Message-Id: <20180806223300.113891-9-ebiggers@kernel.org>
Date:   Mon,  6 Aug 2018 15:32:59 -0700
From:   Eric Biggers <ebiggers@...nel.org>
To:     linux-crypto@...r.kernel.org
Cc:     linux-fscrypt@...r.kernel.org,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
        Herbert Xu <herbert@...dor.apana.org.au>,
        Paul Crowley <paulcrowley@...gle.com>,
        Greg Kaiser <gkaiser@...gle.com>,
        Michael Halcrow <mhalcrow@...gle.com>,
        "Jason A . Donenfeld" <Jason@...c4.com>,
        Samuel Neves <samuel.c.p.neves@...il.com>,
        Tomer Ashur <tomer.ashur@...t.kuleuven.be>,
        Eric Biggers <ebiggers@...gle.com>
Subject: [RFC PATCH 8/9] crypto: arm/poly1305 - add NEON accelerated Poly1305 implementation

From: Eric Biggers <ebiggers@...gle.com>

Add the Poly1305 code from OpenSSL, which was written by Andy Polyakov.
I took the .S file from WireGuard, whose author has made the needed
tweaks for Linux kernel integration and verified that Andy had given
permission for GPLv2 distribution.  I didn't make any additional changes
to the .S file.

Note, for HPolyC I'd eventually like a Poly1305 implementation that
allows precomputing powers of the key.  But for now this implementation
just provides the existing semantics where the key and nonce are treated
as a "one-time key" that must be provided for every message.

Signed-off-by: Eric Biggers <ebiggers@...gle.com>
---
 arch/arm/crypto/Kconfig              |    5 +
 arch/arm/crypto/Makefile             |    2 +
 arch/arm/crypto/poly1305-neon-core.S | 1115 ++++++++++++++++++++++++++
 arch/arm/crypto/poly1305-neon-glue.c |  325 ++++++++
 4 files changed, 1447 insertions(+)
 create mode 100644 arch/arm/crypto/poly1305-neon-core.S
 create mode 100644 arch/arm/crypto/poly1305-neon-glue.c

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 75c613413e31..8c205994120e 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -121,6 +121,11 @@ config CRYPTO_CHACHA20_NEON
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20
 
+config CRYPTO_POLY1305_NEON
+	tristate "NEON accelerated Poly1305 authenticator algorithm"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_POLY1305
+
 config CRYPTO_SPECK_NEON
 	tristate "NEON accelerated Speck cipher algorithms"
 	depends on KERNEL_MODE_NEON
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 6f58a24faa4a..6423442c86fe 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
 obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
 
 ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
@@ -54,6 +55,7 @@ ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
 crct10dif-arm-ce-y	:= crct10dif-ce-core.o crct10dif-ce-glue.o
 crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o
 chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
+poly1305-neon-y := poly1305-neon-core.o poly1305-neon-glue.o
 speck-neon-y := speck-neon-core.o speck-neon-glue.o
 
