[PATCH v2 4/5] crypto/arm: AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions

[Ard Biesheuvel <ard.biesheuvel@linaro.org>]

This implements the ECB, CBC, CTR and XTS asynchronous block ciphers
using the AArch32 versions of the ARMv8 Crypto Extensions for AES.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---
 arch/arm/crypto/Kconfig       |   9 +
 arch/arm/crypto/Makefile      |   2 +
 arch/arm/crypto/aes-ce-core.S | 518 +++++++++++++++++++++++++++++++++++++++++
 arch/arm/crypto/aes-ce-glue.c | 520 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 1049 insertions(+)
 create mode 100644 arch/arm/crypto/aes-ce-core.S
 create mode 100644 arch/arm/crypto/aes-ce-glue.c

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 9c1478e55a40..63588bdf3b5d 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -101,4 +101,13 @@ config CRYPTO_AES_ARM_BS
 	  This implementation does not rely on any lookup tables so it is
 	  believed to be invulnerable to cache timing attacks.
 
+config CRYPTO_AES_ARM_CE
+	tristate "Accelerated AES using ARMv8 Crypto Extensions"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_ABLK_HELPER
+	help
+	  Use an implementation of AES in CBC, CTR and XTS modes that uses
+	  ARMv8 Crypto Extensions
+
 endif
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 4ea9f96c2782..2514c420e8d3 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -4,6 +4,7 @@
 
 obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
 obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
+obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
@@ -17,6 +18,7 @@ sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
 sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
 sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
 sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
+aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)
diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S
new file mode 100644
index 000000000000..8cfa468ee570
--- /dev/null
+++ b/arch/arm/crypto/aes-ce-core.S
@@ -0,0 +1,518 @@
+/*
+ * aes-ce-core.S - AES in CBC/CTR/XTS mode using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.fpu		crypto-neon-fp-armv8
+	.align		3
+
+	.macro		enc_round, state, key
+	aese.8		\state, \key
+	aesmc.8		\state, \state
+	.endm
+
+	.macro		dec_round, state, key
+	aesd.8		\state, \key
+	aesimc.8	\state, \state
+	.endm
+
+	.macro		enc_dround, key1, key2
+	enc_round	q0, \key1
+	enc_round	q0, \key2
+	.endm
+
+	.macro		dec_dround, key1, key2
+	dec_round	q0, \key1
+	dec_round	q0, \key2
+	.endm
+
+	.macro		enc_fround, key1, key2, key3
+	enc_round	q0, \key1
+	aese.8		q0, \key2
+	veor		q0, q0, \key3
+	.endm
+
+	.macro		dec_fround, key1, key2, key3
+	dec_round	q0, \key1
+	aesd.8		q0, \key2
+	veor		q0, q0, \key3
+	.endm
+
+	.macro		enc_dround_3x, key1, key2
+	enc_round	q0, \key1
+	enc_round	q1, \key1
+	enc_round	q2, \key1
+	enc_round	q0, \key2
+	enc_round	q1, \key2
+	enc_round	q2, \key2
+	.endm
+
+	.macro		dec_dround_3x, key1, key2
+	dec_round	q0, \key1
+	dec_round	q1, \key1
+	dec_round	q2, \key1
+	dec_round	q0, \key2
+	dec_round	q1, \key2
+	dec_round	q2, \key2
+	.endm
+
+	.macro		enc_fround_3x, key1, key2, key3
+	enc_round	q0, \key1
+	enc_round	q1, \key1
+	enc_round	q2, \key1
+	aese.8		q0, \key2
+	aese.8		q1, \key2
+	aese.8		q2, \key2
+	veor		q0, q0, \key3
+	veor		q1, q1, \key3
+	veor		q2, q2, \key3
+	.endm
+
+	.macro		dec_fround_3x, key1, key2, key3
+	dec_round	q0, \key1
+	dec_round	q1, \key1
+	dec_round	q2, \key1
+	aesd.8		q0, \key2
+	aesd.8		q1, \key2
+	aesd.8		q2, \key2
+	veor		q0, q0, \key3
+	veor		q1, q1, \key3
+	veor		q2, q2, \key3
+	.endm
+
+	.macro		do_block, dround, fround
+	cmp		r3, #12			@ which key size?
