[PATCH net-next v3 04/17] zinc: ChaCha20 ARM and ARM64 implementations

[Jason A. Donenfeld]

These NEON and non-NEON implementations come from Andy Polyakov's
implementation, with several modifications for being friendly to kernel
space.

Signed-off-by: Jason A. Donenfeld <Jason@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Samuel Neves <sneves@xxxxxxxxx>
Cc: Jean-Philippe Aumasson <jeanphilippe.aumasson@xxxxxxxxx>
Cc: Andy Polyakov <appro@xxxxxxxxxxx>
Cc: Russell King <linux@xxxxxxxxxxxxxxx>
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Cc: linux-crypto@xxxxxxxxxxxxxxx
---
 lib/zinc/Makefile                     |    8 +
 lib/zinc/chacha20/chacha20-arm-glue.h |   50 +
 lib/zinc/chacha20/chacha20-arm.S      | 1473 +++++++++++++++++++
 lib/zinc/chacha20/chacha20-arm64.S    | 1942 +++++++++++++++++++++++++
 4 files changed, 3473 insertions(+)
 create mode 100644 lib/zinc/chacha20/chacha20-arm-glue.h
 create mode 100644 lib/zinc/chacha20/chacha20-arm.S
 create mode 100644 lib/zinc/chacha20/chacha20-arm64.S

diff --git a/lib/zinc/Makefile b/lib/zinc/Makefile
index 0b5a964bfba6..3f7f8a44e246 100644
--- a/lib/zinc/Makefile
+++ b/lib/zinc/Makefile
@@ -5,6 +5,14 @@ ccflags-$(CONFIG_ZINC_DEBUG) += -DDEBUG
 
 ifeq ($(CONFIG_ZINC_CHACHA20),y)
 zinc-y += chacha20/chacha20.o
+ifeq ($(CONFIG_ARM),y)
+zinc-y += chacha20/chacha20-arm.o
+CFLAGS_chacha20.o += -include $(srctree)/$(src)/chacha20/chacha20-arm-glue.h
+endif
+ifeq ($(CONFIG_ARM64),y)
+zinc-y += chacha20/chacha20-arm64.o
+CFLAGS_chacha20.o += -include $(srctree)/$(src)/chacha20/chacha20-arm-glue.h
+endif
 endif
 
 zinc-y += main.o
diff --git a/lib/zinc/chacha20/chacha20-arm-glue.h b/lib/zinc/chacha20/chacha20-arm-glue.h
new file mode 100644
index 000000000000..d32361514f3a
--- /dev/null
+++ b/lib/zinc/chacha20/chacha20-arm-glue.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved.
+ */
+
+#include <zinc/chacha20.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+
+asmlinkage void chacha20_arm(u8 *out, const u8 *in, const size_t len,
+			     const u32 key[8], const u32 counter[4]);
+#if IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&                                     \
+	(defined(CONFIG_64BIT) || __LINUX_ARM_ARCH__ >= 7)
+#define ARM_USE_NEON
+asmlinkage void chacha20_neon(u8 *out, const u8 *in, const size_t len,
+			      const u32 key[8], const u32 counter[4]);
+#endif
+
+static bool chacha20_use_neon __ro_after_init;
+
+void __init chacha20_fpu_init(void)
+{
+#if defined(CONFIG_ARM64)
+	chacha20_use_neon = elf_hwcap & HWCAP_ASIMD;
+#elif defined(CONFIG_ARM)
+	chacha20_use_neon = elf_hwcap & HWCAP_NEON;
+#endif
+}
+
+static inline bool chacha20_arch(u8 *dst, const u8 *src, const size_t len,
+				 const u32 key[8], const u32 counter[4],
+				 simd_context_t simd_context)
+{
+#if defined(ARM_USE_NEON)
+	if (simd_context == HAVE_FULL_SIMD && chacha20_use_neon) {
+		chacha20_neon(dst, src, len, key, counter);
+		return true;
+	}
+#endif
+	chacha20_arm(dst, src, len, key, counter);
+	return true;
+}
+
+static inline bool hchacha20_arch(u8 *derived_key, const u8 *nonce,
+				  const u8 *key, simd_context_t simd_context)
+{
+	return false;
+}
+
+#define HAVE_CHACHA20_ARCH_IMPLEMENTATION
diff --git a/lib/zinc/chacha20/chacha20-arm.S b/lib/zinc/chacha20/chacha20-arm.S
new file mode 100644
index 000000000000..4336524094d1
--- /dev/null
+++ b/lib/zinc/chacha20/chacha20-arm.S
@@ -0,0 +1,1473 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved.
+ * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@xxxxxxxxxxx>. All Rights Reserved.
+ *
+ * This is based in part on Andy Polyakov's implementation from CRYPTOGAMS.
+ */
+
+#include <linux/linkage.h>
+
+.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	5
+.Lsigma:
+.long	0x61707865,0x3320646e,0x79622d32,0x6b206574	@ endian-neutral
+.Lone:
+.long	1,0,0,0
+.word -1
+
+#if __LINUX_ARM_ARCH__ >= 7 && IS_ENABLED(CONFIG_KERNEL_MODE_NEON)
+.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
+	cmp		r2,#192			@ test len
+	bls		.Lshort
+.Lchacha20_neon_begin:
+	adr		r14,.Lsigma
+	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
+	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
+	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
+	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)]
+	vadd.i32	q7,q3,q12		@ counter+1
+	ldr		r12,[sp,#4*(12)]	@ modulo-scheduled load
+	vmov		q6,q2
+	ldr		r10, [sp,#4*(13)]
+	vmov		q10,q2
+	ldr		r14,[sp,#4*(14)]
+	vadd.i32	q11,q7,q12		@ counter+2
+	str		r11, [sp,#4*(16+15)]
+	mov		r11,#10
+	add		r12,r12,#3	@ counter+3
+	b		.Loop_neon
+
+.align	4
+.Loop_neon:
+	subs		r11,r11,#1
+	vadd.i32	q0,q0,q1
+	add	r0,r0,r4
+	vadd.i32	q4,q4,q5
+	mov	r12,r12,ror#16
+	vadd.i32	q8,q8,q9
+	add	r1,r1,r5
+	veor	q3,q3,q0
+	mov	r10,r10,ror#16
+	veor	q7,q7,q4
+	eor	r12,r12,r0,ror#16
+	veor	q11,q11,q8
+	eor	r10,r10,r1,ror#16
+	vrev32.16	q3,q3
+	add	r8,r8,r12
+	vrev32.16	q7,q7
+	mov	r4,r4,ror#20
+	vrev32.16	q11,q11
+	add	r9,r9,r10
+	vadd.i32	q2,q2,q3
+	mov	r5,r5,ror#20
+	vadd.i32	q6,q6,q7
+	eor	r4,r4,r8,ror#20
+	vadd.i32	q10,q10,q11
+	eor	r5,r5,r9,ror#20
+	veor	q12,q1,q2
+	add	r0,r0,r4
+	veor	q13,q5,q6
+	mov	r12,r12,ror#24
+	veor	q14,q9,q10
+	add	r1,r1,r5
+	vshr.u32	q1,q12,#20
+	mov	r10,r10,ror#24
+	vshr.u32	q5,q13,#20
+	eor	r12,r12,r0,ror#24
+	vshr.u32	q9,q14,#20
+	eor	r10,r10,r1,ror#24
+	vsli.32	q1,q12,#12
+	add	r8,r8,r12
+	vsli.32	q5,q13,#12
+	mov	r4,r4,ror#25
+	vsli.32	q9,q14,#12
+	add	r9,r9,r10
+	vadd.i32	q0,q0,q1
+	mov	r5,r5,ror#25
+	vadd.i32	q4,q4,q5
+	str	r10,[sp,#4*(16+13)]
+	vadd.i32	q8,q8,q9
+	ldr	r10,[sp,#4*(16+15)]
+	veor	q12,q3,q0
+	eor	r4,r4,r8,ror#25
+	veor	q13,q7,q4
+	eor	r5,r5,r9,ror#25
+	veor	q14,q11,q8
+	str	r8,[sp,#4*(16+8)]
+	vshr.u32	q3,q12,#24
+	ldr	r8,[sp,#4*(16+10)]
+	vshr.u32	q7,q13,#24
+	add	r2,r2,r6
+	vshr.u32	q11,q14,#24
+	mov	r14,r14,ror#16
+	vsli.32	q3,q12,#8
+	str	r9,[sp,#4*(16+9)]
+	vsli.32	q7,q13,#8
