Adding upstream version 5.10.209.upstream/5.10.209upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

44 files changed, 16254 insertions, 0 deletions

diff --git a/arch/arm64/crypto/.gitignore b/arch/arm64/crypto/.gitignore
new file mode 100644
index 000000000..fcf2d731e
--- /dev/null
+++ b/arch/arm64/crypto/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+sha256-core.S
+sha512-core.S
+poly1305-core.S
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
new file mode 100644
index 000000000..6bd4e749a
--- /dev/null
+++ b/arch/arm64/crypto/Kconfig
@@ -0,0 +1,130 @@
+# SPDX-License-Identifier: GPL-2.0
+
+menuconfig ARM64_CRYPTO
+	bool "ARM64 Accelerated Cryptographic Algorithms"
+	depends on ARM64
+	help
+	  Say Y here to choose from a selection of cryptographic algorithms
+	  implemented using ARM64 specific CPU features or instructions.
+
+if ARM64_CRYPTO
+
+config CRYPTO_SHA256_ARM64
+	tristate "SHA-224/SHA-256 digest algorithm for arm64"
+	select CRYPTO_HASH
+
+config CRYPTO_SHA512_ARM64
+	tristate "SHA-384/SHA-512 digest algorithm for arm64"
+	select CRYPTO_HASH
+
+config CRYPTO_SHA1_ARM64_CE
+	tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_SHA1
+
+config CRYPTO_SHA2_ARM64_CE
+	tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_SHA256_ARM64
+
+config CRYPTO_SHA512_ARM64_CE
+	tristate "SHA-384/SHA-512 digest algorithm (ARMv8 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_SHA512_ARM64
+
+config CRYPTO_SHA3_ARM64
+	tristate "SHA3 digest algorithm (ARMv8.2 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_SHA3
+
+config CRYPTO_SM3_ARM64_CE
+	tristate "SM3 digest algorithm (ARMv8.2 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_SM3
+
+config CRYPTO_SM4_ARM64_CE
+	tristate "SM4 symmetric cipher (ARMv8.2 Crypto Extensions)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_SM4
+
+config CRYPTO_GHASH_ARM64_CE
+	tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_GF128MUL
+	select CRYPTO_LIB_AES
+	select CRYPTO_AEAD
+
+config CRYPTO_CRCT10DIF_ARM64_CE
+	tristate "CRCT10DIF digest algorithm using PMULL instructions"
+	depends on KERNEL_MODE_NEON && CRC_T10DIF
+	select CRYPTO_HASH
+
+config CRYPTO_AES_ARM64
+	tristate "AES core cipher using scalar instructions"
+	select CRYPTO_AES
+
+config CRYPTO_AES_ARM64_CE
+	tristate "AES core cipher using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_LIB_AES
+
+config CRYPTO_AES_ARM64_CE_CCM
+	tristate "AES in CCM mode using ARMv8 Crypto Extensions"
+	depends on ARM64 && KERNEL_MODE_NEON
+	select CRYPTO_ALGAPI
+	select CRYPTO_AES_ARM64_CE
+	select CRYPTO_AEAD
+	select CRYPTO_LIB_AES
+
+config CRYPTO_AES_ARM64_CE_BLK
+	tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_SKCIPHER
+	select CRYPTO_AES_ARM64_CE
+	select CRYPTO_AES_ARM64
+	select CRYPTO_SIMD
+
+config CRYPTO_AES_ARM64_NEON_BLK
+	tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_SKCIPHER
+	select CRYPTO_AES_ARM64
+	select CRYPTO_LIB_AES
+	select CRYPTO_SIMD
+
+config CRYPTO_CHACHA20_NEON
+	tristate "ChaCha20, XChaCha20, and XChaCha12 stream ciphers using NEON instructions"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_SKCIPHER
+	select CRYPTO_LIB_CHACHA_GENERIC
+	select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_NEON
+	tristate "Poly1305 hash function using scalar or NEON instructions"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_HASH
+	select CRYPTO_ARCH_HAVE_LIB_POLY1305
+
+config CRYPTO_NHPOLY1305_NEON
+	tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_NHPOLY1305
+
+config CRYPTO_AES_ARM64_BS
+	tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm"
+	depends on KERNEL_MODE_NEON
+	select CRYPTO_SKCIPHER
+	select CRYPTO_AES_ARM64_NEON_BLK
+	select CRYPTO_AES_ARM64
+	select CRYPTO_LIB_AES
+	select CRYPTO_SIMD
+
+endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
new file mode 100644
index 000000000..d0901e610
--- /dev/null
+++ b/arch/arm64/crypto/Makefile
@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# linux/arch/arm64/crypto/Makefile
+#
+# Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+#
+
+obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
+sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
+sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA512_ARM64_CE) += sha512-ce.o
+sha512-ce-y := sha512-ce-glue.o sha512-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SHA3_ARM64) += sha3-ce.o
+sha3-ce-y := sha3-ce-glue.o sha3-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SM3_ARM64_CE) += sm3-ce.o
+sm3-ce-y := sm3-ce-glue.o sm3-ce-core.o
+
+obj-$(CONFIG_CRYPTO_SM4_ARM64_CE) += sm4-ce.o
+sm4-ce-y := sm4-ce-glue.o sm4-ce-core.o
+
+obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
+ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
+
+obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM64_CE) += crct10dif-ce.o
+crct10dif-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
+aes-ce-cipher-y := aes-ce-core.o aes-ce-glue.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_CCM) += aes-ce-ccm.o
+aes-ce-ccm-y := aes-ce-ccm-glue.o aes-ce-ccm-core.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_CE_BLK) += aes-ce-blk.o
+aes-ce-blk-y := aes-glue-ce.o aes-ce.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
+aes-neon-blk-y := aes-glue-neon.o aes-neon.o
+
+obj-$(CONFIG_CRYPTO_SHA256_ARM64) += sha256-arm64.o
+sha256-arm64-y := sha256-glue.o sha256-core.o
+
+obj-$(CONFIG_CRYPTO_SHA512_ARM64) += sha512-arm64.o
+sha512-arm64-y := sha512-glue.o sha512-core.o
+
+obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
+
+obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
+poly1305-neon-y := poly1305-core.o poly1305-glue.o
+AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_init_arm64
+
+obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
+nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64) += aes-arm64.o
+aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o
+
+obj-$(CONFIG_CRYPTO_AES_ARM64_BS) += aes-neon-bs.o
+aes-neon-bs-y := aes-neonbs-core.o aes-neonbs-glue.o
+
+CFLAGS_aes-glue-ce.o	:= -DUSE_V8_CRYPTO_EXTENSIONS
+
+$(obj)/aes-glue-%.o: $(src)/aes-glue.c FORCE
+	$(call if_changed_rule,cc_o_c)
+
+ifdef REGENERATE_ARM64_CRYPTO
+quiet_cmd_perlasm = PERLASM $@
+      cmd_perlasm = $(PERL) $(<) void $(@)
+
+$(src)/poly1305-core.S_shipped: $(src)/poly1305-armv8.pl
+	$(call cmd,perlasm)
+
+$(src)/sha256-core.S_shipped: $(src)/sha512-armv8.pl
+	$(call cmd,perlasm)
+
+$(src)/sha512-core.S_shipped: $(src)/sha512-armv8.pl
+	$(call cmd,perlasm)
+
+endif
+
+clean-files += poly1305-core.S sha256-core.S sha512-core.S
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
new file mode 100644
index 000000000..99a028e29
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch	armv8-a+crypto
+
+	/*
+	 * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+	 *			     u32 *macp, u8 const rk[], u32 rounds);
+	 */
+SYM_FUNC_START(ce_aes_ccm_auth_data)
+	ldr	w8, [x3]			/* leftover from prev round? */
+	ld1	{v0.16b}, [x0]			/* load mac */
+	cbz	w8, 1f
+	sub	w8, w8, #16
+	eor	v1.16b, v1.16b, v1.16b
+0:	ldrb	w7, [x1], #1			/* get 1 byte of input */
+	subs	w2, w2, #1
+	add	w8, w8, #1
+	ins	v1.b[0], w7
+	ext	v1.16b, v1.16b, v1.16b, #1	/* rotate in the input bytes */
+	beq	8f				/* out of input? */
+	cbnz	w8, 0b
+	eor	v0.16b, v0.16b, v1.16b
+1:	ld1	{v3.4s}, [x4]			/* load first round key */
+	prfm	pldl1strm, [x1]
+	cmp	w5, #12				/* which key size? */
+	add	x6, x4, #16
+	sub	w7, w5, #2			/* modified # of rounds */
+	bmi	2f
+	bne	5f
+	mov	v5.16b, v3.16b
+	b	4f
+2:	mov	v4.16b, v3.16b
+	ld1	{v5.4s}, [x6], #16		/* load 2nd round key */
+3:	aese	v0.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+4:	ld1	{v3.4s}, [x6], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+5:	ld1	{v4.4s}, [x6], #16		/* load next round key */
+	subs	w7, w7, #3
+	aese	v0.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	ld1	{v5.4s}, [x6], #16		/* load next round key */
+	bpl	3b
+	aese	v0.16b, v4.16b
+	subs	w2, w2, #16			/* last data? */
+	eor	v0.16b, v0.16b, v5.16b		/* final round */
+	bmi	6f
+	ld1	{v1.16b}, [x1], #16		/* load next input block */
+	eor	v0.16b, v0.16b, v1.16b		/* xor with mac */
+	bne	1b
+6:	st1	{v0.16b}, [x0]			/* store mac */
+	beq	10f
+	adds	w2, w2, #16
+	beq	10f
+	mov	w8, w2
+7:	ldrb	w7, [x1], #1
+	umov	w6, v0.b[0]
+	eor	w6, w6, w7
+	strb	w6, [x0], #1
+	subs	w2, w2, #1
+	beq	10f
+	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
+	b	7b
+8:	cbz	w8, 91f
+	mov	w7, w8
+	add	w8, w8, #16
+9:	ext	v1.16b, v1.16b, v1.16b, #1
+	adds	w7, w7, #1
+	bne	9b
+91:	eor	v0.16b, v0.16b, v1.16b
+	st1	{v0.16b}, [x0]
+10:	str	w8, [x3]
+	ret
+SYM_FUNC_END(ce_aes_ccm_auth_data)
+
+	/*
+	 * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
+	 * 			 u32 rounds);
+	 */
+SYM_FUNC_START(ce_aes_ccm_final)
+	ld1	{v3.4s}, [x2], #16		/* load first round key */
+	ld1	{v0.16b}, [x0]			/* load mac */
+	cmp	w3, #12				/* which key size? */
+	sub	w3, w3, #2			/* modified # of rounds */
+	ld1	{v1.16b}, [x1]			/* load 1st ctriv */
+	bmi	0f
+	bne	3f
+	mov	v5.16b, v3.16b
+	b	2f
+0:	mov	v4.16b, v3.16b
+1:	ld1	{v5.4s}, [x2], #16		/* load next round key */
+	aese	v0.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v4.16b
+	aesmc	v1.16b, v1.16b
+2:	ld1	{v3.4s}, [x2], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v5.16b
+	aesmc	v1.16b, v1.16b
+3:	ld1	{v4.4s}, [x2], #16		/* load next round key */
+	subs	w3, w3, #3
+	aese	v0.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v3.16b
+	aesmc	v1.16b, v1.16b
+	bpl	1b
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	/* final round key cancels out */
+	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
+	st1	{v0.16b}, [x0]			/* store result */
+	ret
+SYM_FUNC_END(ce_aes_ccm_final)
+
+	.macro	aes_ccm_do_crypt,enc
+	ldr	x8, [x6, #8]			/* load lower ctr */
+	ld1	{v0.16b}, [x5]			/* load mac */
+CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
+0:	/* outer loop */
+	ld1	{v1.8b}, [x6]			/* load upper ctr */
+	prfm	pldl1strm, [x1]
+	add	x8, x8, #1
+	rev	x9, x8
+	cmp	w4, #12				/* which key size? */
+	sub	w7, w4, #2			/* get modified # of rounds */
+	ins	v1.d[1], x9			/* no carry in lower ctr */
+	ld1	{v3.4s}, [x3]			/* load first round key */
+	add	x10, x3, #16
+	bmi	1f
+	bne	4f
+	mov	v5.16b, v3.16b
+	b	3f
+1:	mov	v4.16b, v3.16b
+	ld1	{v5.4s}, [x10], #16		/* load 2nd round key */
+2:	/* inner loop: 3 rounds, 2x interleaved */
+	aese	v0.16b, v4.16b
+	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v4.16b
+	aesmc	v1.16b, v1.16b
+3:	ld1	{v3.4s}, [x10], #16		/* load next round key */
+	aese	v0.16b, v5.16b
+	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v5.16b
+	aesmc	v1.16b, v1.16b
+4:	ld1	{v4.4s}, [x10], #16		/* load next round key */
+	subs	w7, w7, #3
+	aese	v0.16b, v3.16b
+	aesmc	v0.16b, v0.16b
+	aese	v1.16b, v3.16b
+	aesmc	v1.16b, v1.16b
+	ld1	{v5.4s}, [x10], #16		/* load next round key */
+	bpl	2b
+	aese	v0.16b, v4.16b
+	aese	v1.16b, v4.16b
+	subs	w2, w2, #16
+	bmi	6f				/* partial block? */
+	ld1	{v2.16b}, [x1], #16		/* load next input block */
+	.if	\enc == 1
+	eor	v2.16b, v2.16b, v5.16b		/* final round enc+mac */
+	eor	v1.16b, v1.16b, v2.16b		/* xor with crypted ctr */
+	.else
+	eor	v2.16b, v2.16b, v1.16b		/* xor with crypted ctr */
+	eor	v1.16b, v2.16b, v5.16b		/* final round enc */
+	.endif
+	eor	v0.16b, v0.16b, v2.16b		/* xor mac with pt ^ rk[last] */
+	st1	{v1.16b}, [x0], #16		/* write output block */
+	bne	0b
+CPU_LE(	rev	x8, x8			)
+	st1	{v0.16b}, [x5]			/* store mac */
+	str	x8, [x6, #8]			/* store lsb end of ctr (BE) */
+5:	ret
+
+6:	eor	v0.16b, v0.16b, v5.16b		/* final round mac */
+	eor	v1.16b, v1.16b, v5.16b		/* final round enc */
+	st1	{v0.16b}, [x5]			/* store mac */
+	add	w2, w2, #16			/* process partial tail block */
+7:	ldrb	w9, [x1], #1			/* get 1 byte of input */
+	umov	w6, v1.b[0]			/* get top crypted ctr byte */
+	umov	w7, v0.b[0]			/* get top mac byte */
+	.if	\enc == 1
+	eor	w7, w7, w9
+	eor	w9, w9, w6
+	.else
+	eor	w9, w9, w6
+	eor	w7, w7, w9
+	.endif
+	strb	w9, [x0], #1			/* store out byte */
+	strb	w7, [x5], #1			/* store mac byte */
+	subs	w2, w2, #1
+	beq	5b
+	ext	v0.16b, v0.16b, v0.16b, #1	/* shift out mac byte */
+	ext	v1.16b, v1.16b, v1.16b, #1	/* shift out ctr byte */
+	b	7b
+	.endm
+
+	/*
+	 * void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+	 * 			   u8 const rk[], u32 rounds, u8 mac[],
+	 * 			   u8 ctr[]);
+	 * void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+	 * 			   u8 const rk[], u32 rounds, u8 mac[],
+	 * 			   u8 ctr[]);
+	 */
+SYM_FUNC_START(ce_aes_ccm_encrypt)
+	aes_ccm_do_crypt	1
+SYM_FUNC_END(ce_aes_ccm_encrypt)
+
+SYM_FUNC_START(ce_aes_ccm_decrypt)
+	aes_ccm_do_crypt	0
+SYM_FUNC_END(ce_aes_ccm_decrypt)
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
new file mode 100644
index 000000000..f6d19b0dc
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/module.h>
+
+#include "aes-ce-setkey.h"
+
+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;
+}
+
+asmlinkage void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
+				     u32 *macp, u32 const rk[], u32 rounds);
+
+asmlinkage void ce_aes_ccm_encrypt(u8 out[], u8 const in[], u32 cbytes,
+				   u32 const rk[], u32 rounds, u8 mac[],
+				   u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
+				   u32 const rk[], u32 rounds, u8 mac[],
+				   u8 ctr[]);
+
+asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
+				 u32 rounds);
+
+static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
+		      unsigned int key_len)
+{
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(tfm);
+
+	return ce_aes_expandkey(ctx, in_key, key_len);
+}
+
+static int ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	if ((authsize & 1) || authsize < 4)
+		return -EINVAL;
+	return 0;
+}
+
+static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	__be32 *n = (__be32 *)&maciv[AES_BLOCK_SIZE - 8];
+	u32 l = req->iv[0] + 1;
+
+	/* verify that CCM dimension 'L' is set correctly in the IV */
+	if (l < 2 || l > 8)
+		return -EINVAL;
+
+	/* verify that msglen can in fact be represented in L bytes */
+	if (l < 4 && msglen >> (8 * l))
+		return -EOVERFLOW;
+
+	/*
+	 * Even if the CCM spec allows L values of up to 8, the Linux cryptoapi
+	 * uses a u32 type to represent msglen so the top 4 bytes are always 0.
+	 */
+	n[0] = 0;
+	n[1] = cpu_to_be32(msglen);
+
+	memcpy(maciv, req->iv, AES_BLOCK_SIZE - l);
+
+	/*
+	 * Meaning of byte 0 according to CCM spec (RFC 3610/NIST 800-38C)
+	 * - bits 0..2	: max # of bytes required to represent msglen, minus 1
+	 *                (already set by caller)
+	 * - bits 3..5	: size of auth tag (1 => 4 bytes, 2 => 6 bytes, etc)
+	 * - bit 6	: indicates presence of authenticate-only data
+	 */
+	maciv[0] |= (crypto_aead_authsize(aead) - 2) << 2;
+	if (req->assoclen)
+		maciv[0] |= 0x40;
+
+	memset(&req->iv[AES_BLOCK_SIZE - l], 0, l);
+	return 0;
+}
+
+static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
+			   u32 abytes, u32 *macp)
+{
+	if (crypto_simd_usable()) {
+		kernel_neon_begin();
+		ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc,
+				     num_rounds(key));
+		kernel_neon_end();
+	} else {
+		if (*macp > 0 && *macp < AES_BLOCK_SIZE) {
+			int added = min(abytes, AES_BLOCK_SIZE - *macp);
+
+			crypto_xor(&mac[*macp], in, added);
+
+			*macp += added;
+			in += added;
+			abytes -= added;
+		}
+
+		while (abytes >= AES_BLOCK_SIZE) {
+			aes_encrypt(key, mac, mac);
+			crypto_xor(mac, in, AES_BLOCK_SIZE);
+
+			in += AES_BLOCK_SIZE;
+			abytes -= AES_BLOCK_SIZE;
+		}
+
+		if (abytes > 0) {
+			aes_encrypt(key, mac, mac);
+			crypto_xor(mac, in, abytes);
+			*macp = abytes;
+		}
+	}
+}
+
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	struct __packed { __be16 l; __be32 h; u16 len; } ltag;
+	struct scatter_walk walk;
+	u32 len = req->assoclen;
+	u32 macp = 0;
+
+	/* prepend the AAD with a length tag */
+	if (len < 0xff00) {
+		ltag.l = cpu_to_be16(len);
+		ltag.len = 2;
+	} else  {
+		ltag.l = cpu_to_be16(0xfffe);
+		put_unaligned_be32(len, &ltag.h);
+		ltag.len = 6;
+	}
+
+	ccm_update_mac(ctx, mac, (u8 *)&ltag, ltag.len, &macp);
+	scatterwalk_start(&walk, req->src);
+
+	do {
+		u32 n = scatterwalk_clamp(&walk, len);
+		u8 *p;
+
+		if (!n) {
+			scatterwalk_start(&walk, sg_next(walk.sg));
+			n = scatterwalk_clamp(&walk, len);
+		}
+		p = scatterwalk_map(&walk);
+		ccm_update_mac(ctx, mac, p, n, &macp);
+		len -= n;
+
+		scatterwalk_unmap(p);
+		scatterwalk_advance(&walk, n);
+		scatterwalk_done(&walk, 0, len);
+	} while (len);
+}
+
+static int ccm_crypt_fallback(struct skcipher_walk *walk, u8 mac[], u8 iv0[],
+			      struct crypto_aes_ctx *ctx, bool enc)
+{
+	u8 buf[AES_BLOCK_SIZE];
+	int err = 0;
+
+	while (walk->nbytes) {
+		int blocks = walk->nbytes / AES_BLOCK_SIZE;
+		u32 tail = walk->nbytes % AES_BLOCK_SIZE;
+		u8 *dst = walk->dst.virt.addr;
+		u8 *src = walk->src.virt.addr;
+		u32 nbytes = walk->nbytes;
+
+		if (nbytes == walk->total && tail > 0) {
+			blocks++;
+			tail = 0;
+		}
+
+		do {
+			u32 bsize = AES_BLOCK_SIZE;
+
+			if (nbytes < AES_BLOCK_SIZE)
+				bsize = nbytes;
+
+			crypto_inc(walk->iv, AES_BLOCK_SIZE);
+			aes_encrypt(ctx, buf, walk->iv);
+			aes_encrypt(ctx, mac, mac);
+			if (enc)
+				crypto_xor(mac, src, bsize);
+			crypto_xor_cpy(dst, src, buf, bsize);
+			if (!enc)
+				crypto_xor(mac, dst, bsize);
+			dst += bsize;
+			src += bsize;
+			nbytes -= bsize;
+		} while (--blocks);
+
+		err = skcipher_walk_done(walk, tail);
+	}
+
+	if (!err) {
+		aes_encrypt(ctx, buf, iv0);
+		aes_encrypt(ctx, mac, mac);
+		crypto_xor(mac, buf, AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
+static int ccm_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	struct skcipher_walk walk;
+	u8 __aligned(8) mac[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 len = req->cryptlen;
+	int err;
+
+	err = ccm_init_mac(req, mac, len);
+	if (err)
+		return err;
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	/* preserve the original iv for the final round */
+	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+	err = skcipher_walk_aead_encrypt(&walk, req, false);
+
+	if (crypto_simd_usable()) {
+		while (walk.nbytes) {
+			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+			if (walk.nbytes == walk.total)
+				tail = 0;
+
+			kernel_neon_begin();
+			ce_aes_ccm_encrypt(walk.dst.virt.addr,
+					   walk.src.virt.addr,
+					   walk.nbytes - tail, ctx->key_enc,
+					   num_rounds(ctx), mac, walk.iv);
+			kernel_neon_end();
+
+			err = skcipher_walk_done(&walk, tail);
+		}
+		if (!err) {
+			kernel_neon_begin();
+			ce_aes_ccm_final(mac, buf, ctx->key_enc,
+					 num_rounds(ctx));
+			kernel_neon_end();
+		}
+	} else {
+		err = ccm_crypt_fallback(&walk, mac, buf, ctx, true);
+	}
+	if (err)
+		return err;
+
+	/* copy authtag to end of dst */
+	scatterwalk_map_and_copy(mac, req->dst, req->assoclen + req->cryptlen,
+				 crypto_aead_authsize(aead), 1);
+
+	return 0;
+}
+
+static int ccm_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int authsize = crypto_aead_authsize(aead);
+	struct skcipher_walk walk;
+	u8 __aligned(8) mac[AES_BLOCK_SIZE];
+	u8 buf[AES_BLOCK_SIZE];
+	u32 len = req->cryptlen - authsize;
+	int err;
+
+	err = ccm_init_mac(req, mac, len);
+	if (err)
+		return err;
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	/* preserve the original iv for the final round */
+	memcpy(buf, req->iv, AES_BLOCK_SIZE);
+
+	err = skcipher_walk_aead_decrypt(&walk, req, false);
+
+	if (crypto_simd_usable()) {
+		while (walk.nbytes) {
+			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+
+			if (walk.nbytes == walk.total)
+				tail = 0;
+
+			kernel_neon_begin();
+			ce_aes_ccm_decrypt(walk.dst.virt.addr,
+					   walk.src.virt.addr,
+					   walk.nbytes - tail, ctx->key_enc,
+					   num_rounds(ctx), mac, walk.iv);
+			kernel_neon_end();
+
+			err = skcipher_walk_done(&walk, tail);
+		}
+		if (!err) {
+			kernel_neon_begin();
+			ce_aes_ccm_final(mac, buf, ctx->key_enc,
+					 num_rounds(ctx));
+			kernel_neon_end();
+		}
+	} else {
+		err = ccm_crypt_fallback(&walk, mac, buf, ctx, false);
+	}
+
+	if (err)
+		return err;
+
+	/* compare calculated auth tag with the stored one */
+	scatterwalk_map_and_copy(buf, req->src,
+				 req->assoclen + req->cryptlen - authsize,
+				 authsize, 0);
+
+	if (crypto_memneq(mac, buf, authsize))
+		return -EBADMSG;
+	return 0;
+}
+
+static struct aead_alg ccm_aes_alg = {
+	.base = {
+		.cra_name		= "ccm(aes)",
+		.cra_driver_name	= "ccm-aes-ce",
+		.cra_priority		= 300,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+	.ivsize		= AES_BLOCK_SIZE,
+	.chunksize	= AES_BLOCK_SIZE,
+	.maxauthsize	= AES_BLOCK_SIZE,
+	.setkey		= ccm_setkey,
+	.setauthsize	= ccm_setauthsize,
+	.encrypt	= ccm_encrypt,
+	.decrypt	= ccm_decrypt,
+};
+
+static int __init aes_mod_init(void)
+{
+	if (!cpu_have_named_feature(AES))
+		return -ENODEV;
+	return crypto_register_aead(&ccm_aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_aead(&ccm_aes_alg);
+}
+
+module_init(aes_mod_init);
+module_exit(aes_mod_exit);
+
+MODULE_DESCRIPTION("Synchronous AES in CCM mode using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("ccm(aes)");
diff --git a/arch/arm64/crypto/aes-ce-core.S b/arch/arm64/crypto/aes-ce-core.S
new file mode 100644
index 000000000..e52e13eb8
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-core.S
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.arch		armv8-a+crypto
+
+SYM_FUNC_START(__aes_ce_encrypt)
+	sub		w3, w3, #2
+	ld1		{v0.16b}, [x2]
+	ld1		{v1.4s}, [x0], #16
+	cmp		w3, #10
+	bmi		0f
+	bne		3f
+	mov		v3.16b, v1.16b
+	b		2f
+0:	mov		v2.16b, v1.16b
+	ld1		{v3.4s}, [x0], #16
+1:	aese		v0.16b, v2.16b
+	aesmc		v0.16b, v0.16b
+2:	ld1		{v1.4s}, [x0], #16
+	aese		v0.16b, v3.16b
+	aesmc		v0.16b, v0.16b
+3:	ld1		{v2.4s}, [x0], #16
+	subs		w3, w3, #3
+	aese		v0.16b, v1.16b
+	aesmc		v0.16b, v0.16b
+	ld1		{v3.4s}, [x0], #16
+	bpl		1b
+	aese		v0.16b, v2.16b
+	eor		v0.16b, v0.16b, v3.16b
+	st1		{v0.16b}, [x1]
+	ret
+SYM_FUNC_END(__aes_ce_encrypt)
+
+SYM_FUNC_START(__aes_ce_decrypt)
+	sub		w3, w3, #2
+	ld1		{v0.16b}, [x2]
+	ld1		{v1.4s}, [x0], #16
+	cmp		w3, #10
+	bmi		0f
+	bne		3f
+	mov		v3.16b, v1.16b
+	b		2f
+0:	mov		v2.16b, v1.16b
+	ld1		{v3.4s}, [x0], #16
+1:	aesd		v0.16b, v2.16b
+	aesimc		v0.16b, v0.16b
+2:	ld1		{v1.4s}, [x0], #16
+	aesd		v0.16b, v3.16b
+	aesimc		v0.16b, v0.16b
+3:	ld1		{v2.4s}, [x0], #16
+	subs		w3, w3, #3
+	aesd		v0.16b, v1.16b
+	aesimc		v0.16b, v0.16b
+	ld1		{v3.4s}, [x0], #16
+	bpl		1b
+	aesd		v0.16b, v2.16b
+	eor		v0.16b, v0.16b, v3.16b
+	st1		{v0.16b}, [x1]
+	ret
+SYM_FUNC_END(__aes_ce_decrypt)
+
+/*
+ * __aes_ce_sub() - use the aese instruction to perform the AES sbox
+ *                  substitution on each byte in 'input'
+ */
+SYM_FUNC_START(__aes_ce_sub)
+	dup		v1.4s, w0
+	movi		v0.16b, #0
+	aese		v0.16b, v1.16b
+	umov		w0, v0.s[0]
+	ret
+SYM_FUNC_END(__aes_ce_sub)
+
+SYM_FUNC_START(__aes_ce_invert)
+	ld1		{v0.4s}, [x1]
+	aesimc		v1.16b, v0.16b
+	st1		{v1.4s}, [x0]
+	ret
+SYM_FUNC_END(__aes_ce_invert)
diff --git a/arch/arm64/crypto/aes-ce-glue.c b/arch/arm64/crypto/aes-ce-glue.c
new file mode 100644
index 000000000..56a5f6f0b
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-glue.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/internal/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include "aes-ce-setkey.h"
+
+MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+struct aes_block {
+	u8 b[AES_BLOCK_SIZE];
+};
+
+asmlinkage void __aes_ce_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+asmlinkage void __aes_ce_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
+asmlinkage u32 __aes_ce_sub(u32 l);
+asmlinkage void __aes_ce_invert(struct aes_block *out,
+				const struct aes_block *in);
+
+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 void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!crypto_simd_usable()) {
+		aes_encrypt(ctx, dst, src);
+		return;
+	}
+
+	kernel_neon_begin();
+	__aes_ce_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
+	kernel_neon_end();
+}
+
+static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!crypto_simd_usable()) {
+		aes_decrypt(ctx, dst, src);
+		return;
+	}
+
+	kernel_neon_begin();
+	__aes_ce_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
+	kernel_neon_end();
+}
+
+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;
+
+	ctx->key_length = key_len;
+	for (i = 0; i < kwords; i++)
+		ctx->key_enc[i] = get_unaligned_le32(in_key + i * sizeof(u32));
+
+	kernel_neon_begin();
+	for (i = 0; i < sizeof(rcon); i++) {
+		u32 *rki = ctx->key_enc + (i * kwords);
+		u32 *rko = rki + kwords;
+
+		rko[0] = ror32(__aes_ce_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
+		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] = __aes_ce_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--)
+		__aes_ce_invert(key_dec + i, key_enc + j);
+	key_dec[i] = key_enc[0];
+
+	kernel_neon_end();
+	return 0;
+}
+EXPORT_SYMBOL(ce_aes_expandkey);
+
+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);
+
+	return ce_aes_expandkey(ctx, in_key, key_len);
+}
+EXPORT_SYMBOL(ce_aes_setkey);
+
+static struct crypto_alg aes_alg = {
+	.cra_name		= "aes",
+	.cra_driver_name	= "aes-ce",
+	.cra_priority		= 250,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_cipher = {
+		.cia_min_keysize	= AES_MIN_KEY_SIZE,
+		.cia_max_keysize	= AES_MAX_KEY_SIZE,
+		.cia_setkey		= ce_aes_setkey,
+		.cia_encrypt		= aes_cipher_encrypt,
+		.cia_decrypt		= aes_cipher_decrypt
+	}
+};
+
+static int __init aes_mod_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_mod_exit(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_cpu_feature_match(AES, aes_mod_init);
+module_exit(aes_mod_exit);
diff --git a/arch/arm64/crypto/aes-ce-setkey.h b/arch/arm64/crypto/aes-ce-setkey.h
new file mode 100644
index 000000000..fd9ecf07d
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce-setkey.h
@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+		  unsigned int key_len);
+int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
+		     unsigned int key_len);
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
new file mode 100644
index 000000000..1dc5bbbfe
--- /dev/null
+++ b/arch/arm64/crypto/aes-ce.S
@@ -0,0 +1,152 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
+ *                                    Crypto Extensions
+ *
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#define AES_FUNC_START(func)		SYM_FUNC_START(ce_ ## func)
+#define AES_FUNC_END(func)		SYM_FUNC_END(ce_ ## func)
+
+	.arch		armv8-a+crypto
+
+	xtsmask		.req	v16
+	cbciv		.req	v16
+	vctr		.req	v16
+
+	.macro		xts_reload_mask, tmp
+	.endm
+
+	.macro		xts_cts_skip_tw, reg, lbl
+	.endm
+
+	/* preload all round keys */
+	.macro		load_round_keys, rounds, rk
+	cmp		\rounds, #12
+	blo		2222f		/* 128 bits */
+	beq		1111f		/* 192 bits */
+	ld1		{v17.4s-v18.4s}, [\rk], #32
+1111:	ld1		{v19.4s-v20.4s}, [\rk], #32
+2222:	ld1		{v21.4s-v24.4s}, [\rk], #64
+	ld1		{v25.4s-v28.4s}, [\rk], #64
+	ld1		{v29.4s-v31.4s}, [\rk]
+	.endm
+
+	/* prepare for encryption with key in rk[] */
+	.macro		enc_prepare, rounds, rk, temp
+	mov		\temp, \rk
+	load_round_keys	\rounds, \temp
+	.endm
+
+	/* prepare for encryption (again) but with new key in rk[] */
+	.macro		enc_switch_key, rounds, rk, temp
+	mov		\temp, \rk
+	load_round_keys	\rounds, \temp
+	.endm
+
+	/* prepare for decryption with key in rk[] */
+	.macro		dec_prepare, rounds, rk, temp
+	mov		\temp, \rk
+	load_round_keys	\rounds, \temp
+	.endm
+
+	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3, i4
+	aes\de		\i0\().16b, \k\().16b
+	aes\mc		\i0\().16b, \i0\().16b
+	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
+	aes\mc		\i1\().16b, \i1\().16b
+	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
+	aes\mc		\i2\().16b, \i2\().16b
+	aes\de		\i3\().16b, \k\().16b
+	aes\mc		\i3\().16b, \i3\().16b
+	.ifnb		\i4
+	aes\de		\i4\().16b, \k\().16b
+	aes\mc		\i4\().16b, \i4\().16b
+	.endif
+	.endif
+	.endif
+	.endm
+
+	/* up to 5 interleaved encryption rounds with the same round key */
+	.macro		round_Nx, enc, k, i0, i1, i2, i3, i4
+	.ifc		\enc, e
+	do_enc_Nx	e, mc, \k, \i0, \i1, \i2, \i3, \i4
+	.else
+	do_enc_Nx	d, imc, \k, \i0, \i1, \i2, \i3, \i4
+	.endif
+	.endm
+
+	/* up to 5 interleaved final rounds */
+	.macro		fin_round_Nx, de, k, k2, i0, i1, i2, i3, i4
+	aes\de		\i0\().16b, \k\().16b
+	.ifnb		\i1
+	aes\de		\i1\().16b, \k\().16b
+	.ifnb		\i3
+	aes\de		\i2\().16b, \k\().16b
+	aes\de		\i3\().16b, \k\().16b
+	.ifnb		\i4
+	aes\de		\i4\().16b, \k\().16b
+	.endif
+	.endif
+	.endif
+	eor		\i0\().16b, \i0\().16b, \k2\().16b
+	.ifnb		\i1
+	eor		\i1\().16b, \i1\().16b, \k2\().16b
+	.ifnb		\i3
+	eor		\i2\().16b, \i2\().16b, \k2\().16b
+	eor		\i3\().16b, \i3\().16b, \k2\().16b
+	.ifnb		\i4
+	eor		\i4\().16b, \i4\().16b, \k2\().16b
+	.endif
+	.endif
+	.endif
+	.endm
+
+	/* up to 5 interleaved blocks */
+	.macro		do_block_Nx, enc, rounds, i0, i1, i2, i3, i4
+	cmp		\rounds, #12
+	blo		2222f		/* 128 bits */
+	beq		1111f		/* 192 bits */
+	round_Nx	\enc, v17, \i0, \i1, \i2, \i3, \i4
+	round_Nx	\enc, v18, \i0, \i1, \i2, \i3, \i4
+1111:	round_Nx	\enc, v19, \i0, \i1, \i2, \i3, \i4
+	round_Nx	\enc, v20, \i0, \i1, \i2, \i3, \i4
+2222:	.irp		key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+	round_Nx	\enc, \key, \i0, \i1, \i2, \i3, \i4
+	.endr
+	fin_round_Nx	\enc, v30, v31, \i0, \i1, \i2, \i3, \i4
+	.endm
+
+	.macro		encrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \in
+	.endm
+
+	.macro		encrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1, \i2, \i3
+	.endm
+
+	.macro		encrypt_block5x, i0, i1, i2, i3, i4, rounds, t0, t1, t2
+	do_block_Nx	e, \rounds, \i0, \i1, \i2, \i3, \i4
+	.endm
+
+	.macro		decrypt_block, in, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \in
+	.endm
+
+	.macro		decrypt_block4x, i0, i1, i2, i3, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1, \i2, \i3
+	.endm
+
+	.macro		decrypt_block5x, i0, i1, i2, i3, i4, rounds, t0, t1, t2
+	do_block_Nx	d, \rounds, \i0, \i1, \i2, \i3, \i4
+	.endm
+
+#define MAX_STRIDE	5
+
+#include "aes-modes.S"
diff --git a/arch/arm64/crypto/aes-cipher-core.S b/arch/arm64/crypto/aes-cipher-core.S
new file mode 100644
index 000000000..c9d6955f8
--- /dev/null
+++ b/arch/arm64/crypto/aes-cipher-core.S
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
+
+	.text
+
+	rk		.req	x0
+	out		.req	x1
+	in		.req	x2
+	rounds		.req	x3
+	tt		.req	x2
+
+	.macro		__pair1, sz, op, reg0, reg1, in0, in1e, in1d, shift
+	.ifc		\op\shift, b0
+	ubfiz		\reg0, \in0, #2, #8
+	ubfiz		\reg1, \in1e, #2, #8
+	.else
+	ubfx		\reg0, \in0, #\shift, #8
+	ubfx		\reg1, \in1e, #\shift, #8
+	.endif
+
+	/*
+	 * AArch64 cannot do byte size indexed loads from a table containing
+	 * 32-bit quantities, i.e., 'ldrb w12, [tt, w12, uxtw #2]' is not a
+	 * valid instruction. So perform the shift explicitly first for the
+	 * high bytes (the low byte is shifted implicitly by using ubfiz rather
+	 * than ubfx above)
+	 */
+	.ifnc		\op, b
+	ldr		\reg0, [tt, \reg0, uxtw #2]
+	ldr		\reg1, [tt, \reg1, uxtw #2]
+	.else
+	.if		\shift > 0
+	lsl		\reg0, \reg0, #2
+	lsl		\reg1, \reg1, #2
+	.endif
+	ldrb		\reg0, [tt, \reg0, uxtw]
+	ldrb		\reg1, [tt, \reg1, uxtw]
+	.endif
+	.endm
+
+	.macro		__pair0, sz, op, reg0, reg1, in0, in1e, in1d, shift
+	ubfx		\reg0, \in0, #\shift, #8
+	ubfx		\reg1, \in1d, #\shift, #8
+	ldr\op		\reg0, [tt, \reg0, uxtw #\sz]
+	ldr\op		\reg1, [tt, \reg1, uxtw #\sz]
+	.endm
+
+	.macro		__hround, out0, out1, in0, in1, in2, in3, t0, t1, enc, sz, op
+	ldp		\out0, \out1, [rk], #8
+
+	__pair\enc	\sz, \op, w12, w13, \in0, \in1, \in3, 0
+	__pair\enc	\sz, \op, w14, w15, \in1, \in2, \in0, 8
+	__pair\enc	\sz, \op, w16, w17, \in2, \in3, \in1, 16
+	__pair\enc	\sz, \op, \t0, \t1, \in3, \in0, \in2, 24
+
+	eor		\out0, \out0, w12
+	eor		\out1, \out1, w13
+	eor		\out0, \out0, w14, ror #24
+	eor		\out1, \out1, w15, ror #24
+	eor		\out0, \out0, w16, ror #16
+	eor		\out1, \out1, w17, ror #16
+	eor		\out0, \out0, \t0, ror #8
+	eor		\out1, \out1, \t1, ror #8
+	.endm
+
+	.macro		fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
+	__hround	\out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op
+	__hround	\out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op
+	.endm
+
+	.macro		iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
+	__hround	\out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op
+	__hround	\out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op
+	.endm
+
+	.macro		do_crypt, round, ttab, ltab, bsz
+	ldp		w4, w5, [in]
+	ldp		w6, w7, [in, #8]
+	ldp		w8, w9, [rk], #16
+	ldp		w10, w11, [rk, #-8]
+
+CPU_BE(	rev		w4, w4		)
+CPU_BE(	rev		w5, w5		)
+CPU_BE(	rev		w6, w6		)
+CPU_BE(	rev		w7, w7		)
+
+	eor		w4, w4, w8
+	eor		w5, w5, w9
+	eor		w6, w6, w10
+	eor		w7, w7, w11
+
+	adr_l		tt, \ttab
+
+	tbnz		rounds, #1, 1f
+
+0:	\round		w8, w9, w10, w11, w4, w5, w6, w7
+	\round		w4, w5, w6, w7, w8, w9, w10, w11
+
+1:	subs		rounds, rounds, #4
+	\round		w8, w9, w10, w11, w4, w5, w6, w7
+	b.ls		3f
+2:	\round		w4, w5, w6, w7, w8, w9, w10, w11
+	b		0b
+3:	adr_l		tt, \ltab
+	\round		w4, w5, w6, w7, w8, w9, w10, w11, \bsz, b
+
+CPU_BE(	rev		w4, w4		)
+CPU_BE(	rev		w5, w5		)
+CPU_BE(	rev		w6, w6		)
+CPU_BE(	rev		w7, w7		)
+
+	stp		w4, w5, [out]
+	stp		w6, w7, [out, #8]
+	ret
+	.endm
+
+SYM_FUNC_START(__aes_arm64_encrypt)
+	do_crypt	fround, crypto_ft_tab, crypto_ft_tab + 1, 2
+SYM_FUNC_END(__aes_arm64_encrypt)
+
+	.align		5
+SYM_FUNC_START(__aes_arm64_decrypt)
+	do_crypt	iround, crypto_it_tab, crypto_aes_inv_sbox, 0
+SYM_FUNC_END(__aes_arm64_decrypt)
diff --git a/arch/arm64/crypto/aes-cipher-glue.c b/arch/arm64/crypto/aes-cipher-glue.c
new file mode 100644
index 000000000..8caf6dfef
--- /dev/null
+++ b/arch/arm64/crypto/aes-cipher-glue.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Scalar AES core transform
+ *
+ * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <crypto/aes.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+asmlinkage void __aes_arm64_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
+static void aes_arm64_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int rounds = 6 + ctx->key_length / 4;
+
+	__aes_arm64_encrypt(ctx->key_enc, out, in, rounds);
+}
+
+static void aes_arm64_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
+	int rounds = 6 + ctx->key_length / 4;
+
+	__aes_arm64_decrypt(ctx->key_dec, out, in, rounds);
+}
+
+static struct crypto_alg aes_alg = {
+	.cra_name			= "aes",
+	.cra_driver_name		= "aes-arm64",
+	.cra_priority			= 200,
+	.cra_flags			= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize			= AES_BLOCK_SIZE,
+	.cra_ctxsize			= sizeof(struct crypto_aes_ctx),
+	.cra_module			= THIS_MODULE,
+
+	.cra_cipher.cia_min_keysize	= AES_MIN_KEY_SIZE,
+	.cra_cipher.cia_max_keysize	= AES_MAX_KEY_SIZE,
+	.cra_cipher.cia_setkey		= crypto_aes_set_key,
+	.cra_cipher.cia_encrypt		= aes_arm64_encrypt,
+	.cra_cipher.cia_decrypt		= aes_arm64_decrypt
+};
+
+static int __init aes_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_fini(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_init(aes_init);
+module_exit(aes_fini);
+
+MODULE_DESCRIPTION("Scalar AES cipher for arm64");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
new file mode 100644
index 000000000..53c92e060
--- /dev/null
+++ b/arch/arm64/crypto/aes-glue.c
@@ -0,0 +1,1054 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * linux/arch/arm64/crypto/aes-glue.c - wrapper code for ARMv8 AES
+ *
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/hwcap.h>
+#include <asm/simd.h>
+#include <crypto/aes.h>
+#include <crypto/ctr.h>
+#include <crypto/sha.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <crypto/xts.h>
+
+#include "aes-ce-setkey.h"
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+#define MODE			"ce"
+#define PRIO			300
+#define aes_expandkey		ce_aes_expandkey
+#define aes_ecb_encrypt		ce_aes_ecb_encrypt
+#define aes_ecb_decrypt		ce_aes_ecb_decrypt
+#define aes_cbc_encrypt		ce_aes_cbc_encrypt
+#define aes_cbc_decrypt		ce_aes_cbc_decrypt
+#define aes_cbc_cts_encrypt	ce_aes_cbc_cts_encrypt
+#define aes_cbc_cts_decrypt	ce_aes_cbc_cts_decrypt
+#define aes_essiv_cbc_encrypt	ce_aes_essiv_cbc_encrypt
+#define aes_essiv_cbc_decrypt	ce_aes_essiv_cbc_decrypt
+#define aes_ctr_encrypt		ce_aes_ctr_encrypt
+#define aes_xts_encrypt		ce_aes_xts_encrypt
+#define aes_xts_decrypt		ce_aes_xts_decrypt
+#define aes_mac_update		ce_aes_mac_update
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
+#else
+#define MODE			"neon"
+#define PRIO			200
+#define aes_ecb_encrypt		neon_aes_ecb_encrypt
+#define aes_ecb_decrypt		neon_aes_ecb_decrypt
+#define aes_cbc_encrypt		neon_aes_cbc_encrypt
+#define aes_cbc_decrypt		neon_aes_cbc_decrypt
+#define aes_cbc_cts_encrypt	neon_aes_cbc_cts_encrypt
+#define aes_cbc_cts_decrypt	neon_aes_cbc_cts_decrypt
+#define aes_essiv_cbc_encrypt	neon_aes_essiv_cbc_encrypt
+#define aes_essiv_cbc_decrypt	neon_aes_essiv_cbc_decrypt
+#define aes_ctr_encrypt		neon_aes_ctr_encrypt
+#define aes_xts_encrypt		neon_aes_xts_encrypt
+#define aes_xts_decrypt		neon_aes_xts_decrypt
+#define aes_mac_update		neon_aes_mac_update
+MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 NEON");
+#endif
+#if defined(USE_V8_CRYPTO_EXTENSIONS) || !IS_ENABLED(CONFIG_CRYPTO_AES_ARM64_BS)
+MODULE_ALIAS_CRYPTO("ecb(aes)");
+MODULE_ALIAS_CRYPTO("cbc(aes)");
+MODULE_ALIAS_CRYPTO("ctr(aes)");
+MODULE_ALIAS_CRYPTO("xts(aes)");
+#endif
+MODULE_ALIAS_CRYPTO("cts(cbc(aes))");
+MODULE_ALIAS_CRYPTO("essiv(cbc(aes),sha256)");
+MODULE_ALIAS_CRYPTO("cmac(aes)");
+MODULE_ALIAS_CRYPTO("xcbc(aes)");
+MODULE_ALIAS_CRYPTO("cbcmac(aes)");
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+/* defined in aes-modes.S */
+asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[],
+				int rounds, int blocks);
+asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u32 const rk[],
+				int rounds, int blocks);
+
+asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[],
+				int rounds, int blocks, u8 iv[]);
+asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u32 const rk[],
+				int rounds, int blocks, u8 iv[]);
+
+asmlinkage void aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
+				int rounds, int bytes, u8 const iv[]);
+asmlinkage void aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
+				int rounds, int bytes, u8 const iv[]);
+
+asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
+				int rounds, int blocks, u8 ctr[]);
+
+asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[],
+				int rounds, int bytes, u32 const rk2[], u8 iv[],
+				int first);
+asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[],
+				int rounds, int bytes, u32 const rk2[], u8 iv[],
+				int first);
+
+asmlinkage void aes_essiv_cbc_encrypt(u8 out[], u8 const in[], u32 const rk1[],
+				      int rounds, int blocks, u8 iv[],
+				      u32 const rk2[]);
+asmlinkage void aes_essiv_cbc_decrypt(u8 out[], u8 const in[], u32 const rk1[],
+				      int rounds, int blocks, u8 iv[],
+				      u32 const rk2[]);
+
+asmlinkage void aes_mac_update(u8 const in[], u32 const rk[], int rounds,
+			       int blocks, u8 dg[], int enc_before,
+			       int enc_after);
+
+struct crypto_aes_xts_ctx {
+	struct crypto_aes_ctx key1;
+	struct crypto_aes_ctx __aligned(8) key2;
+};
+
+struct crypto_aes_essiv_cbc_ctx {
+	struct crypto_aes_ctx key1;
+	struct crypto_aes_ctx __aligned(8) key2;
+	struct crypto_shash *hash;
+};
+
+struct mac_tfm_ctx {
+	struct crypto_aes_ctx key;
+	u8 __aligned(8) consts[];
+};
+
+struct mac_desc_ctx {
+	unsigned int len;
+	u8 dg[AES_BLOCK_SIZE];
+};
+
+static int skcipher_aes_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			       unsigned int key_len)
+{
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return aes_expandkey(ctx, in_key, key_len);
+}
+
+static int __maybe_unused xts_set_key(struct crypto_skcipher *tfm,
+				      const u8 *in_key, unsigned int key_len)
+{
+	struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int ret;
+
+	ret = xts_verify_key(tfm, in_key, key_len);
+	if (ret)
+		return ret;
+
+	ret = aes_expandkey(&ctx->key1, in_key, key_len / 2);
+	if (!ret)
+		ret = aes_expandkey(&ctx->key2, &in_key[key_len / 2],
+				    key_len / 2);
+	return ret;
+}
+
+static int __maybe_unused essiv_cbc_set_key(struct crypto_skcipher *tfm,
+					    const u8 *in_key,
+					    unsigned int key_len)
+{
+	struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	u8 digest[SHA256_DIGEST_SIZE];
+	int ret;
+
+	ret = aes_expandkey(&ctx->key1, in_key, key_len);
+	if (ret)
+		return ret;
+
+	crypto_shash_tfm_digest(ctx->hash, in_key, key_len, digest);
+
+	return aes_expandkey(&ctx->key2, digest, sizeof(digest));
+}
+
+static int __maybe_unused ecb_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, rounds = 6 + ctx->key_length / 4;
+	struct skcipher_walk walk;
+	unsigned int blocks;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
+		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				ctx->key_enc, rounds, blocks);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
+static int __maybe_unused ecb_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, rounds = 6 + ctx->key_length / 4;
+	struct skcipher_walk walk;
+	unsigned int blocks;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
+		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				ctx->key_dec, rounds, blocks);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
+static int cbc_encrypt_walk(struct skcipher_request *req,
+			    struct skcipher_walk *walk)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err = 0, rounds = 6 + ctx->key_length / 4;
+	unsigned int blocks;
+
+	while ((blocks = (walk->nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
+		aes_cbc_encrypt(walk->dst.virt.addr, walk->src.virt.addr,
+				ctx->key_enc, rounds, blocks, walk->iv);
+		kernel_neon_end();
+		err = skcipher_walk_done(walk, walk->nbytes % AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
+static int __maybe_unused cbc_encrypt(struct skcipher_request *req)
+{
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
+	return cbc_encrypt_walk(req, &walk);
+}
+
+static int cbc_decrypt_walk(struct skcipher_request *req,
+			    struct skcipher_walk *walk)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err = 0, rounds = 6 + ctx->key_length / 4;
+	unsigned int blocks;
+
+	while ((blocks = (walk->nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
+		aes_cbc_decrypt(walk->dst.virt.addr, walk->src.virt.addr,
+				ctx->key_dec, rounds, blocks, walk->iv);
+		kernel_neon_end();
+		err = skcipher_walk_done(walk, walk->nbytes % AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
+static int __maybe_unused cbc_decrypt(struct skcipher_request *req)
+{
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
+	return cbc_decrypt_walk(req, &walk);
+}
+
+static int cts_cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, rounds = 6 + ctx->key_length / 4;
+	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+	struct scatterlist *src = req->src, *dst = req->dst;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct skcipher_walk walk;
+
+	skcipher_request_set_tfm(&subreq, tfm);
+	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+				      NULL, NULL);
+
+	if (req->cryptlen <= AES_BLOCK_SIZE) {
+		if (req->cryptlen < AES_BLOCK_SIZE)
+			return -EINVAL;
+		cbc_blocks = 1;
+	}
+
+	if (cbc_blocks > 0) {
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   cbc_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+
+		err = skcipher_walk_virt(&walk, &subreq, false) ?:
+		      cbc_encrypt_walk(&subreq, &walk);
+		if (err)
+			return err;
+
+		if (req->cryptlen == AES_BLOCK_SIZE)
+			return 0;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst,
+					       subreq.cryptlen);
+	}
+
+	/* handle ciphertext stealing */
+	skcipher_request_set_crypt(&subreq, src, dst,
+				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_neon_begin();
+	aes_cbc_cts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			    ctx->key_enc, rounds, walk.nbytes, walk.iv);
+	kernel_neon_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
+static int cts_cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, rounds = 6 + ctx->key_length / 4;
+	int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+	struct scatterlist *src = req->src, *dst = req->dst;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct skcipher_walk walk;
+
+	skcipher_request_set_tfm(&subreq, tfm);
+	skcipher_request_set_callback(&subreq, skcipher_request_flags(req),
+				      NULL, NULL);
+
+	if (req->cryptlen <= AES_BLOCK_SIZE) {
+		if (req->cryptlen < AES_BLOCK_SIZE)
+			return -EINVAL;
+		cbc_blocks = 1;
+	}
+
+	if (cbc_blocks > 0) {
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   cbc_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+
+		err = skcipher_walk_virt(&walk, &subreq, false) ?:
+		      cbc_decrypt_walk(&subreq, &walk);
+		if (err)
+			return err;
+
+		if (req->cryptlen == AES_BLOCK_SIZE)
+			return 0;
+
+		dst = src = scatterwalk_ffwd(sg_src, req->src, subreq.cryptlen);
+		if (req->dst != req->src)
+			dst = scatterwalk_ffwd(sg_dst, req->dst,
+					       subreq.cryptlen);
+	}
+
+	/* handle ciphertext stealing */
+	skcipher_request_set_crypt(&subreq, src, dst,
+				   req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_neon_begin();
+	aes_cbc_cts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			    ctx->key_dec, rounds, walk.nbytes, walk.iv);
+	kernel_neon_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
+static int __maybe_unused essiv_cbc_init_tfm(struct crypto_skcipher *tfm)
+{
+	struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	ctx->hash = crypto_alloc_shash("sha256", 0, 0);
+
+	return PTR_ERR_OR_ZERO(ctx->hash);
+}
+
+static void __maybe_unused essiv_cbc_exit_tfm(struct crypto_skcipher *tfm)
+{
+	struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	crypto_free_shash(ctx->hash);
+}
+
+static int __maybe_unused essiv_cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, rounds = 6 + ctx->key1.key_length / 4;
+	struct skcipher_walk walk;
+	unsigned int blocks;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	blocks = walk.nbytes / AES_BLOCK_SIZE;
+	if (blocks) {
+		kernel_neon_begin();
+		aes_essiv_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				      ctx->key1.key_enc, rounds, blocks,
+				      req->iv, ctx->key2.key_enc);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+	}
+	return err ?: cbc_encrypt_walk(req, &walk);
+}
+
+static int __maybe_unused essiv_cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_essiv_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, rounds = 6 + ctx->key1.key_length / 4;
+	struct skcipher_walk walk;
+	unsigned int blocks;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	blocks = walk.nbytes / AES_BLOCK_SIZE;
+	if (blocks) {
+		kernel_neon_begin();
+		aes_essiv_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				      ctx->key1.key_dec, rounds, blocks,
+				      req->iv, ctx->key2.key_enc);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+	}
+	return err ?: cbc_decrypt_walk(req, &walk);
+}
+
+static int ctr_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, rounds = 6 + ctx->key_length / 4;
+	struct skcipher_walk walk;
+	int blocks;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
+		aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				ctx->key_enc, rounds, blocks, walk.iv);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+	}
+	if (walk.nbytes) {
+		u8 __aligned(8) tail[AES_BLOCK_SIZE];
+		unsigned int nbytes = walk.nbytes;
+		u8 *tdst = walk.dst.virt.addr;
+		u8 *tsrc = walk.src.virt.addr;
+
+		/*
+		 * Tell aes_ctr_encrypt() to process a tail block.
+		 */
+		blocks = -1;
+
+		kernel_neon_begin();
+		aes_ctr_encrypt(tail, NULL, ctx->key_enc, rounds,
+				blocks, walk.iv);
+		kernel_neon_end();
+		crypto_xor_cpy(tdst, tsrc, tail, nbytes);
+		err = skcipher_walk_done(&walk, 0);
+	}
+
+	return err;
+}
+
+static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
+{
+	const struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+	unsigned long flags;
+
+	/*
+	 * Temporarily disable interrupts to avoid races where
+	 * cachelines are evicted when the CPU is interrupted
+	 * to do something else.
+	 */
+	local_irq_save(flags);
+	aes_encrypt(ctx, dst, src);
+	local_irq_restore(flags);
+}
+
+static int __maybe_unused ctr_encrypt_sync(struct skcipher_request *req)
+{
+	if (!crypto_simd_usable())
+		return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
+
+	return ctr_encrypt(req);
+}
+
+static int __maybe_unused xts_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct scatterlist *src, *dst;
+	struct skcipher_walk walk;
+
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+		int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+					      AES_BLOCK_SIZE) - 2;
+
+		skcipher_walk_abort(&walk);
+
+		skcipher_request_set_tfm(&subreq, tfm);
+		skcipher_request_set_callback(&subreq,
+					      skcipher_request_flags(req),
+					      NULL, NULL);
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   xts_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+		req = &subreq;
+		err = skcipher_walk_virt(&walk, req, false);
+	} else {
+		tail = 0;
+	}
+
+	for (first = 1; walk.nbytes >= AES_BLOCK_SIZE; first = 0) {
+		int nbytes = walk.nbytes;
+
+		if (walk.nbytes < walk.total)
+			nbytes &= ~(AES_BLOCK_SIZE - 1);
+
+		kernel_neon_begin();
+		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				ctx->key1.key_enc, rounds, nbytes,
+				ctx->key2.key_enc, walk.iv, first);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	if (err || likely(!tail))
+		return err;
+
+	dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+	if (req->dst != req->src)
+		dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+	skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+	kernel_neon_begin();
+	aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			ctx->key1.key_enc, rounds, walk.nbytes,
+			ctx->key2.key_enc, walk.iv, first);
+	kernel_neon_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
+static int __maybe_unused xts_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err, first, rounds = 6 + ctx->key1.key_length / 4;
+	int tail = req->cryptlen % AES_BLOCK_SIZE;
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct scatterlist *src, *dst;
+	struct skcipher_walk walk;
+
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	if (unlikely(tail > 0 && walk.nbytes < walk.total)) {
+		int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+					      AES_BLOCK_SIZE) - 2;
+
+		skcipher_walk_abort(&walk);
+
+		skcipher_request_set_tfm(&subreq, tfm);
+		skcipher_request_set_callback(&subreq,
+					      skcipher_request_flags(req),
+					      NULL, NULL);
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   xts_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+		req = &subreq;
+		err = skcipher_walk_virt(&walk, req, false);
+	} else {
+		tail = 0;
+	}
+
+	for (first = 1; walk.nbytes >= AES_BLOCK_SIZE; first = 0) {
+		int nbytes = walk.nbytes;
+
+		if (walk.nbytes < walk.total)
+			nbytes &= ~(AES_BLOCK_SIZE - 1);
+
+		kernel_neon_begin();
+		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				ctx->key1.key_dec, rounds, nbytes,
+				ctx->key2.key_enc, walk.iv, first);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	if (err || likely(!tail))
+		return err;
+
+	dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+	if (req->dst != req->src)
+		dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+	skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, &subreq, false);
+	if (err)
+		return err;
+
+
+	kernel_neon_begin();
+	aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+			ctx->key1.key_dec, rounds, walk.nbytes,
+			ctx->key2.key_enc, walk.iv, first);
+	kernel_neon_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
+static struct skcipher_alg aes_algs[] = { {
+#if defined(USE_V8_CRYPTO_EXTENSIONS) || !IS_ENABLED(CONFIG_CRYPTO_AES_ARM64_BS)
+	.base = {
+		.cra_name		= "__ecb(aes)",
+		.cra_driver_name	= "__ecb-aes-" MODE,
+		.cra_priority		= PRIO,
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= AES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+	.min_keysize	= AES_MIN_KEY_SIZE,
+	.max_keysize	= AES_MAX_KEY_SIZE,
+	.setkey		= skcipher_aes_setkey,
+	.encrypt	= ecb_encrypt,
+	.decrypt	= ecb_decrypt,
+}, {
+	.base = {
+		.cra_name		= "__cbc(aes)",
+		.cra_driver_name	= "__cbc-aes-" MODE,
+		.cra_priority		= PRIO,
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= AES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+	.min_keysize	= AES_MIN_KEY_SIZE,
+	.max_keysize	= AES_MAX_KEY_SIZE,
+	.ivsize		= AES_BLOCK_SIZE,
+	.setkey		= skcipher_aes_setkey,
+	.encrypt	= cbc_encrypt,
+	.decrypt	= cbc_decrypt,
+}, {
+	.base = {
+		.cra_name		= "__ctr(aes)",
+		.cra_driver_name	= "__ctr-aes-" MODE,
+		.cra_priority		= PRIO,
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+	.min_keysize	= AES_MIN_KEY_SIZE,
+	.max_keysize	= AES_MAX_KEY_SIZE,
+	.ivsize		= AES_BLOCK_SIZE,
+	.chunksize	= AES_BLOCK_SIZE,
+	.setkey		= skcipher_aes_setkey,
+	.encrypt	= ctr_encrypt,
+	.decrypt	= ctr_encrypt,
+}, {
+	.base = {
+		.cra_name		= "ctr(aes)",
+		.cra_driver_name	= "ctr-aes-" MODE,
+		.cra_priority		= PRIO - 1,
+		.cra_blocksize		= 1,
+		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+	.min_keysize	= AES_MIN_KEY_SIZE,
+	.max_keysize	= AES_MAX_KEY_SIZE,
+	.ivsize		= AES_BLOCK_SIZE,
+	.chunksize	= AES_BLOCK_SIZE,
+	.setkey		= skcipher_aes_setkey,
+	.encrypt	= ctr_encrypt_sync,
+	.decrypt	= ctr_encrypt_sync,
+}, {
+	.base = {
+		.cra_name		= "__xts(aes)",
+		.cra_driver_name	= "__xts-aes-" MODE,
+		.cra_priority		= PRIO,
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= AES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct crypto_aes_xts_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+	.min_keysize	= 2 * AES_MIN_KEY_SIZE,
+	.max_keysize	= 2 * AES_MAX_KEY_SIZE,
+	.ivsize		= AES_BLOCK_SIZE,
+	.walksize	= 2 * AES_BLOCK_SIZE,
+	.setkey		= xts_set_key,
+	.encrypt	= xts_encrypt,
+	.decrypt	= xts_decrypt,
+}, {
+#endif
+	.base = {
+		.cra_name		= "__cts(cbc(aes))",
+		.cra_driver_name	= "__cts-cbc-aes-" MODE,
+		.cra_priority		= PRIO,
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= AES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+	.min_keysize	= AES_MIN_KEY_SIZE,
+	.max_keysize	= AES_MAX_KEY_SIZE,
+	.ivsize		= AES_BLOCK_SIZE,
+	.walksize	= 2 * AES_BLOCK_SIZE,
+	.setkey		= skcipher_aes_setkey,
+	.encrypt	= cts_cbc_encrypt,
+	.decrypt	= cts_cbc_decrypt,
+}, {
+	.base = {
+		.cra_name		= "__essiv(cbc(aes),sha256)",
+		.cra_driver_name	= "__essiv-cbc-aes-sha256-" MODE,
+		.cra_priority		= PRIO + 1,
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
+		.cra_blocksize		= AES_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct crypto_aes_essiv_cbc_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+	.min_keysize	= AES_MIN_KEY_SIZE,
+	.max_keysize	= AES_MAX_KEY_SIZE,
+	.ivsize		= AES_BLOCK_SIZE,
+	.setkey		= essiv_cbc_set_key,
+	.encrypt	= essiv_cbc_encrypt,
+	.decrypt	= essiv_cbc_decrypt,
+	.init		= essiv_cbc_init_tfm,
+	.exit		= essiv_cbc_exit_tfm,
+} };
+
+static int cbcmac_setkey(struct crypto_shash *tfm, const u8 *in_key,
+			 unsigned int key_len)
+{
+	struct mac_tfm_ctx *ctx = crypto_shash_ctx(tfm);
+
+	return aes_expandkey(&ctx->key, in_key, key_len);
+}
+
+static void cmac_gf128_mul_by_x(be128 *y, const be128 *x)
+{
+	u64 a = be64_to_cpu(x->a);
+	u64 b = be64_to_cpu(x->b);
+
+	y->a = cpu_to_be64((a << 1) | (b >> 63));
+	y->b = cpu_to_be64((b << 1) ^ ((a >> 63) ? 0x87 : 0));
+}
+
+static int cmac_setkey(struct crypto_shash *tfm, const u8 *in_key,
+		       unsigned int key_len)
+{
+	struct mac_tfm_ctx *ctx = crypto_shash_ctx(tfm);
+	be128 *consts = (be128 *)ctx->consts;
+	int rounds = 6 + key_len / 4;
+	int err;
+
+	err = cbcmac_setkey(tfm, in_key, key_len);
+	if (err)
+		return err;
+
+	/* encrypt the zero vector */
+	kernel_neon_begin();
+	aes_ecb_encrypt(ctx->consts, (u8[AES_BLOCK_SIZE]){}, ctx->key.key_enc,
+			rounds, 1);
+	kernel_neon_end();
+
+	cmac_gf128_mul_by_x(consts, consts);
+	cmac_gf128_mul_by_x(consts + 1, consts);
+
+	return 0;
+}
+
+static int xcbc_setkey(struct crypto_shash *tfm, const u8 *in_key,
+		       unsigned int key_len)
+{
+	static u8 const ks[3][AES_BLOCK_SIZE] = {
+		{ [0 ... AES_BLOCK_SIZE - 1] = 0x1 },
+		{ [0 ... AES_BLOCK_SIZE - 1] = 0x2 },
+		{ [0 ... AES_BLOCK_SIZE - 1] = 0x3 },
+	};
+
+	struct mac_tfm_ctx *ctx = crypto_shash_ctx(tfm);
+	int rounds = 6 + key_len / 4;
+	u8 key[AES_BLOCK_SIZE];
+	int err;
+
+	err = cbcmac_setkey(tfm, in_key, key_len);
+	if (err)
+		return err;
+
+	kernel_neon_begin();
+	aes_ecb_encrypt(key, ks[0], ctx->key.key_enc, rounds, 1);
+	aes_ecb_encrypt(ctx->consts, ks[1], ctx->key.key_enc, rounds, 2);
+	kernel_neon_end();
+
+	return cbcmac_setkey(tfm, key, sizeof(key));
+}
+
+static int mac_init(struct shash_desc *desc)
+{
+	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	memset(ctx->dg, 0, AES_BLOCK_SIZE);
+	ctx->len = 0;
+
+	return 0;
+}
+
+static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks,
+			  u8 dg[], int enc_before, int enc_after)
+{
+	int rounds = 6 + ctx->key_length / 4;
+
+	if (crypto_simd_usable()) {
+		kernel_neon_begin();
+		aes_mac_update(in, ctx->key_enc, rounds, blocks, dg, enc_before,
+			       enc_after);
+		kernel_neon_end();
+	} else {
+		if (enc_before)
+			aes_encrypt(ctx, dg, dg);
+
+		while (blocks--) {
+			crypto_xor(dg, in, AES_BLOCK_SIZE);
+			in += AES_BLOCK_SIZE;
+
+			if (blocks || enc_after)
+				aes_encrypt(ctx, dg, dg);
+		}
+	}
+}
+
+static int mac_update(struct shash_desc *desc, const u8 *p, unsigned int len)
+{
+	struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	while (len > 0) {
+		unsigned int l;
+
+		if ((ctx->len % AES_BLOCK_SIZE) == 0 &&
+		    (ctx->len + len) > AES_BLOCK_SIZE) {
+
+			int blocks = len / AES_BLOCK_SIZE;
+
+			len %= AES_BLOCK_SIZE;
+
+			mac_do_update(&tctx->key, p, blocks, ctx->dg,
+				      (ctx->len != 0), (len != 0));
+
+			p += blocks * AES_BLOCK_SIZE;
+
+			if (!len) {
+				ctx->len = AES_BLOCK_SIZE;
+				break;
+			}
+			ctx->len = 0;
+		}
+
+		l = min(len, AES_BLOCK_SIZE - ctx->len);
+
+		if (l <= AES_BLOCK_SIZE) {
+			crypto_xor(ctx->dg + ctx->len, p, l);
+			ctx->len += l;
+			len -= l;
+			p += l;
+		}
+	}
+
+	return 0;
+}
+
+static int cbcmac_final(struct shash_desc *desc, u8 *out)
+{
+	struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	mac_do_update(&tctx->key, NULL, 0, ctx->dg, (ctx->len != 0), 0);
+
+	memcpy(out, ctx->dg, AES_BLOCK_SIZE);
+
+	return 0;
+}
+
+static int cmac_final(struct shash_desc *desc, u8 *out)
+{
+	struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
+	u8 *consts = tctx->consts;
+
+	if (ctx->len != AES_BLOCK_SIZE) {
+		ctx->dg[ctx->len] ^= 0x80;
+		consts += AES_BLOCK_SIZE;
+	}
+
+	mac_do_update(&tctx->key, consts, 1, ctx->dg, 0, 1);
+
+	memcpy(out, ctx->dg, AES_BLOCK_SIZE);
+
+	return 0;
+}
+
+static struct shash_alg mac_algs[] = { {
+	.base.cra_name		= "cmac(aes)",
+	.base.cra_driver_name	= "cmac-aes-" MODE,
+	.base.cra_priority	= PRIO,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx) +
+				  2 * AES_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= AES_BLOCK_SIZE,
+	.init			= mac_init,
+	.update			= mac_update,
+	.final			= cmac_final,
+	.setkey			= cmac_setkey,
+	.descsize		= sizeof(struct mac_desc_ctx),
+}, {
+	.base.cra_name		= "xcbc(aes)",
+	.base.cra_driver_name	= "xcbc-aes-" MODE,
+	.base.cra_priority	= PRIO,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx) +
+				  2 * AES_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= AES_BLOCK_SIZE,
+	.init			= mac_init,
+	.update			= mac_update,
+	.final			= cmac_final,
+	.setkey			= xcbc_setkey,
+	.descsize		= sizeof(struct mac_desc_ctx),
+}, {
+	.base.cra_name		= "cbcmac(aes)",
+	.base.cra_driver_name	= "cbcmac-aes-" MODE,
+	.base.cra_priority	= PRIO,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= AES_BLOCK_SIZE,
+	.init			= mac_init,
+	.update			= mac_update,
+	.final			= cbcmac_final,
+	.setkey			= cbcmac_setkey,
+	.descsize		= sizeof(struct mac_desc_ctx),
+} };
+
+static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
+
+static void aes_exit(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(aes_simd_algs); i++)
+		if (aes_simd_algs[i])
+			simd_skcipher_free(aes_simd_algs[i]);
+
+	crypto_unregister_shashes(mac_algs, ARRAY_SIZE(mac_algs));
+	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static int __init aes_init(void)
+{
+	struct simd_skcipher_alg *simd;
+	const char *basename;
+	const char *algname;
+	const char *drvname;
+	int err;
+	int i;
+
+	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+	if (err)
+		return err;
+
+	err = crypto_register_shashes(mac_algs, ARRAY_SIZE(mac_algs));
+	if (err)
+		goto unregister_ciphers;
+
+	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+		if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
+			continue;
+
+		algname = aes_algs[i].base.cra_name + 2;
+		drvname = aes_algs[i].base.cra_driver_name + 2;
+		basename = aes_algs[i].base.cra_driver_name;
+		simd = simd_skcipher_create_compat(algname, drvname, basename);
+		err = PTR_ERR(simd);
+		if (IS_ERR(simd))
+			goto unregister_simds;
+
+		aes_simd_algs[i] = simd;
+	}
+
+	return 0;
+
+unregister_simds:
+	aes_exit();
+	return err;
+unregister_ciphers:
+	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+	return err;
+}
+
+#ifdef USE_V8_CRYPTO_EXTENSIONS
+module_cpu_feature_match(AES, aes_init);
+#else
+module_init(aes_init);
+EXPORT_SYMBOL(neon_aes_ecb_encrypt);
+EXPORT_SYMBOL(neon_aes_cbc_encrypt);
+EXPORT_SYMBOL(neon_aes_xts_encrypt);
+EXPORT_SYMBOL(neon_aes_xts_decrypt);
+#endif
+module_exit(aes_exit);
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
new file mode 100644
index 000000000..cf618d8f6
--- /dev/null
+++ b/arch/arm64/crypto/aes-modes.S
@@ -0,0 +1,679 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * linux/arch/arm64/crypto/aes-modes.S - chaining mode wrappers for AES
+ *
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+/* included by aes-ce.S and aes-neon.S */
+
+	.text
+	.align		4
+
+#ifndef MAX_STRIDE
+#define MAX_STRIDE	4
+#endif
+
+#if MAX_STRIDE == 4
+#define ST4(x...) x
+#define ST5(x...)