+	vld1.8		{q10-q11}, [ip]!
+	\dround		q8, q9
+	vld1.8		{q12-q13}, [ip]!
+	\dround		q10, q11
+	vld1.8		{q10-q11}, [ip]!
+	\dround		q12, q13
+	vld1.8		{q12-q13}, [ip]!
+	\dround		q10, q11
+	blo		0f			@ AES-128: 10 rounds
+	vld1.8		{q10-q11}, [ip]!
+	beq		1f			@ AES-192: 12 rounds
+	\dround		q12, q13
+	vld1.8		{q12-q13}, [ip]
+	\dround		q10, q11
+0:	\fround		q12, q13, q14
+	bx		lr
+
+1:	\dround		q12, q13
+	\fround		q10, q11, q14
+	bx		lr
+	.endm
+
+	/*
+	 * Internal, non-AAPCS compliant functions that implement the core AES
+	 * transforms. These should preserve all registers except q0 - q2 and ip
+	 * Arguments:
+	 *   q0        : first in/output block
+	 *   q1        : second in/output block (_3x version only)
+	 *   q2        : third in/output block (_3x version only)
+	 *   q8        : first round key
+	 *   q9        : secound round key
+	 *   ip        : address of 3rd round key
+	 *   q14       : final round key
+	 *   r3        : number of rounds
+	 */
+	.align		6
+aes_encrypt:
+	add		ip, r2, #32		@ 3rd round key
+.Laes_encrypt_tweak:
+	do_block	enc_dround, enc_fround
+ENDPROC(aes_encrypt)
+
+	.align		6
+aes_decrypt:
+	add		ip, r2, #32		@ 3rd round key
+	do_block	dec_dround, dec_fround
+ENDPROC(aes_decrypt)
+
+	.align		6
+aes_encrypt_3x:
+	add		ip, r2, #32		@ 3rd round key
+	do_block	enc_dround_3x, enc_fround_3x
+ENDPROC(aes_encrypt_3x)
+
+	.align		6
+aes_decrypt_3x:
+	add		ip, r2, #32		@ 3rd round key
+	do_block	dec_dround_3x, dec_fround_3x
+ENDPROC(aes_decrypt_3x)
+
+	.macro		prepare_key, rk, rounds
+	add		ip, \rk, \rounds, lsl #4
+	vld1.8		{q8-q9}, [\rk]		@ load first 2 round keys
+	vld1.8		{q14}, [ip]		@ load last round key
+	.endm
+
+	/*
+	 * aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks)
+	 * aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks)
+	 */
+ENTRY(ce_aes_ecb_encrypt)
+	push		{r4, lr}
+	ldr		r4, [sp, #8]
+	prepare_key	r2, r3
+.Lecbencloop3x:
+	subs		r4, r4, #3
+	bmi		.Lecbenc1x
+	vld1.8		{q0-q1}, [r1, :64]!
+	vld1.8		{q2}, [r1, :64]!
+	bl		aes_encrypt_3x
+	vst1.8		{q0-q1}, [r0, :64]!
+	vst1.8		{q2}, [r0, :64]!
+	b		.Lecbencloop3x
+.Lecbenc1x:
+	adds		r4, r4, #3
+	beq		.Lecbencout
+.Lecbencloop:
+	vld1.8		{q0}, [r1, :64]!
+	bl		aes_encrypt
+	vst1.8		{q0}, [r0, :64]!
+	subs		r4, r4, #1
+	bne		.Lecbencloop
+.Lecbencout:
+	pop		{r4, pc}
+ENDPROC(ce_aes_ecb_encrypt)
+
+ENTRY(ce_aes_ecb_decrypt)
+	push		{r4, lr}
+	ldr		r4, [sp, #8]
+	prepare_key	r2, r3
+.Lecbdecloop3x:
+	subs		r4, r4, #3
+	bmi		.Lecbdec1x
+	vld1.8		{q0-q1}, [r1, :64]!
+	vld1.8		{q2}, [r1, :64]!
+	bl		aes_decrypt_3x
+	vst1.8		{q0-q1}, [r0, :64]!
+	vst1.8		{q2}, [r0, :64]!