 ifdef REGENERATE_ARM_CRYPTO
diff --git a/arch/arm/crypto/poly1305-neon-core.S b/arch/arm/crypto/poly1305-neon-core.S
new file mode 100644
index 000000000000..d6b9a80dcc8b
--- /dev/null
+++ b/arch/arm/crypto/poly1305-neon-core.S
@@ -0,0 +1,1115 @@
+/* SPDX-License-Identifier: OpenSSL OR (BSD-3-Clause OR GPL-2.0)
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@...c4.com>. All Rights Reserved.
+ * Copyright 2016 The OpenSSL Project Authors. All Rights Reserved.
+ */
+
+#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)
+
+
+#if __LINUX_ARM_ARCH__ >= 7
+.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/arch/arm/crypto/poly1305-neon-glue.c b/arch/arm/crypto/poly1305-neon-glue.c
new file mode 100644
index 000000000000..633ac0d157db
--- /dev/null
+++ b/arch/arm/crypto/poly1305-neon-glue.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Poly1305 authenticator, NEON-accelerated -
+ * glue code for OpenSSL implementation
+ *
+ * Copyright (c) 2018 Google LLC
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/cryptd.h>
+#include <crypto/internal/hash.h>
+#include <crypto/poly1305.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+asmlinkage void poly1305_init_arm(void *ctx, const u8 key[16]);
+asmlinkage void poly1305_blocks_neon(void *ctx, const u8 *inp, size_t len,
+				     u32 padbit);
+asmlinkage void poly1305_emit_neon(void *ctx, u8 mac[16], const u32 nonce[4]);
+
+struct poly1305_neon_desc_ctx {
+	u8 buf[POLY1305_BLOCK_SIZE];
+	unsigned int buflen;
+	bool key_set;
+	bool nonce_set;
+	u32 nonce[4];
+	u8 neon_ctx[192] __aligned(16);
+} __aligned(16);
+
+static int poly1305_neon_init(struct shash_desc *desc)
+{
+	struct poly1305_neon_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	dctx->buflen = 0;
+	dctx->key_set = false;
+	dctx->nonce_set = false;
+	return 0;
+}
+
+static void poly1305_neon_blocks(struct poly1305_neon_desc_ctx *dctx,
+				 const u8 *src, unsigned int srclen, u32 padbit)
+{
+	if (!dctx->key_set) {
+		poly1305_init_arm(dctx->neon_ctx, src);
+		dctx->key_set = true;
+		src += POLY1305_BLOCK_SIZE;
+		srclen -= POLY1305_BLOCK_SIZE;
+		if (!srclen)
+			return;
+	}
+
+	if (!dctx->nonce_set) {
+		dctx->nonce[0] = get_unaligned_le32(src +  0);
+		dctx->nonce[1] = get_unaligned_le32(src +  4);
+		dctx->nonce[2] = get_unaligned_le32(src +  8);
+		dctx->nonce[3] = get_unaligned_le32(src + 12);
+		dctx->nonce_set = true;
+		src += POLY1305_BLOCK_SIZE;
+		srclen -= POLY1305_BLOCK_SIZE;
+		if (!srclen)
+			return;
+	}
+
+	kernel_neon_begin();
+	poly1305_blocks_neon(dctx->neon_ctx, src, srclen, padbit);
+	kernel_neon_end();
+}
+
+static int poly1305_neon_update(struct shash_desc *desc,
+				const u8 *src, unsigned int srclen)
+{
+	struct poly1305_neon_desc_ctx *dctx = shash_desc_ctx(desc);
+	unsigned int bytes;
+
+	if (dctx->buflen) {
+		bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
+		memcpy(&dctx->buf[dctx->buflen], src, bytes);
+		dctx->buflen += bytes;
+		src += bytes;
+		srclen -= bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_neon_blocks(dctx, dctx->buf,
+					     POLY1305_BLOCK_SIZE, 1);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (srclen >= POLY1305_BLOCK_SIZE) {
+		bytes = round_down(srclen, POLY1305_BLOCK_SIZE);
+		poly1305_neon_blocks(dctx, src, bytes, 1);
+		src += bytes;
+		srclen -= bytes;
+	}
+
+	if (srclen) {
+		memcpy(dctx->buf, src, srclen);
+		dctx->buflen = srclen;
+	}
+
+	return 0;
+}
+
+static int poly1305_neon_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_neon_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (!dctx->nonce_set)
+		return -ENOKEY;
+
+	if (dctx->buflen) {
+		dctx->buf[dctx->buflen++] = 1;
+		memset(&dctx->buf[dctx->buflen], 0,
+		       POLY1305_BLOCK_SIZE - dctx->buflen);
+		poly1305_neon_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	/*
+	 * This part doesn't actually use NEON instructions, so no need for
+	 * kernel_neon_begin().
+	 */
+	poly1305_emit_neon(dctx->neon_ctx, dst, dctx->nonce);
+	return 0;
+}
+
+static struct shash_alg poly1305_alg = {
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.init			= poly1305_neon_init,
+	.update			= poly1305_neon_update,
+	.final			= poly1305_neon_final,
+	.descsize		= sizeof(struct poly1305_desc_ctx),