+#else
+#define ST4(x...)
+#define ST5(x...) x
+#endif
+
+SYM_FUNC_START_LOCAL(aes_encrypt_block4x)
+	encrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
+	ret
+SYM_FUNC_END(aes_encrypt_block4x)
+
+SYM_FUNC_START_LOCAL(aes_decrypt_block4x)
+	decrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
+	ret
+SYM_FUNC_END(aes_decrypt_block4x)
+
+#if MAX_STRIDE == 5
+SYM_FUNC_START_LOCAL(aes_encrypt_block5x)
+	encrypt_block5x	v0, v1, v2, v3, v4, w3, x2, x8, w7
+	ret
+SYM_FUNC_END(aes_encrypt_block5x)
+
+SYM_FUNC_START_LOCAL(aes_decrypt_block5x)
+	decrypt_block5x	v0, v1, v2, v3, v4, w3, x2, x8, w7
+	ret
+SYM_FUNC_END(aes_decrypt_block5x)
+#endif
+
+	/*
+	 * 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)
+	 */
+
+AES_FUNC_START(aes_ecb_encrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	enc_prepare	w3, x2, x5
+
+.LecbencloopNx:
+	subs		w4, w4, #MAX_STRIDE
+	bmi		.Lecbenc1x
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+ST4(	bl		aes_encrypt_block4x		)
+ST5(	ld1		{v4.16b}, [x1], #16		)
+ST5(	bl		aes_encrypt_block5x		)
+	st1		{v0.16b-v3.16b}, [x0], #64
+ST5(	st1		{v4.16b}, [x0], #16		)
+	b		.LecbencloopNx
+.Lecbenc1x:
+	adds		w4, w4, #MAX_STRIDE
+	beq		.Lecbencout
+.Lecbencloop:
+	ld1		{v0.16b}, [x1], #16		/* get next pt block */
+	encrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lecbencloop
+.Lecbencout:
+	ldp		x29, x30, [sp], #16
+	ret
+AES_FUNC_END(aes_ecb_encrypt)
+
+
+AES_FUNC_START(aes_ecb_decrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	dec_prepare	w3, x2, x5
+
+.LecbdecloopNx:
+	subs		w4, w4, #MAX_STRIDE
+	bmi		.Lecbdec1x
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+ST4(	bl		aes_decrypt_block4x		)
+ST5(	ld1		{v4.16b}, [x1], #16		)
+ST5(	bl		aes_decrypt_block5x		)
+	st1		{v0.16b-v3.16b}, [x0], #64
+ST5(	st1		{v4.16b}, [x0], #16		)
+	b		.LecbdecloopNx
+.Lecbdec1x:
+	adds		w4, w4, #MAX_STRIDE
+	beq		.Lecbdecout
+.Lecbdecloop:
+	ld1		{v0.16b}, [x1], #16		/* get next ct block */
+	decrypt_block	v0, w3, x2, x5, w6
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lecbdecloop
+.Lecbdecout:
+	ldp		x29, x30, [sp], #16
+	ret
+AES_FUNC_END(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[])
+	 * aes_essiv_cbc_encrypt(u8 out[], u8 const in[], u32 const rk1[],
+	 *			 int rounds, int blocks, u8 iv[],
+	 *			 u32 const rk2[]);
+	 * aes_essiv_cbc_decrypt(u8 out[], u8 const in[], u32 const rk1[],
+	 *			 int rounds, int blocks, u8 iv[],
+	 *			 u32 const rk2[]);
+	 */
+
+AES_FUNC_START(aes_essiv_cbc_encrypt)
+	ld1		{v4.16b}, [x5]			/* get iv */
+
+	mov		w8, #14				/* AES-256: 14 rounds */
+	enc_prepare	w8, x6, x7
+	encrypt_block	v4, w8, x6, x7, w9
+	enc_switch_key	w3, x2, x6
+	b		.Lcbcencloop4x
+
+AES_FUNC_START(aes_cbc_encrypt)
+	ld1		{v4.16b}, [x5]			/* get iv */
+	enc_prepare	w3, x2, x6
+
+.Lcbcencloop4x:
+	subs		w4, w4, #4
+	bmi		.Lcbcenc1x
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	eor		v0.16b, v0.16b, v4.16b		/* ..and xor with iv */
+	encrypt_block	v0, w3, x2, x6, w7
+	eor		v1.16b, v1.16b, v0.16b
+	encrypt_block	v1, w3, x2, x6, w7
+	eor		v2.16b, v2.16b, v1.16b
+	encrypt_block	v2, w3, x2, x6, w7
+	eor		v3.16b, v3.16b, v2.16b
+	encrypt_block	v3, w3, x2, x6, w7
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v3.16b
+	b		.Lcbcencloop4x
+.Lcbcenc1x:
+	adds		w4, w4, #4
+	beq		.Lcbcencout
+.Lcbcencloop:
+	ld1		{v0.16b}, [x1], #16		/* get next pt block */
+	eor		v4.16b, v4.16b, v0.16b		/* ..and xor with iv */
+	encrypt_block	v4, w3, x2, x6, w7
+	st1		{v4.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lcbcencloop
+.Lcbcencout:
+	st1		{v4.16b}, [x5]			/* return iv */
+	ret
+AES_FUNC_END(aes_cbc_encrypt)
+AES_FUNC_END(aes_essiv_cbc_encrypt)
+
+AES_FUNC_START(aes_essiv_cbc_decrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	ld1		{cbciv.16b}, [x5]		/* get iv */
+
+	mov		w8, #14				/* AES-256: 14 rounds */
+	enc_prepare	w8, x6, x7
+	encrypt_block	cbciv, w8, x6, x7, w9
+	b		.Lessivcbcdecstart
+
+AES_FUNC_START(aes_cbc_decrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	ld1		{cbciv.16b}, [x5]		/* get iv */
+.Lessivcbcdecstart:
+	dec_prepare	w3, x2, x6
+
+.LcbcdecloopNx:
+	subs		w4, w4, #MAX_STRIDE
+	bmi		.Lcbcdec1x
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+#if MAX_STRIDE == 5
+	ld1		{v4.16b}, [x1], #16		/* get 1 ct block */
+	mov		v5.16b, v0.16b
+	mov		v6.16b, v1.16b
+	mov		v7.16b, v2.16b
+	bl		aes_decrypt_block5x
+	sub		x1, x1, #32
+	eor		v0.16b, v0.16b, cbciv.16b
+	eor		v1.16b, v1.16b, v5.16b
+	ld1		{v5.16b}, [x1], #16		/* reload 1 ct block */
+	ld1		{cbciv.16b}, [x1], #16		/* reload 1 ct block */
+	eor		v2.16b, v2.16b, v6.16b
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v4.16b, v4.16b, v5.16b
+#else
+	mov		v4.16b, v0.16b
+	mov		v5.16b, v1.16b
+	mov		v6.16b, v2.16b
+	bl		aes_decrypt_block4x
+	sub		x1, x1, #16
+	eor		v0.16b, v0.16b, cbciv.16b
+	eor		v1.16b, v1.16b, v4.16b
+	ld1		{cbciv.16b}, [x1], #16		/* reload 1 ct block */
+	eor		v2.16b, v2.16b, v5.16b
+	eor		v3.16b, v3.16b, v6.16b
+#endif
+	st1		{v0.16b-v3.16b}, [x0], #64
+ST5(	st1		{v4.16b}, [x0], #16		)
+	b		.LcbcdecloopNx
+.Lcbcdec1x:
+	adds		w4, w4, #MAX_STRIDE
+	beq		.Lcbcdecout
+.Lcbcdecloop:
+	ld1		{v1.16b}, [x1], #16		/* get next ct block */
+	mov		v0.16b, v1.16b			/* ...and copy to v0 */
+	decrypt_block	v0, w3, x2, x6, w7
+	eor		v0.16b, v0.16b, cbciv.16b	/* xor with iv => pt */
+	mov		cbciv.16b, v1.16b		/* ct is next iv */
+	st1		{v0.16b}, [x0], #16
+	subs		w4, w4, #1
+	bne		.Lcbcdecloop
+.Lcbcdecout:
+	st1		{cbciv.16b}, [x5]		/* return iv */
+	ldp		x29, x30, [sp], #16
+	ret
+AES_FUNC_END(aes_cbc_decrypt)
+AES_FUNC_END(aes_essiv_cbc_decrypt)
+
+
+	/*
+	 * aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
+	 *		       int rounds, int bytes, u8 const iv[])
+	 * aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
+	 *		       int rounds, int bytes, u8 const iv[])
+	 */
+
+AES_FUNC_START(aes_cbc_cts_encrypt)
+	adr_l		x8, .Lcts_permute_table
+	sub		x4, x4, #16
+	add		x9, x8, #32
+	add		x8, x8, x4
+	sub		x9, x9, x4
+	ld1		{v3.16b}, [x8]
+	ld1		{v4.16b}, [x9]
+
+	ld1		{v0.16b}, [x1], x4		/* overlapping loads */
+	ld1		{v1.16b}, [x1]
+
+	ld1		{v5.16b}, [x5]			/* get iv */
+	enc_prepare	w3, x2, x6
+
+	eor		v0.16b, v0.16b, v5.16b		/* xor with iv */
+	tbl		v1.16b, {v1.16b}, v4.16b
+	encrypt_block	v0, w3, x2, x6, w7
+
+	eor		v1.16b, v1.16b, v0.16b
+	tbl		v0.16b, {v0.16b}, v3.16b
+	encrypt_block	v1, w3, x2, x6, w7
+
+	add		x4, x0, x4
+	st1		{v0.16b}, [x4]			/* overlapping stores */
+	st1		{v1.16b}, [x0]
+	ret
+AES_FUNC_END(aes_cbc_cts_encrypt)
+
+AES_FUNC_START(aes_cbc_cts_decrypt)
+	adr_l		x8, .Lcts_permute_table
+	sub		x4, x4, #16
+	add		x9, x8, #32
+	add		x8, x8, x4
+	sub		x9, x9, x4
+	ld1		{v3.16b}, [x8]
+	ld1		{v4.16b}, [x9]
+
+	ld1		{v0.16b}, [x1], x4		/* overlapping loads */
+	ld1		{v1.16b}, [x1]
+
+	ld1		{v5.16b}, [x5]			/* get iv */
+	dec_prepare	w3, x2, x6
+
+	decrypt_block	v0, w3, x2, x6, w7
+	tbl		v2.16b, {v0.16b}, v3.16b
+	eor		v2.16b, v2.16b, v1.16b
+
+	tbx		v0.16b, {v1.16b}, v4.16b
+	decrypt_block	v0, w3, x2, x6, w7
+	eor		v0.16b, v0.16b, v5.16b		/* xor with iv */
+
+	add		x4, x0, x4
+	st1		{v2.16b}, [x4]			/* overlapping stores */
+	st1		{v0.16b}, [x0]
+	ret
+AES_FUNC_END(aes_cbc_cts_decrypt)
+
+	.section	".rodata", "a"
+	.align		6
+.Lcts_permute_table:
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
+	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe,  0xf
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.previous
+
+
+	/*
+	 * aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		   int blocks, u8 ctr[])
+	 */
+
+AES_FUNC_START(aes_ctr_encrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	enc_prepare	w3, x2, x6
+	ld1		{vctr.16b}, [x5]
+
+	umov		x6, vctr.d[1]		/* keep swabbed ctr in reg */
+	rev		x6, x6
+	cmn		w6, w4			/* 32 bit overflow? */
+	bcs		.Lctrloop
+.LctrloopNx:
+	subs		w4, w4, #MAX_STRIDE
+	bmi		.Lctr1x
+	add		w7, w6, #1
+	mov		v0.16b, vctr.16b
+	add		w8, w6, #2
+	mov		v1.16b, vctr.16b
+	add		w9, w6, #3
+	mov		v2.16b, vctr.16b
+	add		w9, w6, #3
+	rev		w7, w7
+	mov		v3.16b, vctr.16b
+	rev		w8, w8
+ST5(	mov		v4.16b, vctr.16b		)
+	mov		v1.s[3], w7
+	rev		w9, w9
+ST5(	add		w10, w6, #4			)
+	mov		v2.s[3], w8
+ST5(	rev		w10, w10			)
+	mov		v3.s[3], w9
+ST5(	mov		v4.s[3], w10			)
+	ld1		{v5.16b-v7.16b}, [x1], #48	/* get 3 input blocks */
+ST4(	bl		aes_encrypt_block4x		)
+ST5(	bl		aes_encrypt_block5x		)
+	eor		v0.16b, v5.16b, v0.16b
+ST4(	ld1		{v5.16b}, [x1], #16		)
+	eor		v1.16b, v6.16b, v1.16b
+ST5(	ld1		{v5.16b-v6.16b}, [x1], #32	)
+	eor		v2.16b, v7.16b, v2.16b
+	eor		v3.16b, v5.16b, v3.16b
+ST5(	eor		v4.16b, v6.16b, v4.16b		)
+	st1		{v0.16b-v3.16b}, [x0], #64
+ST5(	st1		{v4.16b}, [x0], #16		)
+	add		x6, x6, #MAX_STRIDE
+	rev		x7, x6
+	ins		vctr.d[1], x7
+	cbz		w4, .Lctrout
+	b		.LctrloopNx
+.Lctr1x:
+	adds		w4, w4, #MAX_STRIDE
+	beq		.Lctrout
+.Lctrloop:
+	mov		v0.16b, vctr.16b
+	encrypt_block	v0, w3, x2, x8, w7
+
+	adds		x6, x6, #1		/* increment BE ctr */
+	rev		x7, x6
+	ins		vctr.d[1], x7
+	bcs		.Lctrcarry		/* overflow? */
+
+.Lctrcarrydone:
+	subs		w4, w4, #1
+	bmi		.Lctrtailblock		/* blocks <0 means tail block */
+	ld1		{v3.16b}, [x1], #16
+	eor		v3.16b, v0.16b, v3.16b
+	st1		{v3.16b}, [x0], #16
+	bne		.Lctrloop
+
+.Lctrout:
+	st1		{vctr.16b}, [x5]	/* return next CTR value */
+	ldp		x29, x30, [sp], #16
+	ret
+
+.Lctrtailblock:
+	st1		{v0.16b}, [x0]
+	b		.Lctrout
+
+.Lctrcarry:
+	umov		x7, vctr.d[0]		/* load upper word of ctr  */
+	rev		x7, x7			/* ... to handle the carry */
+	add		x7, x7, #1
+	rev		x7, x7
+	ins		vctr.d[0], x7
+	b		.Lctrcarrydone
+AES_FUNC_END(aes_ctr_encrypt)
+
+
+	/*
+	 * aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int bytes, u8 const rk2[], u8 iv[], int first)
+	 * aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[], int rounds,
+	 *		   int bytes, u8 const rk2[], u8 iv[], int first)
+	 */
+
+	.macro		next_tweak, out, in, tmp
+	sshr		\tmp\().2d,  \in\().2d,   #63
+	and		\tmp\().16b, \tmp\().16b, xtsmask.16b
+	add		\out\().2d,  \in\().2d,   \in\().2d
+	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+	eor		\out\().16b, \out\().16b, \tmp\().16b
+	.endm
+
+	.macro		xts_load_mask, tmp
+	movi		xtsmask.2s, #0x1
+	movi		\tmp\().2s, #0x87
+	uzp1		xtsmask.4s, xtsmask.4s, \tmp\().4s
+	.endm
+
+AES_FUNC_START(aes_xts_encrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	ld1		{v4.16b}, [x6]
+	xts_load_mask	v8
+	cbz		w7, .Lxtsencnotfirst
+
+	enc_prepare	w3, x5, x8
+	xts_cts_skip_tw	w7, .LxtsencNx
+	encrypt_block	v4, w3, x5, x8, w7		/* first tweak */
+	enc_switch_key	w3, x2, x8
+	b		.LxtsencNx
+
+.Lxtsencnotfirst:
+	enc_prepare	w3, x2, x8
+.LxtsencloopNx:
+	next_tweak	v4, v4, v8
+.LxtsencNx:
+	subs		w4, w4, #64
+	bmi		.Lxtsenc1x
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	next_tweak	v5, v4, v8
+	eor		v0.16b, v0.16b, v4.16b
+	next_tweak	v6, v5, v8
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	next_tweak	v7, v6, v8
+	eor		v3.16b, v3.16b, v7.16b
+	bl		aes_encrypt_block4x
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v7.16b
+	cbz		w4, .Lxtsencret
+	xts_reload_mask	v8
+	b		.LxtsencloopNx
+.Lxtsenc1x:
+	adds		w4, w4, #64
+	beq		.Lxtsencout
+	subs		w4, w4, #16
+	bmi		.LxtsencctsNx
+.Lxtsencloop:
+	ld1		{v0.16b}, [x1], #16
+.Lxtsencctsout:
+	eor		v0.16b, v0.16b, v4.16b
+	encrypt_block	v0, w3, x2, x8, w7
+	eor		v0.16b, v0.16b, v4.16b
+	cbz		w4, .Lxtsencout
+	subs		w4, w4, #16
+	next_tweak	v4, v4, v8
+	bmi		.Lxtsenccts
+	st1		{v0.16b}, [x0], #16
+	b		.Lxtsencloop
+.Lxtsencout:
+	st1		{v0.16b}, [x0]
+.Lxtsencret:
+	st1		{v4.16b}, [x6]
+	ldp		x29, x30, [sp], #16
+	ret
+
+.LxtsencctsNx:
+	mov		v0.16b, v3.16b
+	sub		x0, x0, #16
+.Lxtsenccts:
+	adr_l		x8, .Lcts_permute_table
+
+	add		x1, x1, w4, sxtw	/* rewind input pointer */
+	add		w4, w4, #16		/* # bytes in final block */
+	add		x9, x8, #32
+	add		x8, x8, x4
+	sub		x9, x9, x4
+	add		x4, x0, x4		/* output address of final block */
+
+	ld1		{v1.16b}, [x1]		/* load final block */
+	ld1		{v2.16b}, [x8]
+	ld1		{v3.16b}, [x9]
+
+	tbl		v2.16b, {v0.16b}, v2.16b
+	tbx		v0.16b, {v1.16b}, v3.16b
+	st1		{v2.16b}, [x4]			/* overlapping stores */
+	mov		w4, wzr
+	b		.Lxtsencctsout
+AES_FUNC_END(aes_xts_encrypt)
+
+AES_FUNC_START(aes_xts_decrypt)
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	/* subtract 16 bytes if we are doing CTS */
+	sub		w8, w4, #0x10
+	tst		w4, #0xf
+	csel		w4, w4, w8, eq
+
+	ld1		{v4.16b}, [x6]
+	xts_load_mask	v8
+	xts_cts_skip_tw	w7, .Lxtsdecskiptw
+	cbz		w7, .Lxtsdecnotfirst
+
+	enc_prepare	w3, x5, x8
+	encrypt_block	v4, w3, x5, x8, w7		/* first tweak */
+.Lxtsdecskiptw:
+	dec_prepare	w3, x2, x8
+	b		.LxtsdecNx
+
+.Lxtsdecnotfirst:
+	dec_prepare	w3, x2, x8
+.LxtsdecloopNx:
+	next_tweak	v4, v4, v8
+.LxtsdecNx:
+	subs		w4, w4, #64
+	bmi		.Lxtsdec1x
+	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	next_tweak	v5, v4, v8
+	eor		v0.16b, v0.16b, v4.16b
+	next_tweak	v6, v5, v8
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	next_tweak	v7, v6, v8
+	eor		v3.16b, v3.16b, v7.16b
+	bl		aes_decrypt_block4x
+	eor		v3.16b, v3.16b, v7.16b
+	eor		v0.16b, v0.16b, v4.16b
+	eor		v1.16b, v1.16b, v5.16b
+	eor		v2.16b, v2.16b, v6.16b
+	st1		{v0.16b-v3.16b}, [x0], #64
+	mov		v4.16b, v7.16b
+	cbz		w4, .Lxtsdecout
+	xts_reload_mask	v8
+	b		.LxtsdecloopNx
+.Lxtsdec1x:
+	adds		w4, w4, #64
+	beq		.Lxtsdecout
+	subs		w4, w4, #16
+.Lxtsdecloop:
+	ld1		{v0.16b}, [x1], #16
+	bmi		.Lxtsdeccts
+.Lxtsdecctsout:
+	eor		v0.16b, v0.16b, v4.16b
+	decrypt_block	v0, w3, x2, x8, w7
+	eor		v0.16b, v0.16b, v4.16b
+	st1		{v0.16b}, [x0], #16
+	cbz		w4, .Lxtsdecout
+	subs		w4, w4, #16
+	next_tweak	v4, v4, v8
+	b		.Lxtsdecloop
+.Lxtsdecout:
+	st1		{v4.16b}, [x6]
+	ldp		x29, x30, [sp], #16
+	ret
+
+.Lxtsdeccts:
+	adr_l		x8, .Lcts_permute_table
+
+	add		x1, x1, w4, sxtw	/* rewind input pointer */
+	add		w4, w4, #16		/* # bytes in final block */
+	add		x9, x8, #32
+	add		x8, x8, x4
+	sub		x9, x9, x4
+	add		x4, x0, x4		/* output address of final block */
+
+	next_tweak	v5, v4, v8
+
+	ld1		{v1.16b}, [x1]		/* load final block */
+	ld1		{v2.16b}, [x8]
+	ld1		{v3.16b}, [x9]
+
+	eor		v0.16b, v0.16b, v5.16b
+	decrypt_block	v0, w3, x2, x8, w7
+	eor		v0.16b, v0.16b, v5.16b
+
+	tbl		v2.16b, {v0.16b}, v2.16b
+	tbx		v0.16b, {v1.16b}, v3.16b
+
+	st1		{v2.16b}, [x4]			/* overlapping stores */
+	mov		w4, wzr
+	b		.Lxtsdecctsout
+AES_FUNC_END(aes_xts_decrypt)
+
+	/*
+	 * aes_mac_update(u8 const in[], u32 const rk[], int rounds,
+	 *		  int blocks, u8 dg[], int enc_before, int enc_after)
+	 */
+AES_FUNC_START(aes_mac_update)
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x6
+
+	ld1		{v0.16b}, [x23]			/* get dg */
+	enc_prepare	w2, x1, x7
+	cbz		w5, .Lmacloop4x
+
+	encrypt_block	v0, w2, x1, x7, w8
+
+.Lmacloop4x:
+	subs		w22, w22, #4
+	bmi		.Lmac1x
+	ld1		{v1.16b-v4.16b}, [x19], #64	/* get next pt block */
+	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
+	encrypt_block	v0, w21, x20, x7, w8
+	eor		v0.16b, v0.16b, v2.16b
+	encrypt_block	v0, w21, x20, x7, w8
+	eor		v0.16b, v0.16b, v3.16b
+	encrypt_block	v0, w21, x20, x7, w8
+	eor		v0.16b, v0.16b, v4.16b
+	cmp		w22, wzr
+	csinv		x5, x24, xzr, eq
+	cbz		w5, .Lmacout
+	encrypt_block	v0, w21, x20, x7, w8
+	st1		{v0.16b}, [x23]			/* return dg */
+	cond_yield_neon	.Lmacrestart
+	b		.Lmacloop4x
+.Lmac1x:
+	add		w22, w22, #4
+.Lmacloop:
+	cbz		w22, .Lmacout
+	ld1		{v1.16b}, [x19], #16		/* get next pt block */
+	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
+
+	subs		w22, w22, #1
+	csinv		x5, x24, xzr, eq
+	cbz		w5, .Lmacout
+
+.Lmacenc:
+	encrypt_block	v0, w21, x20, x7, w8
+	b		.Lmacloop
+
+.Lmacout:
+	st1		{v0.16b}, [x23]			/* return dg */
+	frame_pop
+	ret
+
+.Lmacrestart:
+	ld1		{v0.16b}, [x23]			/* get dg */
+	enc_prepare	w21, x20, x0
+	b		.Lmacloop4x
+AES_FUNC_END(aes_mac_update)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
new file mode 100644
index 000000000..e47d3ec2c
--- /dev/null
+++ b/arch/arm64/crypto/aes-neon.S
@@ -0,0 +1,250 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * linux/arch/arm64/crypto/aes-neon.S - AES cipher for ARMv8 NEON
+ *
+ * Copyright (C) 2013 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#define AES_FUNC_START(func)		SYM_FUNC_START(neon_ ## func)
+#define AES_FUNC_END(func)		SYM_FUNC_END(neon_ ## func)
+
+	xtsmask		.req	v7
+	cbciv		.req	v7
+	vctr		.req	v4
+
+	.macro		xts_reload_mask, tmp
+	xts_load_mask	\tmp
+	.endm
+
+	/* special case for the neon-bs driver calling into this one for CTS */
+	.macro		xts_cts_skip_tw, reg, lbl
+	tbnz		\reg, #1, \lbl
+	.endm
+
+	/* multiply by polynomial 'x' in GF(2^8) */
+	.macro		mul_by_x, out, in, temp, const
+	sshr		\temp, \in, #7
+	shl		\out, \in, #1
+	and		\temp, \temp, \const
+	eor		\out, \out, \temp
+	.endm
+
+	/* multiply by polynomial 'x^2' in GF(2^8) */
+	.macro		mul_by_x2, out, in, temp, const
+	ushr		\temp, \in, #6
+	shl		\out, \in, #2
+	pmul		\temp, \temp, \const
+	eor		\out, \out, \temp
+	.endm
+
+	/* preload the entire Sbox */
+	.macro		prepare, sbox, shiftrows, temp
+	movi		v12.16b, #0x1b
+	ldr_l		q13, \shiftrows, \temp
+	ldr_l		q14, .Lror32by8, \temp
+	adr_l		\temp, \sbox
+	ld1		{v16.16b-v19.16b}, [\temp], #64
+	ld1		{v20.16b-v23.16b}, [\temp], #64
+	ld1		{v24.16b-v27.16b}, [\temp], #64
+	ld1		{v28.16b-v31.16b}, [\temp]
+	.endm
+
+	/* do preload for encryption */
+	.macro		enc_prepare, ignore0, ignore1, temp
+	prepare		crypto_aes_sbox, .LForward_ShiftRows, \temp
+	.endm
+
+	.macro		enc_switch_key, ignore0, ignore1, temp
+	/* do nothing */
+	.endm
+
+	/* do preload for decryption */
+	.macro		dec_prepare, ignore0, ignore1, temp
+	prepare		crypto_aes_inv_sbox, .LReverse_ShiftRows, \temp
+	.endm
+
+	/* apply SubBytes transformation using the the preloaded Sbox */
+	.macro		sub_bytes, in
+	sub		v9.16b, \in\().16b, v15.16b
+	tbl		\in\().16b, {v16.16b-v19.16b}, \in\().16b
+	sub		v10.16b, v9.16b, v15.16b
+	tbx		\in\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v11.16b, v10.16b, v15.16b
+	tbx		\in\().16b, {v24.16b-v27.16b}, v10.16b
+	tbx		\in\().16b, {v28.16b-v31.16b}, v11.16b
+	.endm
+
+	/* apply MixColumns transformation */
+	.macro		mix_columns, in, enc
+	.if		\enc == 0
+	/* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
+	mul_by_x2	v8.16b, \in\().16b, v9.16b, v12.16b
+	eor		\in\().16b, \in\().16b, v8.16b
+	rev32		v8.8h, v8.8h
+	eor		\in\().16b, \in\().16b, v8.16b
+	.endif
+
+	mul_by_x	v9.16b, \in\().16b, v8.16b, v12.16b
+	rev32		v8.8h, \in\().8h
+	eor		v8.16b, v8.16b, v9.16b
+	eor		\in\().16b, \in\().16b, v8.16b
+	tbl		\in\().16b, {\in\().16b}, v14.16b
+	eor		\in\().16b, \in\().16b, v8.16b
+	.endm
+
+	.macro		do_block, enc, in, rounds, rk, rkp, i
+	ld1		{v15.4s}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	movi		v15.16b, #0x40
+	tbl		\in\().16b, {\in\().16b}, v13.16b	/* ShiftRows */
+	sub_bytes	\in
+	subs		\i, \i, #1
+	ld1		{v15.4s}, [\rkp], #16
+	beq		2222f
+	mix_columns	\in, \enc
+	b		1111b
+2222:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	.endm
+
+	.macro		encrypt_block, in, rounds, rk, rkp, i
+	do_block	1, \in, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block, in, rounds, rk, rkp, i
+	do_block	0, \in, \rounds, \rk, \rkp, \i
+	.endm
+
+	/*
+	 * Interleaved versions: functionally equivalent to the
+	 * ones above, but applied to AES states in parallel.
+	 */
+
+	.macro		sub_bytes_4x, in0, in1, in2, in3
+	sub		v8.16b, \in0\().16b, v15.16b
+	tbl		\in0\().16b, {v16.16b-v19.16b}, \in0\().16b
+	sub		v9.16b, \in1\().16b, v15.16b
+	tbl		\in1\().16b, {v16.16b-v19.16b}, \in1\().16b
+	sub		v10.16b, \in2\().16b, v15.16b
+	tbl		\in2\().16b, {v16.16b-v19.16b}, \in2\().16b
+	sub		v11.16b, \in3\().16b, v15.16b
+	tbl		\in3\().16b, {v16.16b-v19.16b}, \in3\().16b
+	tbx		\in0\().16b, {v20.16b-v23.16b}, v8.16b
+	tbx		\in1\().16b, {v20.16b-v23.16b}, v9.16b
+	sub		v8.16b, v8.16b, v15.16b
+	tbx		\in2\().16b, {v20.16b-v23.16b}, v10.16b
+	sub		v9.16b, v9.16b, v15.16b
+	tbx		\in3\().16b, {v20.16b-v23.16b}, v11.16b
+	sub		v10.16b, v10.16b, v15.16b
+	tbx		\in0\().16b, {v24.16b-v27.16b}, v8.16b
+	sub		v11.16b, v11.16b, v15.16b
+	tbx		\in1\().16b, {v24.16b-v27.16b}, v9.16b
+	sub		v8.16b, v8.16b, v15.16b
+	tbx		\in2\().16b, {v24.16b-v27.16b}, v10.16b
+	sub		v9.16b, v9.16b, v15.16b
+	tbx		\in3\().16b, {v24.16b-v27.16b}, v11.16b
+	sub		v10.16b, v10.16b, v15.16b
+	tbx		\in0\().16b, {v28.16b-v31.16b}, v8.16b
+	sub		v11.16b, v11.16b, v15.16b
+	tbx		\in1\().16b, {v28.16b-v31.16b}, v9.16b
+	tbx		\in2\().16b, {v28.16b-v31.16b}, v10.16b
+	tbx		\in3\().16b, {v28.16b-v31.16b}, v11.16b
+	.endm
+
+	.macro		mul_by_x_2x, out0, out1, in0, in1, tmp0, tmp1, const
+	sshr		\tmp0\().16b, \in0\().16b, #7
+	shl		\out0\().16b, \in0\().16b, #1
+	sshr		\tmp1\().16b, \in1\().16b, #7
+	and		\tmp0\().16b, \tmp0\().16b, \const\().16b
+	shl		\out1\().16b, \in1\().16b, #1
+	and		\tmp1\().16b, \tmp1\().16b, \const\().16b
+	eor		\out0\().16b, \out0\().16b, \tmp0\().16b
+	eor		\out1\().16b, \out1\().16b, \tmp1\().16b
+	.endm
+
+	.macro		mul_by_x2_2x, out0, out1, in0, in1, tmp0, tmp1, const
+	ushr		\tmp0\().16b, \in0\().16b, #6
+	shl		\out0\().16b, \in0\().16b, #2
+	ushr		\tmp1\().16b, \in1\().16b, #6
+	pmul		\tmp0\().16b, \tmp0\().16b, \const\().16b
+	shl		\out1\().16b, \in1\().16b, #2
+	pmul		\tmp1\().16b, \tmp1\().16b, \const\().16b
+	eor		\out0\().16b, \out0\().16b, \tmp0\().16b
+	eor		\out1\().16b, \out1\().16b, \tmp1\().16b
+	.endm
+
+	.macro		mix_columns_2x, in0, in1, enc
+	.if		\enc == 0
+	/* Inverse MixColumns: pre-multiply by { 5, 0, 4, 0 } */
+	mul_by_x2_2x	v8, v9, \in0, \in1, v10, v11, v12
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	rev32		v8.8h, v8.8h
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	rev32		v9.8h, v9.8h
+	eor		\in0\().16b, \in0\().16b, v8.16b
+	eor		\in1\().16b, \in1\().16b, v9.16b
+	.endif
+
+	mul_by_x_2x	v8, v9, \in0, \in1, v10, v11, v12
+	rev32		v10.8h, \in0\().8h
+	rev32		v11.8h, \in1\().8h
+	eor		v10.16b, v10.16b, v8.16b
+	eor		v11.16b, v11.16b, v9.16b
+	eor		\in0\().16b, \in0\().16b, v10.16b
+	eor		\in1\().16b, \in1\().16b, v11.16b
+	tbl		\in0\().16b, {\in0\().16b}, v14.16b
+	tbl		\in1\().16b, {\in1\().16b}, v14.16b
+	eor		\in0\().16b, \in0\().16b, v10.16b
+	eor		\in1\().16b, \in1\().16b, v11.16b
+	.endm
+
+	.macro		do_block_4x, enc, in0, in1, in2, in3, rounds, rk, rkp, i
+	ld1		{v15.4s}, [\rk]
+	add		\rkp, \rk, #16
+	mov		\i, \rounds
+1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
+	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
+	movi		v15.16b, #0x40
+	tbl		\in0\().16b, {\in0\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in1\().16b, {\in1\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in2\().16b, {\in2\().16b}, v13.16b	/* ShiftRows */
+	tbl		\in3\().16b, {\in3\().16b}, v13.16b	/* ShiftRows */
+	sub_bytes_4x	\in0, \in1, \in2, \in3
+	subs		\i, \i, #1
+	ld1		{v15.4s}, [\rkp], #16
+	beq		2222f
+	mix_columns_2x	\in0, \in1, \enc
+	mix_columns_2x	\in2, \in3, \enc
+	b		1111b
+2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
+	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
+	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
+	.endm
+
+	.macro		encrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+	do_block_4x	1, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+	.endm
+
+	.macro		decrypt_block4x, in0, in1, in2, in3, rounds, rk, rkp, i
+	do_block_4x	0, \in0, \in1, \in2, \in3, \rounds, \rk, \rkp, \i
+	.endm
+
+#include "aes-modes.S"
+
+	.section	".rodata", "a"
+	.align		4
+.LForward_ShiftRows:
+	.octa		0x0b06010c07020d08030e09040f0a0500
+
+.LReverse_ShiftRows:
+	.octa		0x0306090c0f0205080b0e0104070a0d00
+
+.Lror32by8:
+	.octa		0x0c0f0e0d080b0a090407060500030201
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
new file mode 100644
index 000000000..63a52ad9a
--- /dev/null
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -0,0 +1,1005 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Bit sliced AES using NEON instructions
+ *
+ * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+/*
+ * The algorithm implemented here is described in detail by the paper
+ * 'Faster and Timing-Attack Resistant AES-GCM' by Emilia Kaesper and
+ * Peter Schwabe (https://eprint.iacr.org/2009/129.pdf)
+ *
+ * This implementation is based primarily on the OpenSSL implementation
+ * for 32-bit ARM written by Andy Polyakov <appro@openssl.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+
+	rounds		.req	x11
+	bskey		.req	x12
+
+	.macro		in_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
+	eor		\b2, \b2, \b1
+	eor		\b5, \b5, \b6
+	eor		\b3, \b3, \b0
+	eor		\b6, \b6, \b2
+	eor		\b5, \b5, \b0
+	eor		\b6, \b6, \b3
+	eor		\b3, \b3, \b7
+	eor		\b7, \b7, \b5
+	eor		\b3, \b3, \b4
+	eor		\b4, \b4, \b5
+	eor		\b2, \b2, \b7
+	eor		\b3, \b3, \b1
+	eor		\b1, \b1, \b5
+	.endm
+
+	.macro		out_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
+	eor		\b0, \b0, \b6
+	eor		\b1, \b1, \b4
+	eor		\b4, \b4, \b6
+	eor		\b2, \b2, \b0
+	eor		\b6, \b6, \b1
+	eor		\b1, \b1, \b5
+	eor		\b5, \b5, \b3
+	eor		\b3, \b3, \b7
+	eor		\b7, \b7, \b5
+	eor		\b2, \b2, \b5
+	eor		\b4, \b4, \b7
+	.endm
+
+	.macro		inv_in_bs_ch, b6, b1, b2, b4, b7, b0, b3, b5
+	eor		\b1, \b1, \b7
+	eor		\b4, \b4, \b7
+	eor		\b7, \b7, \b5
+	eor		\b1, \b1, \b3
+	eor		\b2, \b2, \b5
+	eor		\b3, \b3, \b7
+	eor		\b6, \b6, \b1
+	eor		\b2, \b2, \b0
+	eor		\b5, \b5, \b3
+	eor		\b4, \b4, \b6
+	eor		\b0, \b0, \b6
+	eor		\b1, \b1, \b4
+	.endm
+
+	.macro		inv_out_bs_ch, b6, b5, b0, b3, b7, b1, b4, b2
+	eor		\b1, \b1, \b5
+	eor		\b2, \b2, \b7
+	eor		\b3, \b3, \b1
+	eor		\b4, \b4, \b5
+	eor		\b7, \b7, \b5
+	eor		\b3, \b3, \b4
+	eor 		\b5, \b5, \b0
+	eor		\b3, \b3, \b7
+	eor		\b6, \b6, \b2
+	eor		\b2, \b2, \b1
+	eor		\b6, \b6, \b3
+	eor		\b3, \b3, \b0
+	eor		\b5, \b5, \b6
+	.endm
+
+	.macro		mul_gf4, x0, x1, y0, y1, t0, t1
+	eor 		\t0, \y0, \y1
+	and		\t0, \t0, \x0
+	eor		\x0, \x0, \x1
+	and		\t1, \x1, \y0
+	and		\x0, \x0, \y1
+	eor		\x1, \t1, \t0
+	eor		\x0, \x0, \t1
+	.endm
+
+	.macro		mul_gf4_n_gf4, x0, x1, y0, y1, t0, x2, x3, y2, y3, t1
+	eor		\t0, \y0, \y1
+	eor 		\t1, \y2, \y3
+	and		\t0, \t0, \x0
+	and		\t1, \t1, \x2
+	eor		\x0, \x0, \x1
+	eor		\x2, \x2, \x3
+	and		\x1, \x1, \y0
+	and		\x3, \x3, \y2
+	and		\x0, \x0, \y1
+	and		\x2, \x2, \y3
+	eor		\x1, \x1, \x0
+	eor		\x2, \x2, \x3
+	eor		\x0, \x0, \t0
+	eor		\x3, \x3, \t1
+	.endm
+
+	.macro		mul_gf16_2, x0, x1, x2, x3, x4, x5, x6, x7, \
+				    y0, y1, y2, y3, t0, t1, t2, t3
+	eor		\t0, \x0, \x2
+	eor		\t1, \x1, \x3
+	mul_gf4  	\x0, \x1, \y0, \y1, \t2, \t3
+	eor		\y0, \y0, \y2
+	eor		\y1, \y1, \y3
+	mul_gf4_n_gf4	\t0, \t1, \y0, \y1, \t3, \x2, \x3, \y2, \y3, \t2
+	eor		\x0, \x0, \t0
+	eor		\x2, \x2, \t0
+	eor		\x1, \x1, \t1
+	eor		\x3, \x3, \t1
+	eor		\t0, \x4, \x6
+	eor		\t1, \x5, \x7
+	mul_gf4_n_gf4	\t0, \t1, \y0, \y1, \t3, \x6, \x7, \y2, \y3, \t2
+	eor		\y0, \y0, \y2
+	eor		\y1, \y1, \y3
+	mul_gf4  	\x4, \x5, \y0, \y1, \t2, \t3
+	eor		\x4, \x4, \t0
+	eor		\x6, \x6, \t0
+	eor		\x5, \x5, \t1
+	eor		\x7, \x7, \t1
+	.endm
+
+	.macro		inv_gf256, x0, x1, x2, x3, x4, x5, x6, x7, \
+				   t0, t1, t2, t3, s0, s1, s2, s3
+	eor		\t3, \x4, \x6
+	eor		\t0, \x5, \x7
+	eor		\t1, \x1, \x3
+	eor		\s1, \x7, \x6
+	eor		\s0, \x0, \x2
+	eor		\s3, \t3, \t0
+	orr		\t2, \t0, \t1
+	and		\s2, \t3, \s0
+	orr		\t3, \t3, \s0
+	eor		\s0, \s0, \t1
+	and		\t0, \t0, \t1
+	eor		\t1, \x3, \x2
+	and		\s3, \s3, \s0
+	and		\s1, \s1, \t1
+	eor		\t1, \x4, \x5
+	eor		\s0, \x1, \x0
+	eor		\t3, \t3, \s1
+	eor		\t2, \t2, \s1
+	and		\s1, \t1, \s0
+	orr		\t1, \t1, \s0
+	eor		\t3, \t3, \s3
+	eor		\t0, \t0, \s1
+	eor		\t2, \t2, \s2
+	eor		\t1, \t1, \s3
+	eor		\t0, \t0, \s2
+	and		\s0, \x7, \x3
+	eor		\t1, \t1, \s2
+	and		\s1, \x6, \x2
+	and		\s2, \x5, \x1
+	orr		\s3, \x4, \x0
+	eor		\t3, \t3, \s0
+	eor		\t1, \t1, \s2
+	eor		\s0, \t0, \s3
+	eor		\t2, \t2, \s1
+	and		\s2, \t3, \t1
+	eor		\s1, \t2, \s2
+	eor		\s3, \s0, \s2
+	bsl		\s1, \t1, \s0
+	not		\t0, \s0
+	bsl		\s0, \s1, \s3
+	bsl		\t0, \s1, \s3
+	bsl		\s3, \t3, \t2
+	eor		\t3, \t3, \t2
+	and		\s2, \s0, \s3
+	eor		\t1, \t1, \t0
+	eor		\s2, \s2, \t3
+	mul_gf16_2	\x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
+			\s3, \s2, \s1, \t1, \s0, \t0, \t2, \t3
+	.endm
+
+	.macro		sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
+			      t0, t1, t2, t3, s0, s1, s2, s3
+	in_bs_ch	\b0\().16b, \b1\().16b, \b2\().16b, \b3\().16b, \
+			\b4\().16b, \b5\().16b, \b6\().16b, \b7\().16b
+	inv_gf256	\b6\().16b, \b5\().16b, \b0\().16b, \b3\().16b, \
+			\b7\().16b, \b1\().16b, \b4\().16b, \b2\().16b, \
+			\t0\().16b, \t1\().16b, \t2\().16b, \t3\().16b, \
+			\s0\().16b, \s1\().16b, \s2\().16b, \s3\().16b
+	out_bs_ch	\b7\().16b, \b1\().16b, \b4\().16b, \b2\().16b, \
+			\b6\().16b, \b5\().16b, \b0\().16b, \b3\().16b
+	.endm
+
+	.macro		inv_sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
+				  t0, t1, t2, t3, s0, s1, s2, s3
+	inv_in_bs_ch	\b0\().16b, \b1\().16b, \b2\().16b, \b3\().16b, \
+			\b4\().16b, \b5\().16b, \b6\().16b, \b7\().16b
+	inv_gf256	\b5\().16b, \b1\().16b, \b2\().16b, \b6\().16b, \
+			\b3\().16b, \b7\().16b, \b0\().16b, \b4\().16b, \
+			\t0\().16b, \t1\().16b, \t2\().16b, \t3\().16b, \
+			\s0\().16b, \s1\().16b, \s2\().16b, \s3\().16b
+	inv_out_bs_ch	\b3\().16b, \b7\().16b, \b0\().16b, \b4\().16b, \
+			\b5\().16b, \b1\().16b, \b2\().16b, \b6\().16b
+	.endm
+
+	.macro		enc_next_rk
+	ldp		q16, q17, [bskey], #128
+	ldp		q18, q19, [bskey, #-96]
+	ldp		q20, q21, [bskey, #-64]
+	ldp		q22, q23, [bskey, #-32]
+	.endm
+
+	.macro		dec_next_rk
+	ldp		q16, q17, [bskey, #-128]!
+	ldp		q18, q19, [bskey, #32]
+	ldp		q20, q21, [bskey, #64]
+	ldp		q22, q23, [bskey, #96]
+	.endm
+
+	.macro		add_round_key, x0, x1, x2, x3, x4, x5, x6, x7
+	eor		\x0\().16b, \x0\().16b, v16.16b
+	eor		\x1\().16b, \x1\().16b, v17.16b
+	eor		\x2\().16b, \x2\().16b, v18.16b
+	eor		\x3\().16b, \x3\().16b, v19.16b
+	eor		\x4\().16b, \x4\().16b, v20.16b
+	eor		\x5\().16b, \x5\().16b, v21.16b
+	eor		\x6\().16b, \x6\().16b, v22.16b
+	eor		\x7\().16b, \x7\().16b, v23.16b
+	.endm
+
+	.macro		shift_rows, x0, x1, x2, x3, x4, x5, x6, x7, mask
+	tbl		\x0\().16b, {\x0\().16b}, \mask\().16b
+	tbl		\x1\().16b, {\x1\().16b}, \mask\().16b
+	tbl		\x2\().16b, {\x2\().16b}, \mask\().16b
+	tbl		\x3\().16b, {\x3\().16b}, \mask\().16b
+	tbl		\x4\().16b, {\x4\().16b}, \mask\().16b
+	tbl		\x5\().16b, {\x5\().16b}, \mask\().16b
+	tbl		\x6\().16b, {\x6\().16b}, \mask\().16b
+	tbl		\x7\().16b, {\x7\().16b}, \mask\().16b
+	.endm
+
+	.macro		mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
+				  t0, t1, t2, t3, t4, t5, t6, t7, inv
+	ext		\t0\().16b, \x0\().16b, \x0\().16b, #12
+	ext		\t1\().16b, \x1\().16b, \x1\().16b, #12
+	eor		\x0\().16b, \x0\().16b, \t0\().16b
+	ext		\t2\().16b, \x2\().16b, \x2\().16b, #12
+	eor		\x1\().16b, \x1\().16b, \t1\().16b
+	ext		\t3\().16b, \x3\().16b, \x3\().16b, #12
+	eor		\x2\().16b, \x2\().16b, \t2\().16b
+	ext		\t4\().16b, \x4\().16b, \x4\().16b, #12
+	eor		\x3\().16b, \x3\().16b, \t3\().16b
+	ext		\t5\().16b, \x5\().16b, \x5\().16b, #12
+	eor		\x4\().16b, \x4\().16b, \t4\().16b
+	ext		\t6\().16b, \x6\().16b, \x6\().16b, #12
+	eor		\x5\().16b, \x5\().16b, \t5\().16b
+	ext		\t7\().16b, \x7\().16b, \x7\().16b, #12
+	eor		\x6\().16b, \x6\().16b, \t6\().16b
+	eor		\t1\().16b, \t1\().16b, \x0\().16b
+	eor		\x7\().16b, \x7\().16b, \t7\().16b
+	ext		\x0\().16b, \x0\().16b, \x0\().16b, #8
+	eor		\t2\().16b, \t2\().16b, \x1\().16b
+	eor		\t0\().16b, \t0\().16b, \x7\().16b
+	eor		\t1\().16b, \t1\().16b, \x7\().16b
+	ext		\x1\().16b, \x1\().16b, \x1\().16b, #8
+	eor		\t5\().16b, \t5\().16b, \x4\().16b
+	eor		\x0\().16b, \x0\().16b, \t0\().16b
+	eor		\t6\().16b, \t6\().16b, \x5\().16b
+	eor		\x1\().16b, \x1\().16b, \t1\().16b
+	ext		\t0\().16b, \x4\().16b, \x4\().16b, #8
+	eor		\t4\().16b, \t4\().16b, \x3\().16b
+	ext		\t1\().16b, \x5\().16b, \x5\().16b, #8
+	eor		\t7\().16b, \t7\().16b, \x6\().16b
+	ext		\x4\().16b, \x3\().16b, \x3\().16b, #8
+	eor		\t3\().16b, \t3\().16b, \x2\().16b
+	ext		\x5\().16b, \x7\().16b, \x7\().16b, #8
+	eor		\t4\().16b, \t4\().16b, \x7\().16b
+	ext		\x3\().16b, \x6\().16b, \x6\().16b, #8
+	eor		\t3\().16b, \t3\().16b, \x7\().16b
+	ext		\x6\().16b, \x2\().16b, \x2\().16b, #8
+	eor		\x7\().16b, \t1\().16b, \t5\().16b
+	.ifb		\inv
+	eor		\x2\().16b, \t0\().16b, \t4\().16b
+	eor		\x4\().16b, \x4\().16b, \t3\().16b
+	eor		\x5\().16b, \x5\().16b, \t7\().16b
+	eor		\x3\().16b, \x3\().16b, \t6\().16b
+	eor		\x6\().16b, \x6\().16b, \t2\().16b
+	.else
+	eor		\t3\().16b, \t3\().16b, \x4\().16b
+	eor		\x5\().16b, \x5\().16b, \t7\().16b
+	eor		\x2\().16b, \x3\().16b, \t6\().16b
+	eor		\x3\().16b, \t0\().16b, \t4\().16b
+	eor		\x4\().16b, \x6\().16b, \t2\().16b
+	mov		\x6\().16b, \t3\().16b
+	.endif
+	.endm
+
+	.macro		inv_mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
+				      t0, t1, t2, t3, t4, t5, t6, t7
+	ext		\t0\().16b, \x0\().16b, \x0\().16b, #8
+	ext		\t6\().16b, \x6\().16b, \x6\().16b, #8
+	ext		\t7\().16b, \x7\().16b, \x7\().16b, #8
+	eor		\t0\().16b, \t0\().16b, \x0\().16b
+	ext		\t1\().16b, \x1\().16b, \x1\().16b, #8
+	eor		\t6\().16b, \t6\().16b, \x6\().16b
+	ext		\t2\().16b, \x2\().16b, \x2\().16b, #8
+	eor		\t7\().16b, \t7\().16b, \x7\().16b
+	ext		\t3\().16b, \x3\().16b, \x3\().16b, #8
+	eor		\t1\().16b, \t1\().16b, \x1\().16b
+	ext		\t4\().16b, \x4\().16b, \x4\().16b, #8
+	eor		\t2\().16b, \t2\().16b, \x2\().16b
+	ext		\t5\().16b, \x5\().16b, \x5\().16b, #8
+	eor		\t3\().16b, \t3\().16b, \x3\().16b
+	eor		\t4\().16b, \t4\().16b, \x4\().16b
+	eor		\t5\().16b, \t5\().16b, \x5\().16b
+	eor		\x0\().16b, \x0\().16b, \t6\().16b
+	eor		\x1\().16b, \x1\().16b, \t6\().16b
+	eor		\x2\().16b, \x2\().16b, \t0\().16b
+	eor		\x4\().16b, \x4\().16b, \t2\().16b
+	eor		\x3\().16b, \x3\().16b, \t1\().16b
+	eor		\x1\().16b, \x1\().16b, \t7\().16b
+	eor		\x2\().16b, \x2\().16b, \t7\().16b
+	eor		\x4\().16b, \x4\().16b, \t6\().16b
+	eor		\x5\().16b, \x5\().16b, \t3\().16b
+	eor		\x3\().16b, \x3\().16b, \t6\().16b
+	eor		\x6\().16b, \x6\().16b, \t4\().16b
+	eor		\x4\().16b, \x4\().16b, \t7\().16b
+	eor		\x5\().16b, \x5\().16b, \t7\().16b
+	eor		\x7\().16b, \x7\().16b, \t5\().16b
+	mix_cols	\x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
+			\t0, \t1, \t2, \t3, \t4, \t5, \t6, \t7, 1
+	.endm
+
+	.macro		swapmove_2x, a0, b0, a1, b1, n, mask, t0, t1
+	ushr		\t0\().2d, \b0\().2d, #\n
+	ushr		\t1\().2d, \b1\().2d, #\n
+	eor		\t0\().16b, \t0\().16b, \a0\().16b
+	eor		\t1\().16b, \t1\().16b, \a1\().16b
+	and		\t0\().16b, \t0\().16b, \mask\().16b
+	and		\t1\().16b, \t1\().16b, \mask\().16b
+	eor		\a0\().16b, \a0\().16b, \t0\().16b
+	shl		\t0\().2d, \t0\().2d, #\n
+	eor		\a1\().16b, \a1\().16b, \t1\().16b
+	shl		\t1\().2d, \t1\().2d, #\n
+	eor		\b0\().16b, \b0\().16b, \t0\().16b
+	eor		\b1\().16b, \b1\().16b, \t1\().16b
+	.endm
+
+	.macro		bitslice, x7, x6, x5, x4, x3, x2, x1, x0, t0, t1, t2, t3
+	movi		\t0\().16b, #0x55
+	movi		\t1\().16b, #0x33
+	swapmove_2x	\x0, \x1, \x2, \x3, 1, \t0, \t2, \t3
+	swapmove_2x	\x4, \x5, \x6, \x7, 1, \t0, \t2, \t3
+	movi		\t0\().16b, #0x0f
+	swapmove_2x	\x0, \x2, \x1, \x3, 2, \t1, \t2, \t3
+	swapmove_2x	\x4, \x6, \x5, \x7, 2, \t1, \t2, \t3
+	swapmove_2x	\x0, \x4, \x1, \x5, 4, \t0, \t2, \t3
+	swapmove_2x	\x2, \x6, \x3, \x7, 4, \t0, \t2, \t3
+	.endm
+
+
+	.align		6
+M0:	.octa		0x0004080c0105090d02060a0e03070b0f
+
+M0SR:	.octa		0x0004080c05090d010a0e02060f03070b
+SR:	.octa		0x0f0e0d0c0a09080b0504070600030201
+SRM0:	.octa		0x01060b0c0207080d0304090e00050a0f
+
+M0ISR:	.octa		0x0004080c0d0105090a0e0206070b0f03
+ISR:	.octa		0x0f0e0d0c080b0a090504070602010003
+ISRM0:	.octa		0x0306090c00070a0d01040b0e0205080f
+
+	/*
+	 * void aesbs_convert_key(u8 out[], u32 const rk[], int rounds)
+	 */
+SYM_FUNC_START(aesbs_convert_key)
+	ld1		{v7.4s}, [x1], #16		// load round 0 key
+	ld1		{v17.4s}, [x1], #16		// load round 1 key
+
+	movi		v8.16b,  #0x01			// bit masks
+	movi		v9.16b,  #0x02
+	movi		v10.16b, #0x04
+	movi		v11.16b, #0x08
+	movi		v12.16b, #0x10
+	movi		v13.16b, #0x20
+	movi		v14.16b, #0x40
+	movi		v15.16b, #0x80
+	ldr		q16, M0
+
+	sub		x2, x2, #1
+	str		q7, [x0], #16		// save round 0 key
+
+.Lkey_loop:
+	tbl		v7.16b ,{v17.16b}, v16.16b
+	ld1		{v17.4s}, [x1], #16		// load next round key
+
+	cmtst		v0.16b, v7.16b, v8.16b
+	cmtst		v1.16b, v7.16b, v9.16b
+	cmtst		v2.16b, v7.16b, v10.16b
+	cmtst		v3.16b, v7.16b, v11.16b
+	cmtst		v4.16b, v7.16b, v12.16b
+	cmtst		v5.16b, v7.16b, v13.16b
+	cmtst		v6.16b, v7.16b, v14.16b
+	cmtst		v7.16b, v7.16b, v15.16b
+	not		v0.16b, v0.16b
+	not		v1.16b, v1.16b
+	not		v5.16b, v5.16b
+	not		v6.16b, v6.16b
+
+	subs		x2, x2, #1
+	stp		q0, q1, [x0], #128
+	stp		q2, q3, [x0, #-96]
+	stp		q4, q5, [x0, #-64]
+	stp		q6, q7, [x0, #-32]
+	b.ne		.Lkey_loop
+
+	movi		v7.16b, #0x63			// compose .L63
+	eor		v17.16b, v17.16b, v7.16b
+	str		q17, [x0]
+	ret
+SYM_FUNC_END(aesbs_convert_key)
+
+	.align		4
+SYM_FUNC_START_LOCAL(aesbs_encrypt8)
+	ldr		q9, [bskey], #16		// round 0 key
+	ldr		q8, M0SR
+	ldr		q24, SR
+
+	eor		v10.16b, v0.16b, v9.16b		// xor with round0 key
+	eor		v11.16b, v1.16b, v9.16b
+	tbl		v0.16b, {v10.16b}, v8.16b
+	eor		v12.16b, v2.16b, v9.16b
+	tbl		v1.16b, {v11.16b}, v8.16b
+	eor		v13.16b, v3.16b, v9.16b
+	tbl		v2.16b, {v12.16b}, v8.16b
+	eor		v14.16b, v4.16b, v9.16b
+	tbl		v3.16b, {v13.16b}, v8.16b
+	eor		v15.16b, v5.16b, v9.16b
+	tbl		v4.16b, {v14.16b}, v8.16b
+	eor		v10.16b, v6.16b, v9.16b
+	tbl		v5.16b, {v15.16b}, v8.16b
+	eor		v11.16b, v7.16b, v9.16b
+	tbl		v6.16b, {v10.16b}, v8.16b
+	tbl		v7.16b, {v11.16b}, v8.16b
+
+	bitslice	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11
+
+	sub		rounds, rounds, #1
+	b		.Lenc_sbox
+
+.Lenc_loop:
+	shift_rows	v0, v1, v2, v3, v4, v5, v6, v7, v24
+.Lenc_sbox:
+	sbox		v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, \
+								v13, v14, v15
+	subs		rounds, rounds, #1
+	b.cc		.Lenc_done
+
+	enc_next_rk
+
+	mix_cols	v0, v1, v4, v6, v3, v7, v2, v5, v8, v9, v10, v11, v12, \
+								v13, v14, v15
+
+	add_round_key	v0, v1, v2, v3, v4, v5, v6, v7
+
+	b.ne		.Lenc_loop
+	ldr		q24, SRM0
+	b		.Lenc_loop
+
+.Lenc_done:
+	ldr		q12, [bskey]			// last round key
+
+	bitslice	v0, v1, v4, v6, v3, v7, v2, v5, v8, v9, v10, v11
+
+	eor		v0.16b, v0.16b, v12.16b
+	eor		v1.16b, v1.16b, v12.16b
+	eor		v4.16b, v4.16b, v12.16b
+	eor		v6.16b, v6.16b, v12.16b
+	eor		v3.16b, v3.16b, v12.16b
+	eor		v7.16b, v7.16b, v12.16b
+	eor		v2.16b, v2.16b, v12.16b
+	eor		v5.16b, v5.16b, v12.16b
+	ret
+SYM_FUNC_END(aesbs_encrypt8)
+
+	.align		4
+SYM_FUNC_START_LOCAL(aesbs_decrypt8)
+	lsl		x9, rounds, #7
+	add		bskey, bskey, x9
+
+	ldr		q9, [bskey, #-112]!		// round 0 key
+	ldr		q8, M0ISR
+	ldr		q24, ISR
+
+	eor		v10.16b, v0.16b, v9.16b		// xor with round0 key
+	eor		v11.16b, v1.16b, v9.16b
+	tbl		v0.16b, {v10.16b}, v8.16b
+	eor		v12.16b, v2.16b, v9.16b
+	tbl		v1.16b, {v11.16b}, v8.16b
+	eor		v13.16b, v3.16b, v9.16b
+	tbl		v2.16b, {v12.16b}, v8.16b
+	eor		v14.16b, v4.16b, v9.16b
+	tbl		v3.16b, {v13.16b}, v8.16b
+	eor		v15.16b, v5.16b, v9.16b
+	tbl		v4.16b, {v14.16b}, v8.16b
+	eor		v10.16b, v6.16b, v9.16b
+	tbl		v5.16b, {v15.16b}, v8.16b
+	eor		v11.16b, v7.16b, v9.16b
+	tbl		v6.16b, {v10.16b}, v8.16b
+	tbl		v7.16b, {v11.16b}, v8.16b
+
+	bitslice	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11
+
+	sub		rounds, rounds, #1
+	b		.Ldec_sbox
+
+.Ldec_loop:
+	shift_rows	v0, v1, v2, v3, v4, v5, v6, v7, v24
+.Ldec_sbox:
+	inv_sbox	v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, \
+								v13, v14, v15
+	subs		rounds, rounds, #1
+	b.cc		.Ldec_done
+
+	dec_next_rk
+
+	add_round_key	v0, v1, v6, v4, v2, v7, v3, v5
+
+	inv_mix_cols	v0, v1, v6, v4, v2, v7, v3, v5, v8, v9, v10, v11, v12, \
+								v13, v14, v15
+
+	b.ne		.Ldec_loop
+	ldr		q24, ISRM0
+	b		.Ldec_loop
+.Ldec_done:
+	ldr		q12, [bskey, #-16]		// last round key
+
+	bitslice	v0, v1, v6, v4, v2, v7, v3, v5, v8, v9, v10, v11
+
+	eor		v0.16b, v0.16b, v12.16b
+	eor		v1.16b, v1.16b, v12.16b
+	eor		v6.16b, v6.16b, v12.16b
+	eor		v4.16b, v4.16b, v12.16b
+	eor		v2.16b, v2.16b, v12.16b
+	eor		v7.16b, v7.16b, v12.16b
+	eor		v3.16b, v3.16b, v12.16b
+	eor		v5.16b, v5.16b, v12.16b
+	ret
+SYM_FUNC_END(aesbs_decrypt8)
+
+	/*
+	 * aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks)
+	 * aesbs_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks)
+	 */
+	.macro		__ecb_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
+	frame_push	5
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+
+99:	mov		x5, #1
+	lsl		x5, x5, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
+	csel		x5, x5, xzr, mi
+
+	ld1		{v0.16b}, [x20], #16
+	tbnz		x5, #1, 0f
+	ld1		{v1.16b}, [x20], #16
+	tbnz		x5, #2, 0f
+	ld1		{v2.16b}, [x20], #16
+	tbnz		x5, #3, 0f
+	ld1		{v3.16b}, [x20], #16
+	tbnz		x5, #4, 0f
+	ld1		{v4.16b}, [x20], #16
+	tbnz		x5, #5, 0f
+	ld1		{v5.16b}, [x20], #16
+	tbnz		x5, #6, 0f
+	ld1		{v6.16b}, [x20], #16
+	tbnz		x5, #7, 0f
+	ld1		{v7.16b}, [x20], #16
+
+0:	mov		bskey, x21
+	mov		rounds, x22
+	bl		\do8
+
+	st1		{\o0\().16b}, [x19], #16
+	tbnz		x5, #1, 1f
+	st1		{\o1\().16b}, [x19], #16
+	tbnz		x5, #2, 1f
+	st1		{\o2\().16b}, [x19], #16
+	tbnz		x5, #3, 1f
+	st1		{\o3\().16b}, [x19], #16
+	tbnz		x5, #4, 1f
+	st1		{\o4\().16b}, [x19], #16
+	tbnz		x5, #5, 1f
+	st1		{\o5\().16b}, [x19], #16
+	tbnz		x5, #6, 1f
+	st1		{\o6\().16b}, [x19], #16
+	tbnz		x5, #7, 1f
+	st1		{\o7\().16b}, [x19], #16
+
+	cbz		x23, 1f
+	cond_yield_neon
+	b		99b
+
+1:	frame_pop
+	ret
+	.endm
+
+	.align		4
+SYM_FUNC_START(aesbs_ecb_encrypt)
+	__ecb_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
+SYM_FUNC_END(aesbs_ecb_encrypt)
+
+	.align		4
+SYM_FUNC_START(aesbs_ecb_decrypt)
+	__ecb_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
+SYM_FUNC_END(aesbs_ecb_decrypt)
+
+	/*
+	 * aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks, u8 iv[])
+	 */
+	.align		4
+SYM_FUNC_START(aesbs_cbc_decrypt)
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+
+99:	mov		x6, #1
+	lsl		x6, x6, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
+	csel		x6, x6, xzr, mi
+
+	ld1		{v0.16b}, [x20], #16
+	mov		v25.16b, v0.16b
+	tbnz		x6, #1, 0f
+	ld1		{v1.16b}, [x20], #16
+	mov		v26.16b, v1.16b
+	tbnz		x6, #2, 0f
+	ld1		{v2.16b}, [x20], #16
+	mov		v27.16b, v2.16b
+	tbnz		x6, #3, 0f
+	ld1		{v3.16b}, [x20], #16
+	mov		v28.16b, v3.16b
+	tbnz		x6, #4, 0f
+	ld1		{v4.16b}, [x20], #16
+	mov		v29.16b, v4.16b
+	tbnz		x6, #5, 0f
+	ld1		{v5.16b}, [x20], #16
+	mov		v30.16b, v5.16b
+	tbnz		x6, #6, 0f
+	ld1		{v6.16b}, [x20], #16
+	mov		v31.16b, v6.16b
+	tbnz		x6, #7, 0f
+	ld1		{v7.16b}, [x20]
+
+0:	mov		bskey, x21
+	mov		rounds, x22
+	bl		aesbs_decrypt8
+
+	ld1		{v24.16b}, [x24]		// load IV
+
+	eor		v1.16b, v1.16b, v25.16b
+	eor		v6.16b, v6.16b, v26.16b
+	eor		v4.16b, v4.16b, v27.16b
+	eor		v2.16b, v2.16b, v28.16b
+	eor		v7.16b, v7.16b, v29.16b
+	eor		v0.16b, v0.16b, v24.16b
+	eor		v3.16b, v3.16b, v30.16b
+	eor		v5.16b, v5.16b, v31.16b
+
+	st1		{v0.16b}, [x19], #16
+	mov		v24.16b, v25.16b
+	tbnz		x6, #1, 1f
+	st1		{v1.16b}, [x19], #16
+	mov		v24.16b, v26.16b
+	tbnz		x6, #2, 1f
+	st1		{v6.16b}, [x19], #16
+	mov		v24.16b, v27.16b
+	tbnz		x6, #3, 1f
+	st1		{v4.16b}, [x19], #16
+	mov		v24.16b, v28.16b
+	tbnz		x6, #4, 1f
+	st1		{v2.16b}, [x19], #16
+	mov		v24.16b, v29.16b
+	tbnz		x6, #5, 1f
+	st1		{v7.16b}, [x19], #16
+	mov		v24.16b, v30.16b
+	tbnz		x6, #6, 1f
+	st1		{v3.16b}, [x19], #16
+	mov		v24.16b, v31.16b
+	tbnz		x6, #7, 1f
+	ld1		{v24.16b}, [x20], #16
+	st1		{v5.16b}, [x19], #16
+1:	st1		{v24.16b}, [x24]		// store IV
+
+	cbz		x23, 2f
+	cond_yield_neon
+	b		99b
+
+2:	frame_pop
+	ret
+SYM_FUNC_END(aesbs_cbc_decrypt)
+
+	.macro		next_tweak, out, in, const, tmp
+	sshr		\tmp\().2d,  \in\().2d,   #63
+	and		\tmp\().16b, \tmp\().16b, \const\().16b
+	add		\out\().2d,  \in\().2d,   \in\().2d
+	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+	eor		\out\().16b, \out\().16b, \tmp\().16b
+	.endm
+
+	/*
+	 * aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks, u8 iv[])
+	 * aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks, u8 iv[])
+	 */
+SYM_FUNC_START_LOCAL(__xts_crypt8)
+	mov		x6, #1
+	lsl		x6, x6, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
+	csel		x6, x6, xzr, mi
+
+	ld1		{v0.16b}, [x20], #16
+	next_tweak	v26, v25, v30, v31
+	eor		v0.16b, v0.16b, v25.16b
+	tbnz		x6, #1, 0f
+
+	ld1		{v1.16b}, [x20], #16
+	next_tweak	v27, v26, v30, v31
+	eor		v1.16b, v1.16b, v26.16b
+	tbnz		x6, #2, 0f
+
+	ld1		{v2.16b}, [x20], #16
+	next_tweak	v28, v27, v30, v31
+	eor		v2.16b, v2.16b, v27.16b
+	tbnz		x6, #3, 0f
+
+	ld1		{v3.16b}, [x20], #16
+	next_tweak	v29, v28, v30, v31
+	eor		v3.16b, v3.16b, v28.16b
+	tbnz		x6, #4, 0f
+
+	ld1		{v4.16b}, [x20], #16
+	str		q29, [sp, #.Lframe_local_offset]
+	eor		v4.16b, v4.16b, v29.16b
+	next_tweak	v29, v29, v30, v31
+	tbnz		x6, #5, 0f
+
+	ld1		{v5.16b}, [x20], #16
+	str		q29, [sp, #.Lframe_local_offset + 16]
+	eor		v5.16b, v5.16b, v29.16b
+	next_tweak	v29, v29, v30, v31
+	tbnz		x6, #6, 0f
+
+	ld1		{v6.16b}, [x20], #16
+	str		q29, [sp, #.Lframe_local_offset + 32]
+	eor		v6.16b, v6.16b, v29.16b
+	next_tweak	v29, v29, v30, v31
+	tbnz		x6, #7, 0f
+
+	ld1		{v7.16b}, [x20], #16
+	str		q29, [sp, #.Lframe_local_offset + 48]
+	eor		v7.16b, v7.16b, v29.16b
+	next_tweak	v29, v29, v30, v31
+
+0:	mov		bskey, x21
+	mov		rounds, x22
+	br		x16
+SYM_FUNC_END(__xts_crypt8)
+
+	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
+	frame_push	6, 64
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+
+0:	movi		v30.2s, #0x1
+	movi		v25.2s, #0x87
+	uzp1		v30.4s, v30.4s, v25.4s
+	ld1		{v25.16b}, [x24]
+
+99:	adr		x16, \do8
+	bl		__xts_crypt8
+
+	ldp		q16, q17, [sp, #.Lframe_local_offset]
+	ldp		q18, q19, [sp, #.Lframe_local_offset + 32]
+
+	eor		\o0\().16b, \o0\().16b, v25.16b
+	eor		\o1\().16b, \o1\().16b, v26.16b
+	eor		\o2\().16b, \o2\().16b, v27.16b
+	eor		\o3\().16b, \o3\().16b, v28.16b
+
+	st1		{\o0\().16b}, [x19], #16
+	mov		v25.16b, v26.16b
+	tbnz		x6, #1, 1f
+	st1		{\o1\().16b}, [x19], #16
+	mov		v25.16b, v27.16b
+	tbnz		x6, #2, 1f
+	st1		{\o2\().16b}, [x19], #16
+	mov		v25.16b, v28.16b
+	tbnz		x6, #3, 1f
+	st1		{\o3\().16b}, [x19], #16
+	mov		v25.16b, v29.16b
+	tbnz		x6, #4, 1f
+
+	eor		\o4\().16b, \o4\().16b, v16.16b
+	eor		\o5\().16b, \o5\().16b, v17.16b
+	eor		\o6\().16b, \o6\().16b, v18.16b
+	eor		\o7\().16b, \o7\().16b, v19.16b
+
+	st1		{\o4\().16b}, [x19], #16
+	tbnz		x6, #5, 1f
+	st1		{\o5\().16b}, [x19], #16
+	tbnz		x6, #6, 1f
+	st1		{\o6\().16b}, [x19], #16
+	tbnz		x6, #7, 1f
+	st1		{\o7\().16b}, [x19], #16
+
+	cbz		x23, 1f
+	st1		{v25.16b}, [x24]
+
+	cond_yield_neon	0b
+	b		99b
+
+1:	st1		{v25.16b}, [x24]
+	frame_pop
+	ret
+	.endm
+
+SYM_FUNC_START(aesbs_xts_encrypt)
+	__xts_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
+SYM_FUNC_END(aesbs_xts_encrypt)
+
+SYM_FUNC_START(aesbs_xts_decrypt)
+	__xts_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
+SYM_FUNC_END(aesbs_xts_decrypt)
+
+	.macro		next_ctr, v
+	mov		\v\().d[1], x8
+	adds		x8, x8, #1
+	mov		\v\().d[0], x7
+	adc		x7, x7, xzr
+	rev64		\v\().16b, \v\().16b
+	.endm
+
+	/*
+	 * aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+	 *		     int rounds, int blocks, u8 iv[], u8 final[])
+	 */
+SYM_FUNC_START(aesbs_ctr_encrypt)
+	frame_push	8
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+	mov		x25, x6
+
+	cmp		x25, #0
+	cset		x26, ne
+	add		x23, x23, x26		// do one extra block if final
+
+98:	ldp		x7, x8, [x24]
+	ld1		{v0.16b}, [x24]
+CPU_LE(	rev		x7, x7		)
+CPU_LE(	rev		x8, x8		)
+	adds		x8, x8, #1
+	adc		x7, x7, xzr
+
+99:	mov		x9, #1
+	lsl		x9, x9, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
+	csel		x9, x9, xzr, le
+
+	tbnz		x9, #1, 0f
+	next_ctr	v1
+	tbnz		x9, #2, 0f
+	next_ctr	v2
+	tbnz		x9, #3, 0f
+	next_ctr	v3
+	tbnz		x9, #4, 0f
+	next_ctr	v4
+	tbnz		x9, #5, 0f
+	next_ctr	v5
+	tbnz		x9, #6, 0f
+	next_ctr	v6
+	tbnz		x9, #7, 0f
+	next_ctr	v7
+
+0:	mov		bskey, x21
+	mov		rounds, x22
+	bl		aesbs_encrypt8
+
+	lsr		x9, x9, x26		// disregard the extra block
+	tbnz		x9, #0, 0f
+
+	ld1		{v8.16b}, [x20], #16
+	eor		v0.16b, v0.16b, v8.16b
+	st1		{v0.16b}, [x19], #16
+	tbnz		x9, #1, 1f
+
+	ld1		{v9.16b}, [x20], #16
+	eor		v1.16b, v1.16b, v9.16b
+	st1		{v1.16b}, [x19], #16
+	tbnz		x9, #2, 2f
+
+	ld1		{v10.16b}, [x20], #16
+	eor		v4.16b, v4.16b, v10.16b
+	st1		{v4.16b}, [x19], #16
+	tbnz		x9, #3, 3f
+
+	ld1		{v11.16b}, [x20], #16
+	eor		v6.16b, v6.16b, v11.16b
+	st1		{v6.16b}, [x19], #16
+	tbnz		x9, #4, 4f
+
+	ld1		{v12.16b}, [x20], #16
+	eor		v3.16b, v3.16b, v12.16b
+	st1		{v3.16b}, [x19], #16
+	tbnz		x9, #5, 5f
+
+	ld1		{v13.16b}, [x20], #16
+	eor		v7.16b, v7.16b, v13.16b
+	st1		{v7.16b}, [x19], #16
+	tbnz		x9, #6, 6f
+
+	ld1		{v14.16b}, [x20], #16
+	eor		v2.16b, v2.16b, v14.16b
+	st1		{v2.16b}, [x19], #16
+	tbnz		x9, #7, 7f
+
+	ld1		{v15.16b}, [x20], #16
+	eor		v5.16b, v5.16b, v15.16b
+	st1		{v5.16b}, [x19], #16
+
+8:	next_ctr	v0
+	st1		{v0.16b}, [x24]
+	cbz		x23, .Lctr_done
+
+	cond_yield_neon	98b
+	b		99b
+
+.Lctr_done:
+	frame_pop
+	ret
+
+	/*
+	 * If we are handling the tail of the input (x6 != NULL), return the
+	 * final keystream block back to the caller.