+	b		.Lecbdecloop3x
+.Lecbdec1x:
+	adds		r4, r4, #3
+	beq		.Lecbdecout
+.Lecbdecloop:
+	vld1.8		{q0}, [r1, :64]!
+	bl		aes_decrypt
+	vst1.8		{q0}, [r0, :64]!
+	subs		r4, r4, #1
+	bne		.Lecbdecloop
+.Lecbdecout:
+	pop		{r4, pc}
+ENDPROC(ce_aes_ecb_decrypt)
+
+	/*
+	 * aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 iv[])
+	 * aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 iv[])
+	 */
+ENTRY(ce_aes_cbc_encrypt)
+	push		{r4-r6, lr}
+	ldrd		r4, r5, [sp, #16]
+	vld1.8		{q0}, [r5]
+	prepare_key	r2, r3
+.Lcbcencloop:
+	vld1.8		{q1}, [r1, :64]!	@ get next pt block
+	veor		q0, q0, q1		@ ..and xor with iv
+	bl		aes_encrypt
+	vst1.8		{q0}, [r0, :64]!
+	subs		r4, r4, #1
+	bne		.Lcbcencloop
+	vst1.8		{q0}, [r5]
+	pop		{r4-r6, pc}
+ENDPROC(ce_aes_cbc_encrypt)
+
+ENTRY(ce_aes_cbc_decrypt)
+	push		{r4-r6, lr}
+	ldrd		r4, r5, [sp, #16]
+	vld1.8		{q6}, [r5]		@ keep iv in q6
+	prepare_key	r2, r3
+.Lcbcdecloop3x:
+	subs		r4, r4, #3
+	bmi		.Lcbcdec1x
+	vld1.8		{q0-q1}, [r1, :64]!
+	vld1.8		{q2}, [r1, :64]!
+	vmov		q3, q0
+	vmov		q4, q1
+	vmov		q5, q2
+	bl		aes_decrypt_3x
+	veor		q0, q0, q6
+	veor		q1, q1, q3
+	veor		q2, q2, q4
+	vmov		q6, q5
+	vst1.8		{q0-q1}, [r0, :64]!
+	vst1.8		{q2}, [r0, :64]!
+	b		.Lcbcdecloop3x
+.Lcbcdec1x:
+	adds		r4, r4, #3
+	beq		.Lcbcdecout
+	vmov		q15, q14		@ preserve last round key
+.Lcbcdecloop:
+	vld1.8		{q0}, [r1, :64]!	@ get next ct block
+	veor		q14, q15, q6		@ combine prev ct with last key
+	vmov		q6, q0
+	bl		aes_decrypt
+	vst1.8		{q0}, [r0, :64]!
+	subs		r4, r4, #1
+	bne		.Lcbcdecloop
+.Lcbcdecout:
+	vst1.8		{q6}, [r5]		@ keep iv in q6
+	pop		{r4-r6, pc}
+ENDPROC(ce_aes_cbc_decrypt)
+
+	/*
+	 * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 ctr[])
+	 */
+ENTRY(ce_aes_ctr_encrypt)
+	push		{r4-r6, lr}
+	ldrd		r4, r5, [sp, #16]
+	vld1.8		{q6}, [r5]		@ load ctr
+	prepare_key	r2, r3
+	vmov		r6, s27			@ keep swabbed ctr in r6
+	rev		r6, r6
+	cmn		r6, r4			@ 32 bit overflow?
+	bcs		.Lctrloop
+.Lctrloop3x:
+	subs		r4, r4, #3
+	bmi		.Lctr1x
+	add		r6, r6, #1
+	vmov		q0, q6
+	vmov		q1, q6
+	rev		ip, r6
+	add		r6, r6, #1
+	vmov		q2, q6
+	vmov		s7, ip
+	rev		ip, r6
+	add		r6, r6, #1
+	vmov		s11, ip
+	vld1.8		{q3-q4}, [r1, :64]!
+	vld1.8		{q5}, [r1, :64]!
+	bl		aes_encrypt_3x
+	veor		q0, q0, q3
+	veor		q1, q1, q4
+	veor		q2, q2, q5
+	rev		ip, r6
+	vst1.8		{q0-q1}, [r0, :64]!
+	vst1.8		{q2}, [r0, :64]!
