#128+48]
-
-	sub	x2,x2,#512			// not typo
-
-.Loop_outer_512_neon:
-	mov	v0.16b,v24.16b
-	mov	v4.16b,v24.16b
-	mov	v8.16b,v24.16b
-	mov	v12.16b,v24.16b
-	mov	v16.16b,v24.16b
-	mov	v20.16b,v24.16b
-	mov	v1.16b,v25.16b
-	mov	w5,w22			// unpack key block
-	mov	v5.16b,v25.16b
-	lsr	x6,x22,#32
-	mov	v9.16b,v25.16b
-	mov	w7,w23
-	mov	v13.16b,v25.16b
-	lsr	x8,x23,#32
-	mov	v17.16b,v25.16b
-	mov	w9,w24
-	mov	v21.16b,v25.16b
-	lsr	x10,x24,#32
-	mov	v3.16b,v27.16b
-	mov	w11,w25
-	mov	v7.16b,v28.16b
-	lsr	x12,x25,#32
-	mov	v11.16b,v29.16b
-	mov	w13,w26
-	mov	v15.16b,v30.16b
-	lsr	x14,x26,#32
-	mov	v2.16b,v26.16b
-	mov	w15,w27
-	mov	v6.16b,v26.16b
-	lsr	x16,x27,#32
-	add	v19.4s,v3.4s,v31.4s			// +4
-	mov	w17,w28
-	add	v23.4s,v7.4s,v31.4s			// +4
-	lsr	x19,x28,#32
-	mov	v10.16b,v26.16b
-	mov	w20,w30
-	mov	v14.16b,v26.16b
-	lsr	x21,x30,#32
-	mov	v18.16b,v26.16b
-	stp	q27,q28,[sp,#48]		// off-load key block, variable part
-	mov	v22.16b,v26.16b
-	str	q29,[sp,#80]
-
-	mov	x4,#5
-	subs	x2,x2,#512
-.Loop_upper_neon:
-	sub	x4,x4,#1
-	add	v0.4s,v0.4s,v1.4s
-	add	w5,w5,w9
-	add	v4.4s,v4.4s,v5.4s
-	add	w6,w6,w10
-	add	v8.4s,v8.4s,v9.4s
-	add	w7,w7,w11
-	add	v12.4s,v12.4s,v13.4s
-	add	w8,w8,w12
-	add	v16.4s,v16.4s,v17.4s
-	eor	w17,w17,w5
-	add	v20.4s,v20.4s,v21.4s
-	eor	w19,w19,w6
-	eor	v3.16b,v3.16b,v0.16b
-	eor	w20,w20,w7
-	eor	v7.16b,v7.16b,v4.16b
-	eor	w21,w21,w8
-	eor	v11.16b,v11.16b,v8.16b
-	ror	w17,w17,#16
-	eor	v15.16b,v15.16b,v12.16b
-	ror	w19,w19,#16
-	eor	v19.16b,v19.16b,v16.16b
-	ror	w20,w20,#16
-	eor	v23.16b,v23.16b,v20.16b
-	ror	w21,w21,#16
-	rev32	v3.8h,v3.8h
-	add	w13,w13,w17
-	rev32	v7.8h,v7.8h
-	add	w14,w14,w19
-	rev32	v11.8h,v11.8h
-	add	w15,w15,w20
-	rev32	v15.8h,v15.8h
-	add	w16,w16,w21
-	rev32	v19.8h,v19.8h
-	eor	w9,w9,w13
-	rev32	v23.8h,v23.8h
-	eor	w10,w10,w14
-	add	v2.4s,v2.4s,v3.4s
-	eor	w11,w11,w15
-	add	v6.4s,v6.4s,v7.4s
-	eor	w12,w12,w16
-	add	v10.4s,v10.4s,v11.4s
-	ror	w9,w9,#20
-	add	v14.4s,v14.4s,v15.4s
-	ror	w10,w10,#20
-	add	v18.4s,v18.4s,v19.4s
-	ror	w11,w11,#20
-	add	v22.4s,v22.4s,v23.4s
-	ror	w12,w12,#20
-	eor	v24.16b,v1.16b,v2.16b
-	add	w5,w5,w9
-	eor	v25.16b,v5.16b,v6.16b
-	add	w6,w6,w10
-	eor	v26.16b,v9.16b,v10.16b
-	add	w7,w7,w11
-	eor	v27.16b,v13.16b,v14.16b
-	add	w8,w8,w12
-	eor	v28.16b,v17.16b,v18.16b
-	eor	w17,w17,w5
-	eor	v29.16b,v21.16b,v22.16b
-	eor	w19,w19,w6
-	ushr	v1.4s,v24.4s,#20
-	eor	w20,w20,w7
-	ushr	v5.4s,v25.4s,#20
-	eor	w21,w21,w8
-	ushr	v9.4s,v26.4s,#20
-	ror	w17,w17,#24
-	ushr	v13.4s,v27.4s,#20
-	ror	w19,w19,#24
-	ushr	v17.4s,v28.4s,#20
-	ror	w20,w20,#24
-	ushr	v21.4s,v29.4s,#20
-	ror	w21,w21,#24
-	sli	v1.4s,v24.4s,#12
-	add	w13,w13,w17
-	sli	v5.4s,v25.4s,#12
-	add	w14,w14,w19
-	sli	v9.4s,v26.4s,#12
-	add	w15,w15,w20
-	sli	v13.4s,v27.4s,#12
-	add	w16,w16,w21
-	sli	v17.4s,v28.4s,#12
-	eor	w9,w9,w13
-	sli	v21.4s,v29.4s,#12
-	eor	w10,w10,w14
-	add	v0.4s,v0.4s,v1.4s
-	eor	w11,w11,w15
-	add	v4.4s,v4.4s,v5.4s
-	eor	w12,w12,w16
-	add	v8.4s,v8.4s,v9.4s
-	ror	w9,w9,#25
-	add	v12.4s,v12.4s,v13.4s
-	ror	w10,w10,#25
-	add	v16.4s,v16.4s,v17.4s
-	ror	w11,w11,#25
-	add	v20.4s,v20.4s,v21.4s
-	ror	w12,w12,#25
-	eor	v24.16b,v3.16b,v0.16b
-	add	w5,w5,w10
-	eor	v25.16b,v7.16b,v4.16b
-	add	w6,w6,w11
-	eor	v26.16b,v11.16b,v8.16b
-	add	w7,w7,w12
-	eor	v27.16b,v15.16b,v12.16b
-	add	w8,w8,w9
-	eor	v28.16b,v19.16b,v16.16b
-	eor	w21,w21,w5
-	eor	v29.16b,v23.16b,v20.16b
-	eor	w17,w17,w6
-	ushr	v3.4s,v24.4s,#24
-	eor	w19,w19,w7
-	ushr	v7.4s,v25.4s,#24
-	eor	w20,w20,w8
-	ushr	v11.4s,v26.4s,#24
-	ror	w21,w21,#16
-	ushr	v15.4s,v27.4s,#24
-	ror	w17,w17,#16
-	ushr	v19.4s,v28.4s,#24
-	ror	w19,w19,#16
-	ushr	v23.4s,v29.4s,#24
-	ror	w20,w20,#16
-	sli	v3.4s,v24.4s,#8
-	add	w15,w15,w21
-	sli	v7.4s,v25.4s,#8
-	add	w16,w16,w17
-	sli	v11.4s,v26.4s,#8
-	add	w13,w13,w19
-	sli	v15.4s,v27.4s,#8
-	add	w14,w14,w20
-	sli	v19.4s,v28.4s,#8
-	eor	w10,w10,w15
-	sli	v23.4s,v29.4s,#8
-	eor	w11,w11,w16
-	add	v2.4s,v2.4s,v3.4s
-	eor	w12,w12,w13
-	add	v6.4s,v6.4s,v7.4s
-	eor	w9,w9,w14
-	add	v10.4s,v10.4s,v11.4s
-	ror	w10,w10,#20
-	add	v14.4s,v14.4s,v15.4s
-	ror	w11,w11,#20
-	add	v18.4s,v18.4s,v19.4s
-	ror	w12,w12,#20
-	add	v22.4s,v22.4s,v23.4s
-	ror	w9,w9,#20
-	eor	v24.16b,v1.16b,v2.16b
-	add	w5,w5,w10
-	eor	v25.16b,v5.16b,v6.16b
-	add	w6,w6,w11
-	eor	v26.16b,v9.16b,v10.16b
-	add	w7,w7,w12
-	eor	v27.16b,v13.16b,v14.16b
-	add	w8,w8,w9
-	eor	v28.16b,v17.16b,v18.16b
-	eor	w21,w21,w5
-	eor	v29.16b,v21.16b,v22.16b
-	eor	w17,w17,w6
-	ushr	v1.4s,v24.4s,#25
-	eor	w19,w19,w7
-	ushr	v5.4s,v25.4s,#25
-	eor	w20,w20,w8
-	ushr	v9.4s,v26.4s,#25
-	ror	w21,w21,#24
-	ushr	v13.4s,v27.4s,#25
-	ror	w17,w17,#24
-	ushr	v17.4s,v28.4s,#25
-	ror	w19,w19,#24
-	ushr	v21.4s,v29.4s,#25
-	ror	w20,w20,#24
-	sli	v1.4s,v24.4s,#7
-	add	w15,w15,w21
-	sli	v5.4s,v25.4s,#7
-	add	w16,w16,w17
-	sli	v9.4s,v26.4s,#7
-	add	w13,w13,w19
-	sli	v13.4s,v27.4s,#7
-	add	w14,w14,w20
-	sli	v17.4s,v28.4s,#7
-	eor	w10,w10,w15
-	sli	v21.4s,v29.4s,#7
-	eor	w11,w11,w16
-	ext	v2.16b,v2.16b,v2.16b,#8
-	eor	w12,w12,w13
-	ext	v6.16b,v6.16b,v6.16b,#8
-	eor	w9,w9,w14
-	ext	v10.16b,v10.16b,v10.16b,#8
-	ror	w10,w10,#25
-	ext	v14.16b,v14.16b,v14.16b,#8
-	ror	w11,w11,#25
-	ext	v18.16b,v18.16b,v18.16b,#8
-	ror	w12,w12,#25
-	ext	v22.16b,v22.16b,v22.16b,#8
-	ror	w9,w9,#25
-	ext	v3.16b,v3.16b,v3.16b,#12
-	ext	v7.16b,v7.16b,v7.16b,#12
-	ext	v11.16b,v11.16b,v11.16b,#12
-	ext	v15.16b,v15.16b,v15.16b,#12
-	ext	v19.16b,v19.16b,v19.16b,#12
-	ext	v23.16b,v23.16b,v23.16b,#12
-	ext	v1.16b,v1.16b,v1.16b,#4
-	ext	v5.16b,v5.16b,v5.16b,#4
-	ext	v9.16b,v9.16b,v9.16b,#4
-	ext	v13.16b,v13.16b,v13.16b,#4
-	ext	v17.16b,v17.16b,v17.16b,#4
-	ext	v21.16b,v21.16b,v21.16b,#4
-	add	v0.4s,v0.4s,v1.4s
-	add	w5,w5,w9
-	add	v4.4s,v4.4s,v5.4s
-	add	w6,w6,w10
-	add	v8.4s,v8.4s,v9.4s
-	add	w7,w7,w11
-	add	v12.4s,v12.4s,v13.4s
-	add	w8,w8,w12
-	add	v16.4s,v16.4s,v17.4s
-	eor	w17,w17,w5
-	add	v20.4s,v20.4s,v21.4s
-	eor	w19,w19,w6
-	eor	v3.16b,v3.16b,v0.16b
-	eor	w20,w20,w7
-	eor	v7.16b,v7.16b,v4.16b
-	eor	w21,w21,w8
-	eor	v11.16b,v11.16b,v8.16b
-	ror	w17,w17,#16
-	eor	v15.16b,v15.16b,v12.16b
-	ror	w19,w19,#16
-	eor	v19.16b,v19.16b,v16.16b
-	ror	w20,w20,#16
-	eor	v23.16b,v23.16b,v20.16b
-	ror	w21,w21,#16
-	rev32	v3.8h,v3.8h
-	add	w13,w13,w17
-	rev32	v7.8h,v7.8h
-	add	w14,w14,w19
-	rev32	v11.8h,v11.8h
-	add	w15,w15,w20
-	rev32	v15.8h,v15.8h
-	add	w16,w16,w21
-	rev32	v19.8h,v19.8h
-	eor	w9,w9,w13
-	rev32	v23.8h,v23.8h
-	eor	w10,w10,w14
-	add	v2.4s,v2.4s,v3.4s
-	eor	w11,w11,w15
-	add	v6.4s,v6.4s,v7.4s
-	eor	w12,w12,w16
-	add	v10.4s,v10.4s,v11.4s
-	ror	w9,w9,#20
-	add	v14.4s,v14.4s,v15.4s
-	ror	w10,w10,#20
-	add	v18.4s,v18.4s,v19.4s
-	ror	w11,w11,#20
-	add	v22.4s,v22.4s,v23.4s
-	ror	w12,w12,#20
-	eor	v24.16b,v1.16b,v2.16b
-	add	w5,w5,w9
-	eor	v25.16b,v5.16b,v6.16b
-	add	w6,w6,w10
-	eor	v26.16b,v9.16b,v10.16b
-	add	w7,w7,w11
-	eor	v27.16b,v13.16b,v14.16b
-	add	w8,w8,w12
-	eor	v28.16b,v17.16b,v18.16b
-	eor	w17,w17,w5
-	eor	v29.16b,v21.16b,v22.16b
-	eor	w19,w19,w6
-	ushr	v1.4s,v24.4s,#20
-	eor	w20,w20,w7
-	ushr	v5.4s,v25.4s,#20
-	eor	w21,w21,w8
-	ushr	v9.4s,v26.4s,#20
-	ror	w17,w17,#24
-	ushr	v13.4s,v27.4s,#20
-	ror	w19,w19,#24
-	ushr	v17.4s,v28.4s,#20
-	ror	w20,w20,#24
-	ushr	v21.4s,v29.4s,#20
-	ror	w21,w21,#24
-	sli	v1.4s,v24.4s,#12
-	add	w13,w13,w17
-	sli	v5.4s,v25.4s,#12
-	add	w14,w14,w19
-	sli	v9.4s,v26.4s,#12
-	add	w15,w15,w20
-	sli	v13.4s,v27.4s,#12
-	add	w16,w16,w21
-	sli	v17.4s,v28.4s,#12
-	eor	w9,w9,w13
-	sli	v21.4s,v29.4s,#12
-	eor	w10,w10,w14
-	add	v0.4s,v0.4s,v1.4s
-	eor	w11,w11,w15
-	add	v4.4s,v4.4s,v5.4s
-	eor	w12,w12,w16
-	add	v8.4s,v8.4s,v9.4s
-	ror	w9,w9,#25
-	add	v12.4s,v12.4s,v13.4s
-	ror	w10,w10,#25
-	add	v16.4s,v16.4s,v17.4s
-	ror	w11,w11,#25
-	add	v20.4s,v20.4s,v21.4s
-	ror	w12,w12,#25
-	eor	v24.16b,v3.16b,v0.16b
-	add	w5,w5,w10
-	eor	v25.16b,v7.16b,v4.16b
-	add	w6,w6,w11
-	eor	v26.16b,v11.16b,v8.16b
-	add	w7,w7,w12
-	eor	v27.16b,v15.16b,v12.16b
-	add	w8,w8,w9
-	eor	v28.16b,v19.16b,v16.16b
-	eor	w21,w21,w5
-	eor	v29.16b,v23.16b,v20.16b
-	eor	w17,w17,w6
-	ushr	v3.4s,v24.4s,#24
-	eor	w19,w19,w7
-	ushr	v7.4s,v25.4s,#24
-	eor	w20,w20,w8
-	ushr	v11.4s,v26.4s,#24
-	ror	w21,w21,#16
-	ushr	v15.4s,v27.4s,#24
-	ror	w17,w17,#16
-	ushr	v19.4s,v28.4s,#24
-	ror	w19,w19,#16
-	ushr	v23.4s,v29.4s,#24
-	ror	w20,w20,#16
-	sli	v3.4s,v24.4s,#8
-	add	w15,w15,w21
-	sli	v7.4s,v25.4s,#8
-	add	w16,w16,w17
-	sli	v11.4s,v26.4s,#8
-	add	w13,w13,w19
-	sli	v15.4s,v27.4s,#8
-	add	w14,w14,w20
-	sli	v19.4s,v28.4s,#8
-	eor	w10,w10,w15
-	sli	v23.4s,v29.4s,#8
-	eor	w11,w11,w16
-	add	v2.4s,v2.4s,v3.4s
-	eor	w12,w12,w13
-	add	v6.4s,v6.4s,v7.4s
-	eor	w9,w9,w14
-	add	v10.4s,v10.4s,v11.4s
-	ror	w10,w10,#20
-	add	v14.4s,v14.4s,v15.4s
-	ror	w11,w11,#20
-	add	v18.4s,v18.4s,v19.4s
-	ror	w12,w12,#20
-	add	v22.4s,v22.4s,v23.4s
-	ror	w9,w9,#20
-	eor	v24.16b,v1.16b,v2.16b
-	add	w5,w5,w10
-	eor	v25.16b,v5.16b,v6.16b
-	add	w6,w6,w11
-	eor	v26.16b,v9.16b,v10.16b
-	add	w7,w7,w12
-	eor	v27.16b,v13.16b,v14.16b
-	add	w8,w8,w9
-	eor	v28.16b,v17.16b,v18.16b
-	eor	w21,w21,w5
-	eor	v29.16b,v21.16b,v22.16b
-	eor	w17,w17,w6
-	ushr	v1.4s,v24.4s,#25
-	eor	w19,w19,w7
-	ushr	v5.4s,v25.4s,#25
-	eor	w20,w20,w8
-	ushr	v9.4s,v26.4s,#25
-	ror	w21,w21,#24
-	ushr	v13.4s,v27.4s,#25
-	ror	w17,w17,#24
-	ushr	v17.4s,v28.4s,#25
-	ror	w19,w19,#24
-	ushr	v21.4s,v29.4s,#25
-	ror	w20,w20,#24
-	sli	v1.4s,v24.4s,#7
-	add	w15,w15,w21
-	sli	v5.4s,v25.4s,#7
-	add	w16,w16,w17
-	sli	v9.4s,v26.4s,#7
-	add	w13,w13,w19
-	sli	v13.4s,v27.4s,#7
-	add	w14,w14,w20
-	sli	v17.4s,v28.4s,#7
-	eor	w10,w10,w15
-	sli	v21.4s,v29.4s,#7
-	eor	w11,w11,w16
-	ext	v2.16b,v2.16b,v2.16b,#8
-	eor	w12,w12,w13
-	ext	v6.16b,v6.16b,v6.16b,#8
-	eor	w9,w9,w14
-	ext	v10.16b,v10.16b,v10.16b,#8
-	ror	w10,w10,#25
-	ext	v14.16b,v14.16b,v14.16b,#8
-	ror	w11,w11,#25
-	ext	v18.16b,v18.16b,v18.16b,#8
-	ror	w12,w12,#25
-	ext	v22.16b,v22.16b,v22.16b,#8
-	ror	w9,w9,#25
-	ext	v3.16b,v3.16b,v3.16b,#4
-	ext	v7.16b,v7.16b,v7.16b,#4
-	ext	v11.16b,v11.16b,v11.16b,#4
-	ext	v15.16b,v15.16b,v15.16b,#4
-	ext	v19.16b,v19.16b,v19.16b,#4
-	ext	v23.16b,v23.16b,v23.16b,#4
-	ext	v1.16b,v1.16b,v1.16b,#12
-	ext	v5.16b,v5.16b,v5.16b,#12
-	ext	v9.16b,v9.16b,v9.16b,#12
-	ext	v13.16b,v13.16b,v13.16b,#12
-	ext	v17.16b,v17.16b,v17.16b,#12
-	ext	v21.16b,v21.16b,v21.16b,#12
-	cbnz	x4,.Loop_upper_neon
-
-	add	w5,w5,w22		// accumulate key block
-	add	x6,x6,x22,lsr#32
-	add	w7,w7,w23
-	add	x8,x8,x23,lsr#32
-	add	w9,w9,w24
-	add	x10,x10,x24,lsr#32
-	add	w11,w11,w25
-	add	x12,x12,x25,lsr#32
-	add	w13,w13,w26
-	add	x14,x14,x26,lsr#32
-	add	w15,w15,w27
-	add	x16,x16,x27,lsr#32
-	add	w17,w17,w28
-	add	x19,x19,x28,lsr#32
-	add	w20,w20,w30
-	add	x21,x21,x30,lsr#32
-
-	add	x5,x5,x6,lsl#32	// pack
-	add	x7,x7,x8,lsl#32
-	ldp	x6,x8,[x1,#0]		// load input
-	add	x9,x9,x10,lsl#32
-	add	x11,x11,x12,lsl#32
-	ldp	x10,x12,[x1,#16]
-	add	x13,x13,x14,lsl#32
-	add	x15,x15,x16,lsl#32
-	ldp	x14,x16,[x1,#32]
-	add	x17,x17,x19,lsl#32
-	add	x20,x20,x21,lsl#32
-	ldp	x19,x21,[x1,#48]
-	add	x1,x1,#64
-#ifdef	__AARCH64EB__
-	rev	x5,x5
-	rev	x7,x7
-	rev	x9,x9
-	rev	x11,x11
-	rev	x13,x13
-	rev	x15,x15
-	rev	x17,x17
-	rev	x20,x20
-#endif
-	eor	x5,x5,x6
-	eor	x7,x7,x8
-	eor	x9,x9,x10
-	eor	x11,x11,x12
-	eor	x13,x13,x14
-	eor	x15,x15,x16
-	eor	x17,x17,x19
-	eor	x20,x20,x21
-
-	stp	x5,x7,[x0,#0]		// store output
-	add	x28,x28,#1			// increment counter
-	mov	w5,w22			// unpack key block
-	lsr	x6,x22,#32
-	stp	x9,x11,[x0,#16]
-	mov	w7,w23
-	lsr	x8,x23,#32
-	stp	x13,x15,[x0,#32]
-	mov	w9,w24
-	lsr	x10,x24,#32
-	stp	x17,x20,[x0,#48]
-	add	x0,x0,#64
-	mov	w11,w25
-	lsr	x12,x25,#32
-	mov	w13,w26
-	lsr	x14,x26,#32
-	mov	w15,w27
-	lsr	x16,x27,#32
-	mov	w17,w28
-	lsr	x19,x28,#32
-	mov	w20,w30
-	lsr	x21,x30,#32
-
-	mov	x4,#5
-.Loop_lower_neon:
-	sub	x4,x4,#1
-	add	v0.4s,v0.4s,v1.4s
-	add	w5,w5,w9
-	add	v4.4s,v4.4s,v5.4s
-	add	w6,w6,w10
-	add	v8.4s,v8.4s,v9.4s
-	add	w7,w7,w11
-	add	v12.4s,v12.4s,v13.4s
-	add	w8,w8,w12
-	add	v16.4s,v16.4s,v17.4s
-	eor	w17,w17,w5
-	add	v20.4s,v20.4s,v21.4s
-	eor	w19,w19,w6
-	eor	v3.16b,v3.16b,v0.16b
-	eor	w20,w20,w7
-	eor	v7.16b,v7.16b,v4.16b
-	eor	w21,w21,w8
-	eor	v11.16b,v11.16b,v8.16b
-	ror	w17,w17,#16
-	eor	v15.16b,v15.16b,v12.16b
-	ror	w19,w19,#16
-	eor	v19.16b,v19.16b,v16.16b
-	ror	w20,w20,#16
-	eor	v23.16b,v23.16b,v20.16b
-	ror	w21,w21,#16
-	rev32	v3.8h,v3.8h
-	add	w13,w13,w17
-	rev32	v7.8h,v7.8h
-	add	w14,w14,w19
-	rev32	v11.8h,v11.8h
-	add	w15,w15,w20
-	rev32	v15.8h,v15.8h
-	add	w16,w16,w21
-	rev32	v19.8h,v19.8h
-	eor	w9,w9,w13
-	rev32	v23.8h,v23.8h
-	eor	w10,w10,w14
-	add	v2.4s,v2.4s,v3.4s
-	eor	w11,w11,w15
-	add	v6.4s,v6.4s,v7.4s
-	eor	w12,w12,w16
-	add	v10.4s,v10.4s,v11.4s
-	ror	w9,w9,#20
-	add	v14.4s,v14.4s,v15.4s
-	ror	w10,w10,#20
-	add	v18.4s,v18.4s,v19.4s
-	ror	w11,w11,#20
-	add	v22.4s,v22.4s,v23.4s
-	ror	w12,w12,#20
-	eor	v24.16b,v1.16b,v2.16b
-	add	w5,w5,w9
-	eor	v25.16b,v5.16b,v6.16b
-	add	w6,w6,w10
-	eor	v26.16b,v9.16b,v10.16b
-	add	w7,w7,w11
-	eor	v27.16b,v13.16b,v14.16b
-	add	w8,w8,w12
-	eor	v28.16b,v17.16b,v18.16b
-	eor	w17,w17,w5
-	eor	v29.16b,v21.16b,v22.16b
-	eor	w19,w19,w6
-	ushr	v1.4s,v24.4s,#20
-	eor	w20,w20,w7
-	ushr	v5.4s,v25.4s,#20
-	eor	w21,w21,w8
-	ushr	v9.4s,v26.4s,#20
-	ror	w17,w17,#24
-	ushr	v13.4s,v27.4s,#20
-	ror	w19,w19,#24
-	ushr	v17.4s,v28.4s,#20
-	ror	w20,w20,#24
-	ushr	v21.4s,v29.4s,#20
-	ror	w21,w21,#24
-	sli	v1.4s,v24.4s,#12
-	add	w13,w13,w17
-	sli	v5.4s,v25.4s,#12
-	add	w14,w14,w19
-	sli	v9.4s,v26.4s,#12
-	add	w15,w15,w20
-	sli	v13.4s,v27.4s,#12
-	add	w16,w16,w21
-	sli	v17.4s,v28.4s,#12
-	eor	w9,w9,w13
-	sli	v21.4s,v29.4s,#12
-	eor	w10,w10,w14
-	add	v0.4s,v0.4s,v1.4s
-	eor	w11,w11,w15
-	add	v4.4s,v4.4s,v5.4s
-	eor	w12,w12,w16
-	add	v8.4s,v8.4s,v9.4s
-	ror	w9,w9,#25
-	add	v12.4s,v12.4s,v13.4s
-	ror	w10,w10,#25
-	add	v16.4s,v16.4s,v17.4s
-	ror	w11,w11,#25
-	add	v20.4s,v20.4s,v21.4s
-	ror	w12,w12,#25
-	eor	v24.16b,v3.16b,v0.16b
-	add	w5,w5,w10
-	eor	v25.16b,v7.16b,v4.16b
-	add	w6,w6,w11
-	eor	v26.16b,v11.16b,v8.16b
-	add	w7,w7,w12
-	eor	v27.16b,v15.16b,v12.16b
-	add	w8,w8,w9
-	eor	v28.16b,v19.16b,v16.16b
-	eor	w21,w21,w5
-	eor	v29.16b,v23.16b,v20.16b
-	eor	w17,w17,w6
-	ushr	v3.4s,v24.4s,#24
-	eor	w19,w19,w7
-	ushr	v7.4s,v25.4s,#24
-	eor	w20,w20,w8
-	ushr	v11.4s,v26.4s,#24
-	ror	w21,w21,#16
-	ushr	v15.4s,v27.4s,#24
-	ror	w17,w17,#16
-	ushr	v19.4s,v28.4s,#24
-	ror	w19,w19,#16
-	ushr	v23.4s,v29.4s,#24
-	ror	w20,w20,#16
-	sli	v3.4s,v24.4s,#8
-	add	w15,w15,w21
-	sli	v7.4s,v25.4s,#8
-	add	w16,w16,w17
-	sli	v11.4s,v26.4s,#8
-	add	w13,w13,w19
-	sli	v15.4s,v27.4s,#8
-	add	w14,w14,w20
-	sli	v19.4s,v28.4s,#8
-	eor	w10,w10,w15
-	sli	v23.4s,v29.4s,#8
-	eor	w11,w11,w16
-	add	v2.4s,v2.4s,v3.4s
-	eor	w12,w12,w13
-	add	v6.4s,v6.4s,v7.4s
-	eor	w9,w9,w14
-	add	v10.4s,v10.4s,v11.4s
-	ror	w10,w10,#20
-	add	v14.4s,v14.4s,v15.4s
-	ror	w11,w11,#20
-	add	v18.4s,v18.4s,v19.4s
-	ror	w12,w12,#20
-	add	v22.4s,v22.4s,v23.4s
-	ror	w9,w9,#20
-	eor	v24.16b,v1.16b,v2.16b
-	add	w5,w5,w10
-	eor	v25.16b,v5.16b,v6.16b
-	add	w6,w6,w11
-	eor	v26.16b,v9.16b,v10.16b
-	add	w7,w7,w12
-	eor	v27.16b,v13.16b,v14.16b
-	add	w8,w8,w9
-	eor	v28.16b,v17.16b,v18.16b
-	eor	w21,w21,w5
-	eor	v29.16b,v21.16b,v22.16b
-	eor	w17,w17,w6
-	ushr	v1.4s,v24.4s,#25
-	eor	w19,w19,w7
-	ushr	v5.4s,v25.4s,#25
-	eor	w20,w20,w8
-	ushr	v9.4s,v26.4s,#25
-	ror	w21,w21,#24
-	ushr	v13.4s,v27.4s,#25
-	ror	w17,w17,#24
-	ushr	v17.4s,v28.4s,#25
-	ror	w19,w19,#24
-	ushr	v21.4s,v29.4s,#25
-	ror	w20,w20,#24
-	sli	v1.4s,v24.4s,#7
-	add	w15,w15,w21
-	sli	v5.4s,v25.4s,#7
-	add	w16,w16,w17
-	sli	v9.4s,v26.4s,#7
-	add	w13,w13,w19
-	sli	v13.4s,v27.4s,#7
-	add	w14,w14,w20
-	sli	v17.4s,v28.4s,#7
-	eor	w10,w10,w15
-	sli	v21.4s,v29.4s,#7
-	eor	w11,w11,w16
-	ext	v2.16b,v2.16b,v2.16b,#8
-	eor	w12,w12,w13
-	ext	v6.16b,v6.16b,v6.16b,#8
-	eor	w9,w9,w14
-	ext	v10.16b,v10.16b,v10.16b,#8
-	ror	w10,w10,#25
-	ext	v14.16b,v14.16b,v14.16b,#8
-	ror	w11,w11,#25
-	ext	v18.16b,v18.16b,v18.16b,#8
-	ror	w12,w12,#25
-	ext	v22.16b,v22.16b,v22.16b,#8
-	ror	w9,w9,#25
-	ext	v3.16b,v3.16b,v3.16b,#12
-	ext	v7.16b,v7.16b,v7.16b,#12
-	ext	v11.16b,v11.16b,v11.16b,#12
-	ext	v15.16b,v15.16b,v15.16b,#12
-	ext	v19.16b,v19.16b,v19.16b,#12
-	ext	v23.16b,v23.16b,v23.16b,#12
-	ext	v1.16b,v1.16b,v1.16b,#4
-	ext	v5.16b,v5.16b,v5.16b,#4
-	ext	v9.16b,v9.16b,v9.16b,#4
-	ext	v13.16b,v13.16b,v13.16b,#4
-	ext	v17.16b,v17.16b,v17.16b,#4
-	ext	v21.16b,v21.16b,v21.16b,#4
-	add	v0.4s,v0.4s,v1.4s
-	add	w5,w5,w9
-	add	v4.4s,v4.4s,v5.4s
-	add	w6,w6,w10
-	add	v8.4s,v8.4s,v9.4s
-	add	w7,w7,w11
-	add	v12.4s,v12.4s,v13.4s
-	add	w8,w8,w12
-	add	v16.4s,v16.4s,v17.4s
-	eor	w17,w17,w5
-	add	v20.4s,v20.4s,v21.4s
-	eor	w19,w19,w6
-	eor	v3.16b,v3.16b,v0.16b
-	eor	w20,w20,w7
-	eor	v7.16b,v7.16b,v4.16b
-	eor	w21,w21,w8
-	eor	v11.16b,v11.16b,v8.16b
-	ror	w17,w17,#16
-	eor	v15.16b,v15.16b,v12.16b
-	ror	w19,w19,#16
-	eor	v19.16b,v19.16b,v16.16b
-	ror	w20,w20,#16
-	eor	v23.16b,v23.16b,v20.16b
-	ror	w21,w21,#16
-	rev32	v3.8h,v3.8h
-	add	w13,w13,w17
-	rev32	v7.8h,v7.8h
-	add	w14,w14,w19
-	rev32	v11.8h,v11.8h
-	add	w15,w15,w20
-	rev32	v15.8h,v15.8h
-	add	w16,w16,w21
-	rev32	v19.8h,v19.8h
-	eor	w9,w9,w13
-	rev32	v23.8h,v23.8h
-	eor	w10,w10,w14
-	add	v2.4s,v2.4s,v3.4s
-	eor	w11,w11,w15
-	add	v6.4s,v6.4s,v7.4s
-	eor	w12,w12,w16
-	add	v10.4s,v10.4s,v11.4s
-	ror	w9,w9,#20
-	add	v14.4s,v14.4s,v15.4s
-	ror	w10,w10,#20
-	add	v18.4s,v18.4s,v19.4s
-	ror	w11,w11,#20
-	add	v22.4s,v22.4s,v23.4s
-	ror	w12,w12,#20
-	eor	v24.16b,v1.16b,v2.16b