+	ldr	r9,[sp,#4*(16+11)]
+	vsli.32	q11,q14,#8
+	add	r3,r3,r7
+	vadd.i32	q2,q2,q3
+	mov	r10,r10,ror#16
+	vadd.i32	q6,q6,q7
+	eor	r14,r14,r2,ror#16
+	vadd.i32	q10,q10,q11
+	eor	r10,r10,r3,ror#16
+	veor	q12,q1,q2
+	add	r8,r8,r14
+	veor	q13,q5,q6
+	mov	r6,r6,ror#20
+	veor	q14,q9,q10
+	add	r9,r9,r10
+	vshr.u32	q1,q12,#25
+	mov	r7,r7,ror#20
+	vshr.u32	q5,q13,#25
+	eor	r6,r6,r8,ror#20
+	vshr.u32	q9,q14,#25
+	eor	r7,r7,r9,ror#20
+	vsli.32	q1,q12,#7
+	add	r2,r2,r6
+	vsli.32	q5,q13,#7
+	mov	r14,r14,ror#24
+	vsli.32	q9,q14,#7
+	add	r3,r3,r7
+	vext.8	q2,q2,q2,#8
+	mov	r10,r10,ror#24
+	vext.8	q6,q6,q6,#8
+	eor	r14,r14,r2,ror#24
+	vext.8	q10,q10,q10,#8
+	eor	r10,r10,r3,ror#24
+	vext.8	q1,q1,q1,#4
+	add	r8,r8,r14
+	vext.8	q5,q5,q5,#4
+	mov	r6,r6,ror#25
+	vext.8	q9,q9,q9,#4
+	add	r9,r9,r10
+	vext.8	q3,q3,q3,#12
+	mov	r7,r7,ror#25
+	vext.8	q7,q7,q7,#12
+	eor	r6,r6,r8,ror#25
+	vext.8	q11,q11,q11,#12
+	eor	r7,r7,r9,ror#25
+	vadd.i32	q0,q0,q1
+	add	r0,r0,r5
+	vadd.i32	q4,q4,q5
+	mov	r10,r10,ror#16
+	vadd.i32	q8,q8,q9
+	add	r1,r1,r6
+	veor	q3,q3,q0
+	mov	r12,r12,ror#16
+	veor	q7,q7,q4
+	eor	r10,r10,r0,ror#16
+	veor	q11,q11,q8
+	eor	r12,r12,r1,ror#16
+	vrev32.16	q3,q3
+	add	r8,r8,r10
+	vrev32.16	q7,q7
+	mov	r5,r5,ror#20
+	vrev32.16	q11,q11
+	add	r9,r9,r12
+	vadd.i32	q2,q2,q3
+	mov	r6,r6,ror#20
+	vadd.i32	q6,q6,q7
+	eor	r5,r5,r8,ror#20
+	vadd.i32	q10,q10,q11
+	eor	r6,r6,r9,ror#20
+	veor	q12,q1,q2
+	add	r0,r0,r5
+	veor	q13,q5,q6
+	mov	r10,r10,ror#24
+	veor	q14,q9,q10
+	add	r1,r1,r6
+	vshr.u32	q1,q12,#20
+	mov	r12,r12,ror#24
+	vshr.u32	q5,q13,#20
+	eor	r10,r10,r0,ror#24
+	vshr.u32	q9,q14,#20
+	eor	r12,r12,r1,ror#24
+	vsli.32	q1,q12,#12
+	add	r8,r8,r10
+	vsli.32	q5,q13,#12
+	mov	r5,r5,ror#25
+	vsli.32	q9,q14,#12
+	str	r10,[sp,#4*(16+15)]
+	vadd.i32	q0,q0,q1
+	ldr	r10,[sp,#4*(16+13)]
+	vadd.i32	q4,q4,q5
+	add	r9,r9,r12
+	vadd.i32	q8,q8,q9
+	mov	r6,r6,ror#25
+	veor	q12,q3,q0
+	eor	r5,r5,r8,ror#25
+	veor	q13,q7,q4
+	eor	r6,r6,r9,ror#25
+	veor	q14,q11,q8
+	str	r8,[sp,#4*(16+10)]
+	vshr.u32	q3,q12,#24
+	ldr	r8,[sp,#4*(16+8)]
+	vshr.u32	q7,q13,#24
+	add	r2,r2,r7
+	vshr.u32	q11,q14,#24
+	mov	r10,r10,ror#16
+	vsli.32	q3,q12,#8
+	str	r9,[sp,#4*(16+11)]
+	vsli.32	q7,q13,#8
+	ldr	r9,[sp,#4*(16+9)]
+	vsli.32	q11,q14,#8
+	add	r3,r3,r4
+	vadd.i32	q2,q2,q3
+	mov	r14,r14,ror#16
+	vadd.i32	q6,q6,q7
+	eor	r10,r10,r2,ror#16
+	vadd.i32	q10,q10,q11
+	eor	r14,r14,r3,ror#16
+	veor	q12,q1,q2
+	add	r8,r8,r10
+	veor	q13,q5,q6