+	.base			= {
+		.cra_name	= "__poly1305",
+		.cra_driver_name = "__driver-poly1305-neon",
+		.cra_priority	= 0,
+		.cra_flags	= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize	= POLY1305_BLOCK_SIZE,
+		.cra_module	= THIS_MODULE,
+	},
+};
+
+/* Boilerplate to wrap the use of kernel_neon_begin() */
+
+struct poly1305_async_ctx {
+	struct cryptd_ahash *cryptd_tfm;
+};
+
+static int poly1305_async_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct poly1305_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
+
+	desc->tfm = child;
+	desc->flags = req->base.flags;
+	return crypto_shash_init(desc);
+}
+
+static int poly1305_async_update(struct ahash_request *req)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct poly1305_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_update(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		return shash_ahash_update(req, desc);
+	}
+}
+
+static int poly1305_async_final(struct ahash_request *req)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct poly1305_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_final(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		return crypto_shash_final(desc, req->result);
+	}
+}
+
+static int poly1305_async_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct poly1305_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_digest(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
+
+		desc->tfm = child;
+		desc->flags = req->base.flags;
+		return shash_ahash_digest(req, desc);
+	}
+}
+
+static int poly1305_async_import(struct ahash_request *req, const void *in)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct poly1305_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+	desc->tfm = cryptd_ahash_child(ctx->cryptd_tfm);
+	desc->flags = req->base.flags;
+
+	return crypto_shash_import(desc, in);
+}
+
+static int poly1305_async_export(struct ahash_request *req, void *out)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+
+	return crypto_shash_export(desc, out);
+}
+
+static int poly1305_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct cryptd_ahash *cryptd_tfm;
+	struct poly1305_async_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_tfm = cryptd_alloc_ahash("__driver-poly1305-neon",
+					CRYPTO_ALG_INTERNAL,
+					CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+	ctx->cryptd_tfm = cryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct ahash_request) +
+				 crypto_ahash_reqsize(&cryptd_tfm->base));
+
+	return 0;
+}
+
+static void poly1305_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct poly1305_async_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_free_ahash(ctx->cryptd_tfm);
+}
+
+static struct ahash_alg poly1305_async_alg = {
+	.init			= poly1305_async_init,
+	.update			= poly1305_async_update,
+	.final			= poly1305_async_final,
+	.digest			= poly1305_async_digest,
+	.import			= poly1305_async_import,
+	.export			= poly1305_async_export,
+	.halg.digestsize	= POLY1305_DIGEST_SIZE,
+	.halg.statesize		= sizeof(struct poly1305_neon_desc_ctx),
+	.halg.base		= {
+		.cra_name	= "poly1305",
+		.cra_driver_name = "poly1305-neon",
+		.cra_priority	= 300,
+		.cra_flags	= CRYPTO_ALG_ASYNC,
+		.cra_blocksize	= POLY1305_BLOCK_SIZE,
+		.cra_ctxsize	= sizeof(struct poly1305_async_ctx),
+		.cra_module	= THIS_MODULE,
+		.cra_init	= poly1305_async_init_tfm,
+		.cra_exit	= poly1305_async_exit_tfm,
+	},
+};
+
+static int __init poly1305_neon_module_init(void)
+{
+	int err;
+
+	if (!(elf_hwcap & HWCAP_NEON))
+		return -ENODEV;
+
+	err = crypto_register_shash(&poly1305_alg);
+	if (err)
+		return err;
+	err = crypto_register_ahash(&poly1305_async_alg);
+	if (err)
+		goto err_shash;
+
+	return 0;
+
+err_shash:
+	crypto_unregister_shash(&poly1305_alg);
+	return err;
+}
+
+static void __exit poly1305_neon_module_exit(void)
+{
+	crypto_unregister_shash(&poly1305_alg);
+	crypto_unregister_ahash(&poly1305_async_alg);
+}
+
+module_init(poly1305_neon_module_init);
+module_exit(poly1305_neon_module_exit);
+
+MODULE_DESCRIPTION("Poly1305 authenticator (NEON-accelerated)");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-neon");
-- 
2.18.0.597.ga71716f1ad-goog

Powered by blists - more mailing lists