+	 */
+0:	cbz		x25, 8b
+	st1		{v0.16b}, [x25]
+	b		8b
+1:	cbz		x25, 8b
+	st1		{v1.16b}, [x25]
+	b		8b
+2:	cbz		x25, 8b
+	st1		{v4.16b}, [x25]
+	b		8b
+3:	cbz		x25, 8b
+	st1		{v6.16b}, [x25]
+	b		8b
+4:	cbz		x25, 8b
+	st1		{v3.16b}, [x25]
+	b		8b
+5:	cbz		x25, 8b
+	st1		{v7.16b}, [x25]
+	b		8b
+6:	cbz		x25, 8b
+	st1		{v2.16b}, [x25]
+	b		8b
+7:	cbz		x25, 8b
+	st1		{v5.16b}, [x25]
+	b		8b
+SYM_FUNC_END(aesbs_ctr_encrypt)
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
new file mode 100644
index 000000000..fb507d569
--- /dev/null
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -0,0 +1,566 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Bit sliced AES using NEON instructions
+ *
+ * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/aes.h>
+#include <crypto/ctr.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/xts.h>
+#include <linux/module.h>
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+MODULE_ALIAS_CRYPTO("ecb(aes)");
+MODULE_ALIAS_CRYPTO("cbc(aes)");
+MODULE_ALIAS_CRYPTO("ctr(aes)");
+MODULE_ALIAS_CRYPTO("xts(aes)");
+
+asmlinkage void aesbs_convert_key(u8 out[], u32 const rk[], int rounds);
+
+asmlinkage void aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks);
+asmlinkage void aesbs_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks);
+
+asmlinkage void aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[]);
+
+asmlinkage void aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[], u8 final[]);
+
+asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[]);
+asmlinkage void aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[]);
+
+/* borrowed from aes-neon-blk.ko */
+asmlinkage void neon_aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[],
+				     int rounds, int blocks);
+asmlinkage void neon_aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[],
+				     int rounds, int blocks, u8 iv[]);
+asmlinkage void neon_aes_xts_encrypt(u8 out[], u8 const in[],
+				     u32 const rk1[], int rounds, int bytes,
+				     u32 const rk2[], u8 iv[], int first);
+asmlinkage void neon_aes_xts_decrypt(u8 out[], u8 const in[],
+				     u32 const rk1[], int rounds, int bytes,
+				     u32 const rk2[], u8 iv[], int first);
+
+struct aesbs_ctx {
+	u8	rk[13 * (8 * AES_BLOCK_SIZE) + 32];
+	int	rounds;
+} __aligned(AES_BLOCK_SIZE);
+
+struct aesbs_cbc_ctx {
+	struct aesbs_ctx	key;
+	u32			enc[AES_MAX_KEYLENGTH_U32];
+};
+
+struct aesbs_ctr_ctx {
+	struct aesbs_ctx	key;		/* must be first member */
+	struct crypto_aes_ctx	fallback;
+};
+
+struct aesbs_xts_ctx {
+	struct aesbs_ctx	key;
+	u32			twkey[AES_MAX_KEYLENGTH_U32];
+	struct crypto_aes_ctx	cts;
+};
+
+static int aesbs_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			unsigned int key_len)
+{
+	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_aes_ctx rk;
+	int err;
+
+	err = aes_expandkey(&rk, in_key, key_len);
+	if (err)
+		return err;
+
+	ctx->rounds = 6 + key_len / 4;
+
+	kernel_neon_begin();
+	aesbs_convert_key(ctx->rk, rk.key_enc, ctx->rounds);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int __ecb_crypt(struct skcipher_request *req,
+		       void (*fn)(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks))
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		if (walk.nbytes < walk.total)
+			blocks = round_down(blocks,
+					    walk.stride / AES_BLOCK_SIZE);
+
+		kernel_neon_begin();
+		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
+		   ctx->rounds, blocks);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+	}
+
+	return err;
+}
+
+static int ecb_encrypt(struct skcipher_request *req)
+{
+	return __ecb_crypt(req, aesbs_ecb_encrypt);
+}
+
+static int ecb_decrypt(struct skcipher_request *req)
+{
+	return __ecb_crypt(req, aesbs_ecb_decrypt);
+}
+
+static int aesbs_cbc_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			    unsigned int key_len)
+{
+	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_aes_ctx rk;
+	int err;
+
+	err = aes_expandkey(&rk, in_key, key_len);
+	if (err)
+		return err;
+
+	ctx->key.rounds = 6 + key_len / 4;
+
+	memcpy(ctx->enc, rk.key_enc, sizeof(ctx->enc));
+
+	kernel_neon_begin();
+	aesbs_convert_key(ctx->key.rk, rk.key_enc, ctx->key.rounds);
+	kernel_neon_end();
+	memzero_explicit(&rk, sizeof(rk));
+
+	return 0;
+}
+
+static int cbc_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		/* fall back to the non-bitsliced NEON implementation */
+		kernel_neon_begin();
+		neon_aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				     ctx->enc, ctx->key.rounds, blocks,
+				     walk.iv);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
+static int cbc_decrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_cbc_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		if (walk.nbytes < walk.total)
+			blocks = round_down(blocks,
+					    walk.stride / AES_BLOCK_SIZE);
+
+		kernel_neon_begin();
+		aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				  ctx->key.rk, ctx->key.rounds, blocks,
+				  walk.iv);
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+	}
+
+	return err;
+}
+
+static int aesbs_ctr_setkey_sync(struct crypto_skcipher *tfm, const u8 *in_key,
+				 unsigned int key_len)
+{
+	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int err;
+
+	err = aes_expandkey(&ctx->fallback, in_key, key_len);
+	if (err)
+		return err;
+
+	ctx->key.rounds = 6 + key_len / 4;
+
+	kernel_neon_begin();
+	aesbs_convert_key(ctx->key.rk, ctx->fallback.key_enc, ctx->key.rounds);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int ctr_encrypt(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct skcipher_walk walk;
+	u8 buf[AES_BLOCK_SIZE];
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	while (walk.nbytes > 0) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+		u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
+
+		if (walk.nbytes < walk.total) {
+			blocks = round_down(blocks,
+					    walk.stride / AES_BLOCK_SIZE);
+			final = NULL;
+		}
+
+		kernel_neon_begin();
+		aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+				  ctx->rk, ctx->rounds, blocks, walk.iv, final);
+		kernel_neon_end();
+
+		if (final) {
+			u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
+			u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
+
+			crypto_xor_cpy(dst, src, final,
+				       walk.total % AES_BLOCK_SIZE);
+
+			err = skcipher_walk_done(&walk, 0);
+			break;
+		}
+		err = skcipher_walk_done(&walk,
+					 walk.nbytes - blocks * AES_BLOCK_SIZE);
+	}
+	return err;
+}
+
+static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
+			    unsigned int key_len)
+{
+	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct crypto_aes_ctx rk;
+	int err;
+
+	err = xts_verify_key(tfm, in_key, key_len);
+	if (err)
+		return err;
+
+	key_len /= 2;
+	err = aes_expandkey(&ctx->cts, in_key, key_len);
+	if (err)
+		return err;
+
+	err = aes_expandkey(&rk, in_key + key_len, key_len);
+	if (err)
+		return err;
+
+	memcpy(ctx->twkey, rk.key_enc, sizeof(ctx->twkey));
+
+	return aesbs_setkey(tfm, in_key, key_len);
+}
+
+static void ctr_encrypt_one(struct crypto_skcipher *tfm, const u8 *src, u8 *dst)
+{
+	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+	unsigned long flags;
+
+	/*
+	 * Temporarily disable interrupts to avoid races where
+	 * cachelines are evicted when the CPU is interrupted
+	 * to do something else.
+	 */
+	local_irq_save(flags);
+	aes_encrypt(&ctx->fallback, dst, src);
+	local_irq_restore(flags);
+}
+
+static int ctr_encrypt_sync(struct skcipher_request *req)
+{
+	if (!crypto_simd_usable())
+		return crypto_ctr_encrypt_walk(req, ctr_encrypt_one);
+
+	return ctr_encrypt(req);
+}
+
+static int __xts_crypt(struct skcipher_request *req, bool encrypt,
+		       void (*fn)(u8 out[], u8 const in[], u8 const rk[],
+				  int rounds, int blocks, u8 iv[]))
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct aesbs_xts_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int tail = req->cryptlen % (8 * AES_BLOCK_SIZE);
+	struct scatterlist sg_src[2], sg_dst[2];
+	struct skcipher_request subreq;
+	struct scatterlist *src, *dst;
+	struct skcipher_walk walk;
+	int nbytes, err;
+	int first = 1;
+	u8 *out, *in;
+
+	if (req->cryptlen < AES_BLOCK_SIZE)
+		return -EINVAL;
+
+	/* ensure that the cts tail is covered by a single step */
+	if (unlikely(tail > 0 && tail < AES_BLOCK_SIZE)) {
+		int xts_blocks = DIV_ROUND_UP(req->cryptlen,
+					      AES_BLOCK_SIZE) - 2;
+
+		skcipher_request_set_tfm(&subreq, tfm);
+		skcipher_request_set_callback(&subreq,
+					      skcipher_request_flags(req),
+					      NULL, NULL);
+		skcipher_request_set_crypt(&subreq, req->src, req->dst,
+					   xts_blocks * AES_BLOCK_SIZE,
+					   req->iv);
+		req = &subreq;
+	} else {
+		tail = 0;
+	}
+
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
+
+	while (walk.nbytes >= AES_BLOCK_SIZE) {
+		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+		if (walk.nbytes < walk.total || walk.nbytes % AES_BLOCK_SIZE)
+			blocks = round_down(blocks,
+					    walk.stride / AES_BLOCK_SIZE);
+
+		out = walk.dst.virt.addr;
+		in = walk.src.virt.addr;
+		nbytes = walk.nbytes;
+
+		kernel_neon_begin();
+		if (likely(blocks > 6)) { /* plain NEON is faster otherwise */
+			if (first)
+				neon_aes_ecb_encrypt(walk.iv, walk.iv,
+						     ctx->twkey,
+						     ctx->key.rounds, 1);
+			first = 0;
+
+			fn(out, in, ctx->key.rk, ctx->key.rounds, blocks,
+			   walk.iv);
+
+			out += blocks * AES_BLOCK_SIZE;
+			in += blocks * AES_BLOCK_SIZE;
+			nbytes -= blocks * AES_BLOCK_SIZE;
+		}
+
+		if (walk.nbytes == walk.total && nbytes > 0)
+			goto xts_tail;
+
+		kernel_neon_end();
+		err = skcipher_walk_done(&walk, nbytes);
+	}
+
+	if (err || likely(!tail))
+		return err;
+
+	/* handle ciphertext stealing */
+	dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen);
+	if (req->dst != req->src)
+		dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen);
+
+	skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail,
+				   req->iv);
+
+	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
+
+	out = walk.dst.virt.addr;
+	in = walk.src.virt.addr;
+	nbytes = walk.nbytes;
+
+	kernel_neon_begin();
+xts_tail:
+	if (encrypt)
+		neon_aes_xts_encrypt(out, in, ctx->cts.key_enc, ctx->key.rounds,
+				     nbytes, ctx->twkey, walk.iv, first ?: 2);
+	else
+		neon_aes_xts_decrypt(out, in, ctx->cts.key_dec, ctx->key.rounds,
+				     nbytes, ctx->twkey, walk.iv, first ?: 2);
+	kernel_neon_end();
+
+	return skcipher_walk_done(&walk, 0);
+}
+
+static int xts_encrypt(struct skcipher_request *req)
+{
+	return __xts_crypt(req, true, aesbs_xts_encrypt);
+}
+
+static int xts_decrypt(struct skcipher_request *req)
+{
+	return __xts_crypt(req, false, aesbs_xts_decrypt);
+}
+
+static struct skcipher_alg aes_algs[] = { {
+	.base.cra_name		= "__ecb(aes)",
+	.base.cra_driver_name	= "__ecb-aes-neonbs",
+	.base.cra_priority	= 250,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.setkey			= aesbs_setkey,
+	.encrypt		= ecb_encrypt,
+	.decrypt		= ecb_decrypt,
+}, {
+	.base.cra_name		= "__cbc(aes)",
+	.base.cra_driver_name	= "__cbc-aes-neonbs",
+	.base.cra_priority	= 250,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct aesbs_cbc_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_cbc_setkey,
+	.encrypt		= cbc_encrypt,
+	.decrypt		= cbc_decrypt,
+}, {
+	.base.cra_name		= "__ctr(aes)",
+	.base.cra_driver_name	= "__ctr-aes-neonbs",
+	.base.cra_priority	= 250,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct aesbs_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_setkey,
+	.encrypt		= ctr_encrypt,
+	.decrypt		= ctr_encrypt,
+}, {
+	.base.cra_name		= "ctr(aes)",
+	.base.cra_driver_name	= "ctr-aes-neonbs",
+	.base.cra_priority	= 250 - 1,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct aesbs_ctr_ctx),
+	.base.cra_module	= THIS_MODULE,
+
+	.min_keysize		= AES_MIN_KEY_SIZE,
+	.max_keysize		= AES_MAX_KEY_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_ctr_setkey_sync,
+	.encrypt		= ctr_encrypt_sync,
+	.decrypt		= ctr_encrypt_sync,
+}, {
+	.base.cra_name		= "__xts(aes)",
+	.base.cra_driver_name	= "__xts-aes-neonbs",
+	.base.cra_priority	= 250,
+	.base.cra_blocksize	= AES_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct aesbs_xts_ctx),
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_flags		= CRYPTO_ALG_INTERNAL,
+
+	.min_keysize		= 2 * AES_MIN_KEY_SIZE,
+	.max_keysize		= 2 * AES_MAX_KEY_SIZE,
+	.walksize		= 8 * AES_BLOCK_SIZE,
+	.ivsize			= AES_BLOCK_SIZE,
+	.setkey			= aesbs_xts_setkey,
+	.encrypt		= xts_encrypt,
+	.decrypt		= xts_decrypt,
+} };
+
+static struct simd_skcipher_alg *aes_simd_algs[ARRAY_SIZE(aes_algs)];
+
+static void aes_exit(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(aes_simd_algs); i++)
+		if (aes_simd_algs[i])
+			simd_skcipher_free(aes_simd_algs[i]);
+
+	crypto_unregister_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+}
+
+static int __init aes_init(void)
+{
+	struct simd_skcipher_alg *simd;
+	const char *basename;
+	const char *algname;
+	const char *drvname;
+	int err;
+	int i;
+
+	if (!cpu_have_named_feature(ASIMD))
+		return -ENODEV;
+
+	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(aes_algs); i++) {
+		if (!(aes_algs[i].base.cra_flags & CRYPTO_ALG_INTERNAL))
+			continue;
+
+		algname = aes_algs[i].base.cra_name + 2;
+		drvname = aes_algs[i].base.cra_driver_name + 2;
+		basename = aes_algs[i].base.cra_driver_name;
+		simd = simd_skcipher_create_compat(algname, drvname, basename);
+		err = PTR_ERR(simd);
+		if (IS_ERR(simd))
+			goto unregister_simds;
+
+		aes_simd_algs[i] = simd;
+	}
+	return 0;
+
+unregister_simds:
+	aes_exit();
+	return err;
+}
+
+module_init(aes_init);
+module_exit(aes_exit);
diff --git a/arch/arm64/crypto/chacha-neon-core.S b/arch/arm64/crypto/chacha-neon-core.S
new file mode 100644
index 000000000..e90386a7d
--- /dev/null
+++ b/arch/arm64/crypto/chacha-neon-core.S
@@ -0,0 +1,860 @@
+/*
+ * ChaCha/XChaCha NEON helper functions
+ *
+ * Copyright (C) 2016-2018 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.
+ *
+ * Originally based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+#include <asm/cache.h>
+
+	.text
+	.align		6
+
+/*
+ * chacha_permute - permute one block
+ *
+ * Permute one 64-byte block where the state matrix is stored in the four NEON
+ * registers v0-v3.  It performs matrix operations on four words in parallel,
+ * but requires shuffling to rearrange the words after each round.
+ *
+ * The round count is given in w3.
+ *
+ * Clobbers: w3, x10, v4, v12
+ */
+SYM_FUNC_START_LOCAL(chacha_permute)
+
+	adr_l		x10, ROT8
+	ld1		{v12.4s}, [x10]
+
+.Ldoubleround:
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	add		v0.4s, v0.4s, v1.4s
+	eor		v3.16b, v3.16b, v0.16b
+	rev32		v3.8h, v3.8h
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	add		v2.4s, v2.4s, v3.4s
+	eor		v4.16b, v1.16b, v2.16b
+	shl		v1.4s, v4.4s, #12
+	sri		v1.4s, v4.4s, #20
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	add		v0.4s, v0.4s, v1.4s
+	eor		v3.16b, v3.16b, v0.16b
+	tbl		v3.16b, {v3.16b}, v12.16b
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	add		v2.4s, v2.4s, v3.4s
+	eor		v4.16b, v1.16b, v2.16b
+	shl		v1.4s, v4.4s, #7
+	sri		v1.4s, v4.4s, #25
+
+	// x1 = shuffle32(x1, MASK(0, 3, 2, 1))
+	ext		v1.16b, v1.16b, v1.16b, #4
+	// x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	ext		v2.16b, v2.16b, v2.16b, #8
+	// x3 = shuffle32(x3, MASK(2, 1, 0, 3))
+	ext		v3.16b, v3.16b, v3.16b, #12
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	add		v0.4s, v0.4s, v1.4s
+	eor		v3.16b, v3.16b, v0.16b
+	rev32		v3.8h, v3.8h
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	add		v2.4s, v2.4s, v3.4s
+	eor		v4.16b, v1.16b, v2.16b
+	shl		v1.4s, v4.4s, #12
+	sri		v1.4s, v4.4s, #20
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	add		v0.4s, v0.4s, v1.4s
+	eor		v3.16b, v3.16b, v0.16b
+	tbl		v3.16b, {v3.16b}, v12.16b
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	add		v2.4s, v2.4s, v3.4s
+	eor		v4.16b, v1.16b, v2.16b
+	shl		v1.4s, v4.4s, #7
+	sri		v1.4s, v4.4s, #25
+
+	// x1 = shuffle32(x1, MASK(2, 1, 0, 3))
+	ext		v1.16b, v1.16b, v1.16b, #12
+	// x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	ext		v2.16b, v2.16b, v2.16b, #8
+	// x3 = shuffle32(x3, MASK(0, 3, 2, 1))
+	ext		v3.16b, v3.16b, v3.16b, #4
+
+	subs		w3, w3, #2
+	b.ne		.Ldoubleround
+
+	ret
+SYM_FUNC_END(chacha_permute)
+
+SYM_FUNC_START(chacha_block_xor_neon)
+	// x0: Input state matrix, s
+	// x1: 1 data block output, o
+	// x2: 1 data block input, i
+	// w3: nrounds
+
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	// x0..3 = s0..3
+	ld1		{v0.4s-v3.4s}, [x0]
+	ld1		{v8.4s-v11.4s}, [x0]
+
+	bl		chacha_permute
+
+	ld1		{v4.16b-v7.16b}, [x2]
+
+	// o0 = i0 ^ (x0 + s0)
+	add		v0.4s, v0.4s, v8.4s
+	eor		v0.16b, v0.16b, v4.16b
+
+	// o1 = i1 ^ (x1 + s1)
+	add		v1.4s, v1.4s, v9.4s
+	eor		v1.16b, v1.16b, v5.16b
+
+	// o2 = i2 ^ (x2 + s2)
+	add		v2.4s, v2.4s, v10.4s
+	eor		v2.16b, v2.16b, v6.16b
+
+	// o3 = i3 ^ (x3 + s3)
+	add		v3.4s, v3.4s, v11.4s
+	eor		v3.16b, v3.16b, v7.16b
+
+	st1		{v0.16b-v3.16b}, [x1]
+
+	ldp		x29, x30, [sp], #16
+	ret
+SYM_FUNC_END(chacha_block_xor_neon)
+
+SYM_FUNC_START(hchacha_block_neon)
+	// x0: Input state matrix, s
+	// x1: output (8 32-bit words)
+	// w2: nrounds
+
+	stp		x29, x30, [sp, #-16]!
+	mov		x29, sp
+
+	ld1		{v0.4s-v3.4s}, [x0]
+
+	mov		w3, w2
+	bl		chacha_permute
+
+	st1		{v0.4s}, [x1], #16
+	st1		{v3.4s}, [x1]
+
+	ldp		x29, x30, [sp], #16
+	ret
+SYM_FUNC_END(hchacha_block_neon)
+
+	a0		.req	w12
+	a1		.req	w13
+	a2		.req	w14
+	a3		.req	w15
+	a4		.req	w16
+	a5		.req	w17
+	a6		.req	w19
+	a7		.req	w20
+	a8		.req	w21
+	a9		.req	w22
+	a10		.req	w23
+	a11		.req	w24
+	a12		.req	w25
+	a13		.req	w26
+	a14		.req	w27
+	a15		.req	w28
+
+	.align		6
+SYM_FUNC_START(chacha_4block_xor_neon)
+	frame_push	10
+
+	// x0: Input state matrix, s
+	// x1: 4 data blocks output, o
+	// x2: 4 data blocks input, i
+	// w3: nrounds
+	// x4: byte count
+
+	adr_l		x10, .Lpermute
+	and		x5, x4, #63
+	add		x10, x10, x5
+	add		x11, x10, #64
+
+	//
+	// This function encrypts four consecutive ChaCha blocks by loading
+	// the state matrix in NEON registers four times. The algorithm performs
+	// each operation on the corresponding word of each state matrix, hence
+	// requires no word shuffling. For final XORing step we transpose the
+	// matrix by interleaving 32- and then 64-bit words, which allows us to
+	// do XOR in NEON registers.
+	//
+	// At the same time, a fifth block is encrypted in parallel using
+	// scalar registers
+	//
+	adr_l		x9, CTRINC		// ... and ROT8
+	ld1		{v30.4s-v31.4s}, [x9]
+
+	// x0..15[0-3] = s0..3[0..3]
+	add		x8, x0, #16
+	ld4r		{ v0.4s- v3.4s}, [x0]
+	ld4r		{ v4.4s- v7.4s}, [x8], #16
+	ld4r		{ v8.4s-v11.4s}, [x8], #16
+	ld4r		{v12.4s-v15.4s}, [x8]
+
+	mov		a0, v0.s[0]
+	mov		a1, v1.s[0]
+	mov		a2, v2.s[0]
+	mov		a3, v3.s[0]
+	mov		a4, v4.s[0]
+	mov		a5, v5.s[0]
+	mov		a6, v6.s[0]
+	mov		a7, v7.s[0]
+	mov		a8, v8.s[0]
+	mov		a9, v9.s[0]
+	mov		a10, v10.s[0]
+	mov		a11, v11.s[0]
+	mov		a12, v12.s[0]
+	mov		a13, v13.s[0]
+	mov		a14, v14.s[0]
+	mov		a15, v15.s[0]
+
+	// x12 += counter values 1-4
+	add		v12.4s, v12.4s, v30.4s
+
+.Ldoubleround4:
+	// x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+	// x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+	// x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+	// x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+	add		v0.4s, v0.4s, v4.4s
+	  add		a0, a0, a4
+	add		v1.4s, v1.4s, v5.4s
+	  add		a1, a1, a5
+	add		v2.4s, v2.4s, v6.4s
+	  add		a2, a2, a6
+	add		v3.4s, v3.4s, v7.4s
+	  add		a3, a3, a7
+
+	eor		v12.16b, v12.16b, v0.16b
+	  eor		a12, a12, a0
+	eor		v13.16b, v13.16b, v1.16b
+	  eor		a13, a13, a1
+	eor		v14.16b, v14.16b, v2.16b
+	  eor		a14, a14, a2
+	eor		v15.16b, v15.16b, v3.16b
+	  eor		a15, a15, a3
+
+	rev32		v12.8h, v12.8h
+	  ror		a12, a12, #16
+	rev32		v13.8h, v13.8h
+	  ror		a13, a13, #16
+	rev32		v14.8h, v14.8h
+	  ror		a14, a14, #16
+	rev32		v15.8h, v15.8h
+	  ror		a15, a15, #16
+
+	// x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+	// x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+	// x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+	// x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+	add		v8.4s, v8.4s, v12.4s
+	  add		a8, a8, a12
+	add		v9.4s, v9.4s, v13.4s
+	  add		a9, a9, a13
+	add		v10.4s, v10.4s, v14.4s
+	  add		a10, a10, a14
+	add		v11.4s, v11.4s, v15.4s
+	  add		a11, a11, a15
+
+	eor		v16.16b, v4.16b, v8.16b
+	  eor		a4, a4, a8
+	eor		v17.16b, v5.16b, v9.16b
+	  eor		a5, a5, a9
+	eor		v18.16b, v6.16b, v10.16b
+	  eor		a6, a6, a10
+	eor		v19.16b, v7.16b, v11.16b
+	  eor		a7, a7, a11
+
+	shl		v4.4s, v16.4s, #12
+	shl		v5.4s, v17.4s, #12
+	shl		v6.4s, v18.4s, #12
+	shl		v7.4s, v19.4s, #12
+
+	sri		v4.4s, v16.4s, #20
+	  ror		a4, a4, #20
+	sri		v5.4s, v17.4s, #20
+	  ror		a5, a5, #20
+	sri		v6.4s, v18.4s, #20
+	  ror		a6, a6, #20
+	sri		v7.4s, v19.4s, #20
+	  ror		a7, a7, #20
+
+	// x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+	// x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+	// x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+	// x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+	add		v0.4s, v0.4s, v4.4s
+	  add		a0, a0, a4
+	add		v1.4s, v1.4s, v5.4s
+	  add		a1, a1, a5
+	add		v2.4s, v2.4s, v6.4s
+	  add		a2, a2, a6
+	add		v3.4s, v3.4s, v7.4s
+	  add		a3, a3, a7
+
+	eor		v12.16b, v12.16b, v0.16b
+	  eor		a12, a12, a0
+	eor		v13.16b, v13.16b, v1.16b
+	  eor		a13, a13, a1
+	eor		v14.16b, v14.16b, v2.16b
+	  eor		a14, a14, a2
+	eor		v15.16b, v15.16b, v3.16b
+	  eor		a15, a15, a3
+
+	tbl		v12.16b, {v12.16b}, v31.16b
+	  ror		a12, a12, #24
+	tbl		v13.16b, {v13.16b}, v31.16b
+	  ror		a13, a13, #24
+	tbl		v14.16b, {v14.16b}, v31.16b
+	  ror		a14, a14, #24
+	tbl		v15.16b, {v15.16b}, v31.16b
+	  ror		a15, a15, #24
+
+	// x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+	// x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+	// x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+	// x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+	add		v8.4s, v8.4s, v12.4s
+	  add		a8, a8, a12
+	add		v9.4s, v9.4s, v13.4s
+	  add		a9, a9, a13
+	add		v10.4s, v10.4s, v14.4s
+	  add		a10, a10, a14
+	add		v11.4s, v11.4s, v15.4s
+	  add		a11, a11, a15
+
+	eor		v16.16b, v4.16b, v8.16b
+	  eor		a4, a4, a8
+	eor		v17.16b, v5.16b, v9.16b
+	  eor		a5, a5, a9
+	eor		v18.16b, v6.16b, v10.16b
+	  eor		a6, a6, a10
+	eor		v19.16b, v7.16b, v11.16b
+	  eor		a7, a7, a11
+
+	shl		v4.4s, v16.4s, #7
+	shl		v5.4s, v17.4s, #7
+	shl		v6.4s, v18.4s, #7
+	shl		v7.4s, v19.4s, #7
+
+	sri		v4.4s, v16.4s, #25
+	  ror		a4, a4, #25
+	sri		v5.4s, v17.4s, #25
+	  ror		a5, a5, #25
+	sri		v6.4s, v18.4s, #25
+	 ror		a6, a6, #25
+	sri		v7.4s, v19.4s, #25
+	  ror		a7, a7, #25
+
+	// x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+	// x1 += x6, x12 = rotl32(x12 ^ x1, 16)
+	// x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+	// x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+	add		v0.4s, v0.4s, v5.4s
+	  add		a0, a0, a5
+	add		v1.4s, v1.4s, v6.4s
+	  add		a1, a1, a6
+	add		v2.4s, v2.4s, v7.4s
+	  add		a2, a2, a7
+	add		v3.4s, v3.4s, v4.4s
+	  add		a3, a3, a4
+
+	eor		v15.16b, v15.16b, v0.16b
+	  eor		a15, a15, a0
+	eor		v12.16b, v12.16b, v1.16b
+	  eor		a12, a12, a1
+	eor		v13.16b, v13.16b, v2.16b
+	  eor		a13, a13, a2
+	eor		v14.16b, v14.16b, v3.16b
+	  eor		a14, a14, a3
+
+	rev32		v15.8h, v15.8h
+	  ror		a15, a15, #16
+	rev32		v12.8h, v12.8h
+	  ror		a12, a12, #16
+	rev32		v13.8h, v13.8h
+	  ror		a13, a13, #16
+	rev32		v14.8h, v14.8h
+	  ror		a14, a14, #16
+
+	// x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+	// x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+	// x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+	// x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+	add		v10.4s, v10.4s, v15.4s
+	  add		a10, a10, a15
+	add		v11.4s, v11.4s, v12.4s
+	  add		a11, a11, a12
+	add		v8.4s, v8.4s, v13.4s
+	  add		a8, a8, a13
+	add		v9.4s, v9.4s, v14.4s
+	  add		a9, a9, a14
+
+	eor		v16.16b, v5.16b, v10.16b
+	  eor		a5, a5, a10
+	eor		v17.16b, v6.16b, v11.16b
+	  eor		a6, a6, a11
+	eor		v18.16b, v7.16b, v8.16b
+	  eor		a7, a7, a8
+	eor		v19.16b, v4.16b, v9.16b
+	  eor		a4, a4, a9
+
+	shl		v5.4s, v16.4s, #12
+	shl		v6.4s, v17.4s, #12
+	shl		v7.4s, v18.4s, #12
+	shl		v4.4s, v19.4s, #12
+
+	sri		v5.4s, v16.4s, #20
+	  ror		a5, a5, #20
+	sri		v6.4s, v17.4s, #20
+	  ror		a6, a6, #20
+	sri		v7.4s, v18.4s, #20
+	  ror		a7, a7, #20
+	sri		v4.4s, v19.4s, #20
+	  ror		a4, a4, #20
+
+	// x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+	// x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+	// x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+	// x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+	add		v0.4s, v0.4s, v5.4s
+	  add		a0, a0, a5
+	add		v1.4s, v1.4s, v6.4s
+	  add		a1, a1, a6
+	add		v2.4s, v2.4s, v7.4s
+	  add		a2, a2, a7
+	add		v3.4s, v3.4s, v4.4s
+	  add		a3, a3, a4
+
+	eor		v15.16b, v15.16b, v0.16b
+	  eor		a15, a15, a0
+	eor		v12.16b, v12.16b, v1.16b
+	  eor		a12, a12, a1
+	eor		v13.16b, v13.16b, v2.16b
+	  eor		a13, a13, a2
+	eor		v14.16b, v14.16b, v3.16b
+	  eor		a14, a14, a3
+
+	tbl		v15.16b, {v15.16b}, v31.16b
+	  ror		a15, a15, #24
+	tbl		v12.16b, {v12.16b}, v31.16b
+	  ror		a12, a12, #24
+	tbl		v13.16b, {v13.16b}, v31.16b
+	  ror		a13, a13, #24
+	tbl		v14.16b, {v14.16b}, v31.16b
+	  ror		a14, a14, #24
+
+	// x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+	// x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+	// x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+	// x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+	add		v10.4s, v10.4s, v15.4s
+	  add		a10, a10, a15
+	add		v11.4s, v11.4s, v12.4s
+	  add		a11, a11, a12
+	add		v8.4s, v8.4s, v13.4s
+	  add		a8, a8, a13
+	add		v9.4s, v9.4s, v14.4s
+	  add		a9, a9, a14
+
+	eor		v16.16b, v5.16b, v10.16b
+	  eor		a5, a5, a10
+	eor		v17.16b, v6.16b, v11.16b
+	  eor		a6, a6, a11
+	eor		v18.16b, v7.16b, v8.16b
+	  eor		a7, a7, a8
+	eor		v19.16b, v4.16b, v9.16b
+	  eor		a4, a4, a9
+
+	shl		v5.4s, v16.4s, #7
+	shl		v6.4s, v17.4s, #7
+	shl		v7.4s, v18.4s, #7
+	shl		v4.4s, v19.4s, #7
+
+	sri		v5.4s, v16.4s, #25
+	  ror		a5, a5, #25
+	sri		v6.4s, v17.4s, #25
+	  ror		a6, a6, #25
+	sri		v7.4s, v18.4s, #25
+	  ror		a7, a7, #25
+	sri		v4.4s, v19.4s, #25
+	  ror		a4, a4, #25
+
+	subs		w3, w3, #2
+	b.ne		.Ldoubleround4
+
+	ld4r		{v16.4s-v19.4s}, [x0], #16
+	ld4r		{v20.4s-v23.4s}, [x0], #16
+
+	// x12 += counter values 0-3
+	add		v12.4s, v12.4s, v30.4s
+
+	// x0[0-3] += s0[0]
+	// x1[0-3] += s0[1]
+	// x2[0-3] += s0[2]
+	// x3[0-3] += s0[3]
+	add		v0.4s, v0.4s, v16.4s
+	  mov		w6, v16.s[0]
+	  mov		w7, v17.s[0]
+	add		v1.4s, v1.4s, v17.4s
+	  mov		w8, v18.s[0]
+	  mov		w9, v19.s[0]
+	add		v2.4s, v2.4s, v18.4s
+	  add		a0, a0, w6
+	  add		a1, a1, w7
+	add		v3.4s, v3.4s, v19.4s
+	  add		a2, a2, w8
+	  add		a3, a3, w9
+CPU_BE(	  rev		a0, a0		)
+CPU_BE(	  rev		a1, a1		)
+CPU_BE(	  rev		a2, a2		)
+CPU_BE(	  rev		a3, a3		)
+
+	ld4r		{v24.4s-v27.4s}, [x0], #16
+	ld4r		{v28.4s-v31.4s}, [x0]
+
+	// x4[0-3] += s1[0]
+	// x5[0-3] += s1[1]
+	// x6[0-3] += s1[2]
+	// x7[0-3] += s1[3]
+	add		v4.4s, v4.4s, v20.4s
+	  mov		w6, v20.s[0]
+	  mov		w7, v21.s[0]
+	add		v5.4s, v5.4s, v21.4s
+	  mov		w8, v22.s[0]
+	  mov		w9, v23.s[0]
+	add		v6.4s, v6.4s, v22.4s
+	  add		a4, a4, w6
+	  add		a5, a5, w7
+	add		v7.4s, v7.4s, v23.4s
+	  add		a6, a6, w8
+	  add		a7, a7, w9
+CPU_BE(	  rev		a4, a4		)
+CPU_BE(	  rev		a5, a5		)
+CPU_BE(	  rev		a6, a6		)
+CPU_BE(	  rev		a7, a7		)
+
+	// x8[0-3] += s2[0]
+	// x9[0-3] += s2[1]
+	// x10[0-3] += s2[2]
+	// x11[0-3] += s2[3]
+	add		v8.4s, v8.4s, v24.4s
+	  mov		w6, v24.s[0]
+	  mov		w7, v25.s[0]
+	add		v9.4s, v9.4s, v25.4s
+	  mov		w8, v26.s[0]
+	  mov		w9, v27.s[0]
+	add		v10.4s, v10.4s, v26.4s
+	  add		a8, a8, w6
+	  add		a9, a9, w7
+	add		v11.4s, v11.4s, v27.4s
+	  add		a10, a10, w8
+	  add		a11, a11, w9
+CPU_BE(	  rev		a8, a8		)
+CPU_BE(	  rev		a9, a9		)
+CPU_BE(	  rev		a10, a10	)
+CPU_BE(	  rev		a11, a11	)
+
+	// x12[0-3] += s3[0]
+	// x13[0-3] += s3[1]
+	// x14[0-3] += s3[2]
+	// x15[0-3] += s3[3]
+	add		v12.4s, v12.4s, v28.4s
+	  mov		w6, v28.s[0]
+	  mov		w7, v29.s[0]
+	add		v13.4s, v13.4s, v29.4s
+	  mov		w8, v30.s[0]
+	  mov		w9, v31.s[0]
+	add		v14.4s, v14.4s, v30.4s
+	  add		a12, a12, w6
+	  add		a13, a13, w7
+	add		v15.4s, v15.4s, v31.4s
+	  add		a14, a14, w8
+	  add		a15, a15, w9
+CPU_BE(	  rev		a12, a12	)
+CPU_BE(	  rev		a13, a13	)
+CPU_BE(	  rev		a14, a14	)
+CPU_BE(	  rev		a15, a15	)
+
+	// interleave 32-bit words in state n, n+1
+	  ldp		w6, w7, [x2], #64
+	zip1		v16.4s, v0.4s, v1.4s
+	  ldp		w8, w9, [x2, #-56]
+	  eor		a0, a0, w6
+	zip2		v17.4s, v0.4s, v1.4s
+	  eor		a1, a1, w7
+	zip1		v18.4s, v2.4s, v3.4s
+	  eor		a2, a2, w8
+	zip2		v19.4s, v2.4s, v3.4s
+	  eor		a3, a3, w9
+	  ldp		w6, w7, [x2, #-48]
+	zip1		v20.4s, v4.4s, v5.4s
+	  ldp		w8, w9, [x2, #-40]
+	  eor		a4, a4, w6
+	zip2		v21.4s, v4.4s, v5.4s
+	  eor		a5, a5, w7
+	zip1		v22.4s, v6.4s, v7.4s
+	  eor		a6, a6, w8
+	zip2		v23.4s, v6.4s, v7.4s
+	  eor		a7, a7, w9
+	  ldp		w6, w7, [x2, #-32]
+	zip1		v24.4s, v8.4s, v9.4s
+	  ldp		w8, w9, [x2, #-24]
+	  eor		a8, a8, w6
+	zip2		v25.4s, v8.4s, v9.4s
+	  eor		a9, a9, w7
+	zip1		v26.4s, v10.4s, v11.4s
+	  eor		a10, a10, w8
+	zip2		v27.4s, v10.4s, v11.4s
+	  eor		a11, a11, w9
+	  ldp		w6, w7, [x2, #-16]
+	zip1		v28.4s, v12.4s, v13.4s
+	  ldp		w8, w9, [x2, #-8]
+	  eor		a12, a12, w6
+	zip2		v29.4s, v12.4s, v13.4s
+	  eor		a13, a13, w7
+	zip1		v30.4s, v14.4s, v15.4s
+	  eor		a14, a14, w8
+	zip2		v31.4s, v14.4s, v15.4s
+	  eor		a15, a15, w9
+
+	mov		x3, #64
+	subs		x5, x4, #128
+	add		x6, x5, x2
+	csel		x3, x3, xzr, ge
+	csel		x2, x2, x6, ge
+
+	// interleave 64-bit words in state n, n+2
+	zip1		v0.2d, v16.2d, v18.2d
+	zip2		v4.2d, v16.2d, v18.2d
+	  stp		a0, a1, [x1], #64
+	zip1		v8.2d, v17.2d, v19.2d
+	zip2		v12.2d, v17.2d, v19.2d
+	  stp		a2, a3, [x1, #-56]
+	ld1		{v16.16b-v19.16b}, [x2], x3
+
+	subs		x6, x4, #192
+	ccmp		x3, xzr, #4, lt
+	add		x7, x6, x2
+	csel		x3, x3, xzr, eq
+	csel		x2, x2, x7, eq
+
+	zip1		v1.2d, v20.2d, v22.2d
+	zip2		v5.2d, v20.2d, v22.2d
+	  stp		a4, a5, [x1, #-48]
+	zip1		v9.2d, v21.2d, v23.2d
+	zip2		v13.2d, v21.2d, v23.2d
+	  stp		a6, a7, [x1, #-40]
+	ld1		{v20.16b-v23.16b}, [x2], x3
+
+	subs		x7, x4, #256
+	ccmp		x3, xzr, #4, lt
+	add		x8, x7, x2
+	csel		x3, x3, xzr, eq
+	csel		x2, x2, x8, eq
+
+	zip1		v2.2d, v24.2d, v26.2d
+	zip2		v6.2d, v24.2d, v26.2d
+	  stp		a8, a9, [x1, #-32]
+	zip1		v10.2d, v25.2d, v27.2d
+	zip2		v14.2d, v25.2d, v27.2d
+	  stp		a10, a11, [x1, #-24]
+	ld1		{v24.16b-v27.16b}, [x2], x3
+
+	subs		x8, x4, #320
+	ccmp		x3, xzr, #4, lt
+	add		x9, x8, x2
+	csel		x2, x2, x9, eq
+
+	zip1		v3.2d, v28.2d, v30.2d
+	zip2		v7.2d, v28.2d, v30.2d
+	  stp		a12, a13, [x1, #-16]
+	zip1		v11.2d, v29.2d, v31.2d
+	zip2		v15.2d, v29.2d, v31.2d
+	  stp		a14, a15, [x1, #-8]
+	ld1		{v28.16b-v31.16b}, [x2]
+
+	// xor with corresponding input, write to output
+	tbnz		x5, #63, 0f
+	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-v19.16b}, [x1], #64
+	cbz		x5, .Lout
+
+	tbnz		x6, #63, 1f
+	eor		v20.16b, v20.16b, v4.16b
+	eor		v21.16b, v21.16b, v5.16b
+	eor		v22.16b, v22.16b, v6.16b
+	eor		v23.16b, v23.16b, v7.16b
+	st1		{v20.16b-v23.16b}, [x1], #64
+	cbz		x6, .Lout
+
+	tbnz		x7, #63, 2f
+	eor		v24.16b, v24.16b, v8.16b
+	eor		v25.16b, v25.16b, v9.16b
+	eor		v26.16b, v26.16b, v10.16b
+	eor		v27.16b, v27.16b, v11.16b
+	st1		{v24.16b-v27.16b}, [x1], #64
+	cbz		x7, .Lout
+
+	tbnz		x8, #63, 3f
+	eor		v28.16b, v28.16b, v12.16b
+	eor		v29.16b, v29.16b, v13.16b
+	eor		v30.16b, v30.16b, v14.16b
+	eor		v31.16b, v31.16b, v15.16b
+	st1		{v28.16b-v31.16b}, [x1]
+
+.Lout:	frame_pop
+	ret
+
+	// fewer than 128 bytes of in/output
+0:	ld1		{v8.16b}, [x10]
+	ld1		{v9.16b}, [x11]
+	movi		v10.16b, #16
+	sub		x2, x1, #64
+	add		x1, x1, x5
+	ld1		{v16.16b-v19.16b}, [x2]
+	tbl		v4.16b, {v0.16b-v3.16b}, v8.16b
+	tbx		v20.16b, {v16.16b-v19.16b}, v9.16b
+	add		v8.16b, v8.16b, v10.16b
+	add		v9.16b, v9.16b, v10.16b
+	tbl		v5.16b, {v0.16b-v3.16b}, v8.16b
+	tbx		v21.16b, {v16.16b-v19.16b}, v9.16b
+	add		v8.16b, v8.16b, v10.16b
+	add		v9.16b, v9.16b, v10.16b
+	tbl		v6.16b, {v0.16b-v3.16b}, v8.16b
+	tbx		v22.16b, {v16.16b-v19.16b}, v9.16b
+	add		v8.16b, v8.16b, v10.16b
+	add		v9.16b, v9.16b, v10.16b
+	tbl		v7.16b, {v0.16b-v3.16b}, v8.16b
+	tbx		v23.16b, {v16.16b-v19.16b}, v9.16b
+
+	eor		v20.16b, v20.16b, v4.16b
+	eor		v21.16b, v21.16b, v5.16b
+	eor		v22.16b, v22.16b, v6.16b
+	eor		v23.16b, v23.16b, v7.16b
+	st1		{v20.16b-v23.16b}, [x1]
+	b		.Lout
+
+	// fewer than 192 bytes of in/output
+1:	ld1		{v8.16b}, [x10]
+	ld1		{v9.16b}, [x11]
+	movi		v10.16b, #16
+	add		x1, x1, x6
+	tbl		v0.16b, {v4.16b-v7.16b}, v8.16b
+	tbx		v20.16b, {v16.16b-v19.16b}, v9.16b
+	add		v8.16b, v8.16b, v10.16b
+	add		v9.16b, v9.16b, v10.16b
+	tbl		v1.16b, {v4.16b-v7.16b}, v8.16b
+	tbx		v21.16b, {v16.16b-v19.16b}, v9.16b
+	add		v8.16b, v8.16b, v10.16b
+	add		v9.16b, v9.16b, v10.16b
+	tbl		v2.16b, {v4.16b-v7.16b}, v8.16b
+	tbx		v22.16b, {v16.16b-v19.16b}, v9.16b
+	add		v8.16b, v8.16b, v10.16b
+	add		v9.16b, v9.16b, v10.16b
+	tbl		v3.16b, {v4.16b-v7.16b}, v8.16b
+	tbx		v23.16b, {v16.16b-v19.16b}, v9.16b
+
+	eor		v20.16b, v20.16b, v0.16b
+	eor		v21.16b, v21.16b, v1.16b
+	eor		v22.16b, v22.16b, v2.16b
+	eor		v23.16b, v23.16b, v3.16b
+	st1		{v20.16b-v23.16b}, [x1]
+	b		.Lout
+
+	// fewer than 256 bytes of in/output
+2:	ld1		{v4.16b}, [x10]
+	ld1		{v5.16b}, [x11]
+	movi		v6.16b, #16
+	add		x1, x1, x7
+	tbl		v0.16b, {v8.16b-v11.16b}, v4.16b
+	tbx		v24.16b, {v20.16b-v23.16b}, v5.16b
+	add		v4.16b, v4.16b, v6.16b
+	add		v5.16b, v5.16b, v6.16b
+	tbl		v1.16b, {v8.16b-v11.16b}, v4.16b
+	tbx		v25.16b, {v20.16b-v23.16b}, v5.16b
+	add		v4.16b, v4.16b, v6.16b
+	add		v5.16b, v5.16b, v6.16b
+	tbl		v2.16b, {v8.16b-v11.16b}, v4.16b
+	tbx		v26.16b, {v20.16b-v23.16b}, v5.16b
+	add		v4.16b, v4.16b, v6.16b
+	add		v5.16b, v5.16b, v6.16b
+	tbl		v3.16b, {v8.16b-v11.16b}, v4.16b
+	tbx		v27.16b, {v20.16b-v23.16b}, v5.16b
+
+	eor		v24.16b, v24.16b, v0.16b
+	eor		v25.16b, v25.16b, v1.16b
+	eor		v26.16b, v26.16b, v2.16b
+	eor		v27.16b, v27.16b, v3.16b
+	st1		{v24.16b-v27.16b}, [x1]
+	b		.Lout
+
+	// fewer than 320 bytes of in/output
+3:	ld1		{v4.16b}, [x10]
+	ld1		{v5.16b}, [x11]
+	movi		v6.16b, #16
+	add		x1, x1, x8
+	tbl		v0.16b, {v12.16b-v15.16b}, v4.16b
+	tbx		v28.16b, {v24.16b-v27.16b}, v5.16b
+	add		v4.16b, v4.16b, v6.16b
+	add		v5.16b, v5.16b, v6.16b
+	tbl		v1.16b, {v12.16b-v15.16b}, v4.16b
+	tbx		v29.16b, {v24.16b-v27.16b}, v5.16b
+	add		v4.16b, v4.16b, v6.16b
+	add		v5.16b, v5.16b, v6.16b
+	tbl		v2.16b, {v12.16b-v15.16b}, v4.16b
+	tbx		v30.16b, {v24.16b-v27.16b}, v5.16b
+	add		v4.16b, v4.16b, v6.16b
+	add		v5.16b, v5.16b, v6.16b
+	tbl		v3.16b, {v12.16b-v15.16b}, v4.16b
+	tbx		v31.16b, {v24.16b-v27.16b}, v5.16b
+
+	eor		v28.16b, v28.16b, v0.16b
+	eor		v29.16b, v29.16b, v1.16b
+	eor		v30.16b, v30.16b, v2.16b
+	eor		v31.16b, v31.16b, v3.16b
+	st1		{v28.16b-v31.16b}, [x1]
+	b		.Lout
+SYM_FUNC_END(chacha_4block_xor_neon)
+
+	.section	".rodata", "a", %progbits
+	.align		L1_CACHE_SHIFT
+.Lpermute:
+	.set		.Li, 0
+	.rept		192
+	.byte		(.Li - 64)
+	.set		.Li, .Li + 1
+	.endr
+
+CTRINC:	.word		1, 2, 3, 4
+ROT8:	.word		0x02010003, 0x06050407, 0x0a09080b, 0x0e0d0c0f
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
new file mode 100644
index 000000000..af2bbca38
--- /dev/null
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -0,0 +1,243 @@
+/*
+ * ARM NEON and scalar accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
+ *
+ * Copyright (C) 2016 - 2017 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.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/chacha.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha_block_xor_neon(u32 *state, u8 *dst, const u8 *src,
+				      int nrounds);
+asmlinkage void chacha_4block_xor_neon(u32 *state, u8 *dst, const u8 *src,
+				       int nrounds, int bytes);
+asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
+			  int bytes, int nrounds)
+{
+	while (bytes > 0) {
+		int l = min(bytes, CHACHA_BLOCK_SIZE * 5);
+
+		if (l <= CHACHA_BLOCK_SIZE) {
+			u8 buf[CHACHA_BLOCK_SIZE];
+
+			memcpy(buf, src, l);
+			chacha_block_xor_neon(state, buf, buf, nrounds);
+			memcpy(dst, buf, l);
+			state[12] += 1;
+			break;
+		}
+		chacha_4block_xor_neon(state, dst, src, nrounds, l);
+		bytes -= l;
+		src += l;
+		dst += l;
+		state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
+	}
+}
+
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+	if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
+		hchacha_block_generic(state, stream, nrounds);
+	} else {
+		kernel_neon_begin();
+		hchacha_block_neon(state, stream, nrounds);
+		kernel_neon_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+	chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+		       int nrounds)
+{
+	if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE ||
+	    !crypto_simd_usable())
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_neon_begin();
+		chacha_doneon(state, dst, src, todo, nrounds);
+		kernel_neon_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+static int chacha_neon_stream_xor(struct skcipher_request *req,
+				  const struct chacha_ctx *ctx, const u8 *iv)
+{
+	struct skcipher_walk walk;
+	u32 state[16];
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
+
+	chacha_init_generic(state, ctx->key, iv);
+
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
+
+		if (nbytes < walk.total)
+			nbytes = rounddown(nbytes, walk.stride);
+
+		if (!static_branch_likely(&have_neon) ||
+		    !crypto_simd_usable()) {
+			chacha_crypt_generic(state, walk.dst.virt.addr,
+					     walk.src.virt.addr, nbytes,
+					     ctx->nrounds);
+		} else {
+			kernel_neon_begin();
+			chacha_doneon(state, walk.dst.virt.addr,
+				      walk.src.virt.addr, nbytes, ctx->nrounds);
+			kernel_neon_end();
+		}
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+	}
+
+	return err;
+}
+
+static int chacha_neon(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	return chacha_neon_stream_xor(req, ctx, req->iv);
+}
+
+static int xchacha_neon(struct skcipher_request *req)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct chacha_ctx subctx;
+	u32 state[16];
+	u8 real_iv[16];
+
+	chacha_init_generic(state, ctx->key, req->iv);
+	hchacha_block_arch(state, subctx.key, ctx->nrounds);
+	subctx.nrounds = ctx->nrounds;
+
+	memcpy(&real_iv[0], req->iv + 24, 8);
+	memcpy(&real_iv[8], req->iv + 16, 8);
+	return chacha_neon_stream_xor(req, &subctx, real_iv);
+}
+
+static struct skcipher_alg algs[] = {
+	{
+		.base.cra_name		= "chacha20",
+		.base.cra_driver_name	= "chacha20-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= CHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.walksize		= 5 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= chacha_neon,
+		.decrypt		= chacha_neon,
+	}, {
+		.base.cra_name		= "xchacha20",
+		.base.cra_driver_name	= "xchacha20-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.walksize		= 5 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha20_setkey,
+		.encrypt		= xchacha_neon,
+		.decrypt		= xchacha_neon,
+	}, {
+		.base.cra_name		= "xchacha12",
+		.base.cra_driver_name	= "xchacha12-neon",
+		.base.cra_priority	= 300,
+		.base.cra_blocksize	= 1,
+		.base.cra_ctxsize	= sizeof(struct chacha_ctx),
+		.base.cra_module	= THIS_MODULE,
+
+		.min_keysize		= CHACHA_KEY_SIZE,
+		.max_keysize		= CHACHA_KEY_SIZE,
+		.ivsize			= XCHACHA_IV_SIZE,
+		.chunksize		= CHACHA_BLOCK_SIZE,
+		.walksize		= 5 * CHACHA_BLOCK_SIZE,
+		.setkey			= chacha12_setkey,
+		.encrypt		= xchacha_neon,
+		.decrypt		= xchacha_neon,
+	}
+};
+
+static int __init chacha_simd_mod_init(void)
+{
+	if (!cpu_have_named_feature(ASIMD))
+		return 0;
+
+	static_branch_enable(&have_neon);
+
+	return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
+		crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
+}
+
+static void __exit chacha_simd_mod_fini(void)
+{
+	if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && cpu_have_named_feature(ASIMD))
+		crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+module_init(chacha_simd_mod_init);
+module_exit(chacha_simd_mod_fini);
+
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-neon");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-neon");
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
new file mode 100644
index 000000000..111d9c9ab
--- /dev/null
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -0,0 +1,536 @@
+//
+// Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
+//
+// Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+// Copyright (C) 2019 Google LLC <ebiggers@google.com>
+//
+// 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.
+//
+
+// Derived from the x86 version:
+//
+// Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
+//
+// Copyright (c) 2013, Intel Corporation
+//
+// Authors:
+//     Erdinc Ozturk <erdinc.ozturk@intel.com>
+//     Vinodh Gopal <vinodh.gopal@intel.com>
+//     James Guilford <james.guilford@intel.com>
+//     Tim Chen <tim.c.chen@linux.intel.com>
+//
+// This software is available to you under a choice of one of two
+// licenses.  You may choose to be licensed under the terms of the GNU
+// General Public License (GPL) Version 2, available from the file
+// COPYING in the main directory of this source tree, or the
+// OpenIB.org BSD license below:
+//
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+// * Redistributions of source code must retain the above copyright
+//   notice, this list of conditions and the following disclaimer.
+//
+// * Redistributions in binary form must reproduce the above copyright
+//   notice, this list of conditions and the following disclaimer in the
+//   documentation and/or other materials provided with the
+//   distribution.
+//
+// * Neither the name of the Intel Corporation nor the names of its
+//   contributors may be used to endorse or promote products derived from
+//   this software without specific prior written permission.
+//
+//
+// THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
+// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
+// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+// LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+// NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+// SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+//
+//       Reference paper titled "Fast CRC Computation for Generic
+//	Polynomials Using PCLMULQDQ Instruction"
+//       URL: http://www.intel.com/content/dam/www/public/us/en/documents
+//  /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
+//
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	init_crc	.req	w19
+	buf		.req	x20
+	len		.req	x21
+	fold_consts_ptr	.req	x22
+
+	fold_consts	.req	v10
+
+	ad		.req	v14
+
+	k00_16		.req	v15
+	k32_48		.req	v16
+
+	t3		.req	v17
+	t4		.req	v18
+	t5		.req	v19
+	t6		.req	v20
+	t7		.req	v21
+	t8		.req	v22
+	t9		.req	v23
+
+	perm1		.req	v24
+	perm2		.req	v25
+	perm3		.req	v26
+	perm4		.req	v27
+
+	bd1		.req	v28
+	bd2		.req	v29
+	bd3		.req	v30
+	bd4		.req	v31
+
+	.macro		__pmull_init_p64
+	.endm
+
+	.macro		__pmull_pre_p64, bd
+	.endm
+
+	.macro		__pmull_init_p8
+	// k00_16 := 0x0000000000000000_000000000000ffff
+	// k32_48 := 0x00000000ffffffff_0000ffffffffffff
+	movi		k32_48.2d, #0xffffffff
+	mov		k32_48.h[2], k32_48.h[0]
+	ushr		k00_16.2d, k32_48.2d, #32
+
+	// prepare the permutation vectors
+	mov_q		x5, 0x080f0e0d0c0b0a09
+	movi		perm4.8b, #8
+	dup		perm1.2d, x5
+	eor		perm1.16b, perm1.16b, perm4.16b
+	ushr		perm2.2d, perm1.2d, #8
+	ushr		perm3.2d, perm1.2d, #16
+	ushr		perm4.2d, perm1.2d, #24
+	sli		perm2.2d, perm1.2d, #56
+	sli		perm3.2d, perm1.2d, #48
+	sli		perm4.2d, perm1.2d, #40
+	.endm
+
+	.macro		__pmull_pre_p8, bd
+	tbl		bd1.16b, {\bd\().16b}, perm1.16b
+	tbl		bd2.16b, {\bd\().16b}, perm2.16b
+	tbl		bd3.16b, {\bd\().16b}, perm3.16b
+	tbl		bd4.16b, {\bd\().16b}, perm4.16b
+	.endm
+
+SYM_FUNC_START_LOCAL(__pmull_p8_core)
+.L__pmull_p8_core:
+	ext		t4.8b, ad.8b, ad.8b, #1			// A1
+	ext		t5.8b, ad.8b, ad.8b, #2			// A2
+	ext		t6.8b, ad.8b, ad.8b, #3			// A3
+
+	pmull		t4.8h, t4.8b, fold_consts.8b		// F = A1*B
+	pmull		t8.8h, ad.8b, bd1.8b			// E = A*B1
+	pmull		t5.8h, t5.8b, fold_consts.8b		// H = A2*B
+	pmull		t7.8h, ad.8b, bd2.8b			// G = A*B2
+	pmull		t6.8h, t6.8b, fold_consts.8b		// J = A3*B
+	pmull		t9.8h, ad.8b, bd3.8b			// I = A*B3
+	pmull		t3.8h, ad.8b, bd4.8b			// K = A*B4
+	b		0f
+
+.L__pmull_p8_core2:
+	tbl		t4.16b, {ad.16b}, perm1.16b		// A1
+	tbl		t5.16b, {ad.16b}, perm2.16b		// A2
+	tbl		t6.16b, {ad.16b}, perm3.16b		// A3
+
+	pmull2		t4.8h, t4.16b, fold_consts.16b		// F = A1*B
+	pmull2		t8.8h, ad.16b, bd1.16b			// E = A*B1
+	pmull2		t5.8h, t5.16b, fold_consts.16b		// H = A2*B
+	pmull2		t7.8h, ad.16b, bd2.16b			// G = A*B2
+	pmull2		t6.8h, t6.16b, fold_consts.16b		// J = A3*B
+	pmull2		t9.8h, ad.16b, bd3.16b			// I = A*B3
+	pmull2		t3.8h, ad.16b, bd4.16b			// K = A*B4
+
+0:	eor		t4.16b, t4.16b, t8.16b			// L = E + F
+	eor		t5.16b, t5.16b, t7.16b			// M = G + H
+	eor		t6.16b, t6.16b, t9.16b			// N = I + J
+
+	uzp1		t8.2d, t4.2d, t5.2d
+	uzp2		t4.2d, t4.2d, t5.2d
+	uzp1		t7.2d, t6.2d, t3.2d
+	uzp2		t6.2d, t6.2d, t3.2d
+
+	// t4 = (L) (P0 + P1) << 8
+	// t5 = (M) (P2 + P3) << 16
+	eor		t8.16b, t8.16b, t4.16b
+	and		t4.16b, t4.16b, k32_48.16b
+
+	// t6 = (N) (P4 + P5) << 24
+	// t7 = (K) (P6 + P7) << 32
+	eor		t7.16b, t7.16b, t6.16b
+	and		t6.16b, t6.16b, k00_16.16b
+
+	eor		t8.16b, t8.16b, t4.16b
+	eor		t7.16b, t7.16b, t6.16b
+
+	zip2		t5.2d, t8.2d, t4.2d
+	zip1		t4.2d, t8.2d, t4.2d
+	zip2		t3.2d, t7.2d, t6.2d
+	zip1		t6.2d, t7.2d, t6.2d
+
+	ext		t4.16b, t4.16b, t4.16b, #15
+	ext		t5.16b, t5.16b, t5.16b, #14
+	ext		t6.16b, t6.16b, t6.16b, #13
+	ext		t3.16b, t3.16b, t3.16b, #12
+
+	eor		t4.16b, t4.16b, t5.16b
+	eor		t6.16b, t6.16b, t3.16b
+	ret
+SYM_FUNC_END(__pmull_p8_core)
+
+	.macro		__pmull_p8, rq, ad, bd, i
+	.ifnc		\bd, fold_consts
+	.err
+	.endif
+	mov		ad.16b, \ad\().16b
+	.ifb		\i
+	pmull		\rq\().8h, \ad\().8b, \bd\().8b		// D = A*B
+	.else
+	pmull2		\rq\().8h, \ad\().16b, \bd\().16b	// D = A*B
+	.endif
+
+	bl		.L__pmull_p8_core\i
+
+	eor		\rq\().16b, \rq\().16b, t4.16b
+	eor		\rq\().16b, \rq\().16b, t6.16b
+	.endm
+
+	// Fold reg1, reg2 into the next 32 data bytes, storing the result back
+	// into reg1, reg2.
+	.macro		fold_32_bytes, p, reg1, reg2
+	ldp		q11, q12, [buf], #0x20
+
+	__pmull_\p	v8, \reg1, fold_consts, 2
+	__pmull_\p	\reg1, \reg1, fold_consts
+
+CPU_LE(	rev64		v11.16b, v11.16b		)
+CPU_LE(	rev64		v12.16b, v12.16b		)
+
+	__pmull_\p	v9, \reg2, fold_consts, 2
+	__pmull_\p	\reg2, \reg2, fold_consts
+
+CPU_LE(	ext		v11.16b, v11.16b, v11.16b, #8	)
+CPU_LE(	ext		v12.16b, v12.16b, v12.16b, #8	)
+
+	eor		\reg1\().16b, \reg1\().16b, v8.16b
+	eor		\reg2\().16b, \reg2\().16b, v9.16b
+	eor		\reg1\().16b, \reg1\().16b, v11.16b
+	eor		\reg2\().16b, \reg2\().16b, v12.16b
+	.endm
+
+	// Fold src_reg into dst_reg, optionally loading the next fold constants
+	.macro		fold_16_bytes, p, src_reg, dst_reg, load_next_consts
+	__pmull_\p	v8, \src_reg, fold_consts
+	__pmull_\p	\src_reg, \src_reg, fold_consts, 2
+	.ifnb		\load_next_consts
+	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
+	__pmull_pre_\p	fold_consts
+	.endif
+	eor		\dst_reg\().16b, \dst_reg\().16b, v8.16b
+	eor		\dst_reg\().16b, \dst_reg\().16b, \src_reg\().16b
+	.endm
+
+	.macro		__pmull_p64, rd, rn, rm, n
+	.ifb		\n
+	pmull		\rd\().1q, \rn\().1d, \rm\().1d
+	.else
+	pmull2		\rd\().1q, \rn\().2d, \rm\().2d
+	.endif
+	.endm
+
+	.macro		crc_t10dif_pmull, p
+	frame_push	4, 128
+
+	mov		init_crc, w0
+	mov		buf, x1
+	mov		len, x2
+
+	__pmull_init_\p
+
+	// For sizes less than 256 bytes, we can't fold 128 bytes at a time.
+	cmp		len, #256
+	b.lt		.Lless_than_256_bytes_\@
+
+	adr_l		fold_consts_ptr, .Lfold_across_128_bytes_consts
+
+	// Load the first 128 data bytes.  Byte swapping is necessary to make
+	// the bit order match the polynomial coefficient order.
+	ldp		q0, q1, [buf]
+	ldp		q2, q3, [buf, #0x20]
+	ldp		q4, q5, [buf, #0x40]
+	ldp		q6, q7, [buf, #0x60]
+	add		buf, buf, #0x80
+CPU_LE(	rev64		v0.16b, v0.16b			)
+CPU_LE(	rev64		v1.16b, v1.16b			)
+CPU_LE(	rev64		v2.16b, v2.16b			)
+CPU_LE(	rev64		v3.16b, v3.16b			)
+CPU_LE(	rev64		v4.16b, v4.16b			)
+CPU_LE(	rev64		v5.16b, v5.16b			)
+CPU_LE(	rev64		v6.16b, v6.16b			)
+CPU_LE(	rev64		v7.16b, v7.16b			)
+CPU_LE(	ext		v0.16b, v0.16b, v0.16b, #8	)
+CPU_LE(	ext		v1.16b, v1.16b, v1.16b, #8	)
+CPU_LE(	ext		v2.16b, v2.16b, v2.16b, #8	)
+CPU_LE(	ext		v3.16b, v3.16b, v3.16b, #8	)
+CPU_LE(	ext		v4.16b, v4.16b, v4.16b, #8	)
+CPU_LE(	ext		v5.16b, v5.16b, v5.16b, #8	)
+CPU_LE(	ext		v6.16b, v6.16b, v6.16b, #8	)
+CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
+
+	// XOR the first 16 data *bits* with the initial CRC value.