-	add	w5,w5,w9
-	eor	v25.16b,v5.16b,v6.16b
-	add	w6,w6,w10
-	eor	v26.16b,v9.16b,v10.16b
-	add	w7,w7,w11
-	eor	v27.16b,v13.16b,v14.16b
-	add	w8,w8,w12
-	eor	v28.16b,v17.16b,v18.16b
-	eor	w17,w17,w5
-	eor	v29.16b,v21.16b,v22.16b
-	eor	w19,w19,w6
-	ushr	v1.4s,v24.4s,#20
-	eor	w20,w20,w7
-	ushr	v5.4s,v25.4s,#20
-	eor	w21,w21,w8
-	ushr	v9.4s,v26.4s,#20
-	ror	w17,w17,#24
-	ushr	v13.4s,v27.4s,#20
-	ror	w19,w19,#24
-	ushr	v17.4s,v28.4s,#20
-	ror	w20,w20,#24
-	ushr	v21.4s,v29.4s,#20
-	ror	w21,w21,#24
-	sli	v1.4s,v24.4s,#12
-	add	w13,w13,w17
-	sli	v5.4s,v25.4s,#12
-	add	w14,w14,w19
-	sli	v9.4s,v26.4s,#12
-	add	w15,w15,w20
-	sli	v13.4s,v27.4s,#12
-	add	w16,w16,w21
-	sli	v17.4s,v28.4s,#12
-	eor	w9,w9,w13
-	sli	v21.4s,v29.4s,#12
-	eor	w10,w10,w14
-	add	v0.4s,v0.4s,v1.4s
-	eor	w11,w11,w15
-	add	v4.4s,v4.4s,v5.4s
-	eor	w12,w12,w16
-	add	v8.4s,v8.4s,v9.4s
-	ror	w9,w9,#25
-	add	v12.4s,v12.4s,v13.4s
-	ror	w10,w10,#25
-	add	v16.4s,v16.4s,v17.4s
-	ror	w11,w11,#25
-	add	v20.4s,v20.4s,v21.4s
-	ror	w12,w12,#25
-	eor	v24.16b,v3.16b,v0.16b
-	add	w5,w5,w10
-	eor	v25.16b,v7.16b,v4.16b
-	add	w6,w6,w11
-	eor	v26.16b,v11.16b,v8.16b
-	add	w7,w7,w12
-	eor	v27.16b,v15.16b,v12.16b
-	add	w8,w8,w9
-	eor	v28.16b,v19.16b,v16.16b
-	eor	w21,w21,w5
-	eor	v29.16b,v23.16b,v20.16b
-	eor	w17,w17,w6
-	ushr	v3.4s,v24.4s,#24
-	eor	w19,w19,w7
-	ushr	v7.4s,v25.4s,#24
-	eor	w20,w20,w8
-	ushr	v11.4s,v26.4s,#24
-	ror	w21,w21,#16
-	ushr	v15.4s,v27.4s,#24
-	ror	w17,w17,#16
-	ushr	v19.4s,v28.4s,#24
-	ror	w19,w19,#16
-	ushr	v23.4s,v29.4s,#24
-	ror	w20,w20,#16
-	sli	v3.4s,v24.4s,#8
-	add	w15,w15,w21
-	sli	v7.4s,v25.4s,#8
-	add	w16,w16,w17
-	sli	v11.4s,v26.4s,#8
-	add	w13,w13,w19
-	sli	v15.4s,v27.4s,#8
-	add	w14,w14,w20
-	sli	v19.4s,v28.4s,#8
-	eor	w10,w10,w15
-	sli	v23.4s,v29.4s,#8
-	eor	w11,w11,w16
-	add	v2.4s,v2.4s,v3.4s
-	eor	w12,w12,w13
-	add	v6.4s,v6.4s,v7.4s
-	eor	w9,w9,w14
-	add	v10.4s,v10.4s,v11.4s
-	ror	w10,w10,#20
-	add	v14.4s,v14.4s,v15.4s
-	ror	w11,w11,#20
-	add	v18.4s,v18.4s,v19.4s
-	ror	w12,w12,#20
-	add	v22.4s,v22.4s,v23.4s
-	ror	w9,w9,#20
-	eor	v24.16b,v1.16b,v2.16b
-	add	w5,w5,w10
-	eor	v25.16b,v5.16b,v6.16b
-	add	w6,w6,w11
-	eor	v26.16b,v9.16b,v10.16b
-	add	w7,w7,w12
-	eor	v27.16b,v13.16b,v14.16b
-	add	w8,w8,w9
-	eor	v28.16b,v17.16b,v18.16b
-	eor	w21,w21,w5
-	eor	v29.16b,v21.16b,v22.16b
-	eor	w17,w17,w6
-	ushr	v1.4s,v24.4s,#25
-	eor	w19,w19,w7
-	ushr	v5.4s,v25.4s,#25
-	eor	w20,w20,w8
-	ushr	v9.4s,v26.4s,#25
-	ror	w21,w21,#24
-	ushr	v13.4s,v27.4s,#25
-	ror	w17,w17,#24
-	ushr	v17.4s,v28.4s,#25
-	ror	w19,w19,#24
-	ushr	v21.4s,v29.4s,#25
-	ror	w20,w20,#24
-	sli	v1.4s,v24.4s,#7
-	add	w15,w15,w21
-	sli	v5.4s,v25.4s,#7
-	add	w16,w16,w17
-	sli	v9.4s,v26.4s,#7
-	add	w13,w13,w19
-	sli	v13.4s,v27.4s,#7
-	add	w14,w14,w20
-	sli	v17.4s,v28.4s,#7
-	eor	w10,w10,w15
-	sli	v21.4s,v29.4s,#7
-	eor	w11,w11,w16
-	ext	v2.16b,v2.16b,v2.16b,#8
-	eor	w12,w12,w13
-	ext	v6.16b,v6.16b,v6.16b,#8
-	eor	w9,w9,w14
-	ext	v10.16b,v10.16b,v10.16b,#8
-	ror	w10,w10,#25
-	ext	v14.16b,v14.16b,v14.16b,#8
-	ror	w11,w11,#25
-	ext	v18.16b,v18.16b,v18.16b,#8
-	ror	w12,w12,#25
-	ext	v22.16b,v22.16b,v22.16b,#8
-	ror	w9,w9,#25
-	ext	v3.16b,v3.16b,v3.16b,#4
-	ext	v7.16b,v7.16b,v7.16b,#4
-	ext	v11.16b,v11.16b,v11.16b,#4
-	ext	v15.16b,v15.16b,v15.16b,#4
-	ext	v19.16b,v19.16b,v19.16b,#4
-	ext	v23.16b,v23.16b,v23.16b,#4
-	ext	v1.16b,v1.16b,v1.16b,#12
-	ext	v5.16b,v5.16b,v5.16b,#12
-	ext	v9.16b,v9.16b,v9.16b,#12
-	ext	v13.16b,v13.16b,v13.16b,#12
-	ext	v17.16b,v17.16b,v17.16b,#12
-	ext	v21.16b,v21.16b,v21.16b,#12
-	cbnz	x4,.Loop_lower_neon
-
-	add	w5,w5,w22		// accumulate key block
-	ldp	q24,q25,[sp,#0]
-	add	x6,x6,x22,lsr#32
-	ldp	q26,q27,[sp,#32]
-	add	w7,w7,w23
-	ldp	q28,q29,[sp,#64]
-	add	x8,x8,x23,lsr#32
-	add	v0.4s,v0.4s,v24.4s
-	add	w9,w9,w24
-	add	v4.4s,v4.4s,v24.4s
-	add	x10,x10,x24,lsr#32
-	add	v8.4s,v8.4s,v24.4s
-	add	w11,w11,w25
-	add	v12.4s,v12.4s,v24.4s
-	add	x12,x12,x25,lsr#32
-	add	v16.4s,v16.4s,v24.4s
-	add	w13,w13,w26
-	add	v20.4s,v20.4s,v24.4s
-	add	x14,x14,x26,lsr#32
-	add	v2.4s,v2.4s,v26.4s
-	add	w15,w15,w27
-	add	v6.4s,v6.4s,v26.4s
-	add	x16,x16,x27,lsr#32
-	add	v10.4s,v10.4s,v26.4s
-	add	w17,w17,w28
-	add	v14.4s,v14.4s,v26.4s
-	add	x19,x19,x28,lsr#32
-	add	v18.4s,v18.4s,v26.4s
-	add	w20,w20,w30
-	add	v22.4s,v22.4s,v26.4s
-	add	x21,x21,x30,lsr#32
-	add	v19.4s,v19.4s,v31.4s			// +4
-	add	x5,x5,x6,lsl#32	// pack
-	add	v23.4s,v23.4s,v31.4s			// +4
-	add	x7,x7,x8,lsl#32
-	add	v3.4s,v3.4s,v27.4s
-	ldp	x6,x8,[x1,#0]		// load input
-	add	v7.4s,v7.4s,v28.4s
-	add	x9,x9,x10,lsl#32
-	add	v11.4s,v11.4s,v29.4s
-	add	x11,x11,x12,lsl#32
-	add	v15.4s,v15.4s,v30.4s
-	ldp	x10,x12,[x1,#16]
-	add	v19.4s,v19.4s,v27.4s
-	add	x13,x13,x14,lsl#32
-	add	v23.4s,v23.4s,v28.4s
-	add	x15,x15,x16,lsl#32
-	add	v1.4s,v1.4s,v25.4s
-	ldp	x14,x16,[x1,#32]
-	add	v5.4s,v5.4s,v25.4s
-	add	x17,x17,x19,lsl#32
-	add	v9.4s,v9.4s,v25.4s
-	add	x20,x20,x21,lsl#32
-	add	v13.4s,v13.4s,v25.4s
-	ldp	x19,x21,[x1,#48]
-	add	v17.4s,v17.4s,v25.4s
-	add	x1,x1,#64
-	add	v21.4s,v21.4s,v25.4s
-
-#ifdef	__AARCH64EB__
-	rev	x5,x5
-	rev	x7,x7
-	rev	x9,x9
-	rev	x11,x11
-	rev	x13,x13
-	rev	x15,x15
-	rev	x17,x17
-	rev	x20,x20
-#endif
-	ld1	{v24.16b,v25.16b,v26.16b,v27.16b},[x1],#64
-	eor	x5,x5,x6
-	eor	x7,x7,x8
-	eor	x9,x9,x10
-	eor	x11,x11,x12
-	eor	x13,x13,x14
-	eor	v0.16b,v0.16b,v24.16b
-	eor	x15,x15,x16
-	eor	v1.16b,v1.16b,v25.16b
-	eor	x17,x17,x19
-	eor	v2.16b,v2.16b,v26.16b
-	eor	x20,x20,x21
-	eor	v3.16b,v3.16b,v27.16b
-	ld1	{v24.16b,v25.16b,v26.16b,v27.16b},[x1],#64
-
-	stp	x5,x7,[x0,#0]		// store output
-	add	x28,x28,#7			// increment counter
-	stp	x9,x11,[x0,#16]
-	stp	x13,x15,[x0,#32]
-	stp	x17,x20,[x0,#48]
-	add	x0,x0,#64
-	st1	{v0.16b,v1.16b,v2.16b,v3.16b},[x0],#64
-
-	ld1	{v0.16b,v1.16b,v2.16b,v3.16b},[x1],#64
-	eor	v4.16b,v4.16b,v24.16b
-	eor	v5.16b,v5.16b,v25.16b
-	eor	v6.16b,v6.16b,v26.16b
-	eor	v7.16b,v7.16b,v27.16b
-	st1	{v4.16b,v5.16b,v6.16b,v7.16b},[x0],#64
-
-	ld1	{v4.16b,v5.16b,v6.16b,v7.16b},[x1],#64
-	eor	v8.16b,v8.16b,v0.16b
-	ldp	q24,q25,[sp,#0]
-	eor	v9.16b,v9.16b,v1.16b
-	ldp	q26,q27,[sp,#32]
-	eor	v10.16b,v10.16b,v2.16b
-	eor	v11.16b,v11.16b,v3.16b
-	st1	{v8.16b,v9.16b,v10.16b,v11.16b},[x0],#64
-
-	ld1	{v8.16b,v9.16b,v10.16b,v11.16b},[x1],#64
-	eor	v12.16b,v12.16b,v4.16b
-	eor	v13.16b,v13.16b,v5.16b
-	eor	v14.16b,v14.16b,v6.16b
-	eor	v15.16b,v15.16b,v7.16b
-	st1	{v12.16b,v13.16b,v14.16b,v15.16b},[x0],#64
-
-	ld1	{v12.16b,v13.16b,v14.16b,v15.16b},[x1],#64
-	eor	v16.16b,v16.16b,v8.16b
-	eor	v17.16b,v17.16b,v9.16b
-	eor	v18.16b,v18.16b,v10.16b
-	eor	v19.16b,v19.16b,v11.16b
-	st1	{v16.16b,v17.16b,v18.16b,v19.16b},[x0],#64
-
-	shl	v0.4s,v31.4s,#1			// 4 -> 8
-	eor	v20.16b,v20.16b,v12.16b
-	eor	v21.16b,v21.16b,v13.16b
-	eor	v22.16b,v22.16b,v14.16b
-	eor	v23.16b,v23.16b,v15.16b
-	st1	{v20.16b,v21.16b,v22.16b,v23.16b},[x0],#64
-
-	add	v27.4s,v27.4s,v0.4s			// += 8
-	add	v28.4s,v28.4s,v0.4s
-	add	v29.4s,v29.4s,v0.4s
-	add	v30.4s,v30.4s,v0.4s
-
-	b.hs	.Loop_outer_512_neon
-
-	adds	x2,x2,#512
-	ushr	v0.4s,v31.4s,#2			// 4 -> 1
-
-	ldp	d8,d9,[sp,#128+0]		// meet ABI requirements
-	ldp	d10,d11,[sp,#128+16]
-	ldp	d12,d13,[sp,#128+32]
-	ldp	d14,d15,[sp,#128+48]
-
-	stp	q24,q31,[sp,#0]		// wipe off-load area
-	stp	q24,q31,[sp,#32]
-	stp	q24,q31,[sp,#64]
-
-	b.eq	.Ldone_512_neon
-
-	cmp	x2,#192
-	sub	v27.4s,v27.4s,v0.4s			// -= 1
-	sub	v28.4s,v28.4s,v0.4s
-	sub	v29.4s,v29.4s,v0.4s
-	add	sp,sp,#128
-	b.hs	.Loop_outer_neon
-
-	eor	v25.16b,v25.16b,v25.16b
-	eor	v26.16b,v26.16b,v26.16b
-	eor	v27.16b,v27.16b,v27.16b
-	eor	v28.16b,v28.16b,v28.16b
-	eor	v29.16b,v29.16b,v29.16b
-	eor	v30.16b,v30.16b,v30.16b
-	b	.Loop_outer
-
-.Ldone_512_neon:
-	ldp	x19,x20,[x29,#16]
-	add	sp,sp,#128+64
-	ldp	x21,x22,[x29,#32]
-	ldp	x23,x24,[x29,#48]
-	ldp	x25,x26,[x29,#64]
-	ldp	x27,x28,[x29,#80]
-	ldp	x29,x30,[sp],#96
-.Labort_neon:
-	ret
-ENDPROC(chacha20_neon)
-#endif
diff --git a/src/crypto/zinc/chacha20/chacha20-arm64.pl b/src/crypto/zinc/chacha20/chacha20-arm64.pl
new file mode 100644
index 0000000..7926c8d
--- /dev/null
+++ b/src/crypto/zinc/chacha20/chacha20-arm64.pl
@@ -0,0 +1,1164 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+#
+# This code is taken from the OpenSSL project but the author, Andy Polyakov,
+# has relicensed it under the licenses specified in the SPDX header above.
+# The original headers, including the original license headers, are
+# included below for completeness.
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# June 2015
+#
+# ChaCha20 for ARMv8.
+#
+# Performance in cycles per byte out of large buffer.
+#
+#			IALU/gcc-4.9    3xNEON+1xIALU	6xNEON+2xIALU(*)
+#
+# Apple A7		5.50/+49%       3.33            1.70
+# Cortex-A53		8.40/+80%       4.72		4.72(**)
+# Cortex-A57		8.06/+43%       4.90            4.43(***)
+# Denver		4.50/+82%       2.63		2.67(**)
+# X-Gene		9.50/+46%       8.82		8.89(**)
+# Mongoose		8.00/+44%	3.64		3.25(***)
+# Kryo			8.17/+50%	4.83		4.65(***)
+#
+# (*)	since no non-Apple processor exhibits significantly better
+#	performance, the code path is #ifdef __APPLE__-ed;
+# (**)	it's expected that doubling interleave factor doesn't help
+#	all processors, only those with higher NEON latency and
+#	higher instruction issue rate;
+# (***)	expected improvement was actually higher;
+
+$flavour=shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
+
+sub AUTOLOAD()		# thunk [simplified] x86-style perlasm
+{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./;
+  my $arg = pop;
+    $arg = "#$arg" if ($arg*1 eq $arg);
+    $code .= "\t$opcode\t".join(',',@_,$arg)."\n";
+}
+
+my ($out,$inp,$len,$key,$ctr) = map("x$_",(0..4));
+
+my @x=map("x$_",(5..17,19..21));
+my @d=map("x$_",(22..28,30));
+
+sub ROUND {
+my ($a0,$b0,$c0,$d0)=@_;
+my ($a1,$b1,$c1,$d1)=map(($_&~3)+(($_+1)&3),($a0,$b0,$c0,$d0));
+my ($a2,$b2,$c2,$d2)=map(($_&~3)+(($_+1)&3),($a1,$b1,$c1,$d1));
+my ($a3,$b3,$c3,$d3)=map(($_&~3)+(($_+1)&3),($a2,$b2,$c2,$d2));
+
+    (
+	"&add_32	(@x[$a0],@x[$a0],@x[$b0])",
+	 "&add_32	(@x[$a1],@x[$a1],@x[$b1])",
+	  "&add_32	(@x[$a2],@x[$a2],@x[$b2])",
+	   "&add_32	(@x[$a3],@x[$a3],@x[$b3])",
+	"&eor_32	(@x[$d0],@x[$d0],@x[$a0])",
+	 "&eor_32	(@x[$d1],@x[$d1],@x[$a1])",
+	  "&eor_32	(@x[$d2],@x[$d2],@x[$a2])",
+	   "&eor_32	(@x[$d3],@x[$d3],@x[$a3])",
+	"&ror_32	(@x[$d0],@x[$d0],16)",
+	 "&ror_32	(@x[$d1],@x[$d1],16)",
+	  "&ror_32	(@x[$d2],@x[$d2],16)",
+	   "&ror_32	(@x[$d3],@x[$d3],16)",
+
+	"&add_32	(@x[$c0],@x[$c0],@x[$d0])",
+	 "&add_32	(@x[$c1],@x[$c1],@x[$d1])",
+	  "&add_32	(@x[$c2],@x[$c2],@x[$d2])",
+	   "&add_32	(@x[$c3],@x[$c3],@x[$d3])",
+	"&eor_32	(@x[$b0],@x[$b0],@x[$c0])",
+	 "&eor_32	(@x[$b1],@x[$b1],@x[$c1])",
+	  "&eor_32	(@x[$b2],@x[$b2],@x[$c2])",
+	   "&eor_32	(@x[$b3],@x[$b3],@x[$c3])",
+	"&ror_32	(@x[$b0],@x[$b0],20)",
+	 "&ror_32	(@x[$b1],@x[$b1],20)",
+	  "&ror_32	(@x[$b2],@x[$b2],20)",
+	   "&ror_32	(@x[$b3],@x[$b3],20)",
+
+	"&add_32	(@x[$a0],@x[$a0],@x[$b0])",
+	 "&add_32	(@x[$a1],@x[$a1],@x[$b1])",
+	  "&add_32	(@x[$a2],@x[$a2],@x[$b2])",
+	   "&add_32	(@x[$a3],@x[$a3],@x[$b3])",
+	"&eor_32	(@x[$d0],@x[$d0],@x[$a0])",
+	 "&eor_32	(@x[$d1],@x[$d1],@x[$a1])",
+	  "&eor_32	(@x[$d2],@x[$d2],@x[$a2])",
+	   "&eor_32	(@x[$d3],@x[$d3],@x[$a3])",
+	"&ror_32	(@x[$d0],@x[$d0],24)",
+	 "&ror_32	(@x[$d1],@x[$d1],24)",
+	  "&ror_32	(@x[$d2],@x[$d2],24)",
+	   "&ror_32	(@x[$d3],@x[$d3],24)",
+
+	"&add_32	(@x[$c0],@x[$c0],@x[$d0])",
+	 "&add_32	(@x[$c1],@x[$c1],@x[$d1])",
+	  "&add_32	(@x[$c2],@x[$c2],@x[$d2])",
+	   "&add_32	(@x[$c3],@x[$c3],@x[$d3])",
+	"&eor_32	(@x[$b0],@x[$b0],@x[$c0])",
+	 "&eor_32	(@x[$b1],@x[$b1],@x[$c1])",
+	  "&eor_32	(@x[$b2],@x[$b2],@x[$c2])",
+	   "&eor_32	(@x[$b3],@x[$b3],@x[$c3])",
+	"&ror_32	(@x[$b0],@x[$b0],25)",
+	 "&ror_32	(@x[$b1],@x[$b1],25)",
+	  "&ror_32	(@x[$b2],@x[$b2],25)",
+	   "&ror_32	(@x[$b3],@x[$b3],25)"
+    );
+}
+
+$code.=<<___;
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+.extern	OPENSSL_armcap_P
+#else
+# define ChaCha20_ctr32 chacha20_arm
+# define ChaCha20_neon  chacha20_neon
+#endif
+
+.text
+
+.align	5
+.Lsigma:
+.quad	0x3320646e61707865,0x6b20657479622d32		// endian-neutral
+.Lone:
+.long	1,0,0,0
+#ifndef	__KERNEL__
+.LOPENSSL_armcap_P:
+# ifdef	__ILP32__
+.long	OPENSSL_armcap_P-.
+# else
+.quad	OPENSSL_armcap_P-.
+# endif
+#endif
+
+.globl	ChaCha20_ctr32
+.type	ChaCha20_ctr32,%function
+.align	5
+ChaCha20_ctr32:
+	cbz	$len,.Labort
+#ifndef	__KERNEL__
+	adr	@x[0],.LOPENSSL_armcap_P
+	cmp	$len,#192
+	b.lo	.Lshort
+# ifdef	__ILP32__
+	ldrsw	@x[1],[@x[0]]
+# else
+	ldr	@x[1],[@x[0]]
+# endif
+	ldr	w17,[@x[1],@x[0]]
+	tst	w17,#ARMV7_NEON
+	b.ne	ChaCha20_neon
+
+.Lshort:
+#endif
+	stp	x29,x30,[sp,#-96]!
+	add	x29,sp,#0
+
+	adr	@x[0],.Lsigma
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+	sub	sp,sp,#64
+
+	ldp	@d[0],@d[1],[@x[0]]		// load sigma
+	ldp	@d[2],@d[3],[$key]		// load key
+	ldp	@d[4],@d[5],[$key,#16]
+	ldp	@d[6],@d[7],[$ctr]		// load counter
+#ifdef	__AARCH64EB__
+	ror	@d[2],@d[2],#32
+	ror	@d[3],@d[3],#32
+	ror	@d[4],@d[4],#32
+	ror	@d[5],@d[5],#32
+	ror	@d[6],@d[6],#32
+	ror	@d[7],@d[7],#32
+#endif
+
+.Loop_outer:
+	mov.32	@x[0],@d[0]			// unpack key block
+	lsr	@x[1],@d[0],#32
+	mov.32	@x[2],@d[1]
+	lsr	@x[3],@d[1],#32
+	mov.32	@x[4],@d[2]
+	lsr	@x[5],@d[2],#32
+	mov.32	@x[6],@d[3]
+	lsr	@x[7],@d[3],#32
+	mov.32	@x[8],@d[4]
+	lsr	@x[9],@d[4],#32
+	mov.32	@x[10],@d[5]
+	lsr	@x[11],@d[5],#32
+	mov.32	@x[12],@d[6]
+	lsr	@x[13],@d[6],#32
+	mov.32	@x[14],@d[7]
+	lsr	@x[15],@d[7],#32
+
+	mov	$ctr,#10
+	subs	$len,$len,#64
+.Loop:
+	sub	$ctr,$ctr,#1
+___
+	foreach (&ROUND(0, 4, 8,12)) { eval; }
+	foreach (&ROUND(0, 5,10,15)) { eval; }
+$code.=<<___;
+	cbnz	$ctr,.Loop
+
+	add.32	@x[0],@x[0],@d[0]		// accumulate key block
+	add	@x[1],@x[1],@d[0],lsr#32
+	add.32	@x[2],@x[2],@d[1]
+	add	@x[3],@x[3],@d[1],lsr#32
+	add.32	@x[4],@x[4],@d[2]
+	add	@x[5],@x[5],@d[2],lsr#32
+	add.32	@x[6],@x[6],@d[3]
+	add	@x[7],@x[7],@d[3],lsr#32
+	add.32	@x[8],@x[8],@d[4]
+	add	@x[9],@x[9],@d[4],lsr#32
+	add.32	@x[10],@x[10],@d[5]
+	add	@x[11],@x[11],@d[5],lsr#32
+	add.32	@x[12],@x[12],@d[6]
+	add	@x[13],@x[13],@d[6],lsr#32
+	add.32	@x[14],@x[14],@d[7]
+	add	@x[15],@x[15],@d[7],lsr#32
+
+	b.lo	.Ltail
+
+	add	@x[0],@x[0],@x[1],lsl#32	// pack
+	add	@x[2],@x[2],@x[3],lsl#32
+	ldp	@x[1],@x[3],[$inp,#0]		// load input
+	add	@x[4],@x[4],@x[5],lsl#32
+	add	@x[6],@x[6],@x[7],lsl#32
+	ldp	@x[5],@x[7],[$inp,#16]
+	add	@x[8],@x[8],@x[9],lsl#32
+	add	@x[10],@x[10],@x[11],lsl#32
+	ldp	@x[9],@x[11],[$inp,#32]
+	add	@x[12],@x[12],@x[13],lsl#32
+	add	@x[14],@x[14],@x[15],lsl#32
+	ldp	@x[13],@x[15],[$inp,#48]
+	add	$inp,$inp,#64
+#ifdef	__AARCH64EB__
+	rev	@x[0],@x[0]
+	rev	@x[2],@x[2]
+	rev	@x[4],@x[4]
+	rev	@x[6],@x[6]
+	rev	@x[8],@x[8]
+	rev	@x[10],@x[10]
+	rev	@x[12],@x[12]
+	rev	@x[14],@x[14]
+#endif
+	eor	@x[0],@x[0],@x[1]
+	eor	@x[2],@x[2],@x[3]
+	eor	@x[4],@x[4],@x[5]
+	eor	@x[6],@x[6],@x[7]
+	eor	@x[8],@x[8],@x[9]
+	eor	@x[10],@x[10],@x[11]
+	eor	@x[12],@x[12],@x[13]
+	eor	@x[14],@x[14],@x[15]
+
+	stp	@x[0],@x[2],[$out,#0]		// store output
+	 add	@d[6],@d[6],#1			// increment counter
+	stp	@x[4],@x[6],[$out,#16]
+	stp	@x[8],@x[10],[$out,#32]
+	stp	@x[12],@x[14],[$out,#48]
+	add	$out,$out,#64
+
+	b.hi	.Loop_outer
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+.Labort:
+	ret
+
+.align	4
+.Ltail:
+	add	$len,$len,#64
+.Less_than_64:
+	sub	$out,$out,#1
+	add	$inp,$inp,$len
+	add	$out,$out,$len
+	add	$ctr,sp,$len
+	neg	$len,$len
+
+	add	@x[0],@x[0],@x[1],lsl#32	// pack
+	add	@x[2],@x[2],@x[3],lsl#32
+	add	@x[4],@x[4],@x[5],lsl#32
+	add	@x[6],@x[6],@x[7],lsl#32
+	add	@x[8],@x[8],@x[9],lsl#32
+	add	@x[10],@x[10],@x[11],lsl#32
+	add	@x[12],@x[12],@x[13],lsl#32
+	add	@x[14],@x[14],@x[15],lsl#32
+#ifdef	__AARCH64EB__
+	rev	@x[0],@x[0]
+	rev	@x[2],@x[2]
+	rev	@x[4],@x[4]
+	rev	@x[6],@x[6]
+	rev	@x[8],@x[8]
+	rev	@x[10],@x[10]
+	rev	@x[12],@x[12]
+	rev	@x[14],@x[14]
+#endif
+	stp	@x[0],@x[2],[sp,#0]
+	stp	@x[4],@x[6],[sp,#16]
+	stp	@x[8],@x[10],[sp,#32]
+	stp	@x[12],@x[14],[sp,#48]
+
+.Loop_tail:
+	ldrb	w10,[$inp,$len]
+	ldrb	w11,[$ctr,$len]
+	add	$len,$len,#1
+	eor	w10,w10,w11
+	strb	w10,[$out,$len]
+	cbnz	$len,.Loop_tail
+
+	stp	xzr,xzr,[sp,#0]
+	stp	xzr,xzr,[sp,#16]
+	stp	xzr,xzr,[sp,#32]
+	stp	xzr,xzr,[sp,#48]
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+	ret
+.size	ChaCha20_ctr32,.-ChaCha20_ctr32
+___
+
+{{{
+my ($A0,$B0,$C0,$D0,$A1,$B1,$C1,$D1,$A2,$B2,$C2,$D2,$T0,$T1,$T2,$T3) =
+    map("v$_.4s",(0..7,16..23));
+my (@K)=map("v$_.4s",(24..30));
+my $ONE="v31.4s";
+
+sub NEONROUND {
+my $odd = pop;
+my ($a,$b,$c,$d,$t)=@_;
+
+	(
+	"&add		('$a','$a','$b')",
+	"&eor		('$d','$d','$a')",
+	"&rev32_16	('$d','$d')",		# vrot ($d,16)
+
+	"&add		('$c','$c','$d')",
+	"&eor		('$t','$b','$c')",
+	"&ushr		('$b','$t',20)",
+	"&sli		('$b','$t',12)",
+
+	"&add		('$a','$a','$b')",
+	"&eor		('$t','$d','$a')",
+	"&ushr		('$d','$t',24)",
+	"&sli		('$d','$t',8)",
+
+	"&add		('$c','$c','$d')",
+	"&eor		('$t','$b','$c')",
+	"&ushr		('$b','$t',25)",
+	"&sli		('$b','$t',7)",
+
+	"&ext		('$c','$c','$c',8)",
+	"&ext		('$d','$d','$d',$odd?4:12)",
+	"&ext		('$b','$b','$b',$odd?12:4)"
+	);
+}
+
+$code.=<<___;
+
+#ifdef __KERNEL__
+.globl  ChaCha20_neon
+.type   ChaCha20_neon,%function
+#endif
+.type	ChaCha20_neon,%function
+.align	5
+ChaCha20_neon:
+	stp	x29,x30,[sp,#-96]!