+	vmov		s27, ip
+	b		.Lctrloop3x
+.Lctr1x:
+	adds		r4, r4, #3
+	beq		.Lctrout
+.Lctrloop:
+	vmov		q0, q6
+	bl		aes_encrypt
+	subs		r4, r4, #1
+	bmi		.Lctrhalfblock		@ blocks < 0 means 1/2 block
+	vld1.8		{q3}, [r1, :64]!
+	veor		q3, q0, q3
+	vst1.8		{q3}, [r0, :64]!
+
+	adds		r6, r6, #1		@ increment BE ctr
+	rev		ip, r6
+	vmov		s27, ip
+	bcs		.Lctrcarry
+	teq		r4, #0
+	bne		.Lctrloop
+.Lctrout:
+	vst1.8		{q6}, [r5]
+	pop		{r4-r6, pc}
+
+.Lctrhalfblock:
+	vld1.8		{d1}, [r1, :64]
+	veor		d0, d0, d1
+	vst1.8		{d0}, [r0, :64]
+	pop		{r4-r6, pc}
+
+.Lctrcarry:
+	.irp		sreg, s26, s25, s24
+	vmov		ip, \sreg		@ load next word of ctr
+	rev		ip, ip			@ ... to handle the carry
+	adds		ip, ip, #1
+	rev		ip, ip
+	vmov		\sreg, ip
+	bcc		0f
+	.endr
+0:	teq		r4, #0
+	beq		.Lctrout
+	b		.Lctrloop
+ENDPROC(ce_aes_ctr_encrypt)
+
+	/*
+	 * aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int blocks, u8 iv[], u8 const rk2[], int first)
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int blocks, u8 iv[], u8 const rk2[], int first)
+	 */
+
+	.macro		next_tweak, out, in, const, tmp
+	vshr.s64	\tmp, \in, #63
+	vand		\tmp, \tmp, \const
+	vadd.u64	\out, \in, \in
+	vext.8		\tmp, \tmp, \tmp, #8
+	veor		\out, \out, \tmp
+	.endm
+
+	.align		3
+.Lxts_mul_x:
+	.quad		1, 0x87
+
+ce_aes_xts_init:
+	vldr		d14, .Lxts_mul_x
+	vldr		d15, .Lxts_mul_x + 8
+
+	ldrd		r4, r5, [sp, #16]	@ load args
+	ldr		r6, [sp, #28]
+	vld1.8		{q0}, [r5]		@ load iv
+	teq		r6, #1			@ start of a block?
+	bxne		lr
+
+	@ Encrypt the IV in q0 with the second AES key. This should only
+	@ be done at the start of a block.
+	ldr		r6, [sp, #24]		@ load AES key 2
+	prepare_key	r6, r3
+	add		ip, r6, #32		@ 3rd round key of key 2
+	b		.Laes_encrypt_tweak	@ tail call
+ENDPROC(ce_aes_xts_init)
+
+ENTRY(ce_aes_xts_encrypt)
+	push		{r4-r6, lr}
+
+	bl		ce_aes_xts_init		@ run shared prologue
+	prepare_key	r2, r3
+	vmov		q3, q0
+
+	teq		r6, #0			@ start of a block?
+	bne		.Lxtsenc3x
+
+.Lxtsencloop3x:
+	next_tweak	q3, q3, q7, q6
+.Lxtsenc3x:
+	subs		r4, r4, #3
+	bmi		.Lxtsenc1x
+	vld1.8		{q0-q1}, [r1, :64]!	@ get 3 pt blocks
+	vld1.8		{q2}, [r1, :64]!
+	next_tweak	q4, q3, q7, q6
+	veor		q0, q0, q3
+	next_tweak	q5, q4, q7, q6
+	veor		q1, q1, q4
+	veor		q2, q2, q5
+	bl		aes_encrypt_3x
+	veor		q0, q0, q3
+	veor		q1, q1, q4
+	veor		q2, q2, q5
+	vst1.8		{q0-q1}, [r0, :64]!	@ write 3 ct blocks
+	vst1.8		{q2}, [r0, :64]!