+	movi		v8.16b, #0
+	mov		v8.h[7], init_crc
+	eor		v0.16b, v0.16b, v8.16b
+
+	// Load the constants for folding across 128 bytes.
+	ld1		{fold_consts.2d}, [fold_consts_ptr]
+	__pmull_pre_\p	fold_consts
+
+	// Subtract 128 for the 128 data bytes just consumed.  Subtract another
+	// 128 to simplify the termination condition of the following loop.
+	sub		len, len, #256
+
+	// While >= 128 data bytes remain (not counting v0-v7), fold the 128
+	// bytes v0-v7 into them, storing the result back into v0-v7.
+.Lfold_128_bytes_loop_\@:
+	fold_32_bytes	\p, v0, v1
+	fold_32_bytes	\p, v2, v3
+	fold_32_bytes	\p, v4, v5
+	fold_32_bytes	\p, v6, v7
+
+	subs		len, len, #128
+	b.lt		.Lfold_128_bytes_loop_done_\@
+
+	if_will_cond_yield_neon
+	stp		q0, q1, [sp, #.Lframe_local_offset]
+	stp		q2, q3, [sp, #.Lframe_local_offset + 32]
+	stp		q4, q5, [sp, #.Lframe_local_offset + 64]
+	stp		q6, q7, [sp, #.Lframe_local_offset + 96]
+	do_cond_yield_neon
+	ldp		q0, q1, [sp, #.Lframe_local_offset]
+	ldp		q2, q3, [sp, #.Lframe_local_offset + 32]
+	ldp		q4, q5, [sp, #.Lframe_local_offset + 64]
+	ldp		q6, q7, [sp, #.Lframe_local_offset + 96]
+	ld1		{fold_consts.2d}, [fold_consts_ptr]
+	__pmull_init_\p
+	__pmull_pre_\p	fold_consts
+	endif_yield_neon
+
+	b		.Lfold_128_bytes_loop_\@
+
+.Lfold_128_bytes_loop_done_\@:
+
+	// Now fold the 112 bytes in v0-v6 into the 16 bytes in v7.
+
+	// Fold across 64 bytes.
+	add		fold_consts_ptr, fold_consts_ptr, #16
+	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
+	__pmull_pre_\p	fold_consts
+	fold_16_bytes	\p, v0, v4
+	fold_16_bytes	\p, v1, v5
+	fold_16_bytes	\p, v2, v6
+	fold_16_bytes	\p, v3, v7, 1
+	// Fold across 32 bytes.
+	fold_16_bytes	\p, v4, v6
+	fold_16_bytes	\p, v5, v7, 1
+	// Fold across 16 bytes.
+	fold_16_bytes	\p, v6, v7
+
+	// Add 128 to get the correct number of data bytes remaining in 0...127
+	// (not counting v7), following the previous extra subtraction by 128.
+	// Then subtract 16 to simplify the termination condition of the
+	// following loop.
+	adds		len, len, #(128-16)
+
+	// While >= 16 data bytes remain (not counting v7), fold the 16 bytes v7
+	// into them, storing the result back into v7.
+	b.lt		.Lfold_16_bytes_loop_done_\@
+.Lfold_16_bytes_loop_\@:
+	__pmull_\p	v8, v7, fold_consts
+	__pmull_\p	v7, v7, fold_consts, 2
+	eor		v7.16b, v7.16b, v8.16b
+	ldr		q0, [buf], #16
+CPU_LE(	rev64		v0.16b, v0.16b			)
+CPU_LE(	ext		v0.16b, v0.16b, v0.16b, #8	)
+	eor		v7.16b, v7.16b, v0.16b
+	subs		len, len, #16
+	b.ge		.Lfold_16_bytes_loop_\@
+
+.Lfold_16_bytes_loop_done_\@:
+	// Add 16 to get the correct number of data bytes remaining in 0...15
+	// (not counting v7), following the previous extra subtraction by 16.
+	adds		len, len, #16
+	b.eq		.Lreduce_final_16_bytes_\@
+
+.Lhandle_partial_segment_\@:
+	// Reduce the last '16 + len' bytes where 1 <= len <= 15 and the first
+	// 16 bytes are in v7 and the rest are the remaining data in 'buf'.  To
+	// do this without needing a fold constant for each possible 'len',
+	// redivide the bytes into a first chunk of 'len' bytes and a second
+	// chunk of 16 bytes, then fold the first chunk into the second.
+
+	// v0 = last 16 original data bytes
+	add		buf, buf, len
+	ldr		q0, [buf, #-16]
+CPU_LE(	rev64		v0.16b, v0.16b			)
+CPU_LE(	ext		v0.16b, v0.16b, v0.16b, #8	)
+
+	// v1 = high order part of second chunk: v7 left-shifted by 'len' bytes.
+	adr_l		x4, .Lbyteshift_table + 16
+	sub		x4, x4, len
+	ld1		{v2.16b}, [x4]
+	tbl		v1.16b, {v7.16b}, v2.16b
+
+	// v3 = first chunk: v7 right-shifted by '16-len' bytes.
+	movi		v3.16b, #0x80
+	eor		v2.16b, v2.16b, v3.16b
+	tbl		v3.16b, {v7.16b}, v2.16b
+
+	// Convert to 8-bit masks: 'len' 0x00 bytes, then '16-len' 0xff bytes.
+	sshr		v2.16b, v2.16b, #7
+
+	// v2 = second chunk: 'len' bytes from v0 (low-order bytes),
+	// then '16-len' bytes from v1 (high-order bytes).
+	bsl		v2.16b, v1.16b, v0.16b
+
+	// Fold the first chunk into the second chunk, storing the result in v7.
+	__pmull_\p	v0, v3, fold_consts
+	__pmull_\p	v7, v3, fold_consts, 2
+	eor		v7.16b, v7.16b, v0.16b
+	eor		v7.16b, v7.16b, v2.16b
+
+.Lreduce_final_16_bytes_\@:
+	// Reduce the 128-bit value M(x), stored in v7, to the final 16-bit CRC.
+
+	movi		v2.16b, #0		// init zero register
+
+	// Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
+	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
+	__pmull_pre_\p	fold_consts
+
+	// Fold the high 64 bits into the low 64 bits, while also multiplying by
+	// x^64.  This produces a 128-bit value congruent to x^64 * M(x) and
+	// whose low 48 bits are 0.
+	ext		v0.16b, v2.16b, v7.16b, #8
+	__pmull_\p	v7, v7, fold_consts, 2	// high bits * x^48 * (x^80 mod G(x))
+	eor		v0.16b, v0.16b, v7.16b	// + low bits * x^64
+
+	// Fold the high 32 bits into the low 96 bits.  This produces a 96-bit
+	// value congruent to x^64 * M(x) and whose low 48 bits are 0.
+	ext		v1.16b, v0.16b, v2.16b, #12	// extract high 32 bits
+	mov		v0.s[3], v2.s[0]	// zero high 32 bits
+	__pmull_\p	v1, v1, fold_consts	// high 32 bits * x^48 * (x^48 mod G(x))
+	eor		v0.16b, v0.16b, v1.16b	// + low bits
+
+	// Load G(x) and floor(x^48 / G(x)).
+	ld1		{fold_consts.2d}, [fold_consts_ptr]
+	__pmull_pre_\p	fold_consts
+
+	// Use Barrett reduction to compute the final CRC value.
+	__pmull_\p	v1, v0, fold_consts, 2	// high 32 bits * floor(x^48 / G(x))
+	ushr		v1.2d, v1.2d, #32	// /= x^32
+	__pmull_\p	v1, v1, fold_consts	// *= G(x)
+	ushr		v0.2d, v0.2d, #48
+	eor		v0.16b, v0.16b, v1.16b	// + low 16 nonzero bits
+	// Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0.
+
+	umov		w0, v0.h[0]
+	frame_pop
+	ret
+
+.Lless_than_256_bytes_\@:
+	// Checksumming a buffer of length 16...255 bytes
+
+	adr_l		fold_consts_ptr, .Lfold_across_16_bytes_consts
+
+	// Load the first 16 data bytes.
+	ldr		q7, [buf], #0x10
+CPU_LE(	rev64		v7.16b, v7.16b			)
+CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
+
+	// XOR the first 16 data *bits* with the initial CRC value.
+	movi		v0.16b, #0
+	mov		v0.h[7], init_crc
+	eor		v7.16b, v7.16b, v0.16b
+
+	// Load the fold-across-16-bytes constants.
+	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
+	__pmull_pre_\p	fold_consts
+
+	cmp		len, #16
+	b.eq		.Lreduce_final_16_bytes_\@	// len == 16
+	subs		len, len, #32
+	b.ge		.Lfold_16_bytes_loop_\@		// 32 <= len <= 255
+	add		len, len, #16
+	b		.Lhandle_partial_segment_\@	// 17 <= len <= 31
+	.endm
+
+//
+// u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len);
+//
+// Assumes len >= 16.
+//
+SYM_FUNC_START(crc_t10dif_pmull_p8)
+	crc_t10dif_pmull	p8
+SYM_FUNC_END(crc_t10dif_pmull_p8)
+
+	.align		5
+//
+// u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
+//
+// Assumes len >= 16.
+//
+SYM_FUNC_START(crc_t10dif_pmull_p64)
+	crc_t10dif_pmull	p64
+SYM_FUNC_END(crc_t10dif_pmull_p64)
+
+	.section	".rodata", "a"
+	.align		4
+
+// Fold constants precomputed from the polynomial 0x18bb7
+// G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+.Lfold_across_128_bytes_consts:
+	.quad		0x0000000000006123	// x^(8*128)	mod G(x)
+	.quad		0x0000000000002295	// x^(8*128+64)	mod G(x)
+// .Lfold_across_64_bytes_consts:
+	.quad		0x0000000000001069	// x^(4*128)	mod G(x)
+	.quad		0x000000000000dd31	// x^(4*128+64)	mod G(x)
+// .Lfold_across_32_bytes_consts:
+	.quad		0x000000000000857d	// x^(2*128)	mod G(x)
+	.quad		0x0000000000007acc	// x^(2*128+64)	mod G(x)
+.Lfold_across_16_bytes_consts:
+	.quad		0x000000000000a010	// x^(1*128)	mod G(x)
+	.quad		0x0000000000001faa	// x^(1*128+64)	mod G(x)
+// .Lfinal_fold_consts:
+	.quad		0x1368000000000000	// x^48 * (x^48 mod G(x))
+	.quad		0x2d56000000000000	// x^48 * (x^80 mod G(x))
+// .Lbarrett_reduction_consts:
+	.quad		0x0000000000018bb7	// G(x)
+	.quad		0x00000001f65a57f8	// floor(x^48 / G(x))
+
+// For 1 <= len <= 15, the 16-byte vector beginning at &byteshift_table[16 -
+// len] is the index vector to shift left by 'len' bytes, and is also {0x80,
+// ..., 0x80} XOR the index vector to shift right by '16 - len' bytes.
+.Lbyteshift_table:
+	.byte		 0x0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87
+	.byte		0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f
+	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
+	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe , 0x0
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
new file mode 100644
index 000000000..ccc3f6067
--- /dev/null
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
+ *
+ * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/cpufeature.h>
+#include <linux/crc-t10dif.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+#define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
+
+asmlinkage u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len);
+asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
+
+static int crct10dif_init(struct shash_desc *desc)
+{
+	u16 *crc = shash_desc_ctx(desc);
+
+	*crc = 0;
+	return 0;
+}
+
+static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data,
+			    unsigned int length)
+{
+	u16 *crc = shash_desc_ctx(desc);
+
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
+		kernel_neon_begin();
+		*crc = crc_t10dif_pmull_p8(*crc, data, length);
+		kernel_neon_end();
+	} else {
+		*crc = crc_t10dif_generic(*crc, data, length);
+	}
+
+	return 0;
+}
+
+static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data,
+			    unsigned int length)
+{
+	u16 *crc = shash_desc_ctx(desc);
+
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
+		kernel_neon_begin();
+		*crc = crc_t10dif_pmull_p64(*crc, data, length);
+		kernel_neon_end();
+	} else {
+		*crc = crc_t10dif_generic(*crc, data, length);
+	}
+
+	return 0;
+}
+
+static int crct10dif_final(struct shash_desc *desc, u8 *out)
+{
+	u16 *crc = shash_desc_ctx(desc);
+
+	*(u16 *)out = *crc;
+	return 0;
+}
+
+static struct shash_alg crc_t10dif_alg[] = {{
+	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
+	.init			= crct10dif_init,
+	.update			= crct10dif_update_pmull_p8,
+	.final			= crct10dif_final,
+	.descsize		= CRC_T10DIF_DIGEST_SIZE,
+
+	.base.cra_name		= "crct10dif",
+	.base.cra_driver_name	= "crct10dif-arm64-neon",
+	.base.cra_priority	= 100,
+	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
+	.init			= crct10dif_init,
+	.update			= crct10dif_update_pmull_p64,
+	.final			= crct10dif_final,
+	.descsize		= CRC_T10DIF_DIGEST_SIZE,
+
+	.base.cra_name		= "crct10dif",
+	.base.cra_driver_name	= "crct10dif-arm64-ce",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}};
+
+static int __init crc_t10dif_mod_init(void)
+{
+	if (cpu_have_named_feature(PMULL))
+		return crypto_register_shashes(crc_t10dif_alg,
+					       ARRAY_SIZE(crc_t10dif_alg));
+	else
+		/* only register the first array element */
+		return crypto_register_shash(crc_t10dif_alg);
+}
+
+static void __exit crc_t10dif_mod_exit(void)
+{
+	if (cpu_have_named_feature(PMULL))
+		crypto_unregister_shashes(crc_t10dif_alg,
+					  ARRAY_SIZE(crc_t10dif_alg));
+	else
+		crypto_unregister_shash(crc_t10dif_alg);
+}
+
+module_cpu_feature_match(ASIMD, crc_t10dif_mod_init);
+module_exit(crc_t10dif_mod_exit);
+
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-arm64-ce");
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
new file mode 100644
index 000000000..6b958dcdf
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -0,0 +1,762 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	SHASH		.req	v0
+	SHASH2		.req	v1
+	T1		.req	v2
+	T2		.req	v3
+	MASK		.req	v4
+	XM		.req	v5
+	XL		.req	v6
+	XH		.req	v7
+	IN1		.req	v7
+
+	k00_16		.req	v8
+	k32_48		.req	v9
+
+	t3		.req	v10
+	t4		.req	v11
+	t5		.req	v12
+	t6		.req	v13
+	t7		.req	v14
+	t8		.req	v15
+	t9		.req	v16
+
+	perm1		.req	v17
+	perm2		.req	v18
+	perm3		.req	v19
+
+	sh1		.req	v20
+	sh2		.req	v21
+	sh3		.req	v22
+	sh4		.req	v23
+
+	ss1		.req	v24
+	ss2		.req	v25
+	ss3		.req	v26
+	ss4		.req	v27
+
+	XL2		.req	v8
+	XM2		.req	v9
+	XH2		.req	v10
+	XL3		.req	v11
+	XM3		.req	v12
+	XH3		.req	v13
+	TT3		.req	v14
+	TT4		.req	v15
+	HH		.req	v16
+	HH3		.req	v17
+	HH4		.req	v18
+	HH34		.req	v19
+
+	.text
+	.arch		armv8-a+crypto
+
+	.macro		__pmull_p64, rd, rn, rm
+	pmull		\rd\().1q, \rn\().1d, \rm\().1d
+	.endm
+
+	.macro		__pmull2_p64, rd, rn, rm
+	pmull2		\rd\().1q, \rn\().2d, \rm\().2d
+	.endm
+
+	.macro		__pmull_p8, rq, ad, bd
+	ext		t3.8b, \ad\().8b, \ad\().8b, #1		// A1
+	ext		t5.8b, \ad\().8b, \ad\().8b, #2		// A2
+	ext		t7.8b, \ad\().8b, \ad\().8b, #3		// A3
+
+	__pmull_p8_\bd	\rq, \ad
+	.endm
+
+	.macro		__pmull2_p8, rq, ad, bd
+	tbl		t3.16b, {\ad\().16b}, perm1.16b		// A1
+	tbl		t5.16b, {\ad\().16b}, perm2.16b		// A2
+	tbl		t7.16b, {\ad\().16b}, perm3.16b		// A3
+
+	__pmull2_p8_\bd	\rq, \ad
+	.endm
+
+	.macro		__pmull_p8_SHASH, rq, ad
+	__pmull_p8_tail	\rq, \ad\().8b, SHASH.8b, 8b,, sh1, sh2, sh3, sh4
+	.endm
+
+	.macro		__pmull_p8_SHASH2, rq, ad
+	__pmull_p8_tail	\rq, \ad\().8b, SHASH2.8b, 8b,, ss1, ss2, ss3, ss4
+	.endm
+
+	.macro		__pmull2_p8_SHASH, rq, ad
+	__pmull_p8_tail	\rq, \ad\().16b, SHASH.16b, 16b, 2, sh1, sh2, sh3, sh4
+	.endm
+
+	.macro		__pmull_p8_tail, rq, ad, bd, nb, t, b1, b2, b3, b4
+	pmull\t		t3.8h, t3.\nb, \bd			// F = A1*B
+	pmull\t		t4.8h, \ad, \b1\().\nb			// E = A*B1
+	pmull\t		t5.8h, t5.\nb, \bd			// H = A2*B
+	pmull\t		t6.8h, \ad, \b2\().\nb			// G = A*B2
+	pmull\t		t7.8h, t7.\nb, \bd			// J = A3*B
+	pmull\t		t8.8h, \ad, \b3\().\nb			// I = A*B3
+	pmull\t		t9.8h, \ad, \b4\().\nb			// K = A*B4
+	pmull\t		\rq\().8h, \ad, \bd			// D = A*B
+
+	eor		t3.16b, t3.16b, t4.16b			// L = E + F
+	eor		t5.16b, t5.16b, t6.16b			// M = G + H
+	eor		t7.16b, t7.16b, t8.16b			// N = I + J
+
+	uzp1		t4.2d, t3.2d, t5.2d
+	uzp2		t3.2d, t3.2d, t5.2d
+	uzp1		t6.2d, t7.2d, t9.2d
+	uzp2		t7.2d, t7.2d, t9.2d
+
+	// t3 = (L) (P0 + P1) << 8
+	// t5 = (M) (P2 + P3) << 16
+	eor		t4.16b, t4.16b, t3.16b
+	and		t3.16b, t3.16b, k32_48.16b
+
+	// t7 = (N) (P4 + P5) << 24
+	// t9 = (K) (P6 + P7) << 32
+	eor		t6.16b, t6.16b, t7.16b
+	and		t7.16b, t7.16b, k00_16.16b
+
+	eor		t4.16b, t4.16b, t3.16b
+	eor		t6.16b, t6.16b, t7.16b
+
+	zip2		t5.2d, t4.2d, t3.2d
+	zip1		t3.2d, t4.2d, t3.2d
+	zip2		t9.2d, t6.2d, t7.2d
+	zip1		t7.2d, t6.2d, t7.2d
+
+	ext		t3.16b, t3.16b, t3.16b, #15
+	ext		t5.16b, t5.16b, t5.16b, #14
+	ext		t7.16b, t7.16b, t7.16b, #13
+	ext		t9.16b, t9.16b, t9.16b, #12
+
+	eor		t3.16b, t3.16b, t5.16b
+	eor		t7.16b, t7.16b, t9.16b
+	eor		\rq\().16b, \rq\().16b, t3.16b
+	eor		\rq\().16b, \rq\().16b, t7.16b
+	.endm
+
+	.macro		__pmull_pre_p64
+	add		x8, x3, #16
+	ld1		{HH.2d-HH4.2d}, [x8]
+
+	trn1		SHASH2.2d, SHASH.2d, HH.2d
+	trn2		T1.2d, SHASH.2d, HH.2d
+	eor		SHASH2.16b, SHASH2.16b, T1.16b
+
+	trn1		HH34.2d, HH3.2d, HH4.2d
+	trn2		T1.2d, HH3.2d, HH4.2d
+	eor		HH34.16b, HH34.16b, T1.16b
+
+	movi		MASK.16b, #0xe1
+	shl		MASK.2d, MASK.2d, #57
+	.endm
+
+	.macro		__pmull_pre_p8
+	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
+
+	// k00_16 := 0x0000000000000000_000000000000ffff
+	// k32_48 := 0x00000000ffffffff_0000ffffffffffff
+	movi		k32_48.2d, #0xffffffff
+	mov		k32_48.h[2], k32_48.h[0]
+	ushr		k00_16.2d, k32_48.2d, #32
+
+	// prepare the permutation vectors
+	mov_q		x5, 0x080f0e0d0c0b0a09
+	movi		T1.8b, #8
+	dup		perm1.2d, x5
+	eor		perm1.16b, perm1.16b, T1.16b
+	ushr		perm2.2d, perm1.2d, #8
+	ushr		perm3.2d, perm1.2d, #16
+	ushr		T1.2d, perm1.2d, #24
+	sli		perm2.2d, perm1.2d, #56
+	sli		perm3.2d, perm1.2d, #48
+	sli		T1.2d, perm1.2d, #40
+
+	// precompute loop invariants
+	tbl		sh1.16b, {SHASH.16b}, perm1.16b
+	tbl		sh2.16b, {SHASH.16b}, perm2.16b
+	tbl		sh3.16b, {SHASH.16b}, perm3.16b
+	tbl		sh4.16b, {SHASH.16b}, T1.16b
+	ext		ss1.8b, SHASH2.8b, SHASH2.8b, #1
+	ext		ss2.8b, SHASH2.8b, SHASH2.8b, #2
+	ext		ss3.8b, SHASH2.8b, SHASH2.8b, #3
+	ext		ss4.8b, SHASH2.8b, SHASH2.8b, #4
+	.endm
+
+	//
+	// PMULL (64x64->128) based reduction for CPUs that can do
+	// it in a single instruction.
+	//
+	.macro		__pmull_reduce_p64
+	pmull		T2.1q, XL.1d, MASK.1d
+	eor		XM.16b, XM.16b, T1.16b
+
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	eor		XL.16b, XM.16b, T2.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
+	pmull		XL.1q, XL.1d, MASK.1d
+	.endm
+
+	//
+	// Alternative reduction for CPUs that lack support for the
+	// 64x64->128 PMULL instruction
+	//
+	.macro		__pmull_reduce_p8
+	eor		XM.16b, XM.16b, T1.16b
+
+	mov		XL.d[1], XM.d[0]
+	mov		XH.d[0], XM.d[1]
+
+	shl		T1.2d, XL.2d, #57
+	shl		T2.2d, XL.2d, #62
+	eor		T2.16b, T2.16b, T1.16b
+	shl		T1.2d, XL.2d, #63
+	eor		T2.16b, T2.16b, T1.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, T2.16b, T1.16b
+
+	mov		XL.d[1], T2.d[0]
+	mov		XH.d[0], T2.d[1]
+
+	ushr		T2.2d, XL.2d, #1
+	eor		XH.16b, XH.16b, XL.16b
+	eor		XL.16b, XL.16b, T2.16b
+	ushr		T2.2d, T2.2d, #6
+	ushr		XL.2d, XL.2d, #1
+	.endm
+
+	.macro		__pmull_ghash, pn
+	ld1		{SHASH.2d}, [x3]
+	ld1		{XL.2d}, [x1]
+
+	__pmull_pre_\pn
+
+	/* do the head block first, if supplied */
+	cbz		x4, 0f
+	ld1		{T1.2d}, [x4]
+	mov		x4, xzr
+	b		3f
+
+0:	.ifc		\pn, p64
+	tbnz		w0, #0, 2f		// skip until #blocks is a
+	tbnz		w0, #1, 2f		// round multiple of 4
+
+1:	ld1		{XM3.16b-TT4.16b}, [x2], #64
+
+	sub		w0, w0, #4
+
+	rev64		T1.16b, XM3.16b
+	rev64		T2.16b, XH3.16b
+	rev64		TT4.16b, TT4.16b
+	rev64		TT3.16b, TT3.16b
+
+	ext		IN1.16b, TT4.16b, TT4.16b, #8
+	ext		XL3.16b, TT3.16b, TT3.16b, #8
+
+	eor		TT4.16b, TT4.16b, IN1.16b
+	pmull2		XH2.1q, SHASH.2d, IN1.2d	// a1 * b1
+	pmull		XL2.1q, SHASH.1d, IN1.1d	// a0 * b0
+	pmull		XM2.1q, SHASH2.1d, TT4.1d	// (a1 + a0)(b1 + b0)
+
+	eor		TT3.16b, TT3.16b, XL3.16b
+	pmull2		XH3.1q, HH.2d, XL3.2d		// a1 * b1
+	pmull		XL3.1q, HH.1d, XL3.1d		// a0 * b0
+	pmull2		XM3.1q, SHASH2.2d, TT3.2d	// (a1 + a0)(b1 + b0)
+
+	ext		IN1.16b, T2.16b, T2.16b, #8
+	eor		XL2.16b, XL2.16b, XL3.16b
+	eor		XH2.16b, XH2.16b, XH3.16b
+	eor		XM2.16b, XM2.16b, XM3.16b
+
+	eor		T2.16b, T2.16b, IN1.16b
+	pmull2		XH3.1q, HH3.2d, IN1.2d		// a1 * b1
+	pmull		XL3.1q, HH3.1d, IN1.1d		// a0 * b0
+	pmull		XM3.1q, HH34.1d, T2.1d		// (a1 + a0)(b1 + b0)
+
+	eor		XL2.16b, XL2.16b, XL3.16b
+	eor		XH2.16b, XH2.16b, XH3.16b
+	eor		XM2.16b, XM2.16b, XM3.16b
+
+	ext		IN1.16b, T1.16b, T1.16b, #8
+	ext		TT3.16b, XL.16b, XL.16b, #8
+	eor		XL.16b, XL.16b, IN1.16b
+	eor		T1.16b, T1.16b, TT3.16b
+
+	pmull2		XH.1q, HH4.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+	pmull		XL.1q, HH4.1d, XL.1d		// a0 * b0
+	pmull2		XM.1q, HH34.2d, T1.2d		// (a1 + a0)(b1 + b0)
+
+	eor		XL.16b, XL.16b, XL2.16b
+	eor		XH.16b, XH.16b, XH2.16b
+	eor		XM.16b, XM.16b, XM2.16b
+
+	eor		T2.16b, XL.16b, XH.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		XM.16b, XM.16b, T2.16b
+
+	__pmull_reduce_p64
+
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
+
+	cbz		w0, 5f
+	b		1b
+	.endif
+
+2:	ld1		{T1.2d}, [x2], #16
+	sub		w0, w0, #1
+
+3:	/* multiply XL by SHASH in GF(2^128) */
+CPU_LE(	rev64		T1.16b, T1.16b	)
+
+	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		IN1.16b, T1.16b, T1.16b, #8
+	eor		T1.16b, T1.16b, T2.16b
+	eor		XL.16b, XL.16b, IN1.16b
+
+	__pmull2_\pn	XH, XL, SHASH			// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+	__pmull_\pn 	XL, XL, SHASH			// a0 * b0
+	__pmull_\pn	XM, T1, SHASH2			// (a1 + a0)(b1 + b0)
+
+4:	eor		T2.16b, XL.16b, XH.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		XM.16b, XM.16b, T2.16b
+
+	__pmull_reduce_\pn
+
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
+
+	cbnz		w0, 0b
+
+5:	st1		{XL.2d}, [x1]
+	ret
+	.endm
+
+	/*
+	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+	 *			   struct ghash_key const *k, const char *head)
+	 */
+SYM_FUNC_START(pmull_ghash_update_p64)
+	__pmull_ghash	p64
+SYM_FUNC_END(pmull_ghash_update_p64)
+
+SYM_FUNC_START(pmull_ghash_update_p8)
+	__pmull_ghash	p8
+SYM_FUNC_END(pmull_ghash_update_p8)
+
+	KS0		.req	v8
+	KS1		.req	v9
+	KS2		.req	v10
+	KS3		.req	v11
+
+	INP0		.req	v21
+	INP1		.req	v22
+	INP2		.req	v23
+	INP3		.req	v24
+
+	K0		.req	v25
+	K1		.req	v26
+	K2		.req	v27
+	K3		.req	v28
+	K4		.req	v12
+	K5		.req	v13
+	K6		.req	v4
+	K7		.req	v5
+	K8		.req	v14
+	K9		.req	v15
+	KK		.req	v29
+	KL		.req	v30
+	KM		.req	v31
+
+	.macro		load_round_keys, rounds, rk, tmp
+	add		\tmp, \rk, #64
+	ld1		{K0.4s-K3.4s}, [\rk]
+	ld1		{K4.4s-K5.4s}, [\tmp]
+	add		\tmp, \rk, \rounds, lsl #4
+	sub		\tmp, \tmp, #32
+	ld1		{KK.4s-KM.4s}, [\tmp]
+	.endm
+
+	.macro		enc_round, state, key
+	aese		\state\().16b, \key\().16b
+	aesmc		\state\().16b, \state\().16b
+	.endm
+
+	.macro		enc_qround, s0, s1, s2, s3, key
+	enc_round	\s0, \key
+	enc_round	\s1, \key
+	enc_round	\s2, \key
+	enc_round	\s3, \key
+	.endm
+
+	.macro		enc_block, state, rounds, rk, tmp
+	add		\tmp, \rk, #96
+	ld1		{K6.4s-K7.4s}, [\tmp], #32
+	.irp		key, K0, K1, K2, K3, K4 K5
+	enc_round	\state, \key
+	.endr
+
+	tbnz		\rounds, #2, .Lnot128_\@
+.Lout256_\@:
+	enc_round	\state, K6
+	enc_round	\state, K7
+
+.Lout192_\@:
+	enc_round	\state, KK
+	aese		\state\().16b, KL.16b
+	eor		\state\().16b, \state\().16b, KM.16b
+
+	.subsection	1
+.Lnot128_\@:
+	ld1		{K8.4s-K9.4s}, [\tmp], #32
+	enc_round	\state, K6
+	enc_round	\state, K7
+	ld1		{K6.4s-K7.4s}, [\tmp]
+	enc_round	\state, K8
+	enc_round	\state, K9
+	tbz		\rounds, #1, .Lout192_\@
+	b		.Lout256_\@
+	.previous
+	.endm
+
+	.align		6
+	.macro		pmull_gcm_do_crypt, enc
+	stp		x29, x30, [sp, #-32]!
+	mov		x29, sp
+	str		x19, [sp, #24]
+
+	load_round_keys	x7, x6, x8
+
+	ld1		{SHASH.2d}, [x3], #16
+	ld1		{HH.2d-HH4.2d}, [x3]
+
+	trn1		SHASH2.2d, SHASH.2d, HH.2d
+	trn2		T1.2d, SHASH.2d, HH.2d
+	eor		SHASH2.16b, SHASH2.16b, T1.16b
+
+	trn1		HH34.2d, HH3.2d, HH4.2d
+	trn2		T1.2d, HH3.2d, HH4.2d
+	eor		HH34.16b, HH34.16b, T1.16b
+
+	ld1		{XL.2d}, [x4]
+
+	cbz		x0, 3f				// tag only?
+
+	ldr		w8, [x5, #12]			// load lower counter
+CPU_LE(	rev		w8, w8		)
+
+0:	mov		w9, #4				// max blocks per round
+	add		x10, x0, #0xf
+	lsr		x10, x10, #4			// remaining blocks
+
+	subs		x0, x0, #64
+	csel		w9, w10, w9, mi
+	add		w8, w8, w9
+
+	bmi		1f
+	ld1		{INP0.16b-INP3.16b}, [x2], #64
+	.subsection	1
+	/*
+	 * Populate the four input registers right to left with up to 63 bytes
+	 * of data, using overlapping loads to avoid branches.
+	 *
+	 *                INP0     INP1     INP2     INP3
+	 *  1 byte     |        |        |        |x       |
+	 * 16 bytes    |        |        |        |xxxxxxxx|
+	 * 17 bytes    |        |        |xxxxxxxx|x       |
+	 * 47 bytes    |        |xxxxxxxx|xxxxxxxx|xxxxxxx |
+	 * etc etc
+	 *
+	 * Note that this code may read up to 15 bytes before the start of
+	 * the input. It is up to the calling code to ensure this is safe if
+	 * this happens in the first iteration of the loop (i.e., when the
+	 * input size is < 16 bytes)
+	 */
+1:	mov		x15, #16
+	ands		x19, x0, #0xf
+	csel		x19, x19, x15, ne
+	adr_l		x17, .Lpermute_table + 16
+
+	sub		x11, x15, x19
+	add		x12, x17, x11
+	sub		x17, x17, x11
+	ld1		{T1.16b}, [x12]
+	sub		x10, x1, x11
+	sub		x11, x2, x11
+
+	cmp		x0, #-16
+	csel		x14, x15, xzr, gt
+	cmp		x0, #-32
+	csel		x15, x15, xzr, gt
+	cmp		x0, #-48
+	csel		x16, x19, xzr, gt
+	csel		x1, x1, x10, gt
+	csel		x2, x2, x11, gt
+
+	ld1		{INP0.16b}, [x2], x14
+	ld1		{INP1.16b}, [x2], x15
+	ld1		{INP2.16b}, [x2], x16
+	ld1		{INP3.16b}, [x2]
+	tbl		INP3.16b, {INP3.16b}, T1.16b
+	b		2f
+	.previous
+
+2:	.if		\enc == 0
+	bl		pmull_gcm_ghash_4x
+	.endif
+
+	bl		pmull_gcm_enc_4x
+
+	tbnz		x0, #63, 6f
+	st1		{INP0.16b-INP3.16b}, [x1], #64
+	.if		\enc == 1
+	bl		pmull_gcm_ghash_4x
+	.endif
+	bne		0b
+
+3:	ldp		x19, x10, [sp, #24]
+	cbz		x10, 5f				// output tag?
+
+	ld1		{INP3.16b}, [x10]		// load lengths[]
+	mov		w9, #1
+	bl		pmull_gcm_ghash_4x
+
+	mov		w11, #(0x1 << 24)		// BE '1U'
+	ld1		{KS0.16b}, [x5]
+	mov		KS0.s[3], w11
+
+	enc_block	KS0, x7, x6, x12
+
+	ext		XL.16b, XL.16b, XL.16b, #8
+	rev64		XL.16b, XL.16b
+	eor		XL.16b, XL.16b, KS0.16b
+	st1		{XL.16b}, [x10]			// store tag
+
+4:	ldp		x29, x30, [sp], #32
+	ret
+
+5:
+CPU_LE(	rev		w8, w8		)
+	str		w8, [x5, #12]			// store lower counter
+	st1		{XL.2d}, [x4]
+	b		4b
+
+6:	ld1		{T1.16b-T2.16b}, [x17], #32	// permute vectors
+	sub		x17, x17, x19, lsl #1
+
+	cmp		w9, #1
+	beq		7f
+	.subsection	1
+7:	ld1		{INP2.16b}, [x1]
+	tbx		INP2.16b, {INP3.16b}, T1.16b
+	mov		INP3.16b, INP2.16b
+	b		8f
+	.previous
+
+	st1		{INP0.16b}, [x1], x14
+	st1		{INP1.16b}, [x1], x15
+	st1		{INP2.16b}, [x1], x16
+	tbl		INP3.16b, {INP3.16b}, T1.16b
+	tbx		INP3.16b, {INP2.16b}, T2.16b
+8:	st1		{INP3.16b}, [x1]
+
+	.if		\enc == 1
+	ld1		{T1.16b}, [x17]
+	tbl		INP3.16b, {INP3.16b}, T1.16b	// clear non-data bits
+	bl		pmull_gcm_ghash_4x
+	.endif
+	b		3b
+	.endm
+
+	/*
+	 * void pmull_gcm_encrypt(int blocks, u8 dst[], const u8 src[],
+	 *			  struct ghash_key const *k, u64 dg[], u8 ctr[],
+	 *			  int rounds, u8 tag)
+	 */
+SYM_FUNC_START(pmull_gcm_encrypt)
+	pmull_gcm_do_crypt	1
+SYM_FUNC_END(pmull_gcm_encrypt)
+
+	/*
+	 * void pmull_gcm_decrypt(int blocks, u8 dst[], const u8 src[],
+	 *			  struct ghash_key const *k, u64 dg[], u8 ctr[],
+	 *			  int rounds, u8 tag)
+	 */
+SYM_FUNC_START(pmull_gcm_decrypt)
+	pmull_gcm_do_crypt	0
+SYM_FUNC_END(pmull_gcm_decrypt)
+
+SYM_FUNC_START_LOCAL(pmull_gcm_ghash_4x)
+	movi		MASK.16b, #0xe1
+	shl		MASK.2d, MASK.2d, #57
+
+	rev64		T1.16b, INP0.16b
+	rev64		T2.16b, INP1.16b
+	rev64		TT3.16b, INP2.16b
+	rev64		TT4.16b, INP3.16b
+
+	ext		XL.16b, XL.16b, XL.16b, #8
+
+	tbz		w9, #2, 0f			// <4 blocks?
+	.subsection	1
+0:	movi		XH2.16b, #0
+	movi		XM2.16b, #0
+	movi		XL2.16b, #0
+
+	tbz		w9, #0, 1f			// 2 blocks?
+	tbz		w9, #1, 2f			// 1 block?
+
+	eor		T2.16b, T2.16b, XL.16b
+	ext		T1.16b, T2.16b, T2.16b, #8
+	b		.Lgh3
+
+1:	eor		TT3.16b, TT3.16b, XL.16b
+	ext		T2.16b, TT3.16b, TT3.16b, #8
+	b		.Lgh2
+
+2:	eor		TT4.16b, TT4.16b, XL.16b
+	ext		IN1.16b, TT4.16b, TT4.16b, #8
+	b		.Lgh1
+	.previous
+
+	eor		T1.16b, T1.16b, XL.16b
+	ext		IN1.16b, T1.16b, T1.16b, #8
+
+	pmull2		XH2.1q, HH4.2d, IN1.2d		// a1 * b1
+	eor		T1.16b, T1.16b, IN1.16b
+	pmull		XL2.1q, HH4.1d, IN1.1d		// a0 * b0
+	pmull2		XM2.1q, HH34.2d, T1.2d		// (a1 + a0)(b1 + b0)
+
+	ext		T1.16b, T2.16b, T2.16b, #8
+.Lgh3:	eor		T2.16b, T2.16b, T1.16b
+	pmull2		XH.1q, HH3.2d, T1.2d		// a1 * b1
+	pmull		XL.1q, HH3.1d, T1.1d		// a0 * b0
+	pmull		XM.1q, HH34.1d, T2.1d		// (a1 + a0)(b1 + b0)
+
+	eor		XH2.16b, XH2.16b, XH.16b
+	eor		XL2.16b, XL2.16b, XL.16b
+	eor		XM2.16b, XM2.16b, XM.16b
+
+	ext		T2.16b, TT3.16b, TT3.16b, #8
+.Lgh2:	eor		TT3.16b, TT3.16b, T2.16b
+	pmull2		XH.1q, HH.2d, T2.2d		// a1 * b1
+	pmull		XL.1q, HH.1d, T2.1d		// a0 * b0
+	pmull2		XM.1q, SHASH2.2d, TT3.2d	// (a1 + a0)(b1 + b0)
+
+	eor		XH2.16b, XH2.16b, XH.16b
+	eor		XL2.16b, XL2.16b, XL.16b
+	eor		XM2.16b, XM2.16b, XM.16b
+
+	ext		IN1.16b, TT4.16b, TT4.16b, #8
+.Lgh1:	eor		TT4.16b, TT4.16b, IN1.16b
+	pmull		XL.1q, SHASH.1d, IN1.1d		// a0 * b0
+	pmull2		XH.1q, SHASH.2d, IN1.2d		// a1 * b1
+	pmull		XM.1q, SHASH2.1d, TT4.1d	// (a1 + a0)(b1 + b0)
+
+	eor		XH.16b, XH.16b, XH2.16b
+	eor		XL.16b, XL.16b, XL2.16b
+	eor		XM.16b, XM.16b, XM2.16b
+
+	eor		T2.16b, XL.16b, XH.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		XM.16b, XM.16b, T2.16b
+
+	__pmull_reduce_p64
+
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
+
+	ret
+SYM_FUNC_END(pmull_gcm_ghash_4x)
+
+SYM_FUNC_START_LOCAL(pmull_gcm_enc_4x)
+	ld1		{KS0.16b}, [x5]			// load upper counter
+	sub		w10, w8, #4
+	sub		w11, w8, #3
+	sub		w12, w8, #2
+	sub		w13, w8, #1
+	rev		w10, w10
+	rev		w11, w11
+	rev		w12, w12
+	rev		w13, w13
+	mov		KS1.16b, KS0.16b
+	mov		KS2.16b, KS0.16b
+	mov		KS3.16b, KS0.16b
+	ins		KS0.s[3], w10			// set lower counter
+	ins		KS1.s[3], w11
+	ins		KS2.s[3], w12
+	ins		KS3.s[3], w13
+
+	add		x10, x6, #96			// round key pointer
+	ld1		{K6.4s-K7.4s}, [x10], #32
+	.irp		key, K0, K1, K2, K3, K4, K5
+	enc_qround	KS0, KS1, KS2, KS3, \key
+	.endr
+
+	tbnz		x7, #2, .Lnot128
+	.subsection	1
+.Lnot128:
+	ld1		{K8.4s-K9.4s}, [x10], #32
+	.irp		key, K6, K7
+	enc_qround	KS0, KS1, KS2, KS3, \key
+	.endr
+	ld1		{K6.4s-K7.4s}, [x10]
+	.irp		key, K8, K9
+	enc_qround	KS0, KS1, KS2, KS3, \key
+	.endr
+	tbz		x7, #1, .Lout192
+	b		.Lout256
+	.previous
+
+.Lout256:
+	.irp		key, K6, K7
+	enc_qround	KS0, KS1, KS2, KS3, \key
+	.endr
+
+.Lout192:
+	enc_qround	KS0, KS1, KS2, KS3, KK
+
+	aese		KS0.16b, KL.16b
+	aese		KS1.16b, KL.16b
+	aese		KS2.16b, KL.16b
+	aese		KS3.16b, KL.16b
+
+	eor		KS0.16b, KS0.16b, KM.16b
+	eor		KS1.16b, KS1.16b, KM.16b
+	eor		KS2.16b, KS2.16b, KM.16b
+	eor		KS3.16b, KS3.16b, KM.16b
+
+	eor		INP0.16b, INP0.16b, KS0.16b
+	eor		INP1.16b, INP1.16b, KS1.16b
+	eor		INP2.16b, INP2.16b, KS2.16b
+	eor		INP3.16b, INP3.16b, KS3.16b
+
+	ret
+SYM_FUNC_END(pmull_gcm_enc_4x)
+
+	.section	".rodata", "a"
+	.align		6
+.Lpermute_table:
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
+	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe,  0xf
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
+	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe,  0xf
+	.previous
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
new file mode 100644
index 000000000..8536008e3
--- /dev/null
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -0,0 +1,614 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Accelerated GHASH implementation with ARMv8 PMULL instructions.
+ *
+ * Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/b128ops.h>
+#include <crypto/gf128mul.h>
+#include <crypto/internal/aead.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("GHASH and AES-GCM using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("ghash");
+
+#define GHASH_BLOCK_SIZE	16
+#define GHASH_DIGEST_SIZE	16
+#define GCM_IV_SIZE		12
+
+struct ghash_key {
+	be128			k;
+	u64			h[][2];
+};
+
+struct ghash_desc_ctx {
+	u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
+	u8 buf[GHASH_BLOCK_SIZE];
+	u32 count;
+};
+
+struct gcm_aes_ctx {
+	struct crypto_aes_ctx	aes_key;
+	struct ghash_key	ghash_key;
+};
+
+asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
+				       u64 const h[][2], const char *head);
+
+asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
+				      u64 const h[][2], const char *head);
+
+asmlinkage void pmull_gcm_encrypt(int bytes, u8 dst[], const u8 src[],
+				  u64 const h[][2], u64 dg[], u8 ctr[],
+				  u32 const rk[], int rounds, u8 tag[]);
+
+asmlinkage void pmull_gcm_decrypt(int bytes, u8 dst[], const u8 src[],
+				  u64 const h[][2], u64 dg[], u8 ctr[],
+				  u32 const rk[], int rounds, u8 tag[]);
+
+static int ghash_init(struct shash_desc *desc)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static void ghash_do_update(int blocks, u64 dg[], const char *src,
+			    struct ghash_key *key, const char *head)
+{
+	be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
+
+	do {
+		const u8 *in = src;
+
+		if (head) {
+			in = head;
+			blocks++;
+			head = NULL;
+		} else {
+			src += GHASH_BLOCK_SIZE;
+		}
+
+		crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
+		gf128mul_lle(&dst, &key->k);
+	} while (--blocks);
+
+	dg[0] = be64_to_cpu(dst.b);
+	dg[1] = be64_to_cpu(dst.a);
+}
+
+static __always_inline
+void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
+			  struct ghash_key *key, const char *head,
+			  void (*simd_update)(int blocks, u64 dg[],
+					      const char *src,
+					      u64 const h[][2],
+					      const char *head))
+{
+	if (likely(crypto_simd_usable())) {
+		kernel_neon_begin();
+		simd_update(blocks, dg, src, key->h, head);
+		kernel_neon_end();
+	} else {
+		ghash_do_update(blocks, dg, src, key, head);
+	}
+}
+
+/* avoid hogging the CPU for too long */
+#define MAX_BLOCKS	(SZ_64K / GHASH_BLOCK_SIZE)
+
+static int ghash_update(struct shash_desc *desc, const u8 *src,
+			unsigned int len)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	ctx->count += len;
+
+	if ((partial + len) >= GHASH_BLOCK_SIZE) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+		int blocks;
+
+		if (partial) {
+			int p = GHASH_BLOCK_SIZE - partial;
+
+			memcpy(ctx->buf + partial, src, p);
+			src += p;
+			len -= p;
+		}
+
+		blocks = len / GHASH_BLOCK_SIZE;
+		len %= GHASH_BLOCK_SIZE;
+
+		do {
+			int chunk = min(blocks, MAX_BLOCKS);
+
+			ghash_do_simd_update(chunk, ctx->digest, src, key,
+					     partial ? ctx->buf : NULL,
+					     pmull_ghash_update_p8);
+
+			blocks -= chunk;
+			src += chunk * GHASH_BLOCK_SIZE;
+			partial = 0;
+		} while (unlikely(blocks > 0));
+	}
+	if (len)
+		memcpy(ctx->buf + partial, src, len);
+	return 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+	struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+	unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+
+	if (partial) {
+		struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+
+		memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+
+		ghash_do_simd_update(1, ctx->digest, ctx->buf, key, NULL,
+				     pmull_ghash_update_p8);
+	}
+	put_unaligned_be64(ctx->digest[1], dst);
+	put_unaligned_be64(ctx->digest[0], dst + 8);
+
+	*ctx = (struct ghash_desc_ctx){};
+	return 0;
+}
+
+static void ghash_reflect(u64 h[], const be128 *k)
+{
+	u64 carry = be64_to_cpu(k->a) & BIT(63) ? 1 : 0;
+
+	h[0] = (be64_to_cpu(k->b) << 1) | carry;
+	h[1] = (be64_to_cpu(k->a) << 1) | (be64_to_cpu(k->b) >> 63);
+
+	if (carry)
+		h[1] ^= 0xc200000000000000UL;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+			const u8 *inkey, unsigned int keylen)
+{
+	struct ghash_key *key = crypto_shash_ctx(tfm);
+
+	if (keylen != GHASH_BLOCK_SIZE)
+		return -EINVAL;
+
+	/* needed for the fallback */
+	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
+
+	ghash_reflect(key->h[0], &key->k);
+	return 0;
+}
+
+static struct shash_alg ghash_alg = {
+	.base.cra_name		= "ghash",
+	.base.cra_driver_name	= "ghash-neon",
+	.base.cra_priority	= 150,
+	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
+	.base.cra_ctxsize	= sizeof(struct ghash_key) + sizeof(u64[2]),
+	.base.cra_module	= THIS_MODULE,
+
+	.digestsize		= GHASH_DIGEST_SIZE,
+	.init			= ghash_init,
+	.update			= ghash_update,
+	.final			= ghash_final,
+	.setkey			= ghash_setkey,
+	.descsize		= sizeof(struct ghash_desc_ctx),
+};
+
+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 gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
+		      unsigned int keylen)
+{
+	struct gcm_aes_ctx *ctx = crypto_aead_ctx(tfm);
+	u8 key[GHASH_BLOCK_SIZE];
+	be128 h;
+	int ret;
+
+	ret = aes_expandkey(&ctx->aes_key, inkey, keylen);
+	if (ret)
+		return -EINVAL;
+
+	aes_encrypt(&ctx->aes_key, key, (u8[AES_BLOCK_SIZE]){});
+
+	/* needed for the fallback */
+	memcpy(&ctx->ghash_key.k, key, GHASH_BLOCK_SIZE);
+
+	ghash_reflect(ctx->ghash_key.h[0], &ctx->ghash_key.k);
+
+	h = ctx->ghash_key.k;
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[1], &h);
+
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[2], &h);
+
+	gf128mul_lle(&h, &ctx->ghash_key.k);
+	ghash_reflect(ctx->ghash_key.h[3], &h);
+
+	return 0;
+}
+
+static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	switch (authsize) {
+	case 4:
+	case 8:
+	case 12 ... 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void gcm_update_mac(u64 dg[], const u8 *src, int count, u8 buf[],
+			   int *buf_count, struct gcm_aes_ctx *ctx)
+{
+	if (*buf_count > 0) {
+		int buf_added = min(count, GHASH_BLOCK_SIZE - *buf_count);
+
+		memcpy(&buf[*buf_count], src, buf_added);
+
+		*buf_count += buf_added;
+		src += buf_added;
+		count -= buf_added;
+	}
+
+	if (count >= GHASH_BLOCK_SIZE || *buf_count == GHASH_BLOCK_SIZE) {
+		int blocks = count / GHASH_BLOCK_SIZE;
+
+		ghash_do_simd_update(blocks, dg, src, &ctx->ghash_key,
+				     *buf_count ? buf : NULL,
+				     pmull_ghash_update_p64);
+
+		src += blocks * GHASH_BLOCK_SIZE;
+		count %= GHASH_BLOCK_SIZE;
+		*buf_count = 0;
+	}
+
+	if (count > 0) {
+		memcpy(buf, src, count);
+		*buf_count = count;
+	}
+}
+
+static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[])
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
+	u8 buf[GHASH_BLOCK_SIZE];
+	struct scatter_walk walk;
+	u32 len = req->assoclen;
+	int buf_count = 0;
+
+	scatterwalk_start(&walk, req->src);
+
+	do {
+		u32 n = scatterwalk_clamp(&walk, len);
+		u8 *p;
+
+		if (!n) {
+			scatterwalk_start(&walk, sg_next(walk.sg));
+			n = scatterwalk_clamp(&walk, len);
+		}
+		p = scatterwalk_map(&walk);
+
+		gcm_update_mac(dg, p, n, buf, &buf_count, ctx);
+		len -= n;
+
+		scatterwalk_unmap(p);
+		scatterwalk_advance(&walk, n);
+		scatterwalk_done(&walk, 0, len);
+	} while (len);
+
+	if (buf_count) {
+		memset(&buf[buf_count], 0, GHASH_BLOCK_SIZE - buf_count);
+		ghash_do_simd_update(1, dg, buf, &ctx->ghash_key, NULL,
+				     pmull_ghash_update_p64);
+	}
+}
+
+static int gcm_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
+	int nrounds = num_rounds(&ctx->aes_key);
+	struct skcipher_walk walk;
+	u8 buf[AES_BLOCK_SIZE];
+	u8 iv[AES_BLOCK_SIZE];
+	u64 dg[2] = {};
+	be128 lengths;
+	u8 *tag;
+	int err;
+
+	lengths.a = cpu_to_be64(req->assoclen * 8);
+	lengths.b = cpu_to_be64(req->cryptlen * 8);
+
+	if (req->assoclen)
+		gcm_calculate_auth_mac(req, dg);
+
+	memcpy(iv, req->iv, GCM_IV_SIZE);
+	put_unaligned_be32(2, iv + GCM_IV_SIZE);
+
+	err = skcipher_walk_aead_encrypt(&walk, req, false);
+
+	if (likely(crypto_simd_usable())) {
+		do {
+			const u8 *src = walk.src.virt.addr;
+			u8 *dst = walk.dst.virt.addr;
+			int nbytes = walk.nbytes;
+
+			tag = (u8 *)&lengths;
+
+			if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE)) {
+				src = dst = memcpy(buf + sizeof(buf) - nbytes,
+						   src, nbytes);
+			} else if (nbytes < walk.total) {
+				nbytes &= ~(AES_BLOCK_SIZE - 1);
+				tag = NULL;
+			}
+
+			kernel_neon_begin();
+			pmull_gcm_encrypt(nbytes, dst, src, ctx->ghash_key.h,
+					  dg, iv, ctx->aes_key.key_enc, nrounds,
+					  tag);
+			kernel_neon_end();
+
+			if (unlikely(!nbytes))
+				break;
+
+			if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE))
+				memcpy(walk.dst.virt.addr,
+				       buf + sizeof(buf) - nbytes, nbytes);
+
+			err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+		} while (walk.nbytes);
+	} else {
+		while (walk.nbytes >= AES_BLOCK_SIZE) {
+			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			const u8 *src = walk.src.virt.addr;
+			u8 *dst = walk.dst.virt.addr;
+			int remaining = blocks;
+
+			do {
+				aes_encrypt(&ctx->aes_key, buf, iv);
+				crypto_xor_cpy(dst, src, buf, AES_BLOCK_SIZE);
+				crypto_inc(iv, AES_BLOCK_SIZE);
+
+				dst += AES_BLOCK_SIZE;
+				src += AES_BLOCK_SIZE;
+			} while (--remaining > 0);
+
+			ghash_do_update(blocks, dg, walk.dst.virt.addr,
+					&ctx->ghash_key, NULL);
+
+			err = skcipher_walk_done(&walk,
+						 walk.nbytes % AES_BLOCK_SIZE);
+		}
+
+		/* handle the tail */
+		if (walk.nbytes) {
+			aes_encrypt(&ctx->aes_key, buf, iv);
+
+			crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr,
+				       buf, walk.nbytes);
+
+			memcpy(buf, walk.dst.virt.addr, walk.nbytes);
+			memset(buf + walk.nbytes, 0, sizeof(buf) - walk.nbytes);
+		}
+
+		tag = (u8 *)&lengths;
+		ghash_do_update(1, dg, tag, &ctx->ghash_key,
+				walk.nbytes ? buf : NULL);
+
+		if (walk.nbytes)
+			err = skcipher_walk_done(&walk, 0);
+
+		put_unaligned_be64(dg[1], tag);
+		put_unaligned_be64(dg[0], tag + 8);
+		put_unaligned_be32(1, iv + GCM_IV_SIZE);
+		aes_encrypt(&ctx->aes_key, iv, iv);
+		crypto_xor(tag, iv, AES_BLOCK_SIZE);
+	}
+
+	if (err)
+		return err;
+
+	/* copy authtag to end of dst */
+	scatterwalk_map_and_copy(tag, req->dst, req->assoclen + req->cryptlen,
+				 crypto_aead_authsize(aead), 1);
+
+	return 0;
+}
+
+static int gcm_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
+	unsigned int authsize = crypto_aead_authsize(aead);
+	int nrounds = num_rounds(&ctx->aes_key);
+	struct skcipher_walk walk;
+	u8 buf[AES_BLOCK_SIZE];
+	u8 iv[AES_BLOCK_SIZE];
+	u64 dg[2] = {};
+	be128 lengths;
+	u8 *tag;
+	int err;
+
+	lengths.a = cpu_to_be64(req->assoclen * 8);
+	lengths.b = cpu_to_be64((req->cryptlen - authsize) * 8);
+
+	if (req->assoclen)
+		gcm_calculate_auth_mac(req, dg);
+
+	memcpy(iv, req->iv, GCM_IV_SIZE);
+	put_unaligned_be32(2, iv + GCM_IV_SIZE);
+
+	err = skcipher_walk_aead_decrypt(&walk, req, false);
+
+	if (likely(crypto_simd_usable())) {
+		do {
+			const u8 *src = walk.src.virt.addr;
+			u8 *dst = walk.dst.virt.addr;
+			int nbytes = walk.nbytes;
+
+			tag = (u8 *)&lengths;
+
+			if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE)) {
+				src = dst = memcpy(buf + sizeof(buf) - nbytes,
+						   src, nbytes);
+			} else if (nbytes < walk.total) {
+				nbytes &= ~(AES_BLOCK_SIZE - 1);
+				tag = NULL;
+			}
+
+			kernel_neon_begin();
+			pmull_gcm_decrypt(nbytes, dst, src, ctx->ghash_key.h,
+					  dg, iv, ctx->aes_key.key_enc, nrounds,
+					  tag);
+			kernel_neon_end();
+
+			if (unlikely(!nbytes))
+				break;
+
+			if (unlikely(nbytes > 0 && nbytes < AES_BLOCK_SIZE))
+				memcpy(walk.dst.virt.addr,
+				       buf + sizeof(buf) - nbytes, nbytes);
+
+			err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+		} while (walk.nbytes);
+	} else {
+		while (walk.nbytes >= AES_BLOCK_SIZE) {
+			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			const u8 *src = walk.src.virt.addr;
+			u8 *dst = walk.dst.virt.addr;
+
+			ghash_do_update(blocks, dg, walk.src.virt.addr,
+					&ctx->ghash_key, NULL);
+
+			do {
+				aes_encrypt(&ctx->aes_key, buf, iv);
+				crypto_xor_cpy(dst, src, buf, AES_BLOCK_SIZE);
+				crypto_inc(iv, AES_BLOCK_SIZE);
+
+				dst += AES_BLOCK_SIZE;
+				src += AES_BLOCK_SIZE;
+			} while (--blocks > 0);
+
+			err = skcipher_walk_done(&walk,
+						 walk.nbytes % AES_BLOCK_SIZE);
+		}
+
+		/* handle the tail */
+		if (walk.nbytes) {
+			memcpy(buf, walk.src.virt.addr, walk.nbytes);
+			memset(buf + walk.nbytes, 0, sizeof(buf) - walk.nbytes);
+		}
+
+		tag = (u8 *)&lengths;
+		ghash_do_update(1, dg, tag, &ctx->ghash_key,
+				walk.nbytes ? buf : NULL);
+
+		if (walk.nbytes) {
+			aes_encrypt(&ctx->aes_key, buf, iv);
+
+			crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr,
+				       buf, walk.nbytes);
+
+			err = skcipher_walk_done(&walk, 0);
+		}
+
+		put_unaligned_be64(dg[1], tag);
+		put_unaligned_be64(dg[0], tag + 8);
+		put_unaligned_be32(1, iv + GCM_IV_SIZE);
+		aes_encrypt(&ctx->aes_key, iv, iv);
+		crypto_xor(tag, iv, AES_BLOCK_SIZE);
+	}
+
+	if (err)
+		return err;
+
+	/* compare calculated auth tag with the stored one */
+	scatterwalk_map_and_copy(buf, req->src,
+				 req->assoclen + req->cryptlen - authsize,
+				 authsize, 0);
+
+	if (crypto_memneq(tag, buf, authsize))
+		return -EBADMSG;
+	return 0;
+}
+
+static struct aead_alg gcm_aes_alg = {
+	.ivsize			= GCM_IV_SIZE,
+	.chunksize		= AES_BLOCK_SIZE,
+	.maxauthsize		= AES_BLOCK_SIZE,
+	.setkey			= gcm_setkey,
+	.setauthsize		= gcm_setauthsize,
+	.encrypt		= gcm_encrypt,
+	.decrypt		= gcm_decrypt,
+
+	.base.cra_name		= "gcm(aes)",
+	.base.cra_driver_name	= "gcm-aes-ce",
+	.base.cra_priority	= 300,
+	.base.cra_blocksize	= 1,
+	.base.cra_ctxsize	= sizeof(struct gcm_aes_ctx) +
+				  4 * sizeof(u64[2]),
+	.base.cra_module	= THIS_MODULE,
+};
+
+static int __init ghash_ce_mod_init(void)
+{
+	if (!cpu_have_named_feature(ASIMD))
+		return -ENODEV;
+
+	if (cpu_have_named_feature(PMULL))
+		return crypto_register_aead(&gcm_aes_alg);
+
+	return crypto_register_shash(&ghash_alg);
+}
+
+static void __exit ghash_ce_mod_exit(void)
+{
+	if (cpu_have_named_feature(PMULL))
+		crypto_unregister_aead(&gcm_aes_alg);
+	else
+		crypto_unregister_shash(&ghash_alg);
+}
+
+static const struct cpu_feature ghash_cpu_feature[] = {
+	{ cpu_feature(PMULL) }, { }
+};
+MODULE_DEVICE_TABLE(cpu, ghash_cpu_feature);
+
+module_init(ghash_ce_mod_init);
+module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm64/crypto/nh-neon-core.S b/arch/arm64/crypto/nh-neon-core.S
new file mode 100644
index 000000000..51c0a534e
--- /dev/null
+++ b/arch/arm64/crypto/nh-neon-core.S
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * NH - ε-almost-universal hash function, ARM64 NEON accelerated version
+ *
+ * Copyright 2018 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+	KEY		.req	x0
+	MESSAGE		.req	x1
+	MESSAGE_LEN	.req	x2
+	HASH		.req	x3
+
+	PASS0_SUMS	.req	v0
+	PASS1_SUMS	.req	v1
+	PASS2_SUMS	.req	v2
+	PASS3_SUMS	.req	v3
+	K0		.req	v4
+	K1		.req	v5
+	K2		.req	v6
+	K3		.req	v7
+	T0		.req	v8
+	T1		.req	v9
+	T2		.req	v10
+	T3		.req	v11
+	T4		.req	v12
+	T5		.req	v13
+	T6		.req	v14
+	T7		.req	v15
+
+.macro _nh_stride	k0, k1, k2, k3
+
+	// Load next message stride
+	ld1		{T3.16b}, [MESSAGE], #16
+
+	// Load next key stride
+	ld1		{\k3\().4s}, [KEY], #16
+
+	// Add message words to key words
+	add		T0.4s, T3.4s, \k0\().4s
+	add		T1.4s, T3.4s, \k1\().4s
+	add		T2.4s, T3.4s, \k2\().4s
+	add		T3.4s, T3.4s, \k3\().4s
+
+	// Multiply 32x32 => 64 and accumulate
+	mov		T4.d[0], T0.d[1]
+	mov		T5.d[0], T1.d[1]
+	mov		T6.d[0], T2.d[1]
+	mov		T7.d[0], T3.d[1]
+	umlal		PASS0_SUMS.2d, T0.2s, T4.2s
+	umlal		PASS1_SUMS.2d, T1.2s, T5.2s
+	umlal		PASS2_SUMS.2d, T2.2s, T6.2s
+	umlal		PASS3_SUMS.2d, T3.2s, T7.2s
+.endm
+
+/*
+ * void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+ *		u8 hash[NH_HASH_BYTES])
+ *
+ * It's guaranteed that message_len % 16 == 0.
+ */
+SYM_FUNC_START(nh_neon)
+
+	ld1		{K0.4s,K1.4s}, [KEY], #32
+	  movi		PASS0_SUMS.2d, #0
+	  movi		PASS1_SUMS.2d, #0
+	ld1		{K2.4s}, [KEY], #16
+	  movi		PASS2_SUMS.2d, #0
+	  movi		PASS3_SUMS.2d, #0
+
+	subs		MESSAGE_LEN, MESSAGE_LEN, #64
+	blt		.Lloop4_done
+.Lloop4:
+	_nh_stride	K0, K1, K2, K3
+	_nh_stride	K1, K2, K3, K0
+	_nh_stride	K2, K3, K0, K1
+	_nh_stride	K3, K0, K1, K2
+	subs		MESSAGE_LEN, MESSAGE_LEN, #64
+	bge		.Lloop4
+
+.Lloop4_done:
+	ands		MESSAGE_LEN, MESSAGE_LEN, #63
+	beq		.Ldone
+	_nh_stride	K0, K1, K2, K3
+
+	subs		MESSAGE_LEN, MESSAGE_LEN, #16
+	beq		.Ldone
+	_nh_stride	K1, K2, K3, K0
+
+	subs		MESSAGE_LEN, MESSAGE_LEN, #16
+	beq		.Ldone
+	_nh_stride	K2, K3, K0, K1
+
+.Ldone:
+	// Sum the accumulators for each pass, then store the sums to 'hash'
+	addp		T0.2d, PASS0_SUMS.2d, PASS1_SUMS.2d
+	addp		T1.2d, PASS2_SUMS.2d, PASS3_SUMS.2d
+	st1		{T0.16b,T1.16b}, [HASH]
+	ret
+SYM_FUNC_END(nh_neon)
diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c
new file mode 100644
index 000000000..c5405e6a6
--- /dev/null
+++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum
+ * (ARM64 NEON accelerated version)
+ *
+ * Copyright 2018 Google LLC
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/nhpoly1305.h>
+#include <linux/module.h>
+
+asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len,
+			u8 hash[NH_HASH_BYTES]);
+
+/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */
+static void _nh_neon(const u32 *key, const u8 *message, size_t message_len,
+		     __le64 hash[NH_NUM_PASSES])
+{
+	nh_neon(key, message, message_len, (u8 *)hash);
+}
+
+static int nhpoly1305_neon_update(struct shash_desc *desc,
+				  const u8 *src, unsigned int srclen)
+{
+	if (srclen < 64 || !crypto_simd_usable())
+		return crypto_nhpoly1305_update(desc, src, srclen);
+
+	do {
+		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
+
+		kernel_neon_begin();
+		crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon);
+		kernel_neon_end();
+		src += n;
+		srclen -= n;
+	} while (srclen);
+	return 0;
+}
+
+static struct shash_alg nhpoly1305_alg = {
+	.base.cra_name		= "nhpoly1305",
+	.base.cra_driver_name	= "nhpoly1305-neon",
+	.base.cra_priority	= 200,
+	.base.cra_ctxsize	= sizeof(struct nhpoly1305_key),
+	.base.cra_module	= THIS_MODULE,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.init			= crypto_nhpoly1305_init,
+	.update			= nhpoly1305_neon_update,
+	.final			= crypto_nhpoly1305_final,
+	.setkey			= crypto_nhpoly1305_setkey,
+	.descsize		= sizeof(struct nhpoly1305_state),
+};
+
+static int __init nhpoly1305_mod_init(void)
+{
+	if (!cpu_have_named_feature(ASIMD))
+		return -ENODEV;
+
+	return crypto_register_shash(&nhpoly1305_alg);
+}
+
+static void __exit nhpoly1305_mod_exit(void)
+{
+	crypto_unregister_shash(&nhpoly1305_alg);
+}
+
+module_init(nhpoly1305_mod_init);
+module_exit(nhpoly1305_mod_exit);
+
+MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (NEON-accelerated)");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("nhpoly1305");
+MODULE_ALIAS_CRYPTO("nhpoly1305-neon");
diff --git a/arch/arm64/crypto/poly1305-armv8.pl b/arch/arm64/crypto/poly1305-armv8.pl
new file mode 100644
index 000000000..cbc980fb0
--- /dev/null
+++ b/arch/arm64/crypto/poly1305-armv8.pl
@@ -0,0 +1,913 @@
+#!/usr/bin/env perl
+# SPDX-License-Identifier: GPL-1.0+ OR BSD-3-Clause
+#
+# ====================================================================
+# Written by Andy Polyakov, @dot-asm, initially for the OpenSSL
+# project.
+# ====================================================================
+#
+# This module implements Poly1305 hash for ARMv8.
+#
+# June 2015
+#
+# Numbers are cycles per processed byte with poly1305_blocks alone.
+#
+#		IALU/gcc-4.9	NEON
+#
+# Apple A7	1.86/+5%	0.72
+# Cortex-A53	2.69/+58%	1.47
+# Cortex-A57	2.70/+7%	1.14
+# Denver	1.64/+50%	1.18(*)
+# X-Gene	2.13/+68%	2.27
+# Mongoose	1.77/+75%	1.12
+# Kryo		2.70/+55%	1.13
+# ThunderX2	1.17/+95%	1.36
+#
+# (*)	estimate based on resources availability is less than 1.0,
+#	i.e. measured result is worse than expected, presumably binary
+#	translator is not almighty;
+
+$flavour=shift;
+$output=shift;
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
+
+my ($ctx,$inp,$len,$padbit) = map("x$_",(0..3));
+my ($mac,$nonce)=($inp,$len);
+
+my ($h0,$h1,$h2,$r0,$r1,$s1,$t0,$t1,$d0,$d1,$d2) = map("x$_",(4..14));
+
+$code.=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+.extern	OPENSSL_armcap_P
+#endif
+
+.text
+
+// forward "declarations" are required for Apple
+.globl	poly1305_blocks
+.globl	poly1305_emit
+
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+	cmp	$inp,xzr
+	stp	xzr,xzr,[$ctx]		// zero hash value
+	stp	xzr,xzr,[$ctx,#16]	// [along with is_base2_26]
+
+	csel	x0,xzr,x0,eq
+	b.eq	.Lno_key
+
+#ifndef	__KERNEL__
+	adrp	x17,OPENSSL_armcap_P
+	ldr	w17,[x17,#:lo12:OPENSSL_armcap_P]
+#endif
+
+	ldp	$r0,$r1,[$inp]		// load key
+	mov	$s1,#0xfffffffc0fffffff
+	movk	$s1,#0x0fff,lsl#48
+#ifdef	__AARCH64EB__
+	rev	$r0,$r0			// flip bytes
+	rev	$r1,$r1
+#endif
+	and	$r0,$r0,$s1		// &=0ffffffc0fffffff
+	and	$s1,$s1,#-4
+	and	$r1,$r1,$s1		// &=0ffffffc0ffffffc
+	mov	w#$s1,#-1
+	stp	$r0,$r1,[$ctx,#32]	// save key value
+	str	w#$s1,[$ctx,#48]	// impossible key power value
+
+#ifndef	__KERNEL__
+	tst	w17,#ARMV7_NEON
+
+	adr	$d0,.Lpoly1305_blocks
+	adr	$r0,.Lpoly1305_blocks_neon
+	adr	$d1,.Lpoly1305_emit
+
+	csel	$d0,$d0,$r0,eq
+
+# ifdef	__ILP32__
+	stp	w#$d0,w#$d1,[$len]
+# else
+	stp	$d0,$d1,[$len]
+# endif
+#endif
+	mov	x0,#1
+.Lno_key:
+	ret
+.size	poly1305_init,.-poly1305_init
+
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	ands	$len,$len,#-16
+	b.eq	.Lno_data
+
+	ldp	$h0,$h1,[$ctx]		// load hash value
+	ldp	$h2,x17,[$ctx,#16]	// [along with is_base2_26]
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+
+#ifdef	__AARCH64EB__
+	lsr	$d0,$h0,#32
+	mov	w#$d1,w#$h0
+	lsr	$d2,$h1,#32
+	mov	w15,w#$h1
+	lsr	x16,$h2,#32
+#else
+	mov	w#$d0,w#$h0
+	lsr	$d1,$h0,#32
+	mov	w#$d2,w#$h1
+	lsr	x15,$h1,#32
+	mov	w16,w#$h2
+#endif
+
+	add	$d0,$d0,$d1,lsl#26	// base 2^26 -> base 2^64
+	lsr	$d1,$d2,#12
+	adds	$d0,$d0,$d2,lsl#52
+	add	$d1,$d1,x15,lsl#14
+	adc	$d1,$d1,xzr
+	lsr	$d2,x16,#24
+	adds	$d1,$d1,x16,lsl#40
+	adc	$d2,$d2,xzr
+
+	cmp	x17,#0			// is_base2_26?