+	add	x29,sp,#0
+
+	adr	@x[0],.Lsigma
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+#ifdef	__APPLE__
+	cmp	$len,#512
+	b.hs	.L512_or_more_neon
+#endif
+
+	sub	sp,sp,#64
+
+	ldp	@d[0],@d[1],[@x[0]]		// load sigma
+	ld1	{@K[0]},[@x[0]],#16
+	ldp	@d[2],@d[3],[$key]		// load key
+	ldp	@d[4],@d[5],[$key,#16]
+	ld1	{@K[1],@K[2]},[$key]
+	ldp	@d[6],@d[7],[$ctr]		// load counter
+	ld1	{@K[3]},[$ctr]
+	ld1	{$ONE},[@x[0]]
+#ifdef	__AARCH64EB__
+	rev64	@K[0],@K[0]
+	ror	@d[2],@d[2],#32
+	ror	@d[3],@d[3],#32
+	ror	@d[4],@d[4],#32
+	ror	@d[5],@d[5],#32
+	ror	@d[6],@d[6],#32
+	ror	@d[7],@d[7],#32
+#endif
+	add	@K[3],@K[3],$ONE		// += 1
+	add	@K[4],@K[3],$ONE
+	add	@K[5],@K[4],$ONE
+	shl	$ONE,$ONE,#2			// 1 -> 4
+
+.Loop_outer_neon:
+	mov.32	@x[0],@d[0]			// unpack key block
+	lsr	@x[1],@d[0],#32
+	 mov	$A0,@K[0]
+	mov.32	@x[2],@d[1]
+	lsr	@x[3],@d[1],#32
+	 mov	$A1,@K[0]
+	mov.32	@x[4],@d[2]
+	lsr	@x[5],@d[2],#32
+	 mov	$A2,@K[0]
+	mov.32	@x[6],@d[3]
+	 mov	$B0,@K[1]
+	lsr	@x[7],@d[3],#32
+	 mov	$B1,@K[1]
+	mov.32	@x[8],@d[4]
+	 mov	$B2,@K[1]
+	lsr	@x[9],@d[4],#32
+	 mov	$D0,@K[3]
+	mov.32	@x[10],@d[5]
+	 mov	$D1,@K[4]
+	lsr	@x[11],@d[5],#32
+	 mov	$D2,@K[5]
+	mov.32	@x[12],@d[6]
+	 mov	$C0,@K[2]
+	lsr	@x[13],@d[6],#32
+	 mov	$C1,@K[2]
+	mov.32	@x[14],@d[7]
+	 mov	$C2,@K[2]
+	lsr	@x[15],@d[7],#32
+
+	mov	$ctr,#10
+	subs	$len,$len,#256
+.Loop_neon:
+	sub	$ctr,$ctr,#1
+___
+	my @thread0=&NEONROUND($A0,$B0,$C0,$D0,$T0,0);
+	my @thread1=&NEONROUND($A1,$B1,$C1,$D1,$T1,0);
+	my @thread2=&NEONROUND($A2,$B2,$C2,$D2,$T2,0);
+	my @thread3=&ROUND(0,4,8,12);
+
+	foreach (@thread0) {
+		eval;			eval(shift(@thread3));
+		eval(shift(@thread1));	eval(shift(@thread3));
+		eval(shift(@thread2));	eval(shift(@thread3));
+	}
+
+	@thread0=&NEONROUND($A0,$B0,$C0,$D0,$T0,1);
+	@thread1=&NEONROUND($A1,$B1,$C1,$D1,$T1,1);
+	@thread2=&NEONROUND($A2,$B2,$C2,$D2,$T2,1);
+	@thread3=&ROUND(0,5,10,15);
+
+	foreach (@thread0) {
+		eval;			eval(shift(@thread3));
+		eval(shift(@thread1));	eval(shift(@thread3));
+		eval(shift(@thread2));	eval(shift(@thread3));
+	}
+$code.=<<___;
+	cbnz	$ctr,.Loop_neon
+
+	add.32	@x[0],@x[0],@d[0]		// accumulate key block
+	 add	$A0,$A0,@K[0]
+	add	@x[1],@x[1],@d[0],lsr#32
+	 add	$A1,$A1,@K[0]
+	add.32	@x[2],@x[2],@d[1]
+	 add	$A2,$A2,@K[0]
+	add	@x[3],@x[3],@d[1],lsr#32
+	 add	$C0,$C0,@K[2]
+	add.32	@x[4],@x[4],@d[2]
+	 add	$C1,$C1,@K[2]
+	add	@x[5],@x[5],@d[2],lsr#32
+	 add	$C2,$C2,@K[2]
+	add.32	@x[6],@x[6],@d[3]
+	 add	$D0,$D0,@K[3]
+	add	@x[7],@x[7],@d[3],lsr#32
+	add.32	@x[8],@x[8],@d[4]
+	 add	$D1,$D1,@K[4]
+	add	@x[9],@x[9],@d[4],lsr#32
+	add.32	@x[10],@x[10],@d[5]
+	 add	$D2,$D2,@K[5]
+	add	@x[11],@x[11],@d[5],lsr#32
+	add.32	@x[12],@x[12],@d[6]
+	 add	$B0,$B0,@K[1]
+	add	@x[13],@x[13],@d[6],lsr#32
+	add.32	@x[14],@x[14],@d[7]
+	 add	$B1,$B1,@K[1]
+	add	@x[15],@x[15],@d[7],lsr#32
+	 add	$B2,$B2,@K[1]
+
+	b.lo	.Ltail_neon
+
+	add	@x[0],@x[0],@x[1],lsl#32	// pack
+	add	@x[2],@x[2],@x[3],lsl#32
+	ldp	@x[1],@x[3],[$inp,#0]		// load input
+	add	@x[4],@x[4],@x[5],lsl#32
+	add	@x[6],@x[6],@x[7],lsl#32
+	ldp	@x[5],@x[7],[$inp,#16]
+	add	@x[8],@x[8],@x[9],lsl#32
+	add	@x[10],@x[10],@x[11],lsl#32
+	ldp	@x[9],@x[11],[$inp,#32]
+	add	@x[12],@x[12],@x[13],lsl#32
+	add	@x[14],@x[14],@x[15],lsl#32
+	ldp	@x[13],@x[15],[$inp,#48]
+	add	$inp,$inp,#64
+#ifdef	__AARCH64EB__
+	rev	@x[0],@x[0]
+	rev	@x[2],@x[2]
+	rev	@x[4],@x[4]
+	rev	@x[6],@x[6]
+	rev	@x[8],@x[8]
+	rev	@x[10],@x[10]
+	rev	@x[12],@x[12]
+	rev	@x[14],@x[14]
+#endif
+	ld1.8	{$T0-$T3},[$inp],#64
+	eor	@x[0],@x[0],@x[1]
+	eor	@x[2],@x[2],@x[3]
+	eor	@x[4],@x[4],@x[5]
+	eor	@x[6],@x[6],@x[7]
+	eor	@x[8],@x[8],@x[9]
+	 eor	$A0,$A0,$T0
+	eor	@x[10],@x[10],@x[11]
+	 eor	$B0,$B0,$T1
+	eor	@x[12],@x[12],@x[13]
+	 eor	$C0,$C0,$T2
+	eor	@x[14],@x[14],@x[15]
+	 eor	$D0,$D0,$T3
+	 ld1.8	{$T0-$T3},[$inp],#64
+
+	stp	@x[0],@x[2],[$out,#0]		// store output
+	 add	@d[6],@d[6],#4			// increment counter
+	stp	@x[4],@x[6],[$out,#16]
+	 add	@K[3],@K[3],$ONE		// += 4
+	stp	@x[8],@x[10],[$out,#32]
+	 add	@K[4],@K[4],$ONE
+	stp	@x[12],@x[14],[$out,#48]
+	 add	@K[5],@K[5],$ONE
+	add	$out,$out,#64
+
+	st1.8	{$A0-$D0},[$out],#64
+	ld1.8	{$A0-$D0},[$inp],#64
+
+	eor	$A1,$A1,$T0
+	eor	$B1,$B1,$T1
+	eor	$C1,$C1,$T2
+	eor	$D1,$D1,$T3
+	st1.8	{$A1-$D1},[$out],#64
+
+	eor	$A2,$A2,$A0
+	eor	$B2,$B2,$B0
+	eor	$C2,$C2,$C0
+	eor	$D2,$D2,$D0
+	st1.8	{$A2-$D2},[$out],#64
+
+	b.hi	.Loop_outer_neon
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+	ret
+
+.Ltail_neon:
+	add	$len,$len,#256
+	cmp	$len,#64
+	b.lo	.Less_than_64
+
+	add	@x[0],@x[0],@x[1],lsl#32	// pack
+	add	@x[2],@x[2],@x[3],lsl#32
+	ldp	@x[1],@x[3],[$inp,#0]		// load input
+	add	@x[4],@x[4],@x[5],lsl#32
+	add	@x[6],@x[6],@x[7],lsl#32
+	ldp	@x[5],@x[7],[$inp,#16]
+	add	@x[8],@x[8],@x[9],lsl#32
+	add	@x[10],@x[10],@x[11],lsl#32
+	ldp	@x[9],@x[11],[$inp,#32]
+	add	@x[12],@x[12],@x[13],lsl#32
+	add	@x[14],@x[14],@x[15],lsl#32
+	ldp	@x[13],@x[15],[$inp,#48]
+	add	$inp,$inp,#64
+#ifdef	__AARCH64EB__
+	rev	@x[0],@x[0]
+	rev	@x[2],@x[2]
+	rev	@x[4],@x[4]
+	rev	@x[6],@x[6]
+	rev	@x[8],@x[8]
+	rev	@x[10],@x[10]
+	rev	@x[12],@x[12]
+	rev	@x[14],@x[14]
+#endif
+	eor	@x[0],@x[0],@x[1]
+	eor	@x[2],@x[2],@x[3]
+	eor	@x[4],@x[4],@x[5]
+	eor	@x[6],@x[6],@x[7]
+	eor	@x[8],@x[8],@x[9]
+	eor	@x[10],@x[10],@x[11]
+	eor	@x[12],@x[12],@x[13]
+	eor	@x[14],@x[14],@x[15]
+
+	stp	@x[0],@x[2],[$out,#0]		// store output
+	 add	@d[6],@d[6],#4			// increment counter
+	stp	@x[4],@x[6],[$out,#16]
+	stp	@x[8],@x[10],[$out,#32]
+	stp	@x[12],@x[14],[$out,#48]
+	add	$out,$out,#64
+	b.eq	.Ldone_neon
+	sub	$len,$len,#64
+	cmp	$len,#64
+	b.lo	.Less_than_128
+
+	ld1.8	{$T0-$T3},[$inp],#64
+	eor	$A0,$A0,$T0
+	eor	$B0,$B0,$T1
+	eor	$C0,$C0,$T2
+	eor	$D0,$D0,$T3
+	st1.8	{$A0-$D0},[$out],#64
+	b.eq	.Ldone_neon
+	sub	$len,$len,#64
+	cmp	$len,#64
+	b.lo	.Less_than_192
+
+	ld1.8	{$T0-$T3},[$inp],#64
+	eor	$A1,$A1,$T0
+	eor	$B1,$B1,$T1
+	eor	$C1,$C1,$T2
+	eor	$D1,$D1,$T3
+	st1.8	{$A1-$D1},[$out],#64
+	b.eq	.Ldone_neon
+	sub	$len,$len,#64
+
+	st1.8	{$A2-$D2},[sp]
+	b	.Last_neon
+
+.Less_than_128:
+	st1.8	{$A0-$D0},[sp]
+	b	.Last_neon
+.Less_than_192:
+	st1.8	{$A1-$D1},[sp]
+	b	.Last_neon
+
+.align	4
+.Last_neon:
+	sub	$out,$out,#1
+	add	$inp,$inp,$len
+	add	$out,$out,$len
+	add	$ctr,sp,$len
+	neg	$len,$len
+
+.Loop_tail_neon:
+	ldrb	w10,[$inp,$len]
+	ldrb	w11,[$ctr,$len]
+	add	$len,$len,#1
+	eor	w10,w10,w11
+	strb	w10,[$out,$len]
+	cbnz	$len,.Loop_tail_neon
+
+	stp	xzr,xzr,[sp,#0]
+	stp	xzr,xzr,[sp,#16]
+	stp	xzr,xzr,[sp,#32]
+	stp	xzr,xzr,[sp,#48]
+
+.Ldone_neon:
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+	ret
+.size	ChaCha20_neon,.-ChaCha20_neon
+___
+{
+my ($T0,$T1,$T2,$T3,$T4,$T5)=@K;
+my ($A0,$B0,$C0,$D0,$A1,$B1,$C1,$D1,$A2,$B2,$C2,$D2,
+    $A3,$B3,$C3,$D3,$A4,$B4,$C4,$D4,$A5,$B5,$C5,$D5) = map("v$_.4s",(0..23));
+
+$code.=<<___;
+#ifdef	__APPLE__
+.type	ChaCha20_512_neon,%function
+.align	5
+ChaCha20_512_neon:
+	stp	x29,x30,[sp,#-96]!
+	add	x29,sp,#0
+
+	adr	@x[0],.Lsigma
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+
+.L512_or_more_neon:
+	sub	sp,sp,#128+64
+
+	ldp	@d[0],@d[1],[@x[0]]		// load sigma
+	ld1	{@K[0]},[@x[0]],#16
+	ldp	@d[2],@d[3],[$key]		// load key
+	ldp	@d[4],@d[5],[$key,#16]
+	ld1	{@K[1],@K[2]},[$key]
+	ldp	@d[6],@d[7],[$ctr]		// load counter
+	ld1	{@K[3]},[$ctr]
+	ld1	{$ONE},[@x[0]]
+# ifdef	__AARCH64EB__
+	rev64	@K[0],@K[0]
+	ror	@d[2],@d[2],#32
+	ror	@d[3],@d[3],#32
+	ror	@d[4],@d[4],#32
+	ror	@d[5],@d[5],#32
+	ror	@d[6],@d[6],#32
+	ror	@d[7],@d[7],#32
+# endif
+	add	@K[3],@K[3],$ONE		// += 1
+	stp	@K[0],@K[1],[sp,#0]		// off-load key block, invariant part
+	add	@K[3],@K[3],$ONE		// not typo
+	str	@K[2],[sp,#32]
+	add	@K[4],@K[3],$ONE
+	add	@K[5],@K[4],$ONE
+	add	@K[6],@K[5],$ONE
+	shl	$ONE,$ONE,#2			// 1 -> 4
+
+	stp	d8,d9,[sp,#128+0]		// meet ABI requirements
+	stp	d10,d11,[sp,#128+16]
+	stp	d12,d13,[sp,#128+32]
+	stp	d14,d15,[sp,#128+48]
+
+	sub	$len,$len,#512			// not typo
+
+.Loop_outer_512_neon:
+	 mov	$A0,@K[0]
+	 mov	$A1,@K[0]
+	 mov	$A2,@K[0]
+	 mov	$A3,@K[0]
+	 mov	$A4,@K[0]
+	 mov	$A5,@K[0]
+	 mov	$B0,@K[1]
+	mov.32	@x[0],@d[0]			// unpack key block
+	 mov	$B1,@K[1]
+	lsr	@x[1],@d[0],#32
+	 mov	$B2,@K[1]
+	mov.32	@x[2],@d[1]
+	 mov	$B3,@K[1]
+	lsr	@x[3],@d[1],#32
+	 mov	$B4,@K[1]
+	mov.32	@x[4],@d[2]
+	 mov	$B5,@K[1]
+	lsr	@x[5],@d[2],#32
+	 mov	$D0,@K[3]
+	mov.32	@x[6],@d[3]
+	 mov	$D1,@K[4]
+	lsr	@x[7],@d[3],#32
+	 mov	$D2,@K[5]
+	mov.32	@x[8],@d[4]
+	 mov	$D3,@K[6]
+	lsr	@x[9],@d[4],#32
+	 mov	$C0,@K[2]
+	mov.32	@x[10],@d[5]
+	 mov	$C1,@K[2]
+	lsr	@x[11],@d[5],#32
+	 add	$D4,$D0,$ONE			// +4
+	mov.32	@x[12],@d[6]
+	 add	$D5,$D1,$ONE			// +4
+	lsr	@x[13],@d[6],#32
+	 mov	$C2,@K[2]
+	mov.32	@x[14],@d[7]
+	 mov	$C3,@K[2]
+	lsr	@x[15],@d[7],#32
+	 mov	$C4,@K[2]
+	 stp	@K[3],@K[4],[sp,#48]		// off-load key block, variable part
+	 mov	$C5,@K[2]
+	 str	@K[5],[sp,#80]
+
+	mov	$ctr,#5
+	subs	$len,$len,#512
+.Loop_upper_neon:
+	sub	$ctr,$ctr,#1
+___
+	my @thread0=&NEONROUND($A0,$B0,$C0,$D0,$T0,0);
+	my @thread1=&NEONROUND($A1,$B1,$C1,$D1,$T1,0);
+	my @thread2=&NEONROUND($A2,$B2,$C2,$D2,$T2,0);
+	my @thread3=&NEONROUND($A3,$B3,$C3,$D3,$T3,0);
+	my @thread4=&NEONROUND($A4,$B4,$C4,$D4,$T4,0);
+	my @thread5=&NEONROUND($A5,$B5,$C5,$D5,$T5,0);
+	my @thread67=(&ROUND(0,4,8,12),&ROUND(0,5,10,15));
+	my $diff = ($#thread0+1)*6 - $#thread67 - 1;
+	my $i = 0;
+
+	foreach (@thread0) {
+		eval;			eval(shift(@thread67));
+		eval(shift(@thread1));	eval(shift(@thread67));
+		eval(shift(@thread2));	eval(shift(@thread67));
+		eval(shift(@thread3));	eval(shift(@thread67));
+		eval(shift(@thread4));	eval(shift(@thread67));
+		eval(shift(@thread5));	eval(shift(@thread67));
+	}
+
+	@thread0=&NEONROUND($A0,$B0,$C0,$D0,$T0,1);
+	@thread1=&NEONROUND($A1,$B1,$C1,$D1,$T1,1);
+	@thread2=&NEONROUND($A2,$B2,$C2,$D2,$T2,1);
+	@thread3=&NEONROUND($A3,$B3,$C3,$D3,$T3,1);
+	@thread4=&NEONROUND($A4,$B4,$C4,$D4,$T4,1);
+	@thread5=&NEONROUND($A5,$B5,$C5,$D5,$T5,1);
+	@thread67=(&ROUND(0,4,8,12),&ROUND(0,5,10,15));
+
+	foreach (@thread0) {
+		eval;			eval(shift(@thread67));
+		eval(shift(@thread1));	eval(shift(@thread67));
+		eval(shift(@thread2));	eval(shift(@thread67));
+		eval(shift(@thread3));	eval(shift(@thread67));
+		eval(shift(@thread4));	eval(shift(@thread67));
+		eval(shift(@thread5));	eval(shift(@thread67));
+	}
+$code.=<<___;
+	cbnz	$ctr,.Loop_upper_neon
+
+	add.32	@x[0],@x[0],@d[0]		// accumulate key block
+	add	@x[1],@x[1],@d[0],lsr#32
+	add.32	@x[2],@x[2],@d[1]
+	add	@x[3],@x[3],@d[1],lsr#32
+	add.32	@x[4],@x[4],@d[2]
+	add	@x[5],@x[5],@d[2],lsr#32
+	add.32	@x[6],@x[6],@d[3]
+	add	@x[7],@x[7],@d[3],lsr#32
+	add.32	@x[8],@x[8],@d[4]
+	add	@x[9],@x[9],@d[4],lsr#32
+	add.32	@x[10],@x[10],@d[5]
+	add	@x[11],@x[11],@d[5],lsr#32
+	add.32	@x[12],@x[12],@d[6]
+	add	@x[13],@x[13],@d[6],lsr#32
+	add.32	@x[14],@x[14],@d[7]
+	add	@x[15],@x[15],@d[7],lsr#32
+
+	add	@x[0],@x[0],@x[1],lsl#32	// pack
+	add	@x[2],@x[2],@x[3],lsl#32
+	ldp	@x[1],@x[3],[$inp,#0]		// load input
+	add	@x[4],@x[4],@x[5],lsl#32
+	add	@x[6],@x[6],@x[7],lsl#32
+	ldp	@x[5],@x[7],[$inp,#16]
+	add	@x[8],@x[8],@x[9],lsl#32
+	add	@x[10],@x[10],@x[11],lsl#32
+	ldp	@x[9],@x[11],[$inp,#32]
+	add	@x[12],@x[12],@x[13],lsl#32
+	add	@x[14],@x[14],@x[15],lsl#32
+	ldp	@x[13],@x[15],[$inp,#48]
+	add	$inp,$inp,#64
+# ifdef	__AARCH64EB__
+	rev	@x[0],@x[0]
+	rev	@x[2],@x[2]
+	rev	@x[4],@x[4]
+	rev	@x[6],@x[6]
+	rev	@x[8],@x[8]
+	rev	@x[10],@x[10]
+	rev	@x[12],@x[12]
+	rev	@x[14],@x[14]
+# endif
+	eor	@x[0],@x[0],@x[1]
+	eor	@x[2],@x[2],@x[3]
+	eor	@x[4],@x[4],@x[5]
+	eor	@x[6],@x[6],@x[7]
+	eor	@x[8],@x[8],@x[9]
+	eor	@x[10],@x[10],@x[11]
+	eor	@x[12],@x[12],@x[13]
+	eor	@x[14],@x[14],@x[15]
+
+	 stp	@x[0],@x[2],[$out,#0]		// store output
+	 add	@d[6],@d[6],#1			// increment counter
+	mov.32	@x[0],@d[0]			// unpack key block
+	lsr	@x[1],@d[0],#32
+	 stp	@x[4],@x[6],[$out,#16]
+	mov.32	@x[2],@d[1]
+	lsr	@x[3],@d[1],#32
+	 stp	@x[8],@x[10],[$out,#32]
+	mov.32	@x[4],@d[2]
+	lsr	@x[5],@d[2],#32
+	 stp	@x[12],@x[14],[$out,#48]
+	 add	$out,$out,#64
+	mov.32	@x[6],@d[3]
+	lsr	@x[7],@d[3],#32
+	mov.32	@x[8],@d[4]
+	lsr	@x[9],@d[4],#32
+	mov.32	@x[10],@d[5]
+	lsr	@x[11],@d[5],#32
+	mov.32	@x[12],@d[6]
+	lsr	@x[13],@d[6],#32
+	mov.32	@x[14],@d[7]
+	lsr	@x[15],@d[7],#32
+
+	mov	$ctr,#5
+.Loop_lower_neon:
+	sub	$ctr,$ctr,#1
+___
+	@thread0=&NEONROUND($A0,$B0,$C0,$D0,$T0,0);
+	@thread1=&NEONROUND($A1,$B1,$C1,$D1,$T1,0);
+	@thread2=&NEONROUND($A2,$B2,$C2,$D2,$T2,0);
+	@thread3=&NEONROUND($A3,$B3,$C3,$D3,$T3,0);
+	@thread4=&NEONROUND($A4,$B4,$C4,$D4,$T4,0);
+	@thread5=&NEONROUND($A5,$B5,$C5,$D5,$T5,0);
+	@thread67=(&ROUND(0,4,8,12),&ROUND(0,5,10,15));
+
+	foreach (@thread0) {
+		eval;			eval(shift(@thread67));
+		eval(shift(@thread1));	eval(shift(@thread67));
+		eval(shift(@thread2));	eval(shift(@thread67));
+		eval(shift(@thread3));	eval(shift(@thread67));
+		eval(shift(@thread4));	eval(shift(@thread67));
+		eval(shift(@thread5));	eval(shift(@thread67));
+	}
+
+	@thread0=&NEONROUND($A0,$B0,$C0,$D0,$T0,1);
+	@thread1=&NEONROUND($A1,$B1,$C1,$D1,$T1,1);
+	@thread2=&NEONROUND($A2,$B2,$C2,$D2,$T2,1);
+	@thread3=&NEONROUND($A3,$B3,$C3,$D3,$T3,1);
+	@thread4=&NEONROUND($A4,$B4,$C4,$D4,$T4,1);
+	@thread5=&NEONROUND($A5,$B5,$C5,$D5,$T5,1);
+	@thread67=(&ROUND(0,4,8,12),&ROUND(0,5,10,15));
+
+	foreach (@thread0) {
+		eval;			eval(shift(@thread67));
+		eval(shift(@thread1));	eval(shift(@thread67));
+		eval(shift(@thread2));	eval(shift(@thread67));
+		eval(shift(@thread3));	eval(shift(@thread67));
+		eval(shift(@thread4));	eval(shift(@thread67));
+		eval(shift(@thread5));	eval(shift(@thread67));
+	}
+$code.=<<___;
+	cbnz	$ctr,.Loop_lower_neon
+
+	add.32	@x[0],@x[0],@d[0]		// accumulate key block
+	 ldp	@K[0],@K[1],[sp,#0]
+	add	@x[1],@x[1],@d[0],lsr#32
+	 ldp	@K[2],@K[3],[sp,#32]
+	add.32	@x[2],@x[2],@d[1]
+	 ldp	@K[4],@K[5],[sp,#64]
+	add	@x[3],@x[3],@d[1],lsr#32
+	 add	$A0,$A0,@K[0]
+	add.32	@x[4],@x[4],@d[2]
+	 add	$A1,$A1,@K[0]
+	add	@x[5],@x[5],@d[2],lsr#32
+	 add	$A2,$A2,@K[0]
+	add.32	@x[6],@x[6],@d[3]
+	 add	$A3,$A3,@K[0]
+	add	@x[7],@x[7],@d[3],lsr#32
+	 add	$A4,$A4,@K[0]
+	add.32	@x[8],@x[8],@d[4]
+	 add	$A5,$A5,@K[0]
+	add	@x[9],@x[9],@d[4],lsr#32
+	 add	$C0,$C0,@K[2]
+	add.32	@x[10],@x[10],@d[5]
+	 add	$C1,$C1,@K[2]
+	add	@x[11],@x[11],@d[5],lsr#32
+	 add	$C2,$C2,@K[2]
+	add.32	@x[12],@x[12],@d[6]
+	 add	$C3,$C3,@K[2]
+	add	@x[13],@x[13],@d[6],lsr#32
+	 add	$C4,$C4,@K[2]
+	add.32	@x[14],@x[14],@d[7]
+	 add	$C5,$C5,@K[2]
+	add	@x[15],@x[15],@d[7],lsr#32
+	 add	$D4,$D4,$ONE			// +4
+	add	@x[0],@x[0],@x[1],lsl#32	// pack
+	 add	$D5,$D5,$ONE			// +4
+	add	@x[2],@x[2],@x[3],lsl#32
+	 add	$D0,$D0,@K[3]
+	ldp	@x[1],@x[3],[$inp,#0]		// load input
+	 add	$D1,$D1,@K[4]
+	add	@x[4],@x[4],@x[5],lsl#32
+	 add	$D2,$D2,@K[5]
+	add	@x[6],@x[6],@x[7],lsl#32
+	 add	$D3,$D3,@K[6]
+	ldp	@x[5],@x[7],[$inp,#16]
+	 add	$D4,$D4,@K[3]
+	add	@x[8],@x[8],@x[9],lsl#32
+	 add	$D5,$D5,@K[4]
+	add	@x[10],@x[10],@x[11],lsl#32
+	 add	$B0,$B0,@K[1]
+	ldp	@x[9],@x[11],[$inp,#32]
+	 add	$B1,$B1,@K[1]
+	add	@x[12],@x[12],@x[13],lsl#32
+	 add	$B2,$B2,@K[1]
+	add	@x[14],@x[14],@x[15],lsl#32
+	 add	$B3,$B3,@K[1]
+	ldp	@x[13],@x[15],[$inp,#48]
+	 add	$B4,$B4,@K[1]
+	add	$inp,$inp,#64
+	 add	$B5,$B5,@K[1]
+
+# ifdef	__AARCH64EB__
+	rev	@x[0],@x[0]
+	rev	@x[2],@x[2]
+	rev	@x[4],@x[4]
+	rev	@x[6],@x[6]
+	rev	@x[8],@x[8]
+	rev	@x[10],@x[10]
+	rev	@x[12],@x[12]
+	rev	@x[14],@x[14]
+# endif
+	ld1.8	{$T0-$T3},[$inp],#64
+	eor	@x[0],@x[0],@x[1]
+	eor	@x[2],@x[2],@x[3]
+	eor	@x[4],@x[4],@x[5]
+	eor	@x[6],@x[6],@x[7]
+	eor	@x[8],@x[8],@x[9]
+	 eor	$A0,$A0,$T0
+	eor	@x[10],@x[10],@x[11]
+	 eor	$B0,$B0,$T1
+	eor	@x[12],@x[12],@x[13]
+	 eor	$C0,$C0,$T2
+	eor	@x[14],@x[14],@x[15]
+	 eor	$D0,$D0,$T3
+	 ld1.8	{$T0-$T3},[$inp],#64
+
+	stp	@x[0],@x[2],[$out,#0]		// store output
+	 add	@d[6],@d[6],#7			// increment counter
+	stp	@x[4],@x[6],[$out,#16]
+	stp	@x[8],@x[10],[$out,#32]
+	stp	@x[12],@x[14],[$out,#48]
+	add	$out,$out,#64
+	st1.8	{$A0-$D0},[$out],#64
+
+	ld1.8	{$A0-$D0},[$inp],#64
+	eor	$A1,$A1,$T0
+	eor	$B1,$B1,$T1
+	eor	$C1,$C1,$T2
+	eor	$D1,$D1,$T3
+	st1.8	{$A1-$D1},[$out],#64
+
+	ld1.8	{$A1-$D1},[$inp],#64
+	eor	$A2,$A2,$A0
+	 ldp	@K[0],@K[1],[sp,#0]
+	eor	$B2,$B2,$B0
+	 ldp	@K[2],@K[3],[sp,#32]
+	eor	$C2,$C2,$C0
+	eor	$D2,$D2,$D0
+	st1.8	{$A2-$D2},[$out],#64
+
+	ld1.8	{$A2-$D2},[$inp],#64
+	eor	$A3,$A3,$A1
+	eor	$B3,$B3,$B1
+	eor	$C3,$C3,$C1
+	eor	$D3,$D3,$D1
+	st1.8	{$A3-$D3},[$out],#64
+
+	ld1.8	{$A3-$D3},[$inp],#64
+	eor	$A4,$A4,$A2
+	eor	$B4,$B4,$B2
+	eor	$C4,$C4,$C2
+	eor	$D4,$D4,$D2
+	st1.8	{$A4-$D4},[$out],#64
+
+	shl	$A0,$ONE,#1			// 4 -> 8
+	eor	$A5,$A5,$A3
+	eor	$B5,$B5,$B3
+	eor	$C5,$C5,$C3
+	eor	$D5,$D5,$D3
+	st1.8	{$A5-$D5},[$out],#64
+
+	add	@K[3],@K[3],$A0			// += 8
+	add	@K[4],@K[4],$A0
+	add	@K[5],@K[5],$A0
+	add	@K[6],@K[6],$A0
+
+	b.hs	.Loop_outer_512_neon
+
+	adds	$len,$len,#512
+	ushr	$A0,$ONE,#2			// 4 -> 1
+
+	ldp	d8,d9,[sp,#128+0]		// meet ABI requirements
+	ldp	d10,d11,[sp,#128+16]
+	ldp	d12,d13,[sp,#128+32]
+	ldp	d14,d15,[sp,#128+48]
+
+	stp	@K[0],$ONE,[sp,#0]		// wipe off-load area
+	stp	@K[0],$ONE,[sp,#32]
+	stp	@K[0],$ONE,[sp,#64]
+
+	b.eq	.Ldone_512_neon
+
+	cmp	$len,#192
+	sub	@K[3],@K[3],$A0			// -= 1
+	sub	@K[4],@K[4],$A0
+	sub	@K[5],@K[5],$A0
+	add	sp,sp,#128
+	b.hs	.Loop_outer_neon
+
+	eor	@K[1],@K[1],@K[1]
+	eor	@K[2],@K[2],@K[2]
+	eor	@K[3],@K[3],@K[3]
+	eor	@K[4],@K[4],@K[4]
+	eor	@K[5],@K[5],@K[5]
+	eor	@K[6],@K[6],@K[6]
+	b	.Loop_outer
+
+.Ldone_512_neon:
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#128+64
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#96
+	ret
+.size	ChaCha20_512_neon,.-ChaCha20_512_neon
+#endif
+___
+}
+}}}
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/\/\// and !/^$/);
+	print;
+}
+close SELF;
+
+foreach (split("\n",$code)) {
+	s/\`([^\`]*)\`/eval $1/geo;
+
+	(s/\b([a-z]+)\.32\b/$1/ and (s/x([0-9]+)/w$1/g or 1))	or
+	(m/\b(eor|ext|mov)\b/ and (s/\.4s/\.16b/g or 1))	or
+	(s/\b((?:ld|st)1)\.8\b/$1/ and (s/\.4s/\.16b/g or 1))	or
+	(m/\b(ld|st)[rp]\b/ and (s/v([0-9]+)\.4s/q$1/g or 1))	or
+	(s/\brev32\.16\b/rev32/ and (s/\.4s/\.8h/g or 1));
+
+	#s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo;
+
+	print $_,"\n";
+}
+close STDOUT;	# flush
diff --git a/src/crypto/zinc/chacha20/chacha20-unrolled-arm.S b/src/crypto/zinc/chacha20/chacha20-unrolled-arm.S
new file mode 100644
index 0000000..2140319
--- /dev/null
+++ b/src/crypto/zinc/chacha20/chacha20-unrolled-arm.S
@@ -0,0 +1,461 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Google, Inc.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * Design notes:
+ *
+ * 16 registers would be needed to hold the state matrix, but only 14 are
+ * available because 'sp' and 'pc' cannot be used.  So we spill the elements
+ * (x8, x9) to the stack and swap them out with (x10, x11).  This adds one
+ * 'ldrd' and one 'strd' instruction per round.
+ *
+ * All rotates are performed using the implicit rotate operand accepted by the
+ * 'add' and 'eor' instructions.  This is faster than using explicit rotate
+ * instructions.  To make this work, we allow the values in the second and last
+ * rows of the ChaCha state matrix (rows 'b' and 'd') to temporarily have the
+ * wrong rotation amount.  The rotation amount is then fixed up just in time
+ * when the values are used.  'brot' is the number of bits the values in row 'b'
+ * need to be rotated right to arrive at the correct values, and 'drot'
+ * similarly for row 'd'.  (brot, drot) start out as (0, 0) but we make it such
+ * that they end up as (25, 24) after every round.