+	mov	r7,r7,ror#20
+	veor	q14,q9,q10
+	add	r9,r9,r14
+	vshr.u32	q1,q12,#25
+	mov	r4,r4,ror#20
+	vshr.u32	q5,q13,#25
+	eor	r7,r7,r8,ror#20
+	vshr.u32	q9,q14,#25
+	eor	r4,r4,r9,ror#20
+	vsli.32	q1,q12,#7
+	add	r2,r2,r7
+	vsli.32	q5,q13,#7
+	mov	r10,r10,ror#24
+	vsli.32	q9,q14,#7
+	add	r3,r3,r4
+	vext.8	q2,q2,q2,#8
+	mov	r14,r14,ror#24
+	vext.8	q6,q6,q6,#8
+	eor	r10,r10,r2,ror#24
+	vext.8	q10,q10,q10,#8
+	eor	r14,r14,r3,ror#24
+	vext.8	q1,q1,q1,#12
+	add	r8,r8,r10
+	vext.8	q5,q5,q5,#12
+	mov	r7,r7,ror#25
+	vext.8	q9,q9,q9,#12
+	add	r9,r9,r14
+	vext.8	q3,q3,q3,#4
+	mov	r4,r4,ror#25
+	vext.8	q7,q7,q7,#4
+	eor	r7,r7,r8,ror#25
+	vext.8	q11,q11,q11,#4
+	eor	r4,r4,r9,ror#25
+	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,r4,r8	@ accumulate key material
+	ldr		r8,[r12],#16		@ load input
+	add		r5,r5,r9
+	ldr		r9,[r12,#-12]
+	add		r6,r6,r10
+	ldr		r10,[r12,#-8]
+	add		r7,r7,r11
+	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,r4,r8	@ accumulate key material
+	 add		r8,r8,#4		@ next counter value
+	add		r5,r5,r9
+	 str		r8,[sp,#4*(12)]	@ save next counter value
+	ldr		r8,[r12],#16		@ load input
+	add		r6,r6,r10
+	 add		r4,r4,#3		@ counter+3
+	ldr		r9,[r12,#-12]
+	add		r7,r7,r11
+	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)]
+	ldr		r12,[sp,#4*(12)]		@ modulo-scheduled load
+	ldr		r10, [sp,#4*(13)]
+	ldr		r14,[sp,#4*(14)]
+	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,r4,r8	@ accumulate key material
+	 add		r8,sp,#4*(8)
+	add		r5,r5,r9
+	add		r6,r6,r10
+	add		r7,r7,r11
+	 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,r4,r8	@ accumulate key material
+	 add		r8,sp,#4*(8)
+	add		r5,r5,r9
+	 add		r4,r4,#3		@ counter+3
+	add		r6,r6,r10
+	add		r7,r7,r11
+	 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
+
+.align	5
+.Lsigma2:
+.long	0x61707865,0x3320646e,0x79622d32,0x6b206574	@ endian-neutral
+.Lone2:
+.long	1,0,0,0
+.word -1
+
+.align	5
+ENTRY(chacha20_arm)
+	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_arm
+.Lshort:
+	ldmia	r12,{r4-r7}		@ load counter and nonce
+	sub	sp,sp,#4*(16)		@ off-load area
+#if __LINUX_ARM_ARCH__ < 7 && !defined(__thumb2__)
+	sub	r14,pc,#100		@ .Lsigma2
+#else
+	adr	r14,.Lsigma2		@ .Lsigma2
+#endif
+	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 "rx"
+	str	r11,[sp,#4*(16+11)]	@ off-load "rx"
+	b	.Loop_outer_enter
+
+.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)]