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+	csel	$h0,$h0,$d0,eq		// choose between radixes
+	csel	$h1,$h1,$d1,eq
+	csel	$h2,$h2,$d2,eq
+
+.Loop:
+	ldp	$t0,$t1,[$inp],#16	// load input
+	sub	$len,$len,#16
+#ifdef	__AARCH64EB__
+	rev	$t0,$t0
+	rev	$t1,$t1
+#endif
+	adds	$h0,$h0,$t0		// accumulate input
+	adcs	$h1,$h1,$t1
+
+	mul	$d0,$h0,$r0		// h0*r0
+	adc	$h2,$h2,$padbit
+	umulh	$d1,$h0,$r0
+
+	mul	$t0,$h1,$s1		// h1*5*r1
+	umulh	$t1,$h1,$s1
+
+	adds	$d0,$d0,$t0
+	mul	$t0,$h0,$r1		// h0*r1
+	adc	$d1,$d1,$t1
+	umulh	$d2,$h0,$r1
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h1,$r0		// h1*r0
+	adc	$d2,$d2,xzr
+	umulh	$t1,$h1,$r0
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h2,$s1		// h2*5*r1
+	adc	$d2,$d2,$t1
+	mul	$t1,$h2,$r0		// h2*r0
+
+	adds	$d1,$d1,$t0
+	adc	$d2,$d2,$t1
+
+	and	$t0,$d2,#-4		// final reduction
+	and	$h2,$d2,#3
+	add	$t0,$t0,$d2,lsr#2
+	adds	$h0,$d0,$t0
+	adcs	$h1,$d1,xzr
+	adc	$h2,$h2,xzr
+
+	cbnz	$len,.Loop
+
+	stp	$h0,$h1,[$ctx]		// store hash value
+	stp	$h2,xzr,[$ctx,#16]	// [and clear is_base2_26]
+
+.Lno_data:
+	ret
+.size	poly1305_blocks,.-poly1305_blocks
+
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	ldp	$h0,$h1,[$ctx]		// load hash base 2^64
+	ldp	$h2,$r0,[$ctx,#16]	// [along with is_base2_26]
+	ldp	$t0,$t1,[$nonce]	// load nonce
+
+#ifdef	__AARCH64EB__
+	lsr	$d0,$h0,#32
+	mov	w#$d1,w#$h0
+	lsr	$d2,$h1,#32
+	mov	w15,w#$h1
+	lsr	x16,$h2,#32
+#else
+	mov	w#$d0,w#$h0
+	lsr	$d1,$h0,#32
+	mov	w#$d2,w#$h1
+	lsr	x15,$h1,#32
+	mov	w16,w#$h2
+#endif
+
+	add	$d0,$d0,$d1,lsl#26	// base 2^26 -> base 2^64
+	lsr	$d1,$d2,#12
+	adds	$d0,$d0,$d2,lsl#52
+	add	$d1,$d1,x15,lsl#14
+	adc	$d1,$d1,xzr
+	lsr	$d2,x16,#24
+	adds	$d1,$d1,x16,lsl#40
+	adc	$d2,$d2,xzr
+
+	cmp	$r0,#0			// is_base2_26?
+	csel	$h0,$h0,$d0,eq		// choose between radixes
+	csel	$h1,$h1,$d1,eq
+	csel	$h2,$h2,$d2,eq
+
+	adds	$d0,$h0,#5		// compare to modulus
+	adcs	$d1,$h1,xzr
+	adc	$d2,$h2,xzr
+
+	tst	$d2,#-4			// see if it's carried/borrowed
+
+	csel	$h0,$h0,$d0,eq
+	csel	$h1,$h1,$d1,eq
+
+#ifdef	__AARCH64EB__
+	ror	$t0,$t0,#32		// flip nonce words
+	ror	$t1,$t1,#32
+#endif
+	adds	$h0,$h0,$t0		// accumulate nonce
+	adc	$h1,$h1,$t1
+#ifdef	__AARCH64EB__
+	rev	$h0,$h0			// flip output bytes
+	rev	$h1,$h1
+#endif
+	stp	$h0,$h1,[$mac]		// write result
+
+	ret
+.size	poly1305_emit,.-poly1305_emit
+___
+my ($R0,$R1,$S1,$R2,$S2,$R3,$S3,$R4,$S4) = map("v$_.4s",(0..8));
+my ($IN01_0,$IN01_1,$IN01_2,$IN01_3,$IN01_4) = map("v$_.2s",(9..13));
+my ($IN23_0,$IN23_1,$IN23_2,$IN23_3,$IN23_4) = map("v$_.2s",(14..18));
+my ($ACC0,$ACC1,$ACC2,$ACC3,$ACC4) = map("v$_.2d",(19..23));
+my ($H0,$H1,$H2,$H3,$H4) = map("v$_.2s",(24..28));
+my ($T0,$T1,$MASK) = map("v$_",(29..31));
+
+my ($in2,$zeros)=("x16","x17");
+my $is_base2_26 = $zeros;		# borrow
+
+$code.=<<___;
+.type	poly1305_mult,%function
+.align	5
+poly1305_mult:
+	mul	$d0,$h0,$r0		// h0*r0
+	umulh	$d1,$h0,$r0
+
+	mul	$t0,$h1,$s1		// h1*5*r1
+	umulh	$t1,$h1,$s1
+
+	adds	$d0,$d0,$t0
+	mul	$t0,$h0,$r1		// h0*r1
+	adc	$d1,$d1,$t1
+	umulh	$d2,$h0,$r1
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h1,$r0		// h1*r0
+	adc	$d2,$d2,xzr
+	umulh	$t1,$h1,$r0
+
+	adds	$d1,$d1,$t0
+	mul	$t0,$h2,$s1		// h2*5*r1
+	adc	$d2,$d2,$t1
+	mul	$t1,$h2,$r0		// h2*r0
+
+	adds	$d1,$d1,$t0
+	adc	$d2,$d2,$t1
+
+	and	$t0,$d2,#-4		// final reduction
+	and	$h2,$d2,#3
+	add	$t0,$t0,$d2,lsr#2
+	adds	$h0,$d0,$t0
+	adcs	$h1,$d1,xzr
+	adc	$h2,$h2,xzr
+
+	ret
+.size	poly1305_mult,.-poly1305_mult
+
+.type	poly1305_splat,%function
+.align	4
+poly1305_splat:
+	and	x12,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x13,$h0,#26,#26
+	extr	x14,$h1,$h0,#52
+	and	x14,x14,#0x03ffffff
+	ubfx	x15,$h1,#14,#26
+	extr	x16,$h2,$h1,#40
+
+	str	w12,[$ctx,#16*0]	// r0
+	add	w12,w13,w13,lsl#2	// r1*5
+	str	w13,[$ctx,#16*1]	// r1
+	add	w13,w14,w14,lsl#2	// r2*5
+	str	w12,[$ctx,#16*2]	// s1
+	str	w14,[$ctx,#16*3]	// r2
+	add	w14,w15,w15,lsl#2	// r3*5
+	str	w13,[$ctx,#16*4]	// s2
+	str	w15,[$ctx,#16*5]	// r3
+	add	w15,w16,w16,lsl#2	// r4*5
+	str	w14,[$ctx,#16*6]	// s3
+	str	w16,[$ctx,#16*7]	// r4
+	str	w15,[$ctx,#16*8]	// s4
+
+	ret
+.size	poly1305_splat,.-poly1305_splat
+
+#ifdef	__KERNEL__
+.globl	poly1305_blocks_neon
+#endif
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	$is_base2_26,[$ctx,#24]
+	cmp	$len,#128
+	b.lo	.Lpoly1305_blocks
+
+	.inst	0xd503233f		// paciasp
+	stp	x29,x30,[sp,#-80]!
+	add	x29,sp,#0
+
+	stp	d8,d9,[sp,#16]		// meet ABI requirements
+	stp	d10,d11,[sp,#32]
+	stp	d12,d13,[sp,#48]
+	stp	d14,d15,[sp,#64]
+
+	cbz	$is_base2_26,.Lbase2_64_neon
+
+	ldp	w10,w11,[$ctx]		// load hash value base 2^26
+	ldp	w12,w13,[$ctx,#8]
+	ldr	w14,[$ctx,#16]
+
+	tst	$len,#31
+	b.eq	.Leven_neon
+
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+
+	add	$h0,x10,x11,lsl#26	// base 2^26 -> base 2^64
+	lsr	$h1,x12,#12
+	adds	$h0,$h0,x12,lsl#52
+	add	$h1,$h1,x13,lsl#14
+	adc	$h1,$h1,xzr
+	lsr	$h2,x14,#24
+	adds	$h1,$h1,x14,lsl#40
+	adc	$d2,$h2,xzr		// can be partially reduced...
+
+	ldp	$d0,$d1,[$inp],#16	// load input
+	sub	$len,$len,#16
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+
+#ifdef	__AARCH64EB__
+	rev	$d0,$d0
+	rev	$d1,$d1
+#endif
+	adds	$h0,$h0,$d0		// accumulate input
+	adcs	$h1,$h1,$d1
+	adc	$h2,$h2,$padbit
+
+	bl	poly1305_mult
+
+	and	x10,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,$h0,#26,#26
+	extr	x12,$h1,$h0,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,$h1,#14,#26
+	extr	x14,$h2,$h1,#40
+
+	b	.Leven_neon
+
+.align	4
+.Lbase2_64_neon:
+	ldp	$r0,$r1,[$ctx,#32]	// load key value
+
+	ldp	$h0,$h1,[$ctx]		// load hash value base 2^64
+	ldr	$h2,[$ctx,#16]
+
+	tst	$len,#31
+	b.eq	.Linit_neon
+
+	ldp	$d0,$d1,[$inp],#16	// load input
+	sub	$len,$len,#16
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+#ifdef	__AARCH64EB__
+	rev	$d0,$d0
+	rev	$d1,$d1
+#endif
+	adds	$h0,$h0,$d0		// accumulate input
+	adcs	$h1,$h1,$d1
+	adc	$h2,$h2,$padbit
+
+	bl	poly1305_mult
+
+.Linit_neon:
+	ldr	w17,[$ctx,#48]		// first table element
+	and	x10,$h0,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,$h0,#26,#26
+	extr	x12,$h1,$h0,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,$h1,#14,#26
+	extr	x14,$h2,$h1,#40
+
+	cmp	w17,#-1			// is value impossible?
+	b.ne	.Leven_neon
+
+	fmov	${H0},x10
+	fmov	${H1},x11
+	fmov	${H2},x12
+	fmov	${H3},x13
+	fmov	${H4},x14
+
+	////////////////////////////////// initialize r^n table
+	mov	$h0,$r0			// r^1
+	add	$s1,$r1,$r1,lsr#2	// s1 = r1 + (r1 >> 2)
+	mov	$h1,$r1
+	mov	$h2,xzr
+	add	$ctx,$ctx,#48+12
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^2
+	sub	$ctx,$ctx,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^3
+	sub	$ctx,$ctx,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^4
+	sub	$ctx,$ctx,#4
+	bl	poly1305_splat
+	sub	$ctx,$ctx,#48		// restore original $ctx
+	b	.Ldo_neon
+
+.align	4
+.Leven_neon:
+	fmov	${H0},x10
+	fmov	${H1},x11
+	fmov	${H2},x12
+	fmov	${H3},x13
+	fmov	${H4},x14
+
+.Ldo_neon:
+	ldp	x8,x12,[$inp,#32]	// inp[2:3]
+	subs	$len,$len,#64
+	ldp	x9,x13,[$inp,#48]
+	add	$in2,$inp,#96
+	adr	$zeros,.Lzeros
+
+	lsl	$padbit,$padbit,#24
+	add	x15,$ctx,#48
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	$IN23_0,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,$padbit,x12,lsr#40
+	add	x13,$padbit,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	$IN23_1,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	fmov	$IN23_2,x8
+	fmov	$IN23_3,x10
+	fmov	$IN23_4,x12
+
+	ldp	x8,x12,[$inp],#16	// inp[0:1]
+	ldp	x9,x13,[$inp],#48
+
+	ld1	{$R0,$R1,$S1,$R2},[x15],#64
+	ld1	{$S2,$R3,$S3,$R4},[x15],#64
+	ld1	{$S4},[x15]
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	$IN01_0,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,$padbit,x12,lsr#40
+	add	x13,$padbit,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	$IN01_1,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	movi	$MASK.2d,#-1
+	fmov	$IN01_2,x8
+	fmov	$IN01_3,x10
+	fmov	$IN01_4,x12
+	ushr	$MASK.2d,$MASK.2d,#38
+
+	b.ls	.Lskip_loop
+
+.align	4
+.Loop_neon:
+	////////////////////////////////////////////////////////////////
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	//   \___________________/
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	//   \___________________/ \____________________/
+	//
+	// Note that we start with inp[2:3]*r^2. This is because it
+	// doesn't depend on reduction in previous iteration.
+	////////////////////////////////////////////////////////////////
+	// d4 = h0*r4 + h1*r3   + h2*r2   + h3*r1   + h4*r0
+	// d3 = h0*r3 + h1*r2   + h2*r1   + h3*r0   + h4*5*r4
+	// d2 = h0*r2 + h1*r1   + h2*r0   + h3*5*r4 + h4*5*r3
+	// d1 = h0*r1 + h1*r0   + h2*5*r4 + h3*5*r3 + h4*5*r2
+	// d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1
+
+	subs	$len,$len,#64
+	umull	$ACC4,$IN23_0,${R4}[2]
+	csel	$in2,$zeros,$in2,lo
+	umull	$ACC3,$IN23_0,${R3}[2]
+	umull	$ACC2,$IN23_0,${R2}[2]
+	 ldp	x8,x12,[$in2],#16	// inp[2:3] (or zero)
+	umull	$ACC1,$IN23_0,${R1}[2]
+	 ldp	x9,x13,[$in2],#48
+	umull	$ACC0,$IN23_0,${R0}[2]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	umlal	$ACC4,$IN23_1,${R3}[2]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	$ACC3,$IN23_1,${R2}[2]
+	 and	x5,x9,#0x03ffffff
+	umlal	$ACC2,$IN23_1,${R1}[2]
+	 ubfx	x6,x8,#26,#26
+	umlal	$ACC1,$IN23_1,${R0}[2]
+	 ubfx	x7,x9,#26,#26
+	umlal	$ACC0,$IN23_1,${S4}[2]
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+
+	umlal	$ACC4,$IN23_2,${R2}[2]
+	 extr	x8,x12,x8,#52
+	umlal	$ACC3,$IN23_2,${R1}[2]
+	 extr	x9,x13,x9,#52
+	umlal	$ACC2,$IN23_2,${R0}[2]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	$ACC1,$IN23_2,${S4}[2]
+	 fmov	$IN23_0,x4
+	umlal	$ACC0,$IN23_2,${S3}[2]
+	 and	x8,x8,#0x03ffffff
+
+	umlal	$ACC4,$IN23_3,${R1}[2]
+	 and	x9,x9,#0x03ffffff
+	umlal	$ACC3,$IN23_3,${R0}[2]
+	 ubfx	x10,x12,#14,#26
+	umlal	$ACC2,$IN23_3,${S4}[2]
+	 ubfx	x11,x13,#14,#26
+	umlal	$ACC1,$IN23_3,${S3}[2]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	$ACC0,$IN23_3,${S2}[2]
+	 fmov	$IN23_1,x6
+
+	add	$IN01_2,$IN01_2,$H2
+	 add	x12,$padbit,x12,lsr#40
+	umlal	$ACC4,$IN23_4,${R0}[2]
+	 add	x13,$padbit,x13,lsr#40
+	umlal	$ACC3,$IN23_4,${S4}[2]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	$ACC2,$IN23_4,${S3}[2]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	$ACC1,$IN23_4,${S2}[2]
+	 fmov	$IN23_2,x8
+	umlal	$ACC0,$IN23_4,${S1}[2]
+	 fmov	$IN23_3,x10
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4 and accumulate
+
+	add	$IN01_0,$IN01_0,$H0
+	 fmov	$IN23_4,x12
+	umlal	$ACC3,$IN01_2,${R1}[0]
+	 ldp	x8,x12,[$inp],#16	// inp[0:1]
+	umlal	$ACC0,$IN01_2,${S3}[0]
+	 ldp	x9,x13,[$inp],#48
+	umlal	$ACC4,$IN01_2,${R2}[0]
+	umlal	$ACC1,$IN01_2,${S4}[0]
+	umlal	$ACC2,$IN01_2,${R0}[0]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	add	$IN01_1,$IN01_1,$H1
+	umlal	$ACC3,$IN01_0,${R3}[0]
+	umlal	$ACC4,$IN01_0,${R4}[0]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	$ACC2,$IN01_0,${R2}[0]
+	 and	x5,x9,#0x03ffffff
+	umlal	$ACC0,$IN01_0,${R0}[0]
+	 ubfx	x6,x8,#26,#26
+	umlal	$ACC1,$IN01_0,${R1}[0]
+	 ubfx	x7,x9,#26,#26
+
+	add	$IN01_3,$IN01_3,$H3
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	umlal	$ACC3,$IN01_1,${R2}[0]
+	 extr	x8,x12,x8,#52
+	umlal	$ACC4,$IN01_1,${R3}[0]
+	 extr	x9,x13,x9,#52
+	umlal	$ACC0,$IN01_1,${S4}[0]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	$ACC2,$IN01_1,${R1}[0]
+	 fmov	$IN01_0,x4
+	umlal	$ACC1,$IN01_1,${R0}[0]
+	 and	x8,x8,#0x03ffffff
+
+	add	$IN01_4,$IN01_4,$H4
+	 and	x9,x9,#0x03ffffff
+	umlal	$ACC3,$IN01_3,${R0}[0]
+	 ubfx	x10,x12,#14,#26
+	umlal	$ACC0,$IN01_3,${S2}[0]
+	 ubfx	x11,x13,#14,#26
+	umlal	$ACC4,$IN01_3,${R1}[0]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	$ACC1,$IN01_3,${S3}[0]
+	 fmov	$IN01_1,x6
+	umlal	$ACC2,$IN01_3,${S4}[0]
+	 add	x12,$padbit,x12,lsr#40
+
+	umlal	$ACC3,$IN01_4,${S4}[0]
+	 add	x13,$padbit,x13,lsr#40
+	umlal	$ACC0,$IN01_4,${S1}[0]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	$ACC4,$IN01_4,${R0}[0]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	$ACC1,$IN01_4,${S2}[0]
+	 fmov	$IN01_2,x8
+	umlal	$ACC2,$IN01_4,${S3}[0]
+	 fmov	$IN01_3,x10
+	 fmov	$IN01_4,x12
+
+	/////////////////////////////////////////////////////////////////
+	// lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	// and P. Schwabe
+	//
+	// [see discussion in poly1305-armv4 module]
+
+	ushr	$T0.2d,$ACC3,#26
+	xtn	$H3,$ACC3
+	 ushr	$T1.2d,$ACC0,#26
+	 and	$ACC0,$ACC0,$MASK.2d
+	add	$ACC4,$ACC4,$T0.2d	// h3 -> h4
+	bic	$H3,#0xfc,lsl#24	// &=0x03ffffff
+	 add	$ACC1,$ACC1,$T1.2d	// h0 -> h1
+
+	ushr	$T0.2d,$ACC4,#26
+	xtn	$H4,$ACC4
+	 ushr	$T1.2d,$ACC1,#26
+	 xtn	$H1,$ACC1
+	bic	$H4,#0xfc,lsl#24
+	 add	$ACC2,$ACC2,$T1.2d	// h1 -> h2
+
+	add	$ACC0,$ACC0,$T0.2d
+	shl	$T0.2d,$T0.2d,#2
+	 shrn	$T1.2s,$ACC2,#26
+	 xtn	$H2,$ACC2
+	add	$ACC0,$ACC0,$T0.2d	// h4 -> h0
+	 bic	$H1,#0xfc,lsl#24
+	 add	$H3,$H3,$T1.2s		// h2 -> h3
+	 bic	$H2,#0xfc,lsl#24
+
+	shrn	$T0.2s,$ACC0,#26
+	xtn	$H0,$ACC0
+	 ushr	$T1.2s,$H3,#26
+	 bic	$H3,#0xfc,lsl#24
+	 bic	$H0,#0xfc,lsl#24
+	add	$H1,$H1,$T0.2s		// h0 -> h1
+	 add	$H4,$H4,$T1.2s		// h3 -> h4
+
+	b.hi	.Loop_neon
+
+.Lskip_loop:
+	dup	$IN23_2,${IN23_2}[0]
+	add	$IN01_2,$IN01_2,$H2
+
+	////////////////////////////////////////////////////////////////
+	// multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	adds	$len,$len,#32
+	b.ne	.Long_tail
+
+	dup	$IN23_2,${IN01_2}[0]
+	add	$IN23_0,$IN01_0,$H0
+	add	$IN23_3,$IN01_3,$H3
+	add	$IN23_1,$IN01_1,$H1
+	add	$IN23_4,$IN01_4,$H4
+
+.Long_tail:
+	dup	$IN23_0,${IN23_0}[0]
+	umull2	$ACC0,$IN23_2,${S3}
+	umull2	$ACC3,$IN23_2,${R1}
+	umull2	$ACC4,$IN23_2,${R2}
+	umull2	$ACC2,$IN23_2,${R0}
+	umull2	$ACC1,$IN23_2,${S4}
+
+	dup	$IN23_1,${IN23_1}[0]
+	umlal2	$ACC0,$IN23_0,${R0}
+	umlal2	$ACC2,$IN23_0,${R2}
+	umlal2	$ACC3,$IN23_0,${R3}
+	umlal2	$ACC4,$IN23_0,${R4}
+	umlal2	$ACC1,$IN23_0,${R1}
+
+	dup	$IN23_3,${IN23_3}[0]
+	umlal2	$ACC0,$IN23_1,${S4}
+	umlal2	$ACC3,$IN23_1,${R2}
+	umlal2	$ACC2,$IN23_1,${R1}
+	umlal2	$ACC4,$IN23_1,${R3}
+	umlal2	$ACC1,$IN23_1,${R0}
+
+	dup	$IN23_4,${IN23_4}[0]
+	umlal2	$ACC3,$IN23_3,${R0}
+	umlal2	$ACC4,$IN23_3,${R1}
+	umlal2	$ACC0,$IN23_3,${S2}
+	umlal2	$ACC1,$IN23_3,${S3}
+	umlal2	$ACC2,$IN23_3,${S4}
+
+	umlal2	$ACC3,$IN23_4,${S4}
+	umlal2	$ACC0,$IN23_4,${S1}
+	umlal2	$ACC4,$IN23_4,${R0}
+	umlal2	$ACC1,$IN23_4,${S2}
+	umlal2	$ACC2,$IN23_4,${S3}
+
+	b.eq	.Lshort_tail
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	add	$IN01_0,$IN01_0,$H0
+	umlal	$ACC3,$IN01_2,${R1}
+	umlal	$ACC0,$IN01_2,${S3}
+	umlal	$ACC4,$IN01_2,${R2}
+	umlal	$ACC1,$IN01_2,${S4}
+	umlal	$ACC2,$IN01_2,${R0}
+
+	add	$IN01_1,$IN01_1,$H1
+	umlal	$ACC3,$IN01_0,${R3}
+	umlal	$ACC0,$IN01_0,${R0}
+	umlal	$ACC4,$IN01_0,${R4}
+	umlal	$ACC1,$IN01_0,${R1}
+	umlal	$ACC2,$IN01_0,${R2}
+
+	add	$IN01_3,$IN01_3,$H3
+	umlal	$ACC3,$IN01_1,${R2}
+	umlal	$ACC0,$IN01_1,${S4}
+	umlal	$ACC4,$IN01_1,${R3}
+	umlal	$ACC1,$IN01_1,${R0}
+	umlal	$ACC2,$IN01_1,${R1}
+
+	add	$IN01_4,$IN01_4,$H4
+	umlal	$ACC3,$IN01_3,${R0}
+	umlal	$ACC0,$IN01_3,${S2}
+	umlal	$ACC4,$IN01_3,${R1}
+	umlal	$ACC1,$IN01_3,${S3}
+	umlal	$ACC2,$IN01_3,${S4}
+
+	umlal	$ACC3,$IN01_4,${S4}
+	umlal	$ACC0,$IN01_4,${S1}
+	umlal	$ACC4,$IN01_4,${R0}
+	umlal	$ACC1,$IN01_4,${S2}
+	umlal	$ACC2,$IN01_4,${S3}
+
+.Lshort_tail:
+	////////////////////////////////////////////////////////////////
+	// horizontal add
+
+	addp	$ACC3,$ACC3,$ACC3
+	 ldp	d8,d9,[sp,#16]		// meet ABI requirements
+	addp	$ACC0,$ACC0,$ACC0
+	 ldp	d10,d11,[sp,#32]
+	addp	$ACC4,$ACC4,$ACC4
+	 ldp	d12,d13,[sp,#48]
+	addp	$ACC1,$ACC1,$ACC1
+	 ldp	d14,d15,[sp,#64]
+	addp	$ACC2,$ACC2,$ACC2
+	 ldr	x30,[sp,#8]
+
+	////////////////////////////////////////////////////////////////
+	// lazy reduction, but without narrowing
+
+	ushr	$T0.2d,$ACC3,#26
+	and	$ACC3,$ACC3,$MASK.2d
+	 ushr	$T1.2d,$ACC0,#26
+	 and	$ACC0,$ACC0,$MASK.2d
+
+	add	$ACC4,$ACC4,$T0.2d	// h3 -> h4
+	 add	$ACC1,$ACC1,$T1.2d	// h0 -> h1
+
+	ushr	$T0.2d,$ACC4,#26
+	and	$ACC4,$ACC4,$MASK.2d
+	 ushr	$T1.2d,$ACC1,#26
+	 and	$ACC1,$ACC1,$MASK.2d
+	 add	$ACC2,$ACC2,$T1.2d	// h1 -> h2
+
+	add	$ACC0,$ACC0,$T0.2d
+	shl	$T0.2d,$T0.2d,#2
+	 ushr	$T1.2d,$ACC2,#26
+	 and	$ACC2,$ACC2,$MASK.2d
+	add	$ACC0,$ACC0,$T0.2d	// h4 -> h0
+	 add	$ACC3,$ACC3,$T1.2d	// h2 -> h3
+
+	ushr	$T0.2d,$ACC0,#26
+	and	$ACC0,$ACC0,$MASK.2d
+	 ushr	$T1.2d,$ACC3,#26
+	 and	$ACC3,$ACC3,$MASK.2d
+	add	$ACC1,$ACC1,$T0.2d	// h0 -> h1
+	 add	$ACC4,$ACC4,$T1.2d	// h3 -> h4
+
+	////////////////////////////////////////////////////////////////
+	// write the result, can be partially reduced
+
+	st4	{$ACC0,$ACC1,$ACC2,$ACC3}[0],[$ctx],#16
+	mov	x4,#1
+	st1	{$ACC4}[0],[$ctx]
+	str	x4,[$ctx,#8]		// set is_base2_26
+
+	ldr	x29,[sp],#80
+	 .inst	0xd50323bf		// autiasp
+	ret
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0
+.asciz	"Poly1305 for ARMv8, CRYPTOGAMS by \@dot-asm"
+.align	2
+#if !defined(__KERNEL__) && !defined(_WIN64)
+.comm	OPENSSL_armcap_P,4,4
+.hidden	OPENSSL_armcap_P
+#endif
+___
+
+foreach (split("\n",$code)) {
+	s/\b(shrn\s+v[0-9]+)\.[24]d/$1.2s/			or
+	s/\b(fmov\s+)v([0-9]+)[^,]*,\s*x([0-9]+)/$1d$2,x$3/	or
+	(m/\bdup\b/ and (s/\.[24]s/.2d/g or 1))			or
+	(m/\b(eor|and)/ and (s/\.[248][sdh]/.16b/g or 1))	or
+	(m/\bum(ul|la)l\b/ and (s/\.4s/.2s/g or 1))		or
+	(m/\bum(ul|la)l2\b/ and (s/\.2s/.4s/g or 1))		or
+	(m/\bst[1-4]\s+{[^}]+}\[/ and (s/\.[24]d/.s/g or 1));
+
+	s/\.[124]([sd])\[/.$1\[/;
+	s/w#x([0-9]+)/w$1/g;
+
+	print $_,"\n";
+}
+close STDOUT;
diff --git a/arch/arm64/crypto/poly1305-core.S_shipped b/arch/arm64/crypto/poly1305-core.S_shipped
new file mode 100644
index 000000000..fb2822abf
--- /dev/null
+++ b/arch/arm64/crypto/poly1305-core.S_shipped
@@ -0,0 +1,835 @@
+#ifndef __KERNEL__
+# include "arm_arch.h"
+.extern	OPENSSL_armcap_P
+#endif
+
+.text
+
+// forward "declarations" are required for Apple
+.globl	poly1305_blocks
+.globl	poly1305_emit
+
+.globl	poly1305_init
+.type	poly1305_init,%function
+.align	5
+poly1305_init:
+	cmp	x1,xzr
+	stp	xzr,xzr,[x0]		// zero hash value
+	stp	xzr,xzr,[x0,#16]	// [along with is_base2_26]
+
+	csel	x0,xzr,x0,eq
+	b.eq	.Lno_key
+
+#ifndef	__KERNEL__
+	adrp	x17,OPENSSL_armcap_P
+	ldr	w17,[x17,#:lo12:OPENSSL_armcap_P]
+#endif
+
+	ldp	x7,x8,[x1]		// load key
+	mov	x9,#0xfffffffc0fffffff
+	movk	x9,#0x0fff,lsl#48
+#ifdef	__AARCH64EB__
+	rev	x7,x7			// flip bytes
+	rev	x8,x8
+#endif
+	and	x7,x7,x9		// &=0ffffffc0fffffff
+	and	x9,x9,#-4
+	and	x8,x8,x9		// &=0ffffffc0ffffffc
+	mov	w9,#-1
+	stp	x7,x8,[x0,#32]	// save key value
+	str	w9,[x0,#48]	// impossible key power value
+
+#ifndef	__KERNEL__
+	tst	w17,#ARMV7_NEON
+
+	adr	x12,.Lpoly1305_blocks
+	adr	x7,.Lpoly1305_blocks_neon
+	adr	x13,.Lpoly1305_emit
+
+	csel	x12,x12,x7,eq
+
+# ifdef	__ILP32__
+	stp	w12,w13,[x2]
+# else
+	stp	x12,x13,[x2]
+# endif
+#endif
+	mov	x0,#1
+.Lno_key:
+	ret
+.size	poly1305_init,.-poly1305_init
+
+.type	poly1305_blocks,%function
+.align	5
+poly1305_blocks:
+.Lpoly1305_blocks:
+	ands	x2,x2,#-16
+	b.eq	.Lno_data
+
+	ldp	x4,x5,[x0]		// load hash value
+	ldp	x6,x17,[x0,#16]	// [along with is_base2_26]
+	ldp	x7,x8,[x0,#32]	// load key value
+
+#ifdef	__AARCH64EB__
+	lsr	x12,x4,#32
+	mov	w13,w4
+	lsr	x14,x5,#32
+	mov	w15,w5
+	lsr	x16,x6,#32
+#else
+	mov	w12,w4
+	lsr	x13,x4,#32
+	mov	w14,w5
+	lsr	x15,x5,#32
+	mov	w16,w6
+#endif
+
+	add	x12,x12,x13,lsl#26	// base 2^26 -> base 2^64
+	lsr	x13,x14,#12
+	adds	x12,x12,x14,lsl#52
+	add	x13,x13,x15,lsl#14
+	adc	x13,x13,xzr
+	lsr	x14,x16,#24
+	adds	x13,x13,x16,lsl#40
+	adc	x14,x14,xzr
+
+	cmp	x17,#0			// is_base2_26?
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+	csel	x4,x4,x12,eq		// choose between radixes
+	csel	x5,x5,x13,eq
+	csel	x6,x6,x14,eq
+
+.Loop:
+	ldp	x10,x11,[x1],#16	// load input
+	sub	x2,x2,#16
+#ifdef	__AARCH64EB__
+	rev	x10,x10
+	rev	x11,x11
+#endif
+	adds	x4,x4,x10		// accumulate input
+	adcs	x5,x5,x11
+
+	mul	x12,x4,x7		// h0*r0
+	adc	x6,x6,x3
+	umulh	x13,x4,x7
+
+	mul	x10,x5,x9		// h1*5*r1
+	umulh	x11,x5,x9
+
+	adds	x12,x12,x10
+	mul	x10,x4,x8		// h0*r1
+	adc	x13,x13,x11
+	umulh	x14,x4,x8
+
+	adds	x13,x13,x10
+	mul	x10,x5,x7		// h1*r0
+	adc	x14,x14,xzr
+	umulh	x11,x5,x7
+
+	adds	x13,x13,x10
+	mul	x10,x6,x9		// h2*5*r1
+	adc	x14,x14,x11
+	mul	x11,x6,x7		// h2*r0
+
+	adds	x13,x13,x10
+	adc	x14,x14,x11
+
+	and	x10,x14,#-4		// final reduction
+	and	x6,x14,#3
+	add	x10,x10,x14,lsr#2
+	adds	x4,x12,x10
+	adcs	x5,x13,xzr
+	adc	x6,x6,xzr
+
+	cbnz	x2,.Loop
+
+	stp	x4,x5,[x0]		// store hash value
+	stp	x6,xzr,[x0,#16]	// [and clear is_base2_26]
+
+.Lno_data:
+	ret
+.size	poly1305_blocks,.-poly1305_blocks
+
+.type	poly1305_emit,%function
+.align	5
+poly1305_emit:
+.Lpoly1305_emit:
+	ldp	x4,x5,[x0]		// load hash base 2^64
+	ldp	x6,x7,[x0,#16]	// [along with is_base2_26]
+	ldp	x10,x11,[x2]	// load nonce
+
+#ifdef	__AARCH64EB__
+	lsr	x12,x4,#32
+	mov	w13,w4
+	lsr	x14,x5,#32
+	mov	w15,w5
+	lsr	x16,x6,#32
+#else
+	mov	w12,w4
+	lsr	x13,x4,#32
+	mov	w14,w5
+	lsr	x15,x5,#32
+	mov	w16,w6
+#endif
+
+	add	x12,x12,x13,lsl#26	// base 2^26 -> base 2^64
+	lsr	x13,x14,#12
+	adds	x12,x12,x14,lsl#52
+	add	x13,x13,x15,lsl#14
+	adc	x13,x13,xzr
+	lsr	x14,x16,#24
+	adds	x13,x13,x16,lsl#40
+	adc	x14,x14,xzr
+
+	cmp	x7,#0			// is_base2_26?
+	csel	x4,x4,x12,eq		// choose between radixes
+	csel	x5,x5,x13,eq
+	csel	x6,x6,x14,eq
+
+	adds	x12,x4,#5		// compare to modulus
+	adcs	x13,x5,xzr
+	adc	x14,x6,xzr
+
+	tst	x14,#-4			// see if it's carried/borrowed
+
+	csel	x4,x4,x12,eq
+	csel	x5,x5,x13,eq
+
+#ifdef	__AARCH64EB__
+	ror	x10,x10,#32		// flip nonce words
+	ror	x11,x11,#32
+#endif
+	adds	x4,x4,x10		// accumulate nonce
+	adc	x5,x5,x11
+#ifdef	__AARCH64EB__
+	rev	x4,x4			// flip output bytes
+	rev	x5,x5
+#endif
+	stp	x4,x5,[x1]		// write result
+
+	ret
+.size	poly1305_emit,.-poly1305_emit
+.type	poly1305_mult,%function
+.align	5
+poly1305_mult:
+	mul	x12,x4,x7		// h0*r0
+	umulh	x13,x4,x7
+
+	mul	x10,x5,x9		// h1*5*r1
+	umulh	x11,x5,x9
+
+	adds	x12,x12,x10
+	mul	x10,x4,x8		// h0*r1
+	adc	x13,x13,x11
+	umulh	x14,x4,x8
+
+	adds	x13,x13,x10
+	mul	x10,x5,x7		// h1*r0
+	adc	x14,x14,xzr
+	umulh	x11,x5,x7
+
+	adds	x13,x13,x10
+	mul	x10,x6,x9		// h2*5*r1
+	adc	x14,x14,x11
+	mul	x11,x6,x7		// h2*r0
+
+	adds	x13,x13,x10
+	adc	x14,x14,x11
+
+	and	x10,x14,#-4		// final reduction
+	and	x6,x14,#3
+	add	x10,x10,x14,lsr#2
+	adds	x4,x12,x10
+	adcs	x5,x13,xzr
+	adc	x6,x6,xzr
+
+	ret
+.size	poly1305_mult,.-poly1305_mult
+
+.type	poly1305_splat,%function
+.align	4
+poly1305_splat:
+	and	x12,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x13,x4,#26,#26
+	extr	x14,x5,x4,#52
+	and	x14,x14,#0x03ffffff
+	ubfx	x15,x5,#14,#26
+	extr	x16,x6,x5,#40
+
+	str	w12,[x0,#16*0]	// r0
+	add	w12,w13,w13,lsl#2	// r1*5
+	str	w13,[x0,#16*1]	// r1
+	add	w13,w14,w14,lsl#2	// r2*5
+	str	w12,[x0,#16*2]	// s1
+	str	w14,[x0,#16*3]	// r2
+	add	w14,w15,w15,lsl#2	// r3*5
+	str	w13,[x0,#16*4]	// s2
+	str	w15,[x0,#16*5]	// r3
+	add	w15,w16,w16,lsl#2	// r4*5
+	str	w14,[x0,#16*6]	// s3
+	str	w16,[x0,#16*7]	// r4
+	str	w15,[x0,#16*8]	// s4
+
+	ret
+.size	poly1305_splat,.-poly1305_splat
+
+#ifdef	__KERNEL__
+.globl	poly1305_blocks_neon
+#endif
+.type	poly1305_blocks_neon,%function
+.align	5
+poly1305_blocks_neon:
+.Lpoly1305_blocks_neon:
+	ldr	x17,[x0,#24]
+	cmp	x2,#128
+	b.lo	.Lpoly1305_blocks
+
+	.inst	0xd503233f		// paciasp
+	stp	x29,x30,[sp,#-80]!
+	add	x29,sp,#0
+
+	stp	d8,d9,[sp,#16]		// meet ABI requirements
+	stp	d10,d11,[sp,#32]
+	stp	d12,d13,[sp,#48]
+	stp	d14,d15,[sp,#64]
+
+	cbz	x17,.Lbase2_64_neon
+
+	ldp	w10,w11,[x0]		// load hash value base 2^26
+	ldp	w12,w13,[x0,#8]
+	ldr	w14,[x0,#16]
+
+	tst	x2,#31
+	b.eq	.Leven_neon
+
+	ldp	x7,x8,[x0,#32]	// load key value
+
+	add	x4,x10,x11,lsl#26	// base 2^26 -> base 2^64
+	lsr	x5,x12,#12
+	adds	x4,x4,x12,lsl#52
+	add	x5,x5,x13,lsl#14
+	adc	x5,x5,xzr
+	lsr	x6,x14,#24
+	adds	x5,x5,x14,lsl#40
+	adc	x14,x6,xzr		// can be partially reduced...
+
+	ldp	x12,x13,[x1],#16	// load input
+	sub	x2,x2,#16
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+
+#ifdef	__AARCH64EB__
+	rev	x12,x12
+	rev	x13,x13
+#endif
+	adds	x4,x4,x12		// accumulate input
+	adcs	x5,x5,x13
+	adc	x6,x6,x3
+
+	bl	poly1305_mult
+
+	and	x10,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,x4,#26,#26
+	extr	x12,x5,x4,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,x5,#14,#26
+	extr	x14,x6,x5,#40
+
+	b	.Leven_neon
+
+.align	4
+.Lbase2_64_neon:
+	ldp	x7,x8,[x0,#32]	// load key value
+
+	ldp	x4,x5,[x0]		// load hash value base 2^64
+	ldr	x6,[x0,#16]
+
+	tst	x2,#31
+	b.eq	.Linit_neon
+
+	ldp	x12,x13,[x1],#16	// load input
+	sub	x2,x2,#16
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+#ifdef	__AARCH64EB__
+	rev	x12,x12
+	rev	x13,x13
+#endif
+	adds	x4,x4,x12		// accumulate input
+	adcs	x5,x5,x13
+	adc	x6,x6,x3
+
+	bl	poly1305_mult
+
+.Linit_neon:
+	ldr	w17,[x0,#48]		// first table element
+	and	x10,x4,#0x03ffffff	// base 2^64 -> base 2^26
+	ubfx	x11,x4,#26,#26
+	extr	x12,x5,x4,#52
+	and	x12,x12,#0x03ffffff
+	ubfx	x13,x5,#14,#26
+	extr	x14,x6,x5,#40
+
+	cmp	w17,#-1			// is value impossible?
+	b.ne	.Leven_neon
+
+	fmov	d24,x10
+	fmov	d25,x11
+	fmov	d26,x12
+	fmov	d27,x13
+	fmov	d28,x14
+
+	////////////////////////////////// initialize r^n table
+	mov	x4,x7			// r^1
+	add	x9,x8,x8,lsr#2	// s1 = r1 + (r1 >> 2)
+	mov	x5,x8
+	mov	x6,xzr
+	add	x0,x0,#48+12
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^2
+	sub	x0,x0,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^3
+	sub	x0,x0,#4
+	bl	poly1305_splat
+
+	bl	poly1305_mult		// r^4
+	sub	x0,x0,#4
+	bl	poly1305_splat
+	sub	x0,x0,#48		// restore original x0
+	b	.Ldo_neon
+
+.align	4
+.Leven_neon:
+	fmov	d24,x10
+	fmov	d25,x11
+	fmov	d26,x12
+	fmov	d27,x13
+	fmov	d28,x14
+
+.Ldo_neon:
+	ldp	x8,x12,[x1,#32]	// inp[2:3]
+	subs	x2,x2,#64
+	ldp	x9,x13,[x1,#48]
+	add	x16,x1,#96
+	adr	x17,.Lzeros
+
+	lsl	x3,x3,#24
+	add	x15,x0,#48
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	d14,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,x3,x12,lsr#40
+	add	x13,x3,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	d15,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	fmov	d16,x8
+	fmov	d17,x10
+	fmov	d18,x12
+
+	ldp	x8,x12,[x1],#16	// inp[0:1]
+	ldp	x9,x13,[x1],#48
+
+	ld1	{v0.4s,v1.4s,v2.4s,v3.4s},[x15],#64
+	ld1	{v4.4s,v5.4s,v6.4s,v7.4s},[x15],#64
+	ld1	{v8.4s},[x15]
+
+#ifdef	__AARCH64EB__
+	rev	x8,x8
+	rev	x12,x12
+	rev	x9,x9
+	rev	x13,x13
+#endif
+	and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	and	x5,x9,#0x03ffffff
+	ubfx	x6,x8,#26,#26
+	ubfx	x7,x9,#26,#26
+	add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	extr	x8,x12,x8,#52
+	extr	x9,x13,x9,#52
+	add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	fmov	d9,x4
+	and	x8,x8,#0x03ffffff
+	and	x9,x9,#0x03ffffff
+	ubfx	x10,x12,#14,#26
+	ubfx	x11,x13,#14,#26
+	add	x12,x3,x12,lsr#40
+	add	x13,x3,x13,lsr#40
+	add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	fmov	d10,x6
+	add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	movi	v31.2d,#-1
+	fmov	d11,x8
+	fmov	d12,x10
+	fmov	d13,x12
+	ushr	v31.2d,v31.2d,#38
+
+	b.ls	.Lskip_loop
+
+.align	4
+.Loop_neon:
+	////////////////////////////////////////////////////////////////
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
+	//   ___________________/
+	// ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
+	// ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
+	//   ___________________/ ____________________/
+	//
+	// Note that we start with inp[2:3]*r^2. This is because it
+	// doesn't depend on reduction in previous iteration.
+	////////////////////////////////////////////////////////////////
+	// d4 = h0*r4 + h1*r3   + h2*r2   + h3*r1   + h4*r0
+	// d3 = h0*r3 + h1*r2   + h2*r1   + h3*r0   + h4*5*r4
+	// d2 = h0*r2 + h1*r1   + h2*r0   + h3*5*r4 + h4*5*r3
+	// d1 = h0*r1 + h1*r0   + h2*5*r4 + h3*5*r3 + h4*5*r2
+	// d0 = h0*r0 + h1*5*r4 + h2*5*r3 + h3*5*r2 + h4*5*r1
+
+	subs	x2,x2,#64
+	umull	v23.2d,v14.2s,v7.s[2]
+	csel	x16,x17,x16,lo
+	umull	v22.2d,v14.2s,v5.s[2]
+	umull	v21.2d,v14.2s,v3.s[2]
+	 ldp	x8,x12,[x16],#16	// inp[2:3] (or zero)
+	umull	v20.2d,v14.2s,v1.s[2]
+	 ldp	x9,x13,[x16],#48
+	umull	v19.2d,v14.2s,v0.s[2]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	umlal	v23.2d,v15.2s,v5.s[2]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	v22.2d,v15.2s,v3.s[2]
+	 and	x5,x9,#0x03ffffff
+	umlal	v21.2d,v15.2s,v1.s[2]
+	 ubfx	x6,x8,#26,#26
+	umlal	v20.2d,v15.2s,v0.s[2]
+	 ubfx	x7,x9,#26,#26
+	umlal	v19.2d,v15.2s,v8.s[2]
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+
+	umlal	v23.2d,v16.2s,v3.s[2]
+	 extr	x8,x12,x8,#52
+	umlal	v22.2d,v16.2s,v1.s[2]
+	 extr	x9,x13,x9,#52
+	umlal	v21.2d,v16.2s,v0.s[2]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	v20.2d,v16.2s,v8.s[2]
+	 fmov	d14,x4
+	umlal	v19.2d,v16.2s,v6.s[2]
+	 and	x8,x8,#0x03ffffff
+
+	umlal	v23.2d,v17.2s,v1.s[2]
+	 and	x9,x9,#0x03ffffff
+	umlal	v22.2d,v17.2s,v0.s[2]
+	 ubfx	x10,x12,#14,#26
+	umlal	v21.2d,v17.2s,v8.s[2]
+	 ubfx	x11,x13,#14,#26
+	umlal	v20.2d,v17.2s,v6.s[2]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	v19.2d,v17.2s,v4.s[2]
+	 fmov	d15,x6
+
+	add	v11.2s,v11.2s,v26.2s
+	 add	x12,x3,x12,lsr#40
+	umlal	v23.2d,v18.2s,v0.s[2]
+	 add	x13,x3,x13,lsr#40
+	umlal	v22.2d,v18.2s,v8.s[2]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	v21.2d,v18.2s,v6.s[2]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	v20.2d,v18.2s,v4.s[2]
+	 fmov	d16,x8
+	umlal	v19.2d,v18.2s,v2.s[2]
+	 fmov	d17,x10
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4 and accumulate
+
+	add	v9.2s,v9.2s,v24.2s
+	 fmov	d18,x12
+	umlal	v22.2d,v11.2s,v1.s[0]
+	 ldp	x8,x12,[x1],#16	// inp[0:1]
+	umlal	v19.2d,v11.2s,v6.s[0]
+	 ldp	x9,x13,[x1],#48
+	umlal	v23.2d,v11.2s,v3.s[0]
+	umlal	v20.2d,v11.2s,v8.s[0]
+	umlal	v21.2d,v11.2s,v0.s[0]
+#ifdef	__AARCH64EB__
+	 rev	x8,x8
+	 rev	x12,x12
+	 rev	x9,x9
+	 rev	x13,x13
+#endif
+
+	add	v10.2s,v10.2s,v25.2s
+	umlal	v22.2d,v9.2s,v5.s[0]
+	umlal	v23.2d,v9.2s,v7.s[0]
+	 and	x4,x8,#0x03ffffff	// base 2^64 -> base 2^26
+	umlal	v21.2d,v9.2s,v3.s[0]
+	 and	x5,x9,#0x03ffffff
+	umlal	v19.2d,v9.2s,v0.s[0]
+	 ubfx	x6,x8,#26,#26
+	umlal	v20.2d,v9.2s,v1.s[0]
+	 ubfx	x7,x9,#26,#26
+
+	add	v12.2s,v12.2s,v27.2s
+	 add	x4,x4,x5,lsl#32		// bfi	x4,x5,#32,#32
+	umlal	v22.2d,v10.2s,v3.s[0]
+	 extr	x8,x12,x8,#52
+	umlal	v23.2d,v10.2s,v5.s[0]
+	 extr	x9,x13,x9,#52
+	umlal	v19.2d,v10.2s,v8.s[0]
+	 add	x6,x6,x7,lsl#32		// bfi	x6,x7,#32,#32
+	umlal	v21.2d,v10.2s,v1.s[0]
+	 fmov	d9,x4
+	umlal	v20.2d,v10.2s,v0.s[0]
+	 and	x8,x8,#0x03ffffff
+
+	add	v13.2s,v13.2s,v28.2s
+	 and	x9,x9,#0x03ffffff
+	umlal	v22.2d,v12.2s,v0.s[0]
+	 ubfx	x10,x12,#14,#26
+	umlal	v19.2d,v12.2s,v4.s[0]
+	 ubfx	x11,x13,#14,#26
+	umlal	v23.2d,v12.2s,v1.s[0]
+	 add	x8,x8,x9,lsl#32		// bfi	x8,x9,#32,#32
+	umlal	v20.2d,v12.2s,v6.s[0]
+	 fmov	d10,x6
+	umlal	v21.2d,v12.2s,v8.s[0]
+	 add	x12,x3,x12,lsr#40
+
+	umlal	v22.2d,v13.2s,v8.s[0]
+	 add	x13,x3,x13,lsr#40
+	umlal	v19.2d,v13.2s,v2.s[0]
+	 add	x10,x10,x11,lsl#32	// bfi	x10,x11,#32,#32
+	umlal	v23.2d,v13.2s,v0.s[0]
+	 add	x12,x12,x13,lsl#32	// bfi	x12,x13,#32,#32
+	umlal	v20.2d,v13.2s,v4.s[0]
+	 fmov	d11,x8
+	umlal	v21.2d,v13.2s,v6.s[0]
+	 fmov	d12,x10
+	 fmov	d13,x12
+
+	/////////////////////////////////////////////////////////////////
+	// lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
+	// and P. Schwabe
+	//
+	// [see discussion in poly1305-armv4 module]
+
+	ushr	v29.2d,v22.2d,#26
+	xtn	v27.2s,v22.2d
+	 ushr	v30.2d,v19.2d,#26
+	 and	v19.16b,v19.16b,v31.16b
+	add	v23.2d,v23.2d,v29.2d	// h3 -> h4
+	bic	v27.2s,#0xfc,lsl#24	// &=0x03ffffff
+	 add	v20.2d,v20.2d,v30.2d	// h0 -> h1
+
+	ushr	v29.2d,v23.2d,#26
+	xtn	v28.2s,v23.2d
+	 ushr	v30.2d,v20.2d,#26
+	 xtn	v25.2s,v20.2d
+	bic	v28.2s,#0xfc,lsl#24
+	 add	v21.2d,v21.2d,v30.2d	// h1 -> h2
+
+	add	v19.2d,v19.2d,v29.2d
+	shl	v29.2d,v29.2d,#2
+	 shrn	v30.2s,v21.2d,#26
+	 xtn	v26.2s,v21.2d
+	add	v19.2d,v19.2d,v29.2d	// h4 -> h0
+	 bic	v25.2s,#0xfc,lsl#24
+	 add	v27.2s,v27.2s,v30.2s		// h2 -> h3
+	 bic	v26.2s,#0xfc,lsl#24
+
+	shrn	v29.2s,v19.2d,#26
+	xtn	v24.2s,v19.2d
+	 ushr	v30.2s,v27.2s,#26
+	 bic	v27.2s,#0xfc,lsl#24
+	 bic	v24.2s,#0xfc,lsl#24
+	add	v25.2s,v25.2s,v29.2s		// h0 -> h1
+	 add	v28.2s,v28.2s,v30.2s		// h3 -> h4
+
+	b.hi	.Loop_neon
+
+.Lskip_loop:
+	dup	v16.2d,v16.d[0]
+	add	v11.2s,v11.2s,v26.2s
+
+	////////////////////////////////////////////////////////////////
+	// multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
+
+	adds	x2,x2,#32
+	b.ne	.Long_tail
+
+	dup	v16.2d,v11.d[0]
+	add	v14.2s,v9.2s,v24.2s
+	add	v17.2s,v12.2s,v27.2s
+	add	v15.2s,v10.2s,v25.2s
+	add	v18.2s,v13.2s,v28.2s
+
+.Long_tail:
+	dup	v14.2d,v14.d[0]
+	umull2	v19.2d,v16.4s,v6.4s
+	umull2	v22.2d,v16.4s,v1.4s
+	umull2	v23.2d,v16.4s,v3.4s
+	umull2	v21.2d,v16.4s,v0.4s
+	umull2	v20.2d,v16.4s,v8.4s
+
+	dup	v15.2d,v15.d[0]
+	umlal2	v19.2d,v14.4s,v0.4s
+	umlal2	v21.2d,v14.4s,v3.4s
+	umlal2	v22.2d,v14.4s,v5.4s
+	umlal2	v23.2d,v14.4s,v7.4s
+	umlal2	v20.2d,v14.4s,v1.4s
+
+	dup	v17.2d,v17.d[0]
+	umlal2	v19.2d,v15.4s,v8.4s
+	umlal2	v22.2d,v15.4s,v3.4s
+	umlal2	v21.2d,v15.4s,v1.4s
+	umlal2	v23.2d,v15.4s,v5.4s
+	umlal2	v20.2d,v15.4s,v0.4s
+
+	dup	v18.2d,v18.d[0]
+	umlal2	v22.2d,v17.4s,v0.4s
+	umlal2	v23.2d,v17.4s,v1.4s
+	umlal2	v19.2d,v17.4s,v4.4s
+	umlal2	v20.2d,v17.4s,v6.4s
+	umlal2	v21.2d,v17.4s,v8.4s
+
+	umlal2	v22.2d,v18.4s,v8.4s
+	umlal2	v19.2d,v18.4s,v2.4s
+	umlal2	v23.2d,v18.4s,v0.4s
+	umlal2	v20.2d,v18.4s,v4.4s
+	umlal2	v21.2d,v18.4s,v6.4s
+
+	b.eq	.Lshort_tail
+
+	////////////////////////////////////////////////////////////////
+	// (hash+inp[0:1])*r^4:r^3 and accumulate
+
+	add	v9.2s,v9.2s,v24.2s
+	umlal	v22.2d,v11.2s,v1.2s
+	umlal	v19.2d,v11.2s,v6.2s
+	umlal	v23.2d,v11.2s,v3.2s
+	umlal	v20.2d,v11.2s,v8.2s
+	umlal	v21.2d,v11.2s,v0.2s
+
+	add	v10.2s,v10.2s,v25.2s
+	umlal	v22.2d,v9.2s,v5.2s
+	umlal	v19.2d,v9.2s,v0.2s
+	umlal	v23.2d,v9.2s,v7.2s
+	umlal	v20.2d,v9.2s,v1.2s
+	umlal	v21.2d,v9.2s,v3.2s
+
+	add	v12.2s,v12.2s,v27.2s
+	umlal	v22.2d,v10.2s,v3.2s
+	umlal	v19.2d,v10.2s,v8.2s
+	umlal	v23.2d,v10.2s,v5.2s
+	umlal	v20.2d,v10.2s,v0.2s
+	umlal	v21.2d,v10.2s,v1.2s
+
+	add	v13.2s,v13.2s,v28.2s
+	umlal	v22.2d,v12.2s,v0.2s
+	umlal	v19.2d,v12.2s,v4.2s
+	umlal	v23.2d,v12.2s,v1.2s
+	umlal	v20.2d,v12.2s,v6.2s
+	umlal	v21.2d,v12.2s,v8.2s
+
+	umlal	v22.2d,v13.2s,v8.2s
+	umlal	v19.2d,v13.2s,v2.2s
+	umlal	v23.2d,v13.2s,v0.2s
+	umlal	v20.2d,v13.2s,v4.2s
+	umlal	v21.2d,v13.2s,v6.2s
+
+.Lshort_tail:
+	////////////////////////////////////////////////////////////////
+	// horizontal add
+
+	addp	v22.2d,v22.2d,v22.2d
+	 ldp	d8,d9,[sp,#16]		// meet ABI requirements
+	addp	v19.2d,v19.2d,v19.2d
+	 ldp	d10,d11,[sp,#32]
+	addp	v23.2d,v23.2d,v23.2d
+	 ldp	d12,d13,[sp,#48]
+	addp	v20.2d,v20.2d,v20.2d
+	 ldp	d14,d15,[sp,#64]
+	addp	v21.2d,v21.2d,v21.2d
+	 ldr	x30,[sp,#8]
+
+	////////////////////////////////////////////////////////////////
+	// lazy reduction, but without narrowing
+
+	ushr	v29.2d,v22.2d,#26
+	and	v22.16b,v22.16b,v31.16b
+	 ushr	v30.2d,v19.2d,#26
+	 and	v19.16b,v19.16b,v31.16b
+
+	add	v23.2d,v23.2d,v29.2d	// h3 -> h4
+	 add	v20.2d,v20.2d,v30.2d	// h0 -> h1
+
+	ushr	v29.2d,v23.2d,#26
+	and	v23.16b,v23.16b,v31.16b
+	 ushr	v30.2d,v20.2d,#26
+	 and	v20.16b,v20.16b,v31.16b
+	 add	v21.2d,v21.2d,v30.2d	// h1 -> h2
+
+	add	v19.2d,v19.2d,v29.2d
+	shl	v29.2d,v29.2d,#2
+	 ushr	v30.2d,v21.2d,#26
+	 and	v21.16b,v21.16b,v31.16b
+	add	v19.2d,v19.2d,v29.2d	// h4 -> h0
+	 add	v22.2d,v22.2d,v30.2d	// h2 -> h3
+
+	ushr	v29.2d,v19.2d,#26
+	and	v19.16b,v19.16b,v31.16b
+	 ushr	v30.2d,v22.2d,#26
+	 and	v22.16b,v22.16b,v31.16b
+	add	v20.2d,v20.2d,v29.2d	// h0 -> h1
+	 add	v23.2d,v23.2d,v30.2d	// h3 -> h4
+
+	////////////////////////////////////////////////////////////////
+	// write the result, can be partially reduced
+
+	st4	{v19.s,v20.s,v21.s,v22.s}[0],[x0],#16
+	mov	x4,#1
+	st1	{v23.s}[0],[x0]
+	str	x4,[x0,#8]		// set is_base2_26
+
+	ldr	x29,[sp],#80
+	 .inst	0xd50323bf		// autiasp
+	ret
+.size	poly1305_blocks_neon,.-poly1305_blocks_neon
+
+.align	5
+.Lzeros:
+.long	0,0,0,0,0,0,0,0
+.asciz	"Poly1305 for ARMv8, CRYPTOGAMS by @dot-asm"
+.align	2
+#if !defined(__KERNEL__) && !defined(_WIN64)
+.comm	OPENSSL_armcap_P,4,4
+.hidden	OPENSSL_armcap_P
+#endif
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
new file mode 100644
index 000000000..9f4599014
--- /dev/null
+++ b/arch/arm64/crypto/poly1305-glue.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/algapi.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/poly1305.h>
+#include <crypto/internal/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/jump_label.h>
+#include <linux/module.h>
+
+asmlinkage void poly1305_init_arm64(void *state, const u8 *key);
+asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
+{
+	poly1305_init_arm64(&dctx->h, key);
+	dctx->s[0] = get_unaligned_le32(key + 16);
+	dctx->s[1] = get_unaligned_le32(key + 20);
+	dctx->s[2] = get_unaligned_le32(key + 24);
+	dctx->s[3] = get_unaligned_le32(key + 28);
+	dctx->buflen = 0;
+}
+EXPORT_SYMBOL(poly1305_init_arch);
+
+static int neon_poly1305_init(struct shash_desc *desc)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	dctx->buflen = 0;
+	dctx->rset = 0;
+	dctx->sset = false;
+
+	return 0;
+}
+
+static void neon_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
+				 u32 len, u32 hibit, bool do_neon)
+{
+	if (unlikely(!dctx->sset)) {
+		if (!dctx->rset) {
+			poly1305_init_arm64(&dctx->h, src);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->rset = 1;
+		}
+		if (len >= POLY1305_BLOCK_SIZE) {
+			dctx->s[0] = get_unaligned_le32(src +  0);
+			dctx->s[1] = get_unaligned_le32(src +  4);
+			dctx->s[2] = get_unaligned_le32(src +  8);
+			dctx->s[3] = get_unaligned_le32(src + 12);
+			src += POLY1305_BLOCK_SIZE;
+			len -= POLY1305_BLOCK_SIZE;
+			dctx->sset = true;
+		}
+		if (len < POLY1305_BLOCK_SIZE)
+			return;
+	}
+
+	len &= ~(POLY1305_BLOCK_SIZE - 1);
+
+	if (static_branch_likely(&have_neon) && likely(do_neon))
+		poly1305_blocks_neon(&dctx->h, src, len, hibit);
+	else
+		poly1305_blocks(&dctx->h, src, len, hibit);
+}
+
+static void neon_poly1305_do_update(struct poly1305_desc_ctx *dctx,
+				    const u8 *src, u32 len, bool do_neon)
+{
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		len -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			neon_poly1305_blocks(dctx, dctx->buf,
+					     POLY1305_BLOCK_SIZE, 1, false);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(len >= POLY1305_BLOCK_SIZE)) {
+		neon_poly1305_blocks(dctx, src, len, 1, do_neon);
+		src += round_down(len, POLY1305_BLOCK_SIZE);
+		len %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(len)) {
+		dctx->buflen = len;
+		memcpy(dctx->buf, src, len);
+	}
+}
+
+static int neon_poly1305_update(struct shash_desc *desc,
+				const u8 *src, unsigned int srclen)
+{
+	bool do_neon = crypto_simd_usable() && srclen > 128;
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (static_branch_likely(&have_neon) && do_neon)
+		kernel_neon_begin();
+	neon_poly1305_do_update(dctx, src, srclen, do_neon);
+	if (static_branch_likely(&have_neon) && do_neon)
+		kernel_neon_end();
+	return 0;
+}
+
+void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
+			  unsigned int nbytes)
+{
+	if (unlikely(dctx->buflen)) {
+		u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
+
+		memcpy(dctx->buf + dctx->buflen, src, bytes);
+		src += bytes;
+		nbytes -= bytes;
+		dctx->buflen += bytes;
+
+		if (dctx->buflen == POLY1305_BLOCK_SIZE) {
+			poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1);
+			dctx->buflen = 0;
+		}
+	}
+
+	if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
+		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
+
+		if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
+			do {
+				unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+				kernel_neon_begin();
+				poly1305_blocks_neon(&dctx->h, src, todo, 1);
+				kernel_neon_end();
+
+				len -= todo;
+				src += todo;
+			} while (len);
+		} else {
+			poly1305_blocks(&dctx->h, src, len, 1);
+			src += len;
+		}
+		nbytes %= POLY1305_BLOCK_SIZE;
+	}
+
+	if (unlikely(nbytes)) {
+		dctx->buflen = nbytes;
+		memcpy(dctx->buf, src, nbytes);
+	}
+}
+EXPORT_SYMBOL(poly1305_update_arch);
+
+void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
+{
+	if (unlikely(dctx->buflen)) {
+		dctx->buf[dctx->buflen++] = 1;
+		memset(dctx->buf + dctx->buflen, 0,
+		       POLY1305_BLOCK_SIZE - dctx->buflen);
+		poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
+	}
+
+	poly1305_emit(&dctx->h, dst, dctx->s);
+	*dctx = (struct poly1305_desc_ctx){};
+}
+EXPORT_SYMBOL(poly1305_final_arch);
+
+static int neon_poly1305_final(struct shash_desc *desc, u8 *dst)
+{
+	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	if (unlikely(!dctx->sset))
+		return -ENOKEY;
+
+	poly1305_final_arch(dctx, dst);
+	return 0;
+}
+
+static struct shash_alg neon_poly1305_alg = {
+	.init			= neon_poly1305_init,
+	.update			= neon_poly1305_update,
+	.final			= neon_poly1305_final,
+	.digestsize		= POLY1305_DIGEST_SIZE,
+	.descsize		= sizeof(struct poly1305_desc_ctx),
+
+	.base.cra_name		= "poly1305",
+	.base.cra_driver_name	= "poly1305-neon",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= POLY1305_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+};
+
+static int __init neon_poly1305_mod_init(void)
+{
+	if (!cpu_have_named_feature(ASIMD))
+		return 0;
+
+	static_branch_enable(&have_neon);
+
+	return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
+		crypto_register_shash(&neon_poly1305_alg) : 0;
+}
+
+static void __exit neon_poly1305_mod_exit(void)
+{
+	if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && cpu_have_named_feature(ASIMD))
+		crypto_unregister_shash(&neon_poly1305_alg);
+}
+
+module_init(neon_poly1305_mod_init);
+module_exit(neon_poly1305_mod_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("poly1305");
+MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
new file mode 100644
index 000000000..92d0d2753
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -0,0 +1,163 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * sha1-ce-core.S - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	k0		.req	v0
+	k1		.req	v1
+	k2		.req	v2
+	k3		.req	v3
+
+	t0		.req	v4
+	t1		.req	v5
+
+	dga		.req	q6
+	dgav		.req	v6
+	dgb		.req	s7
+	dgbv		.req	v7
+
+	dg0q		.req	q12
+	dg0s		.req	s12
+	dg0v		.req	v12
+	dg1s		.req	s13
+	dg1v		.req	v13
+	dg2s		.req	s14
+
+	.macro		add_only, op, ev, rc, s0, dg1
+	.ifc		\ev, ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha1h		dg2s, dg0s
+	.ifnb		\dg1
+	sha1\op		dg0q, \dg1, t0.4s
+	.else
+	sha1\op		dg0q, dg1s, t0.4s
+	.endif
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha1h		dg1s, dg0s
+	sha1\op		dg0q, dg2s, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, op, ev, rc, s0, s1, s2, s3, dg1
+	sha1su0		v\s0\().4s, v\s1\().4s, v\s2\().4s
+	add_only	\op, \ev, \rc, \s1, \dg1
+	sha1su1		v\s0\().4s, v\s3\().4s
+	.endm
+
+	.macro		loadrc, k, val, tmp
+	movz		\tmp, :abs_g0_nc:\val
+	movk		\tmp, :abs_g1:\val
+	dup		\k, \tmp
+	.endm
+
+	/*
+	 * void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
+	 *			  int blocks)
+	 */
+SYM_FUNC_START(sha1_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
+	/* load round constants */
+0:	loadrc		k0.4s, 0x5a827999, w6
+	loadrc		k1.4s, 0x6ed9eba1, w6
+	loadrc		k2.4s, 0x8f1bbcdc, w6
+	loadrc		k3.4s, 0xca62c1d6, w6
+
+	/* load state */
+	ld1		{dgav.4s}, [x19]
+	ldr		dgb, [x19, #16]
+
+	/* load sha1_ce_state::finalize */
+	ldr_l		w4, sha1_ce_offsetof_finalize, x4
+	ldr		w4, [x19, x4]
+
+	/* load input */
+1:	ld1		{v8.4s-v11.4s}, [x20], #64
+	sub		w21, w21, #1
+
+CPU_LE(	rev32		v8.16b, v8.16b		)
+CPU_LE(	rev32		v9.16b, v9.16b		)
+CPU_LE(	rev32		v10.16b, v10.16b	)
+CPU_LE(	rev32		v11.16b, v11.16b	)
+
+2:	add		t0.4s, v8.4s, k0.4s
+	mov		dg0v.16b, dgav.16b
+
+	add_update	c, ev, k0,  8,  9, 10, 11, dgb
+	add_update	c, od, k0,  9, 10, 11,  8
+	add_update	c, ev, k0, 10, 11,  8,  9
+	add_update	c, od, k0, 11,  8,  9, 10
+	add_update	c, ev, k1,  8,  9, 10, 11
+
+	add_update	p, od, k1,  9, 10, 11,  8
+	add_update	p, ev, k1, 10, 11,  8,  9
+	add_update	p, od, k1, 11,  8,  9, 10
+	add_update	p, ev, k1,  8,  9, 10, 11
+	add_update	p, od, k2,  9, 10, 11,  8
+
+	add_update	m, ev, k2, 10, 11,  8,  9
+	add_update	m, od, k2, 11,  8,  9, 10
+	add_update	m, ev, k2,  8,  9, 10, 11
+	add_update	m, od, k2,  9, 10, 11,  8
+	add_update	m, ev, k3, 10, 11,  8,  9
+
+	add_update	p, od, k3, 11,  8,  9, 10
+	add_only	p, ev, k3,  9
+	add_only	p, od, k3, 10
+	add_only	p, ev, k3, 11
+	add_only	p, od
+
+	/* update state */
+	add		dgbv.2s, dgbv.2s, dg1v.2s
+	add		dgav.4s, dgav.4s, dg0v.4s
+
+	cbz		w21, 3f
+
+	if_will_cond_yield_neon
+	st1		{dgav.4s}, [x19]
+	str		dgb, [x19, #16]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b		1b
+
+	/*
+	 * Final block: add padding and total bit count.
+	 * Skip if the input size was not a round multiple of the block size,
+	 * the padding is handled by the C code in that case.
+	 */
+3:	cbz		x4, 4f
+	ldr_l		w4, sha1_ce_offsetof_count, x4
+	ldr		x4, [x19, x4]
+	movi		v9.2d, #0
+	mov		x8, #0x80000000
+	movi		v10.2d, #0
+	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
+	fmov		d8, x8
+	mov		x4, #0
+	mov		v11.d[0], xzr
+	mov		v11.d[1], x7
+	b		2b
+
+	/* store new state */
+4:	st1		{dgav.4s}, [x19]
+	str		dgb, [x19, #16]
+	frame_pop
+	ret
+SYM_FUNC_END(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
new file mode 100644
index 000000000..8baf8d184
--- /dev/null
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sha.h>
+#include <crypto/sha1_base.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha1");
+
+struct sha1_ce_state {
+	struct sha1_state	sst;
+	u32			finalize;
+};
+
+extern const u32 sha1_ce_offsetof_count;
+extern const u32 sha1_ce_offsetof_finalize;
+
+asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
+				  int blocks);
+
+static void __sha1_ce_transform(struct sha1_state *sst, u8 const *src,
+				int blocks)
+{
+	sha1_ce_transform(container_of(sst, struct sha1_ce_state, sst), src,
+			  blocks);
+}
+
+const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count);
+const u32 sha1_ce_offsetof_finalize = offsetof(struct sha1_ce_state, finalize);
+
+static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
+			  unsigned int len)
+{
+	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+
+	if (!crypto_simd_usable())
+		return crypto_sha1_update(desc, data, len);
+
+	sctx->finalize = 0;
+	kernel_neon_begin();
+	sha1_base_do_update(desc, data, len, __sha1_ce_transform);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
+			 unsigned int len, u8 *out)
+{
+	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+	bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE) && len;
+
+	if (!crypto_simd_usable())
+		return crypto_sha1_finup(desc, data, len, out);
+
+	/*
+	 * Allow the asm code to perform the finalization if there is no
+	 * partial data and the input is a round multiple of the block size.