+ */
+
+	// ChaCha state registers
+	X0	.req	r0
+	X1	.req	r1
+	X2	.req	r2
+	X3	.req	r3
+	X4	.req	r4
+	X5	.req	r5
+	X6	.req	r6
+	X7	.req	r7
+	X8_X10	.req	r8	// shared by x8 and x10
+	X9_X11	.req	r9	// shared by x9 and x11
+	X12	.req	r10
+	X13	.req	r11
+	X14	.req	r12
+	X15	.req	r14
+
+.Lexpand_32byte_k:
+	// "expand 32-byte k"
+	.word	0x61707865, 0x3320646e, 0x79622d32, 0x6b206574
+
+#ifdef __thumb2__
+#  define adrl adr
+#endif
+
+.macro __rev		out, in,  t0, t1, t2
+.if __LINUX_ARM_ARCH__ >= 6
+	rev		\out, \in
+.else
+	lsl		\t0, \in, #24
+	and		\t1, \in, #0xff00
+	and		\t2, \in, #0xff0000
+	orr		\out, \t0, \in, lsr #24
+	orr		\out, \out, \t1, lsl #8
+	orr		\out, \out, \t2, lsr #8
+.endif
+.endm
+
+.macro _le32_bswap	x,  t0, t1, t2
+#ifdef __ARMEB__
+	__rev		\x, \x,  \t0, \t1, \t2
+#endif
+.endm
+
+.macro _le32_bswap_4x	a, b, c, d,  t0, t1, t2
+	_le32_bswap	\a,  \t0, \t1, \t2
+	_le32_bswap	\b,  \t0, \t1, \t2
+	_le32_bswap	\c,  \t0, \t1, \t2
+	_le32_bswap	\d,  \t0, \t1, \t2
+.endm
+
+.macro __ldrd		a, b, src, offset
+#if __LINUX_ARM_ARCH__ >= 6
+	ldrd		\a, \b, [\src, #\offset]
+#else
+	ldr		\a, [\src, #\offset]
+	ldr		\b, [\src, #\offset + 4]
+#endif
+.endm
+
+.macro __strd		a, b, dst, offset
+#if __LINUX_ARM_ARCH__ >= 6
+	strd		\a, \b, [\dst, #\offset]
+#else
+	str		\a, [\dst, #\offset]
+	str		\b, [\dst, #\offset + 4]
+#endif
+.endm
+
+.macro _halfround	a1, b1, c1, d1,  a2, b2, c2, d2
+
+	// a += b; d ^= a; d = rol(d, 16);
+	add		\a1, \a1, \b1, ror #brot
+	add		\a2, \a2, \b2, ror #brot
+	eor		\d1, \a1, \d1, ror #drot
+	eor		\d2, \a2, \d2, ror #drot
+	// drot == 32 - 16 == 16
+
+	// c += d; b ^= c; b = rol(b, 12);
+	add		\c1, \c1, \d1, ror #16
+	add		\c2, \c2, \d2, ror #16
+	eor		\b1, \c1, \b1, ror #brot
+	eor		\b2, \c2, \b2, ror #brot
+	// brot == 32 - 12 == 20
+
+	// a += b; d ^= a; d = rol(d, 8);
+	add		\a1, \a1, \b1, ror #20
+	add		\a2, \a2, \b2, ror #20
+	eor		\d1, \a1, \d1, ror #16
+	eor		\d2, \a2, \d2, ror #16
+	// drot == 32 - 8 == 24
+
+	// c += d; b ^= c; b = rol(b, 7);
+	add		\c1, \c1, \d1, ror #24
+	add		\c2, \c2, \d2, ror #24
+	eor		\b1, \c1, \b1, ror #20
+	eor		\b2, \c2, \b2, ror #20
+	// brot == 32 - 7 == 25
+.endm
+
+.macro _doubleround
+
+	// column round
+
+	// quarterrounds: (x0, x4, x8, x12) and (x1, x5, x9, x13)
+	_halfround	X0, X4, X8_X10, X12,  X1, X5, X9_X11, X13
+
+	// save (x8, x9); restore (x10, x11)
+	__strd		X8_X10, X9_X11, sp, 0
+	__ldrd		X8_X10, X9_X11, sp, 8
+
+	// quarterrounds: (x2, x6, x10, x14) and (x3, x7, x11, x15)
+	_halfround	X2, X6, X8_X10, X14,  X3, X7, X9_X11, X15
+
+	.set brot, 25
+	.set drot, 24
+
+	// diagonal round
+
+	// quarterrounds: (x0, x5, x10, x15) and (x1, x6, x11, x12)
+	_halfround	X0, X5, X8_X10, X15,  X1, X6, X9_X11, X12
+
+	// save (x10, x11); restore (x8, x9)
+	__strd		X8_X10, X9_X11, sp, 8
+	__ldrd		X8_X10, X9_X11, sp, 0
+
+	// quarterrounds: (x2, x7, x8, x13) and (x3, x4, x9, x14)
+	_halfround	X2, X7, X8_X10, X13,  X3, X4, X9_X11, X14
+.endm
+
+.macro _chacha_permute	nrounds
+	.set brot, 0
+	.set drot, 0
+	.rept \nrounds / 2
+	 _doubleround
+	.endr
+.endm
+
+.macro _chacha		nrounds
+
+.Lnext_block\@:
+	// Stack: unused0-unused1 x10-x11 x0-x15 OUT IN LEN
+	// Registers contain x0-x9,x12-x15.
+
+	// Do the core ChaCha permutation to update x0-x15.
+	_chacha_permute	\nrounds
+
+	add		sp, #8
+	// Stack: x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers contain x0-x9,x12-x15.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// Free up some registers (r8-r12,r14) by pushing (x8-x9,x12-x15).
+	push		{X8_X10, X9_X11, X12, X13, X14, X15}
+
+	// Load (OUT, IN, LEN).
+	ldr		r14, [sp, #96]
+	ldr		r12, [sp, #100]
+	ldr		r11, [sp, #104]
+
+	orr		r10, r14, r12
+
+	// Use slow path if fewer than 64 bytes remain.
+	cmp		r11, #64
+	blt		.Lxor_slowpath\@
+
+	// Use slow path if IN and/or OUT isn't 4-byte aligned.  Needed even on
+	// ARMv6+, since ldmia and stmia (used below) still require alignment.
+	tst		r10, #3
+	bne		.Lxor_slowpath\@
+
+	// Fast path: XOR 64 bytes of aligned data.
+
+	// Stack: x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is OUT.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// x0-x3
+	__ldrd		r8, r9, sp, 32
+	__ldrd		r10, r11, sp, 40
+	add		X0, X0, r8
+	add		X1, X1, r9
+	add		X2, X2, r10
+	add		X3, X3, r11
+	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	ldmia		r12!, {r8-r11}
+	eor		X0, X0, r8
+	eor		X1, X1, r9
+	eor		X2, X2, r10
+	eor		X3, X3, r11
+	stmia		r14!, {X0-X3}
+
+	// x4-x7
+	__ldrd		r8, r9, sp, 48
+	__ldrd		r10, r11, sp, 56
+	add		X4, r8, X4, ror #brot
+	add		X5, r9, X5, ror #brot
+	ldmia		r12!, {X0-X3}
+	add		X6, r10, X6, ror #brot
+	add		X7, r11, X7, ror #brot
+	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	eor		X4, X4, X0
+	eor		X5, X5, X1
+	eor		X6, X6, X2
+	eor		X7, X7, X3
+	stmia		r14!, {X4-X7}
+
+	// x8-x15
+	pop		{r0-r7}			// (x8-x9,x12-x15,x10-x11)
+	__ldrd		r8, r9, sp, 32
+	__ldrd		r10, r11, sp, 40
+	add		r0, r0, r8		// x8
+	add		r1, r1, r9		// x9
+	add		r6, r6, r10		// x10
+	add		r7, r7, r11		// x11
+	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	ldmia		r12!, {r8-r11}
+	eor		r0, r0, r8		// x8
+	eor		r1, r1, r9		// x9
+	eor		r6, r6, r10		// x10
+	eor		r7, r7, r11		// x11
+	stmia		r14!, {r0,r1,r6,r7}
+	ldmia		r12!, {r0,r1,r6,r7}
+	__ldrd		r8, r9, sp, 48
+	__ldrd		r10, r11, sp, 56
+	add		r2, r8, r2, ror #drot	// x12
+	add		r3, r9, r3, ror #drot	// x13
+	add		r4, r10, r4, ror #drot	// x14
+	add		r5, r11, r5, ror #drot	// x15
+	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	  ldr		r9, [sp, #72]		// load LEN
+	eor		r2, r2, r0		// x12
+	eor		r3, r3, r1		// x13
+	eor		r4, r4, r6		// x14
+	eor		r5, r5, r7		// x15
+	  subs		r9, #64			// decrement and check LEN
+	stmia		r14!, {r2-r5}
+
+	beq		.Ldone\@
+
+.Lprepare_for_next_block\@:
+
+	// Stack: x0-x15 OUT IN LEN
+
+	// Increment block counter (x12)
+	add		r8, #1
+
+	// Store updated (OUT, IN, LEN)
+	str		r14, [sp, #64]
+	str		r12, [sp, #68]
+	str		r9, [sp, #72]
+
+	  mov		r14, sp
+
+	// Store updated block counter (x12)
+	str		r8, [sp, #48]
+
+	  sub		sp, #16
+
+	// Reload state and do next block
+	ldmia		r14!, {r0-r11}		// load x0-x11
+	__strd		r10, r11, sp, 8		// store x10-x11 before state
+	ldmia		r14, {r10-r12,r14}	// load x12-x15
+	b		.Lnext_block\@
+
+.Lxor_slowpath\@:
+	// Slow path: < 64 bytes remaining, or unaligned input or output buffer.
+	// We handle it by storing the 64 bytes of keystream to the stack, then
+	// XOR-ing the needed portion with the data.
+
+	// Allocate keystream buffer
+	sub		sp, #64
+	mov		r14, sp
+
+	// Stack: ks0-ks15 x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
+	// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is &ks0.
+	// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
+
+	// Save keystream for x0-x3
+	__ldrd		r8, r9, sp, 96
+	__ldrd		r10, r11, sp, 104
+	add		X0, X0, r8
+	add		X1, X1, r9
+	add		X2, X2, r10
+	add		X3, X3, r11
+	_le32_bswap_4x	X0, X1, X2, X3,  r8, r9, r10
+	stmia		r14!, {X0-X3}
+
+	// Save keystream for x4-x7
+	__ldrd		r8, r9, sp, 112
+	__ldrd		r10, r11, sp, 120
+	add		X4, r8, X4, ror #brot
+	add		X5, r9, X5, ror #brot
+	add		X6, r10, X6, ror #brot
+	add		X7, r11, X7, ror #brot
+	_le32_bswap_4x	X4, X5, X6, X7,  r8, r9, r10
+	  add		r8, sp, #64
+	stmia		r14!, {X4-X7}
+
+	// Save keystream for x8-x15
+	ldm		r8, {r0-r7}		// (x8-x9,x12-x15,x10-x11)
+	__ldrd		r8, r9, sp, 128
+	__ldrd		r10, r11, sp, 136
+	add		r0, r0, r8		// x8
+	add		r1, r1, r9		// x9
+	add		r6, r6, r10		// x10
+	add		r7, r7, r11		// x11
+	_le32_bswap_4x	r0, r1, r6, r7,  r8, r9, r10
+	stmia		r14!, {r0,r1,r6,r7}
+	__ldrd		r8, r9, sp, 144
+	__ldrd		r10, r11, sp, 152
+	add		r2, r8, r2, ror #drot	// x12
+	add		r3, r9, r3, ror #drot	// x13
+	add		r4, r10, r4, ror #drot	// x14
+	add		r5, r11, r5, ror #drot	// x15
+	_le32_bswap_4x	r2, r3, r4, r5,  r9, r10, r11
+	stmia		r14, {r2-r5}
+
+	// Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
+	// Registers: r8 is block counter, r12 is IN.
+
+	ldr		r9, [sp, #168]		// LEN
+	ldr		r14, [sp, #160]		// OUT
+	cmp		r9, #64
+	  mov		r0, sp
+	movle		r1, r9
+	movgt		r1, #64
+	// r1 is number of bytes to XOR, in range [1, 64]
+
+.if __LINUX_ARM_ARCH__ < 6
+	orr		r2, r12, r14
+	tst		r2, #3			// IN or OUT misaligned?
+	bne		.Lxor_next_byte\@
+.endif
+
+	// XOR a word at a time
+.rept 16
+	subs		r1, #4
+	blt		.Lxor_words_done\@
+	ldr		r2, [r12], #4
+	ldr		r3, [r0], #4
+	eor		r2, r2, r3
+	str		r2, [r14], #4
+.endr
+	b		.Lxor_slowpath_done\@
+.Lxor_words_done\@:
+	ands		r1, r1, #3
+	beq		.Lxor_slowpath_done\@
+
+	// XOR a byte at a time
+.Lxor_next_byte\@:
+	ldrb		r2, [r12], #1
+	ldrb		r3, [r0], #1
+	eor		r2, r2, r3
+	strb		r2, [r14], #1
+	subs		r1, #1
+	bne		.Lxor_next_byte\@
+
+.Lxor_slowpath_done\@:
+	subs		r9, #64
+	add		sp, #96
+	bgt		.Lprepare_for_next_block\@
+
+.Ldone\@:
+.endm	// _chacha
+
+/*
+ * void chacha20_arm(u8 *out, const u8 *in, size_t len, const u32 key[8],
+ *		     const u32 iv[4]);
+ */
+ENTRY(chacha20_arm)
+	cmp		r2, #0			// len == 0?
+	reteq		lr
+
+	push		{r0-r2,r4-r11,lr}
+
+	// Push state x0-x15 onto stack.
+	// Also store an extra copy of x10-x11 just before the state.
+
+	ldr		r4, [sp, #48]		// iv
+	mov		r0, sp
+	sub		sp, #80
+
+	// iv: x12-x15
+	ldm		r4, {X12,X13,X14,X15}
+	stmdb		r0!, {X12,X13,X14,X15}
+
+	// key: x4-x11
+	__ldrd		X8_X10, X9_X11, r3, 24
+	__strd		X8_X10, X9_X11, sp, 8
+	stmdb		r0!, {X8_X10, X9_X11}
+	ldm		r3, {X4-X9_X11}
+	stmdb		r0!, {X4-X9_X11}
+
+	// constants: x0-x3
+	adrl		X3, .Lexpand_32byte_k
+	ldm		X3, {X0-X3}
+	__strd		X0, X1, sp, 16
+	__strd		X2, X3, sp, 24
+
+	_chacha		20
+
+	add		sp, #76
+	pop		{r4-r11, pc}
+ENDPROC(chacha20_arm)
+
+/*
+ * void hchacha20_arm(const u32 state[16], u32 out[8]);
+ */
+ENTRY(hchacha20_arm)
+	push		{r1,r4-r11,lr}
+
+	mov		r14, r0
+	ldmia		r14!, {r0-r11}		// load x0-x11
+	push		{r10-r11}		// store x10-x11 to stack
+	ldm		r14, {r10-r12,r14}	// load x12-x15
+	sub		sp, #8
+
+	_chacha_permute	20
+
+	// Skip over (unused0-unused1, x10-x11)
+	add		sp, #16
+
+	// Fix up rotations of x12-x15
+	ror		X12, X12, #drot
+	ror		X13, X13, #drot
+	  pop		{r4}			// load 'out'
+	ror		X14, X14, #drot
+	ror		X15, X15, #drot
+
+	// Store (x0-x3,x12-x15) to 'out'
+	stm		r4, {X0,X1,X2,X3,X12,X13,X14,X15}
+
+	pop		{r4-r11,pc}
+ENDPROC(hchacha20_arm)
diff --git a/src/crypto/zinc/poly1305/poly1305-arm.S b/src/crypto/zinc/poly1305/poly1305-arm.S
deleted file mode 100644
index 4a0e9d4..0000000
--- a/src/crypto/zinc/poly1305/poly1305-arm.S
+++ /dev/null
@@ -1,1117 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
-/*
- * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
- *
- * This is based in part on Andy Polyakov's implementation from CRYPTOGAMS.
- */
-
-#include <linux/linkage.h>
-
-.text
-#if defined(__thumb2__)
-.syntax	unified
-.thumb
-#else
-.code	32
-#endif
-
-.align	5
-ENTRY(poly1305_init_arm)
-	stmdb	sp!,{r4-r11}
-
-	eor	r3,r3,r3
-	cmp	r1,#0
-	str	r3,[r0,#0]		@ zero hash value
-	str	r3,[r0,#4]
-	str	r3,[r0,#8]
-	str	r3,[r0,#12]
-	str	r3,[r0,#16]
-	str	r3,[r0,#36]		@ is_base2_26
-	add	r0,r0,#20
-
-#ifdef	__thumb2__
-	it	eq
-#endif
-	moveq	r0,#0
-	beq	.Lno_key
-
-	ldrb	r4,[r1,#0]
-	mov	r10,#0x0fffffff
-	ldrb	r5,[r1,#1]
-	and	r3,r10,#-4		@ 0x0ffffffc
-	ldrb	r6,[r1,#2]
-	ldrb	r7,[r1,#3]
-	orr	r4,r4,r5,lsl#8
-	ldrb	r5,[r1,#4]
-	orr	r4,r4,r6,lsl#16
-	ldrb	r6,[r1,#5]
-	orr	r4,r4,r7,lsl#24
-	ldrb	r7,[r1,#6]
-	and	r4,r4,r10
-
-	ldrb	r8,[r1,#7]
-	orr	r5,r5,r6,lsl#8
-	ldrb	r6,[r1,#8]
-	orr	r5,r5,r7,lsl#16
-	ldrb	r7,[r1,#9]
-	orr	r5,r5,r8,lsl#24
-	ldrb	r8,[r1,#10]
-	and	r5,r5,r3
-
-	ldrb	r9,[r1,#11]
-	orr	r6,r6,r7,lsl#8
-	ldrb	r7,[r1,#12]
-	orr	r6,r6,r8,lsl#16
-	ldrb	r8,[r1,#13]
-	orr	r6,r6,r9,lsl#24
-	ldrb	r9,[r1,#14]
-	and	r6,r6,r3
-
-	ldrb	r10,[r1,#15]
-	orr	r7,r7,r8,lsl#8
-	str	r4,[r0,#0]
-	orr	r7,r7,r9,lsl#16
-	str	r5,[r0,#4]
-	orr	r7,r7,r10,lsl#24
-	str	r6,[r0,#8]
-	and	r7,r7,r3
-	str	r7,[r0,#12]
-.Lno_key:
-	ldmia	sp!,{r4-r11}
-#if __LINUX_ARM_ARCH__ >= 5
-	bx	lr				@ bx	lr
-#else
-	tst	lr,#1
-	moveq	pc,lr			@ be binary compatible with V4, yet
-	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
-#endif
-ENDPROC(poly1305_init_arm)
-
-.align	5
-ENTRY(poly1305_blocks_arm)
-.Lpoly1305_blocks_arm:
-	stmdb	sp!,{r3-r11,lr}
-
-	ands	r2,r2,#-16
-	beq	.Lno_data
-
-	cmp	r3,#0
-	add	r2,r2,r1		@ end pointer
-	sub	sp,sp,#32
-
-	ldmia	r0,{r4-r12}		@ load context
-
-	str	r0,[sp,#12]		@ offload stuff
-	mov	lr,r1
-	str	r2,[sp,#16]
-	str	r10,[sp,#20]
-	str	r11,[sp,#24]
-	str	r12,[sp,#28]
-	b	.Loop
-
-.Loop:
-#if __LINUX_ARM_ARCH__ < 7
-	ldrb	r0,[lr],#16		@ load input
-#ifdef	__thumb2__
-	it	hi
-#endif
-	addhi	r8,r8,#1		@ 1<<128
-	ldrb	r1,[lr,#-15]
-	ldrb	r2,[lr,#-14]
-	ldrb	r3,[lr,#-13]
-	orr	r1,r0,r1,lsl#8
-	ldrb	r0,[lr,#-12]
-	orr	r2,r1,r2,lsl#16
-	ldrb	r1,[lr,#-11]
-	orr	r3,r2,r3,lsl#24
-	ldrb	r2,[lr,#-10]
-	adds	r4,r4,r3		@ accumulate input
-
-	ldrb	r3,[lr,#-9]
-	orr	r1,r0,r1,lsl#8
-	ldrb	r0,[lr,#-8]
-	orr	r2,r1,r2,lsl#16
-	ldrb	r1,[lr,#-7]
-	orr	r3,r2,r3,lsl#24
-	ldrb	r2,[lr,#-6]
-	adcs	r5,r5,r3
-
-	ldrb	r3,[lr,#-5]
-	orr	r1,r0,r1,lsl#8
-	ldrb	r0,[lr,#-4]
-	orr	r2,r1,r2,lsl#16
-	ldrb	r1,[lr,#-3]
-	orr	r3,r2,r3,lsl#24
-	ldrb	r2,[lr,#-2]
-	adcs	r6,r6,r3
-
-	ldrb	r3,[lr,#-1]
-	orr	r1,r0,r1,lsl#8
-	str	lr,[sp,#8]		@ offload input pointer
-	orr	r2,r1,r2,lsl#16
-	add	r10,r10,r10,lsr#2
-	orr	r3,r2,r3,lsl#24
-#else
-	ldr	r0,[lr],#16		@ load input
-#ifdef	__thumb2__
-	it	hi
-#endif
-	addhi	r8,r8,#1		@ padbit
-	ldr	r1,[lr,#-12]
-	ldr	r2,[lr,#-8]
-	ldr	r3,[lr,#-4]
-#ifdef	__ARMEB__
-	rev	r0,r0
-	rev	r1,r1
-	rev	r2,r2
-	rev	r3,r3
-#endif
-	adds	r4,r4,r0		@ accumulate input
-	str	lr,[sp,#8]		@ offload input pointer
-	adcs	r5,r5,r1
-	add	r10,r10,r10,lsr#2
-	adcs	r6,r6,r2
-#endif
-	add	r11,r11,r11,lsr#2
-	adcs	r7,r7,r3
-	add	r12,r12,r12,lsr#2
-
-	umull	r2,r3,r5,r9
-	 adc	r8,r8,#0
-	umull	r0,r1,r4,r9
-	umlal	r2,r3,r8,r10
-	umlal	r0,r1,r7,r10
-	ldr	r10,[sp,#20]		@ reload r10
-	umlal	r2,r3,r6,r12
-	umlal	r0,r1,r5,r12
-	umlal	r2,r3,r7,r11
-	umlal	r0,r1,r6,r11
-	umlal	r2,r3,r4,r10
-	str	r0,[sp,#0]		@ future r4
-	 mul	r0,r11,r8
-	ldr	r11,[sp,#24]		@ reload r11
-	adds	r2,r2,r1		@ d1+=d0>>32
-	 eor	r1,r1,r1
-	adc	lr,r3,#0		@ future r6
-	str	r2,[sp,#4]		@ future r5
-
-	mul	r2,r12,r8
-	eor	r3,r3,r3
-	umlal	r0,r1,r7,r12
-	ldr	r12,[sp,#28]		@ reload r12
-	umlal	r2,r3,r7,r9
-	umlal	r0,r1,r6,r9
-	umlal	r2,r3,r6,r10
-	umlal	r0,r1,r5,r10
-	umlal	r2,r3,r5,r11
-	umlal	r0,r1,r4,r11
-	umlal	r2,r3,r4,r12
-	ldr	r4,[sp,#0]
-	mul	r8,r9,r8
-	ldr	r5,[sp,#4]
-
-	adds	r6,lr,r0		@ d2+=d1>>32
-	ldr	lr,[sp,#8]		@ reload input pointer
-	adc	r1,r1,#0
-	adds	r7,r2,r1		@ d3+=d2>>32
-	ldr	r0,[sp,#16]		@ reload end pointer
-	adc	r3,r3,#0
-	add	r8,r8,r3		@ h4+=d3>>32
-
-	and	r1,r8,#-4
-	and	r8,r8,#3
-	add	r1,r1,r1,lsr#2		@ *=5
-	adds	r4,r4,r1
-	adcs	r5,r5,#0
-	adcs	r6,r6,#0
-	adcs	r7,r7,#0
-	adc	r8,r8,#0
-
-	cmp	r0,lr			@ done yet?
-	bhi	.Loop
-
-	ldr	r0,[sp,#12]
-	add	sp,sp,#32
-	stmia	r0,{r4-r8}		@ store the result
-
-.Lno_data:
-#if __LINUX_ARM_ARCH__ >= 5
-	ldmia	sp!,{r3-r11,pc}
-#else
-	ldmia	sp!,{r3-r11,lr}
-	tst	lr,#1
-	moveq	pc,lr			@ be binary compatible with V4, yet
-	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
-#endif
-ENDPROC(poly1305_blocks_arm)
-
-.align	5
-ENTRY(poly1305_emit_arm)
-	stmdb	sp!,{r4-r11}
-.Lpoly1305_emit_enter:
-	ldmia	r0,{r3-r7}
-	adds	r8,r3,#5		@ compare to modulus
-	adcs	r9,r4,#0
-	adcs	r10,r5,#0
-	adcs	r11,r6,#0
-	adc	r7,r7,#0
-	tst	r7,#4			@ did it carry/borrow?
-
-#ifdef	__thumb2__
-	it	ne
-#endif
-	movne	r3,r8
-	ldr	r8,[r2,#0]
-#ifdef	__thumb2__
-	it	ne
-#endif
-	movne	r4,r9
-	ldr	r9,[r2,#4]
-#ifdef	__thumb2__
-	it	ne
-#endif
-	movne	r5,r10
-	ldr	r10,[r2,#8]
-#ifdef	__thumb2__
-	it	ne
-#endif
-	movne	r6,r11
-	ldr	r11,[r2,#12]
-
-	adds	r3,r3,r8
-	adcs	r4,r4,r9
-	adcs	r5,r5,r10
-	adc	r6,r6,r11
-
-#if __LINUX_ARM_ARCH__ >= 7
-#ifdef __ARMEB__
-	rev	r3,r3
-	rev	r4,r4
-	rev	r5,r5
-	rev	r6,r6
-#endif
-	str	r3,[r1,#0]
-	str	r4,[r1,#4]
-	str	r5,[r1,#8]
-	str	r6,[r1,#12]
-#else
-	strb	r3,[r1,#0]
-	mov	r3,r3,lsr#8
-	strb	r4,[r1,#4]
-	mov	r4,r4,lsr#8
-	strb	r5,[r1,#8]
-	mov	r5,r5,lsr#8
-	strb	r6,[r1,#12]
-	mov	r6,r6,lsr#8
-
-	strb	r3,[r1,#1]
-	mov	r3,r3,lsr#8
-	strb	r4,[r1,#5]
-	mov	r4,r4,lsr#8
-	strb	r5,[r1,#9]
-	mov	r5,r5,lsr#8
-	strb	r6,[r1,#13]
-	mov	r6,r6,lsr#8
-
-	strb	r3,[r1,#2]
-	mov	r3,r3,lsr#8
-	strb	r4,[r1,#6]
-	mov	r4,r4,lsr#8
-	strb	r5,[r1,#10]
-	mov	r5,r5,lsr#8
-	strb	r6,[r1,#14]
-	mov	r6,r6,lsr#8
-
-	strb	r3,[r1,#3]
-	strb	r4,[r1,#7]
-	strb	r5,[r1,#11]
-	strb	r6,[r1,#15]
-#endif
-	ldmia	sp!,{r4-r11}
-#if __LINUX_ARM_ARCH__ >= 5
-	bx	lr				@ bx	lr
-#else
-	tst	lr,#1
-	moveq	pc,lr			@ be binary compatible with V4, yet
-	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
-#endif
-ENDPROC(poly1305_emit_arm)
-
-
-#ifdef CONFIG_KERNEL_MODE_NEON
-.fpu	neon
-
-.align	5
-ENTRY(poly1305_init_neon)
-.Lpoly1305_init_neon:
-	ldr	r4,[r0,#20]		@ load key base 2^32
-	ldr	r5,[r0,#24]
-	ldr	r6,[r0,#28]
-	ldr	r7,[r0,#32]
-
-	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
-	mov	r3,r4,lsr#26
-	mov	r4,r5,lsr#20
-	orr	r3,r3,r5,lsl#6
-	mov	r5,r6,lsr#14
-	orr	r4,r4,r6,lsl#12
-	mov	r6,r7,lsr#8
-	orr	r5,r5,r7,lsl#18
-	and	r3,r3,#0x03ffffff
-	and	r4,r4,#0x03ffffff
-	and	r5,r5,#0x03ffffff
-
-	vdup.32	d0,r2			@ r^1 in both lanes
-	add	r2,r3,r3,lsl#2		@ *5
-	vdup.32	d1,r3
-	add	r3,r4,r4,lsl#2
-	vdup.32	d2,r2
-	vdup.32	d3,r4
-	add	r4,r5,r5,lsl#2
-	vdup.32	d4,r3
-	vdup.32	d5,r5
-	add	r5,r6,r6,lsl#2
-	vdup.32	d6,r4
-	vdup.32	d7,r6
-	vdup.32	d8,r5
-
-	mov	r5,#2		@ counter
-
-.Lsquare_neon:
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
-	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
-	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
-	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
-	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
-
-	vmull.u32	q5,d0,d0[1]
-	vmull.u32	q6,d1,d0[1]
-	vmull.u32	q7,d3,d0[1]
-	vmull.u32	q8,d5,d0[1]
-	vmull.u32	q9,d7,d0[1]
-
-	vmlal.u32	q5,d7,d2[1]
-	vmlal.u32	q6,d0,d1[1]
-	vmlal.u32	q7,d1,d1[1]
-	vmlal.u32	q8,d3,d1[1]
-	vmlal.u32	q9,d5,d1[1]
-
-	vmlal.u32	q5,d5,d4[1]
-	vmlal.u32	q6,d7,d4[1]
-	vmlal.u32	q8,d1,d3[1]
-	vmlal.u32	q7,d0,d3[1]
-	vmlal.u32	q9,d3,d3[1]
-
-	vmlal.u32	q5,d3,d6[1]
-	vmlal.u32	q8,d0,d5[1]
-	vmlal.u32	q6,d5,d6[1]
-	vmlal.u32	q7,d7,d6[1]
-	vmlal.u32	q9,d1,d5[1]
-
-	vmlal.u32	q8,d7,d8[1]
-	vmlal.u32	q5,d1,d8[1]
-	vmlal.u32	q6,d3,d8[1]
-	vmlal.u32	q7,d5,d8[1]
-	vmlal.u32	q9,d0,d7[1]
-
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
-	@ and P. Schwabe
-	@
-	@ H0>>+H1>>+H2>>+H3>>+H4
-	@ H3>>+H4>>*5+H0>>+H1
-	@
-	@ Trivia.
-	@
-	@ Result of multiplication of n-bit number by m-bit number is
-	@ n+m bits wide. However! Even though 2^n is a n+1-bit number,
-	@ m-bit number multiplied by 2^n is still n+m bits wide.
-	@
-	@ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
-	@ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
-	@ one is n+1 bits wide.
-	@
-	@ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
-	@ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
-	@ can be 27. However! In cases when their width exceeds 26 bits
-	@ they are limited by 2^26+2^6. This in turn means that *sum*
-	@ of the products with these values can still be viewed as sum
-	@ of 52-bit numbers as long as the amount of addends is not a
-	@ power of 2. For example,
-	@
-	@ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
-	@
-	@ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
-	@ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
-	@ 8 * (2^52) or 2^55. However, the value is then multiplied by
-	@ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
-	@ which is less than 32 * (2^52) or 2^57. And when processing
-	@ data we are looking at triple as many addends...
-	@
-	@ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
-	@ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
-	@ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
-	@ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
-	@ instruction accepts 2x32-bit input and writes 2x64-bit result.
-	@ This means that result of reduction have to be compressed upon
-	@ loop wrap-around. This can be done in the process of reduction
-	@ to minimize amount of instructions [as well as amount of
-	@ 128-bit instructions, which benefits low-end processors], but
-	@ one has to watch for H2 (which is narrower than H0) and 5*H4
-	@ not being wider than 58 bits, so that result of right shift
-	@ by 26 bits fits in 32 bits. This is also useful on x86,
-	@ because it allows to use paddd in place for paddq, which
-	@ benefits Atom, where paddq is ridiculously slow.
-
-	vshr.u64	q15,q8,#26
-	vmovn.i64	d16,q8
-	 vshr.u64	q4,q5,#26
-	 vmovn.i64	d10,q5
-	vadd.i64	q9,q9,q15		@ h3 -> h4
-	vbic.i32	d16,#0xfc000000	@ &=0x03ffffff
-	 vadd.i64	q6,q6,q4		@ h0 -> h1
-	 vbic.i32	d10,#0xfc000000
-
-	vshrn.u64	d30,q9,#26
-	vmovn.i64	d18,q9
-	 vshr.u64	q4,q6,#26
-	 vmovn.i64	d12,q6
-	 vadd.i64	q7,q7,q4		@ h1 -> h2
-	vbic.i32	d18,#0xfc000000
-	 vbic.i32	d12,#0xfc000000
-
-	vadd.i32	d10,d10,d30
-	vshl.u32	d30,d30,#2
-	 vshrn.u64	d8,q7,#26
-	 vmovn.i64	d14,q7
-	vadd.i32	d10,d10,d30	@ h4 -> h0
-	 vadd.i32	d16,d16,d8	@ h2 -> h3
-	 vbic.i32	d14,#0xfc000000
-
-	vshr.u32	d30,d10,#26
-	vbic.i32	d10,#0xfc000000
-	 vshr.u32	d8,d16,#26
-	 vbic.i32	d16,#0xfc000000
-	vadd.i32	d12,d12,d30	@ h0 -> h1
-	 vadd.i32	d18,d18,d8	@ h3 -> h4
-
-	subs		r5,r5,#1
-	beq		.Lsquare_break_neon
-
-	add		r6,r0,#(48+0*9*4)
-	add		r7,r0,#(48+1*9*4)
-
-	vtrn.32		d0,d10		@ r^2:r^1
-	vtrn.32		d3,d14
-	vtrn.32		d5,d16
-	vtrn.32		d1,d12
-	vtrn.32		d7,d18
-
-	vshl.u32	d4,d3,#2		@ *5
-	vshl.u32	d6,d5,#2
-	vshl.u32	d2,d1,#2
-	vshl.u32	d8,d7,#2
-	vadd.i32	d4,d4,d3
-	vadd.i32	d2,d2,d1
-	vadd.i32	d6,d6,d5
-	vadd.i32	d8,d8,d7
-
-	vst4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!