+	ldr	r12,[sp,#4*(12)]	@ modulo-scheduled load
+	ldr	r10, [sp,#4*(13)]
+	ldr	r14,[sp,#4*(14)]
+	str	r11, [sp,#4*(16+15)]
+	mov	r11,#10
+	b	.Loop
+
+.align	4
+.Loop:
+	subs	r11,r11,#1
+	add	r0,r0,r4
+	mov	r12,r12,ror#16
+	add	r1,r1,r5
+	mov	r10,r10,ror#16
+	eor	r12,r12,r0,ror#16
+	eor	r10,r10,r1,ror#16
+	add	r8,r8,r12
+	mov	r4,r4,ror#20
+	add	r9,r9,r10
+	mov	r5,r5,ror#20
+	eor	r4,r4,r8,ror#20
+	eor	r5,r5,r9,ror#20
+	add	r0,r0,r4
+	mov	r12,r12,ror#24
+	add	r1,r1,r5
+	mov	r10,r10,ror#24
+	eor	r12,r12,r0,ror#24
+	eor	r10,r10,r1,ror#24
+	add	r8,r8,r12
+	mov	r4,r4,ror#25
+	add	r9,r9,r10
+	mov	r5,r5,ror#25
+	str	r10,[sp,#4*(16+13)]
+	ldr	r10,[sp,#4*(16+15)]
+	eor	r4,r4,r8,ror#25
+	eor	r5,r5,r9,ror#25
+	str	r8,[sp,#4*(16+8)]
+	ldr	r8,[sp,#4*(16+10)]
+	add	r2,r2,r6
+	mov	r14,r14,ror#16
+	str	r9,[sp,#4*(16+9)]
+	ldr	r9,[sp,#4*(16+11)]
+	add	r3,r3,r7
+	mov	r10,r10,ror#16
+	eor	r14,r14,r2,ror#16
+	eor	r10,r10,r3,ror#16
+	add	r8,r8,r14
+	mov	r6,r6,ror#20
+	add	r9,r9,r10
+	mov	r7,r7,ror#20
+	eor	r6,r6,r8,ror#20
+	eor	r7,r7,r9,ror#20
+	add	r2,r2,r6
+	mov	r14,r14,ror#24
+	add	r3,r3,r7
+	mov	r10,r10,ror#24
+	eor	r14,r14,r2,ror#24
+	eor	r10,r10,r3,ror#24
+	add	r8,r8,r14
+	mov	r6,r6,ror#25
+	add	r9,r9,r10
+	mov	r7,r7,ror#25
+	eor	r6,r6,r8,ror#25
+	eor	r7,r7,r9,ror#25
+	add	r0,r0,r5
+	mov	r10,r10,ror#16
+	add	r1,r1,r6
+	mov	r12,r12,ror#16
+	eor	r10,r10,r0,ror#16
+	eor	r12,r12,r1,ror#16
+	add	r8,r8,r10
+	mov	r5,r5,ror#20
+	add	r9,r9,r12
+	mov	r6,r6,ror#20
+	eor	r5,r5,r8,ror#20
+	eor	r6,r6,r9,ror#20
+	add	r0,r0,r5
+	mov	r10,r10,ror#24
+	add	r1,r1,r6
+	mov	r12,r12,ror#24
+	eor	r10,r10,r0,ror#24
+	eor	r12,r12,r1,ror#24
+	add	r8,r8,r10
+	mov	r5,r5,ror#25
+	str	r10,[sp,#4*(16+15)]
+	ldr	r10,[sp,#4*(16+13)]
+	add	r9,r9,r12
+	mov	r6,r6,ror#25
+	eor	r5,r5,r8,ror#25
+	eor	r6,r6,r9,ror#25
+	str	r8,[sp,#4*(16+10)]
+	ldr	r8,[sp,#4*(16+8)]
+	add	r2,r2,r7
+	mov	r10,r10,ror#16
+	str	r9,[sp,#4*(16+11)]
+	ldr	r9,[sp,#4*(16+9)]
+	add	r3,r3,r4
+	mov	r14,r14,ror#16
+	eor	r10,r10,r2,ror#16
+	eor	r14,r14,r3,ror#16
+	add	r8,r8,r10
+	mov	r7,r7,ror#20
+	add	r9,r9,r14
+	mov	r4,r4,ror#20
+	eor	r7,r7,r8,ror#20
+	eor	r4,r4,r9,ror#20
+	add	r2,r2,r7
+	mov	r10,r10,ror#24
+	add	r3,r3,r4
+	mov	r14,r14,ror#24
+	eor	r10,r10,r2,ror#24
+	eor	r14,r14,r3,ror#24
+	add	r8,r8,r10
+	mov	r7,r7,ror#25
+	add	r9,r9,r14
+	mov	r4,r4,ror#25
+	eor	r7,r7,r8,ror#25
+	eor	r4,r4,r9,ror#25
+	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,r4,r8	@ accumulate key material