+	 */
+	sctx->finalize = finalize;
+
+	kernel_neon_begin();
+	sha1_base_do_update(desc, data, len, __sha1_ce_transform);
+	if (!finalize)
+		sha1_base_do_finalize(desc, __sha1_ce_transform);
+	kernel_neon_end();
+	return sha1_base_finish(desc, out);
+}
+
+static int sha1_ce_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+
+	if (!crypto_simd_usable())
+		return crypto_sha1_finup(desc, NULL, 0, out);
+
+	sctx->finalize = 0;
+	kernel_neon_begin();
+	sha1_base_do_finalize(desc, __sha1_ce_transform);
+	kernel_neon_end();
+	return sha1_base_finish(desc, out);
+}
+
+static int sha1_ce_export(struct shash_desc *desc, void *out)
+{
+	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(out, &sctx->sst, sizeof(struct sha1_state));
+	return 0;
+}
+
+static int sha1_ce_import(struct shash_desc *desc, const void *in)
+{
+	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(&sctx->sst, in, sizeof(struct sha1_state));
+	sctx->finalize = 0;
+	return 0;
+}
+
+static struct shash_alg alg = {
+	.init			= sha1_base_init,
+	.update			= sha1_ce_update,
+	.final			= sha1_ce_final,
+	.finup			= sha1_ce_finup,
+	.import			= sha1_ce_import,
+	.export			= sha1_ce_export,
+	.descsize		= sizeof(struct sha1_ce_state),
+	.statesize		= sizeof(struct sha1_state),
+	.digestsize		= SHA1_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha1",
+		.cra_driver_name	= "sha1-ce",
+		.cra_priority		= 200,
+		.cra_blocksize		= SHA1_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+};
+
+static int __init sha1_ce_mod_init(void)
+{
+	return crypto_register_shash(&alg);
+}
+
+static void __exit sha1_ce_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_cpu_feature_match(SHA1, sha1_ce_mod_init);
+module_exit(sha1_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
new file mode 100644
index 000000000..3f9d0f326
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * sha2-ce-core.S - core SHA-224/SHA-256 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.arch		armv8-a+crypto
+
+	dga		.req	q20
+	dgav		.req	v20
+	dgb		.req	q21
+	dgbv		.req	v21
+
+	t0		.req	v22
+	t1		.req	v23
+
+	dg0q		.req	q24
+	dg0v		.req	v24
+	dg1q		.req	q25
+	dg1v		.req	v25
+	dg2q		.req	q26
+	dg2v		.req	v26
+
+	.macro		add_only, ev, rc, s0
+	mov		dg2v.16b, dg0v.16b
+	.ifeq		\ev
+	add		t1.4s, v\s0\().4s, \rc\().4s
+	sha256h		dg0q, dg1q, t0.4s
+	sha256h2	dg1q, dg2q, t0.4s
+	.else
+	.ifnb		\s0
+	add		t0.4s, v\s0\().4s, \rc\().4s
+	.endif
+	sha256h		dg0q, dg1q, t1.4s
+	sha256h2	dg1q, dg2q, t1.4s
+	.endif
+	.endm
+
+	.macro		add_update, ev, rc, s0, s1, s2, s3
+	sha256su0	v\s0\().4s, v\s1\().4s
+	add_only	\ev, \rc, \s1
+	sha256su1	v\s0\().4s, v\s2\().4s, v\s3\().4s
+	.endm
+
+	/*
+	 * The SHA-256 round constants
+	 */
+	.section	".rodata", "a"
+	.align		4
+.Lsha2_rcon:
+	.word		0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5
+	.word		0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5
+	.word		0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3
+	.word		0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174
+	.word		0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc
+	.word		0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da
+	.word		0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7
+	.word		0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967
+	.word		0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13
+	.word		0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85
+	.word		0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3
+	.word		0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070
+	.word		0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5
+	.word		0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3
+	.word		0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208
+	.word		0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+
+	/*
+	 * void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
+	 *			  int blocks)
+	 */
+	.text
+SYM_FUNC_START(sha2_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
+	/* load round constants */
+0:	adr_l		x8, .Lsha2_rcon
+	ld1		{ v0.4s- v3.4s}, [x8], #64
+	ld1		{ v4.4s- v7.4s}, [x8], #64
+	ld1		{ v8.4s-v11.4s}, [x8], #64
+	ld1		{v12.4s-v15.4s}, [x8]
+
+	/* load state */
+	ld1		{dgav.4s, dgbv.4s}, [x19]
+
+	/* load sha256_ce_state::finalize */
+	ldr_l		w4, sha256_ce_offsetof_finalize, x4
+	ldr		w4, [x19, x4]
+
+	/* load input */
+1:	ld1		{v16.4s-v19.4s}, [x20], #64
+	sub		w21, w21, #1
+
+CPU_LE(	rev32		v16.16b, v16.16b	)
+CPU_LE(	rev32		v17.16b, v17.16b	)
+CPU_LE(	rev32		v18.16b, v18.16b	)
+CPU_LE(	rev32		v19.16b, v19.16b	)
+
+2:	add		t0.4s, v16.4s, v0.4s
+	mov		dg0v.16b, dgav.16b
+	mov		dg1v.16b, dgbv.16b
+
+	add_update	0,  v1, 16, 17, 18, 19
+	add_update	1,  v2, 17, 18, 19, 16
+	add_update	0,  v3, 18, 19, 16, 17
+	add_update	1,  v4, 19, 16, 17, 18
+
+	add_update	0,  v5, 16, 17, 18, 19
+	add_update	1,  v6, 17, 18, 19, 16
+	add_update	0,  v7, 18, 19, 16, 17
+	add_update	1,  v8, 19, 16, 17, 18
+
+	add_update	0,  v9, 16, 17, 18, 19
+	add_update	1, v10, 17, 18, 19, 16
+	add_update	0, v11, 18, 19, 16, 17
+	add_update	1, v12, 19, 16, 17, 18
+
+	add_only	0, v13, 17
+	add_only	1, v14, 18
+	add_only	0, v15, 19
+	add_only	1
+
+	/* update state */
+	add		dgav.4s, dgav.4s, dg0v.4s
+	add		dgbv.4s, dgbv.4s, dg1v.4s
+
+	/* handled all input blocks? */
+	cbz		w21, 3f
+
+	if_will_cond_yield_neon
+	st1		{dgav.4s, dgbv.4s}, [x19]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b		1b
+
+	/*
+	 * Final block: add padding and total bit count.
+	 * Skip if the input size was not a round multiple of the block size,
+	 * the padding is handled by the C code in that case.
+	 */
+3:	cbz		x4, 4f
+	ldr_l		w4, sha256_ce_offsetof_count, x4
+	ldr		x4, [x19, x4]
+	movi		v17.2d, #0
+	mov		x8, #0x80000000
+	movi		v18.2d, #0
+	ror		x7, x4, #29		// ror(lsl(x4, 3), 32)
+	fmov		d16, x8
+	mov		x4, #0
+	mov		v19.d[0], xzr
+	mov		v19.d[1], x7
+	b		2b
+
+	/* store new state */
+4:	st1		{dgav.4s, dgbv.4s}, [x19]
+	frame_pop
+	ret
+SYM_FUNC_END(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
new file mode 100644
index 000000000..d33d3ee92
--- /dev/null
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sha.h>
+#include <crypto/sha256_base.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+
+struct sha256_ce_state {
+	struct sha256_state	sst;
+	u32			finalize;
+};
+
+extern const u32 sha256_ce_offsetof_count;
+extern const u32 sha256_ce_offsetof_finalize;
+
+asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src,
+				  int blocks);
+
+static void __sha2_ce_transform(struct sha256_state *sst, u8 const *src,
+				int blocks)
+{
+	sha2_ce_transform(container_of(sst, struct sha256_ce_state, sst), src,
+			  blocks);
+}
+
+const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
+					      sst.count);
+const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
+						 finalize);
+
+asmlinkage void sha256_block_data_order(u32 *digest, u8 const *src, int blocks);
+
+static void __sha256_block_data_order(struct sha256_state *sst, u8 const *src,
+				      int blocks)
+{
+	sha256_block_data_order(sst->state, src, blocks);
+}
+
+static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
+			    unsigned int len)
+{
+	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+
+	if (!crypto_simd_usable())
+		return sha256_base_do_update(desc, data, len,
+				__sha256_block_data_order);
+
+	sctx->finalize = 0;
+	kernel_neon_begin();
+	sha256_base_do_update(desc, data, len, __sha2_ce_transform);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
+			   unsigned int len, u8 *out)
+{
+	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+	bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE) && len;
+
+	if (!crypto_simd_usable()) {
+		if (len)
+			sha256_base_do_update(desc, data, len,
+				__sha256_block_data_order);
+		sha256_base_do_finalize(desc, __sha256_block_data_order);
+		return sha256_base_finish(desc, out);
+	}
+
+	/*
+	 * Allow the asm code to perform the finalization if there is no
+	 * partial data and the input is a round multiple of the block size.
+	 */
+	sctx->finalize = finalize;
+
+	kernel_neon_begin();
+	sha256_base_do_update(desc, data, len, __sha2_ce_transform);
+	if (!finalize)
+		sha256_base_do_finalize(desc, __sha2_ce_transform);
+	kernel_neon_end();
+	return sha256_base_finish(desc, out);
+}
+
+static int sha256_ce_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+
+	if (!crypto_simd_usable()) {
+		sha256_base_do_finalize(desc, __sha256_block_data_order);
+		return sha256_base_finish(desc, out);
+	}
+
+	sctx->finalize = 0;
+	kernel_neon_begin();
+	sha256_base_do_finalize(desc, __sha2_ce_transform);
+	kernel_neon_end();
+	return sha256_base_finish(desc, out);
+}
+
+static int sha256_ce_export(struct shash_desc *desc, void *out)
+{
+	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(out, &sctx->sst, sizeof(struct sha256_state));
+	return 0;
+}
+
+static int sha256_ce_import(struct shash_desc *desc, const void *in)
+{
+	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+
+	memcpy(&sctx->sst, in, sizeof(struct sha256_state));
+	sctx->finalize = 0;
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.init			= sha224_base_init,
+	.update			= sha256_ce_update,
+	.final			= sha256_ce_final,
+	.finup			= sha256_ce_finup,
+	.export			= sha256_ce_export,
+	.import			= sha256_ce_import,
+	.descsize		= sizeof(struct sha256_ce_state),
+	.statesize		= sizeof(struct sha256_state),
+	.digestsize		= SHA224_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha224",
+		.cra_driver_name	= "sha224-ce",
+		.cra_priority		= 200,
+		.cra_blocksize		= SHA256_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+}, {
+	.init			= sha256_base_init,
+	.update			= sha256_ce_update,
+	.final			= sha256_ce_final,
+	.finup			= sha256_ce_finup,
+	.export			= sha256_ce_export,
+	.import			= sha256_ce_import,
+	.descsize		= sizeof(struct sha256_ce_state),
+	.statesize		= sizeof(struct sha256_state),
+	.digestsize		= SHA256_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha256",
+		.cra_driver_name	= "sha256-ce",
+		.cra_priority		= 200,
+		.cra_blocksize		= SHA256_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
+
+static int __init sha2_ce_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha2_ce_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA2, sha2_ce_mod_init);
+module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha256-core.S_shipped b/arch/arm64/crypto/sha256-core.S_shipped
new file mode 100644
index 000000000..7c7ce2e3b
--- /dev/null
+++ b/arch/arm64/crypto/sha256-core.S_shipped
@@ -0,0 +1,2069 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// This code is taken from the OpenSSL project but the author (Andy Polyakov)
+// has relicensed it under the GPLv2. Therefore 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.
+//
+// The original headers, including the original license headers, are
+// included below for completeness.
+
+// Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
+//
+// Licensed under the OpenSSL license (the "License").  You may not use
+// this file except in compliance with the License.  You can obtain a copy
+// in the file LICENSE in the source distribution or at
+// https://www.openssl.org/source/license.html
+
+// ====================================================================
+// Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+// project. The module is, however, dual licensed under OpenSSL and
+// CRYPTOGAMS licenses depending on where you obtain it. For further
+// details see http://www.openssl.org/~appro/cryptogams/.
+// ====================================================================
+//
+// SHA256/512 for ARMv8.
+//
+// Performance in cycles per processed byte and improvement coefficient
+// over code generated with "default" compiler:
+//
+//		SHA256-hw	SHA256(*)	SHA512
+// Apple A7	1.97		10.5 (+33%)	6.73 (-1%(**))
+// Cortex-A53	2.38		15.5 (+115%)	10.0 (+150%(***))
+// Cortex-A57	2.31		11.6 (+86%)	7.51 (+260%(***))
+// Denver	2.01		10.5 (+26%)	6.70 (+8%)
+// X-Gene			20.0 (+100%)	12.8 (+300%(***))
+// Mongoose	2.36		13.0 (+50%)	8.36 (+33%)
+//
+// (*)	Software SHA256 results are of lesser relevance, presented
+//	mostly for informational purposes.
+// (**)	The result is a trade-off: it's possible to improve it by
+//	10% (or by 1 cycle per round), but at the cost of 20% loss
+//	on Cortex-A53 (or by 4 cycles per round).
+// (***)	Super-impressive coefficients over gcc-generated code are
+//	indication of some compiler "pathology", most notably code
+//	generated with -mgeneral-regs-only is significanty faster
+//	and the gap is only 40-90%.
+//
+// October 2016.
+//
+// Originally it was reckoned that it makes no sense to implement NEON
+// version of SHA256 for 64-bit processors. This is because performance
+// improvement on most wide-spread Cortex-A5x processors was observed
+// to be marginal, same on Cortex-A53 and ~10% on A57. But then it was
+// observed that 32-bit NEON SHA256 performs significantly better than
+// 64-bit scalar version on *some* of the more recent processors. As
+// result 64-bit NEON version of SHA256 was added to provide best
+// all-round performance. For example it executes ~30% faster on X-Gene
+// and Mongoose. [For reference, NEON version of SHA512 is bound to
+// deliver much less improvement, likely *negative* on Cortex-A5x.
+// Which is why NEON support is limited to SHA256.]
+
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+#endif
+
+.text
+
+.extern	OPENSSL_armcap_P
+.globl	sha256_block_data_order
+.type	sha256_block_data_order,%function
+.align	6
+sha256_block_data_order:
+#ifndef	__KERNEL__
+# ifdef	__ILP32__
+	ldrsw	x16,.LOPENSSL_armcap_P
+# else
+	ldr	x16,.LOPENSSL_armcap_P
+# endif
+	adr	x17,.LOPENSSL_armcap_P
+	add	x16,x16,x17
+	ldr	w16,[x16]
+	tst	w16,#ARMV8_SHA256
+	b.ne	.Lv8_entry
+	tst	w16,#ARMV7_NEON
+	b.ne	.Lneon_entry
+#endif
+	stp	x29,x30,[sp,#-128]!
+	add	x29,sp,#0
+
+	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,#4*4
+
+	ldp	w20,w21,[x0]				// load context
+	ldp	w22,w23,[x0,#2*4]
+	ldp	w24,w25,[x0,#4*4]
+	add	x2,x1,x2,lsl#6	// end of input
+	ldp	w26,w27,[x0,#6*4]
+	adr	x30,.LK256
+	stp	x0,x2,[x29,#96]
+
+.Loop:
+	ldp	w3,w4,[x1],#2*4
+	ldr	w19,[x30],#4			// *K++
+	eor	w28,w21,w22				// magic seed
+	str	x1,[x29,#112]
+#ifndef	__AARCH64EB__
+	rev	w3,w3			// 0
+#endif
+	ror	w16,w24,#6
+	add	w27,w27,w19			// h+=K[i]
+	eor	w6,w24,w24,ror#14
+	and	w17,w25,w24
+	bic	w19,w26,w24
+	add	w27,w27,w3			// h+=X[i]
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w20,w21			// a^b, b^c in next round
+	eor	w16,w16,w6,ror#11	// Sigma1(e)
+	ror	w6,w20,#2
+	add	w27,w27,w17			// h+=Ch(e,f,g)
+	eor	w17,w20,w20,ror#9
+	add	w27,w27,w16			// h+=Sigma1(e)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	add	w23,w23,w27			// d+=h
+	eor	w28,w28,w21			// Maj(a,b,c)
+	eor	w17,w6,w17,ror#13	// Sigma0(a)
+	add	w27,w27,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	//add	w27,w27,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w4,w4			// 1
+#endif
+	ldp	w5,w6,[x1],#2*4
+	add	w27,w27,w17			// h+=Sigma0(a)
+	ror	w16,w23,#6
+	add	w26,w26,w28			// h+=K[i]
+	eor	w7,w23,w23,ror#14
+	and	w17,w24,w23
+	bic	w28,w25,w23
+	add	w26,w26,w4			// h+=X[i]
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w27,w20			// a^b, b^c in next round
+	eor	w16,w16,w7,ror#11	// Sigma1(e)
+	ror	w7,w27,#2
+	add	w26,w26,w17			// h+=Ch(e,f,g)
+	eor	w17,w27,w27,ror#9
+	add	w26,w26,w16			// h+=Sigma1(e)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	add	w22,w22,w26			// d+=h
+	eor	w19,w19,w20			// Maj(a,b,c)
+	eor	w17,w7,w17,ror#13	// Sigma0(a)
+	add	w26,w26,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	//add	w26,w26,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w5,w5			// 2
+#endif
+	add	w26,w26,w17			// h+=Sigma0(a)
+	ror	w16,w22,#6
+	add	w25,w25,w19			// h+=K[i]
+	eor	w8,w22,w22,ror#14
+	and	w17,w23,w22
+	bic	w19,w24,w22
+	add	w25,w25,w5			// h+=X[i]
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w26,w27			// a^b, b^c in next round
+	eor	w16,w16,w8,ror#11	// Sigma1(e)
+	ror	w8,w26,#2
+	add	w25,w25,w17			// h+=Ch(e,f,g)
+	eor	w17,w26,w26,ror#9
+	add	w25,w25,w16			// h+=Sigma1(e)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	add	w21,w21,w25			// d+=h
+	eor	w28,w28,w27			// Maj(a,b,c)
+	eor	w17,w8,w17,ror#13	// Sigma0(a)
+	add	w25,w25,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	//add	w25,w25,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w6,w6			// 3
+#endif
+	ldp	w7,w8,[x1],#2*4
+	add	w25,w25,w17			// h+=Sigma0(a)
+	ror	w16,w21,#6
+	add	w24,w24,w28			// h+=K[i]
+	eor	w9,w21,w21,ror#14
+	and	w17,w22,w21
+	bic	w28,w23,w21
+	add	w24,w24,w6			// h+=X[i]
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w25,w26			// a^b, b^c in next round
+	eor	w16,w16,w9,ror#11	// Sigma1(e)
+	ror	w9,w25,#2
+	add	w24,w24,w17			// h+=Ch(e,f,g)
+	eor	w17,w25,w25,ror#9
+	add	w24,w24,w16			// h+=Sigma1(e)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	add	w20,w20,w24			// d+=h
+	eor	w19,w19,w26			// Maj(a,b,c)
+	eor	w17,w9,w17,ror#13	// Sigma0(a)
+	add	w24,w24,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	//add	w24,w24,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w7,w7			// 4
+#endif
+	add	w24,w24,w17			// h+=Sigma0(a)
+	ror	w16,w20,#6
+	add	w23,w23,w19			// h+=K[i]
+	eor	w10,w20,w20,ror#14
+	and	w17,w21,w20
+	bic	w19,w22,w20
+	add	w23,w23,w7			// h+=X[i]
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w24,w25			// a^b, b^c in next round
+	eor	w16,w16,w10,ror#11	// Sigma1(e)
+	ror	w10,w24,#2
+	add	w23,w23,w17			// h+=Ch(e,f,g)
+	eor	w17,w24,w24,ror#9
+	add	w23,w23,w16			// h+=Sigma1(e)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	add	w27,w27,w23			// d+=h
+	eor	w28,w28,w25			// Maj(a,b,c)
+	eor	w17,w10,w17,ror#13	// Sigma0(a)
+	add	w23,w23,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	//add	w23,w23,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w8,w8			// 5
+#endif
+	ldp	w9,w10,[x1],#2*4
+	add	w23,w23,w17			// h+=Sigma0(a)
+	ror	w16,w27,#6
+	add	w22,w22,w28			// h+=K[i]
+	eor	w11,w27,w27,ror#14
+	and	w17,w20,w27
+	bic	w28,w21,w27
+	add	w22,w22,w8			// h+=X[i]
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w23,w24			// a^b, b^c in next round
+	eor	w16,w16,w11,ror#11	// Sigma1(e)
+	ror	w11,w23,#2
+	add	w22,w22,w17			// h+=Ch(e,f,g)
+	eor	w17,w23,w23,ror#9
+	add	w22,w22,w16			// h+=Sigma1(e)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	add	w26,w26,w22			// d+=h
+	eor	w19,w19,w24			// Maj(a,b,c)
+	eor	w17,w11,w17,ror#13	// Sigma0(a)
+	add	w22,w22,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	//add	w22,w22,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w9,w9			// 6
+#endif
+	add	w22,w22,w17			// h+=Sigma0(a)
+	ror	w16,w26,#6
+	add	w21,w21,w19			// h+=K[i]
+	eor	w12,w26,w26,ror#14
+	and	w17,w27,w26
+	bic	w19,w20,w26
+	add	w21,w21,w9			// h+=X[i]
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w22,w23			// a^b, b^c in next round
+	eor	w16,w16,w12,ror#11	// Sigma1(e)
+	ror	w12,w22,#2
+	add	w21,w21,w17			// h+=Ch(e,f,g)
+	eor	w17,w22,w22,ror#9
+	add	w21,w21,w16			// h+=Sigma1(e)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	add	w25,w25,w21			// d+=h
+	eor	w28,w28,w23			// Maj(a,b,c)
+	eor	w17,w12,w17,ror#13	// Sigma0(a)
+	add	w21,w21,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	//add	w21,w21,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w10,w10			// 7
+#endif
+	ldp	w11,w12,[x1],#2*4
+	add	w21,w21,w17			// h+=Sigma0(a)
+	ror	w16,w25,#6
+	add	w20,w20,w28			// h+=K[i]
+	eor	w13,w25,w25,ror#14
+	and	w17,w26,w25
+	bic	w28,w27,w25
+	add	w20,w20,w10			// h+=X[i]
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w21,w22			// a^b, b^c in next round
+	eor	w16,w16,w13,ror#11	// Sigma1(e)
+	ror	w13,w21,#2
+	add	w20,w20,w17			// h+=Ch(e,f,g)
+	eor	w17,w21,w21,ror#9
+	add	w20,w20,w16			// h+=Sigma1(e)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	add	w24,w24,w20			// d+=h
+	eor	w19,w19,w22			// Maj(a,b,c)
+	eor	w17,w13,w17,ror#13	// Sigma0(a)
+	add	w20,w20,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	//add	w20,w20,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w11,w11			// 8
+#endif
+	add	w20,w20,w17			// h+=Sigma0(a)
+	ror	w16,w24,#6
+	add	w27,w27,w19			// h+=K[i]
+	eor	w14,w24,w24,ror#14
+	and	w17,w25,w24
+	bic	w19,w26,w24
+	add	w27,w27,w11			// h+=X[i]
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w20,w21			// a^b, b^c in next round
+	eor	w16,w16,w14,ror#11	// Sigma1(e)
+	ror	w14,w20,#2
+	add	w27,w27,w17			// h+=Ch(e,f,g)
+	eor	w17,w20,w20,ror#9
+	add	w27,w27,w16			// h+=Sigma1(e)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	add	w23,w23,w27			// d+=h
+	eor	w28,w28,w21			// Maj(a,b,c)
+	eor	w17,w14,w17,ror#13	// Sigma0(a)
+	add	w27,w27,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	//add	w27,w27,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w12,w12			// 9
+#endif
+	ldp	w13,w14,[x1],#2*4
+	add	w27,w27,w17			// h+=Sigma0(a)
+	ror	w16,w23,#6
+	add	w26,w26,w28			// h+=K[i]
+	eor	w15,w23,w23,ror#14
+	and	w17,w24,w23
+	bic	w28,w25,w23
+	add	w26,w26,w12			// h+=X[i]
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w27,w20			// a^b, b^c in next round
+	eor	w16,w16,w15,ror#11	// Sigma1(e)
+	ror	w15,w27,#2
+	add	w26,w26,w17			// h+=Ch(e,f,g)
+	eor	w17,w27,w27,ror#9
+	add	w26,w26,w16			// h+=Sigma1(e)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	add	w22,w22,w26			// d+=h
+	eor	w19,w19,w20			// Maj(a,b,c)
+	eor	w17,w15,w17,ror#13	// Sigma0(a)
+	add	w26,w26,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	//add	w26,w26,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w13,w13			// 10
+#endif
+	add	w26,w26,w17			// h+=Sigma0(a)
+	ror	w16,w22,#6
+	add	w25,w25,w19			// h+=K[i]
+	eor	w0,w22,w22,ror#14
+	and	w17,w23,w22
+	bic	w19,w24,w22
+	add	w25,w25,w13			// h+=X[i]
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w26,w27			// a^b, b^c in next round
+	eor	w16,w16,w0,ror#11	// Sigma1(e)
+	ror	w0,w26,#2
+	add	w25,w25,w17			// h+=Ch(e,f,g)
+	eor	w17,w26,w26,ror#9
+	add	w25,w25,w16			// h+=Sigma1(e)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	add	w21,w21,w25			// d+=h
+	eor	w28,w28,w27			// Maj(a,b,c)
+	eor	w17,w0,w17,ror#13	// Sigma0(a)
+	add	w25,w25,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	//add	w25,w25,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w14,w14			// 11
+#endif
+	ldp	w15,w0,[x1],#2*4
+	add	w25,w25,w17			// h+=Sigma0(a)
+	str	w6,[sp,#12]
+	ror	w16,w21,#6
+	add	w24,w24,w28			// h+=K[i]
+	eor	w6,w21,w21,ror#14
+	and	w17,w22,w21
+	bic	w28,w23,w21
+	add	w24,w24,w14			// h+=X[i]
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w25,w26			// a^b, b^c in next round
+	eor	w16,w16,w6,ror#11	// Sigma1(e)
+	ror	w6,w25,#2
+	add	w24,w24,w17			// h+=Ch(e,f,g)
+	eor	w17,w25,w25,ror#9
+	add	w24,w24,w16			// h+=Sigma1(e)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	add	w20,w20,w24			// d+=h
+	eor	w19,w19,w26			// Maj(a,b,c)
+	eor	w17,w6,w17,ror#13	// Sigma0(a)
+	add	w24,w24,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	//add	w24,w24,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w15,w15			// 12
+#endif
+	add	w24,w24,w17			// h+=Sigma0(a)
+	str	w7,[sp,#0]
+	ror	w16,w20,#6
+	add	w23,w23,w19			// h+=K[i]
+	eor	w7,w20,w20,ror#14
+	and	w17,w21,w20
+	bic	w19,w22,w20
+	add	w23,w23,w15			// h+=X[i]
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w24,w25			// a^b, b^c in next round
+	eor	w16,w16,w7,ror#11	// Sigma1(e)
+	ror	w7,w24,#2
+	add	w23,w23,w17			// h+=Ch(e,f,g)
+	eor	w17,w24,w24,ror#9
+	add	w23,w23,w16			// h+=Sigma1(e)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	add	w27,w27,w23			// d+=h
+	eor	w28,w28,w25			// Maj(a,b,c)
+	eor	w17,w7,w17,ror#13	// Sigma0(a)
+	add	w23,w23,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	//add	w23,w23,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w0,w0			// 13
+#endif
+	ldp	w1,w2,[x1]
+	add	w23,w23,w17			// h+=Sigma0(a)
+	str	w8,[sp,#4]
+	ror	w16,w27,#6
+	add	w22,w22,w28			// h+=K[i]
+	eor	w8,w27,w27,ror#14
+	and	w17,w20,w27
+	bic	w28,w21,w27
+	add	w22,w22,w0			// h+=X[i]
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w23,w24			// a^b, b^c in next round
+	eor	w16,w16,w8,ror#11	// Sigma1(e)
+	ror	w8,w23,#2
+	add	w22,w22,w17			// h+=Ch(e,f,g)
+	eor	w17,w23,w23,ror#9
+	add	w22,w22,w16			// h+=Sigma1(e)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	add	w26,w26,w22			// d+=h
+	eor	w19,w19,w24			// Maj(a,b,c)
+	eor	w17,w8,w17,ror#13	// Sigma0(a)
+	add	w22,w22,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	//add	w22,w22,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w1,w1			// 14
+#endif
+	ldr	w6,[sp,#12]
+	add	w22,w22,w17			// h+=Sigma0(a)
+	str	w9,[sp,#8]
+	ror	w16,w26,#6
+	add	w21,w21,w19			// h+=K[i]
+	eor	w9,w26,w26,ror#14
+	and	w17,w27,w26
+	bic	w19,w20,w26
+	add	w21,w21,w1			// h+=X[i]
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w22,w23			// a^b, b^c in next round
+	eor	w16,w16,w9,ror#11	// Sigma1(e)
+	ror	w9,w22,#2
+	add	w21,w21,w17			// h+=Ch(e,f,g)
+	eor	w17,w22,w22,ror#9
+	add	w21,w21,w16			// h+=Sigma1(e)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	add	w25,w25,w21			// d+=h
+	eor	w28,w28,w23			// Maj(a,b,c)
+	eor	w17,w9,w17,ror#13	// Sigma0(a)
+	add	w21,w21,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	//add	w21,w21,w17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	w2,w2			// 15
+#endif
+	ldr	w7,[sp,#0]
+	add	w21,w21,w17			// h+=Sigma0(a)
+	str	w10,[sp,#12]
+	ror	w16,w25,#6
+	add	w20,w20,w28			// h+=K[i]
+	ror	w9,w4,#7
+	and	w17,w26,w25
+	ror	w8,w1,#17
+	bic	w28,w27,w25
+	ror	w10,w21,#2
+	add	w20,w20,w2			// h+=X[i]
+	eor	w16,w16,w25,ror#11
+	eor	w9,w9,w4,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w21,w22			// a^b, b^c in next round
+	eor	w16,w16,w25,ror#25	// Sigma1(e)
+	eor	w10,w10,w21,ror#13
+	add	w20,w20,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w8,w8,w1,ror#19
+	eor	w9,w9,w4,lsr#3	// sigma0(X[i+1])
+	add	w20,w20,w16			// h+=Sigma1(e)
+	eor	w19,w19,w22			// Maj(a,b,c)
+	eor	w17,w10,w21,ror#22	// Sigma0(a)
+	eor	w8,w8,w1,lsr#10	// sigma1(X[i+14])
+	add	w3,w3,w12
+	add	w24,w24,w20			// d+=h
+	add	w20,w20,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w3,w3,w9
+	add	w20,w20,w17			// h+=Sigma0(a)
+	add	w3,w3,w8
+.Loop_16_xx:
+	ldr	w8,[sp,#4]
+	str	w11,[sp,#0]
+	ror	w16,w24,#6
+	add	w27,w27,w19			// h+=K[i]
+	ror	w10,w5,#7
+	and	w17,w25,w24
+	ror	w9,w2,#17
+	bic	w19,w26,w24
+	ror	w11,w20,#2
+	add	w27,w27,w3			// h+=X[i]
+	eor	w16,w16,w24,ror#11
+	eor	w10,w10,w5,ror#18
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w20,w21			// a^b, b^c in next round
+	eor	w16,w16,w24,ror#25	// Sigma1(e)
+	eor	w11,w11,w20,ror#13
+	add	w27,w27,w17			// h+=Ch(e,f,g)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	eor	w9,w9,w2,ror#19
+	eor	w10,w10,w5,lsr#3	// sigma0(X[i+1])
+	add	w27,w27,w16			// h+=Sigma1(e)
+	eor	w28,w28,w21			// Maj(a,b,c)
+	eor	w17,w11,w20,ror#22	// Sigma0(a)
+	eor	w9,w9,w2,lsr#10	// sigma1(X[i+14])
+	add	w4,w4,w13
+	add	w23,w23,w27			// d+=h
+	add	w27,w27,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	add	w4,w4,w10
+	add	w27,w27,w17			// h+=Sigma0(a)
+	add	w4,w4,w9
+	ldr	w9,[sp,#8]
+	str	w12,[sp,#4]
+	ror	w16,w23,#6
+	add	w26,w26,w28			// h+=K[i]
+	ror	w11,w6,#7
+	and	w17,w24,w23
+	ror	w10,w3,#17
+	bic	w28,w25,w23
+	ror	w12,w27,#2
+	add	w26,w26,w4			// h+=X[i]
+	eor	w16,w16,w23,ror#11
+	eor	w11,w11,w6,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w27,w20			// a^b, b^c in next round
+	eor	w16,w16,w23,ror#25	// Sigma1(e)
+	eor	w12,w12,w27,ror#13
+	add	w26,w26,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w10,w10,w3,ror#19
+	eor	w11,w11,w6,lsr#3	// sigma0(X[i+1])
+	add	w26,w26,w16			// h+=Sigma1(e)
+	eor	w19,w19,w20			// Maj(a,b,c)
+	eor	w17,w12,w27,ror#22	// Sigma0(a)
+	eor	w10,w10,w3,lsr#10	// sigma1(X[i+14])
+	add	w5,w5,w14
+	add	w22,w22,w26			// d+=h
+	add	w26,w26,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w5,w5,w11
+	add	w26,w26,w17			// h+=Sigma0(a)
+	add	w5,w5,w10
+	ldr	w10,[sp,#12]
+	str	w13,[sp,#8]
+	ror	w16,w22,#6
+	add	w25,w25,w19			// h+=K[i]
+	ror	w12,w7,#7
+	and	w17,w23,w22
+	ror	w11,w4,#17
+	bic	w19,w24,w22
+	ror	w13,w26,#2
+	add	w25,w25,w5			// h+=X[i]
+	eor	w16,w16,w22,ror#11
+	eor	w12,w12,w7,ror#18
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w26,w27			// a^b, b^c in next round
+	eor	w16,w16,w22,ror#25	// Sigma1(e)
+	eor	w13,w13,w26,ror#13
+	add	w25,w25,w17			// h+=Ch(e,f,g)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	eor	w11,w11,w4,ror#19
+	eor	w12,w12,w7,lsr#3	// sigma0(X[i+1])
+	add	w25,w25,w16			// h+=Sigma1(e)
+	eor	w28,w28,w27			// Maj(a,b,c)
+	eor	w17,w13,w26,ror#22	// Sigma0(a)
+	eor	w11,w11,w4,lsr#10	// sigma1(X[i+14])
+	add	w6,w6,w15
+	add	w21,w21,w25			// d+=h
+	add	w25,w25,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	add	w6,w6,w12
+	add	w25,w25,w17			// h+=Sigma0(a)
+	add	w6,w6,w11
+	ldr	w11,[sp,#0]
+	str	w14,[sp,#12]
+	ror	w16,w21,#6
+	add	w24,w24,w28			// h+=K[i]
+	ror	w13,w8,#7
+	and	w17,w22,w21
+	ror	w12,w5,#17
+	bic	w28,w23,w21
+	ror	w14,w25,#2
+	add	w24,w24,w6			// h+=X[i]
+	eor	w16,w16,w21,ror#11
+	eor	w13,w13,w8,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w25,w26			// a^b, b^c in next round
+	eor	w16,w16,w21,ror#25	// Sigma1(e)
+	eor	w14,w14,w25,ror#13
+	add	w24,w24,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w12,w12,w5,ror#19
+	eor	w13,w13,w8,lsr#3	// sigma0(X[i+1])
+	add	w24,w24,w16			// h+=Sigma1(e)
+	eor	w19,w19,w26			// Maj(a,b,c)
+	eor	w17,w14,w25,ror#22	// Sigma0(a)
+	eor	w12,w12,w5,lsr#10	// sigma1(X[i+14])
+	add	w7,w7,w0
+	add	w20,w20,w24			// d+=h
+	add	w24,w24,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w7,w7,w13
+	add	w24,w24,w17			// h+=Sigma0(a)
+	add	w7,w7,w12
+	ldr	w12,[sp,#4]
+	str	w15,[sp,#0]
+	ror	w16,w20,#6
+	add	w23,w23,w19			// h+=K[i]
+	ror	w14,w9,#7
+	and	w17,w21,w20
+	ror	w13,w6,#17
+	bic	w19,w22,w20
+	ror	w15,w24,#2
+	add	w23,w23,w7			// h+=X[i]
+	eor	w16,w16,w20,ror#11
+	eor	w14,w14,w9,ror#18
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w24,w25			// a^b, b^c in next round
+	eor	w16,w16,w20,ror#25	// Sigma1(e)
+	eor	w15,w15,w24,ror#13
+	add	w23,w23,w17			// h+=Ch(e,f,g)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	eor	w13,w13,w6,ror#19
+	eor	w14,w14,w9,lsr#3	// sigma0(X[i+1])
+	add	w23,w23,w16			// h+=Sigma1(e)
+	eor	w28,w28,w25			// Maj(a,b,c)
+	eor	w17,w15,w24,ror#22	// Sigma0(a)
+	eor	w13,w13,w6,lsr#10	// sigma1(X[i+14])
+	add	w8,w8,w1
+	add	w27,w27,w23			// d+=h
+	add	w23,w23,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	add	w8,w8,w14
+	add	w23,w23,w17			// h+=Sigma0(a)
+	add	w8,w8,w13
+	ldr	w13,[sp,#8]
+	str	w0,[sp,#4]
+	ror	w16,w27,#6
+	add	w22,w22,w28			// h+=K[i]
+	ror	w15,w10,#7
+	and	w17,w20,w27
+	ror	w14,w7,#17
+	bic	w28,w21,w27
+	ror	w0,w23,#2
+	add	w22,w22,w8			// h+=X[i]
+	eor	w16,w16,w27,ror#11
+	eor	w15,w15,w10,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w23,w24			// a^b, b^c in next round
+	eor	w16,w16,w27,ror#25	// Sigma1(e)
+	eor	w0,w0,w23,ror#13
+	add	w22,w22,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w14,w14,w7,ror#19
+	eor	w15,w15,w10,lsr#3	// sigma0(X[i+1])
+	add	w22,w22,w16			// h+=Sigma1(e)
+	eor	w19,w19,w24			// Maj(a,b,c)
+	eor	w17,w0,w23,ror#22	// Sigma0(a)
+	eor	w14,w14,w7,lsr#10	// sigma1(X[i+14])
+	add	w9,w9,w2
+	add	w26,w26,w22			// d+=h
+	add	w22,w22,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w9,w9,w15
+	add	w22,w22,w17			// h+=Sigma0(a)
+	add	w9,w9,w14
+	ldr	w14,[sp,#12]
+	str	w1,[sp,#8]
+	ror	w16,w26,#6
+	add	w21,w21,w19			// h+=K[i]
+	ror	w0,w11,#7
+	and	w17,w27,w26
+	ror	w15,w8,#17
+	bic	w19,w20,w26
+	ror	w1,w22,#2
+	add	w21,w21,w9			// h+=X[i]
+	eor	w16,w16,w26,ror#11
+	eor	w0,w0,w11,ror#18
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w22,w23			// a^b, b^c in next round
+	eor	w16,w16,w26,ror#25	// Sigma1(e)
+	eor	w1,w1,w22,ror#13
+	add	w21,w21,w17			// h+=Ch(e,f,g)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	eor	w15,w15,w8,ror#19
+	eor	w0,w0,w11,lsr#3	// sigma0(X[i+1])
+	add	w21,w21,w16			// h+=Sigma1(e)
+	eor	w28,w28,w23			// Maj(a,b,c)
+	eor	w17,w1,w22,ror#22	// Sigma0(a)
+	eor	w15,w15,w8,lsr#10	// sigma1(X[i+14])
+	add	w10,w10,w3
+	add	w25,w25,w21			// d+=h
+	add	w21,w21,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	add	w10,w10,w0
+	add	w21,w21,w17			// h+=Sigma0(a)
+	add	w10,w10,w15
+	ldr	w15,[sp,#0]
+	str	w2,[sp,#12]
+	ror	w16,w25,#6
+	add	w20,w20,w28			// h+=K[i]
+	ror	w1,w12,#7
+	and	w17,w26,w25
+	ror	w0,w9,#17
+	bic	w28,w27,w25
+	ror	w2,w21,#2
+	add	w20,w20,w10			// h+=X[i]
+	eor	w16,w16,w25,ror#11
+	eor	w1,w1,w12,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w21,w22			// a^b, b^c in next round
+	eor	w16,w16,w25,ror#25	// Sigma1(e)
+	eor	w2,w2,w21,ror#13
+	add	w20,w20,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w0,w0,w9,ror#19
+	eor	w1,w1,w12,lsr#3	// sigma0(X[i+1])
+	add	w20,w20,w16			// h+=Sigma1(e)
+	eor	w19,w19,w22			// Maj(a,b,c)
+	eor	w17,w2,w21,ror#22	// Sigma0(a)
+	eor	w0,w0,w9,lsr#10	// sigma1(X[i+14])
+	add	w11,w11,w4
+	add	w24,w24,w20			// d+=h
+	add	w20,w20,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w11,w11,w1
+	add	w20,w20,w17			// h+=Sigma0(a)
+	add	w11,w11,w0
+	ldr	w0,[sp,#4]
+	str	w3,[sp,#0]
+	ror	w16,w24,#6
+	add	w27,w27,w19			// h+=K[i]
+	ror	w2,w13,#7
+	and	w17,w25,w24
+	ror	w1,w10,#17
+	bic	w19,w26,w24
+	ror	w3,w20,#2
+	add	w27,w27,w11			// h+=X[i]
+	eor	w16,w16,w24,ror#11
+	eor	w2,w2,w13,ror#18
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w20,w21			// a^b, b^c in next round
+	eor	w16,w16,w24,ror#25	// Sigma1(e)
+	eor	w3,w3,w20,ror#13
+	add	w27,w27,w17			// h+=Ch(e,f,g)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	eor	w1,w1,w10,ror#19
+	eor	w2,w2,w13,lsr#3	// sigma0(X[i+1])
+	add	w27,w27,w16			// h+=Sigma1(e)
+	eor	w28,w28,w21			// Maj(a,b,c)
+	eor	w17,w3,w20,ror#22	// Sigma0(a)
+	eor	w1,w1,w10,lsr#10	// sigma1(X[i+14])
+	add	w12,w12,w5
+	add	w23,w23,w27			// d+=h
+	add	w27,w27,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	add	w12,w12,w2
+	add	w27,w27,w17			// h+=Sigma0(a)
+	add	w12,w12,w1
+	ldr	w1,[sp,#8]
+	str	w4,[sp,#4]
+	ror	w16,w23,#6
+	add	w26,w26,w28			// h+=K[i]
+	ror	w3,w14,#7
+	and	w17,w24,w23
+	ror	w2,w11,#17
+	bic	w28,w25,w23
+	ror	w4,w27,#2
+	add	w26,w26,w12			// h+=X[i]
+	eor	w16,w16,w23,ror#11
+	eor	w3,w3,w14,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w27,w20			// a^b, b^c in next round
+	eor	w16,w16,w23,ror#25	// Sigma1(e)
+	eor	w4,w4,w27,ror#13
+	add	w26,w26,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w2,w2,w11,ror#19
+	eor	w3,w3,w14,lsr#3	// sigma0(X[i+1])
+	add	w26,w26,w16			// h+=Sigma1(e)
+	eor	w19,w19,w20			// Maj(a,b,c)
+	eor	w17,w4,w27,ror#22	// Sigma0(a)
+	eor	w2,w2,w11,lsr#10	// sigma1(X[i+14])
+	add	w13,w13,w6
+	add	w22,w22,w26			// d+=h
+	add	w26,w26,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w13,w13,w3
+	add	w26,w26,w17			// h+=Sigma0(a)
+	add	w13,w13,w2
+	ldr	w2,[sp,#12]
+	str	w5,[sp,#8]
+	ror	w16,w22,#6
+	add	w25,w25,w19			// h+=K[i]
+	ror	w4,w15,#7
+	and	w17,w23,w22
+	ror	w3,w12,#17
+	bic	w19,w24,w22
+	ror	w5,w26,#2
+	add	w25,w25,w13			// h+=X[i]
+	eor	w16,w16,w22,ror#11
+	eor	w4,w4,w15,ror#18
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w26,w27			// a^b, b^c in next round
+	eor	w16,w16,w22,ror#25	// Sigma1(e)
+	eor	w5,w5,w26,ror#13
+	add	w25,w25,w17			// h+=Ch(e,f,g)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	eor	w3,w3,w12,ror#19
+	eor	w4,w4,w15,lsr#3	// sigma0(X[i+1])
+	add	w25,w25,w16			// h+=Sigma1(e)
+	eor	w28,w28,w27			// Maj(a,b,c)
+	eor	w17,w5,w26,ror#22	// Sigma0(a)
+	eor	w3,w3,w12,lsr#10	// sigma1(X[i+14])
+	add	w14,w14,w7
+	add	w21,w21,w25			// d+=h
+	add	w25,w25,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	add	w14,w14,w4
+	add	w25,w25,w17			// h+=Sigma0(a)
+	add	w14,w14,w3
+	ldr	w3,[sp,#0]
+	str	w6,[sp,#12]
+	ror	w16,w21,#6
+	add	w24,w24,w28			// h+=K[i]
+	ror	w5,w0,#7
+	and	w17,w22,w21
+	ror	w4,w13,#17
+	bic	w28,w23,w21
+	ror	w6,w25,#2
+	add	w24,w24,w14			// h+=X[i]
+	eor	w16,w16,w21,ror#11
+	eor	w5,w5,w0,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w25,w26			// a^b, b^c in next round
+	eor	w16,w16,w21,ror#25	// Sigma1(e)
+	eor	w6,w6,w25,ror#13
+	add	w24,w24,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w4,w4,w13,ror#19
+	eor	w5,w5,w0,lsr#3	// sigma0(X[i+1])
+	add	w24,w24,w16			// h+=Sigma1(e)
+	eor	w19,w19,w26			// Maj(a,b,c)
+	eor	w17,w6,w25,ror#22	// Sigma0(a)
+	eor	w4,w4,w13,lsr#10	// sigma1(X[i+14])
+	add	w15,w15,w8
+	add	w20,w20,w24			// d+=h
+	add	w24,w24,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w15,w15,w5
+	add	w24,w24,w17			// h+=Sigma0(a)
+	add	w15,w15,w4
+	ldr	w4,[sp,#4]
+	str	w7,[sp,#0]
+	ror	w16,w20,#6
+	add	w23,w23,w19			// h+=K[i]
+	ror	w6,w1,#7
+	and	w17,w21,w20
+	ror	w5,w14,#17
+	bic	w19,w22,w20
+	ror	w7,w24,#2
+	add	w23,w23,w15			// h+=X[i]
+	eor	w16,w16,w20,ror#11
+	eor	w6,w6,w1,ror#18
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w24,w25			// a^b, b^c in next round
+	eor	w16,w16,w20,ror#25	// Sigma1(e)
+	eor	w7,w7,w24,ror#13
+	add	w23,w23,w17			// h+=Ch(e,f,g)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	eor	w5,w5,w14,ror#19
+	eor	w6,w6,w1,lsr#3	// sigma0(X[i+1])
+	add	w23,w23,w16			// h+=Sigma1(e)
+	eor	w28,w28,w25			// Maj(a,b,c)
+	eor	w17,w7,w24,ror#22	// Sigma0(a)
+	eor	w5,w5,w14,lsr#10	// sigma1(X[i+14])
+	add	w0,w0,w9
+	add	w27,w27,w23			// d+=h
+	add	w23,w23,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	add	w0,w0,w6
+	add	w23,w23,w17			// h+=Sigma0(a)
+	add	w0,w0,w5
+	ldr	w5,[sp,#8]
+	str	w8,[sp,#4]
+	ror	w16,w27,#6
+	add	w22,w22,w28			// h+=K[i]
+	ror	w7,w2,#7
+	and	w17,w20,w27
+	ror	w6,w15,#17
+	bic	w28,w21,w27
+	ror	w8,w23,#2
+	add	w22,w22,w0			// h+=X[i]
+	eor	w16,w16,w27,ror#11
+	eor	w7,w7,w2,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w23,w24			// a^b, b^c in next round
+	eor	w16,w16,w27,ror#25	// Sigma1(e)
+	eor	w8,w8,w23,ror#13
+	add	w22,w22,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w6,w6,w15,ror#19
+	eor	w7,w7,w2,lsr#3	// sigma0(X[i+1])
+	add	w22,w22,w16			// h+=Sigma1(e)
+	eor	w19,w19,w24			// Maj(a,b,c)
+	eor	w17,w8,w23,ror#22	// Sigma0(a)
+	eor	w6,w6,w15,lsr#10	// sigma1(X[i+14])
+	add	w1,w1,w10
+	add	w26,w26,w22			// d+=h
+	add	w22,w22,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w1,w1,w7
+	add	w22,w22,w17			// h+=Sigma0(a)
+	add	w1,w1,w6
+	ldr	w6,[sp,#12]
+	str	w9,[sp,#8]
+	ror	w16,w26,#6
+	add	w21,w21,w19			// h+=K[i]
+	ror	w8,w3,#7
+	and	w17,w27,w26
+	ror	w7,w0,#17
+	bic	w19,w20,w26
+	ror	w9,w22,#2
+	add	w21,w21,w1			// h+=X[i]
+	eor	w16,w16,w26,ror#11
+	eor	w8,w8,w3,ror#18
+	orr	w17,w17,w19			// Ch(e,f,g)
+	eor	w19,w22,w23			// a^b, b^c in next round
+	eor	w16,w16,w26,ror#25	// Sigma1(e)
+	eor	w9,w9,w22,ror#13
+	add	w21,w21,w17			// h+=Ch(e,f,g)
+	and	w28,w28,w19			// (b^c)&=(a^b)
+	eor	w7,w7,w0,ror#19
+	eor	w8,w8,w3,lsr#3	// sigma0(X[i+1])
+	add	w21,w21,w16			// h+=Sigma1(e)
+	eor	w28,w28,w23			// Maj(a,b,c)
+	eor	w17,w9,w22,ror#22	// Sigma0(a)
+	eor	w7,w7,w0,lsr#10	// sigma1(X[i+14])
+	add	w2,w2,w11
+	add	w25,w25,w21			// d+=h
+	add	w21,w21,w28			// h+=Maj(a,b,c)
+	ldr	w28,[x30],#4		// *K++, w19 in next round
+	add	w2,w2,w8
+	add	w21,w21,w17			// h+=Sigma0(a)
+	add	w2,w2,w7
+	ldr	w7,[sp,#0]
+	str	w10,[sp,#12]
+	ror	w16,w25,#6
+	add	w20,w20,w28			// h+=K[i]
+	ror	w9,w4,#7
+	and	w17,w26,w25
+	ror	w8,w1,#17
+	bic	w28,w27,w25
+	ror	w10,w21,#2
+	add	w20,w20,w2			// h+=X[i]
+	eor	w16,w16,w25,ror#11
+	eor	w9,w9,w4,ror#18
+	orr	w17,w17,w28			// Ch(e,f,g)
+	eor	w28,w21,w22			// a^b, b^c in next round
+	eor	w16,w16,w25,ror#25	// Sigma1(e)
+	eor	w10,w10,w21,ror#13
+	add	w20,w20,w17			// h+=Ch(e,f,g)
+	and	w19,w19,w28			// (b^c)&=(a^b)
+	eor	w8,w8,w1,ror#19
+	eor	w9,w9,w4,lsr#3	// sigma0(X[i+1])
+	add	w20,w20,w16			// h+=Sigma1(e)
+	eor	w19,w19,w22			// Maj(a,b,c)
+	eor	w17,w10,w21,ror#22	// Sigma0(a)
+	eor	w8,w8,w1,lsr#10	// sigma1(X[i+14])
+	add	w3,w3,w12
+	add	w24,w24,w20			// d+=h
+	add	w20,w20,w19			// h+=Maj(a,b,c)
+	ldr	w19,[x30],#4		// *K++, w28 in next round
+	add	w3,w3,w9
+	add	w20,w20,w17			// h+=Sigma0(a)
+	add	w3,w3,w8
+	cbnz	w19,.Loop_16_xx
+
+	ldp	x0,x2,[x29,#96]
+	ldr	x1,[x29,#112]
+	sub	x30,x30,#260		// rewind
+
+	ldp	w3,w4,[x0]
+	ldp	w5,w6,[x0,#2*4]
+	add	x1,x1,#14*4			// advance input pointer
+	ldp	w7,w8,[x0,#4*4]
+	add	w20,w20,w3
+	ldp	w9,w10,[x0,#6*4]
+	add	w21,w21,w4
+	add	w22,w22,w5
+	add	w23,w23,w6
+	stp	w20,w21,[x0]
+	add	w24,w24,w7
+	add	w25,w25,w8
+	stp	w22,w23,[x0,#2*4]
+	add	w26,w26,w9
+	add	w27,w27,w10
+	cmp	x1,x2
+	stp	w24,w25,[x0,#4*4]
+	stp	w26,w27,[x0,#6*4]
+	b.ne	.Loop
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#4*4
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#128
+	ret
+.size	sha256_block_data_order,.-sha256_block_data_order
+
+.align	6
+.type	.LK256,%object
+.LK256:
+	.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+	.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+	.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+	.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+	.long	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+	.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+	.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+	.long	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+	.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+	.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+	.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+	.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+	.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+	.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+	.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+	.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+	.long	0	//terminator
+.size	.LK256,.-.LK256
+#ifndef	__KERNEL__
+.align	3
+.LOPENSSL_armcap_P:
+# ifdef	__ILP32__
+	.long	OPENSSL_armcap_P-.
+# else
+	.quad	OPENSSL_armcap_P-.
+# endif
+#endif
+.asciz	"SHA256 block transform for ARMv8, CRYPTOGAMS by <appro@openssl.org>"
+.align	2
+#ifndef	__KERNEL__
+.type	sha256_block_armv8,%function
+.align	6
+sha256_block_armv8:
+.Lv8_entry:
+	stp		x29,x30,[sp,#-16]!