-	vst4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!
-	vst4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
-	vst4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
-	vst1.32		{d8[0]},[r6,:32]
-	vst1.32		{d8[1]},[r7,:32]
-
-	b		.Lsquare_neon
-
-.align	4
-.Lsquare_break_neon:
-	add		r6,r0,#(48+2*4*9)
-	add		r7,r0,#(48+3*4*9)
-
-	vmov		d0,d10		@ r^4:r^3
-	vshl.u32	d2,d12,#2		@ *5
-	vmov		d1,d12
-	vshl.u32	d4,d14,#2
-	vmov		d3,d14
-	vshl.u32	d6,d16,#2
-	vmov		d5,d16
-	vshl.u32	d8,d18,#2
-	vmov		d7,d18
-	vadd.i32	d2,d2,d12
-	vadd.i32	d4,d4,d14
-	vadd.i32	d6,d6,d16
-	vadd.i32	d8,d8,d18
-
-	vst4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!
-	vst4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!
-	vst4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
-	vst4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
-	vst1.32		{d8[0]},[r6]
-	vst1.32		{d8[1]},[r7]
-
-	bx	lr				@ bx	lr
-ENDPROC(poly1305_init_neon)
-
-.align	5
-ENTRY(poly1305_blocks_neon)
-	ldr	ip,[r0,#36]		@ is_base2_26
-	ands	r2,r2,#-16
-	beq	.Lno_data_neon
-
-	cmp	r2,#64
-	bhs	.Lenter_neon
-	tst	ip,ip			@ is_base2_26?
-	beq	.Lpoly1305_blocks_arm
-
-.Lenter_neon:
-	stmdb	sp!,{r4-r7}
-	vstmdb	sp!,{d8-d15}		@ ABI specification says so
-
-	tst	ip,ip			@ is_base2_26?
-	bne	.Lbase2_26_neon
-
-	stmdb	sp!,{r1-r3,lr}
-	bl	.Lpoly1305_init_neon
-
-	ldr	r4,[r0,#0]		@ load hash value base 2^32
-	ldr	r5,[r0,#4]
-	ldr	r6,[r0,#8]
-	ldr	r7,[r0,#12]
-	ldr	ip,[r0,#16]
-
-	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
-	mov	r3,r4,lsr#26
-	 veor	d10,d10,d10
-	mov	r4,r5,lsr#20
-	orr	r3,r3,r5,lsl#6
-	 veor	d12,d12,d12
-	mov	r5,r6,lsr#14
-	orr	r4,r4,r6,lsl#12
-	 veor	d14,d14,d14
-	mov	r6,r7,lsr#8
-	orr	r5,r5,r7,lsl#18
-	 veor	d16,d16,d16
-	and	r3,r3,#0x03ffffff
-	orr	r6,r6,ip,lsl#24
-	 veor	d18,d18,d18
-	and	r4,r4,#0x03ffffff
-	mov	r1,#1
-	and	r5,r5,#0x03ffffff
-	str	r1,[r0,#36]		@ is_base2_26
-
-	vmov.32	d10[0],r2
-	vmov.32	d12[0],r3
-	vmov.32	d14[0],r4
-	vmov.32	d16[0],r5
-	vmov.32	d18[0],r6
-	adr	r5,.Lzeros
-
-	ldmia	sp!,{r1-r3,lr}
-	b	.Lbase2_32_neon
-
-.align	4
-.Lbase2_26_neon:
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ load hash value
-
-	veor		d10,d10,d10
-	veor		d12,d12,d12
-	veor		d14,d14,d14
-	veor		d16,d16,d16
-	veor		d18,d18,d18
-	vld4.32		{d10[0],d12[0],d14[0],d16[0]},[r0]!
-	adr		r5,.Lzeros
-	vld1.32		{d18[0]},[r0]
-	sub		r0,r0,#16		@ rewind
-
-.Lbase2_32_neon:
-	add		r4,r1,#32
-	mov		r3,r3,lsl#24
-	tst		r2,#31
-	beq		.Leven
-
-	vld4.32		{d20[0],d22[0],d24[0],d26[0]},[r1]!
-	vmov.32		d28[0],r3
-	sub		r2,r2,#16
-	add		r4,r1,#32
-
-#ifdef	__ARMEB__
-	vrev32.8	q10,q10
-	vrev32.8	q13,q13
-	vrev32.8	q11,q11
-	vrev32.8	q12,q12
-#endif
-	vsri.u32	d28,d26,#8	@ base 2^32 -> base 2^26
-	vshl.u32	d26,d26,#18
-
-	vsri.u32	d26,d24,#14
-	vshl.u32	d24,d24,#12
-	vadd.i32	d29,d28,d18	@ add hash value and move to #hi
-
-	vbic.i32	d26,#0xfc000000
-	vsri.u32	d24,d22,#20
-	vshl.u32	d22,d22,#6
-
-	vbic.i32	d24,#0xfc000000
-	vsri.u32	d22,d20,#26
-	vadd.i32	d27,d26,d16
-
-	vbic.i32	d20,#0xfc000000
-	vbic.i32	d22,#0xfc000000
-	vadd.i32	d25,d24,d14
-
-	vadd.i32	d21,d20,d10
-	vadd.i32	d23,d22,d12
-
-	mov		r7,r5
-	add		r6,r0,#48
-
-	cmp		r2,r2
-	b		.Long_tail
-
-.align	4
-.Leven:
-	subs		r2,r2,#64
-	it		lo
-	movlo		r4,r5
-
-	vmov.i32	q14,#1<<24		@ padbit, yes, always
-	vld4.32		{d20,d22,d24,d26},[r1]	@ inp[0:1]
-	add		r1,r1,#64
-	vld4.32		{d21,d23,d25,d27},[r4]	@ inp[2:3] (or 0)
-	add		r4,r4,#64
-	itt		hi
-	addhi		r7,r0,#(48+1*9*4)
-	addhi		r6,r0,#(48+3*9*4)
-
-#ifdef	__ARMEB__
-	vrev32.8	q10,q10
-	vrev32.8	q13,q13
-	vrev32.8	q11,q11
-	vrev32.8	q12,q12
-#endif
-	vsri.u32	q14,q13,#8		@ base 2^32 -> base 2^26
-	vshl.u32	q13,q13,#18
-
-	vsri.u32	q13,q12,#14
-	vshl.u32	q12,q12,#12
-
-	vbic.i32	q13,#0xfc000000
-	vsri.u32	q12,q11,#20
-	vshl.u32	q11,q11,#6
-
-	vbic.i32	q12,#0xfc000000
-	vsri.u32	q11,q10,#26
-
-	vbic.i32	q10,#0xfc000000
-	vbic.i32	q11,#0xfc000000
-
-	bls		.Lskip_loop
-
-	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^2
-	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^4
-	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
-	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
-	b		.Loop_neon
-
-.align	5
-.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 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
-	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
-	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
-	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
-	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
-
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ inp[2:3]*r^2
-
-	vadd.i32	d24,d24,d14	@ accumulate inp[0:1]
-	vmull.u32	q7,d25,d0[1]
-	vadd.i32	d20,d20,d10
-	vmull.u32	q5,d21,d0[1]
-	vadd.i32	d26,d26,d16
-	vmull.u32	q8,d27,d0[1]
-	vmlal.u32	q7,d23,d1[1]
-	vadd.i32	d22,d22,d12
-	vmull.u32	q6,d23,d0[1]
-
-	vadd.i32	d28,d28,d18
-	vmull.u32	q9,d29,d0[1]
-	subs		r2,r2,#64
-	vmlal.u32	q5,d29,d2[1]
-	it		lo
-	movlo		r4,r5
-	vmlal.u32	q8,d25,d1[1]
-	vld1.32		d8[1],[r7,:32]
-	vmlal.u32	q6,d21,d1[1]
-	vmlal.u32	q9,d27,d1[1]
-
-	vmlal.u32	q5,d27,d4[1]
-	vmlal.u32	q8,d23,d3[1]
-	vmlal.u32	q9,d25,d3[1]
-	vmlal.u32	q6,d29,d4[1]
-	vmlal.u32	q7,d21,d3[1]
-
-	vmlal.u32	q8,d21,d5[1]
-	vmlal.u32	q5,d25,d6[1]
-	vmlal.u32	q9,d23,d5[1]
-	vmlal.u32	q6,d27,d6[1]
-	vmlal.u32	q7,d29,d6[1]
-
-	vmlal.u32	q8,d29,d8[1]
-	vmlal.u32	q5,d23,d8[1]
-	vmlal.u32	q9,d21,d7[1]
-	vmlal.u32	q6,d25,d8[1]
-	vmlal.u32	q7,d27,d8[1]
-
-	vld4.32		{d21,d23,d25,d27},[r4]	@ inp[2:3] (or 0)
-	add		r4,r4,#64
-
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ (hash+inp[0:1])*r^4 and accumulate
-
-	vmlal.u32	q8,d26,d0[0]
-	vmlal.u32	q5,d20,d0[0]
-	vmlal.u32	q9,d28,d0[0]
-	vmlal.u32	q6,d22,d0[0]
-	vmlal.u32	q7,d24,d0[0]
-	vld1.32		d8[0],[r6,:32]
-
-	vmlal.u32	q8,d24,d1[0]
-	vmlal.u32	q5,d28,d2[0]
-	vmlal.u32	q9,d26,d1[0]
-	vmlal.u32	q6,d20,d1[0]
-	vmlal.u32	q7,d22,d1[0]
-
-	vmlal.u32	q8,d22,d3[0]
-	vmlal.u32	q5,d26,d4[0]
-	vmlal.u32	q9,d24,d3[0]
-	vmlal.u32	q6,d28,d4[0]
-	vmlal.u32	q7,d20,d3[0]
-
-	vmlal.u32	q8,d20,d5[0]
-	vmlal.u32	q5,d24,d6[0]
-	vmlal.u32	q9,d22,d5[0]
-	vmlal.u32	q6,d26,d6[0]
-	vmlal.u32	q8,d28,d8[0]
-
-	vmlal.u32	q7,d28,d6[0]
-	vmlal.u32	q5,d22,d8[0]
-	vmlal.u32	q9,d20,d7[0]
-	vmov.i32	q14,#1<<24		@ padbit, yes, always
-	vmlal.u32	q6,d24,d8[0]
-	vmlal.u32	q7,d26,d8[0]
-
-	vld4.32		{d20,d22,d24,d26},[r1]	@ inp[0:1]
-	add		r1,r1,#64
-#ifdef	__ARMEB__
-	vrev32.8	q10,q10
-	vrev32.8	q11,q11
-	vrev32.8	q12,q12
-	vrev32.8	q13,q13
-#endif
-
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ lazy reduction interleaved with base 2^32 -> base 2^26 of
-	@ inp[0:3] previously loaded to q10-q13 and smashed to q10-q14.
-
-	vshr.u64	q15,q8,#26
-	vmovn.i64	d16,q8
-	 vshr.u64	q4,q5,#26
-	 vmovn.i64	d10,q5
-	vadd.i64	q9,q9,q15		@ h3 -> h4
-	vbic.i32	d16,#0xfc000000
-	  vsri.u32	q14,q13,#8		@ base 2^32 -> base 2^26
-	 vadd.i64	q6,q6,q4		@ h0 -> h1
-	  vshl.u32	q13,q13,#18
-	 vbic.i32	d10,#0xfc000000
-
-	vshrn.u64	d30,q9,#26
-	vmovn.i64	d18,q9
-	 vshr.u64	q4,q6,#26
-	 vmovn.i64	d12,q6
-	 vadd.i64	q7,q7,q4		@ h1 -> h2
-	  vsri.u32	q13,q12,#14
-	vbic.i32	d18,#0xfc000000
-	  vshl.u32	q12,q12,#12
-	 vbic.i32	d12,#0xfc000000
-
-	vadd.i32	d10,d10,d30
-	vshl.u32	d30,d30,#2
-	  vbic.i32	q13,#0xfc000000
-	 vshrn.u64	d8,q7,#26
-	 vmovn.i64	d14,q7
-	vaddl.u32	q5,d10,d30	@ h4 -> h0 [widen for a sec]
-	  vsri.u32	q12,q11,#20
-	 vadd.i32	d16,d16,d8	@ h2 -> h3
-	  vshl.u32	q11,q11,#6
-	 vbic.i32	d14,#0xfc000000
-	  vbic.i32	q12,#0xfc000000
-
-	vshrn.u64	d30,q5,#26		@ re-narrow
-	vmovn.i64	d10,q5
-	  vsri.u32	q11,q10,#26
-	  vbic.i32	q10,#0xfc000000
-	 vshr.u32	d8,d16,#26
-	 vbic.i32	d16,#0xfc000000
-	vbic.i32	d10,#0xfc000000
-	vadd.i32	d12,d12,d30	@ h0 -> h1
-	 vadd.i32	d18,d18,d8	@ h3 -> h4
-	  vbic.i32	q11,#0xfc000000
-
-	bhi		.Loop_neon
-
-.Lskip_loop:
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
-
-	add		r7,r0,#(48+0*9*4)
-	add		r6,r0,#(48+1*9*4)
-	adds		r2,r2,#32
-	it		ne
-	movne		r2,#0
-	bne		.Long_tail
-
-	vadd.i32	d25,d24,d14	@ add hash value and move to #hi
-	vadd.i32	d21,d20,d10
-	vadd.i32	d27,d26,d16
-	vadd.i32	d23,d22,d12
-	vadd.i32	d29,d28,d18
-
-.Long_tail:
-	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^1
-	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^2
-
-	vadd.i32	d24,d24,d14	@ can be redundant
-	vmull.u32	q7,d25,d0
-	vadd.i32	d20,d20,d10
-	vmull.u32	q5,d21,d0
-	vadd.i32	d26,d26,d16
-	vmull.u32	q8,d27,d0
-	vadd.i32	d22,d22,d12
-	vmull.u32	q6,d23,d0
-	vadd.i32	d28,d28,d18
-	vmull.u32	q9,d29,d0
-
-	vmlal.u32	q5,d29,d2
-	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
-	vmlal.u32	q8,d25,d1
-	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
-	vmlal.u32	q6,d21,d1
-	vmlal.u32	q9,d27,d1
-	vmlal.u32	q7,d23,d1
-
-	vmlal.u32	q8,d23,d3
-	vld1.32		d8[1],[r7,:32]
-	vmlal.u32	q5,d27,d4
-	vld1.32		d8[0],[r6,:32]
-	vmlal.u32	q9,d25,d3
-	vmlal.u32	q6,d29,d4
-	vmlal.u32	q7,d21,d3
-
-	vmlal.u32	q8,d21,d5
-	 it		ne
-	 addne		r7,r0,#(48+2*9*4)
-	vmlal.u32	q5,d25,d6
-	 it		ne
-	 addne		r6,r0,#(48+3*9*4)
-	vmlal.u32	q9,d23,d5
-	vmlal.u32	q6,d27,d6
-	vmlal.u32	q7,d29,d6
-
-	vmlal.u32	q8,d29,d8
-	 vorn		q0,q0,q0	@ all-ones, can be redundant
-	vmlal.u32	q5,d23,d8
-	 vshr.u64	q0,q0,#38
-	vmlal.u32	q9,d21,d7
-	vmlal.u32	q6,d25,d8
-	vmlal.u32	q7,d27,d8
-
-	beq		.Lshort_tail
-
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ (hash+inp[0:1])*r^4:r^3 and accumulate
-
-	vld4.32		{d0[1],d1[1],d2[1],d3[1]},[r7]!	@ load r^3
-	vld4.32		{d0[0],d1[0],d2[0],d3[0]},[r6]!	@ load r^4
-
-	vmlal.u32	q7,d24,d0
-	vmlal.u32	q5,d20,d0
-	vmlal.u32	q8,d26,d0
-	vmlal.u32	q6,d22,d0
-	vmlal.u32	q9,d28,d0
-
-	vmlal.u32	q5,d28,d2
-	vld4.32		{d4[1],d5[1],d6[1],d7[1]},[r7]!
-	vmlal.u32	q8,d24,d1
-	vld4.32		{d4[0],d5[0],d6[0],d7[0]},[r6]!
-	vmlal.u32	q6,d20,d1
-	vmlal.u32	q9,d26,d1
-	vmlal.u32	q7,d22,d1
-
-	vmlal.u32	q8,d22,d3
-	vld1.32		d8[1],[r7,:32]
-	vmlal.u32	q5,d26,d4
-	vld1.32		d8[0],[r6,:32]
-	vmlal.u32	q9,d24,d3
-	vmlal.u32	q6,d28,d4
-	vmlal.u32	q7,d20,d3
-
-	vmlal.u32	q8,d20,d5
-	vmlal.u32	q5,d24,d6
-	vmlal.u32	q9,d22,d5
-	vmlal.u32	q6,d26,d6
-	vmlal.u32	q7,d28,d6
-
-	vmlal.u32	q8,d28,d8
-	 vorn		q0,q0,q0	@ all-ones
-	vmlal.u32	q5,d22,d8
-	 vshr.u64	q0,q0,#38
-	vmlal.u32	q9,d20,d7
-	vmlal.u32	q6,d24,d8
-	vmlal.u32	q7,d26,d8
-
-.Lshort_tail:
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ horizontal addition
-
-	vadd.i64	d16,d16,d17
-	vadd.i64	d10,d10,d11
-	vadd.i64	d18,d18,d19
-	vadd.i64	d12,d12,d13
-	vadd.i64	d14,d14,d15
-
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ lazy reduction, but without narrowing
-
-	vshr.u64	q15,q8,#26
-	vand.i64	q8,q8,q0
-	 vshr.u64	q4,q5,#26
-	 vand.i64	q5,q5,q0
-	vadd.i64	q9,q9,q15		@ h3 -> h4
-	 vadd.i64	q6,q6,q4		@ h0 -> h1
-
-	vshr.u64	q15,q9,#26
-	vand.i64	q9,q9,q0
-	 vshr.u64	q4,q6,#26
-	 vand.i64	q6,q6,q0
-	 vadd.i64	q7,q7,q4		@ h1 -> h2
-
-	vadd.i64	q5,q5,q15
-	vshl.u64	q15,q15,#2
-	 vshr.u64	q4,q7,#26
-	 vand.i64	q7,q7,q0
-	vadd.i64	q5,q5,q15		@ h4 -> h0
-	 vadd.i64	q8,q8,q4		@ h2 -> h3
-
-	vshr.u64	q15,q5,#26
-	vand.i64	q5,q5,q0
-	 vshr.u64	q4,q8,#26
-	 vand.i64	q8,q8,q0
-	vadd.i64	q6,q6,q15		@ h0 -> h1
-	 vadd.i64	q9,q9,q4		@ h3 -> h4
-
-	cmp		r2,#0
-	bne		.Leven
-
-	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
-	@ store hash value
-
-	vst4.32		{d10[0],d12[0],d14[0],d16[0]},[r0]!
-	vst1.32		{d18[0]},[r0]
-
-	vldmia	sp!,{d8-d15}			@ epilogue
-	ldmia	sp!,{r4-r7}
-.Lno_data_neon:
-	bx	lr					@ bx	lr
-ENDPROC(poly1305_blocks_neon)
-
-.align	5
-ENTRY(poly1305_emit_neon)
-	ldr	ip,[r0,#36]		@ is_base2_26
-
-	stmdb	sp!,{r4-r11}
-
-	tst	ip,ip
-	beq	.Lpoly1305_emit_enter
-
-	ldmia	r0,{r3-r7}
-	eor	r8,r8,r8
-
-	adds	r3,r3,r4,lsl#26	@ base 2^26 -> base 2^32
-	mov	r4,r4,lsr#6
-	adcs	r4,r4,r5,lsl#20
-	mov	r5,r5,lsr#12
-	adcs	r5,r5,r6,lsl#14
-	mov	r6,r6,lsr#18
-	adcs	r6,r6,r7,lsl#8
-	adc	r7,r8,r7,lsr#24	@ can be partially reduced ...
-
-	and	r8,r7,#-4		@ ... so reduce
-	and	r7,r6,#3
-	add	r8,r8,r8,lsr#2	@ *= 5
-	adds	r3,r3,r8
-	adcs	r4,r4,#0
-	adcs	r5,r5,#0
-	adcs	r6,r6,#0
-	adc	r7,r7,#0
-
-	adds	r8,r3,#5		@ compare to modulus
-	adcs	r9,r4,#0
-	adcs	r10,r5,#0
-	adcs	r11,r6,#0
-	adc	r7,r7,#0
-	tst	r7,#4			@ did it carry/borrow?
-
-	it	ne
-	movne	r3,r8
-	ldr	r8,[r2,#0]
-	it	ne
-	movne	r4,r9
-	ldr	r9,[r2,#4]
-	it	ne
-	movne	r5,r10
-	ldr	r10,[r2,#8]
-	it	ne
-	movne	r6,r11
-	ldr	r11,[r2,#12]
-
-	adds	r3,r3,r8		@ accumulate nonce
-	adcs	r4,r4,r9
-	adcs	r5,r5,r10
-	adc	r6,r6,r11
-
-#ifdef __ARMEB__
-	rev	r3,r3
-	rev	r4,r4
-	rev	r5,r5
-	rev	r6,r6
-#endif
-	str	r3,[r1,#0]		@ store the result
-	str	r4,[r1,#4]
-	str	r5,[r1,#8]
-	str	r6,[r1,#12]
-
-	ldmia	sp!,{r4-r11}
-	bx	lr				@ bx	lr
-ENDPROC(poly1305_emit_neon)
-
-.align	5
-.Lzeros:
-.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-#endif
diff --git a/src/crypto/zinc/poly1305/poly1305-arm.pl b/src/crypto/zinc/poly1305/poly1305-arm.pl
new file mode 100644
index 0000000..88a4260
--- /dev/null
+++ b/src/crypto/zinc/poly1305/poly1305-arm.pl
@@ -0,0 +1,1272 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+#
+# This code is taken from the OpenSSL project but the author, Andy Polyakov,
+# has relicensed it under the licenses specified in the SPDX header above.
+# The original headers, including the original license headers, are
+# included below for completeness.
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+#			IALU(*)/gcc-4.4		NEON
+#
+# ARM11xx(ARMv6)	7.78/+100%		-
+# Cortex-A5		6.35/+130%		3.00
+# Cortex-A8		6.25/+115%		2.36
+# Cortex-A9		5.10/+95%		2.55
+# Cortex-A15		3.85/+85%		1.25(**)
+# Snapdragon S4		5.70/+100%		1.48(**)
+#
+# (*)	this is for -march=armv6, i.e. with bunch of ldrb loading data;
+# (**)	these are trade-off results, they can be improved by ~8% but at
+#	the cost of 15/12% regression on Cortex-A5/A7, it's even possible
+#	to improve Cortex-A9 result, but then A5/A7 loose more than 20%;
+
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
+
+($ctx,$inp,$len,$padbit)=map("r$_",(0..3));
+
+$code.=<<___;
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ __LINUX_ARM_ARCH__
+# define poly1305_init   poly1305_init_arm
+# define poly1305_blocks poly1305_blocks_arm
+# define poly1305_emit   poly1305_emit_arm
+.globl	poly1305_emit_neon
+.globl	poly1305_blocks_neon
+#endif
+
+.text
+#if defined(__thumb2__)
+.syntax	unified
+.thumb
+#else
+.code	32
+#endif
+
+.globl	poly1305_emit
+.globl	poly1305_blocks
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+.Lpoly1305_init:
+	stmdb	sp!,{r4-r11}
+
+	eor	r3,r3,r3
+	cmp	$inp,#0
+	str	r3,[$ctx,#0]		@ zero hash value
+	str	r3,[$ctx,#4]
+	str	r3,[$ctx,#8]
+	str	r3,[$ctx,#12]
+	str	r3,[$ctx,#16]
+	str	r3,[$ctx,#36]		@ is_base2_26
+	add	$ctx,$ctx,#20
+
+#ifdef	__thumb2__
+	it	eq
+#endif
+	moveq	r0,#0
+	beq	.Lno_key
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	adr	r11,.Lpoly1305_init
+	ldr	r12,.LOPENSSL_armcap
+#endif
+	ldrb	r4,[$inp,#0]
+	mov	r10,#0x0fffffff
+	ldrb	r5,[$inp,#1]
+	and	r3,r10,#-4		@ 0x0ffffffc
+	ldrb	r6,[$inp,#2]
+	ldrb	r7,[$inp,#3]
+	orr	r4,r4,r5,lsl#8
+	ldrb	r5,[$inp,#4]
+	orr	r4,r4,r6,lsl#16
+	ldrb	r6,[$inp,#5]
+	orr	r4,r4,r7,lsl#24
+	ldrb	r7,[$inp,#6]
+	and	r4,r4,r10
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,[r11,r12]		@ OPENSSL_armcap_P
+# ifdef	__APPLE__
+	ldr	r12,[r12]
+# endif
+#endif
+	ldrb	r8,[$inp,#7]
+	orr	r5,r5,r6,lsl#8
+	ldrb	r6,[$inp,#8]
+	orr	r5,r5,r7,lsl#16
+	ldrb	r7,[$inp,#9]
+	orr	r5,r5,r8,lsl#24
+	ldrb	r8,[$inp,#10]
+	and	r5,r5,r3
+
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	tst	r12,#ARMV7_NEON		@ check for NEON
+# ifdef	__APPLE__
+	adr	r9,poly1305_blocks_neon
+	adr	r11,poly1305_blocks
+#  ifdef __thumb2__
+	it	ne
+#  endif
+	movne	r11,r9
+	adr	r12,poly1305_emit
+	adr	r10,poly1305_emit_neon
+#  ifdef __thumb2__
+	it	ne
+#  endif
+	movne	r12,r10
+# else
+#  ifdef __thumb2__
+	itete	eq
+#  endif
+	addeq	r12,r11,#(poly1305_emit-.Lpoly1305_init)
+	addne	r12,r11,#(poly1305_emit_neon-.Lpoly1305_init)
+	addeq	r11,r11,#(poly1305_blocks-.Lpoly1305_init)
+	addne	r11,r11,#(poly1305_blocks_neon-.Lpoly1305_init)
+# endif
+# ifdef	__thumb2__
+	orr	r12,r12,#1	@ thumb-ify address
+	orr	r11,r11,#1
+# endif
+#endif
+	ldrb	r9,[$inp,#11]
+	orr	r6,r6,r7,lsl#8
+	ldrb	r7,[$inp,#12]
+	orr	r6,r6,r8,lsl#16
+	ldrb	r8,[$inp,#13]
+	orr	r6,r6,r9,lsl#24
+	ldrb	r9,[$inp,#14]
+	and	r6,r6,r3
+
+	ldrb	r10,[$inp,#15]
+	orr	r7,r7,r8,lsl#8
+	str	r4,[$ctx,#0]
+	orr	r7,r7,r9,lsl#16
+	str	r5,[$ctx,#4]
+	orr	r7,r7,r10,lsl#24
+	str	r6,[$ctx,#8]
+	and	r7,r7,r3
+	str	r7,[$ctx,#12]
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	stmia	r2,{r11,r12}		@ fill functions table
+	mov	r0,#1
+#else
+	mov	r0,#0
+#endif
+.Lno_key:
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	ret				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_init,.-poly1305_init
+___
+{
+my ($h0,$h1,$h2,$h3,$h4,$r0,$r1,$r2,$r3)=map("r$_",(4..12));
+my ($s1,$s2,$s3)=($r1,$r2,$r3);
+
+$code.=<<___;
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	stmdb	sp!,{r3-r11,lr}
+
+	ands	$len,$len,#-16
+	beq	.Lno_data
+
+	cmp	$padbit,#0
+	add	$len,$len,$inp		@ end pointer
+	sub	sp,sp,#32
+
+	ldmia	$ctx,{$h0-$r3}		@ load context
+
+	str	$ctx,[sp,#12]		@ offload stuff
+	mov	lr,$inp
+	str	$len,[sp,#16]
+	str	$r1,[sp,#20]
+	str	$r2,[sp,#24]
+	str	$r3,[sp,#28]
+	b	.Loop
+
+.Loop:
+#if __ARM_ARCH__<7
+	ldrb	r0,[lr],#16		@ load input
+# ifdef	__thumb2__
+	it	hi
+# endif
+	addhi	$h4,$h4,#1		@ 1<<128
+	ldrb	r1,[lr,#-15]
+	ldrb	r2,[lr,#-14]
+	ldrb	r3,[lr,#-13]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-12]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-11]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-10]
+	adds	$h0,$h0,r3		@ accumulate input
+
+	ldrb	r3,[lr,#-9]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-8]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-7]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-6]
+	adcs	$h1,$h1,r3
+
+	ldrb	r3,[lr,#-5]
+	orr	r1,r0,r1,lsl#8
+	ldrb	r0,[lr,#-4]
+	orr	r2,r1,r2,lsl#16
+	ldrb	r1,[lr,#-3]
+	orr	r3,r2,r3,lsl#24
+	ldrb	r2,[lr,#-2]
+	adcs	$h2,$h2,r3
+
+	ldrb	r3,[lr,#-1]
+	orr	r1,r0,r1,lsl#8
+	str	lr,[sp,#8]		@ offload input pointer
+	orr	r2,r1,r2,lsl#16
+	add	$s1,$r1,$r1,lsr#2
+	orr	r3,r2,r3,lsl#24
+#else
+	ldr	r0,[lr],#16		@ load input
+# ifdef	__thumb2__
+	it	hi
+# endif
+	addhi	$h4,$h4,#1		@ padbit
+	ldr	r1,[lr,#-12]
+	ldr	r2,[lr,#-8]
+	ldr	r3,[lr,#-4]
+# ifdef	__ARMEB__
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+# endif
+	adds	$h0,$h0,r0		@ accumulate input
+	str	lr,[sp,#8]		@ offload input pointer
+	adcs	$h1,$h1,r1
+	add	$s1,$r1,$r1,lsr#2
+	adcs	$h2,$h2,r2
+#endif
+	add	$s2,$r2,$r2,lsr#2
+	adcs	$h3,$h3,r3
+	add	$s3,$r3,$r3,lsr#2
+
+	umull	r2,r3,$h1,$r0
+	 adc	$h4,$h4,#0
+	umull	r0,r1,$h0,$r0
+	umlal	r2,r3,$h4,$s1
+	umlal	r0,r1,$h3,$s1
+	ldr	$r1,[sp,#20]		@ reload $r1
+	umlal	r2,r3,$h2,$s3
+	umlal	r0,r1,$h1,$s3
+	umlal	r2,r3,$h3,$s2
+	umlal	r0,r1,$h2,$s2
+	umlal	r2,r3,$h0,$r1
+	str	r0,[sp,#0]		@ future $h0
+	 mul	r0,$s2,$h4
+	ldr	$r2,[sp,#24]		@ reload $r2
+	adds	r2,r2,r1		@ d1+=d0>>32
+	 eor	r1,r1,r1
+	adc	lr,r3,#0		@ future $h2
+	str	r2,[sp,#4]		@ future $h1
+
+	mul	r2,$s3,$h4
+	eor	r3,r3,r3
+	umlal	r0,r1,$h3,$s3
+	ldr	$r3,[sp,#28]		@ reload $r3
+	umlal	r2,r3,$h3,$r0
+	umlal	r0,r1,$h2,$r0
+	umlal	r2,r3,$h2,$r1
+	umlal	r0,r1,$h1,$r1
+	umlal	r2,r3,$h1,$r2
+	umlal	r0,r1,$h0,$r2
+	umlal	r2,r3,$h0,$r3
+	ldr	$h0,[sp,#0]
+	mul	$h4,$r0,$h4
+	ldr	$h1,[sp,#4]
+
+	adds	$h2,lr,r0		@ d2+=d1>>32
+	ldr	lr,[sp,#8]		@ reload input pointer
+	adc	r1,r1,#0
+	adds	$h3,r2,r1		@ d3+=d2>>32
+	ldr	r0,[sp,#16]		@ reload end pointer
+	adc	r3,r3,#0
+	add	$h4,$h4,r3		@ h4+=d3>>32
+
+	and	r1,$h4,#-4
+	and	$h4,$h4,#3
+	add	r1,r1,r1,lsr#2		@ *=5
+	adds	$h0,$h0,r1
+	adcs	$h1,$h1,#0
+	adcs	$h2,$h2,#0
+	adcs	$h3,$h3,#0
+	adc	$h4,$h4,#0
+
+	cmp	r0,lr			@ done yet?