+	add	r5,r5,r9
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+	add	r6,r6,r10
+	add	r7,r7,r11
+#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,r4,r8	@ accumulate key material
+	add	r5,r5,r9
+#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,r6,r10
+	add	r7,r7,r11
+#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,r0,r8		@ accumulate key material
+	add	r1,r1,r9
+	add	r2,r2,r10
+#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,r3,r11
+#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,r4,r8		@ accumulate key material
+	add	r5,r5,r9
+	add	r6,r6,r10
+#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,r7,r11
+#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,r0,r8		@ accumulate key material
+	add	r1,r1,r9
+	add	r2,r2,r10
+#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,r3,r11
+#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,r4,r8		@ 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,r5,r9
+	add	r6,r6,r10
+#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,r7,r11
+#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)
+.Lno_data_arm:
+	ldmia	sp!,{r4-r11,pc}
+ENDPROC(chacha20_arm)
diff --git a/lib/zinc/chacha20/chacha20-arm64.S b/lib/zinc/chacha20/chacha20-arm64.S
new file mode 100644
index 000000000000..f90162c32a33
--- /dev/null
+++ b/lib/zinc/chacha20/chacha20-arm64.S
@@ -0,0 +1,1942 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@xxxxxxxxx>. All Rights Reserved.
+ * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@xxxxxxxxxxx>. 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
+.Lshort:
+	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	__ARMEB__
+	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	__ARMEB__
+	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	__ARMEB__
+	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)
+
+.align	5
+ENTRY(chacha20_neon)
+	cbz	x2,.Labort_neon
+	cmp	x2,#192
+	b.lo	.Lshort
+
+	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	__ARMEB__
+	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	__ARMEB__
+	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	__ARMEB__
+	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	__ARMEB__
+	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	__ARMEB__
+	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	__ARMEB__
+	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)
-- 
2.18.0