+	vmov		q3, q5
+	teq		r4, #0
+	beq		.Lxtsencout
+	b		.Lxtsencloop3x
+.Lxtsenc1x:
+	adds		r4, r4, #3
+	beq		.Lxtsencout
+.Lxtsencloop:
+	vld1.8		{q0}, [r1, :64]!
+	veor		q0, q0, q3
+	bl		aes_encrypt
+	veor		q0, q0, q3
+	vst1.8		{q0}, [r0, :64]!
+	subs		r4, r4, #1
+	beq		.Lxtsencout
+	next_tweak	q3, q3, q7, q6
+	b		.Lxtsencloop
+.Lxtsencout:
+	vst1.8		{q3}, [r5]
+	pop		{r4-r6, pc}
+ENDPROC(ce_aes_xts_encrypt)
+
+
+ENTRY(ce_aes_xts_decrypt)
+	push		{r4-r6, lr}
+
+	bl		ce_aes_xts_init		@ run shared prologue
+	prepare_key	r2, r3
+	vmov		q3, q0
+
+	teq		r6, #0			@ start of a block?
+	bne		.Lxtsdec3x
+
+.Lxtsdecloop3x:
+	next_tweak	q3, q3, q7, q6
+.Lxtsdec3x:
+	subs		r4, r4, #3
+	bmi		.Lxtsdec1x
+	vld1.8		{q0-q1}, [r1, :64]!	@ get 3 ct blocks
+	vld1.8		{q2}, [r1, :64]!
+	next_tweak	q4, q3, q7, q6
+	veor		q0, q0, q3
+	next_tweak	q5, q4, q7, q6
+	veor		q1, q1, q4
+	veor		q2, q2, q5
+	bl		aes_decrypt_3x
+	veor		q0, q0, q3
+	veor		q1, q1, q4
+	veor		q2, q2, q5
+	vst1.8		{q0-q1}, [r0, :64]!	@ write 3 pt blocks
+	vst1.8		{q2}, [r0, :64]!
+	vmov		q3, q5
+	teq		r4, #0
+	beq		.Lxtsdecout
+	b		.Lxtsdecloop3x
+.Lxtsdec1x:
+	adds		r4, r4, #3
+	beq		.Lxtsdecout
+.Lxtsdecloop:
+	vld1.8		{q0}, [r1, :64]!
+	veor		q0, q0, q3
+	add		ip, r2, #32		@ 3rd round key
+	bl		aes_decrypt
+	veor		q0, q0, q3
+	vst1.8		{q0}, [r0, :64]!
+	subs		r4, r4, #1
+	beq		.Lxtsdecout
+	next_tweak	q3, q3, q7, q6
+	b		.Lxtsdecloop
+.Lxtsdecout:
+	vst1.8		{q3}, [r5]
+	pop		{r4-r6, pc}
+ENDPROC(ce_aes_xts_decrypt)
+
+	/*
+	 * u32 ce_aes_sub(u32 input) - use the aese instruction to perform the
+	 *                             AES sbox substitution on each byte in
+	 *                             'input'
+	 */
+ENTRY(ce_aes_sub)
+	vdup.32		q1, r0
+	veor		q0, q0, q0
+	aese.8		q0, q1
+	vmov		r0, s0
+	bx		lr
+ENDPROC(ce_aes_sub)
+
+	/*
+	 * void ce_aes_invert(u8 *dst, u8 *src) - perform the Inverse MixColumns
+	 *                                        operation on round key *src
+	 */
+ENTRY(ce_aes_invert)
+	vld1.8		{q0}, [r1]
+	aesimc.8	q0, q0
+	vst1.8		{q0}, [r0]
+	bx		lr
+ENDPROC(ce_aes_invert)
diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c
new file mode 100644
index 000000000000..d2ee59157ec7
--- /dev/null
+++ b/arch/arm/crypto/aes-ce-glue.c
@@ -0,0 +1,520 @@
+/*
+ * aes-ce-glue.c - wrapper code for ARMv8 AES
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/hwcap.h>
+#include <crypto/aes.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+/* defined in aes-ce-core.S */
+asmlinkage u32 ce_aes_sub(u32 input);
+asmlinkage void ce_aes_invert(void *dst, void *src);
+
+asmlinkage void ce_aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				   int rounds, int blocks);
+asmlinkage void ce_aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				   int rounds, int blocks);
+
+asmlinkage void ce_aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				   int rounds, int blocks, u8 iv[]);
+asmlinkage void ce_aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				   int rounds, int blocks, u8 iv[]);
+
+asmlinkage void ce_aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				   int rounds, int blocks, u8 ctr[]);
+
+asmlinkage void ce_aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
+				   int rounds, int blocks, u8 iv[],
+				   u8 const rk2[], int first);
+asmlinkage void ce_aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[],
+				   int rounds, int blocks, u8 iv[],
+				   u8 const rk2[], int first);
+
+struct aes_block {
+	u8 b[AES_BLOCK_SIZE];
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+	/*
+	 * # of rounds specified by AES:
+	 * 128 bit key		10 rounds
+	 * 192 bit key		12 rounds
+	 * 256 bit key		14 rounds
+	 * => n byte key	=> 6 + (n/4) rounds
+	 */
+	return 6 + ctx->key_length / 4;
+}
+
+static int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
+			    unsigned int key_len)
+{
+	/*
+	 * The AES key schedule round constants
+	 */
+	static u8 const rcon[] = {
+		0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36,
+	};
+