+	bhi	.Loop
+
+	ldr	$ctx,[sp,#12]
+	add	sp,sp,#32
+	stmia	$ctx,{$h0-$h4}		@ store the result
+
+.Lno_data:
+#if	__ARM_ARCH__>=5
+	ldmia	sp!,{r3-r11,pc}
+#else
+	ldmia	sp!,{r3-r11,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_blocks,.-poly1305_blocks
+___
+}
+{
+my ($ctx,$mac,$nonce)=map("r$_",(0..2));
+my ($h0,$h1,$h2,$h3,$h4,$g0,$g1,$g2,$g3)=map("r$_",(3..11));
+my $g4=$h4;
+
+$code.=<<___;
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+	stmdb	sp!,{r4-r11}
+.Lpoly1305_emit_enter:
+
+	ldmia	$ctx,{$h0-$h4}
+	adds	$g0,$h0,#5		@ compare to modulus
+	adcs	$g1,$h1,#0
+	adcs	$g2,$h2,#0
+	adcs	$g3,$h3,#0
+	adc	$g4,$h4,#0
+	tst	$g4,#4			@ did it carry/borrow?
+
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h0,$g0
+	ldr	$g0,[$nonce,#0]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h1,$g1
+	ldr	$g1,[$nonce,#4]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h2,$g2
+	ldr	$g2,[$nonce,#8]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	movne	$h3,$g3
+	ldr	$g3,[$nonce,#12]
+
+	adds	$h0,$h0,$g0
+	adcs	$h1,$h1,$g1
+	adcs	$h2,$h2,$g2
+	adc	$h3,$h3,$g3
+
+#if __ARM_ARCH__>=7
+# ifdef __ARMEB__
+	rev	$h0,$h0
+	rev	$h1,$h1
+	rev	$h2,$h2
+	rev	$h3,$h3
+# endif
+	str	$h0,[$mac,#0]
+	str	$h1,[$mac,#4]
+	str	$h2,[$mac,#8]
+	str	$h3,[$mac,#12]
+#else
+	strb	$h0,[$mac,#0]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#4]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#8]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#12]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#1]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#5]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#9]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#13]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#2]
+	mov	$h0,$h0,lsr#8
+	strb	$h1,[$mac,#6]
+	mov	$h1,$h1,lsr#8
+	strb	$h2,[$mac,#10]
+	mov	$h2,$h2,lsr#8
+	strb	$h3,[$mac,#14]
+	mov	$h3,$h3,lsr#8
+
+	strb	$h0,[$mac,#3]
+	strb	$h1,[$mac,#7]
+	strb	$h2,[$mac,#11]
+	strb	$h3,[$mac,#15]
+#endif
+	ldmia	sp!,{r4-r11}
+#if	__ARM_ARCH__>=5
+	ret				@ bx	lr
+#else
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	poly1305_emit,.-poly1305_emit
+___
+{
+my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("d$_",(0..9));
+my ($D0,$D1,$D2,$D3,$D4, $H0,$H1,$H2,$H3,$H4) = map("q$_",(5..14));
+my ($T0,$T1,$MASK) = map("q$_",(15,4,0));
+
+my ($in2,$zeros,$tbl0,$tbl1) = map("r$_",(4..7));
+
+$code.=<<___;
+#if	__ARM_MAX_ARCH__>=7
+.fpu	neon
+
+.type	poly1305_init_neon,%function
+.align	5
+poly1305_init_neon:
+.Lpoly1305_init_neon:
+	ldr	r4,[$ctx,#20]		@ load key base 2^32
+	ldr	r5,[$ctx,#24]
+	ldr	r6,[$ctx,#28]
+	ldr	r7,[$ctx,#32]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	and	r3,r3,#0x03ffffff
+	and	r4,r4,#0x03ffffff
+	and	r5,r5,#0x03ffffff
+
+	vdup.32	$R0,r2			@ r^1 in both lanes
+	add	r2,r3,r3,lsl#2		@ *5
+	vdup.32	$R1,r3
+	add	r3,r4,r4,lsl#2
+	vdup.32	$S1,r2
+	vdup.32	$R2,r4
+	add	r4,r5,r5,lsl#2
+	vdup.32	$S2,r3
+	vdup.32	$R3,r5
+	add	r5,r6,r6,lsl#2
+	vdup.32	$S3,r4
+	vdup.32	$R4,r6
+	vdup.32	$S4,r5
+
+	mov	$zeros,#2		@ counter
+
+.Lsquare_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d4 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+
+	vmull.u32	$D0,$R0,${R0}[1]
+	vmull.u32	$D1,$R1,${R0}[1]
+	vmull.u32	$D2,$R2,${R0}[1]
+	vmull.u32	$D3,$R3,${R0}[1]
+	vmull.u32	$D4,$R4,${R0}[1]
+
+	vmlal.u32	$D0,$R4,${S1}[1]
+	vmlal.u32	$D1,$R0,${R1}[1]
+	vmlal.u32	$D2,$R1,${R1}[1]
+	vmlal.u32	$D3,$R2,${R1}[1]
+	vmlal.u32	$D4,$R3,${R1}[1]
+
+	vmlal.u32	$D0,$R3,${S2}[1]
+	vmlal.u32	$D1,$R4,${S2}[1]
+	vmlal.u32	$D3,$R1,${R2}[1]
+	vmlal.u32	$D2,$R0,${R2}[1]
+	vmlal.u32	$D4,$R2,${R2}[1]
+
+	vmlal.u32	$D0,$R2,${S3}[1]
+	vmlal.u32	$D3,$R0,${R3}[1]
+	vmlal.u32	$D1,$R3,${S3}[1]
+	vmlal.u32	$D2,$R4,${S3}[1]
+	vmlal.u32	$D4,$R1,${R3}[1]
+
+	vmlal.u32	$D3,$R4,${S4}[1]
+	vmlal.u32	$D0,$R1,${S4}[1]
+	vmlal.u32	$D1,$R2,${S4}[1]
+	vmlal.u32	$D2,$R3,${S4}[1]
+	vmlal.u32	$D4,$R0,${R4}[1]
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	@ and P. Schwabe
+	@
+	@ H0>>+H1>>+H2>>+H3>>+H4
+	@ H3>>+H4>>*5+H0>>+H1
+	@
+	@ Trivia.
+	@
+	@ Result of multiplication of n-bit number by m-bit number is
+	@ n+m bits wide. However! Even though 2^n is a n+1-bit number,
+	@ m-bit number multiplied by 2^n is still n+m bits wide.
+	@
+	@ Sum of two n-bit numbers is n+1 bits wide, sum of three - n+2,
+	@ and so is sum of four. Sum of 2^m n-m-bit numbers and n-bit
+	@ one is n+1 bits wide.
+	@
+	@ >>+ denotes Hnext += Hn>>26, Hn &= 0x3ffffff. This means that
+	@ H0, H2, H3 are guaranteed to be 26 bits wide, while H1 and H4
+	@ can be 27. However! In cases when their width exceeds 26 bits
+	@ they are limited by 2^26+2^6. This in turn means that *sum*
+	@ of the products with these values can still be viewed as sum
+	@ of 52-bit numbers as long as the amount of addends is not a
+	@ power of 2. For example,
+	@
+	@ H4 = H4*R0 + H3*R1 + H2*R2 + H1*R3 + H0 * R4,
+	@
+	@ which can't be larger than 5 * (2^26 + 2^6) * (2^26 + 2^6), or
+	@ 5 * (2^52 + 2*2^32 + 2^12), which in turn is smaller than
+	@ 8 * (2^52) or 2^55. However, the value is then multiplied by
+	@ by 5, so we should be looking at 5 * 5 * (2^52 + 2^33 + 2^12),
+	@ which is less than 32 * (2^52) or 2^57. And when processing
+	@ data we are looking at triple as many addends...
+	@
+	@ In key setup procedure pre-reduced H0 is limited by 5*4+1 and
+	@ 5*H4 - by 5*5 52-bit addends, or 57 bits. But when hashing the
+	@ input H0 is limited by (5*4+1)*3 addends, or 58 bits, while
+	@ 5*H4 by 5*5*3, or 59[!] bits. How is this relevant? vmlal.u32
+	@ instruction accepts 2x32-bit input and writes 2x64-bit result.
+	@ This means that result of reduction have to be compressed upon
+	@ loop wrap-around. This can be done in the process of reduction
+	@ to minimize amount of instructions [as well as amount of
+	@ 128-bit instructions, which benefits low-end processors], but
+	@ one has to watch for H2 (which is narrower than H0) and 5*H4
+	@ not being wider than 58 bits, so that result of right shift
+	@ by 26 bits fits in 32 bits. This is also useful on x86,
+	@ because it allows to use paddd in place for paddq, which
+	@ benefits Atom, where paddq is ridiculously slow.
+
+	vshr.u64	$T0,$D3,#26
+	vmovn.i64	$D3#lo,$D3
+	 vshr.u64	$T1,$D0,#26
+	 vmovn.i64	$D0#lo,$D0
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	vbic.i32	$D3#lo,#0xfc000000	@ &=0x03ffffff
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+	 vbic.i32	$D0#lo,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D4,#26
+	vmovn.i64	$D4#lo,$D4
+	 vshr.u64	$T1,$D1,#26
+	 vmovn.i64	$D1#lo,$D1
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+	vbic.i32	$D4#lo,#0xfc000000
+	 vbic.i32	$D1#lo,#0xfc000000
+
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo
+	vshl.u32	$T0#lo,$T0#lo,#2
+	 vshrn.u64	$T1#lo,$D2,#26
+	 vmovn.i64	$D2#lo,$D2
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo	@ h4 -> h0
+	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
+	 vbic.i32	$D2#lo,#0xfc000000
+
+	vshr.u32	$T0#lo,$D0#lo,#26
+	vbic.i32	$D0#lo,#0xfc000000
+	 vshr.u32	$T1#lo,$D3#lo,#26
+	 vbic.i32	$D3#lo,#0xfc000000
+	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
+	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4
+
+	subs		$zeros,$zeros,#1
+	beq		.Lsquare_break_neon
+
+	add		$tbl0,$ctx,#(48+0*9*4)
+	add		$tbl1,$ctx,#(48+1*9*4)
+
+	vtrn.32		$R0,$D0#lo		@ r^2:r^1
+	vtrn.32		$R2,$D2#lo
+	vtrn.32		$R3,$D3#lo
+	vtrn.32		$R1,$D1#lo
+	vtrn.32		$R4,$D4#lo
+
+	vshl.u32	$S2,$R2,#2		@ *5
+	vshl.u32	$S3,$R3,#2
+	vshl.u32	$S1,$R1,#2
+	vshl.u32	$S4,$R4,#2
+	vadd.i32	$S2,$S2,$R2
+	vadd.i32	$S1,$S1,$R1
+	vadd.i32	$S3,$S3,$R3
+	vadd.i32	$S4,$S4,$R4
+
+	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vst1.32		{${S4}[0]},[$tbl0,:32]
+	vst1.32		{${S4}[1]},[$tbl1,:32]
+
+	b		.Lsquare_neon
+
+.align	4
+.Lsquare_break_neon:
+	add		$tbl0,$ctx,#(48+2*4*9)
+	add		$tbl1,$ctx,#(48+3*4*9)
+
+	vmov		$R0,$D0#lo		@ r^4:r^3
+	vshl.u32	$S1,$D1#lo,#2		@ *5
+	vmov		$R1,$D1#lo
+	vshl.u32	$S2,$D2#lo,#2
+	vmov		$R2,$D2#lo
+	vshl.u32	$S3,$D3#lo,#2
+	vmov		$R3,$D3#lo
+	vshl.u32	$S4,$D4#lo,#2
+	vmov		$R4,$D4#lo
+	vadd.i32	$S1,$S1,$D1#lo
+	vadd.i32	$S2,$S2,$D2#lo
+	vadd.i32	$S3,$S3,$D3#lo
+	vadd.i32	$S4,$S4,$D4#lo
+
+	vst4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!
+	vst4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!
+	vst4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vst4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vst1.32		{${S4}[0]},[$tbl0]
+	vst1.32		{${S4}[1]},[$tbl1]
+
+	ret				@ bx	lr
+.size	poly1305_init_neon,.-poly1305_init_neon
+
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+	ldr	ip,[$ctx,#36]		@ is_base2_26
+	ands	$len,$len,#-16
+	beq	.Lno_data_neon
+
+	cmp	$len,#64
+	bhs	.Lenter_neon
+	tst	ip,ip			@ is_base2_26?
+	beq	.Lpoly1305_blocks
+
+.Lenter_neon:
+	stmdb	sp!,{r4-r7}
+	vstmdb	sp!,{d8-d15}		@ ABI specification says so
+
+	tst	ip,ip			@ is_base2_26?
+	bne	.Lbase2_26_neon
+
+	stmdb	sp!,{r1-r3,lr}
+	bl	.Lpoly1305_init_neon
+
+	ldr	r4,[$ctx,#0]		@ load hash value base 2^32
+	ldr	r5,[$ctx,#4]
+	ldr	r6,[$ctx,#8]
+	ldr	r7,[$ctx,#12]
+	ldr	ip,[$ctx,#16]
+
+	and	r2,r4,#0x03ffffff	@ base 2^32 -> base 2^26
+	mov	r3,r4,lsr#26
+	 veor	$D0#lo,$D0#lo,$D0#lo
+	mov	r4,r5,lsr#20
+	orr	r3,r3,r5,lsl#6
+	 veor	$D1#lo,$D1#lo,$D1#lo
+	mov	r5,r6,lsr#14
+	orr	r4,r4,r6,lsl#12
+	 veor	$D2#lo,$D2#lo,$D2#lo
+	mov	r6,r7,lsr#8
+	orr	r5,r5,r7,lsl#18
+	 veor	$D3#lo,$D3#lo,$D3#lo
+	and	r3,r3,#0x03ffffff
+	orr	r6,r6,ip,lsl#24
+	 veor	$D4#lo,$D4#lo,$D4#lo
+	and	r4,r4,#0x03ffffff
+	mov	r1,#1
+	and	r5,r5,#0x03ffffff
+	str	r1,[$ctx,#36]		@ is_base2_26
+
+	vmov.32	$D0#lo[0],r2
+	vmov.32	$D1#lo[0],r3
+	vmov.32	$D2#lo[0],r4
+	vmov.32	$D3#lo[0],r5
+	vmov.32	$D4#lo[0],r6
+	adr	$zeros,.Lzeros
+
+	ldmia	sp!,{r1-r3,lr}
+	b	.Lbase2_32_neon
+
+.align	4
+.Lbase2_26_neon:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ load hash value
+
+	veor		$D0#lo,$D0#lo,$D0#lo
+	veor		$D1#lo,$D1#lo,$D1#lo
+	veor		$D2#lo,$D2#lo,$D2#lo
+	veor		$D3#lo,$D3#lo,$D3#lo
+	veor		$D4#lo,$D4#lo,$D4#lo
+	vld4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+	adr		$zeros,.Lzeros
+	vld1.32		{$D4#lo[0]},[$ctx]
+	sub		$ctx,$ctx,#16		@ rewind
+
+.Lbase2_32_neon:
+	add		$in2,$inp,#32
+	mov		$padbit,$padbit,lsl#24
+	tst		$len,#31
+	beq		.Leven
+
+	vld4.32		{$H0#lo[0],$H1#lo[0],$H2#lo[0],$H3#lo[0]},[$inp]!
+	vmov.32		$H4#lo[0],$padbit
+	sub		$len,$len,#16
+	add		$in2,$inp,#32
+
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H3,$H3
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+# endif
+	vsri.u32	$H4#lo,$H3#lo,#8	@ base 2^32 -> base 2^26
+	vshl.u32	$H3#lo,$H3#lo,#18
+
+	vsri.u32	$H3#lo,$H2#lo,#14
+	vshl.u32	$H2#lo,$H2#lo,#12
+	vadd.i32	$H4#hi,$H4#lo,$D4#lo	@ add hash value and move to #hi
+
+	vbic.i32	$H3#lo,#0xfc000000
+	vsri.u32	$H2#lo,$H1#lo,#20
+	vshl.u32	$H1#lo,$H1#lo,#6
+
+	vbic.i32	$H2#lo,#0xfc000000
+	vsri.u32	$H1#lo,$H0#lo,#26
+	vadd.i32	$H3#hi,$H3#lo,$D3#lo
+
+	vbic.i32	$H0#lo,#0xfc000000
+	vbic.i32	$H1#lo,#0xfc000000
+	vadd.i32	$H2#hi,$H2#lo,$D2#lo
+
+	vadd.i32	$H0#hi,$H0#lo,$D0#lo
+	vadd.i32	$H1#hi,$H1#lo,$D1#lo
+
+	mov		$tbl1,$zeros
+	add		$tbl0,$ctx,#48
+
+	cmp		$len,$len
+	b		.Long_tail
+
+.align	4
+.Leven:
+	subs		$len,$len,#64
+	it		lo
+	movlo		$in2,$zeros
+
+	vmov.i32	$H4,#1<<24		@ padbit, yes, always
+	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
+	add		$inp,$inp,#64
+	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
+	add		$in2,$in2,#64
+	itt		hi
+	addhi		$tbl1,$ctx,#(48+1*9*4)
+	addhi		$tbl0,$ctx,#(48+3*9*4)
+
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H3,$H3
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+# endif
+	vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
+	vshl.u32	$H3,$H3,#18
+
+	vsri.u32	$H3,$H2,#14
+	vshl.u32	$H2,$H2,#12
+
+	vbic.i32	$H3,#0xfc000000
+	vsri.u32	$H2,$H1,#20
+	vshl.u32	$H1,$H1,#6
+
+	vbic.i32	$H2,#0xfc000000
+	vsri.u32	$H1,$H0,#26
+
+	vbic.i32	$H0,#0xfc000000
+	vbic.i32	$H1,#0xfc000000
+
+	bls		.Lskip_loop
+
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^2
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	b		.Loop_neon
+
+.align	5
+.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 = h4*r0 + h3*r1   + h2*r2   + h1*r3   + h0*r4
+	@ d3 = h3*r0 + h2*r1   + h1*r2   + h0*r3   + h4*5*r4
+	@ d2 = h2*r0 + h1*r1   + h0*r2   + h4*5*r3 + h3*5*r4
+	@ d1 = h1*r0 + h0*r1   + h4*5*r2 + h3*5*r3 + h2*5*r4
+	@ d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ inp[2:3]*r^2
+
+	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ accumulate inp[0:1]
+	vmull.u32	$D2,$H2#hi,${R0}[1]
+	vadd.i32	$H0#lo,$H0#lo,$D0#lo
+	vmull.u32	$D0,$H0#hi,${R0}[1]
+	vadd.i32	$H3#lo,$H3#lo,$D3#lo
+	vmull.u32	$D3,$H3#hi,${R0}[1]
+	vmlal.u32	$D2,$H1#hi,${R1}[1]
+	vadd.i32	$H1#lo,$H1#lo,$D1#lo
+	vmull.u32	$D1,$H1#hi,${R0}[1]
+
+	vadd.i32	$H4#lo,$H4#lo,$D4#lo
+	vmull.u32	$D4,$H4#hi,${R0}[1]
+	subs		$len,$len,#64
+	vmlal.u32	$D0,$H4#hi,${S1}[1]
+	it		lo
+	movlo		$in2,$zeros
+	vmlal.u32	$D3,$H2#hi,${R1}[1]
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D1,$H0#hi,${R1}[1]
+	vmlal.u32	$D4,$H3#hi,${R1}[1]
+
+	vmlal.u32	$D0,$H3#hi,${S2}[1]
+	vmlal.u32	$D3,$H1#hi,${R2}[1]
+	vmlal.u32	$D4,$H2#hi,${R2}[1]
+	vmlal.u32	$D1,$H4#hi,${S2}[1]
+	vmlal.u32	$D2,$H0#hi,${R2}[1]
+
+	vmlal.u32	$D3,$H0#hi,${R3}[1]
+	vmlal.u32	$D0,$H2#hi,${S3}[1]
+	vmlal.u32	$D4,$H1#hi,${R3}[1]
+	vmlal.u32	$D1,$H3#hi,${S3}[1]
+	vmlal.u32	$D2,$H4#hi,${S3}[1]
+
+	vmlal.u32	$D3,$H4#hi,${S4}[1]
+	vmlal.u32	$D0,$H1#hi,${S4}[1]
+	vmlal.u32	$D4,$H0#hi,${R4}[1]
+	vmlal.u32	$D1,$H2#hi,${S4}[1]
+	vmlal.u32	$D2,$H3#hi,${S4}[1]
+
+	vld4.32		{$H0#hi,$H1#hi,$H2#hi,$H3#hi},[$in2]	@ inp[2:3] (or 0)
+	add		$in2,$in2,#64
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4 and accumulate
+
+	vmlal.u32	$D3,$H3#lo,${R0}[0]
+	vmlal.u32	$D0,$H0#lo,${R0}[0]
+	vmlal.u32	$D4,$H4#lo,${R0}[0]
+	vmlal.u32	$D1,$H1#lo,${R0}[0]
+	vmlal.u32	$D2,$H2#lo,${R0}[0]
+	vld1.32		${S4}[0],[$tbl0,:32]
+
+	vmlal.u32	$D3,$H2#lo,${R1}[0]
+	vmlal.u32	$D0,$H4#lo,${S1}[0]
+	vmlal.u32	$D4,$H3#lo,${R1}[0]
+	vmlal.u32	$D1,$H0#lo,${R1}[0]
+	vmlal.u32	$D2,$H1#lo,${R1}[0]
+
+	vmlal.u32	$D3,$H1#lo,${R2}[0]
+	vmlal.u32	$D0,$H3#lo,${S2}[0]
+	vmlal.u32	$D4,$H2#lo,${R2}[0]
+	vmlal.u32	$D1,$H4#lo,${S2}[0]
+	vmlal.u32	$D2,$H0#lo,${R2}[0]
+
+	vmlal.u32	$D3,$H0#lo,${R3}[0]
+	vmlal.u32	$D0,$H2#lo,${S3}[0]
+	vmlal.u32	$D4,$H1#lo,${R3}[0]
+	vmlal.u32	$D1,$H3#lo,${S3}[0]
+	vmlal.u32	$D3,$H4#lo,${S4}[0]
+
+	vmlal.u32	$D2,$H4#lo,${S3}[0]
+	vmlal.u32	$D0,$H1#lo,${S4}[0]
+	vmlal.u32	$D4,$H0#lo,${R4}[0]
+	vmov.i32	$H4,#1<<24		@ padbit, yes, always
+	vmlal.u32	$D1,$H2#lo,${S4}[0]
+	vmlal.u32	$D2,$H3#lo,${S4}[0]
+
+	vld4.32		{$H0#lo,$H1#lo,$H2#lo,$H3#lo},[$inp]	@ inp[0:1]
+	add		$inp,$inp,#64
+# ifdef	__ARMEB__
+	vrev32.8	$H0,$H0
+	vrev32.8	$H1,$H1
+	vrev32.8	$H2,$H2
+	vrev32.8	$H3,$H3
+# endif
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction interleaved with base 2^32 -> base 2^26 of
+	@ inp[0:3] previously loaded to $H0-$H3 and smashed to $H0-$H4.
+
+	vshr.u64	$T0,$D3,#26
+	vmovn.i64	$D3#lo,$D3
+	 vshr.u64	$T1,$D0,#26
+	 vmovn.i64	$D0#lo,$D0
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	vbic.i32	$D3#lo,#0xfc000000
+	  vsri.u32	$H4,$H3,#8		@ base 2^32 -> base 2^26
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+	  vshl.u32	$H3,$H3,#18
+	 vbic.i32	$D0#lo,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D4,#26
+	vmovn.i64	$D4#lo,$D4
+	 vshr.u64	$T1,$D1,#26
+	 vmovn.i64	$D1#lo,$D1
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+	  vsri.u32	$H3,$H2,#14
+	vbic.i32	$D4#lo,#0xfc000000
+	  vshl.u32	$H2,$H2,#12
+	 vbic.i32	$D1#lo,#0xfc000000
+
+	vadd.i32	$D0#lo,$D0#lo,$T0#lo
+	vshl.u32	$T0#lo,$T0#lo,#2
+	  vbic.i32	$H3,#0xfc000000
+	 vshrn.u64	$T1#lo,$D2,#26
+	 vmovn.i64	$D2#lo,$D2
+	vaddl.u32	$D0,$D0#lo,$T0#lo	@ h4 -> h0 [widen for a sec]
+	  vsri.u32	$H2,$H1,#20
+	 vadd.i32	$D3#lo,$D3#lo,$T1#lo	@ h2 -> h3
+	  vshl.u32	$H1,$H1,#6
+	 vbic.i32	$D2#lo,#0xfc000000
+	  vbic.i32	$H2,#0xfc000000
+
+	vshrn.u64	$T0#lo,$D0,#26		@ re-narrow
+	vmovn.i64	$D0#lo,$D0
+	  vsri.u32	$H1,$H0,#26
+	  vbic.i32	$H0,#0xfc000000
+	 vshr.u32	$T1#lo,$D3#lo,#26
+	 vbic.i32	$D3#lo,#0xfc000000
+	vbic.i32	$D0#lo,#0xfc000000
+	vadd.i32	$D1#lo,$D1#lo,$T0#lo	@ h0 -> h1
+	 vadd.i32	$D4#lo,$D4#lo,$T1#lo	@ h3 -> h4
+	  vbic.i32	$H1,#0xfc000000
+
+	bhi		.Loop_neon
+
+.Lskip_loop:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	add		$tbl1,$ctx,#(48+0*9*4)
+	add		$tbl0,$ctx,#(48+1*9*4)
+	adds		$len,$len,#32
+	it		ne
+	movne		$len,#0
+	bne		.Long_tail
+
+	vadd.i32	$H2#hi,$H2#lo,$D2#lo	@ add hash value and move to #hi
+	vadd.i32	$H0#hi,$H0#lo,$D0#lo
+	vadd.i32	$H3#hi,$H3#lo,$D3#lo
+	vadd.i32	$H1#hi,$H1#lo,$D1#lo
+	vadd.i32	$H4#hi,$H4#lo,$D4#lo
+
+.Long_tail:
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^1
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^2
+
+	vadd.i32	$H2#lo,$H2#lo,$D2#lo	@ can be redundant
+	vmull.u32	$D2,$H2#hi,$R0
+	vadd.i32	$H0#lo,$H0#lo,$D0#lo
+	vmull.u32	$D0,$H0#hi,$R0
+	vadd.i32	$H3#lo,$H3#lo,$D3#lo
+	vmull.u32	$D3,$H3#hi,$R0
+	vadd.i32	$H1#lo,$H1#lo,$D1#lo
+	vmull.u32	$D1,$H1#hi,$R0
+	vadd.i32	$H4#lo,$H4#lo,$D4#lo
+	vmull.u32	$D4,$H4#hi,$R0
+
+	vmlal.u32	$D0,$H4#hi,$S1
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vmlal.u32	$D3,$H2#hi,$R1
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vmlal.u32	$D1,$H0#hi,$R1
+	vmlal.u32	$D4,$H3#hi,$R1
+	vmlal.u32	$D2,$H1#hi,$R1
+
+	vmlal.u32	$D3,$H1#hi,$R2
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D0,$H3#hi,$S2
+	vld1.32		${S4}[0],[$tbl0,:32]
+	vmlal.u32	$D4,$H2#hi,$R2
+	vmlal.u32	$D1,$H4#hi,$S2
+	vmlal.u32	$D2,$H0#hi,$R2
+
+	vmlal.u32	$D3,$H0#hi,$R3
+	 it		ne
+	 addne		$tbl1,$ctx,#(48+2*9*4)
+	vmlal.u32	$D0,$H2#hi,$S3
+	 it		ne
+	 addne		$tbl0,$ctx,#(48+3*9*4)
+	vmlal.u32	$D4,$H1#hi,$R3
+	vmlal.u32	$D1,$H3#hi,$S3
+	vmlal.u32	$D2,$H4#hi,$S3
+
+	vmlal.u32	$D3,$H4#hi,$S4
+	 vorn		$MASK,$MASK,$MASK	@ all-ones, can be redundant
+	vmlal.u32	$D0,$H1#hi,$S4
+	 vshr.u64	$MASK,$MASK,#38
+	vmlal.u32	$D4,$H0#hi,$R4
+	vmlal.u32	$D1,$H2#hi,$S4
+	vmlal.u32	$D2,$H3#hi,$S4
+
+	beq		.Lshort_tail
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	vld4.32		{${R0}[1],${R1}[1],${S1}[1],${R2}[1]},[$tbl1]!	@ load r^3
+	vld4.32		{${R0}[0],${R1}[0],${S1}[0],${R2}[0]},[$tbl0]!	@ load r^4
+
+	vmlal.u32	$D2,$H2#lo,$R0
+	vmlal.u32	$D0,$H0#lo,$R0
+	vmlal.u32	$D3,$H3#lo,$R0
+	vmlal.u32	$D1,$H1#lo,$R0
+	vmlal.u32	$D4,$H4#lo,$R0
+
+	vmlal.u32	$D0,$H4#lo,$S1
+	vld4.32		{${S2}[1],${R3}[1],${S3}[1],${R4}[1]},[$tbl1]!
+	vmlal.u32	$D3,$H2#lo,$R1
+	vld4.32		{${S2}[0],${R3}[0],${S3}[0],${R4}[0]},[$tbl0]!
+	vmlal.u32	$D1,$H0#lo,$R1
+	vmlal.u32	$D4,$H3#lo,$R1
+	vmlal.u32	$D2,$H1#lo,$R1
+
+	vmlal.u32	$D3,$H1#lo,$R2
+	vld1.32		${S4}[1],[$tbl1,:32]
+	vmlal.u32	$D0,$H3#lo,$S2
+	vld1.32		${S4}[0],[$tbl0,:32]
+	vmlal.u32	$D4,$H2#lo,$R2
+	vmlal.u32	$D1,$H4#lo,$S2
+	vmlal.u32	$D2,$H0#lo,$R2
+
+	vmlal.u32	$D3,$H0#lo,$R3
+	vmlal.u32	$D0,$H2#lo,$S3
+	vmlal.u32	$D4,$H1#lo,$R3
+	vmlal.u32	$D1,$H3#lo,$S3
+	vmlal.u32	$D2,$H4#lo,$S3
+
+	vmlal.u32	$D3,$H4#lo,$S4
+	 vorn		$MASK,$MASK,$MASK	@ all-ones
+	vmlal.u32	$D0,$H1#lo,$S4
+	 vshr.u64	$MASK,$MASK,#38
+	vmlal.u32	$D4,$H0#lo,$R4
+	vmlal.u32	$D1,$H2#lo,$S4
+	vmlal.u32	$D2,$H3#lo,$S4
+
+.Lshort_tail:
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ horizontal addition
+
+	vadd.i64	$D3#lo,$D3#lo,$D3#hi
+	vadd.i64	$D0#lo,$D0#lo,$D0#hi
+	vadd.i64	$D4#lo,$D4#lo,$D4#hi
+	vadd.i64	$D1#lo,$D1#lo,$D1#hi
+	vadd.i64	$D2#lo,$D2#lo,$D2#hi
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ lazy reduction, but without narrowing
+
+	vshr.u64	$T0,$D3,#26
+	vand.i64	$D3,$D3,$MASK
+	 vshr.u64	$T1,$D0,#26
+	 vand.i64	$D0,$D0,$MASK
+	vadd.i64	$D4,$D4,$T0		@ h3 -> h4
+	 vadd.i64	$D1,$D1,$T1		@ h0 -> h1
+
+	vshr.u64	$T0,$D4,#26
+	vand.i64	$D4,$D4,$MASK
+	 vshr.u64	$T1,$D1,#26
+	 vand.i64	$D1,$D1,$MASK
+	 vadd.i64	$D2,$D2,$T1		@ h1 -> h2
+
+	vadd.i64	$D0,$D0,$T0
+	vshl.u64	$T0,$T0,#2
+	 vshr.u64	$T1,$D2,#26
+	 vand.i64	$D2,$D2,$MASK
+	vadd.i64	$D0,$D0,$T0		@ h4 -> h0
+	 vadd.i64	$D3,$D3,$T1		@ h2 -> h3
+
+	vshr.u64	$T0,$D0,#26
+	vand.i64	$D0,$D0,$MASK
+	 vshr.u64	$T1,$D3,#26
+	 vand.i64	$D3,$D3,$MASK
+	vadd.i64	$D1,$D1,$T0		@ h0 -> h1
+	 vadd.i64	$D4,$D4,$T1		@ h3 -> h4
+
+	cmp		$len,#0
+	bne		.Leven
+
+	@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@
+	@ store hash value
+
+	vst4.32		{$D0#lo[0],$D1#lo[0],$D2#lo[0],$D3#lo[0]},[$ctx]!
+	vst1.32		{$D4#lo[0]},[$ctx]
+
+	vldmia	sp!,{d8-d15}			@ epilogue
+	ldmia	sp!,{r4-r7}
+.Lno_data_neon:
+	ret					@ bx	lr
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.type	poly1305_emit_neon,%function
+.align	5
+poly1305_emit_neon:
+	ldr	ip,[$ctx,#36]		@ is_base2_26
+
+	stmdb	sp!,{r4-r11}
+
+	tst	ip,ip
+	beq	.Lpoly1305_emit_enter
+
+	ldmia	$ctx,{$h0-$h4}
+	eor	$g0,$g0,$g0
+
+	adds	$h0,$h0,$h1,lsl#26	@ base 2^26 -> base 2^32
+	mov	$h1,$h1,lsr#6
+	adcs	$h1,$h1,$h2,lsl#20
+	mov	$h2,$h2,lsr#12
+	adcs	$h2,$h2,$h3,lsl#14
+	mov	$h3,$h3,lsr#18
+	adcs	$h3,$h3,$h4,lsl#8
+	adc	$h4,$g0,$h4,lsr#24	@ can be partially reduced ...