+	add		x29,sp,#0
+
+	ld1		{v0.4s,v1.4s},[x0]
+	adr		x3,.LK256
+
+.Loop_hw:
+	ld1		{v4.16b-v7.16b},[x1],#64
+	sub		x2,x2,#1
+	ld1		{v16.4s},[x3],#16
+	rev32		v4.16b,v4.16b
+	rev32		v5.16b,v5.16b
+	rev32		v6.16b,v6.16b
+	rev32		v7.16b,v7.16b
+	orr		v18.16b,v0.16b,v0.16b		// offload
+	orr		v19.16b,v1.16b,v1.16b
+	ld1		{v17.4s},[x3],#16
+	add		v16.4s,v16.4s,v4.4s
+	.inst	0x5e2828a4	//sha256su0 v4.16b,v5.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
+	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
+	.inst	0x5e0760c4	//sha256su1 v4.16b,v6.16b,v7.16b
+	ld1		{v16.4s},[x3],#16
+	add		v17.4s,v17.4s,v5.4s
+	.inst	0x5e2828c5	//sha256su0 v5.16b,v6.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
+	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
+	.inst	0x5e0460e5	//sha256su1 v5.16b,v7.16b,v4.16b
+	ld1		{v17.4s},[x3],#16
+	add		v16.4s,v16.4s,v6.4s
+	.inst	0x5e2828e6	//sha256su0 v6.16b,v7.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
+	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
+	.inst	0x5e056086	//sha256su1 v6.16b,v4.16b,v5.16b
+	ld1		{v16.4s},[x3],#16
+	add		v17.4s,v17.4s,v7.4s
+	.inst	0x5e282887	//sha256su0 v7.16b,v4.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
+	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
+	.inst	0x5e0660a7	//sha256su1 v7.16b,v5.16b,v6.16b
+	ld1		{v17.4s},[x3],#16
+	add		v16.4s,v16.4s,v4.4s
+	.inst	0x5e2828a4	//sha256su0 v4.16b,v5.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
+	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
+	.inst	0x5e0760c4	//sha256su1 v4.16b,v6.16b,v7.16b
+	ld1		{v16.4s},[x3],#16
+	add		v17.4s,v17.4s,v5.4s
+	.inst	0x5e2828c5	//sha256su0 v5.16b,v6.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
+	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
+	.inst	0x5e0460e5	//sha256su1 v5.16b,v7.16b,v4.16b
+	ld1		{v17.4s},[x3],#16
+	add		v16.4s,v16.4s,v6.4s
+	.inst	0x5e2828e6	//sha256su0 v6.16b,v7.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
+	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
+	.inst	0x5e056086	//sha256su1 v6.16b,v4.16b,v5.16b
+	ld1		{v16.4s},[x3],#16
+	add		v17.4s,v17.4s,v7.4s
+	.inst	0x5e282887	//sha256su0 v7.16b,v4.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
+	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
+	.inst	0x5e0660a7	//sha256su1 v7.16b,v5.16b,v6.16b
+	ld1		{v17.4s},[x3],#16
+	add		v16.4s,v16.4s,v4.4s
+	.inst	0x5e2828a4	//sha256su0 v4.16b,v5.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
+	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
+	.inst	0x5e0760c4	//sha256su1 v4.16b,v6.16b,v7.16b
+	ld1		{v16.4s},[x3],#16
+	add		v17.4s,v17.4s,v5.4s
+	.inst	0x5e2828c5	//sha256su0 v5.16b,v6.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
+	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
+	.inst	0x5e0460e5	//sha256su1 v5.16b,v7.16b,v4.16b
+	ld1		{v17.4s},[x3],#16
+	add		v16.4s,v16.4s,v6.4s
+	.inst	0x5e2828e6	//sha256su0 v6.16b,v7.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
+	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
+	.inst	0x5e056086	//sha256su1 v6.16b,v4.16b,v5.16b
+	ld1		{v16.4s},[x3],#16
+	add		v17.4s,v17.4s,v7.4s
+	.inst	0x5e282887	//sha256su0 v7.16b,v4.16b
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
+	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
+	.inst	0x5e0660a7	//sha256su1 v7.16b,v5.16b,v6.16b
+	ld1		{v17.4s},[x3],#16
+	add		v16.4s,v16.4s,v4.4s
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
+	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
+
+	ld1		{v16.4s},[x3],#16
+	add		v17.4s,v17.4s,v5.4s
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
+	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
+
+	ld1		{v17.4s},[x3]
+	add		v16.4s,v16.4s,v6.4s
+	sub		x3,x3,#64*4-16	// rewind
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e104020	//sha256h v0.16b,v1.16b,v16.4s
+	.inst	0x5e105041	//sha256h2 v1.16b,v2.16b,v16.4s
+
+	add		v17.4s,v17.4s,v7.4s
+	orr		v2.16b,v0.16b,v0.16b
+	.inst	0x5e114020	//sha256h v0.16b,v1.16b,v17.4s
+	.inst	0x5e115041	//sha256h2 v1.16b,v2.16b,v17.4s
+
+	add		v0.4s,v0.4s,v18.4s
+	add		v1.4s,v1.4s,v19.4s
+
+	cbnz		x2,.Loop_hw
+
+	st1		{v0.4s,v1.4s},[x0]
+
+	ldr		x29,[sp],#16
+	ret
+.size	sha256_block_armv8,.-sha256_block_armv8
+#endif
+#ifdef	__KERNEL__
+.globl	sha256_block_neon
+#endif
+.type	sha256_block_neon,%function
+.align	4
+sha256_block_neon:
+.Lneon_entry:
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+	sub	sp,sp,#16*4
+
+	adr	x16,.LK256
+	add	x2,x1,x2,lsl#6	// len to point at the end of inp
+
+	ld1	{v0.16b},[x1], #16
+	ld1	{v1.16b},[x1], #16
+	ld1	{v2.16b},[x1], #16
+	ld1	{v3.16b},[x1], #16
+	ld1	{v4.4s},[x16], #16
+	ld1	{v5.4s},[x16], #16
+	ld1	{v6.4s},[x16], #16
+	ld1	{v7.4s},[x16], #16
+	rev32	v0.16b,v0.16b		// yes, even on
+	rev32	v1.16b,v1.16b		// big-endian
+	rev32	v2.16b,v2.16b
+	rev32	v3.16b,v3.16b
+	mov	x17,sp
+	add	v4.4s,v4.4s,v0.4s
+	add	v5.4s,v5.4s,v1.4s
+	add	v6.4s,v6.4s,v2.4s
+	st1	{v4.4s-v5.4s},[x17], #32
+	add	v7.4s,v7.4s,v3.4s
+	st1	{v6.4s-v7.4s},[x17]
+	sub	x17,x17,#32
+
+	ldp	w3,w4,[x0]
+	ldp	w5,w6,[x0,#8]
+	ldp	w7,w8,[x0,#16]
+	ldp	w9,w10,[x0,#24]
+	ldr	w12,[sp,#0]
+	mov	w13,wzr
+	eor	w14,w4,w5
+	mov	w15,wzr
+	b	.L_00_48
+
+.align	4
+.L_00_48:
+	ext	v4.16b,v0.16b,v1.16b,#4
+	add	w10,w10,w12
+	add	w3,w3,w15
+	and	w12,w8,w7
+	bic	w15,w9,w7
+	ext	v7.16b,v2.16b,v3.16b,#4
+	eor	w11,w7,w7,ror#5
+	add	w3,w3,w13
+	mov	d19,v3.d[1]
+	orr	w12,w12,w15
+	eor	w11,w11,w7,ror#19
+	ushr	v6.4s,v4.4s,#7
+	eor	w15,w3,w3,ror#11
+	ushr	v5.4s,v4.4s,#3
+	add	w10,w10,w12
+	add	v0.4s,v0.4s,v7.4s
+	ror	w11,w11,#6
+	sli	v6.4s,v4.4s,#25
+	eor	w13,w3,w4
+	eor	w15,w15,w3,ror#20
+	ushr	v7.4s,v4.4s,#18
+	add	w10,w10,w11
+	ldr	w12,[sp,#4]
+	and	w14,w14,w13
+	eor	v5.16b,v5.16b,v6.16b
+	ror	w15,w15,#2
+	add	w6,w6,w10
+	sli	v7.4s,v4.4s,#14
+	eor	w14,w14,w4
+	ushr	v16.4s,v19.4s,#17
+	add	w9,w9,w12
+	add	w10,w10,w15
+	and	w12,w7,w6
+	eor	v5.16b,v5.16b,v7.16b
+	bic	w15,w8,w6
+	eor	w11,w6,w6,ror#5
+	sli	v16.4s,v19.4s,#15
+	add	w10,w10,w14
+	orr	w12,w12,w15
+	ushr	v17.4s,v19.4s,#10
+	eor	w11,w11,w6,ror#19
+	eor	w15,w10,w10,ror#11
+	ushr	v7.4s,v19.4s,#19
+	add	w9,w9,w12
+	ror	w11,w11,#6
+	add	v0.4s,v0.4s,v5.4s
+	eor	w14,w10,w3
+	eor	w15,w15,w10,ror#20
+	sli	v7.4s,v19.4s,#13
+	add	w9,w9,w11
+	ldr	w12,[sp,#8]
+	and	w13,w13,w14
+	eor	v17.16b,v17.16b,v16.16b
+	ror	w15,w15,#2
+	add	w5,w5,w9
+	eor	w13,w13,w3
+	eor	v17.16b,v17.16b,v7.16b
+	add	w8,w8,w12
+	add	w9,w9,w15
+	and	w12,w6,w5
+	add	v0.4s,v0.4s,v17.4s
+	bic	w15,w7,w5
+	eor	w11,w5,w5,ror#5
+	add	w9,w9,w13
+	ushr	v18.4s,v0.4s,#17
+	orr	w12,w12,w15
+	ushr	v19.4s,v0.4s,#10
+	eor	w11,w11,w5,ror#19
+	eor	w15,w9,w9,ror#11
+	sli	v18.4s,v0.4s,#15
+	add	w8,w8,w12
+	ushr	v17.4s,v0.4s,#19
+	ror	w11,w11,#6
+	eor	w13,w9,w10
+	eor	v19.16b,v19.16b,v18.16b
+	eor	w15,w15,w9,ror#20
+	add	w8,w8,w11
+	sli	v17.4s,v0.4s,#13
+	ldr	w12,[sp,#12]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	ld1	{v4.4s},[x16], #16
+	add	w4,w4,w8
+	eor	v19.16b,v19.16b,v17.16b
+	eor	w14,w14,w10
+	eor	v17.16b,v17.16b,v17.16b
+	add	w7,w7,w12
+	add	w8,w8,w15
+	and	w12,w5,w4
+	mov	v17.d[1],v19.d[0]
+	bic	w15,w6,w4
+	eor	w11,w4,w4,ror#5
+	add	w8,w8,w14
+	add	v0.4s,v0.4s,v17.4s
+	orr	w12,w12,w15
+	eor	w11,w11,w4,ror#19
+	eor	w15,w8,w8,ror#11
+	add	v4.4s,v4.4s,v0.4s
+	add	w7,w7,w12
+	ror	w11,w11,#6
+	eor	w14,w8,w9
+	eor	w15,w15,w8,ror#20
+	add	w7,w7,w11
+	ldr	w12,[sp,#16]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w3,w3,w7
+	eor	w13,w13,w9
+	st1	{v4.4s},[x17], #16
+	ext	v4.16b,v1.16b,v2.16b,#4
+	add	w6,w6,w12
+	add	w7,w7,w15
+	and	w12,w4,w3
+	bic	w15,w5,w3
+	ext	v7.16b,v3.16b,v0.16b,#4
+	eor	w11,w3,w3,ror#5
+	add	w7,w7,w13
+	mov	d19,v0.d[1]
+	orr	w12,w12,w15
+	eor	w11,w11,w3,ror#19
+	ushr	v6.4s,v4.4s,#7
+	eor	w15,w7,w7,ror#11
+	ushr	v5.4s,v4.4s,#3
+	add	w6,w6,w12
+	add	v1.4s,v1.4s,v7.4s
+	ror	w11,w11,#6
+	sli	v6.4s,v4.4s,#25
+	eor	w13,w7,w8
+	eor	w15,w15,w7,ror#20
+	ushr	v7.4s,v4.4s,#18
+	add	w6,w6,w11
+	ldr	w12,[sp,#20]
+	and	w14,w14,w13
+	eor	v5.16b,v5.16b,v6.16b
+	ror	w15,w15,#2
+	add	w10,w10,w6
+	sli	v7.4s,v4.4s,#14
+	eor	w14,w14,w8
+	ushr	v16.4s,v19.4s,#17
+	add	w5,w5,w12
+	add	w6,w6,w15
+	and	w12,w3,w10
+	eor	v5.16b,v5.16b,v7.16b
+	bic	w15,w4,w10
+	eor	w11,w10,w10,ror#5
+	sli	v16.4s,v19.4s,#15
+	add	w6,w6,w14
+	orr	w12,w12,w15
+	ushr	v17.4s,v19.4s,#10
+	eor	w11,w11,w10,ror#19
+	eor	w15,w6,w6,ror#11
+	ushr	v7.4s,v19.4s,#19
+	add	w5,w5,w12
+	ror	w11,w11,#6
+	add	v1.4s,v1.4s,v5.4s
+	eor	w14,w6,w7
+	eor	w15,w15,w6,ror#20
+	sli	v7.4s,v19.4s,#13
+	add	w5,w5,w11
+	ldr	w12,[sp,#24]
+	and	w13,w13,w14
+	eor	v17.16b,v17.16b,v16.16b
+	ror	w15,w15,#2
+	add	w9,w9,w5
+	eor	w13,w13,w7
+	eor	v17.16b,v17.16b,v7.16b
+	add	w4,w4,w12
+	add	w5,w5,w15
+	and	w12,w10,w9
+	add	v1.4s,v1.4s,v17.4s
+	bic	w15,w3,w9
+	eor	w11,w9,w9,ror#5
+	add	w5,w5,w13
+	ushr	v18.4s,v1.4s,#17
+	orr	w12,w12,w15
+	ushr	v19.4s,v1.4s,#10
+	eor	w11,w11,w9,ror#19
+	eor	w15,w5,w5,ror#11
+	sli	v18.4s,v1.4s,#15
+	add	w4,w4,w12
+	ushr	v17.4s,v1.4s,#19
+	ror	w11,w11,#6
+	eor	w13,w5,w6
+	eor	v19.16b,v19.16b,v18.16b
+	eor	w15,w15,w5,ror#20
+	add	w4,w4,w11
+	sli	v17.4s,v1.4s,#13
+	ldr	w12,[sp,#28]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	ld1	{v4.4s},[x16], #16
+	add	w8,w8,w4
+	eor	v19.16b,v19.16b,v17.16b
+	eor	w14,w14,w6
+	eor	v17.16b,v17.16b,v17.16b
+	add	w3,w3,w12
+	add	w4,w4,w15
+	and	w12,w9,w8
+	mov	v17.d[1],v19.d[0]
+	bic	w15,w10,w8
+	eor	w11,w8,w8,ror#5
+	add	w4,w4,w14
+	add	v1.4s,v1.4s,v17.4s
+	orr	w12,w12,w15
+	eor	w11,w11,w8,ror#19
+	eor	w15,w4,w4,ror#11
+	add	v4.4s,v4.4s,v1.4s
+	add	w3,w3,w12
+	ror	w11,w11,#6
+	eor	w14,w4,w5
+	eor	w15,w15,w4,ror#20
+	add	w3,w3,w11
+	ldr	w12,[sp,#32]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w7,w7,w3
+	eor	w13,w13,w5
+	st1	{v4.4s},[x17], #16
+	ext	v4.16b,v2.16b,v3.16b,#4
+	add	w10,w10,w12
+	add	w3,w3,w15
+	and	w12,w8,w7
+	bic	w15,w9,w7
+	ext	v7.16b,v0.16b,v1.16b,#4
+	eor	w11,w7,w7,ror#5
+	add	w3,w3,w13
+	mov	d19,v1.d[1]
+	orr	w12,w12,w15
+	eor	w11,w11,w7,ror#19
+	ushr	v6.4s,v4.4s,#7
+	eor	w15,w3,w3,ror#11
+	ushr	v5.4s,v4.4s,#3
+	add	w10,w10,w12
+	add	v2.4s,v2.4s,v7.4s
+	ror	w11,w11,#6
+	sli	v6.4s,v4.4s,#25
+	eor	w13,w3,w4
+	eor	w15,w15,w3,ror#20
+	ushr	v7.4s,v4.4s,#18
+	add	w10,w10,w11
+	ldr	w12,[sp,#36]
+	and	w14,w14,w13
+	eor	v5.16b,v5.16b,v6.16b
+	ror	w15,w15,#2
+	add	w6,w6,w10
+	sli	v7.4s,v4.4s,#14
+	eor	w14,w14,w4
+	ushr	v16.4s,v19.4s,#17
+	add	w9,w9,w12
+	add	w10,w10,w15
+	and	w12,w7,w6
+	eor	v5.16b,v5.16b,v7.16b
+	bic	w15,w8,w6
+	eor	w11,w6,w6,ror#5
+	sli	v16.4s,v19.4s,#15
+	add	w10,w10,w14
+	orr	w12,w12,w15
+	ushr	v17.4s,v19.4s,#10
+	eor	w11,w11,w6,ror#19
+	eor	w15,w10,w10,ror#11
+	ushr	v7.4s,v19.4s,#19
+	add	w9,w9,w12
+	ror	w11,w11,#6
+	add	v2.4s,v2.4s,v5.4s
+	eor	w14,w10,w3
+	eor	w15,w15,w10,ror#20
+	sli	v7.4s,v19.4s,#13
+	add	w9,w9,w11
+	ldr	w12,[sp,#40]
+	and	w13,w13,w14
+	eor	v17.16b,v17.16b,v16.16b
+	ror	w15,w15,#2
+	add	w5,w5,w9
+	eor	w13,w13,w3
+	eor	v17.16b,v17.16b,v7.16b
+	add	w8,w8,w12
+	add	w9,w9,w15
+	and	w12,w6,w5
+	add	v2.4s,v2.4s,v17.4s
+	bic	w15,w7,w5
+	eor	w11,w5,w5,ror#5
+	add	w9,w9,w13
+	ushr	v18.4s,v2.4s,#17
+	orr	w12,w12,w15
+	ushr	v19.4s,v2.4s,#10
+	eor	w11,w11,w5,ror#19
+	eor	w15,w9,w9,ror#11
+	sli	v18.4s,v2.4s,#15
+	add	w8,w8,w12
+	ushr	v17.4s,v2.4s,#19
+	ror	w11,w11,#6
+	eor	w13,w9,w10
+	eor	v19.16b,v19.16b,v18.16b
+	eor	w15,w15,w9,ror#20
+	add	w8,w8,w11
+	sli	v17.4s,v2.4s,#13
+	ldr	w12,[sp,#44]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	ld1	{v4.4s},[x16], #16
+	add	w4,w4,w8
+	eor	v19.16b,v19.16b,v17.16b
+	eor	w14,w14,w10
+	eor	v17.16b,v17.16b,v17.16b
+	add	w7,w7,w12
+	add	w8,w8,w15
+	and	w12,w5,w4
+	mov	v17.d[1],v19.d[0]
+	bic	w15,w6,w4
+	eor	w11,w4,w4,ror#5
+	add	w8,w8,w14
+	add	v2.4s,v2.4s,v17.4s
+	orr	w12,w12,w15
+	eor	w11,w11,w4,ror#19
+	eor	w15,w8,w8,ror#11
+	add	v4.4s,v4.4s,v2.4s
+	add	w7,w7,w12
+	ror	w11,w11,#6
+	eor	w14,w8,w9
+	eor	w15,w15,w8,ror#20
+	add	w7,w7,w11
+	ldr	w12,[sp,#48]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w3,w3,w7
+	eor	w13,w13,w9
+	st1	{v4.4s},[x17], #16
+	ext	v4.16b,v3.16b,v0.16b,#4
+	add	w6,w6,w12
+	add	w7,w7,w15
+	and	w12,w4,w3
+	bic	w15,w5,w3
+	ext	v7.16b,v1.16b,v2.16b,#4
+	eor	w11,w3,w3,ror#5
+	add	w7,w7,w13
+	mov	d19,v2.d[1]
+	orr	w12,w12,w15
+	eor	w11,w11,w3,ror#19
+	ushr	v6.4s,v4.4s,#7
+	eor	w15,w7,w7,ror#11
+	ushr	v5.4s,v4.4s,#3
+	add	w6,w6,w12
+	add	v3.4s,v3.4s,v7.4s
+	ror	w11,w11,#6
+	sli	v6.4s,v4.4s,#25
+	eor	w13,w7,w8
+	eor	w15,w15,w7,ror#20
+	ushr	v7.4s,v4.4s,#18
+	add	w6,w6,w11
+	ldr	w12,[sp,#52]
+	and	w14,w14,w13
+	eor	v5.16b,v5.16b,v6.16b
+	ror	w15,w15,#2
+	add	w10,w10,w6
+	sli	v7.4s,v4.4s,#14
+	eor	w14,w14,w8
+	ushr	v16.4s,v19.4s,#17
+	add	w5,w5,w12
+	add	w6,w6,w15
+	and	w12,w3,w10
+	eor	v5.16b,v5.16b,v7.16b
+	bic	w15,w4,w10
+	eor	w11,w10,w10,ror#5
+	sli	v16.4s,v19.4s,#15
+	add	w6,w6,w14
+	orr	w12,w12,w15
+	ushr	v17.4s,v19.4s,#10
+	eor	w11,w11,w10,ror#19
+	eor	w15,w6,w6,ror#11
+	ushr	v7.4s,v19.4s,#19
+	add	w5,w5,w12
+	ror	w11,w11,#6
+	add	v3.4s,v3.4s,v5.4s
+	eor	w14,w6,w7
+	eor	w15,w15,w6,ror#20
+	sli	v7.4s,v19.4s,#13
+	add	w5,w5,w11
+	ldr	w12,[sp,#56]
+	and	w13,w13,w14
+	eor	v17.16b,v17.16b,v16.16b
+	ror	w15,w15,#2
+	add	w9,w9,w5
+	eor	w13,w13,w7
+	eor	v17.16b,v17.16b,v7.16b
+	add	w4,w4,w12
+	add	w5,w5,w15
+	and	w12,w10,w9
+	add	v3.4s,v3.4s,v17.4s
+	bic	w15,w3,w9
+	eor	w11,w9,w9,ror#5
+	add	w5,w5,w13
+	ushr	v18.4s,v3.4s,#17
+	orr	w12,w12,w15
+	ushr	v19.4s,v3.4s,#10
+	eor	w11,w11,w9,ror#19
+	eor	w15,w5,w5,ror#11
+	sli	v18.4s,v3.4s,#15
+	add	w4,w4,w12
+	ushr	v17.4s,v3.4s,#19
+	ror	w11,w11,#6
+	eor	w13,w5,w6
+	eor	v19.16b,v19.16b,v18.16b
+	eor	w15,w15,w5,ror#20
+	add	w4,w4,w11
+	sli	v17.4s,v3.4s,#13
+	ldr	w12,[sp,#60]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	ld1	{v4.4s},[x16], #16
+	add	w8,w8,w4
+	eor	v19.16b,v19.16b,v17.16b
+	eor	w14,w14,w6
+	eor	v17.16b,v17.16b,v17.16b
+	add	w3,w3,w12
+	add	w4,w4,w15
+	and	w12,w9,w8
+	mov	v17.d[1],v19.d[0]
+	bic	w15,w10,w8
+	eor	w11,w8,w8,ror#5
+	add	w4,w4,w14
+	add	v3.4s,v3.4s,v17.4s
+	orr	w12,w12,w15
+	eor	w11,w11,w8,ror#19
+	eor	w15,w4,w4,ror#11
+	add	v4.4s,v4.4s,v3.4s
+	add	w3,w3,w12
+	ror	w11,w11,#6
+	eor	w14,w4,w5
+	eor	w15,w15,w4,ror#20
+	add	w3,w3,w11
+	ldr	w12,[x16]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w7,w7,w3
+	eor	w13,w13,w5
+	st1	{v4.4s},[x17], #16
+	cmp	w12,#0				// check for K256 terminator
+	ldr	w12,[sp,#0]
+	sub	x17,x17,#64
+	bne	.L_00_48
+
+	sub	x16,x16,#256		// rewind x16
+	cmp	x1,x2
+	mov	x17, #64
+	csel	x17, x17, xzr, eq
+	sub	x1,x1,x17			// avoid SEGV
+	mov	x17,sp
+	add	w10,w10,w12
+	add	w3,w3,w15
+	and	w12,w8,w7
+	ld1	{v0.16b},[x1],#16
+	bic	w15,w9,w7
+	eor	w11,w7,w7,ror#5
+	ld1	{v4.4s},[x16],#16
+	add	w3,w3,w13
+	orr	w12,w12,w15
+	eor	w11,w11,w7,ror#19
+	eor	w15,w3,w3,ror#11
+	rev32	v0.16b,v0.16b
+	add	w10,w10,w12
+	ror	w11,w11,#6
+	eor	w13,w3,w4
+	eor	w15,w15,w3,ror#20
+	add	v4.4s,v4.4s,v0.4s
+	add	w10,w10,w11
+	ldr	w12,[sp,#4]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	add	w6,w6,w10
+	eor	w14,w14,w4
+	add	w9,w9,w12
+	add	w10,w10,w15
+	and	w12,w7,w6
+	bic	w15,w8,w6
+	eor	w11,w6,w6,ror#5
+	add	w10,w10,w14
+	orr	w12,w12,w15
+	eor	w11,w11,w6,ror#19
+	eor	w15,w10,w10,ror#11
+	add	w9,w9,w12
+	ror	w11,w11,#6
+	eor	w14,w10,w3
+	eor	w15,w15,w10,ror#20
+	add	w9,w9,w11
+	ldr	w12,[sp,#8]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w5,w5,w9
+	eor	w13,w13,w3
+	add	w8,w8,w12
+	add	w9,w9,w15
+	and	w12,w6,w5
+	bic	w15,w7,w5
+	eor	w11,w5,w5,ror#5
+	add	w9,w9,w13
+	orr	w12,w12,w15
+	eor	w11,w11,w5,ror#19
+	eor	w15,w9,w9,ror#11
+	add	w8,w8,w12
+	ror	w11,w11,#6
+	eor	w13,w9,w10
+	eor	w15,w15,w9,ror#20
+	add	w8,w8,w11
+	ldr	w12,[sp,#12]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	add	w4,w4,w8
+	eor	w14,w14,w10
+	add	w7,w7,w12
+	add	w8,w8,w15
+	and	w12,w5,w4
+	bic	w15,w6,w4
+	eor	w11,w4,w4,ror#5
+	add	w8,w8,w14
+	orr	w12,w12,w15
+	eor	w11,w11,w4,ror#19
+	eor	w15,w8,w8,ror#11
+	add	w7,w7,w12
+	ror	w11,w11,#6
+	eor	w14,w8,w9
+	eor	w15,w15,w8,ror#20
+	add	w7,w7,w11
+	ldr	w12,[sp,#16]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w3,w3,w7
+	eor	w13,w13,w9
+	st1	{v4.4s},[x17], #16
+	add	w6,w6,w12
+	add	w7,w7,w15
+	and	w12,w4,w3
+	ld1	{v1.16b},[x1],#16
+	bic	w15,w5,w3
+	eor	w11,w3,w3,ror#5
+	ld1	{v4.4s},[x16],#16
+	add	w7,w7,w13
+	orr	w12,w12,w15
+	eor	w11,w11,w3,ror#19
+	eor	w15,w7,w7,ror#11
+	rev32	v1.16b,v1.16b
+	add	w6,w6,w12
+	ror	w11,w11,#6
+	eor	w13,w7,w8
+	eor	w15,w15,w7,ror#20
+	add	v4.4s,v4.4s,v1.4s
+	add	w6,w6,w11
+	ldr	w12,[sp,#20]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	add	w10,w10,w6
+	eor	w14,w14,w8
+	add	w5,w5,w12
+	add	w6,w6,w15
+	and	w12,w3,w10
+	bic	w15,w4,w10
+	eor	w11,w10,w10,ror#5
+	add	w6,w6,w14
+	orr	w12,w12,w15
+	eor	w11,w11,w10,ror#19
+	eor	w15,w6,w6,ror#11
+	add	w5,w5,w12
+	ror	w11,w11,#6
+	eor	w14,w6,w7
+	eor	w15,w15,w6,ror#20
+	add	w5,w5,w11
+	ldr	w12,[sp,#24]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w9,w9,w5
+	eor	w13,w13,w7
+	add	w4,w4,w12
+	add	w5,w5,w15
+	and	w12,w10,w9
+	bic	w15,w3,w9
+	eor	w11,w9,w9,ror#5
+	add	w5,w5,w13
+	orr	w12,w12,w15
+	eor	w11,w11,w9,ror#19
+	eor	w15,w5,w5,ror#11
+	add	w4,w4,w12
+	ror	w11,w11,#6
+	eor	w13,w5,w6
+	eor	w15,w15,w5,ror#20
+	add	w4,w4,w11
+	ldr	w12,[sp,#28]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	add	w8,w8,w4
+	eor	w14,w14,w6
+	add	w3,w3,w12
+	add	w4,w4,w15
+	and	w12,w9,w8
+	bic	w15,w10,w8
+	eor	w11,w8,w8,ror#5
+	add	w4,w4,w14
+	orr	w12,w12,w15
+	eor	w11,w11,w8,ror#19
+	eor	w15,w4,w4,ror#11
+	add	w3,w3,w12
+	ror	w11,w11,#6
+	eor	w14,w4,w5
+	eor	w15,w15,w4,ror#20
+	add	w3,w3,w11
+	ldr	w12,[sp,#32]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w7,w7,w3
+	eor	w13,w13,w5
+	st1	{v4.4s},[x17], #16
+	add	w10,w10,w12
+	add	w3,w3,w15
+	and	w12,w8,w7
+	ld1	{v2.16b},[x1],#16
+	bic	w15,w9,w7
+	eor	w11,w7,w7,ror#5
+	ld1	{v4.4s},[x16],#16
+	add	w3,w3,w13
+	orr	w12,w12,w15
+	eor	w11,w11,w7,ror#19
+	eor	w15,w3,w3,ror#11
+	rev32	v2.16b,v2.16b
+	add	w10,w10,w12
+	ror	w11,w11,#6
+	eor	w13,w3,w4
+	eor	w15,w15,w3,ror#20
+	add	v4.4s,v4.4s,v2.4s
+	add	w10,w10,w11
+	ldr	w12,[sp,#36]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	add	w6,w6,w10
+	eor	w14,w14,w4
+	add	w9,w9,w12
+	add	w10,w10,w15
+	and	w12,w7,w6
+	bic	w15,w8,w6
+	eor	w11,w6,w6,ror#5
+	add	w10,w10,w14
+	orr	w12,w12,w15
+	eor	w11,w11,w6,ror#19
+	eor	w15,w10,w10,ror#11
+	add	w9,w9,w12
+	ror	w11,w11,#6
+	eor	w14,w10,w3
+	eor	w15,w15,w10,ror#20
+	add	w9,w9,w11
+	ldr	w12,[sp,#40]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w5,w5,w9
+	eor	w13,w13,w3
+	add	w8,w8,w12
+	add	w9,w9,w15
+	and	w12,w6,w5
+	bic	w15,w7,w5
+	eor	w11,w5,w5,ror#5
+	add	w9,w9,w13
+	orr	w12,w12,w15
+	eor	w11,w11,w5,ror#19
+	eor	w15,w9,w9,ror#11
+	add	w8,w8,w12
+	ror	w11,w11,#6
+	eor	w13,w9,w10
+	eor	w15,w15,w9,ror#20
+	add	w8,w8,w11
+	ldr	w12,[sp,#44]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	add	w4,w4,w8
+	eor	w14,w14,w10
+	add	w7,w7,w12
+	add	w8,w8,w15
+	and	w12,w5,w4
+	bic	w15,w6,w4
+	eor	w11,w4,w4,ror#5
+	add	w8,w8,w14
+	orr	w12,w12,w15
+	eor	w11,w11,w4,ror#19
+	eor	w15,w8,w8,ror#11
+	add	w7,w7,w12
+	ror	w11,w11,#6
+	eor	w14,w8,w9
+	eor	w15,w15,w8,ror#20
+	add	w7,w7,w11
+	ldr	w12,[sp,#48]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w3,w3,w7
+	eor	w13,w13,w9
+	st1	{v4.4s},[x17], #16
+	add	w6,w6,w12
+	add	w7,w7,w15
+	and	w12,w4,w3
+	ld1	{v3.16b},[x1],#16
+	bic	w15,w5,w3
+	eor	w11,w3,w3,ror#5
+	ld1	{v4.4s},[x16],#16
+	add	w7,w7,w13
+	orr	w12,w12,w15
+	eor	w11,w11,w3,ror#19
+	eor	w15,w7,w7,ror#11
+	rev32	v3.16b,v3.16b
+	add	w6,w6,w12
+	ror	w11,w11,#6
+	eor	w13,w7,w8
+	eor	w15,w15,w7,ror#20
+	add	v4.4s,v4.4s,v3.4s
+	add	w6,w6,w11
+	ldr	w12,[sp,#52]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	add	w10,w10,w6
+	eor	w14,w14,w8
+	add	w5,w5,w12
+	add	w6,w6,w15
+	and	w12,w3,w10
+	bic	w15,w4,w10
+	eor	w11,w10,w10,ror#5
+	add	w6,w6,w14
+	orr	w12,w12,w15
+	eor	w11,w11,w10,ror#19
+	eor	w15,w6,w6,ror#11
+	add	w5,w5,w12
+	ror	w11,w11,#6
+	eor	w14,w6,w7
+	eor	w15,w15,w6,ror#20
+	add	w5,w5,w11
+	ldr	w12,[sp,#56]
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w9,w9,w5
+	eor	w13,w13,w7
+	add	w4,w4,w12
+	add	w5,w5,w15
+	and	w12,w10,w9
+	bic	w15,w3,w9
+	eor	w11,w9,w9,ror#5
+	add	w5,w5,w13
+	orr	w12,w12,w15
+	eor	w11,w11,w9,ror#19
+	eor	w15,w5,w5,ror#11
+	add	w4,w4,w12
+	ror	w11,w11,#6
+	eor	w13,w5,w6
+	eor	w15,w15,w5,ror#20
+	add	w4,w4,w11
+	ldr	w12,[sp,#60]
+	and	w14,w14,w13
+	ror	w15,w15,#2
+	add	w8,w8,w4
+	eor	w14,w14,w6
+	add	w3,w3,w12
+	add	w4,w4,w15
+	and	w12,w9,w8
+	bic	w15,w10,w8
+	eor	w11,w8,w8,ror#5
+	add	w4,w4,w14
+	orr	w12,w12,w15
+	eor	w11,w11,w8,ror#19
+	eor	w15,w4,w4,ror#11
+	add	w3,w3,w12
+	ror	w11,w11,#6
+	eor	w14,w4,w5
+	eor	w15,w15,w4,ror#20
+	add	w3,w3,w11
+	and	w13,w13,w14
+	ror	w15,w15,#2
+	add	w7,w7,w3
+	eor	w13,w13,w5
+	st1	{v4.4s},[x17], #16
+	add	w3,w3,w15			// h+=Sigma0(a) from the past
+	ldp	w11,w12,[x0,#0]
+	add	w3,w3,w13			// h+=Maj(a,b,c) from the past
+	ldp	w13,w14,[x0,#8]
+	add	w3,w3,w11			// accumulate
+	add	w4,w4,w12
+	ldp	w11,w12,[x0,#16]
+	add	w5,w5,w13
+	add	w6,w6,w14
+	ldp	w13,w14,[x0,#24]
+	add	w7,w7,w11
+	add	w8,w8,w12
+	 ldr	w12,[sp,#0]
+	stp	w3,w4,[x0,#0]
+	add	w9,w9,w13
+	 mov	w13,wzr
+	stp	w5,w6,[x0,#8]
+	add	w10,w10,w14
+	stp	w7,w8,[x0,#16]
+	 eor	w14,w4,w5
+	stp	w9,w10,[x0,#24]
+	 mov	w15,wzr
+	 mov	x17,sp
+	b.ne	.L_00_48
+
+	ldr	x29,[x29]
+	add	sp,sp,#16*4+16
+	ret
+.size	sha256_block_neon,.-sha256_block_neon
+#ifndef	__KERNEL__
+.comm	OPENSSL_armcap_P,4,4
+#endif
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
new file mode 100644
index 000000000..77bc6e72a
--- /dev/null
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Linux/arm64 port of the OpenSSL SHA256 implementation for AArch64
+ *
+ * Copyright (c) 2016 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sha.h>
+#include <crypto/sha256_base.h>
+#include <linux/types.h>
+#include <linux/string.h>
+
+MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash for arm64");
+MODULE_AUTHOR("Andy Polyakov <appro@openssl.org>");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+
+asmlinkage void sha256_block_data_order(u32 *digest, const void *data,
+					unsigned int num_blks);
+EXPORT_SYMBOL(sha256_block_data_order);
+
+static void __sha256_block_data_order(struct sha256_state *sst, u8 const *src,
+				      int blocks)
+{
+	sha256_block_data_order(sst->state, src, blocks);
+}
+
+asmlinkage void sha256_block_neon(u32 *digest, const void *data,
+				  unsigned int num_blks);
+
+static void __sha256_block_neon(struct sha256_state *sst, u8 const *src,
+				int blocks)
+{
+	sha256_block_neon(sst->state, src, blocks);
+}
+
+static int crypto_sha256_arm64_update(struct shash_desc *desc, const u8 *data,
+				      unsigned int len)
+{
+	return sha256_base_do_update(desc, data, len,
+				     __sha256_block_data_order);
+}
+
+static int crypto_sha256_arm64_finup(struct shash_desc *desc, const u8 *data,
+				     unsigned int len, u8 *out)
+{
+	if (len)
+		sha256_base_do_update(desc, data, len,
+				      __sha256_block_data_order);
+	sha256_base_do_finalize(desc, __sha256_block_data_order);
+
+	return sha256_base_finish(desc, out);
+}
+
+static int crypto_sha256_arm64_final(struct shash_desc *desc, u8 *out)
+{
+	return crypto_sha256_arm64_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg algs[] = { {
+	.digestsize		= SHA256_DIGEST_SIZE,
+	.init			= sha256_base_init,
+	.update			= crypto_sha256_arm64_update,
+	.final			= crypto_sha256_arm64_final,
+	.finup			= crypto_sha256_arm64_finup,
+	.descsize		= sizeof(struct sha256_state),
+	.base.cra_name		= "sha256",
+	.base.cra_driver_name	= "sha256-arm64",
+	.base.cra_priority	= 125,
+	.base.cra_blocksize	= SHA256_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.digestsize		= SHA224_DIGEST_SIZE,
+	.init			= sha224_base_init,
+	.update			= crypto_sha256_arm64_update,
+	.final			= crypto_sha256_arm64_final,
+	.finup			= crypto_sha256_arm64_finup,
+	.descsize		= sizeof(struct sha256_state),
+	.base.cra_name		= "sha224",
+	.base.cra_driver_name	= "sha224-arm64",
+	.base.cra_priority	= 125,
+	.base.cra_blocksize	= SHA224_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+} };
+
+static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
+			      unsigned int len)
+{
+	struct sha256_state *sctx = shash_desc_ctx(desc);
+
+	if (!crypto_simd_usable())
+		return sha256_base_do_update(desc, data, len,
+				__sha256_block_data_order);
+
+	while (len > 0) {
+		unsigned int chunk = len;
+
+		/*
+		 * Don't hog the CPU for the entire time it takes to process all
+		 * input when running on a preemptible kernel, but process the
+		 * data block by block instead.
+		 */
+		if (IS_ENABLED(CONFIG_PREEMPTION) &&
+		    chunk + sctx->count % SHA256_BLOCK_SIZE > SHA256_BLOCK_SIZE)
+			chunk = SHA256_BLOCK_SIZE -
+				sctx->count % SHA256_BLOCK_SIZE;
+
+		kernel_neon_begin();
+		sha256_base_do_update(desc, data, chunk, __sha256_block_neon);
+		kernel_neon_end();
+		data += chunk;
+		len -= chunk;
+	}
+	return 0;
+}
+
+static int sha256_finup_neon(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *out)
+{
+	if (!crypto_simd_usable()) {
+		if (len)
+			sha256_base_do_update(desc, data, len,
+				__sha256_block_data_order);
+		sha256_base_do_finalize(desc, __sha256_block_data_order);
+	} else {
+		if (len)
+			sha256_update_neon(desc, data, len);
+		kernel_neon_begin();
+		sha256_base_do_finalize(desc, __sha256_block_neon);
+		kernel_neon_end();
+	}
+	return sha256_base_finish(desc, out);
+}
+
+static int sha256_final_neon(struct shash_desc *desc, u8 *out)
+{
+	return sha256_finup_neon(desc, NULL, 0, out);
+}
+
+static struct shash_alg neon_algs[] = { {
+	.digestsize		= SHA256_DIGEST_SIZE,
+	.init			= sha256_base_init,
+	.update			= sha256_update_neon,
+	.final			= sha256_final_neon,
+	.finup			= sha256_finup_neon,
+	.descsize		= sizeof(struct sha256_state),
+	.base.cra_name		= "sha256",
+	.base.cra_driver_name	= "sha256-arm64-neon",
+	.base.cra_priority	= 150,
+	.base.cra_blocksize	= SHA256_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.digestsize		= SHA224_DIGEST_SIZE,
+	.init			= sha224_base_init,
+	.update			= sha256_update_neon,
+	.final			= sha256_final_neon,
+	.finup			= sha256_finup_neon,
+	.descsize		= sizeof(struct sha256_state),
+	.base.cra_name		= "sha224",
+	.base.cra_driver_name	= "sha224-arm64-neon",
+	.base.cra_priority	= 150,
+	.base.cra_blocksize	= SHA224_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+} };
+
+static int __init sha256_mod_init(void)
+{
+	int ret = crypto_register_shashes(algs, ARRAY_SIZE(algs));
+	if (ret)
+		return ret;
+
+	if (cpu_have_named_feature(ASIMD)) {
+		ret = crypto_register_shashes(neon_algs, ARRAY_SIZE(neon_algs));
+		if (ret)
+			crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+	}
+	return ret;
+}
+
+static void __exit sha256_mod_fini(void)
+{
+	if (cpu_have_named_feature(ASIMD))
+		crypto_unregister_shashes(neon_algs, ARRAY_SIZE(neon_algs));
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_init(sha256_mod_init);
+module_exit(sha256_mod_fini);
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
new file mode 100644
index 000000000..1cfb768df
--- /dev/null
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -0,0 +1,233 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sha3-ce-core.S - core SHA-3 transform using v8.2 Crypto Extensions
+ *
+ * Copyright (C) 2018 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>
+
+	.irp	b,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
+	.set	.Lv\b\().2d, \b
+	.set	.Lv\b\().16b, \b
+	.endr
+
+	/*
+	 * ARMv8.2 Crypto Extensions instructions
+	 */
+	.macro	eor3, rd, rn, rm, ra
+	.inst	0xce000000 | .L\rd | (.L\rn << 5) | (.L\ra << 10) | (.L\rm << 16)
+	.endm
+
+	.macro	rax1, rd, rn, rm
+	.inst	0xce608c00 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro	bcax, rd, rn, rm, ra
+	.inst	0xce200000 | .L\rd | (.L\rn << 5) | (.L\ra << 10) | (.L\rm << 16)
+	.endm
+
+	.macro	xar, rd, rn, rm, imm6
+	.inst	0xce800000 | .L\rd | (.L\rn << 5) | ((\imm6) << 10) | (.L\rm << 16)
+	.endm
+
+	/*
+	 * sha3_ce_transform(u64 *st, const u8 *data, int blocks, int dg_size)
+	 */
+	.text
+SYM_FUNC_START(sha3_ce_transform)
+	frame_push	4
+
+	mov	x19, x0
+	mov	x20, x1
+	mov	x21, x2
+	mov	x22, x3
+
+0:	/* load state */
+	add	x8, x19, #32
+	ld1	{ v0.1d- v3.1d}, [x19]
+	ld1	{ v4.1d- v7.1d}, [x8], #32
+	ld1	{ v8.1d-v11.1d}, [x8], #32
+	ld1	{v12.1d-v15.1d}, [x8], #32
+	ld1	{v16.1d-v19.1d}, [x8], #32
+	ld1	{v20.1d-v23.1d}, [x8], #32
+	ld1	{v24.1d}, [x8]
+
+1:	sub	w21, w21, #1
+	mov	w8, #24
+	adr_l	x9, .Lsha3_rcon
+
+	/* load input */
+	ld1	{v25.8b-v28.8b}, [x20], #32
+	ld1	{v29.8b-v31.8b}, [x20], #24
+	eor	v0.8b, v0.8b, v25.8b
+	eor	v1.8b, v1.8b, v26.8b
+	eor	v2.8b, v2.8b, v27.8b
+	eor	v3.8b, v3.8b, v28.8b
+	eor	v4.8b, v4.8b, v29.8b
+	eor	v5.8b, v5.8b, v30.8b
+	eor	v6.8b, v6.8b, v31.8b
+
+	tbnz	x22, #6, 3f		// SHA3-512
+
+	ld1	{v25.8b-v28.8b}, [x20], #32
+	ld1	{v29.8b-v30.8b}, [x20], #16
+	eor	 v7.8b,  v7.8b, v25.8b
+	eor	 v8.8b,  v8.8b, v26.8b
+	eor	 v9.8b,  v9.8b, v27.8b
+	eor	v10.8b, v10.8b, v28.8b
+	eor	v11.8b, v11.8b, v29.8b
+	eor	v12.8b, v12.8b, v30.8b
+
+	tbnz	x22, #4, 2f		// SHA3-384 or SHA3-224
+
+	// SHA3-256
+	ld1	{v25.8b-v28.8b}, [x20], #32
+	eor	v13.8b, v13.8b, v25.8b
+	eor	v14.8b, v14.8b, v26.8b
+	eor	v15.8b, v15.8b, v27.8b
+	eor	v16.8b, v16.8b, v28.8b
+	b	4f
+
+2:	tbz	x22, #2, 4f		// bit 2 cleared? SHA-384
+
+	// SHA3-224
+	ld1	{v25.8b-v28.8b}, [x20], #32
+	ld1	{v29.8b}, [x20], #8
+	eor	v13.8b, v13.8b, v25.8b
+	eor	v14.8b, v14.8b, v26.8b
+	eor	v15.8b, v15.8b, v27.8b
+	eor	v16.8b, v16.8b, v28.8b
+	eor	v17.8b, v17.8b, v29.8b
+	b	4f
+
+	// SHA3-512
+3:	ld1	{v25.8b-v26.8b}, [x20], #16
+	eor	 v7.8b,  v7.8b, v25.8b
+	eor	 v8.8b,  v8.8b, v26.8b
+
+4:	sub	w8, w8, #1
+
+	eor3	v29.16b,  v4.16b,  v9.16b, v14.16b
+	eor3	v26.16b,  v1.16b,  v6.16b, v11.16b
+	eor3	v28.16b,  v3.16b,  v8.16b, v13.16b
+	eor3	v25.16b,  v0.16b,  v5.16b, v10.16b
+	eor3	v27.16b,  v2.16b,  v7.16b, v12.16b
+	eor3	v29.16b, v29.16b, v19.16b, v24.16b
+	eor3	v26.16b, v26.16b, v16.16b, v21.16b
+	eor3	v28.16b, v28.16b, v18.16b, v23.16b
+	eor3	v25.16b, v25.16b, v15.16b, v20.16b
+	eor3	v27.16b, v27.16b, v17.16b, v22.16b
+
+	rax1	v30.2d, v29.2d, v26.2d	// bc[0]
+	rax1	v26.2d, v26.2d, v28.2d	// bc[2]
+	rax1	v28.2d, v28.2d, v25.2d	// bc[4]
+	rax1	v25.2d, v25.2d, v27.2d	// bc[1]
+	rax1	v27.2d, v27.2d, v29.2d	// bc[3]
+
+	eor	 v0.16b,  v0.16b, v30.16b
+	xar	 v29.2d,   v1.2d,  v25.2d, (64 - 1)
+	xar	  v1.2d,   v6.2d,  v25.2d, (64 - 44)
+	xar	  v6.2d,   v9.2d,  v28.2d, (64 - 20)
+	xar	  v9.2d,  v22.2d,  v26.2d, (64 - 61)
+	xar	 v22.2d,  v14.2d,  v28.2d, (64 - 39)
+	xar	 v14.2d,  v20.2d,  v30.2d, (64 - 18)
+	xar	 v31.2d,   v2.2d,  v26.2d, (64 - 62)
+	xar	  v2.2d,  v12.2d,  v26.2d, (64 - 43)
+	xar	 v12.2d,  v13.2d,  v27.2d, (64 - 25)
+	xar	 v13.2d,  v19.2d,  v28.2d, (64 - 8)
+	xar	 v19.2d,  v23.2d,  v27.2d, (64 - 56)
+	xar	 v23.2d,  v15.2d,  v30.2d, (64 - 41)
+	xar	 v15.2d,   v4.2d,  v28.2d, (64 - 27)
+	xar	 v28.2d,  v24.2d,  v28.2d, (64 - 14)
+	xar	 v24.2d,  v21.2d,  v25.2d, (64 - 2)
+	xar	  v8.2d,   v8.2d,  v27.2d, (64 - 55)
+	xar	  v4.2d,  v16.2d,  v25.2d, (64 - 45)
+	xar	 v16.2d,   v5.2d,  v30.2d, (64 - 36)
+	xar	  v5.2d,   v3.2d,  v27.2d, (64 - 28)
+	xar	 v27.2d,  v18.2d,  v27.2d, (64 - 21)
+	xar	  v3.2d,  v17.2d,  v26.2d, (64 - 15)
+	xar	 v25.2d,  v11.2d,  v25.2d, (64 - 10)
+	xar	 v26.2d,   v7.2d,  v26.2d, (64 - 6)
+	xar	 v30.2d,  v10.2d,  v30.2d, (64 - 3)
+
+	bcax	v20.16b, v31.16b, v22.16b,  v8.16b
+	bcax	v21.16b,  v8.16b, v23.16b, v22.16b
+	bcax	v22.16b, v22.16b, v24.16b, v23.16b
+	bcax	v23.16b, v23.16b, v31.16b, v24.16b
+	bcax	v24.16b, v24.16b,  v8.16b, v31.16b
+
+	ld1r	{v31.2d}, [x9], #8
+
+	bcax	v17.16b, v25.16b, v19.16b,  v3.16b
+	bcax	v18.16b,  v3.16b, v15.16b, v19.16b
+	bcax	v19.16b, v19.16b, v16.16b, v15.16b
+	bcax	v15.16b, v15.16b, v25.16b, v16.16b
+	bcax	v16.16b, v16.16b,  v3.16b, v25.16b
+
+	bcax	v10.16b, v29.16b, v12.16b, v26.16b
+	bcax	v11.16b, v26.16b, v13.16b, v12.16b
+	bcax	v12.16b, v12.16b, v14.16b, v13.16b
+	bcax	v13.16b, v13.16b, v29.16b, v14.16b
+	bcax	v14.16b, v14.16b, v26.16b, v29.16b
+
+	bcax	 v7.16b, v30.16b,  v9.16b,  v4.16b
+	bcax	 v8.16b,  v4.16b,  v5.16b,  v9.16b
+	bcax	 v9.16b,  v9.16b,  v6.16b,  v5.16b
+	bcax	 v5.16b,  v5.16b, v30.16b,  v6.16b
+	bcax	 v6.16b,  v6.16b,  v4.16b, v30.16b
+
+	bcax	 v3.16b, v27.16b,  v0.16b, v28.16b
+	bcax	 v4.16b, v28.16b,  v1.16b,  v0.16b
+	bcax	 v0.16b,  v0.16b,  v2.16b,  v1.16b
+	bcax	 v1.16b,  v1.16b, v27.16b,  v2.16b
+	bcax	 v2.16b,  v2.16b, v28.16b, v27.16b
+
+	eor	 v0.16b,  v0.16b, v31.16b
+
+	cbnz	w8, 4b
+	cbz	w21, 5f
+
+	if_will_cond_yield_neon
+	add	x8, x19, #32
+	st1	{ v0.1d- v3.1d}, [x19]
+	st1	{ v4.1d- v7.1d}, [x8], #32
+	st1	{ v8.1d-v11.1d}, [x8], #32
+	st1	{v12.1d-v15.1d}, [x8], #32
+	st1	{v16.1d-v19.1d}, [x8], #32
+	st1	{v20.1d-v23.1d}, [x8], #32
+	st1	{v24.1d}, [x8]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b	1b
+
+	/* save state */
+5:	st1	{ v0.1d- v3.1d}, [x19], #32
+	st1	{ v4.1d- v7.1d}, [x19], #32
+	st1	{ v8.1d-v11.1d}, [x19], #32
+	st1	{v12.1d-v15.1d}, [x19], #32
+	st1	{v16.1d-v19.1d}, [x19], #32
+	st1	{v20.1d-v23.1d}, [x19], #32
+	st1	{v24.1d}, [x19]
+	frame_pop
+	ret
+SYM_FUNC_END(sha3_ce_transform)
+
+	.section	".rodata", "a"
+	.align		8
+.Lsha3_rcon:
+	.quad	0x0000000000000001, 0x0000000000008082, 0x800000000000808a
+	.quad	0x8000000080008000, 0x000000000000808b, 0x0000000080000001
+	.quad	0x8000000080008081, 0x8000000000008009, 0x000000000000008a
+	.quad	0x0000000000000088, 0x0000000080008009, 0x000000008000000a
+	.quad	0x000000008000808b, 0x800000000000008b, 0x8000000000008089
+	.quad	0x8000000000008003, 0x8000000000008002, 0x8000000000000080
+	.quad	0x000000000000800a, 0x800000008000000a, 0x8000000080008081
+	.quad	0x8000000000008080, 0x0000000080000001, 0x8000000080008008
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
new file mode 100644
index 000000000..ddf7aca9f
--- /dev/null
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -0,0 +1,162 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sha3-ce-glue.c - core SHA-3 transform using v8.2 Crypto Extensions
+ *
+ * Copyright (C) 2018 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/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sha3.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA3 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha3-224");
+MODULE_ALIAS_CRYPTO("sha3-256");
+MODULE_ALIAS_CRYPTO("sha3-384");
+MODULE_ALIAS_CRYPTO("sha3-512");
+
+asmlinkage void sha3_ce_transform(u64 *st, const u8 *data, int blocks,
+				  int md_len);
+
+static int sha3_update(struct shash_desc *desc, const u8 *data,
+		       unsigned int len)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
+
+	if (!crypto_simd_usable())
+		return crypto_sha3_update(desc, data, len);
+
+	if ((sctx->partial + len) >= sctx->rsiz) {
+		int blocks;
+
+		if (sctx->partial) {
+			int p = sctx->rsiz - sctx->partial;
+
+			memcpy(sctx->buf + sctx->partial, data, p);
+			kernel_neon_begin();
+			sha3_ce_transform(sctx->st, sctx->buf, 1, digest_size);
+			kernel_neon_end();
+
+			data += p;
+			len -= p;
+			sctx->partial = 0;
+		}
+
+		blocks = len / sctx->rsiz;
+		len %= sctx->rsiz;
+
+		if (blocks) {
+			kernel_neon_begin();
+			sha3_ce_transform(sctx->st, data, blocks, digest_size);
+			kernel_neon_end();
+			data += blocks * sctx->rsiz;
+		}
+	}
+
+	if (len) {
+		memcpy(sctx->buf + sctx->partial, data, len);
+		sctx->partial += len;
+	}
+	return 0;
+}
+
+static int sha3_final(struct shash_desc *desc, u8 *out)
+{
+	struct sha3_state *sctx = shash_desc_ctx(desc);
+	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
+	__le64 *digest = (__le64 *)out;
+	int i;
+
+	if (!crypto_simd_usable())
+		return crypto_sha3_final(desc, out);
+
+	sctx->buf[sctx->partial++] = 0x06;
+	memset(sctx->buf + sctx->partial, 0, sctx->rsiz - sctx->partial);
+	sctx->buf[sctx->rsiz - 1] |= 0x80;
+
+	kernel_neon_begin();
+	sha3_ce_transform(sctx->st, sctx->buf, 1, digest_size);
+	kernel_neon_end();
+
+	for (i = 0; i < digest_size / 8; i++)
+		put_unaligned_le64(sctx->st[i], digest++);
+
+	if (digest_size & 4)
+		put_unaligned_le32(sctx->st[i], (__le32 *)digest);
+
+	*sctx = (struct sha3_state){};
+	return 0;
+}
+
+static struct shash_alg algs[] = { {
+	.digestsize		= SHA3_224_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= sha3_update,
+	.final			= sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-224",
+	.base.cra_driver_name	= "sha3-224-ce",
+	.base.cra_blocksize	= SHA3_224_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+}, {
+	.digestsize		= SHA3_256_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= sha3_update,
+	.final			= sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-256",
+	.base.cra_driver_name	= "sha3-256-ce",
+	.base.cra_blocksize	= SHA3_256_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+}, {
+	.digestsize		= SHA3_384_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= sha3_update,
+	.final			= sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-384",
+	.base.cra_driver_name	= "sha3-384-ce",
+	.base.cra_blocksize	= SHA3_384_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+}, {
+	.digestsize		= SHA3_512_DIGEST_SIZE,
+	.init			= crypto_sha3_init,
+	.update			= sha3_update,
+	.final			= sha3_final,
+	.descsize		= sizeof(struct sha3_state),
+	.base.cra_name		= "sha3-512",
+	.base.cra_driver_name	= "sha3-512-ce",
+	.base.cra_blocksize	= SHA3_512_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+} };
+
+static int __init sha3_neon_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha3_neon_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA3, sha3_neon_mod_init);
+module_exit(sha3_neon_mod_fini);
diff --git a/arch/arm64/crypto/sha512-armv8.pl b/arch/arm64/crypto/sha512-armv8.pl
new file mode 100644
index 000000000..2d8655d5b
--- /dev/null
+++ b/arch/arm64/crypto/sha512-armv8.pl
@@ -0,0 +1,786 @@
+#! /usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore 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.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
+
+# Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (the "License").  You may not use
+# this file except in compliance with the License.  You can obtain a copy
+# in the file LICENSE in the source distribution or at
+# https://www.openssl.org/source/license.html
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+#
+# SHA256/512 for ARMv8.
+#
+# Performance in cycles per processed byte and improvement coefficient
+# over code generated with "default" compiler:
+#
+#		SHA256-hw	SHA256(*)	SHA512
+# Apple A7	1.97		10.5 (+33%)	6.73 (-1%(**))
+# Cortex-A53	2.38		15.5 (+115%)	10.0 (+150%(***))
+# Cortex-A57	2.31		11.6 (+86%)	7.51 (+260%(***))
+# Denver	2.01		10.5 (+26%)	6.70 (+8%)
+# X-Gene			20.0 (+100%)	12.8 (+300%(***))
+# Mongoose	2.36		13.0 (+50%)	8.36 (+33%)
+#
+# (*)	Software SHA256 results are of lesser relevance, presented
+#	mostly for informational purposes.
+# (**)	The result is a trade-off: it's possible to improve it by
+#	10% (or by 1 cycle per round), but at the cost of 20% loss
+#	on Cortex-A53 (or by 4 cycles per round).
+# (***)	Super-impressive coefficients over gcc-generated code are
+#	indication of some compiler "pathology", most notably code
+#	generated with -mgeneral-regs-only is significanty faster
+#	and the gap is only 40-90%.
+#
+# October 2016.
+#
+# Originally it was reckoned that it makes no sense to implement NEON
+# version of SHA256 for 64-bit processors. This is because performance
+# improvement on most wide-spread Cortex-A5x processors was observed
+# to be marginal, same on Cortex-A53 and ~10% on A57. But then it was
+# observed that 32-bit NEON SHA256 performs significantly better than
+# 64-bit scalar version on *some* of the more recent processors. As
+# result 64-bit NEON version of SHA256 was added to provide best
+# all-round performance. For example it executes ~30% faster on X-Gene
+# and Mongoose. [For reference, NEON version of SHA512 is bound to
+# deliver much less improvement, likely *negative* on Cortex-A5x.
+# Which is why NEON support is limited to SHA256.]
+
+$output=pop;
+$flavour=pop;
+
+if ($flavour && $flavour ne "void") {
+    $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+    ( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
+    ( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open OUT,"| \"$^X\" $xlate $flavour $output";
+    *STDOUT=*OUT;
+} else {
+    open STDOUT,">$output";
+}
+
+if ($output =~ /512/) {
+	$BITS=512;
+	$SZ=8;
+	@Sigma0=(28,34,39);
+	@Sigma1=(14,18,41);
+	@sigma0=(1,  8, 7);
+	@sigma1=(19,61, 6);
+	$rounds=80;
+	$reg_t="x";
+} else {
+	$BITS=256;
+	$SZ=4;
+	@Sigma0=( 2,13,22);
+	@Sigma1=( 6,11,25);
+	@sigma0=( 7,18, 3);
+	@sigma1=(17,19,10);
+	$rounds=64;
+	$reg_t="w";
+}
+
+$func="sha${BITS}_block_data_order";
+
+($ctx,$inp,$num,$Ktbl)=map("x$_",(0..2,30));
+
+@X=map("$reg_t$_",(3..15,0..2));
+@V=($A,$B,$C,$D,$E,$F,$G,$H)=map("$reg_t$_",(20..27));
+($t0,$t1,$t2,$t3)=map("$reg_t$_",(16,17,19,28));
+
+sub BODY_00_xx {
+my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_;
+my $j=($i+1)&15;
+my ($T0,$T1,$T2)=(@X[($i-8)&15],@X[($i-9)&15],@X[($i-10)&15]);
+   $T0=@X[$i+3] if ($i<11);
+
+$code.=<<___	if ($i<16);
+#ifndef	__AARCH64EB__
+	rev	@X[$i],@X[$i]			// $i
+#endif
+___
+$code.=<<___	if ($i<13 && ($i&1));
+	ldp	@X[$i+1],@X[$i+2],[$inp],#2*$SZ
+___
+$code.=<<___	if ($i==13);
+	ldp	@X[14],@X[15],[$inp]
+___
+$code.=<<___	if ($i>=14);
+	ldr	@X[($i-11)&15],[sp,#`$SZ*(($i-11)%4)`]
+___
+$code.=<<___	if ($i>0 && $i<16);
+	add	$a,$a,$t1			// h+=Sigma0(a)
+___
+$code.=<<___	if ($i>=11);
+	str	@X[($i-8)&15],[sp,#`$SZ*(($i-8)%4)`]
+___
+# While ARMv8 specifies merged rotate-n-logical operation such as
+# 'eor x,y,z,ror#n', it was found to negatively affect performance
+# on Apple A7. The reason seems to be that it requires even 'y' to
+# be available earlier. This means that such merged instruction is
+# not necessarily best choice on critical path... On the other hand
+# Cortex-A5x handles merged instructions much better than disjoint
+# rotate and logical... See (**) footnote above.
+$code.=<<___	if ($i<15);
+	ror	$t0,$e,#$Sigma1[0]
+	add	$h,$h,$t2			// h+=K[i]
+	eor	$T0,$e,$e,ror#`$Sigma1[2]-$Sigma1[1]`
+	and	$t1,$f,$e
+	bic	$t2,$g,$e
+	add	$h,$h,@X[$i&15]			// h+=X[i]
+	orr	$t1,$t1,$t2			// Ch(e,f,g)
+	eor	$t2,$a,$b			// a^b, b^c in next round
+	eor	$t0,$t0,$T0,ror#$Sigma1[1]	// Sigma1(e)
+	ror	$T0,$a,#$Sigma0[0]
+	add	$h,$h,$t1			// h+=Ch(e,f,g)
+	eor	$t1,$a,$a,ror#`$Sigma0[2]-$Sigma0[1]`
+	add	$h,$h,$t0			// h+=Sigma1(e)
+	and	$t3,$t3,$t2			// (b^c)&=(a^b)
+	add	$d,$d,$h			// d+=h
+	eor	$t3,$t3,$b			// Maj(a,b,c)
+	eor	$t1,$T0,$t1,ror#$Sigma0[1]	// Sigma0(a)
+	add	$h,$h,$t3			// h+=Maj(a,b,c)
+	ldr	$t3,[$Ktbl],#$SZ		// *K++, $t2 in next round
+	//add	$h,$h,$t1			// h+=Sigma0(a)
+___
+$code.=<<___	if ($i>=15);
+	ror	$t0,$e,#$Sigma1[0]
+	add	$h,$h,$t2			// h+=K[i]
+	ror	$T1,@X[($j+1)&15],#$sigma0[0]
+	and	$t1,$f,$e
+	ror	$T2,@X[($j+14)&15],#$sigma1[0]
+	bic	$t2,$g,$e
+	ror	$T0,$a,#$Sigma0[0]
+	add	$h,$h,@X[$i&15]			// h+=X[i]
+	eor	$t0,$t0,$e,ror#$Sigma1[1]
+	eor	$T1,$T1,@X[($j+1)&15],ror#$sigma0[1]
+	orr	$t1,$t1,$t2			// Ch(e,f,g)
+	eor	$t2,$a,$b			// a^b, b^c in next round
+	eor	$t0,$t0,$e,ror#$Sigma1[2]	// Sigma1(e)
+	eor	$T0,$T0,$a,ror#$Sigma0[1]
+	add	$h,$h,$t1			// h+=Ch(e,f,g)
+	and	$t3,$t3,$t2			// (b^c)&=(a^b)
+	eor	$T2,$T2,@X[($j+14)&15],ror#$sigma1[1]
+	eor	$T1,$T1,@X[($j+1)&15],lsr#$sigma0[2]	// sigma0(X[i+1])
+	add	$h,$h,$t0			// h+=Sigma1(e)
+	eor	$t3,$t3,$b			// Maj(a,b,c)
+	eor	$t1,$T0,$a,ror#$Sigma0[2]	// Sigma0(a)
+	eor	$T2,$T2,@X[($j+14)&15],lsr#$sigma1[2]	// sigma1(X[i+14])
+	add	@X[$j],@X[$j],@X[($j+9)&15]
+	add	$d,$d,$h			// d+=h
+	add	$h,$h,$t3			// h+=Maj(a,b,c)
+	ldr	$t3,[$Ktbl],#$SZ		// *K++, $t2 in next round
+	add	@X[$j],@X[$j],$T1
+	add	$h,$h,$t1			// h+=Sigma0(a)
+	add	@X[$j],@X[$j],$T2
+___
+	($t2,$t3)=($t3,$t2);
+}
+
+$code.=<<___;
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+#endif
+
+.text
+
+.extern	OPENSSL_armcap_P
+.globl	$func
+.type	$func,%function
+.align	6
+$func:
+___
+$code.=<<___	if ($SZ==4);
+#ifndef	__KERNEL__
+# ifdef	__ILP32__
+	ldrsw	x16,.LOPENSSL_armcap_P
+# else
+	ldr	x16,.LOPENSSL_armcap_P
+# endif
+	adr	x17,.LOPENSSL_armcap_P
+	add	x16,x16,x17
+	ldr	w16,[x16]
+	tst	w16,#ARMV8_SHA256
+	b.ne	.Lv8_entry
+	tst	w16,#ARMV7_NEON
+	b.ne	.Lneon_entry
+#endif
+___
+$code.=<<___;
+	stp	x29,x30,[sp,#-128]!
+	add	x29,sp,#0
+
+	stp	x19,x20,[sp,#16]
+	stp	x21,x22,[sp,#32]
+	stp	x23,x24,[sp,#48]
+	stp	x25,x26,[sp,#64]
+	stp	x27,x28,[sp,#80]
+	sub	sp,sp,#4*$SZ
+
+	ldp	$A,$B,[$ctx]				// load context
+	ldp	$C,$D,[$ctx,#2*$SZ]
+	ldp	$E,$F,[$ctx,#4*$SZ]
+	add	$num,$inp,$num,lsl#`log(16*$SZ)/log(2)`	// end of input
+	ldp	$G,$H,[$ctx,#6*$SZ]
+	adr	$Ktbl,.LK$BITS
+	stp	$ctx,$num,[x29,#96]
+
+.Loop:
+	ldp	@X[0],@X[1],[$inp],#2*$SZ
+	ldr	$t2,[$Ktbl],#$SZ			// *K++
+	eor	$t3,$B,$C				// magic seed
+	str	$inp,[x29,#112]
+___
+for ($i=0;$i<16;$i++)	{ &BODY_00_xx($i,@V); unshift(@V,pop(@V)); }
+$code.=".Loop_16_xx:\n";
+for (;$i<32;$i++)	{ &BODY_00_xx($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	cbnz	$t2,.Loop_16_xx
+
+	ldp	$ctx,$num,[x29,#96]
+	ldr	$inp,[x29,#112]
+	sub	$Ktbl,$Ktbl,#`$SZ*($rounds+1)`		// rewind
+
+	ldp	@X[0],@X[1],[$ctx]
+	ldp	@X[2],@X[3],[$ctx,#2*$SZ]
+	add	$inp,$inp,#14*$SZ			// advance input pointer
+	ldp	@X[4],@X[5],[$ctx,#4*$SZ]
+	add	$A,$A,@X[0]
+	ldp	@X[6],@X[7],[$ctx,#6*$SZ]
+	add	$B,$B,@X[1]
+	add	$C,$C,@X[2]
+	add	$D,$D,@X[3]
+	stp	$A,$B,[$ctx]
+	add	$E,$E,@X[4]
+	add	$F,$F,@X[5]
+	stp	$C,$D,[$ctx,#2*$SZ]
+	add	$G,$G,@X[6]
+	add	$H,$H,@X[7]
+	cmp	$inp,$num
+	stp	$E,$F,[$ctx,#4*$SZ]
+	stp	$G,$H,[$ctx,#6*$SZ]
+	b.ne	.Loop
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#4*$SZ
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#128
+	ret
+.size	$func,.-$func
+
+.align	6
+.type	.LK$BITS,%object
+.LK$BITS:
+___
+$code.=<<___ if ($SZ==8);
+	.quad	0x428a2f98d728ae22,0x7137449123ef65cd
+	.quad	0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
+	.quad	0x3956c25bf348b538,0x59f111f1b605d019
+	.quad	0x923f82a4af194f9b,0xab1c5ed5da6d8118
+	.quad	0xd807aa98a3030242,0x12835b0145706fbe
+	.quad	0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
+	.quad	0x72be5d74f27b896f,0x80deb1fe3b1696b1
+	.quad	0x9bdc06a725c71235,0xc19bf174cf692694
+	.quad	0xe49b69c19ef14ad2,0xefbe4786384f25e3
+	.quad	0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
+	.quad	0x2de92c6f592b0275,0x4a7484aa6ea6e483
+	.quad	0x5cb0a9dcbd41fbd4,0x76f988da831153b5
+	.quad	0x983e5152ee66dfab,0xa831c66d2db43210
+	.quad	0xb00327c898fb213f,0xbf597fc7beef0ee4
+	.quad	0xc6e00bf33da88fc2,0xd5a79147930aa725
+	.quad	0x06ca6351e003826f,0x142929670a0e6e70
+	.quad	0x27b70a8546d22ffc,0x2e1b21385c26c926
+	.quad	0x4d2c6dfc5ac42aed,0x53380d139d95b3df
+	.quad	0x650a73548baf63de,0x766a0abb3c77b2a8
+	.quad	0x81c2c92e47edaee6,0x92722c851482353b
+	.quad	0xa2bfe8a14cf10364,0xa81a664bbc423001
+	.quad	0xc24b8b70d0f89791,0xc76c51a30654be30
+	.quad	0xd192e819d6ef5218,0xd69906245565a910
+	.quad	0xf40e35855771202a,0x106aa07032bbd1b8
+	.quad	0x19a4c116b8d2d0c8,0x1e376c085141ab53
+	.quad	0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
+	.quad	0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
+	.quad	0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
+	.quad	0x748f82ee5defb2fc,0x78a5636f43172f60
+	.quad	0x84c87814a1f0ab72,0x8cc702081a6439ec
+	.quad	0x90befffa23631e28,0xa4506cebde82bde9
+	.quad	0xbef9a3f7b2c67915,0xc67178f2e372532b
+	.quad	0xca273eceea26619c,0xd186b8c721c0c207
+	.quad	0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
+	.quad	0x06f067aa72176fba,0x0a637dc5a2c898a6
+	.quad	0x113f9804bef90dae,0x1b710b35131c471b
+	.quad	0x28db77f523047d84,0x32caab7b40c72493
+	.quad	0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
+	.quad	0x4cc5d4becb3e42b6,0x597f299cfc657e2a
+	.quad	0x5fcb6fab3ad6faec,0x6c44198c4a475817
+	.quad	0	// terminator
+___
+$code.=<<___ if ($SZ==4);
+	.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
+	.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
+	.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
+	.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
+	.long	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
+	.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
+	.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
+	.long	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
+	.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
+	.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
+	.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
+	.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
+	.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
+	.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
+	.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
+	.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
+	.long	0	//terminator
+___
+$code.=<<___;
+.size	.LK$BITS,.-.LK$BITS
+#ifndef	__KERNEL__
+.align	3
+.LOPENSSL_armcap_P:
+# ifdef	__ILP32__
+	.long	OPENSSL_armcap_P-.
+# else
+	.quad	OPENSSL_armcap_P-.
+# endif
+#endif
+.asciz	"SHA$BITS block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
+.align	2
+___
+
+if ($SZ==4) {
+my $Ktbl="x3";
+
+my ($ABCD,$EFGH,$abcd)=map("v$_.16b",(0..2));
+my @MSG=map("v$_.16b",(4..7));
+my ($W0,$W1)=("v16.4s","v17.4s");
+my ($ABCD_SAVE,$EFGH_SAVE)=("v18.16b","v19.16b");
+
+$code.=<<___;
+#ifndef	__KERNEL__
+.type	sha256_block_armv8,%function
+.align	6
+sha256_block_armv8:
+.Lv8_entry:
+	stp		x29,x30,[sp,#-16]!
+	add		x29,sp,#0
+
+	ld1.32		{$ABCD,$EFGH},[$ctx]
+	adr		$Ktbl,.LK256
+
+.Loop_hw:
+	ld1		{@MSG[0]-@MSG[3]},[$inp],#64
+	sub		$num,$num,#1
+	ld1.32		{$W0},[$Ktbl],#16
+	rev32		@MSG[0],@MSG[0]
+	rev32		@MSG[1],@MSG[1]
+	rev32		@MSG[2],@MSG[2]
+	rev32		@MSG[3],@MSG[3]
+	orr		$ABCD_SAVE,$ABCD,$ABCD		// offload
+	orr		$EFGH_SAVE,$EFGH,$EFGH
+___
+for($i=0;$i<12;$i++) {
+$code.=<<___;
+	ld1.32		{$W1},[$Ktbl],#16
+	add.i32		$W0,$W0,@MSG[0]
+	sha256su0	@MSG[0],@MSG[1]
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+	sha256su1	@MSG[0],@MSG[2],@MSG[3]
+___
+	($W0,$W1)=($W1,$W0);	push(@MSG,shift(@MSG));
+}
+$code.=<<___;
+	ld1.32		{$W1},[$Ktbl],#16
+	add.i32		$W0,$W0,@MSG[0]
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+
+	ld1.32		{$W0},[$Ktbl],#16
+	add.i32		$W1,$W1,@MSG[1]
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W1
+	sha256h2	$EFGH,$abcd,$W1
+
+	ld1.32		{$W1},[$Ktbl]
+	add.i32		$W0,$W0,@MSG[2]
+	sub		$Ktbl,$Ktbl,#$rounds*$SZ-16	// rewind
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W0
+	sha256h2	$EFGH,$abcd,$W0
+
+	add.i32		$W1,$W1,@MSG[3]
+	orr		$abcd,$ABCD,$ABCD
+	sha256h		$ABCD,$EFGH,$W1
+	sha256h2	$EFGH,$abcd,$W1
+
+	add.i32		$ABCD,$ABCD,$ABCD_SAVE
+	add.i32		$EFGH,$EFGH,$EFGH_SAVE
+
+	cbnz		$num,.Loop_hw
+
+	st1.32		{$ABCD,$EFGH},[$ctx]
+
+	ldr		x29,[sp],#16
+	ret
+.size	sha256_block_armv8,.-sha256_block_armv8
+#endif
+___
+}
+
+if ($SZ==4) {	######################################### NEON stuff #
+# You'll surely note a lot of similarities with sha256-armv4 module,
+# and of course it's not a coincidence. sha256-armv4 was used as
+# initial template, but was adapted for ARMv8 instruction set and
+# extensively re-tuned for all-round performance.
+
+my @V = ($A,$B,$C,$D,$E,$F,$G,$H) = map("w$_",(3..10));
+my ($t0,$t1,$t2,$t3,$t4) = map("w$_",(11..15));
+my $Ktbl="x16";
+my $Xfer="x17";
+my @X = map("q$_",(0..3));
+my ($T0,$T1,$T2,$T3,$T4,$T5,$T6,$T7) = map("q$_",(4..7,16..19));
+my $j=0;
+
+sub AUTOLOAD()          # thunk [simplified] x86-style perlasm
+{ my $opcode = $AUTOLOAD; $opcode =~ s/.*:://; $opcode =~ s/_/\./;
+  my $arg = pop;
+    $arg = "#$arg" if ($arg*1 eq $arg);
+    $code .= "\t$opcode\t".join(',',@_,$arg)."\n";
+}
+
+sub Dscalar { shift =~ m|[qv]([0-9]+)|?"d$1":""; }
+sub Dlo     { shift =~ m|[qv]([0-9]+)|?"v$1.d[0]":""; }
+sub Dhi     { shift =~ m|[qv]([0-9]+)|?"v$1.d[1]":""; }
+
+sub Xupdate()
+{ use integer;
+  my $body = shift;
+  my @insns = (&$body,&$body,&$body,&$body);
+  my ($a,$b,$c,$d,$e,$f,$g,$h);
+
+	&ext_8		($T0,@X[0],@X[1],4);	# X[1..4]
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&ext_8		($T3,@X[2],@X[3],4);	# X[9..12]
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&mov		(&Dscalar($T7),&Dhi(@X[3]));	# X[14..15]
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&ushr_32	($T2,$T0,$sigma0[0]);
+	 eval(shift(@insns));
+	&ushr_32	($T1,$T0,$sigma0[2]);
+	 eval(shift(@insns));
+	&add_32 	(@X[0],@X[0],$T3);	# X[0..3] += X[9..12]
+	 eval(shift(@insns));
+	&sli_32		($T2,$T0,32-$sigma0[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&ushr_32	($T3,$T0,$sigma0[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&eor_8		($T1,$T1,$T2);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&sli_32		($T3,$T0,32-$sigma0[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &ushr_32	($T4,$T7,$sigma1[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&eor_8		($T1,$T1,$T3);		# sigma0(X[1..4])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &sli_32	($T4,$T7,32-$sigma1[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &ushr_32	($T5,$T7,$sigma1[2]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &ushr_32	($T3,$T7,$sigma1[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&add_32		(@X[0],@X[0],$T1);	# X[0..3] += sigma0(X[1..4])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &sli_u32	($T3,$T7,32-$sigma1[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &eor_8	($T5,$T5,$T4);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &eor_8	($T5,$T5,$T3);		# sigma1(X[14..15])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&add_32		(@X[0],@X[0],$T5);	# X[0..1] += sigma1(X[14..15])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &ushr_32	($T6,@X[0],$sigma1[0]);
+	 eval(shift(@insns));
+	  &ushr_32	($T7,@X[0],$sigma1[2]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &sli_32	($T6,@X[0],32-$sigma1[0]);
+	 eval(shift(@insns));
+	  &ushr_32	($T5,@X[0],$sigma1[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &eor_8	($T7,$T7,$T6);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	  &sli_32	($T5,@X[0],32-$sigma1[1]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&ld1_32		("{$T0}","[$Ktbl], #16");
+	 eval(shift(@insns));
+	  &eor_8	($T7,$T7,$T5);		# sigma1(X[16..17])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&eor_8		($T5,$T5,$T5);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&mov		(&Dhi($T5), &Dlo($T7));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&add_32		(@X[0],@X[0],$T5);	# X[2..3] += sigma1(X[16..17])
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&add_32		($T0,$T0,@X[0]);
+	 while($#insns>=1) { eval(shift(@insns)); }
+	&st1_32		("{$T0}","[$Xfer], #16");
+	 eval(shift(@insns));
+
+	push(@X,shift(@X));		# "rotate" X[]
+}
+
+sub Xpreload()
+{ use integer;
+  my $body = shift;
+  my @insns = (&$body,&$body,&$body,&$body);
+  my ($a,$b,$c,$d,$e,$f,$g,$h);
+
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&ld1_8		("{@X[0]}","[$inp],#16");
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&ld1_32		("{$T0}","[$Ktbl],#16");
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&rev32		(@X[0],@X[0]);
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	 eval(shift(@insns));
+	&add_32		($T0,$T0,@X[0]);
+	 foreach (@insns) { eval; }	# remaining instructions
+	&st1_32		("{$T0}","[$Xfer], #16");
+
+	push(@X,shift(@X));		# "rotate" X[]
+}
+
+sub body_00_15 () {
+	(
+	'($a,$b,$c,$d,$e,$f,$g,$h)=@V;'.
+	'&add	($h,$h,$t1)',			# h+=X[i]+K[i]
+	'&add	($a,$a,$t4);'.			# h+=Sigma0(a) from the past
+	'&and	($t1,$f,$e)',
+	'&bic	($t4,$g,$e)',
+	'&eor	($t0,$e,$e,"ror#".($Sigma1[1]-$Sigma1[0]))',
+	'&add	($a,$a,$t2)',			# h+=Maj(a,b,c) from the past
+	'&orr	($t1,$t1,$t4)',			# Ch(e,f,g)
+	'&eor	($t0,$t0,$e,"ror#".($Sigma1[2]-$Sigma1[0]))',	# Sigma1(e)
+	'&eor	($t4,$a,$a,"ror#".($Sigma0[1]-$Sigma0[0]))',
+	'&add	($h,$h,$t1)',			# h+=Ch(e,f,g)
+	'&ror	($t0,$t0,"#$Sigma1[0]")',
+	'&eor	($t2,$a,$b)',			# a^b, b^c in next round
+	'&eor	($t4,$t4,$a,"ror#".($Sigma0[2]-$Sigma0[0]))',	# Sigma0(a)
+	'&add	($h,$h,$t0)',			# h+=Sigma1(e)
+	'&ldr	($t1,sprintf "[sp,#%d]",4*(($j+1)&15))	if (($j&15)!=15);'.
+	'&ldr	($t1,"[$Ktbl]")				if ($j==15);'.