+	u32 kwords = key_len / sizeof(u32);
+	struct aes_block *key_enc, *key_dec;
+	int i, j;
+
+	if (key_len != AES_KEYSIZE_128 &&
+	    key_len != AES_KEYSIZE_192 &&
+	    key_len != AES_KEYSIZE_256)
+		return -EINVAL;
+
+	memcpy(ctx->key_enc, in_key, key_len);
+	ctx->key_length = key_len;
+
+	kernel_neon_begin();
+	for (i = 0; i < sizeof(rcon); i++) {
+		u32 *rki = ctx->key_enc + (i * kwords);
+		u32 *rko = rki + kwords;
+
+		rko[0] = ror32(ce_aes_sub(rki[kwords - 1]), 8);
+		rko[0] = rko[0] ^ rki[0] ^ rcon[i];
+		rko[1] = rko[0] ^ rki[1];
+		rko[2] = rko[1] ^ rki[2];
+		rko[3] = rko[2] ^ rki[3];
+
+		if (key_len == AES_KEYSIZE_192) {
+			if (i >= 7)
+				break;
+			rko[4] = rko[3] ^ rki[4];
+			rko[5] = rko[4] ^ rki[5];
+		} else if (key_len == AES_KEYSIZE_256) {
+			if (i >= 6)
+				break;
+			rko[4] = ce_aes_sub(rko[3]) ^ rki[4];
+			rko[5] = rko[4] ^ rki[5];
+			rko[6] = rko[5] ^ rki[6];
+			rko[7] = rko[6] ^ rki[7];
+		}
+	}
+
+	/*
+	 * Generate the decryption keys for the Equivalent Inverse Cipher.
+	 * This involves reversing the order of the round keys, and applying
+	 * the Inverse Mix Columns transformation on all but the first and
+	 * the last one.
+	 */
+	key_enc = (struct aes_block *)ctx->key_enc;
+	key_dec = (struct aes_block *)ctx->key_dec;
+	j = num_rounds(ctx);
+
+	key_dec[0] = key_enc[j];
+	for (i = 1, j--; j > 0; i++, j--)
+		ce_aes_invert(key_dec + i, key_enc + j);
+	key_dec[i] = key_enc[0];
+
+	kernel_neon_end();
+	return 0;
+}
+
+static int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+			 unsigned int key_len)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = ce_aes_expandkey(ctx, in_key, key_len);
+	if (!ret)
+		return 0;
+
+	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+
+struct crypto_aes_xts_ctx {
+	struct crypto_aes_ctx key1;
+	struct crypto_aes_ctx __aligned(8) key2;
+};
+
+static int xts_set_key(struct crypto_tfm *tfm, const u8 *in_key,
+		       unsigned int key_len)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	int ret;
+
+	ret = ce_aes_expandkey(&ctx->key1, in_key, key_len / 2);
+	if (!ret)
+		ret = ce_aes_expandkey(&ctx->key2, &in_key[key_len / 2],
+				       key_len / 2);
+	if (!ret)
+		return 0;
+
+	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	return -EINVAL;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+	int err;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		ce_aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   (u8 *)ctx->key_enc, num_rounds(ctx), blocks);
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+	int err;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		ce_aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   (u8 *)ctx->key_dec, num_rounds(ctx), blocks);
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+	int err;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		ce_aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   (u8 *)ctx->key_enc, num_rounds(ctx), blocks,
+				   walk.iv);
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+	int err;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		ce_aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   (u8 *)ctx->key_dec, num_rounds(ctx), blocks,
+				   walk.iv);
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+	return err;
+}
+
+static int ctr_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+	int err, blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
+
+	kernel_neon_begin();
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		ce_aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   (u8 *)ctx->key_enc, num_rounds(ctx), blocks,
+				   walk.iv);
+		nbytes -= blocks * AES_BLOCK_SIZE;
+		if (nbytes && nbytes == walk.nbytes % AES_BLOCK_SIZE)
+			break;
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	if (nbytes) {
+		u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+		u8 __aligned(8) tail[AES_BLOCK_SIZE];
+
+		/*
+		 * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
+		 * to tell aes_ctr_encrypt() to only read half a block.