+
+	and	$g0,$h4,#-4		@ ... so reduce
+	and	$h4,$h3,#3
+	add	$g0,$g0,$g0,lsr#2	@ *= 5
+	adds	$h0,$h0,$g0
+	adcs	$h1,$h1,#0
+	adcs	$h2,$h2,#0
+	adcs	$h3,$h3,#0
+	adc	$h4,$h4,#0
+
+	adds	$g0,$h0,#5		@ compare to modulus
+	adcs	$g1,$h1,#0
+	adcs	$g2,$h2,#0
+	adcs	$g3,$h3,#0
+	adc	$g4,$h4,#0
+	tst	$g4,#4			@ did it carry/borrow?
+
+	it	ne
+	movne	$h0,$g0
+	ldr	$g0,[$nonce,#0]
+	it	ne
+	movne	$h1,$g1
+	ldr	$g1,[$nonce,#4]
+	it	ne
+	movne	$h2,$g2
+	ldr	$g2,[$nonce,#8]
+	it	ne
+	movne	$h3,$g3
+	ldr	$g3,[$nonce,#12]
+
+	adds	$h0,$h0,$g0		@ accumulate nonce
+	adcs	$h1,$h1,$g1
+	adcs	$h2,$h2,$g2
+	adc	$h3,$h3,$g3
+
+# ifdef __ARMEB__
+	rev	$h0,$h0
+	rev	$h1,$h1
+	rev	$h2,$h2
+	rev	$h3,$h3
+# endif
+	str	$h0,[$mac,#0]		@ store the result
+	str	$h1,[$mac,#4]
+	str	$h2,[$mac,#8]
+	str	$h3,[$mac,#12]
+
+	ldmia	sp!,{r4-r11}
+	ret				@ bx	lr
+.size	poly1305_emit_neon,.-poly1305_emit_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+# ifndef __KERNEL__
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-.Lpoly1305_init
+# endif
+#endif
+___
+}	}
+$code.=<<___;
+.align	2
+#if	__ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm   OPENSSL_armcap_P,4,4
+#endif
+___
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/@/ and !/^$/);
+	print;
+}
+close SELF;
+
+foreach (split("\n",$code)) {
+	s/\`([^\`]*)\`/eval $1/geo;
+
+	s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo	or
+	s/\bret\b/bx	lr/go						or
+	s/\bbx\s+lr\b/.word\t0xe12fff1e/go;	# make it possible to compile with -march=armv4
+
+	print $_,"\n";
+}
+close STDOUT; # enforce flush
diff --git a/src/crypto/zinc/poly1305/poly1305-arm64.S b/src/crypto/zinc/poly1305/poly1305-arm64.S
deleted file mode 100644
index 5f4e7fb..0000000
--- a/src/crypto/zinc/poly1305/poly1305-arm64.S
+++ /dev/null
@@ -1,824 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
-/*
- * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
- *
- * This is based in part on Andy Polyakov's implementation from CRYPTOGAMS.
- */
-
-#include <linux/linkage.h>
-.text
-
-.align	5
-ENTRY(poly1305_init_arm)
-	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
-
-	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
-
-.Lno_key:
-	ret
-ENDPROC(poly1305_init_arm)
-
-.align	5
-ENTRY(poly1305_blocks_arm)
-	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
-ENDPROC(poly1305_blocks_arm)
-
-.align	5
-ENTRY(poly1305_emit_arm)
-	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
-ENDPROC(poly1305_emit_arm)
-
-.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
-
-__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
-
-#ifdef CONFIG_KERNEL_MODE_NEON
-.align	5
-ENTRY(poly1305_blocks_neon)
-	ldr	x17,[x0,#24]
-	cmp	x2,#128
-	b.hs	.Lblocks_neon
-	cbz	x17,poly1305_blocks_arm
-
-.Lblocks_neon:
-	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
-	str	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
-	ret
-ENDPROC(poly1305_blocks_neon)
-
-.align	5
-ENTRY(poly1305_emit_neon)
-	ldr	x17,[x0,#24]
-	cbz	x17,poly1305_emit_arm
-
-	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
-ENDPROC(poly1305_emit_neon)
-
-.align	5
-.Lzeros:
-.long	0,0,0,0,0,0,0,0
-#endif
diff --git a/src/crypto/zinc/poly1305/poly1305-arm64.pl b/src/crypto/zinc/poly1305/poly1305-arm64.pl
new file mode 100644
index 0000000..cf0ce9d
--- /dev/null
+++ b/src/crypto/zinc/poly1305/poly1305-arm64.pl
@@ -0,0 +1,972 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+#
+# This code is taken from the OpenSSL project but the author, Andy Polyakov,
+# has relicensed it under the licenses specified in the SPDX header above.
+# The original headers, including the original license headers, are
+# included below for completeness.
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# This module implements Poly1305 hash for ARMv8.
+#
+# June 2015
+#
+# Numbers are cycles per processed byte with poly1305_blocks alone.
+#
+#		IALU/gcc-4.9	NEON
+#
+# Apple A7	1.86/+5%	0.72
+# Cortex-A53	2.69/+58%	1.47
+# Cortex-A57	2.70/+7%	1.14
+# Denver	1.64/+50%	1.18(*)
+# X-Gene	2.13/+68%	2.27
+# Mongoose	1.77/+75%	1.12
+# Kryo		2.70/+55%	1.13
+#
+# (*)	estimate based on resources availability is less than 1.0,
+#	i.e. measured result is worse than expected, presumably binary
+#	translator is not almighty;
+
+$flavour=shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
+
+my ($ctx,$inp,$len,$padbit) = map("x$_",(0..3));
+my ($mac,$nonce)=($inp,$len);
+
+my ($h0,$h1,$h2,$r0,$r1,$s1,$t0,$t1,$d0,$d1,$d2) = map("x$_",(4..14));
+
+$code.=<<___;
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+.extern	OPENSSL_armcap_P
+#else
+# define poly1305_init   poly1305_init_arm
+# define poly1305_blocks poly1305_blocks_arm
+# define poly1305_emit   poly1305_emit_arm
+#endif
+
+.text
+
+// forward "declarations" are required for Apple
+.globl	poly1305_blocks
+.globl	poly1305_emit
+#ifdef	__KERNEL__
+.globl	poly1305_blocks_neon
+.globl	poly1305_emit_neon
+#endif
+
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+	cmp	$inp,xzr
+	stp	xzr,xzr,[$ctx]		// zero hash value
+	stp	xzr,xzr,[$ctx,#16]	// [along with is_base2_26]
+
+	csel	x0,xzr,x0,eq
+	b.eq	.Lno_key
+
+#ifndef	__KERNEL__
+# ifdef	__ILP32__
+	ldrsw	$t1,.LOPENSSL_armcap_P
+# else
+	ldr	$t1,.LOPENSSL_armcap_P
+# endif
+	adr	$t0,.LOPENSSL_armcap_P
+	ldr	w17,[$t0,$t1]
+#endif
+
+	ldp	$r0,$r1,[$inp]		// load key
+	mov	$s1,#0xfffffffc0fffffff
+	movk	$s1,#0x0fff,lsl#48
+#ifdef	__AARCH64EB__
+	rev	$r0,$r0			// flip bytes
+	rev	$r1,$r1
+#endif
+	and	$r0,$r0,$s1		// &=0ffffffc0fffffff
+	and	$s1,$s1,#-4
+	and	$r1,$r1,$s1		// &=0ffffffc0ffffffc
+	stp	$r0,$r1,[$ctx,#32]	// save key value
+
+#ifndef	__KERNEL__
+	tst	w17,#ARMV7_NEON
+
+	adr	$d0,poly1305_blocks
+	adr	$r0,poly1305_blocks_neon
+	adr	$d1,poly1305_emit
+	adr	$r1,poly1305_emit_neon
+
+	csel	$d0,$d0,$r0,eq
+	csel	$d1,$d1,$r1,eq
+
+# ifdef	__ILP32__
+	stp	w12,w13,[$len]
+# else
+	stp	$d0,$d1,[$len]
+# endif
+
+	mov	x0,#1
+#else
+	mov	x0,#0
+#endif
+.Lno_key:
+	ret
+.size	poly1305_init,.-poly1305_init
+
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+	ands	$len,$len,#-16
+	b.eq	.Lno_data
+
+	ldp	$h0,$h1,[$ctx]		// load hash value
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+	ldr	$h2,[$ctx,#16]
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+	b	.Loop
+
+.align	5
+.Loop:
+	ldp	$t0,$t1,[$inp],#16	// load input
+	sub	$len,$len,#16
+#ifdef	__AARCH64EB__
+	rev	$t0,$t0
+	rev	$t1,$t1
+#endif
+	adds	$h0,$h0,$t0		// accumulate input
+	adcs	$h1,$h1,$t1
+
+	mul	$d0,$h0,$r0		// h0*r0
+	adc	$h2,$h2,$padbit
+	umulh	$d1,$h0,$r0
+
+	mul	$t0,$h1,$s1		// h1*5*r1
+	umulh	$t1,$h1,$s1
+
+	adds	$d0,$d0,$t0
+	mul	$t0,$h0,$r1		// h0*r1
+	adc	$d1,$d1,$t1
+	umulh	$d2,$h0,$r1
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h1,$r0		// h1*r0
+	adc	$d2,$d2,xzr
+	umulh	$t1,$h1,$r0
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h2,$s1		// h2*5*r1
+	adc	$d2,$d2,$t1
+	mul	$t1,$h2,$r0		// h2*r0
+
+	adds	$d1,$d1,$t0
+	adc	$d2,$d2,$t1
+
+	and	$t0,$d2,#-4		// final reduction
+	and	$h2,$d2,#3
+	add	$t0,$t0,$d2,lsr#2
+	adds	$h0,$d0,$t0
+	adcs	$h1,$d1,xzr
+	adc	$h2,$h2,xzr
+
+	cbnz	$len,.Loop
+
+	stp	$h0,$h1,[$ctx]		// store hash value
+	str	$h2,[$ctx,#16]
+
+.Lno_data:
+	ret
+.size	poly1305_blocks,.-poly1305_blocks
+
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+	ldp	$h0,$h1,[$ctx]		// load hash base 2^64
+	ldr	$h2,[$ctx,#16]
+	ldp	$t0,$t1,[$nonce]	// load nonce
+
+	adds	$d0,$h0,#5		// compare to modulus
+	adcs	$d1,$h1,xzr
+	adc	$d2,$h2,xzr
+
+	tst	$d2,#-4			// see if it's carried/borrowed
+
+	csel	$h0,$h0,$d0,eq
+	csel	$h1,$h1,$d1,eq
+
+#ifdef	__AARCH64EB__
+	ror	$t0,$t0,#32		// flip nonce words
+	ror	$t1,$t1,#32
+#endif
+	adds	$h0,$h0,$t0		// accumulate nonce
+	adc	$h1,$h1,$t1
+#ifdef	__AARCH64EB__
+	rev	$h0,$h0			// flip output bytes
+	rev	$h1,$h1
+#endif
+	stp	$h0,$h1,[$mac]		// write result
+
+	ret
+.size	poly1305_emit,.-poly1305_emit
+___
+my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("v$_.4s",(0..8));
+my ($IN01_0,$IN01_1,$IN01_2,$IN01_3,$IN01_4) = map("v$_.2s",(9..13));
+my ($IN23_0,$IN23_1,$IN23_2,$IN23_3,$IN23_4) = map("v$_.2s",(14..18));
+my ($ACC0,$ACC1,$ACC2,$ACC3,$ACC4) = map("v$_.2d",(19..23));
+my ($H0,$H1,$H2,$H3,$H4) = map("v$_.2s",(24..28));
+my ($T0,$T1,$MASK) = map("v$_",(29..31));
+
+my ($in2,$zeros)=("x16","x17");
+my $is_base2_26 = $zeros;		# borrow
+
+$code.=<<___;
+.type	__poly1305_mult,%function
+.align	5
+__poly1305_mult:
+	mul	$d0,$h0,$r0		// h0*r0
+	umulh	$d1,$h0,$r0
+
+	mul	$t0,$h1,$s1		// h1*5*r1
+	umulh	$t1,$h1,$s1
+
+	adds	$d0,$d0,$t0
+	mul	$t0,$h0,$r1		// h0*r1
+	adc	$d1,$d1,$t1
+	umulh	$d2,$h0,$r1
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h1,$r0		// h1*r0
+	adc	$d2,$d2,xzr
+	umulh	$t1,$h1,$r0
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h2,$s1		// h2*5*r1
+	adc	$d2,$d2,$t1
+	mul	$t1,$h2,$r0		// h2*r0
+
+	adds	$d1,$d1,$t0
+	adc	$d2,$d2,$t1
+
+	and	$t0,$d2,#-4		// final reduction
+	and	$h2,$d2,#3
+	add	$t0,$t0,$d2,lsr#2
+	adds	$h0,$d0,$t0
+	adcs	$h1,$d1,xzr
+	adc	$h2,$h2,xzr
+
+	ret
+.size	__poly1305_mult,.-__poly1305_mult
+
+.type	__poly1305_splat,%function
+.align	5
+__poly1305_splat:
+	and	x12,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x13,$h0,#26,#26
+	extr	x14,$h1,$h0,#52
+	and	x14,x14,#0x03ffffff
+	ubfx	x15,$h1,#14,#26
+	extr	x16,$h2,$h1,#40
+
+	str	w12,[$ctx,#16*0]	// r0
+	add	w12,w13,w13,lsl#2	// r1*5
+	str	w13,[$ctx,#16*1]	// r1
+	add	w13,w14,w14,lsl#2	// r2*5
+	str	w12,[$ctx,#16*2]	// s1
+	str	w14,[$ctx,#16*3]	// r2
+	add	w14,w15,w15,lsl#2	// r3*5
+	str	w13,[$ctx,#16*4]	// s2
+	str	w15,[$ctx,#16*5]	// r3
+	add	w15,w16,w16,lsl#2	// r4*5
+	str	w14,[$ctx,#16*6]	// s3
+	str	w16,[$ctx,#16*7]	// r4
+	str	w15,[$ctx,#16*8]	// s4
+
+	ret
+.size	__poly1305_splat,.-__poly1305_splat
+
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+	ldr	$is_base2_26,[$ctx,#24]
+	cmp	$len,#128
+	b.hs	.Lblocks_neon
+	cbz	$is_base2_26,poly1305_blocks
+
+.Lblocks_neon:
+	stp	x29,x30,[sp,#-80]!
+	add	x29,sp,#0
+
+	ands	$len,$len,#-16
+	b.eq	.Lno_data_neon
+
+	cbz	$is_base2_26,.Lbase2_64_neon
+
+	ldp	w10,w11,[$ctx]		// load hash value base 2^26
+	ldp	w12,w13,[$ctx,#8]
+	ldr	w14,[$ctx,#16]
+
+	tst	$len,#31
+	b.eq	.Leven_neon
+
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+
+	add	$h0,x10,x11,lsl#26	// base 2^26 -> base 2^64
+	lsr	$h1,x12,#12
+	adds	$h0,$h0,x12,lsl#52
+	add	$h1,$h1,x13,lsl#14
+	adc	$h1,$h1,xzr
+	lsr	$h2,x14,#24
+	adds	$h1,$h1,x14,lsl#40
+	adc	$d2,$h2,xzr		// can be partially reduced...
+
+	ldp	$d0,$d1,[$inp],#16	// load input
+	sub	$len,$len,#16
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+
+	and	$t0,$d2,#-4		// ... so reduce
+	and	$h2,$d2,#3
+	add	$t0,$t0,$d2,lsr#2
+	adds	$h0,$h0,$t0
+	adcs	$h1,$h1,xzr
+	adc	$h2,$h2,xzr
+
+#ifdef	__AARCH64EB__
+	rev	$d0,$d0
+	rev	$d1,$d1
+#endif
+	adds	$h0,$h0,$d0		// accumulate input
+	adcs	$h1,$h1,$d1
+	adc	$h2,$h2,$padbit
+
+	bl	__poly1305_mult
+	ldr	x30,[sp,#8]
+
+	cbz	$padbit,.Lstore_base2_64_neon
+
+	and	x10,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,$h0,#26,#26
+	extr	x12,$h1,$h0,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,$h1,#14,#26
+	extr	x14,$h2,$h1,#40
+
+	cbnz	$len,.Leven_neon
+
+	stp	w10,w11,[$ctx]		// store hash value base 2^26
+	stp	w12,w13,[$ctx,#8]
+	str	w14,[$ctx,#16]
+	b	.Lno_data_neon
+
+.align	4
+.Lstore_base2_64_neon:
+	stp	$h0,$h1,[$ctx]		// store hash value base 2^64
+	stp	$h2,xzr,[$ctx,#16]	// note that is_base2_26 is zeroed
+	b	.Lno_data_neon
+
+.align	4
+.Lbase2_64_neon:
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+
+	ldp	$h0,$h1,[$ctx]		// load hash value base 2^64
+	ldr	$h2,[$ctx,#16]
+
+	tst	$len,#31
+	b.eq	.Linit_neon
+
+	ldp	$d0,$d1,[$inp],#16	// load input
+	sub	$len,$len,#16
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+#ifdef	__AARCH64EB__
+	rev	$d0,$d0
+	rev	$d1,$d1
+#endif
+	adds	$h0,$h0,$d0		// accumulate input
+	adcs	$h1,$h1,$d1
+	adc	$h2,$h2,$padbit
+
+	bl	__poly1305_mult
+
+.Linit_neon:
+	and	x10,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,$h0,#26,#26
+	extr	x12,$h1,$h0,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,$h1,#14,#26
+	extr	x14,$h2,$h1,#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	${H0},x10
+	fmov	${H1},x11
+	fmov	${H2},x12
+	fmov	${H3},x13
+	fmov	${H4},x14
+
+	////////////////////////////////// initialize r^n table
+	mov	$h0,$r0			// r^1
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+	mov	$h1,$r1
+	mov	$h2,xzr
+	add	$ctx,$ctx,#48+12
+	bl	__poly1305_splat
+
+	bl	__poly1305_mult		// r^2
+	sub	$ctx,$ctx,#4
+	bl	__poly1305_splat
+
+	bl	__poly1305_mult		// r^3
+	sub	$ctx,$ctx,#4
+	bl	__poly1305_splat
+
+	bl	__poly1305_mult		// r^4
+	sub	$ctx,$ctx,#4
+	bl	__poly1305_splat
+	ldr	x30,[sp,#8]
+
+	add	$in2,$inp,#32
+	adr	$zeros,.Lzeros
+	subs	$len,$len,#64
+	csel	$in2,$zeros,$in2,lo
+
+	mov	x4,#1
+	str	x4,[$ctx,#-24]		// set is_base2_26
+	sub	$ctx,$ctx,#48		// restore original $ctx
+	b	.Ldo_neon
+
+.align	4
+.Leven_neon:
+	add	$in2,$inp,#32
+	adr	$zeros,.Lzeros
+	subs	$len,$len,#64
+	csel	$in2,$zeros,$in2,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	${H0},x10
+	fmov	${H1},x11
+	fmov	${H2},x12
+	fmov	${H3},x13
+	fmov	${H4},x14
+
+.Ldo_neon:
+	ldp	x8,x12,[$in2],#16	// inp[2:3] (or zero)
+	ldp	x9,x13,[$in2],#48
+
+	lsl	$padbit,$padbit,#24
+	add	x15,$ctx,#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	$IN23_0,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,$padbit,x12,lsr#40
+	add	x13,$padbit,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	$IN23_1,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	fmov	$IN23_2,x8
+	fmov	$IN23_3,x10
+	fmov	$IN23_4,x12
+
+	ldp	x8,x12,[$inp],#16	// inp[0:1]
+	ldp	x9,x13,[$inp],#48
+
+	ld1	{$R0,$R1,$S1,$R2},[x15],#64
+	ld1	{$S2,$R3,$S3,$R4},[x15],#64
+	ld1	{$S4},[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	$IN01_0,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,$padbit,x12,lsr#40
+	add	x13,$padbit,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	$IN01_1,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	movi	$MASK.2d,#-1
+	fmov	$IN01_2,x8
+	fmov	$IN01_3,x10
+	fmov	$IN01_4,x12
+	ushr	$MASK.2d,$MASK.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	$len,$len,#64
+	umull	$ACC4,$IN23_0,${R4}[2]
+	csel	$in2,$zeros,$in2,lo
+	umull	$ACC3,$IN23_0,${R3}[2]
+	umull	$ACC2,$IN23_0,${R2}[2]
+	 ldp	x8,x12,[$in2],#16	// inp[2:3] (or zero)
+	umull	$ACC1,$IN23_0,${R1}[2]
+	 ldp	x9,x13,[$in2],#48
+	umull	$ACC0,$IN23_0,${R0}[2]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	umlal	$ACC4,$IN23_1,${R3}[2]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	$ACC3,$IN23_1,${R2}[2]
+	 and	x5,x9,#0x03ffffff
+	umlal	$ACC2,$IN23_1,${R1}[2]
+	 ubfx	x6,x8,#26,#26
+	umlal	$ACC1,$IN23_1,${R0}[2]
+	 ubfx	x7,x9,#26,#26
+	umlal	$ACC0,$IN23_1,${S4}[2]
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+
+	umlal	$ACC4,$IN23_2,${R2}[2]
+	 extr	x8,x12,x8,#52
+	umlal	$ACC3,$IN23_2,${R1}[2]
+	 extr	x9,x13,x9,#52
+	umlal	$ACC2,$IN23_2,${R0}[2]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	$ACC1,$IN23_2,${S4}[2]
+	 fmov	$IN23_0,x4
+	umlal	$ACC0,$IN23_2,${S3}[2]
+	 and	x8,x8,#0x03ffffff
+
+	umlal	$ACC4,$IN23_3,${R1}[2]
+	 and	x9,x9,#0x03ffffff
+	umlal	$ACC3,$IN23_3,${R0}[2]
+	 ubfx	x10,x12,#14,#26
+	umlal	$ACC2,$IN23_3,${S4}[2]
+	 ubfx	x11,x13,#14,#26
+	umlal	$ACC1,$IN23_3,${S3}[2]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	$ACC0,$IN23_3,${S2}[2]
+	 fmov	$IN23_1,x6
+
+	add	$IN01_2,$IN01_2,$H2
+	 add	x12,$padbit,x12,lsr#40
+	umlal	$ACC4,$IN23_4,${R0}[2]
+	 add	x13,$padbit,x13,lsr#40
+	umlal	$ACC3,$IN23_4,${S4}[2]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	$ACC2,$IN23_4,${S3}[2]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	$ACC1,$IN23_4,${S2}[2]
+	 fmov	$IN23_2,x8
+	umlal	$ACC0,$IN23_4,${S1}[2]
+	 fmov	$IN23_3,x10
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4 and accumulate
+
+	add	$IN01_0,$IN01_0,$H0
+	 fmov	$IN23_4,x12
+	umlal	$ACC3,$IN01_2,${R1}[0]
+	 ldp	x8,x12,[$inp],#16	// inp[0:1]
+	umlal	$ACC0,$IN01_2,${S3}[0]
+	 ldp	x9,x13,[$inp],#48
+	umlal	$ACC4,$IN01_2,${R2}[0]
+	umlal	$ACC1,$IN01_2,${S4}[0]
+	umlal	$ACC2,$IN01_2,${R0}[0]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	add	$IN01_1,$IN01_1,$H1
+	umlal	$ACC3,$IN01_0,${R3}[0]
+	umlal	$ACC4,$IN01_0,${R4}[0]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	$ACC2,$IN01_0,${R2}[0]
+	 and	x5,x9,#0x03ffffff
+	umlal	$ACC0,$IN01_0,${R0}[0]
+	 ubfx	x6,x8,#26,#26
+	umlal	$ACC1,$IN01_0,${R1}[0]
+	 ubfx	x7,x9,#26,#26
+
+	add	$IN01_3,$IN01_3,$H3
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	umlal	$ACC3,$IN01_1,${R2}[0]
+	 extr	x8,x12,x8,#52
+	umlal	$ACC4,$IN01_1,${R3}[0]
+	 extr	x9,x13,x9,#52
+	umlal	$ACC0,$IN01_1,${S4}[0]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	$ACC2,$IN01_1,${R1}[0]
+	 fmov	$IN01_0,x4
+	umlal	$ACC1,$IN01_1,${R0}[0]
+	 and	x8,x8,#0x03ffffff
+
+	add	$IN01_4,$IN01_4,$H4
+	 and	x9,x9,#0x03ffffff
+	umlal	$ACC3,$IN01_3,${R0}[0]
+	 ubfx	x10,x12,#14,#26
+	umlal	$ACC0,$IN01_3,${S2}[0]
+	 ubfx	x11,x13,#14,#26
+	umlal	$ACC4,$IN01_3,${R1}[0]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	$ACC1,$IN01_3,${S3}[0]
+	 fmov	$IN01_1,x6
+	umlal	$ACC2,$IN01_3,${S4}[0]
+	 add	x12,$padbit,x12,lsr#40
+
+	umlal	$ACC3,$IN01_4,${S4}[0]
+	 add	x13,$padbit,x13,lsr#40
+	umlal	$ACC0,$IN01_4,${S1}[0]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	$ACC4,$IN01_4,${R0}[0]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	$ACC1,$IN01_4,${S2}[0]
+	 fmov	$IN01_2,x8
+	umlal	$ACC2,$IN01_4,${S3}[0]
+	 fmov	$IN01_3,x10
+	 fmov	$IN01_4,x12
+
+	/////////////////////////////////////////////////////////////////
+	// lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	// and P. Schwabe
+	//
+	// [see discussion in poly1305-armv4 module]
+
+	ushr	$T0.2d,$ACC3,#26
+	xtn	$H3,$ACC3
+	 ushr	$T1.2d,$ACC0,#26
+	 and	$ACC0,$ACC0,$MASK.2d
+	add	$ACC4,$ACC4,$T0.2d	// h3 -> h4
+	bic	$H3,#0xfc,lsl#24	// &=0x03ffffff
+	 add	$ACC1,$ACC1,$T1.2d	// h0 -> h1
+
+	ushr	$T0.2d,$ACC4,#26
+	xtn	$H4,$ACC4
+	 ushr	$T1.2d,$ACC1,#26
+	 xtn	$H1,$ACC1
+	bic	$H4,#0xfc,lsl#24
+	 add	$ACC2,$ACC2,$T1.2d	// h1 -> h2
+
+	add	$ACC0,$ACC0,$T0.2d
+	shl	$T0.2d,$T0.2d,#2
+	 shrn	$T1.2s,$ACC2,#26
+	 xtn	$H2,$ACC2
+	add	$ACC0,$ACC0,$T0.2d	// h4 -> h0
+	 bic	$H1,#0xfc,lsl#24
+	 add	$H3,$H3,$T1.2s		// h2 -> h3
+	 bic	$H2,#0xfc,lsl#24
+
+	shrn	$T0.2s,$ACC0,#26
+	xtn	$H0,$ACC0
+	 ushr	$T1.2s,$H3,#26
+	 bic	$H3,#0xfc,lsl#24
+	 bic	$H0,#0xfc,lsl#24
+	add	$H1,$H1,$T0.2s		// h0 -> h1
+	 add	$H4,$H4,$T1.2s		// h3 -> h4
+
+	b.hi	.Loop_neon
+
+.Lskip_loop:
+	dup	$IN23_2,${IN23_2}[0]
+	add	$IN01_2,$IN01_2,$H2
+
+	////////////////////////////////////////////////////////////////
+	// multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	adds	$len,$len,#32
+	b.ne	.Long_tail
+
+	dup	$IN23_2,${IN01_2}[0]
+	add	$IN23_0,$IN01_0,$H0
+	add	$IN23_3,$IN01_3,$H3
+	add	$IN23_1,$IN01_1,$H1
+	add	$IN23_4,$IN01_4,$H4
+
+.Long_tail:
+	dup	$IN23_0,${IN23_0}[0]
+	umull2	$ACC0,$IN23_2,${S3}
+	umull2	$ACC3,$IN23_2,${R1}
+	umull2	$ACC4,$IN23_2,${R2}
+	umull2	$ACC2,$IN23_2,${R0}
+	umull2	$ACC1,$IN23_2,${S4}
+
+	dup	$IN23_1,${IN23_1}[0]
+	umlal2	$ACC0,$IN23_0,${R0}
+	umlal2	$ACC2,$IN23_0,${R2}
+	umlal2	$ACC3,$IN23_0,${R3}
+	umlal2	$ACC4,$IN23_0,${R4}
+	umlal2	$ACC1,$IN23_0,${R1}
+
+	dup	$IN23_3,${IN23_3}[0]
+	umlal2	$ACC0,$IN23_1,${S4}
+	umlal2	$ACC3,$IN23_1,${R2}
+	umlal2	$ACC2,$IN23_1,${R1}
+	umlal2	$ACC4,$IN23_1,${R3}
+	umlal2	$ACC1,$IN23_1,${R0}
+
+	dup	$IN23_4,${IN23_4}[0]
+	umlal2	$ACC3,$IN23_3,${R0}
+	umlal2	$ACC4,$IN23_3,${R1}
+	umlal2	$ACC0,$IN23_3,${S2}
+	umlal2	$ACC1,$IN23_3,${S3}
+	umlal2	$ACC2,$IN23_3,${S4}
+
+	umlal2	$ACC3,$IN23_4,${S4}
+	umlal2	$ACC0,$IN23_4,${S1}
+	umlal2	$ACC4,$IN23_4,${R0}
+	umlal2	$ACC1,$IN23_4,${S2}
+	umlal2	$ACC2,$IN23_4,${S3}
+
+	b.eq	.Lshort_tail
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	add	$IN01_0,$IN01_0,$H0
+	umlal	$ACC3,$IN01_2,${R1}
+	umlal	$ACC0,$IN01_2,${S3}
+	umlal	$ACC4,$IN01_2,${R2}
+	umlal	$ACC1,$IN01_2,${S4}
+	umlal	$ACC2,$IN01_2,${R0}
+
+	add	$IN01_1,$IN01_1,$H1
+	umlal	$ACC3,$IN01_0,${R3}
+	umlal	$ACC0,$IN01_0,${R0}
+	umlal	$ACC4,$IN01_0,${R4}
+	umlal	$ACC1,$IN01_0,${R1}
+	umlal	$ACC2,$IN01_0,${R2}
+
+	add	$IN01_3,$IN01_3,$H3
+	umlal	$ACC3,$IN01_1,${R2}
+	umlal	$ACC0,$IN01_1,${S4}
+	umlal	$ACC4,$IN01_1,${R3}
+	umlal	$ACC1,$IN01_1,${R0}
+	umlal	$ACC2,$IN01_1,${R1}
+
+	add	$IN01_4,$IN01_4,$H4
+	umlal	$ACC3,$IN01_3,${R0}
+	umlal	$ACC0,$IN01_3,${S2}
+	umlal	$ACC4,$IN01_3,${R1}
+	umlal	$ACC1,$IN01_3,${S3}
+	umlal	$ACC2,$IN01_3,${S4}
+
+	umlal	$ACC3,$IN01_4,${S4}
+	umlal	$ACC0,$IN01_4,${S1}
+	umlal	$ACC4,$IN01_4,${R0}
+	umlal	$ACC1,$IN01_4,${S2}
+	umlal	$ACC2,$IN01_4,${S3}
+
+.Lshort_tail:
+	////////////////////////////////////////////////////////////////
+	// horizontal add
+
+	addp	$ACC3,$ACC3,$ACC3
+	 ldp	d8,d9,[sp,#16]		// meet ABI requirements
+	addp	$ACC0,$ACC0,$ACC0
+	 ldp	d10,d11,[sp,#32]
+	addp	$ACC4,$ACC4,$ACC4
+	 ldp	d12,d13,[sp,#48]
+	addp	$ACC1,$ACC1,$ACC1
+	 ldp	d14,d15,[sp,#64]
+	addp	$ACC2,$ACC2,$ACC2
+
+	////////////////////////////////////////////////////////////////
+	// lazy reduction, but without narrowing
+
+	ushr	$T0.2d,$ACC3,#26
+	and	$ACC3,$ACC3,$MASK.2d
+	 ushr	$T1.2d,$ACC0,#26
+	 and	$ACC0,$ACC0,$MASK.2d
+
+	add	$ACC4,$ACC4,$T0.2d	// h3 -> h4
+	 add	$ACC1,$ACC1,$T1.2d	// h0 -> h1
+
+	ushr	$T0.2d,$ACC4,#26
+	and	$ACC4,$ACC4,$MASK.2d
+	 ushr	$T1.2d,$ACC1,#26
+	 and	$ACC1,$ACC1,$MASK.2d
+	 add	$ACC2,$ACC2,$T1.2d	// h1 -> h2
+
+	add	$ACC0,$ACC0,$T0.2d
+	shl	$T0.2d,$T0.2d,#2
+	 ushr	$T1.2d,$ACC2,#26
+	 and	$ACC2,$ACC2,$MASK.2d
+	add	$ACC0,$ACC0,$T0.2d	// h4 -> h0
+	 add	$ACC3,$ACC3,$T1.2d	// h2 -> h3
+
+	ushr	$T0.2d,$ACC0,#26
+	and	$ACC0,$ACC0,$MASK.2d
+	 ushr	$T1.2d,$ACC3,#26
+	 and	$ACC3,$ACC3,$MASK.2d
+	add	$ACC1,$ACC1,$T0.2d	// h0 -> h1
+	 add	$ACC4,$ACC4,$T1.2d	// h3 -> h4
+
+	////////////////////////////////////////////////////////////////
+	// write the result, can be partially reduced
+
+	st4	{$ACC0,$ACC1,$ACC2,$ACC3}[0],[$ctx],#16
+	st1	{$ACC4}[0],[$ctx]
+
+.Lno_data_neon:
+	ldr	x29,[sp],#80
+	ret
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.type	poly1305_emit_neon,%function
+.align	5
+poly1305_emit_neon:
+	ldr	$is_base2_26,[$ctx,#24]
+	cbz	$is_base2_26,poly1305_emit
+
+	ldp	w10,w11,[$ctx]		// load hash value base 2^26
+	ldp	w12,w13,[$ctx,#8]
+	ldr	w14,[$ctx,#16]
+
+	add	$h0,x10,x11,lsl#26	// base 2^26 -> base 2^64
+	lsr	$h1,x12,#12
+	adds	$h0,$h0,x12,lsl#52
+	add	$h1,$h1,x13,lsl#14
+	adc	$h1,$h1,xzr
+	lsr	$h2,x14,#24
+	adds	$h1,$h1,x14,lsl#40
+	adc	$h2,$h2,xzr		// can be partially reduced...