+	'&and	($t3,$t3,$t2)',			# (b^c)&=(a^b)
+	'&ror	($t4,$t4,"#$Sigma0[0]")',
+	'&add	($d,$d,$h)',			# d+=h
+	'&eor	($t3,$t3,$b)',			# Maj(a,b,c)
+	'$j++;	unshift(@V,pop(@V)); ($t2,$t3)=($t3,$t2);'
+	)
+}
+
+$code.=<<___;
+#ifdef	__KERNEL__
+.globl	sha256_block_neon
+#endif
+.type	sha256_block_neon,%function
+.align	4
+sha256_block_neon:
+.Lneon_entry:
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+	sub	sp,sp,#16*4
+
+	adr	$Ktbl,.LK256
+	add	$num,$inp,$num,lsl#6	// len to point at the end of inp
+
+	ld1.8	{@X[0]},[$inp], #16
+	ld1.8	{@X[1]},[$inp], #16
+	ld1.8	{@X[2]},[$inp], #16
+	ld1.8	{@X[3]},[$inp], #16
+	ld1.32	{$T0},[$Ktbl], #16
+	ld1.32	{$T1},[$Ktbl], #16
+	ld1.32	{$T2},[$Ktbl], #16
+	ld1.32	{$T3},[$Ktbl], #16
+	rev32	@X[0],@X[0]		// yes, even on
+	rev32	@X[1],@X[1]		// big-endian
+	rev32	@X[2],@X[2]
+	rev32	@X[3],@X[3]
+	mov	$Xfer,sp
+	add.32	$T0,$T0,@X[0]
+	add.32	$T1,$T1,@X[1]
+	add.32	$T2,$T2,@X[2]
+	st1.32	{$T0-$T1},[$Xfer], #32
+	add.32	$T3,$T3,@X[3]
+	st1.32	{$T2-$T3},[$Xfer]
+	sub	$Xfer,$Xfer,#32
+
+	ldp	$A,$B,[$ctx]
+	ldp	$C,$D,[$ctx,#8]
+	ldp	$E,$F,[$ctx,#16]
+	ldp	$G,$H,[$ctx,#24]
+	ldr	$t1,[sp,#0]
+	mov	$t2,wzr
+	eor	$t3,$B,$C
+	mov	$t4,wzr
+	b	.L_00_48
+
+.align	4
+.L_00_48:
+___
+	&Xupdate(\&body_00_15);
+	&Xupdate(\&body_00_15);
+	&Xupdate(\&body_00_15);
+	&Xupdate(\&body_00_15);
+$code.=<<___;
+	cmp	$t1,#0				// check for K256 terminator
+	ldr	$t1,[sp,#0]
+	sub	$Xfer,$Xfer,#64
+	bne	.L_00_48
+
+	sub	$Ktbl,$Ktbl,#256		// rewind $Ktbl
+	cmp	$inp,$num
+	mov	$Xfer, #64
+	csel	$Xfer, $Xfer, xzr, eq
+	sub	$inp,$inp,$Xfer			// avoid SEGV
+	mov	$Xfer,sp
+___
+	&Xpreload(\&body_00_15);
+	&Xpreload(\&body_00_15);
+	&Xpreload(\&body_00_15);
+	&Xpreload(\&body_00_15);
+$code.=<<___;
+	add	$A,$A,$t4			// h+=Sigma0(a) from the past
+	ldp	$t0,$t1,[$ctx,#0]
+	add	$A,$A,$t2			// h+=Maj(a,b,c) from the past
+	ldp	$t2,$t3,[$ctx,#8]
+	add	$A,$A,$t0			// accumulate
+	add	$B,$B,$t1
+	ldp	$t0,$t1,[$ctx,#16]
+	add	$C,$C,$t2
+	add	$D,$D,$t3
+	ldp	$t2,$t3,[$ctx,#24]
+	add	$E,$E,$t0
+	add	$F,$F,$t1
+	 ldr	$t1,[sp,#0]
+	stp	$A,$B,[$ctx,#0]
+	add	$G,$G,$t2
+	 mov	$t2,wzr
+	stp	$C,$D,[$ctx,#8]
+	add	$H,$H,$t3
+	stp	$E,$F,[$ctx,#16]
+	 eor	$t3,$B,$C
+	stp	$G,$H,[$ctx,#24]
+	 mov	$t4,wzr
+	 mov	$Xfer,sp
+	b.ne	.L_00_48
+
+	ldr	x29,[x29]
+	add	sp,sp,#16*4+16
+	ret
+.size	sha256_block_neon,.-sha256_block_neon
+___
+}
+
+$code.=<<___;
+#ifndef	__KERNEL__
+.comm	OPENSSL_armcap_P,4,4
+#endif
+___
+
+{   my  %opcode = (
+	"sha256h"	=> 0x5e004000,	"sha256h2"	=> 0x5e005000,
+	"sha256su0"	=> 0x5e282800,	"sha256su1"	=> 0x5e006000	);
+
+    sub unsha256 {
+	my ($mnemonic,$arg)=@_;
+
+	$arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)[^,]*(?:,\s*[qv]([0-9]+))?/o
+	&&
+	sprintf ".inst\t0x%08x\t//%s %s",
+			$opcode{$mnemonic}|$1|($2<<5)|($3<<16),
+			$mnemonic,$arg;
+    }
+}
+
+open SELF,$0;
+while(<SELF>) {
+        next if (/^#!/);
+        last if (!s/^#/\/\// and !/^$/);
+        print;
+}
+close SELF;
+
+foreach(split("\n",$code)) {
+
+	s/\`([^\`]*)\`/eval($1)/ge;
+
+	s/\b(sha256\w+)\s+([qv].*)/unsha256($1,$2)/ge;
+
+	s/\bq([0-9]+)\b/v$1.16b/g;		# old->new registers
+
+	s/\.[ui]?8(\s)/$1/;
+	s/\.\w?32\b//		and s/\.16b/\.4s/g;
+	m/(ld|st)1[^\[]+\[0\]/	and s/\.4s/\.s/g;
+
+	print $_,"\n";
+}
+
+close STDOUT;
diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S
new file mode 100644
index 000000000..cde606c03
--- /dev/null
+++ b/arch/arm64/crypto/sha512-ce-core.S
@@ -0,0 +1,219 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sha512-ce-core.S - core SHA-384/SHA-512 transform using v8 Crypto Extensions
+ *
+ * Copyright (C) 2018 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>
+
+	.irp		b,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19
+	.set		.Lq\b, \b
+	.set		.Lv\b\().2d, \b
+	.endr
+
+	.macro		sha512h, rd, rn, rm
+	.inst		0xce608000 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro		sha512h2, rd, rn, rm
+	.inst		0xce608400 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro		sha512su0, rd, rn
+	.inst		0xcec08000 | .L\rd | (.L\rn << 5)
+	.endm
+
+	.macro		sha512su1, rd, rn, rm
+	.inst		0xce608800 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	/*
+	 * The SHA-512 round constants
+	 */
+	.section	".rodata", "a"
+	.align		4
+.Lsha512_rcon:
+	.quad		0x428a2f98d728ae22, 0x7137449123ef65cd
+	.quad		0xb5c0fbcfec4d3b2f, 0xe9b5dba58189dbbc
+	.quad		0x3956c25bf348b538, 0x59f111f1b605d019
+	.quad		0x923f82a4af194f9b, 0xab1c5ed5da6d8118
+	.quad		0xd807aa98a3030242, 0x12835b0145706fbe
+	.quad		0x243185be4ee4b28c, 0x550c7dc3d5ffb4e2
+	.quad		0x72be5d74f27b896f, 0x80deb1fe3b1696b1
+	.quad		0x9bdc06a725c71235, 0xc19bf174cf692694
+	.quad		0xe49b69c19ef14ad2, 0xefbe4786384f25e3
+	.quad		0x0fc19dc68b8cd5b5, 0x240ca1cc77ac9c65
+	.quad		0x2de92c6f592b0275, 0x4a7484aa6ea6e483
+	.quad		0x5cb0a9dcbd41fbd4, 0x76f988da831153b5
+	.quad		0x983e5152ee66dfab, 0xa831c66d2db43210
+	.quad		0xb00327c898fb213f, 0xbf597fc7beef0ee4
+	.quad		0xc6e00bf33da88fc2, 0xd5a79147930aa725
+	.quad		0x06ca6351e003826f, 0x142929670a0e6e70
+	.quad		0x27b70a8546d22ffc, 0x2e1b21385c26c926
+	.quad		0x4d2c6dfc5ac42aed, 0x53380d139d95b3df
+	.quad		0x650a73548baf63de, 0x766a0abb3c77b2a8
+	.quad		0x81c2c92e47edaee6, 0x92722c851482353b
+	.quad		0xa2bfe8a14cf10364, 0xa81a664bbc423001
+	.quad		0xc24b8b70d0f89791, 0xc76c51a30654be30
+	.quad		0xd192e819d6ef5218, 0xd69906245565a910
+	.quad		0xf40e35855771202a, 0x106aa07032bbd1b8
+	.quad		0x19a4c116b8d2d0c8, 0x1e376c085141ab53
+	.quad		0x2748774cdf8eeb99, 0x34b0bcb5e19b48a8
+	.quad		0x391c0cb3c5c95a63, 0x4ed8aa4ae3418acb
+	.quad		0x5b9cca4f7763e373, 0x682e6ff3d6b2b8a3
+	.quad		0x748f82ee5defb2fc, 0x78a5636f43172f60
+	.quad		0x84c87814a1f0ab72, 0x8cc702081a6439ec
+	.quad		0x90befffa23631e28, 0xa4506cebde82bde9
+	.quad		0xbef9a3f7b2c67915, 0xc67178f2e372532b
+	.quad		0xca273eceea26619c, 0xd186b8c721c0c207
+	.quad		0xeada7dd6cde0eb1e, 0xf57d4f7fee6ed178
+	.quad		0x06f067aa72176fba, 0x0a637dc5a2c898a6
+	.quad		0x113f9804bef90dae, 0x1b710b35131c471b
+	.quad		0x28db77f523047d84, 0x32caab7b40c72493
+	.quad		0x3c9ebe0a15c9bebc, 0x431d67c49c100d4c
+	.quad		0x4cc5d4becb3e42b6, 0x597f299cfc657e2a
+	.quad		0x5fcb6fab3ad6faec, 0x6c44198c4a475817
+
+	.macro		dround, i0, i1, i2, i3, i4, rc0, rc1, in0, in1, in2, in3, in4
+	.ifnb		\rc1
+	ld1		{v\rc1\().2d}, [x4], #16
+	.endif
+	add		v5.2d, v\rc0\().2d, v\in0\().2d
+	ext		v6.16b, v\i2\().16b, v\i3\().16b, #8
+	ext		v5.16b, v5.16b, v5.16b, #8
+	ext		v7.16b, v\i1\().16b, v\i2\().16b, #8
+	add		v\i3\().2d, v\i3\().2d, v5.2d
+	.ifnb		\in1
+	ext		v5.16b, v\in3\().16b, v\in4\().16b, #8
+	sha512su0	v\in0\().2d, v\in1\().2d
+	.endif
+	sha512h		q\i3, q6, v7.2d
+	.ifnb		\in1
+	sha512su1	v\in0\().2d, v\in2\().2d, v5.2d
+	.endif
+	add		v\i4\().2d, v\i1\().2d, v\i3\().2d
+	sha512h2	q\i3, q\i1, v\i0\().2d
+	.endm
+
+	/*
+	 * void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
+	 *			  int blocks)
+	 */
+	.text
+SYM_FUNC_START(sha512_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
+	/* load state */
+0:	ld1		{v8.2d-v11.2d}, [x19]
+
+	/* load first 4 round constants */
+	adr_l		x3, .Lsha512_rcon
+	ld1		{v20.2d-v23.2d}, [x3], #64
+
+	/* load input */
+1:	ld1		{v12.2d-v15.2d}, [x20], #64
+	ld1		{v16.2d-v19.2d}, [x20], #64
+	sub		w21, w21, #1
+
+CPU_LE(	rev64		v12.16b, v12.16b	)
+CPU_LE(	rev64		v13.16b, v13.16b	)
+CPU_LE(	rev64		v14.16b, v14.16b	)
+CPU_LE(	rev64		v15.16b, v15.16b	)
+CPU_LE(	rev64		v16.16b, v16.16b	)
+CPU_LE(	rev64		v17.16b, v17.16b	)
+CPU_LE(	rev64		v18.16b, v18.16b	)
+CPU_LE(	rev64		v19.16b, v19.16b	)
+
+	mov		x4, x3				// rc pointer
+
+	mov		v0.16b, v8.16b
+	mov		v1.16b, v9.16b
+	mov		v2.16b, v10.16b
+	mov		v3.16b, v11.16b
+
+	// v0  ab  cd  --  ef  gh  ab
+	// v1  cd  --  ef  gh  ab  cd
+	// v2  ef  gh  ab  cd  --  ef
+	// v3  gh  ab  cd  --  ef  gh
+	// v4  --  ef  gh  ab  cd  --
+
+	dround		0, 1, 2, 3, 4, 20, 24, 12, 13, 19, 16, 17
+	dround		3, 0, 4, 2, 1, 21, 25, 13, 14, 12, 17, 18
+	dround		2, 3, 1, 4, 0, 22, 26, 14, 15, 13, 18, 19
+	dround		4, 2, 0, 1, 3, 23, 27, 15, 16, 14, 19, 12
+	dround		1, 4, 3, 0, 2, 24, 28, 16, 17, 15, 12, 13
+
+	dround		0, 1, 2, 3, 4, 25, 29, 17, 18, 16, 13, 14
+	dround		3, 0, 4, 2, 1, 26, 30, 18, 19, 17, 14, 15
+	dround		2, 3, 1, 4, 0, 27, 31, 19, 12, 18, 15, 16
+	dround		4, 2, 0, 1, 3, 28, 24, 12, 13, 19, 16, 17
+	dround		1, 4, 3, 0, 2, 29, 25, 13, 14, 12, 17, 18
+
+	dround		0, 1, 2, 3, 4, 30, 26, 14, 15, 13, 18, 19
+	dround		3, 0, 4, 2, 1, 31, 27, 15, 16, 14, 19, 12
+	dround		2, 3, 1, 4, 0, 24, 28, 16, 17, 15, 12, 13
+	dround		4, 2, 0, 1, 3, 25, 29, 17, 18, 16, 13, 14
+	dround		1, 4, 3, 0, 2, 26, 30, 18, 19, 17, 14, 15
+
+	dround		0, 1, 2, 3, 4, 27, 31, 19, 12, 18, 15, 16
+	dround		3, 0, 4, 2, 1, 28, 24, 12, 13, 19, 16, 17
+	dround		2, 3, 1, 4, 0, 29, 25, 13, 14, 12, 17, 18
+	dround		4, 2, 0, 1, 3, 30, 26, 14, 15, 13, 18, 19
+	dround		1, 4, 3, 0, 2, 31, 27, 15, 16, 14, 19, 12
+
+	dround		0, 1, 2, 3, 4, 24, 28, 16, 17, 15, 12, 13
+	dround		3, 0, 4, 2, 1, 25, 29, 17, 18, 16, 13, 14
+	dround		2, 3, 1, 4, 0, 26, 30, 18, 19, 17, 14, 15
+	dround		4, 2, 0, 1, 3, 27, 31, 19, 12, 18, 15, 16
+	dround		1, 4, 3, 0, 2, 28, 24, 12, 13, 19, 16, 17
+
+	dround		0, 1, 2, 3, 4, 29, 25, 13, 14, 12, 17, 18
+	dround		3, 0, 4, 2, 1, 30, 26, 14, 15, 13, 18, 19
+	dround		2, 3, 1, 4, 0, 31, 27, 15, 16, 14, 19, 12
+	dround		4, 2, 0, 1, 3, 24, 28, 16, 17, 15, 12, 13
+	dround		1, 4, 3, 0, 2, 25, 29, 17, 18, 16, 13, 14
+
+	dround		0, 1, 2, 3, 4, 26, 30, 18, 19, 17, 14, 15
+	dround		3, 0, 4, 2, 1, 27, 31, 19, 12, 18, 15, 16
+	dround		2, 3, 1, 4, 0, 28, 24, 12
+	dround		4, 2, 0, 1, 3, 29, 25, 13
+	dround		1, 4, 3, 0, 2, 30, 26, 14
+
+	dround		0, 1, 2, 3, 4, 31, 27, 15
+	dround		3, 0, 4, 2, 1, 24,   , 16
+	dround		2, 3, 1, 4, 0, 25,   , 17
+	dround		4, 2, 0, 1, 3, 26,   , 18
+	dround		1, 4, 3, 0, 2, 27,   , 19
+
+	/* update state */
+	add		v8.2d, v8.2d, v0.2d
+	add		v9.2d, v9.2d, v1.2d
+	add		v10.2d, v10.2d, v2.2d
+	add		v11.2d, v11.2d, v3.2d
+
+	/* handled all input blocks? */
+	cbz		w21, 3f
+
+	if_will_cond_yield_neon
+	st1		{v8.2d-v11.2d}, [x19]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b		1b
+
+	/* store new state */
+3:	st1		{v8.2d-v11.2d}, [x19]
+	frame_pop
+	ret
+SYM_FUNC_END(sha512_ce_transform)
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
new file mode 100644
index 000000000..57c6f086d
--- /dev/null
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -0,0 +1,122 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * sha512-ce-glue.c - SHA-384/SHA-512 using ARMv8 Crypto Extensions
+ *
+ * Copyright (C) 2018 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/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+
+asmlinkage void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
+				    int blocks);
+
+asmlinkage void sha512_block_data_order(u64 *digest, u8 const *src, int blocks);
+
+static void __sha512_block_data_order(struct sha512_state *sst, u8 const *src,
+				      int blocks)
+{
+	sha512_block_data_order(sst->state, src, blocks);
+}
+
+static int sha512_ce_update(struct shash_desc *desc, const u8 *data,
+			    unsigned int len)
+{
+	if (!crypto_simd_usable())
+		return sha512_base_do_update(desc, data, len,
+					     __sha512_block_data_order);
+
+	kernel_neon_begin();
+	sha512_base_do_update(desc, data, len, sha512_ce_transform);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
+			   unsigned int len, u8 *out)
+{
+	if (!crypto_simd_usable()) {
+		if (len)
+			sha512_base_do_update(desc, data, len,
+					      __sha512_block_data_order);
+		sha512_base_do_finalize(desc, __sha512_block_data_order);
+		return sha512_base_finish(desc, out);
+	}
+
+	kernel_neon_begin();
+	sha512_base_do_update(desc, data, len, sha512_ce_transform);
+	sha512_base_do_finalize(desc, sha512_ce_transform);
+	kernel_neon_end();
+	return sha512_base_finish(desc, out);
+}
+
+static int sha512_ce_final(struct shash_desc *desc, u8 *out)
+{
+	if (!crypto_simd_usable()) {
+		sha512_base_do_finalize(desc, __sha512_block_data_order);
+		return sha512_base_finish(desc, out);
+	}
+
+	kernel_neon_begin();
+	sha512_base_do_finalize(desc, sha512_ce_transform);
+	kernel_neon_end();
+	return sha512_base_finish(desc, out);
+}
+
+static struct shash_alg algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_ce_update,
+	.final			= sha512_ce_final,
+	.finup			= sha512_ce_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base.cra_name		= "sha384",
+	.base.cra_driver_name	= "sha384-ce",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.init			= sha512_base_init,
+	.update			= sha512_ce_update,
+	.final			= sha512_ce_final,
+	.finup			= sha512_ce_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base.cra_name		= "sha512",
+	.base.cra_driver_name	= "sha512-ce",
+	.base.cra_priority	= 200,
+	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+} };
+
+static int __init sha512_ce_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha512_ce_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(SHA512, sha512_ce_mod_init);
+module_exit(sha512_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha512-core.S_shipped b/arch/arm64/crypto/sha512-core.S_shipped
new file mode 100644
index 000000000..e063a6106
--- /dev/null
+++ b/arch/arm64/crypto/sha512-core.S_shipped
@@ -0,0 +1,1093 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// This code is taken from the OpenSSL project but the author (Andy Polyakov)
+// has relicensed it under the GPLv2. Therefore 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.
+//
+// The original headers, including the original license headers, are
+// included below for completeness.
+
+// Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
+//
+// Licensed under the OpenSSL license (the "License").  You may not use
+// this file except in compliance with the License.  You can obtain a copy
+// in the file LICENSE in the source distribution or at
+// https://www.openssl.org/source/license.html
+
+// ====================================================================
+// Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+// project. The module is, however, dual licensed under OpenSSL and
+// CRYPTOGAMS licenses depending on where you obtain it. For further
+// details see http://www.openssl.org/~appro/cryptogams/.
+// ====================================================================
+//
+// SHA256/512 for ARMv8.
+//
+// Performance in cycles per processed byte and improvement coefficient
+// over code generated with "default" compiler:
+//
+//		SHA256-hw	SHA256(*)	SHA512
+// Apple A7	1.97		10.5 (+33%)	6.73 (-1%(**))
+// Cortex-A53	2.38		15.5 (+115%)	10.0 (+150%(***))
+// Cortex-A57	2.31		11.6 (+86%)	7.51 (+260%(***))
+// Denver	2.01		10.5 (+26%)	6.70 (+8%)
+// X-Gene			20.0 (+100%)	12.8 (+300%(***))
+// Mongoose	2.36		13.0 (+50%)	8.36 (+33%)
+//
+// (*)	Software SHA256 results are of lesser relevance, presented
+//	mostly for informational purposes.
+// (**)	The result is a trade-off: it's possible to improve it by
+//	10% (or by 1 cycle per round), but at the cost of 20% loss
+//	on Cortex-A53 (or by 4 cycles per round).
+// (***)	Super-impressive coefficients over gcc-generated code are
+//	indication of some compiler "pathology", most notably code
+//	generated with -mgeneral-regs-only is significanty faster
+//	and the gap is only 40-90%.
+//
+// October 2016.
+//
+// Originally it was reckoned that it makes no sense to implement NEON
+// version of SHA256 for 64-bit processors. This is because performance
+// improvement on most wide-spread Cortex-A5x processors was observed
+// to be marginal, same on Cortex-A53 and ~10% on A57. But then it was
+// observed that 32-bit NEON SHA256 performs significantly better than
+// 64-bit scalar version on *some* of the more recent processors. As
+// result 64-bit NEON version of SHA256 was added to provide best
+// all-round performance. For example it executes ~30% faster on X-Gene
+// and Mongoose. [For reference, NEON version of SHA512 is bound to
+// deliver much less improvement, likely *negative* on Cortex-A5x.
+// Which is why NEON support is limited to SHA256.]
+
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+#endif
+
+.text
+
+.extern	OPENSSL_armcap_P
+.globl	sha512_block_data_order
+.type	sha512_block_data_order,%function
+.align	6
+sha512_block_data_order:
+	stp	x29,x30,[sp,#-128]!
+	add	x29,sp,#0
+
+	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,#4*8
+
+	ldp	x20,x21,[x0]				// load context
+	ldp	x22,x23,[x0,#2*8]
+	ldp	x24,x25,[x0,#4*8]
+	add	x2,x1,x2,lsl#7	// end of input
+	ldp	x26,x27,[x0,#6*8]
+	adr	x30,.LK512
+	stp	x0,x2,[x29,#96]
+
+.Loop:
+	ldp	x3,x4,[x1],#2*8
+	ldr	x19,[x30],#8			// *K++
+	eor	x28,x21,x22				// magic seed
+	str	x1,[x29,#112]
+#ifndef	__AARCH64EB__
+	rev	x3,x3			// 0
+#endif
+	ror	x16,x24,#14
+	add	x27,x27,x19			// h+=K[i]
+	eor	x6,x24,x24,ror#23
+	and	x17,x25,x24
+	bic	x19,x26,x24
+	add	x27,x27,x3			// h+=X[i]
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x20,x21			// a^b, b^c in next round
+	eor	x16,x16,x6,ror#18	// Sigma1(e)
+	ror	x6,x20,#28
+	add	x27,x27,x17			// h+=Ch(e,f,g)
+	eor	x17,x20,x20,ror#5
+	add	x27,x27,x16			// h+=Sigma1(e)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	add	x23,x23,x27			// d+=h
+	eor	x28,x28,x21			// Maj(a,b,c)
+	eor	x17,x6,x17,ror#34	// Sigma0(a)
+	add	x27,x27,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	//add	x27,x27,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x4,x4			// 1
+#endif
+	ldp	x5,x6,[x1],#2*8
+	add	x27,x27,x17			// h+=Sigma0(a)
+	ror	x16,x23,#14
+	add	x26,x26,x28			// h+=K[i]
+	eor	x7,x23,x23,ror#23
+	and	x17,x24,x23
+	bic	x28,x25,x23
+	add	x26,x26,x4			// h+=X[i]
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x27,x20			// a^b, b^c in next round
+	eor	x16,x16,x7,ror#18	// Sigma1(e)
+	ror	x7,x27,#28
+	add	x26,x26,x17			// h+=Ch(e,f,g)
+	eor	x17,x27,x27,ror#5
+	add	x26,x26,x16			// h+=Sigma1(e)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	add	x22,x22,x26			// d+=h
+	eor	x19,x19,x20			// Maj(a,b,c)
+	eor	x17,x7,x17,ror#34	// Sigma0(a)
+	add	x26,x26,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	//add	x26,x26,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x5,x5			// 2
+#endif
+	add	x26,x26,x17			// h+=Sigma0(a)
+	ror	x16,x22,#14
+	add	x25,x25,x19			// h+=K[i]
+	eor	x8,x22,x22,ror#23
+	and	x17,x23,x22
+	bic	x19,x24,x22
+	add	x25,x25,x5			// h+=X[i]
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x26,x27			// a^b, b^c in next round
+	eor	x16,x16,x8,ror#18	// Sigma1(e)
+	ror	x8,x26,#28
+	add	x25,x25,x17			// h+=Ch(e,f,g)
+	eor	x17,x26,x26,ror#5
+	add	x25,x25,x16			// h+=Sigma1(e)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	add	x21,x21,x25			// d+=h
+	eor	x28,x28,x27			// Maj(a,b,c)
+	eor	x17,x8,x17,ror#34	// Sigma0(a)
+	add	x25,x25,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	//add	x25,x25,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x6,x6			// 3
+#endif
+	ldp	x7,x8,[x1],#2*8
+	add	x25,x25,x17			// h+=Sigma0(a)
+	ror	x16,x21,#14
+	add	x24,x24,x28			// h+=K[i]
+	eor	x9,x21,x21,ror#23
+	and	x17,x22,x21
+	bic	x28,x23,x21
+	add	x24,x24,x6			// h+=X[i]
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x25,x26			// a^b, b^c in next round
+	eor	x16,x16,x9,ror#18	// Sigma1(e)
+	ror	x9,x25,#28
+	add	x24,x24,x17			// h+=Ch(e,f,g)
+	eor	x17,x25,x25,ror#5
+	add	x24,x24,x16			// h+=Sigma1(e)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	add	x20,x20,x24			// d+=h
+	eor	x19,x19,x26			// Maj(a,b,c)
+	eor	x17,x9,x17,ror#34	// Sigma0(a)
+	add	x24,x24,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	//add	x24,x24,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x7,x7			// 4
+#endif
+	add	x24,x24,x17			// h+=Sigma0(a)
+	ror	x16,x20,#14
+	add	x23,x23,x19			// h+=K[i]
+	eor	x10,x20,x20,ror#23
+	and	x17,x21,x20
+	bic	x19,x22,x20
+	add	x23,x23,x7			// h+=X[i]
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x24,x25			// a^b, b^c in next round
+	eor	x16,x16,x10,ror#18	// Sigma1(e)
+	ror	x10,x24,#28
+	add	x23,x23,x17			// h+=Ch(e,f,g)
+	eor	x17,x24,x24,ror#5
+	add	x23,x23,x16			// h+=Sigma1(e)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	add	x27,x27,x23			// d+=h
+	eor	x28,x28,x25			// Maj(a,b,c)
+	eor	x17,x10,x17,ror#34	// Sigma0(a)
+	add	x23,x23,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	//add	x23,x23,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x8,x8			// 5
+#endif
+	ldp	x9,x10,[x1],#2*8
+	add	x23,x23,x17			// h+=Sigma0(a)
+	ror	x16,x27,#14
+	add	x22,x22,x28			// h+=K[i]
+	eor	x11,x27,x27,ror#23
+	and	x17,x20,x27
+	bic	x28,x21,x27
+	add	x22,x22,x8			// h+=X[i]
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x23,x24			// a^b, b^c in next round
+	eor	x16,x16,x11,ror#18	// Sigma1(e)
+	ror	x11,x23,#28
+	add	x22,x22,x17			// h+=Ch(e,f,g)
+	eor	x17,x23,x23,ror#5
+	add	x22,x22,x16			// h+=Sigma1(e)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	add	x26,x26,x22			// d+=h
+	eor	x19,x19,x24			// Maj(a,b,c)
+	eor	x17,x11,x17,ror#34	// Sigma0(a)
+	add	x22,x22,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	//add	x22,x22,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x9,x9			// 6
+#endif
+	add	x22,x22,x17			// h+=Sigma0(a)
+	ror	x16,x26,#14
+	add	x21,x21,x19			// h+=K[i]
+	eor	x12,x26,x26,ror#23
+	and	x17,x27,x26
+	bic	x19,x20,x26
+	add	x21,x21,x9			// h+=X[i]
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x22,x23			// a^b, b^c in next round
+	eor	x16,x16,x12,ror#18	// Sigma1(e)
+	ror	x12,x22,#28
+	add	x21,x21,x17			// h+=Ch(e,f,g)
+	eor	x17,x22,x22,ror#5
+	add	x21,x21,x16			// h+=Sigma1(e)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	add	x25,x25,x21			// d+=h
+	eor	x28,x28,x23			// Maj(a,b,c)
+	eor	x17,x12,x17,ror#34	// Sigma0(a)
+	add	x21,x21,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	//add	x21,x21,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x10,x10			// 7
+#endif
+	ldp	x11,x12,[x1],#2*8
+	add	x21,x21,x17			// h+=Sigma0(a)
+	ror	x16,x25,#14
+	add	x20,x20,x28			// h+=K[i]
+	eor	x13,x25,x25,ror#23
+	and	x17,x26,x25
+	bic	x28,x27,x25
+	add	x20,x20,x10			// h+=X[i]
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x21,x22			// a^b, b^c in next round
+	eor	x16,x16,x13,ror#18	// Sigma1(e)
+	ror	x13,x21,#28
+	add	x20,x20,x17			// h+=Ch(e,f,g)
+	eor	x17,x21,x21,ror#5
+	add	x20,x20,x16			// h+=Sigma1(e)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	add	x24,x24,x20			// d+=h
+	eor	x19,x19,x22			// Maj(a,b,c)
+	eor	x17,x13,x17,ror#34	// Sigma0(a)
+	add	x20,x20,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	//add	x20,x20,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x11,x11			// 8
+#endif
+	add	x20,x20,x17			// h+=Sigma0(a)
+	ror	x16,x24,#14
+	add	x27,x27,x19			// h+=K[i]
+	eor	x14,x24,x24,ror#23
+	and	x17,x25,x24
+	bic	x19,x26,x24
+	add	x27,x27,x11			// h+=X[i]
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x20,x21			// a^b, b^c in next round
+	eor	x16,x16,x14,ror#18	// Sigma1(e)
+	ror	x14,x20,#28
+	add	x27,x27,x17			// h+=Ch(e,f,g)
+	eor	x17,x20,x20,ror#5
+	add	x27,x27,x16			// h+=Sigma1(e)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	add	x23,x23,x27			// d+=h
+	eor	x28,x28,x21			// Maj(a,b,c)
+	eor	x17,x14,x17,ror#34	// Sigma0(a)
+	add	x27,x27,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	//add	x27,x27,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x12,x12			// 9
+#endif
+	ldp	x13,x14,[x1],#2*8
+	add	x27,x27,x17			// h+=Sigma0(a)
+	ror	x16,x23,#14
+	add	x26,x26,x28			// h+=K[i]
+	eor	x15,x23,x23,ror#23
+	and	x17,x24,x23
+	bic	x28,x25,x23
+	add	x26,x26,x12			// h+=X[i]
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x27,x20			// a^b, b^c in next round
+	eor	x16,x16,x15,ror#18	// Sigma1(e)
+	ror	x15,x27,#28
+	add	x26,x26,x17			// h+=Ch(e,f,g)
+	eor	x17,x27,x27,ror#5
+	add	x26,x26,x16			// h+=Sigma1(e)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	add	x22,x22,x26			// d+=h
+	eor	x19,x19,x20			// Maj(a,b,c)
+	eor	x17,x15,x17,ror#34	// Sigma0(a)
+	add	x26,x26,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	//add	x26,x26,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x13,x13			// 10
+#endif
+	add	x26,x26,x17			// h+=Sigma0(a)
+	ror	x16,x22,#14
+	add	x25,x25,x19			// h+=K[i]
+	eor	x0,x22,x22,ror#23
+	and	x17,x23,x22
+	bic	x19,x24,x22
+	add	x25,x25,x13			// h+=X[i]
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x26,x27			// a^b, b^c in next round
+	eor	x16,x16,x0,ror#18	// Sigma1(e)
+	ror	x0,x26,#28
+	add	x25,x25,x17			// h+=Ch(e,f,g)
+	eor	x17,x26,x26,ror#5
+	add	x25,x25,x16			// h+=Sigma1(e)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	add	x21,x21,x25			// d+=h
+	eor	x28,x28,x27			// Maj(a,b,c)
+	eor	x17,x0,x17,ror#34	// Sigma0(a)
+	add	x25,x25,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	//add	x25,x25,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x14,x14			// 11
+#endif
+	ldp	x15,x0,[x1],#2*8
+	add	x25,x25,x17			// h+=Sigma0(a)
+	str	x6,[sp,#24]
+	ror	x16,x21,#14
+	add	x24,x24,x28			// h+=K[i]
+	eor	x6,x21,x21,ror#23
+	and	x17,x22,x21
+	bic	x28,x23,x21
+	add	x24,x24,x14			// h+=X[i]
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x25,x26			// a^b, b^c in next round
+	eor	x16,x16,x6,ror#18	// Sigma1(e)
+	ror	x6,x25,#28
+	add	x24,x24,x17			// h+=Ch(e,f,g)
+	eor	x17,x25,x25,ror#5
+	add	x24,x24,x16			// h+=Sigma1(e)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	add	x20,x20,x24			// d+=h
+	eor	x19,x19,x26			// Maj(a,b,c)
+	eor	x17,x6,x17,ror#34	// Sigma0(a)
+	add	x24,x24,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	//add	x24,x24,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x15,x15			// 12
+#endif
+	add	x24,x24,x17			// h+=Sigma0(a)
+	str	x7,[sp,#0]
+	ror	x16,x20,#14
+	add	x23,x23,x19			// h+=K[i]
+	eor	x7,x20,x20,ror#23
+	and	x17,x21,x20
+	bic	x19,x22,x20
+	add	x23,x23,x15			// h+=X[i]
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x24,x25			// a^b, b^c in next round
+	eor	x16,x16,x7,ror#18	// Sigma1(e)
+	ror	x7,x24,#28
+	add	x23,x23,x17			// h+=Ch(e,f,g)
+	eor	x17,x24,x24,ror#5
+	add	x23,x23,x16			// h+=Sigma1(e)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	add	x27,x27,x23			// d+=h
+	eor	x28,x28,x25			// Maj(a,b,c)
+	eor	x17,x7,x17,ror#34	// Sigma0(a)
+	add	x23,x23,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	//add	x23,x23,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x0,x0			// 13
+#endif
+	ldp	x1,x2,[x1]
+	add	x23,x23,x17			// h+=Sigma0(a)
+	str	x8,[sp,#8]
+	ror	x16,x27,#14
+	add	x22,x22,x28			// h+=K[i]
+	eor	x8,x27,x27,ror#23
+	and	x17,x20,x27
+	bic	x28,x21,x27
+	add	x22,x22,x0			// h+=X[i]
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x23,x24			// a^b, b^c in next round
+	eor	x16,x16,x8,ror#18	// Sigma1(e)
+	ror	x8,x23,#28
+	add	x22,x22,x17			// h+=Ch(e,f,g)
+	eor	x17,x23,x23,ror#5
+	add	x22,x22,x16			// h+=Sigma1(e)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	add	x26,x26,x22			// d+=h
+	eor	x19,x19,x24			// Maj(a,b,c)
+	eor	x17,x8,x17,ror#34	// Sigma0(a)
+	add	x22,x22,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	//add	x22,x22,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x1,x1			// 14
+#endif
+	ldr	x6,[sp,#24]
+	add	x22,x22,x17			// h+=Sigma0(a)
+	str	x9,[sp,#16]
+	ror	x16,x26,#14
+	add	x21,x21,x19			// h+=K[i]
+	eor	x9,x26,x26,ror#23
+	and	x17,x27,x26
+	bic	x19,x20,x26
+	add	x21,x21,x1			// h+=X[i]
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x22,x23			// a^b, b^c in next round
+	eor	x16,x16,x9,ror#18	// Sigma1(e)
+	ror	x9,x22,#28
+	add	x21,x21,x17			// h+=Ch(e,f,g)
+	eor	x17,x22,x22,ror#5
+	add	x21,x21,x16			// h+=Sigma1(e)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	add	x25,x25,x21			// d+=h
+	eor	x28,x28,x23			// Maj(a,b,c)
+	eor	x17,x9,x17,ror#34	// Sigma0(a)
+	add	x21,x21,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	//add	x21,x21,x17			// h+=Sigma0(a)
+#ifndef	__AARCH64EB__
+	rev	x2,x2			// 15
+#endif
+	ldr	x7,[sp,#0]
+	add	x21,x21,x17			// h+=Sigma0(a)
+	str	x10,[sp,#24]
+	ror	x16,x25,#14
+	add	x20,x20,x28			// h+=K[i]
+	ror	x9,x4,#1
+	and	x17,x26,x25
+	ror	x8,x1,#19
+	bic	x28,x27,x25
+	ror	x10,x21,#28
+	add	x20,x20,x2			// h+=X[i]
+	eor	x16,x16,x25,ror#18
+	eor	x9,x9,x4,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x21,x22			// a^b, b^c in next round
+	eor	x16,x16,x25,ror#41	// Sigma1(e)
+	eor	x10,x10,x21,ror#34
+	add	x20,x20,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x8,x8,x1,ror#61
+	eor	x9,x9,x4,lsr#7	// sigma0(X[i+1])
+	add	x20,x20,x16			// h+=Sigma1(e)
+	eor	x19,x19,x22			// Maj(a,b,c)
+	eor	x17,x10,x21,ror#39	// Sigma0(a)
+	eor	x8,x8,x1,lsr#6	// sigma1(X[i+14])
+	add	x3,x3,x12
+	add	x24,x24,x20			// d+=h
+	add	x20,x20,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x3,x3,x9
+	add	x20,x20,x17			// h+=Sigma0(a)
+	add	x3,x3,x8
+.Loop_16_xx:
+	ldr	x8,[sp,#8]
+	str	x11,[sp,#0]
+	ror	x16,x24,#14
+	add	x27,x27,x19			// h+=K[i]
+	ror	x10,x5,#1
+	and	x17,x25,x24
+	ror	x9,x2,#19
+	bic	x19,x26,x24
+	ror	x11,x20,#28
+	add	x27,x27,x3			// h+=X[i]
+	eor	x16,x16,x24,ror#18
+	eor	x10,x10,x5,ror#8
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x20,x21			// a^b, b^c in next round
+	eor	x16,x16,x24,ror#41	// Sigma1(e)
+	eor	x11,x11,x20,ror#34
+	add	x27,x27,x17			// h+=Ch(e,f,g)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	eor	x9,x9,x2,ror#61
+	eor	x10,x10,x5,lsr#7	// sigma0(X[i+1])
+	add	x27,x27,x16			// h+=Sigma1(e)
+	eor	x28,x28,x21			// Maj(a,b,c)
+	eor	x17,x11,x20,ror#39	// Sigma0(a)
+	eor	x9,x9,x2,lsr#6	// sigma1(X[i+14])
+	add	x4,x4,x13
+	add	x23,x23,x27			// d+=h
+	add	x27,x27,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	add	x4,x4,x10
+	add	x27,x27,x17			// h+=Sigma0(a)
+	add	x4,x4,x9
+	ldr	x9,[sp,#16]
+	str	x12,[sp,#8]
+	ror	x16,x23,#14
+	add	x26,x26,x28			// h+=K[i]
+	ror	x11,x6,#1
+	and	x17,x24,x23
+	ror	x10,x3,#19
+	bic	x28,x25,x23
+	ror	x12,x27,#28
+	add	x26,x26,x4			// h+=X[i]
+	eor	x16,x16,x23,ror#18
+	eor	x11,x11,x6,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x27,x20			// a^b, b^c in next round
+	eor	x16,x16,x23,ror#41	// Sigma1(e)
+	eor	x12,x12,x27,ror#34
+	add	x26,x26,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x10,x10,x3,ror#61
+	eor	x11,x11,x6,lsr#7	// sigma0(X[i+1])
+	add	x26,x26,x16			// h+=Sigma1(e)
+	eor	x19,x19,x20			// Maj(a,b,c)
+	eor	x17,x12,x27,ror#39	// Sigma0(a)
+	eor	x10,x10,x3,lsr#6	// sigma1(X[i+14])
+	add	x5,x5,x14
+	add	x22,x22,x26			// d+=h
+	add	x26,x26,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x5,x5,x11
+	add	x26,x26,x17			// h+=Sigma0(a)
+	add	x5,x5,x10
+	ldr	x10,[sp,#24]
+	str	x13,[sp,#16]
+	ror	x16,x22,#14
+	add	x25,x25,x19			// h+=K[i]
+	ror	x12,x7,#1
+	and	x17,x23,x22
+	ror	x11,x4,#19
+	bic	x19,x24,x22
+	ror	x13,x26,#28
+	add	x25,x25,x5			// h+=X[i]
+	eor	x16,x16,x22,ror#18
+	eor	x12,x12,x7,ror#8
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x26,x27			// a^b, b^c in next round
+	eor	x16,x16,x22,ror#41	// Sigma1(e)
+	eor	x13,x13,x26,ror#34
+	add	x25,x25,x17			// h+=Ch(e,f,g)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	eor	x11,x11,x4,ror#61
+	eor	x12,x12,x7,lsr#7	// sigma0(X[i+1])
+	add	x25,x25,x16			// h+=Sigma1(e)
+	eor	x28,x28,x27			// Maj(a,b,c)
+	eor	x17,x13,x26,ror#39	// Sigma0(a)
+	eor	x11,x11,x4,lsr#6	// sigma1(X[i+14])
+	add	x6,x6,x15
+	add	x21,x21,x25			// d+=h
+	add	x25,x25,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	add	x6,x6,x12
+	add	x25,x25,x17			// h+=Sigma0(a)
+	add	x6,x6,x11
+	ldr	x11,[sp,#0]
+	str	x14,[sp,#24]
+	ror	x16,x21,#14
+	add	x24,x24,x28			// h+=K[i]
+	ror	x13,x8,#1
+	and	x17,x22,x21
+	ror	x12,x5,#19
+	bic	x28,x23,x21
+	ror	x14,x25,#28
+	add	x24,x24,x6			// h+=X[i]
+	eor	x16,x16,x21,ror#18
+	eor	x13,x13,x8,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x25,x26			// a^b, b^c in next round
+	eor	x16,x16,x21,ror#41	// Sigma1(e)
+	eor	x14,x14,x25,ror#34
+	add	x24,x24,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x12,x12,x5,ror#61
+	eor	x13,x13,x8,lsr#7	// sigma0(X[i+1])
+	add	x24,x24,x16			// h+=Sigma1(e)
+	eor	x19,x19,x26			// Maj(a,b,c)
+	eor	x17,x14,x25,ror#39	// Sigma0(a)
+	eor	x12,x12,x5,lsr#6	// sigma1(X[i+14])
+	add	x7,x7,x0
+	add	x20,x20,x24			// d+=h
+	add	x24,x24,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x7,x7,x13
+	add	x24,x24,x17			// h+=Sigma0(a)
+	add	x7,x7,x12
+	ldr	x12,[sp,#8]
+	str	x15,[sp,#0]
+	ror	x16,x20,#14
+	add	x23,x23,x19			// h+=K[i]
+	ror	x14,x9,#1
+	and	x17,x21,x20
+	ror	x13,x6,#19
+	bic	x19,x22,x20
+	ror	x15,x24,#28
+	add	x23,x23,x7			// h+=X[i]
+	eor	x16,x16,x20,ror#18
+	eor	x14,x14,x9,ror#8
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x24,x25			// a^b, b^c in next round
+	eor	x16,x16,x20,ror#41	// Sigma1(e)
+	eor	x15,x15,x24,ror#34
+	add	x23,x23,x17			// h+=Ch(e,f,g)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	eor	x13,x13,x6,ror#61
+	eor	x14,x14,x9,lsr#7	// sigma0(X[i+1])
+	add	x23,x23,x16			// h+=Sigma1(e)
+	eor	x28,x28,x25			// Maj(a,b,c)
+	eor	x17,x15,x24,ror#39	// Sigma0(a)
+	eor	x13,x13,x6,lsr#6	// sigma1(X[i+14])
+	add	x8,x8,x1
+	add	x27,x27,x23			// d+=h
+	add	x23,x23,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	add	x8,x8,x14
+	add	x23,x23,x17			// h+=Sigma0(a)
+	add	x8,x8,x13
+	ldr	x13,[sp,#16]
+	str	x0,[sp,#8]
+	ror	x16,x27,#14
+	add	x22,x22,x28			// h+=K[i]
+	ror	x15,x10,#1
+	and	x17,x20,x27
+	ror	x14,x7,#19
+	bic	x28,x21,x27
+	ror	x0,x23,#28
+	add	x22,x22,x8			// h+=X[i]
+	eor	x16,x16,x27,ror#18
+	eor	x15,x15,x10,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x23,x24			// a^b, b^c in next round
+	eor	x16,x16,x27,ror#41	// Sigma1(e)
+	eor	x0,x0,x23,ror#34
+	add	x22,x22,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x14,x14,x7,ror#61
+	eor	x15,x15,x10,lsr#7	// sigma0(X[i+1])
+	add	x22,x22,x16			// h+=Sigma1(e)
+	eor	x19,x19,x24			// Maj(a,b,c)
+	eor	x17,x0,x23,ror#39	// Sigma0(a)
+	eor	x14,x14,x7,lsr#6	// sigma1(X[i+14])
+	add	x9,x9,x2
+	add	x26,x26,x22			// d+=h
+	add	x22,x22,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x9,x9,x15
+	add	x22,x22,x17			// h+=Sigma0(a)
+	add	x9,x9,x14
+	ldr	x14,[sp,#24]
+	str	x1,[sp,#16]
+	ror	x16,x26,#14
+	add	x21,x21,x19			// h+=K[i]
+	ror	x0,x11,#1
+	and	x17,x27,x26
+	ror	x15,x8,#19
+	bic	x19,x20,x26
+	ror	x1,x22,#28
+	add	x21,x21,x9			// h+=X[i]
+	eor	x16,x16,x26,ror#18
+	eor	x0,x0,x11,ror#8
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x22,x23			// a^b, b^c in next round
+	eor	x16,x16,x26,ror#41	// Sigma1(e)
+	eor	x1,x1,x22,ror#34
+	add	x21,x21,x17			// h+=Ch(e,f,g)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	eor	x15,x15,x8,ror#61
+	eor	x0,x0,x11,lsr#7	// sigma0(X[i+1])
+	add	x21,x21,x16			// h+=Sigma1(e)
+	eor	x28,x28,x23			// Maj(a,b,c)
+	eor	x17,x1,x22,ror#39	// Sigma0(a)
+	eor	x15,x15,x8,lsr#6	// sigma1(X[i+14])
+	add	x10,x10,x3
+	add	x25,x25,x21			// d+=h
+	add	x21,x21,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	add	x10,x10,x0
+	add	x21,x21,x17			// h+=Sigma0(a)
+	add	x10,x10,x15
+	ldr	x15,[sp,#0]
+	str	x2,[sp,#24]
+	ror	x16,x25,#14
+	add	x20,x20,x28			// h+=K[i]
+	ror	x1,x12,#1
+	and	x17,x26,x25
+	ror	x0,x9,#19
+	bic	x28,x27,x25
+	ror	x2,x21,#28
+	add	x20,x20,x10			// h+=X[i]
+	eor	x16,x16,x25,ror#18
+	eor	x1,x1,x12,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x21,x22			// a^b, b^c in next round
+	eor	x16,x16,x25,ror#41	// Sigma1(e)
+	eor	x2,x2,x21,ror#34
+	add	x20,x20,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x0,x0,x9,ror#61
+	eor	x1,x1,x12,lsr#7	// sigma0(X[i+1])
+	add	x20,x20,x16			// h+=Sigma1(e)
+	eor	x19,x19,x22			// Maj(a,b,c)
+	eor	x17,x2,x21,ror#39	// Sigma0(a)
+	eor	x0,x0,x9,lsr#6	// sigma1(X[i+14])
+	add	x11,x11,x4
+	add	x24,x24,x20			// d+=h
+	add	x20,x20,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x11,x11,x1
+	add	x20,x20,x17			// h+=Sigma0(a)
+	add	x11,x11,x0
+	ldr	x0,[sp,#8]
+	str	x3,[sp,#0]
+	ror	x16,x24,#14
+	add	x27,x27,x19			// h+=K[i]
+	ror	x2,x13,#1
+	and	x17,x25,x24
+	ror	x1,x10,#19
+	bic	x19,x26,x24
+	ror	x3,x20,#28
+	add	x27,x27,x11			// h+=X[i]
+	eor	x16,x16,x24,ror#18
+	eor	x2,x2,x13,ror#8
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x20,x21			// a^b, b^c in next round
+	eor	x16,x16,x24,ror#41	// Sigma1(e)
+	eor	x3,x3,x20,ror#34
+	add	x27,x27,x17			// h+=Ch(e,f,g)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	eor	x1,x1,x10,ror#61
+	eor	x2,x2,x13,lsr#7	// sigma0(X[i+1])
+	add	x27,x27,x16			// h+=Sigma1(e)
+	eor	x28,x28,x21			// Maj(a,b,c)
+	eor	x17,x3,x20,ror#39	// Sigma0(a)
+	eor	x1,x1,x10,lsr#6	// sigma1(X[i+14])
+	add	x12,x12,x5
+	add	x23,x23,x27			// d+=h
+	add	x27,x27,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	add	x12,x12,x2
+	add	x27,x27,x17			// h+=Sigma0(a)
+	add	x12,x12,x1
+	ldr	x1,[sp,#16]
+	str	x4,[sp,#8]
+	ror	x16,x23,#14
+	add	x26,x26,x28			// h+=K[i]
+	ror	x3,x14,#1
+	and	x17,x24,x23
+	ror	x2,x11,#19
+	bic	x28,x25,x23
+	ror	x4,x27,#28
+	add	x26,x26,x12			// h+=X[i]
+	eor	x16,x16,x23,ror#18
+	eor	x3,x3,x14,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x27,x20			// a^b, b^c in next round
+	eor	x16,x16,x23,ror#41	// Sigma1(e)
+	eor	x4,x4,x27,ror#34
+	add	x26,x26,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x2,x2,x11,ror#61
+	eor	x3,x3,x14,lsr#7	// sigma0(X[i+1])
+	add	x26,x26,x16			// h+=Sigma1(e)
+	eor	x19,x19,x20			// Maj(a,b,c)
+	eor	x17,x4,x27,ror#39	// Sigma0(a)
+	eor	x2,x2,x11,lsr#6	// sigma1(X[i+14])
+	add	x13,x13,x6
+	add	x22,x22,x26			// d+=h
+	add	x26,x26,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x13,x13,x3
+	add	x26,x26,x17			// h+=Sigma0(a)
+	add	x13,x13,x2
+	ldr	x2,[sp,#24]
+	str	x5,[sp,#16]
+	ror	x16,x22,#14
+	add	x25,x25,x19			// h+=K[i]
+	ror	x4,x15,#1
+	and	x17,x23,x22
+	ror	x3,x12,#19
+	bic	x19,x24,x22
+	ror	x5,x26,#28
+	add	x25,x25,x13			// h+=X[i]
+	eor	x16,x16,x22,ror#18
+	eor	x4,x4,x15,ror#8
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x26,x27			// a^b, b^c in next round
+	eor	x16,x16,x22,ror#41	// Sigma1(e)
+	eor	x5,x5,x26,ror#34
+	add	x25,x25,x17			// h+=Ch(e,f,g)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	eor	x3,x3,x12,ror#61
+	eor	x4,x4,x15,lsr#7	// sigma0(X[i+1])
+	add	x25,x25,x16			// h+=Sigma1(e)
+	eor	x28,x28,x27			// Maj(a,b,c)
+	eor	x17,x5,x26,ror#39	// Sigma0(a)
+	eor	x3,x3,x12,lsr#6	// sigma1(X[i+14])
+	add	x14,x14,x7
+	add	x21,x21,x25			// d+=h
+	add	x25,x25,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	add	x14,x14,x4
+	add	x25,x25,x17			// h+=Sigma0(a)
+	add	x14,x14,x3
+	ldr	x3,[sp,#0]
+	str	x6,[sp,#24]
+	ror	x16,x21,#14
+	add	x24,x24,x28			// h+=K[i]
+	ror	x5,x0,#1
+	and	x17,x22,x21
+	ror	x4,x13,#19
+	bic	x28,x23,x21
+	ror	x6,x25,#28
+	add	x24,x24,x14			// h+=X[i]
+	eor	x16,x16,x21,ror#18
+	eor	x5,x5,x0,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x25,x26			// a^b, b^c in next round
+	eor	x16,x16,x21,ror#41	// Sigma1(e)
+	eor	x6,x6,x25,ror#34
+	add	x24,x24,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x4,x4,x13,ror#61
+	eor	x5,x5,x0,lsr#7	// sigma0(X[i+1])
+	add	x24,x24,x16			// h+=Sigma1(e)
+	eor	x19,x19,x26			// Maj(a,b,c)
+	eor	x17,x6,x25,ror#39	// Sigma0(a)
+	eor	x4,x4,x13,lsr#6	// sigma1(X[i+14])
+	add	x15,x15,x8
+	add	x20,x20,x24			// d+=h
+	add	x24,x24,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x15,x15,x5
+	add	x24,x24,x17			// h+=Sigma0(a)
+	add	x15,x15,x4
+	ldr	x4,[sp,#8]
+	str	x7,[sp,#0]
+	ror	x16,x20,#14
+	add	x23,x23,x19			// h+=K[i]
+	ror	x6,x1,#1
+	and	x17,x21,x20
+	ror	x5,x14,#19
+	bic	x19,x22,x20
+	ror	x7,x24,#28
+	add	x23,x23,x15			// h+=X[i]
+	eor	x16,x16,x20,ror#18
+	eor	x6,x6,x1,ror#8
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x24,x25			// a^b, b^c in next round
+	eor	x16,x16,x20,ror#41	// Sigma1(e)
+	eor	x7,x7,x24,ror#34
+	add	x23,x23,x17			// h+=Ch(e,f,g)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	eor	x5,x5,x14,ror#61
+	eor	x6,x6,x1,lsr#7	// sigma0(X[i+1])
+	add	x23,x23,x16			// h+=Sigma1(e)
+	eor	x28,x28,x25			// Maj(a,b,c)
+	eor	x17,x7,x24,ror#39	// Sigma0(a)
+	eor	x5,x5,x14,lsr#6	// sigma1(X[i+14])
+	add	x0,x0,x9
+	add	x27,x27,x23			// d+=h
+	add	x23,x23,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	add	x0,x0,x6
+	add	x23,x23,x17			// h+=Sigma0(a)
+	add	x0,x0,x5
+	ldr	x5,[sp,#16]
+	str	x8,[sp,#8]
+	ror	x16,x27,#14
+	add	x22,x22,x28			// h+=K[i]
+	ror	x7,x2,#1
+	and	x17,x20,x27
+	ror	x6,x15,#19
+	bic	x28,x21,x27
+	ror	x8,x23,#28
+	add	x22,x22,x0			// h+=X[i]
+	eor	x16,x16,x27,ror#18
+	eor	x7,x7,x2,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x23,x24			// a^b, b^c in next round
+	eor	x16,x16,x27,ror#41	// Sigma1(e)
+	eor	x8,x8,x23,ror#34
+	add	x22,x22,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x6,x6,x15,ror#61
+	eor	x7,x7,x2,lsr#7	// sigma0(X[i+1])
+	add	x22,x22,x16			// h+=Sigma1(e)
+	eor	x19,x19,x24			// Maj(a,b,c)
+	eor	x17,x8,x23,ror#39	// Sigma0(a)
+	eor	x6,x6,x15,lsr#6	// sigma1(X[i+14])
+	add	x1,x1,x10
+	add	x26,x26,x22			// d+=h
+	add	x22,x22,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x1,x1,x7
+	add	x22,x22,x17			// h+=Sigma0(a)
+	add	x1,x1,x6
+	ldr	x6,[sp,#24]
+	str	x9,[sp,#16]
+	ror	x16,x26,#14
+	add	x21,x21,x19			// h+=K[i]
+	ror	x8,x3,#1
+	and	x17,x27,x26
+	ror	x7,x0,#19
+	bic	x19,x20,x26
+	ror	x9,x22,#28
+	add	x21,x21,x1			// h+=X[i]
+	eor	x16,x16,x26,ror#18
+	eor	x8,x8,x3,ror#8
+	orr	x17,x17,x19			// Ch(e,f,g)
+	eor	x19,x22,x23			// a^b, b^c in next round
+	eor	x16,x16,x26,ror#41	// Sigma1(e)
+	eor	x9,x9,x22,ror#34
+	add	x21,x21,x17			// h+=Ch(e,f,g)
+	and	x28,x28,x19			// (b^c)&=(a^b)
+	eor	x7,x7,x0,ror#61
+	eor	x8,x8,x3,lsr#7	// sigma0(X[i+1])
+	add	x21,x21,x16			// h+=Sigma1(e)
+	eor	x28,x28,x23			// Maj(a,b,c)
+	eor	x17,x9,x22,ror#39	// Sigma0(a)
+	eor	x7,x7,x0,lsr#6	// sigma1(X[i+14])
+	add	x2,x2,x11
+	add	x25,x25,x21			// d+=h
+	add	x21,x21,x28			// h+=Maj(a,b,c)
+	ldr	x28,[x30],#8		// *K++, x19 in next round
+	add	x2,x2,x8
+	add	x21,x21,x17			// h+=Sigma0(a)
+	add	x2,x2,x7
+	ldr	x7,[sp,#0]
+	str	x10,[sp,#24]
+	ror	x16,x25,#14
+	add	x20,x20,x28			// h+=K[i]
+	ror	x9,x4,#1
+	and	x17,x26,x25
+	ror	x8,x1,#19
+	bic	x28,x27,x25
+	ror	x10,x21,#28
+	add	x20,x20,x2			// h+=X[i]
+	eor	x16,x16,x25,ror#18
+	eor	x9,x9,x4,ror#8
+	orr	x17,x17,x28			// Ch(e,f,g)
+	eor	x28,x21,x22			// a^b, b^c in next round
+	eor	x16,x16,x25,ror#41	// Sigma1(e)
+	eor	x10,x10,x21,ror#34
+	add	x20,x20,x17			// h+=Ch(e,f,g)
+	and	x19,x19,x28			// (b^c)&=(a^b)
+	eor	x8,x8,x1,ror#61
+	eor	x9,x9,x4,lsr#7	// sigma0(X[i+1])
+	add	x20,x20,x16			// h+=Sigma1(e)
+	eor	x19,x19,x22			// Maj(a,b,c)
+	eor	x17,x10,x21,ror#39	// Sigma0(a)
+	eor	x8,x8,x1,lsr#6	// sigma1(X[i+14])
+	add	x3,x3,x12
+	add	x24,x24,x20			// d+=h
+	add	x20,x20,x19			// h+=Maj(a,b,c)
+	ldr	x19,[x30],#8		// *K++, x28 in next round
+	add	x3,x3,x9
+	add	x20,x20,x17			// h+=Sigma0(a)
+	add	x3,x3,x8
+	cbnz	x19,.Loop_16_xx
+
+	ldp	x0,x2,[x29,#96]
+	ldr	x1,[x29,#112]
+	sub	x30,x30,#648		// rewind
+
+	ldp	x3,x4,[x0]
+	ldp	x5,x6,[x0,#2*8]
+	add	x1,x1,#14*8			// advance input pointer
+	ldp	x7,x8,[x0,#4*8]
+	add	x20,x20,x3
+	ldp	x9,x10,[x0,#6*8]
+	add	x21,x21,x4
+	add	x22,x22,x5
+	add	x23,x23,x6
+	stp	x20,x21,[x0]
+	add	x24,x24,x7
+	add	x25,x25,x8
+	stp	x22,x23,[x0,#2*8]
+	add	x26,x26,x9
+	add	x27,x27,x10
+	cmp	x1,x2
+	stp	x24,x25,[x0,#4*8]
+	stp	x26,x27,[x0,#6*8]
+	b.ne	.Loop
+
+	ldp	x19,x20,[x29,#16]
+	add	sp,sp,#4*8
+	ldp	x21,x22,[x29,#32]
+	ldp	x23,x24,[x29,#48]
+	ldp	x25,x26,[x29,#64]
+	ldp	x27,x28,[x29,#80]
+	ldp	x29,x30,[sp],#128
+	ret
+.size	sha512_block_data_order,.-sha512_block_data_order
+
+.align	6
+.type	.LK512,%object
+.LK512:
+	.quad	0x428a2f98d728ae22,0x7137449123ef65cd
+	.quad	0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
+	.quad	0x3956c25bf348b538,0x59f111f1b605d019
+	.quad	0x923f82a4af194f9b,0xab1c5ed5da6d8118
+	.quad	0xd807aa98a3030242,0x12835b0145706fbe
+	.quad	0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
+	.quad	0x72be5d74f27b896f,0x80deb1fe3b1696b1
+	.quad	0x9bdc06a725c71235,0xc19bf174cf692694
+	.quad	0xe49b69c19ef14ad2,0xefbe4786384f25e3
+	.quad	0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
+	.quad	0x2de92c6f592b0275,0x4a7484aa6ea6e483
+	.quad	0x5cb0a9dcbd41fbd4,0x76f988da831153b5
+	.quad	0x983e5152ee66dfab,0xa831c66d2db43210
+	.quad	0xb00327c898fb213f,0xbf597fc7beef0ee4
+	.quad	0xc6e00bf33da88fc2,0xd5a79147930aa725
+	.quad	0x06ca6351e003826f,0x142929670a0e6e70
+	.quad	0x27b70a8546d22ffc,0x2e1b21385c26c926
+	.quad	0x4d2c6dfc5ac42aed,0x53380d139d95b3df
+	.quad	0x650a73548baf63de,0x766a0abb3c77b2a8
+	.quad	0x81c2c92e47edaee6,0x92722c851482353b
+	.quad	0xa2bfe8a14cf10364,0xa81a664bbc423001
+	.quad	0xc24b8b70d0f89791,0xc76c51a30654be30
+	.quad	0xd192e819d6ef5218,0xd69906245565a910
+	.quad	0xf40e35855771202a,0x106aa07032bbd1b8
+	.quad	0x19a4c116b8d2d0c8,0x1e376c085141ab53
+	.quad	0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
+	.quad	0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
+	.quad	0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
+	.quad	0x748f82ee5defb2fc,0x78a5636f43172f60
+	.quad	0x84c87814a1f0ab72,0x8cc702081a6439ec
+	.quad	0x90befffa23631e28,0xa4506cebde82bde9
+	.quad	0xbef9a3f7b2c67915,0xc67178f2e372532b
+	.quad	0xca273eceea26619c,0xd186b8c721c0c207
+	.quad	0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
+	.quad	0x06f067aa72176fba,0x0a637dc5a2c898a6
+	.quad	0x113f9804bef90dae,0x1b710b35131c471b
+	.quad	0x28db77f523047d84,0x32caab7b40c72493
+	.quad	0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
+	.quad	0x4cc5d4becb3e42b6,0x597f299cfc657e2a
+	.quad	0x5fcb6fab3ad6faec,0x6c44198c4a475817
+	.quad	0	// terminator
+.size	.LK512,.-.LK512
+#ifndef	__KERNEL__
+.align	3
+.LOPENSSL_armcap_P:
+# ifdef	__ILP32__
+	.long	OPENSSL_armcap_P-.
+# else
+	.quad	OPENSSL_armcap_P-.
+# endif
+#endif
+.asciz	"SHA512 block transform for ARMv8, CRYPTOGAMS by <appro@openssl.org>"
+.align	2
+#ifndef	__KERNEL__
+.comm	OPENSSL_armcap_P,4,4
+#endif
diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c
new file mode 100644
index 000000000..370ccb296
--- /dev/null
+++ b/arch/arm64/crypto/sha512-glue.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Linux/arm64 port of the OpenSSL SHA512 implementation for AArch64
+ *
+ * Copyright (c) 2016 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <crypto/internal/hash.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <asm/neon.h>
+
+MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash for arm64");
+MODULE_AUTHOR("Andy Polyakov <appro@openssl.org>");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+
+asmlinkage void sha512_block_data_order(u64 *digest, const void *data,
+					unsigned int num_blks);
+EXPORT_SYMBOL(sha512_block_data_order);
+
+static void __sha512_block_data_order(struct sha512_state *sst, u8 const *src,
+				      int blocks)
+{
+	sha512_block_data_order(sst->state, src, blocks);
+}
+
+static int sha512_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int len)
+{
+	return sha512_base_do_update(desc, data, len,
+				     __sha512_block_data_order);
+}
+
+static int sha512_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	if (len)
+		sha512_base_do_update(desc, data, len,
+				      __sha512_block_data_order);
+	sha512_base_do_finalize(desc, __sha512_block_data_order);
+
+	return sha512_base_finish(desc, out);
+}
+
+static int sha512_final(struct shash_desc *desc, u8 *out)
+{
+	return sha512_finup(desc, NULL, 0, out);
+}
+
+static struct shash_alg algs[] = { {
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.init			= sha512_base_init,
+	.update			= sha512_update,
+	.final			= sha512_final,
+	.finup			= sha512_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.base.cra_name		= "sha512",
+	.base.cra_driver_name	= "sha512-arm64",
+	.base.cra_priority	= 150,
+	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.init			= sha384_base_init,
+	.update			= sha512_update,
+	.final			= sha512_final,
+	.finup			= sha512_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.base.cra_name		= "sha384",
+	.base.cra_driver_name	= "sha384-arm64",
+	.base.cra_priority	= 150,
+	.base.cra_blocksize	= SHA384_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+} };
+
+static int __init sha512_mod_init(void)
+{
+	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit sha512_mod_fini(void)
+{
+	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
+}
+
+module_init(sha512_mod_init);
+module_exit(sha512_mod_fini);
diff --git a/arch/arm64/crypto/sm3-ce-core.S b/arch/arm64/crypto/sm3-ce-core.S
new file mode 100644
index 000000000..ef97d3187
--- /dev/null
+++ b/arch/arm64/crypto/sm3-ce-core.S
@@ -0,0 +1,138 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * sm3-ce-core.S - SM3 secure hash using ARMv8.2 Crypto Extensions
+ *
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.irp		b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
+	.set		.Lv\b\().4s, \b
+	.endr
+
+	.macro		sm3partw1, rd, rn, rm
+	.inst		0xce60c000 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3partw2, rd, rn, rm
+	.inst		0xce60c400 | .L\rd | (.L\rn << 5) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3ss1, rd, rn, rm, ra
+	.inst		0xce400000 | .L\rd | (.L\rn << 5) | (.L\ra << 10) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3tt1a, rd, rn, rm, imm2
+	.inst		0xce408000 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3tt1b, rd, rn, rm, imm2
+	.inst		0xce408400 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3tt2a, rd, rn, rm, imm2
+	.inst		0xce408800 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
+	.endm
+
+	.macro		sm3tt2b, rd, rn, rm, imm2
+	.inst		0xce408c00 | .L\rd | (.L\rn << 5) | ((\imm2) << 12) | (.L\rm << 16)
+	.endm
+
+	.macro		round, ab, s0, t0, t1, i
+	sm3ss1		v5.4s, v8.4s, \t0\().4s, v9.4s
+	shl		\t1\().4s, \t0\().4s, #1
+	sri		\t1\().4s, \t0\().4s, #31
+	sm3tt1\ab	v8.4s, v5.4s, v10.4s, \i
+	sm3tt2\ab	v9.4s, v5.4s, \s0\().4s, \i
+	.endm
+
+	.macro		qround, ab, s0, s1, s2, s3, s4
+	.ifnb		\s4
+	ext		\s4\().16b, \s1\().16b, \s2\().16b, #12
+	ext		v6.16b, \s0\().16b, \s1\().16b, #12
+	ext		v7.16b, \s2\().16b, \s3\().16b, #8
+	sm3partw1	\s4\().4s, \s0\().4s, \s3\().4s
+	.endif
+
+	eor		v10.16b, \s0\().16b, \s1\().16b
+
+	round		\ab, \s0, v11, v12, 0
+	round		\ab, \s0, v12, v11, 1
+	round		\ab, \s0, v11, v12, 2
+	round		\ab, \s0, v12, v11, 3
+
+	.ifnb		\s4
+	sm3partw2	\s4\().4s, v7.4s, v6.4s
+	.endif
+	.endm
+
+	/*
+	 * void sm3_ce_transform(struct sm3_state *sst, u8 const *src,
+	 *                       int blocks)
+	 */
+	.text
+SYM_FUNC_START(sm3_ce_transform)
+	/* load state */
+	ld1		{v8.4s-v9.4s}, [x0]
+	rev64		v8.4s, v8.4s
+	rev64		v9.4s, v9.4s
+	ext		v8.16b, v8.16b, v8.16b, #8
+	ext		v9.16b, v9.16b, v9.16b, #8
+
+	adr_l		x8, .Lt
+	ldp		s13, s14, [x8]
+
+	/* load input */
+0:	ld1		{v0.16b-v3.16b}, [x1], #64
+	sub		w2, w2, #1
+
+	mov		v15.16b, v8.16b
+	mov		v16.16b, v9.16b
+
+CPU_LE(	rev32		v0.16b, v0.16b		)
+CPU_LE(	rev32		v1.16b, v1.16b		)
+CPU_LE(	rev32		v2.16b, v2.16b		)
+CPU_LE(	rev32		v3.16b, v3.16b		)
+
+	ext		v11.16b, v13.16b, v13.16b, #4
+
+	qround		a, v0, v1, v2, v3, v4
+	qround		a, v1, v2, v3, v4, v0
+	qround		a, v2, v3, v4, v0, v1
+	qround		a, v3, v4, v0, v1, v2
+
+	ext		v11.16b, v14.16b, v14.16b, #4
+
+	qround		b, v4, v0, v1, v2, v3
+	qround		b, v0, v1, v2, v3, v4
+	qround		b, v1, v2, v3, v4, v0
+	qround		b, v2, v3, v4, v0, v1
+	qround		b, v3, v4, v0, v1, v2
+	qround		b, v4, v0, v1, v2, v3
+	qround		b, v0, v1, v2, v3, v4
+	qround		b, v1, v2, v3, v4, v0
+	qround		b, v2, v3, v4, v0, v1
+	qround		b, v3, v4
+	qround		b, v4, v0
+	qround		b, v0, v1
+
+	eor		v8.16b, v8.16b, v15.16b
+	eor		v9.16b, v9.16b, v16.16b
+
+	/* handled all input blocks? */
+	cbnz		w2, 0b
+
+	/* save state */
+	rev64		v8.4s, v8.4s
+	rev64		v9.4s, v9.4s
+	ext		v8.16b, v8.16b, v8.16b, #8
+	ext		v9.16b, v9.16b, v9.16b, #8
+	st1		{v8.4s-v9.4s}, [x0]
+	ret
+SYM_FUNC_END(sm3_ce_transform)
+
+	.section	".rodata", "a"
+	.align		3
+.Lt:	.word		0x79cc4519, 0x9d8a7a87
diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c
new file mode 100644
index 000000000..d71faca32
--- /dev/null
+++ b/arch/arm64/crypto/sm3-ce-glue.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sm3-ce-glue.c - SM3 secure hash using ARMv8.2 Crypto Extensions
+ *
+ * Copyright (C) 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
+#include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
+#include <crypto/sm3.h>
+#include <crypto/sm3_base.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+MODULE_DESCRIPTION("SM3 secure hash using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sm3_ce_transform(struct sm3_state *sst, u8 const *src,
+				 int blocks);
+
+static int sm3_ce_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int len)
+{
+	if (!crypto_simd_usable())
+		return crypto_sm3_update(desc, data, len);
+
+	kernel_neon_begin();
+	sm3_base_do_update(desc, data, len, sm3_ce_transform);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sm3_ce_final(struct shash_desc *desc, u8 *out)
+{
+	if (!crypto_simd_usable())
+		return crypto_sm3_finup(desc, NULL, 0, out);
+
+	kernel_neon_begin();
+	sm3_base_do_finalize(desc, sm3_ce_transform);
+	kernel_neon_end();
+
+	return sm3_base_finish(desc, out);
+}
+
+static int sm3_ce_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	if (!crypto_simd_usable())
+		return crypto_sm3_finup(desc, data, len, out);
+
+	kernel_neon_begin();
+	sm3_base_do_update(desc, data, len, sm3_ce_transform);
+	kernel_neon_end();
+
+	return sm3_ce_final(desc, out);
+}
+
+static struct shash_alg sm3_alg = {
+	.digestsize		= SM3_DIGEST_SIZE,
+	.init			= sm3_base_init,
+	.update			= sm3_ce_update,
+	.final			= sm3_ce_final,
+	.finup			= sm3_ce_finup,
+	.descsize		= sizeof(struct sm3_state),
+	.base.cra_name		= "sm3",
+	.base.cra_driver_name	= "sm3-ce",
+	.base.cra_blocksize	= SM3_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+	.base.cra_priority	= 200,
+};
+
+static int __init sm3_ce_mod_init(void)
+{
+	return crypto_register_shash(&sm3_alg);
+}
+
+static void __exit sm3_ce_mod_fini(void)
+{
+	crypto_unregister_shash(&sm3_alg);
+}
+
+module_cpu_feature_match(SM3, sm3_ce_mod_init);
+module_exit(sm3_ce_mod_fini);
diff --git a/arch/arm64/crypto/sm4-ce-core.S b/arch/arm64/crypto/sm4-ce-core.S
new file mode 100644
index 000000000..4ac6cfbc5
--- /dev/null
+++ b/arch/arm64/crypto/sm4-ce-core.S
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.irp		b, 0, 1, 2, 3, 4, 5, 6, 7, 8
+	.set		.Lv\b\().4s, \b
+	.endr
+
+	.macro		sm4e, rd, rn
+	.inst		0xcec08400 | .L\rd | (.L\rn << 5)
+	.endm
+
+	/*
+	 * void sm4_ce_do_crypt(const u32 *rk, u32 *out, const u32 *in);
+	 */
+	.text
+SYM_FUNC_START(sm4_ce_do_crypt)
+	ld1		{v8.4s}, [x2]
+	ld1		{v0.4s-v3.4s}, [x0], #64
+CPU_LE(	rev32		v8.16b, v8.16b		)
+	ld1		{v4.4s-v7.4s}, [x0]
+	sm4e		v8.4s, v0.4s
+	sm4e		v8.4s, v1.4s
+	sm4e		v8.4s, v2.4s
+	sm4e		v8.4s, v3.4s
+	sm4e		v8.4s, v4.4s
+	sm4e		v8.4s, v5.4s
+	sm4e		v8.4s, v6.4s
+	sm4e		v8.4s, v7.4s
+	rev64		v8.4s, v8.4s
+	ext		v8.16b, v8.16b, v8.16b, #8
+CPU_LE(	rev32		v8.16b, v8.16b		)
+	st1		{v8.4s}, [x1]
+	ret
+SYM_FUNC_END(sm4_ce_do_crypt)
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
new file mode 100644
index 000000000..2754c875d
--- /dev/null
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/sm4.h>
+#include <crypto/internal/simd.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/types.h>
+
+MODULE_ALIAS_CRYPTO("sm4");
+MODULE_ALIAS_CRYPTO("sm4-ce");
+MODULE_DESCRIPTION("SM4 symmetric cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sm4_ce_do_crypt(const u32 *rk, void *out, const void *in);
+
+static void sm4_ce_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!crypto_simd_usable()) {
+		crypto_sm4_encrypt(tfm, out, in);
+	} else {
+		kernel_neon_begin();
+		sm4_ce_do_crypt(ctx->rkey_enc, out, in);
+		kernel_neon_end();
+	}
+}
+
+static void sm4_ce_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (!crypto_simd_usable()) {
+		crypto_sm4_decrypt(tfm, out, in);
+	} else {
+		kernel_neon_begin();
+		sm4_ce_do_crypt(ctx->rkey_dec, out, in);
+		kernel_neon_end();
+	}
+}
+
+static struct crypto_alg sm4_ce_alg = {
+	.cra_name			= "sm4",
+	.cra_driver_name		= "sm4-ce",
+	.cra_priority			= 200,
+	.cra_flags			= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize			= SM4_BLOCK_SIZE,
+	.cra_ctxsize			= sizeof(struct crypto_sm4_ctx),
+	.cra_module			= THIS_MODULE,
+	.cra_u.cipher = {
+		.cia_min_keysize	= SM4_KEY_SIZE,
+		.cia_max_keysize	= SM4_KEY_SIZE,
+		.cia_setkey		= crypto_sm4_set_key,
+		.cia_encrypt		= sm4_ce_encrypt,
+		.cia_decrypt		= sm4_ce_decrypt
+	}
+};
+
+static int __init sm4_ce_mod_init(void)
+{
+	return crypto_register_alg(&sm4_ce_alg);
+}
+
+static void __exit sm4_ce_mod_fini(void)
+{
+	crypto_unregister_alg(&sm4_ce_alg);
+}
+
+module_cpu_feature_match(SM4, sm4_ce_mod_init);
+module_exit(sm4_ce_mod_fini);