+		 */
+		blocks = (nbytes <= 8) ? -1 : 1;
+
+		ce_aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc,
+				   num_rounds(ctx), blocks, walk.iv);
+		memcpy(tdst, tail, nbytes);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = num_rounds(&ctx->key1);
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		ce_aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   (u8 *)ctx->key1.key_enc, rounds, blocks,
+				   walk.iv, (u8 *)ctx->key2.key_enc, first);
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	int err, first, rounds = num_rounds(&ctx->key1);
+	struct blkcipher_walk walk;
+	unsigned int blocks;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	kernel_neon_begin();
+	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		ce_aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				   (u8 *)ctx->key1.key_dec, rounds, blocks,
+				   walk.iv, (u8 *)ctx->key2.key_enc, first);
+		err = blkcipher_walk_done(desc, &walk,
+					  walk.nbytes % AES_BLOCK_SIZE);
+	}
+	kernel_neon_end();
+
+	return err;
+}
+
+static struct crypto_alg aes_algs[] = { {
+	.cra_name		= "__ecb-aes-ce",
+	.cra_driver_name	= "__driver-ecb-aes-ce",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ce_aes_setkey,
+		.encrypt	= ecb_encrypt,
+		.decrypt	= ecb_decrypt,
+	},
+}, {
+	.cra_name		= "__cbc-aes-ce",
+	.cra_driver_name	= "__driver-cbc-aes-ce",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ce_aes_setkey,
+		.encrypt	= cbc_encrypt,
+		.decrypt	= cbc_decrypt,
+	},
+}, {
+	.cra_name		= "__ctr-aes-ce",
+	.cra_driver_name	= "__driver-ctr-aes-ce",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ce_aes_setkey,
+		.encrypt	= ctr_encrypt,
+		.decrypt	= ctr_encrypt,
+	},
+}, {
+	.cra_name		= "__xts-aes-ce",
+	.cra_driver_name	= "__driver-xts-aes-ce",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_xts_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_blkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= xts_set_key,
+		.encrypt	= xts_encrypt,
+		.decrypt	= xts_decrypt,
+	},
+}, {
+	.cra_name		= "ecb(aes)",
+	.cra_driver_name	= "ecb-aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "cbc(aes)",
+	.cra_driver_name	= "cbc-aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "ctr(aes)",
+	.cra_driver_name	= "ctr-aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= AES_MIN_KEY_SIZE,
+		.max_keysize	= AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+}, {
+	.cra_name		= "xts(aes)",
+	.cra_driver_name	= "xts-aes-ce",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 7,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_ablkcipher = {
+		.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+		.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+		.ivsize		= AES_BLOCK_SIZE,
+		.setkey		= ablk_set_key,
+		.encrypt	= ablk_encrypt,
+		.decrypt	= ablk_decrypt,
+	}
+} };
+
+static int __init aes_init(void)
+{
+	if (!(elf_hwcap2 & HWCAP2_AES))
+		return -ENODEV;
+	return crypto_register_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static void __exit aes_exit(void)
+{
+	crypto_unregister_algs(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+module_init(aes_init);
+module_exit(aes_exit);
-- 
1.8.3.2