+
+	ldp	$t0,$t1,[$nonce]	// load nonce
+
+	and	$d0,$h2,#-4		// ... so reduce
+	add	$d0,$d0,$h2,lsr#2
+	and	$h2,$h2,#3
+	adds	$h0,$h0,$d0
+	adcs	$h1,$h1,xzr
+	adc	$h2,$h2,xzr
+
+	adds	$d0,$h0,#5		// compare to modulus
+	adcs	$d1,$h1,xzr
+	adc	$d2,$h2,xzr
+
+	tst	$d2,#-4			// see if it's carried/borrowed
+
+	csel	$h0,$h0,$d0,eq
+	csel	$h1,$h1,$d1,eq
+
+#ifdef	__AARCH64EB__
+	ror	$t0,$t0,#32		// flip nonce words
+	ror	$t1,$t1,#32
+#endif
+	adds	$h0,$h0,$t0		// accumulate nonce
+	adc	$h1,$h1,$t1
+#ifdef	__AARCH64EB__
+	rev	$h0,$h0			// flip output bytes
+	rev	$h1,$h1
+#endif
+	stp	$h0,$h1,[$mac]		// write result
+
+	ret
+.size	poly1305_emit_neon,.-poly1305_emit_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0
+#ifndef __KERNEL__
+.LOPENSSL_armcap_P:
+#ifdef	__ILP32__
+.long	OPENSSL_armcap_P-.
+#else
+.quad	OPENSSL_armcap_P-.
+#endif
+#endif
+.align	2
+___
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/\/\// and !/^$/);
+	print;
+}
+close SELF;
+
+foreach (split("\n",$code)) {
+	s/\b(shrn\s+v[0-9]+)\.[24]d/$1.2s/			or
+	s/\b(fmov\s+)v([0-9]+)[^,]*,\s*x([0-9]+)/$1d$2,x$3/	or
+	(m/\bdup\b/ and (s/\.[24]s/.2d/g or 1))			or
+	(m/\b(eor|and)/ and (s/\.[248][sdh]/.16b/g or 1))	or
+	(m/\bum(ul|la)l\b/ and (s/\.4s/.2s/g or 1))		or
+	(m/\bum(ul|la)l2\b/ and (s/\.2s/.4s/g or 1))		or
+	(m/\bst[1-4]\s+{[^}]+}\[/ and (s/\.[24]d/.s/g or 1));
+
+	s/\.[124]([sd])\[/.$1\[/;
+
+	print $_,"\n";
+}
+close STDOUT;
diff --git a/src/crypto/zinc/poly1305/poly1305-mips64.S b/src/crypto/zinc/poly1305/poly1305-mips64.S
deleted file mode 100644
index 272a86c..0000000
--- a/src/crypto/zinc/poly1305/poly1305-mips64.S
+++ /dev/null
@@ -1,360 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
-/*
- * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
- *
- * This is based in part on Andy Polyakov's implementation from CRYPTOGAMS.
- */
-
-#if (defined(_MIPS_ARCH_MIPS64R3) || defined(_MIPS_ARCH_MIPS64R5) || \
-     defined(_MIPS_ARCH_MIPS64R6)) && !defined(_MIPS_ARCH_MIPS64R2)
-#define _MIPS_ARCH_MIPS64R2
-#endif
-
-#ifdef __MIPSEB__
-#define MSB 0
-#define LSB 7
-#else
-#define MSB 7
-#define LSB 0
-#endif
-
-#if defined(_MIPS_ARCH_MIPS64R6)
-#define dmultu(rs,rt)
-#define mflo(rd,rs,rt)	dmulu	rd,rs,rt
-#define mfhi(rd,rs,rt)	dmuhu	rd,rs,rt
-#else
-#define dmultu(rs,rt)		dmultu	rs,rt
-#define multu(rs,rt)		multu	rs,rt
-#define mflo(rd,rs,rt)	mflo	rd
-#define mfhi(rd,rs,rt)	mfhi	rd
-#endif
-
-.text
-.set	noat
-.set	noreorder
-
-/* While most of the assembly in the kernel prefers ENTRY() and ENDPROC(),
- * there is no existing MIPS assembly that uses it, and MIPS assembler seems
- * to like its own .ent/.end notation, which the MIPS include files don't
- * provide in a MIPS-specific ENTRY/ENDPROC definition. So, we skip these
- * for now, until somebody complains. */
-
-.align	5
-.globl	poly1305_init_mips
-.ent	poly1305_init_mips
-poly1305_init_mips:
-	.frame	$29,0,$31
-	.set	reorder
-
-	sd	$0,0($4)
-	sd	$0,8($4)
-	sd	$0,16($4)
-
-	beqz	$5,.Lno_key
-
-#if defined(_MIPS_ARCH_MIPS64R6)
-	ld	$8,0($5)
-	ld	$9,8($5)
-#else
-	ldl	$8,0+MSB($5)
-	ldl	$9,8+MSB($5)
-	ldr	$8,0+LSB($5)
-	ldr	$9,8+LSB($5)
-#endif
-#ifdef	__MIPSEB__
-#if defined(_MIPS_ARCH_MIPS64R2)
-	dsbh	$8,$8		# byte swap
-	 dsbh	$9,$9
-	dshd	$8,$8
-	 dshd	$9,$9
-#else
-	ori	$10,$0,0xFF
-	dsll	$1,$10,32
-	or	$10,$1		# 0x000000FF000000FF
-
-	and	$11,$8,$10	# byte swap
-	 and	$2,$9,$10
-	dsrl	$1,$8,24
-	 dsrl	$24,$9,24
-	dsll	$11,24
-	 dsll	$2,24
-	and	$1,$10
-	 and	$24,$10
-	dsll	$10,8			# 0x0000FF000000FF00
-	or	$11,$1
-	 or	$2,$24
-	and	$1,$8,$10
-	 and	$24,$9,$10
-	dsrl	$8,8
-	 dsrl	$9,8
-	dsll	$1,8
-	 dsll	$24,8
-	and	$8,$10
-	 and	$9,$10
-	or	$11,$1
-	 or	$2,$24
-	or	$8,$11
-	 or	$9,$2
-	dsrl	$11,$8,32
-	 dsrl	$2,$9,32
-	dsll	$8,32
-	 dsll	$9,32
-	or	$8,$11
-	 or	$9,$2
-#endif
-#endif
-	li	$10,1
-	dsll	$10,32
-	daddiu	$10,-63
-	dsll	$10,28
-	daddiu	$10,-1		# 0ffffffc0fffffff
-
-	and	$8,$10
-	daddiu	$10,-3		# 0ffffffc0ffffffc
-	and	$9,$10
-
-	sd	$8,24($4)
-	dsrl	$10,$9,2
-	sd	$9,32($4)
-	daddu	$10,$9		# s1 = r1 + (r1 >> 2)
-	sd	$10,40($4)
-
-.Lno_key:
-	li	$2,0			# return 0
-	jr	$31
-.end	poly1305_init_mips
-
-.align	5
-.globl	poly1305_blocks_mips
-.ent	poly1305_blocks_mips
-poly1305_blocks_mips:
-	.set	noreorder
-	dsrl	$6,4			# number of complete blocks
-	bnez	$6,poly1305_blocks_internal
-	nop
-	jr	$31
-	nop
-.end	poly1305_blocks_mips
-
-.align	5
-.ent	poly1305_blocks_internal
-poly1305_blocks_internal:
-	.frame	$29,6*8,$31
-	.mask	0x00030000,-8
-	.set	noreorder
-	dsubu	$29,6*8
-	sd	$17,40($29)
-	sd	$16,32($29)
-	.set	reorder
-
-	ld	$12,0($4)		# load hash value
-	ld	$13,8($4)
-	ld	$14,16($4)
-
-	ld	$15,24($4)		# load key
-	ld	$16,32($4)
-	ld	$17,40($4)
-
-.Loop:
-#if defined(_MIPS_ARCH_MIPS64R6)
-	ld	$8,0($5)		# load input
-	ld	$9,8($5)
-#else
-	ldl	$8,0+MSB($5)	# load input
-	ldl	$9,8+MSB($5)
-	ldr	$8,0+LSB($5)
-	ldr	$9,8+LSB($5)
-#endif
-	daddiu	$6,-1
-	daddiu	$5,16
-#ifdef	__MIPSEB__
-#if defined(_MIPS_ARCH_MIPS64R2)
-	dsbh	$8,$8		# byte swap
-	 dsbh	$9,$9
-	dshd	$8,$8
-	 dshd	$9,$9
-#else
-	ori	$10,$0,0xFF
-	dsll	$1,$10,32
-	or	$10,$1		# 0x000000FF000000FF
-
-	and	$11,$8,$10	# byte swap
-	 and	$2,$9,$10
-	dsrl	$1,$8,24
-	 dsrl	$24,$9,24
-	dsll	$11,24
-	 dsll	$2,24
-	and	$1,$10
-	 and	$24,$10
-	dsll	$10,8			# 0x0000FF000000FF00
-	or	$11,$1
-	 or	$2,$24
-	and	$1,$8,$10
-	 and	$24,$9,$10
-	dsrl	$8,8
-	 dsrl	$9,8
-	dsll	$1,8
-	 dsll	$24,8
-	and	$8,$10
-	 and	$9,$10
-	or	$11,$1
-	 or	$2,$24
-	or	$8,$11
-	 or	$9,$2
-	dsrl	$11,$8,32
-	 dsrl	$2,$9,32
-	dsll	$8,32
-	 dsll	$9,32
-	or	$8,$11
-	 or	$9,$2
-#endif
-#endif
-	daddu	$12,$8		# accumulate input
-	daddu	$13,$9
-	sltu	$10,$12,$8
-	sltu	$11,$13,$9
-	daddu	$13,$10
-
-	dmultu	($15,$12)		# h0*r0
-	 daddu	$14,$7
-	 sltu	$10,$13,$10
-	mflo	($8,$15,$12)
-	mfhi	($9,$15,$12)
-
-	dmultu	($17,$13)		# h1*5*r1
-	 daddu	$10,$11
-	 daddu	$14,$10
-	mflo	($10,$17,$13)
-	mfhi	($11,$17,$13)
-
-	dmultu	($16,$12)		# h0*r1
-	 daddu	$8,$10
-	 daddu	$9,$11
-	mflo	($1,$16,$12)
-	mfhi	($25,$16,$12)
-	 sltu	$10,$8,$10
-	 daddu	$9,$10
-
-	dmultu	($15,$13)		# h1*r0
-	 daddu	$9,$1
-	 sltu	$1,$9,$1
-	mflo	($10,$15,$13)
-	mfhi	($11,$15,$13)
-	 daddu	$25,$1
-
-	dmultu	($17,$14)		# h2*5*r1
-	 daddu	$9,$10
-	 daddu	$25,$11
-	mflo	($1,$17,$14)
-
-	dmultu	($15,$14)		# h2*r0
-	 sltu	$10,$9,$10
-	 daddu	$25,$10
-	mflo	($2,$15,$14)
-
-	daddu	$9,$1
-	daddu	$25,$2
-	sltu	$1,$9,$1
-	daddu	$25,$1
-
-	li	$10,-4		# final reduction
-	and	$10,$25
-	dsrl	$11,$25,2
-	andi	$14,$25,3
-	daddu	$10,$11
-	daddu	$12,$8,$10
-	sltu	$10,$12,$10
-	daddu	$13,$9,$10
-	sltu	$10,$13,$10
-	daddu	$14,$14,$10
-
-	bnez	$6,.Loop
-
-	sd	$12,0($4)		# store hash value
-	sd	$13,8($4)
-	sd	$14,16($4)
-
-	.set	noreorder
-	ld	$17,40($29)		# epilogue
-	ld	$16,32($29)
-	jr	$31
-	daddu	$29,6*8
-.end	poly1305_blocks_internal
-
-.align	5
-.globl	poly1305_emit_mips
-.ent	poly1305_emit_mips
-poly1305_emit_mips:
-	.frame	$29,0,$31
-	.set	reorder
-
-	ld	$10,0($4)
-	ld	$11,8($4)
-	ld	$1,16($4)
-
-	daddiu	$8,$10,5		# compare to modulus
-	sltiu	$2,$8,5
-	daddu	$9,$11,$2
-	sltu	$2,$9,$2
-	daddu	$1,$1,$2
-
-	dsrl	$1,2			# see if it carried/borrowed
-	dsubu	$1,$0,$1
-	nor	$2,$0,$1
-
-	and	$8,$1
-	and	$10,$2
-	and	$9,$1
-	and	$11,$2
-	or	$8,$10
-	or	$9,$11
-
-	lwu	$10,0($6)		# load nonce
-	lwu	$11,4($6)
-	lwu	$1,8($6)
-	lwu	$2,12($6)
-	dsll	$11,32
-	dsll	$2,32
-	or	$10,$11
-	or	$1,$2
-
-	daddu	$8,$10		# accumulate nonce
-	daddu	$9,$1
-	sltu	$10,$8,$10
-	daddu	$9,$10
-
-	dsrl	$10,$8,8		# write mac value
-	dsrl	$11,$8,16
-	dsrl	$1,$8,24
-	sb	$8,0($5)
-	dsrl	$2,$8,32
-	sb	$10,1($5)
-	dsrl	$10,$8,40
-	sb	$11,2($5)
-	dsrl	$11,$8,48
-	sb	$1,3($5)
-	dsrl	$1,$8,56
-	sb	$2,4($5)
-	dsrl	$2,$9,8
-	sb	$10,5($5)
-	dsrl	$10,$9,16
-	sb	$11,6($5)
-	dsrl	$11,$9,24
-	sb	$1,7($5)
-
-	sb	$9,8($5)
-	dsrl	$1,$9,32
-	sb	$2,9($5)
-	dsrl	$2,$9,40
-	sb	$10,10($5)
-	dsrl	$10,$9,48
-	sb	$11,11($5)
-	dsrl	$11,$9,56
-	sb	$1,12($5)
-	sb	$2,13($5)
-	sb	$10,14($5)
-	sb	$11,15($5)
-
-	jr	$31
-.end	poly1305_emit_mips
diff --git a/src/crypto/zinc/poly1305/poly1305-mips64.pl b/src/crypto/zinc/poly1305/poly1305-mips64.pl
new file mode 100644
index 0000000..d30a03d
--- /dev/null
+++ b/src/crypto/zinc/poly1305/poly1305-mips64.pl
@@ -0,0 +1,467 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+#
+# This code is taken from the OpenSSL project but the author, Andy Polyakov,
+# has relicensed it under the licenses specified in the SPDX header above.
+# The original headers, including the original license headers, are
+# included below for completeness.
+#
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# Poly1305 hash for MIPS64.
+#
+# May 2016
+#
+# Numbers are cycles per processed byte with poly1305_blocks alone.
+#
+#		IALU/gcc
+# R1x000	5.64/+120%	(big-endian)
+# Octeon II	3.80/+280%	(little-endian)
+
+######################################################################
+# There is a number of MIPS ABI in use, O32 and N32/64 are most
+# widely used. Then there is a new contender: NUBI. It appears that if
+# one picks the latter, it's possible to arrange code in ABI neutral
+# manner. Therefore let's stick to NUBI register layout:
+#
+($zero,$at,$t0,$t1,$t2)=map("\$$_",(0..2,24,25));
+($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11));
+($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7,$s8,$s9,$s10,$s11)=map("\$$_",(12..23));
+($gp,$tp,$sp,$fp,$ra)=map("\$$_",(3,28..31));
+#
+# The return value is placed in $a0. Following coding rules facilitate
+# interoperability:
+#
+# - never ever touch $tp, "thread pointer", former $gp [o32 can be
+#   excluded from the rule, because it's specified volatile];
+# - copy return value to $t0, former $v0 [or to $a0 if you're adapting
+#   old code];
+# - on O32 populate $a4-$a7 with 'lw $aN,4*N($sp)' if necessary;
+#
+# For reference here is register layout for N32/64 MIPS ABIs:
+#
+# ($zero,$at,$v0,$v1)=map("\$$_",(0..3));
+# ($a0,$a1,$a2,$a3,$a4,$a5,$a6,$a7)=map("\$$_",(4..11));
+# ($t0,$t1,$t2,$t3,$t8,$t9)=map("\$$_",(12..15,24,25));
+# ($s0,$s1,$s2,$s3,$s4,$s5,$s6,$s7)=map("\$$_",(16..23));
+# ($gp,$sp,$fp,$ra)=map("\$$_",(28..31));
+#
+# <appro@openssl.org>
+#
+######################################################################
+
+$flavour = shift || "64"; # supported flavours are o32,n32,64,nubi32,nubi64
+
+die "MIPS64 only" unless ($flavour =~ /64|n32/i);
+
+$v0 = ($flavour =~ /nubi/i) ? $a0 : $t0;
+$SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? "0x0003f000" : "0x00030000";
+
+($ctx,$inp,$len,$padbit) = ($a0,$a1,$a2,$a3);
+($in0,$in1,$tmp0,$tmp1,$tmp2,$tmp3,$tmp4) = ($a4,$a5,$a6,$a7,$at,$t0,$t1);
+
+$code.=<<___;
+#if (defined(_MIPS_ARCH_MIPS64R3) || defined(_MIPS_ARCH_MIPS64R5) || \\
+     defined(_MIPS_ARCH_MIPS64R6)) \\
+     && !defined(_MIPS_ARCH_MIPS64R2)
+# define _MIPS_ARCH_MIPS64R2
+#endif
+
+#if defined(_MIPS_ARCH_MIPS64R6)
+# define dmultu(rs,rt)
+# define mflo(rd,rs,rt)	dmulu	rd,rs,rt
+# define mfhi(rd,rs,rt)	dmuhu	rd,rs,rt
+#else
+# define dmultu(rs,rt)		dmultu	rs,rt
+# define mflo(rd,rs,rt)	mflo	rd
+# define mfhi(rd,rs,rt)	mfhi	rd
+#endif
+
+#ifdef	__KERNEL__
+# define poly1305_init   poly1305_init_mips
+# define poly1305_blocks poly1305_blocks_mips
+# define poly1305_emit   poly1305_emit_mips
+#endif
+
+#if defined(__MIPSEB__) && !defined(MIPSEB)
+# define MIPSEB
+#endif
+
+#ifdef MIPSEB
+# define MSB 0
+# define LSB 7
+#else
+# define MSB 7
+# define LSB 0
+#endif
+
+.text
+.set	noat
+.set	noreorder
+
+.align	5
+.globl	poly1305_init
+.ent	poly1305_init
+poly1305_init:
+	.frame	$sp,0,$ra
+	.set	reorder
+
+	sd	$zero,0($ctx)
+	sd	$zero,8($ctx)
+	sd	$zero,16($ctx)
+
+	beqz	$inp,.Lno_key
+
+#if defined(_MIPS_ARCH_MIPS64R6)
+	ld	$in0,0($inp)
+	ld	$in1,8($inp)
+#else
+	ldl	$in0,0+MSB($inp)
+	ldl	$in1,8+MSB($inp)
+	ldr	$in0,0+LSB($inp)
+	ldr	$in1,8+LSB($inp)
+#endif
+#ifdef	MIPSEB
+# if defined(_MIPS_ARCH_MIPS64R2)
+	dsbh	$in0,$in0		# byte swap
+	 dsbh	$in1,$in1
+	dshd	$in0,$in0
+	 dshd	$in1,$in1
+# else
+	ori	$tmp0,$zero,0xFF
+	dsll	$tmp2,$tmp0,32
+	or	$tmp0,$tmp2		# 0x000000FF000000FF
+
+	and	$tmp1,$in0,$tmp0	# byte swap
+	 and	$tmp3,$in1,$tmp0
+	dsrl	$tmp2,$in0,24
+	 dsrl	$tmp4,$in1,24
+	dsll	$tmp1,24
+	 dsll	$tmp3,24
+	and	$tmp2,$tmp0
+	 and	$tmp4,$tmp0
+	dsll	$tmp0,8			# 0x0000FF000000FF00
+	or	$tmp1,$tmp2
+	 or	$tmp3,$tmp4
+	and	$tmp2,$in0,$tmp0
+	 and	$tmp4,$in1,$tmp0
+	dsrl	$in0,8
+	 dsrl	$in1,8
+	dsll	$tmp2,8
+	 dsll	$tmp4,8
+	and	$in0,$tmp0
+	 and	$in1,$tmp0
+	or	$tmp1,$tmp2
+	 or	$tmp3,$tmp4
+	or	$in0,$tmp1
+	 or	$in1,$tmp3
+	dsrl	$tmp1,$in0,32
+	 dsrl	$tmp3,$in1,32
+	dsll	$in0,32
+	 dsll	$in1,32
+	or	$in0,$tmp1
+	 or	$in1,$tmp3
+# endif
+#endif
+	li	$tmp0,1
+	dsll	$tmp0,32
+	daddiu	$tmp0,-63
+	dsll	$tmp0,28
+	daddiu	$tmp0,-1		# 0ffffffc0fffffff
+
+	and	$in0,$tmp0
+	daddiu	$tmp0,-3		# 0ffffffc0ffffffc
+	and	$in1,$tmp0
+
+	sd	$in0,24($ctx)
+	dsrl	$tmp0,$in1,2
+	sd	$in1,32($ctx)
+	daddu	$tmp0,$in1		# s1 = r1 + (r1 >> 2)
+	sd	$tmp0,40($ctx)
+
+.Lno_key:
+	li	$v0,0			# return 0
+	jr	$ra
+.end	poly1305_init
+___
+{
+my ($h0,$h1,$h2,$r0,$r1,$s1,$d0,$d1,$d2) =
+   ($s0,$s1,$s2,$s3,$s4,$s5,$in0,$in1,$t2);
+
+$code.=<<___;
+.align	5
+.globl	poly1305_blocks
+.ent	poly1305_blocks
+poly1305_blocks:
+	.set	noreorder
+	dsrl	$len,4			# number of complete blocks
+	bnez	$len,poly1305_blocks_internal
+	nop
+	jr	$ra
+	nop
+.end	poly1305_blocks
+
+.align	5
+.ent	poly1305_blocks_internal
+poly1305_blocks_internal:
+	.frame	$sp,6*8,$ra
+	.mask	$SAVED_REGS_MASK,-8
+	.set	noreorder
+	dsubu	$sp,6*8
+	sd	$s5,40($sp)
+	sd	$s4,32($sp)
+___
+$code.=<<___ if ($flavour =~ /nubi/i);	# optimize non-nubi prologue
+	sd	$s3,24($sp)
+	sd	$s2,16($sp)
+	sd	$s1,8($sp)
+	sd	$s0,0($sp)
+___
+$code.=<<___;
+	.set	reorder
+
+	ld	$h0,0($ctx)		# load hash value
+	ld	$h1,8($ctx)
+	ld	$h2,16($ctx)
+
+	ld	$r0,24($ctx)		# load key
+	ld	$r1,32($ctx)
+	ld	$s1,40($ctx)
+
+.Loop:
+#if defined(_MIPS_ARCH_MIPS64R6)
+	ld	$in0,0($inp)		# load input
+	ld	$in1,8($inp)
+#else
+	ldl	$in0,0+MSB($inp)	# load input
+	ldl	$in1,8+MSB($inp)
+	ldr	$in0,0+LSB($inp)
+	ldr	$in1,8+LSB($inp)
+#endif
+	daddiu	$len,-1
+	daddiu	$inp,16
+#ifdef	MIPSEB
+# if defined(_MIPS_ARCH_MIPS64R2)
+	dsbh	$in0,$in0		# byte swap
+	 dsbh	$in1,$in1
+	dshd	$in0,$in0
+	 dshd	$in1,$in1
+# else
+	ori	$tmp0,$zero,0xFF
+	dsll	$tmp2,$tmp0,32
+	or	$tmp0,$tmp2		# 0x000000FF000000FF
+
+	and	$tmp1,$in0,$tmp0	# byte swap
+	 and	$tmp3,$in1,$tmp0
+	dsrl	$tmp2,$in0,24
+	 dsrl	$tmp4,$in1,24
+	dsll	$tmp1,24
+	 dsll	$tmp3,24
+	and	$tmp2,$tmp0
+	 and	$tmp4,$tmp0
+	dsll	$tmp0,8			# 0x0000FF000000FF00
+	or	$tmp1,$tmp2
+	 or	$tmp3,$tmp4
+	and	$tmp2,$in0,$tmp0
+	 and	$tmp4,$in1,$tmp0
+	dsrl	$in0,8
+	 dsrl	$in1,8
+	dsll	$tmp2,8
+	 dsll	$tmp4,8
+	and	$in0,$tmp0
+	 and	$in1,$tmp0
+	or	$tmp1,$tmp2
+	 or	$tmp3,$tmp4
+	or	$in0,$tmp1
+	 or	$in1,$tmp3
+	dsrl	$tmp1,$in0,32
+	 dsrl	$tmp3,$in1,32
+	dsll	$in0,32
+	 dsll	$in1,32
+	or	$in0,$tmp1
+	 or	$in1,$tmp3
+# endif
+#endif
+	daddu	$h0,$in0		# accumulate input
+	daddu	$h1,$in1
+	sltu	$tmp0,$h0,$in0
+	sltu	$tmp1,$h1,$in1
+	daddu	$h1,$tmp0
+
+	dmultu	($r0,$h0)		# h0*r0
+	 daddu	$h2,$padbit
+	 sltu	$tmp0,$h1,$tmp0
+	mflo	($d0,$r0,$h0)
+	mfhi	($d1,$r0,$h0)
+
+	dmultu	($s1,$h1)		# h1*5*r1
+	 daddu	$tmp0,$tmp1
+	 daddu	$h2,$tmp0
+	mflo	($tmp0,$s1,$h1)
+	mfhi	($tmp1,$s1,$h1)
+
+	dmultu	($r1,$h0)		# h0*r1
+	 daddu	$d0,$tmp0
+	 daddu	$d1,$tmp1
+	mflo	($tmp2,$r1,$h0)
+	mfhi	($d2,$r1,$h0)
+	 sltu	$tmp0,$d0,$tmp0
+	 daddu	$d1,$tmp0
+
+	dmultu	($r0,$h1)		# h1*r0
+	 daddu	$d1,$tmp2
+	 sltu	$tmp2,$d1,$tmp2
+	mflo	($tmp0,$r0,$h1)
+	mfhi	($tmp1,$r0,$h1)
+	 daddu	$d2,$tmp2
+
+	dmultu	($s1,$h2)		# h2*5*r1
+	 daddu	$d1,$tmp0
+	 daddu	$d2,$tmp1
+	mflo	($tmp2,$s1,$h2)
+
+	dmultu	($r0,$h2)		# h2*r0
+	 sltu	$tmp0,$d1,$tmp0
+	 daddu	$d2,$tmp0
+	mflo	($tmp3,$r0,$h2)
+
+	daddu	$d1,$tmp2
+	daddu	$d2,$tmp3
+	sltu	$tmp2,$d1,$tmp2
+	daddu	$d2,$tmp2
+
+	li	$tmp0,-4		# final reduction
+	and	$tmp0,$d2
+	dsrl	$tmp1,$d2,2
+	andi	$h2,$d2,3
+	daddu	$tmp0,$tmp1
+	daddu	$h0,$d0,$tmp0
+	sltu	$tmp0,$h0,$tmp0
+	daddu	$h1,$d1,$tmp0
+	sltu	$tmp0,$h1,$tmp0
+	daddu	$h2,$h2,$tmp0
+
+	bnez	$len,.Loop
+
+	sd	$h0,0($ctx)		# store hash value
+	sd	$h1,8($ctx)
+	sd	$h2,16($ctx)
+
+	.set	noreorder
+	ld	$s5,40($sp)		# epilogue
+	ld	$s4,32($sp)
+___
+$code.=<<___ if ($flavour =~ /nubi/i);	# optimize non-nubi epilogue
+	ld	$s3,24($sp)
+	ld	$s2,16($sp)
+	ld	$s1,8($sp)
+	ld	$s0,0($sp)
+___
+$code.=<<___;
+	jr	$ra
+	daddu	$sp,6*8
+.end	poly1305_blocks_internal
+___
+}
+{
+my ($ctx,$mac,$nonce) = ($a0,$a1,$a2);
+
+$code.=<<___;
+.align	5
+.globl	poly1305_emit
+.ent	poly1305_emit
+poly1305_emit:
+	.frame	$sp,0,$ra
+	.set	reorder
+
+	ld	$tmp0,0($ctx)
+	ld	$tmp1,8($ctx)
+	ld	$tmp2,16($ctx)
+
+	daddiu	$in0,$tmp0,5		# compare to modulus
+	sltiu	$tmp3,$in0,5
+	daddu	$in1,$tmp1,$tmp3
+	sltu	$tmp3,$in1,$tmp3
+	daddu	$tmp2,$tmp2,$tmp3
+
+	dsrl	$tmp2,2			# see if it carried/borrowed
+	dsubu	$tmp2,$zero,$tmp2
+	nor	$tmp3,$zero,$tmp2
+
+	and	$in0,$tmp2
+	and	$tmp0,$tmp3
+	and	$in1,$tmp2
+	and	$tmp1,$tmp3
+	or	$in0,$tmp0
+	or	$in1,$tmp1
+
+	lwu	$tmp0,0($nonce)		# load nonce
+	lwu	$tmp1,4($nonce)
+	lwu	$tmp2,8($nonce)
+	lwu	$tmp3,12($nonce)
+	dsll	$tmp1,32
+	dsll	$tmp3,32
+	or	$tmp0,$tmp1
+	or	$tmp2,$tmp3
+
+	daddu	$in0,$tmp0		# accumulate nonce
+	daddu	$in1,$tmp2
+	sltu	$tmp0,$in0,$tmp0
+	daddu	$in1,$tmp0
+
+	dsrl	$tmp0,$in0,8		# write mac value
+	dsrl	$tmp1,$in0,16
+	dsrl	$tmp2,$in0,24
+	sb	$in0,0($mac)
+	dsrl	$tmp3,$in0,32
+	sb	$tmp0,1($mac)
+	dsrl	$tmp0,$in0,40
+	sb	$tmp1,2($mac)
+	dsrl	$tmp1,$in0,48
+	sb	$tmp2,3($mac)
+	dsrl	$tmp2,$in0,56
+	sb	$tmp3,4($mac)
+	dsrl	$tmp3,$in1,8
+	sb	$tmp0,5($mac)
+	dsrl	$tmp0,$in1,16
+	sb	$tmp1,6($mac)
+	dsrl	$tmp1,$in1,24
+	sb	$tmp2,7($mac)
+
+	sb	$in1,8($mac)
+	dsrl	$tmp2,$in1,32
+	sb	$tmp3,9($mac)
+	dsrl	$tmp3,$in1,40
+	sb	$tmp0,10($mac)
+	dsrl	$tmp0,$in1,48
+	sb	$tmp1,11($mac)
+	dsrl	$tmp1,$in1,56
+	sb	$tmp2,12($mac)
+	sb	$tmp3,13($mac)
+	sb	$tmp0,14($mac)
+	sb	$tmp1,15($mac)
+
+	jr	$ra
+.end	poly1305_emit
+.rdata
+.align	2
+___
+}
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/\/\// and !/^$/);
+	print;
+}
+close SELF;
+
+$output=pop and open STDOUT,">$output";
+print $code;
+close STDOUT;
+
diff --git a/src/tests/qemu/Makefile b/src/tests/qemu/Makefile
index e511b69..e20509f 100644
--- a/src/tests/qemu/Makefile
+++ b/src/tests/qemu/Makefile
@@ -23,7 +23,7 @@ NR_CPUS ?= 4
 MIRROR := https://download.wireguard.com/qemu-test/distfiles/
 
 rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
-WIREGUARD_SOURCES := ../../Kbuild ../../Kconfig $(filter-out ../../tools/% ../../tests/%,$(call rwildcard,../../,*.c *.h *.S *.include))
+WIREGUARD_SOURCES := ../../Kbuild ../../Kconfig $(filter-out ../../tools/% ../../tests/%,$(call rwildcard,../../,*.c *.h *.S *.pl *.include))
 TOOLS_SOURCES := $(wildcard ../../tools/*.c ../../tools/*.h ../../uapi/*.h ../../crypto/zinc/curve25519/curve25519-hacl64.c ../../crypto/zinc/curve25519/curve25519-fiat32.c)
 
 default: qemu