Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "API:

   - Decryption test vectors are now automatically generated from
     encryption test vectors.

  Algorithms:

   - Fix unaligned access issues in crc32/crc32c.

   - Add zstd compression algorithm.

   - Add AEGIS.

   - Add MORUS.

  Drivers:

   - Add accelerated AEGIS/MORUS on x86.

   - Add accelerated SM4 on arm64.

   - Removed x86 assembly salsa implementation as it is slower than C.

   - Add authenc(hmac(sha*), cbc(aes)) support in inside-secure.

   - Add ctr(aes) support in crypto4xx.

   - Add hardware key support in ccree.

   - Add support for new Centaur CPU in via-rng"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (112 commits)
  crypto: chtls - free beyond end rspq_skb_cache
  crypto: chtls - kbuild warnings
  crypto: chtls - dereference null variable
  crypto: chtls - wait for memory sendmsg, sendpage
  crypto: chtls - key len correction
  crypto: salsa20 - Revert "crypto: salsa20 - export generic helpers"
  crypto: x86/salsa20 - remove x86 salsa20 implementations
  crypto: ccp - Add GET_ID SEV command
  crypto: ccp - Add DOWNLOAD_FIRMWARE SEV command
  crypto: qat - Add MODULE_FIRMWARE for all qat drivers
  crypto: ccree - silence debug prints
  crypto: ccree - better clock handling
  crypto: ccree - correct host regs offset
  crypto: chelsio - Remove separate buffer used for DMA map B0 block in CCM
  crypt: chelsio - Send IV as Immediate for cipher algo
  crypto: chelsio - Return -ENOSPC for transient busy indication.
  crypto: caam/qi - fix warning in init_cgr()
  crypto: caam - fix rfc4543 descriptors
  crypto: caam - fix MC firmware detection
  crypto: clarify licensing of OpenSSL asm code
  ...

43 files changed, 7409 insertions, 2288 deletions

diff --git a/arch/arm/crypto/sha1-armv4-large.S b/arch/arm/crypto/sha1-armv4-large.S
index 99207c45ec10..f82cd8cf5a09 100644
--- a/arch/arm/crypto/sha1-armv4-large.S
+++ b/arch/arm/crypto/sha1-armv4-large.S
@@ -1,4 +1,14 @@
 #define __ARM_ARCH__ __LINUX_ARM_ARCH__
+@ 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.
+
 @ ====================================================================
 @ Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
 @ project. The module is, however, dual licensed under OpenSSL and
diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl
index fac0533ea633..b9ec44060ed3 100644
--- a/arch/arm/crypto/sha256-armv4.pl
+++ b/arch/arm/crypto/sha256-armv4.pl
@@ -1,12 +1,19 @@
 #!/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.
 
 # ====================================================================
 # 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/.
-#
-# Permission to use under GPL terms is granted.
 # ====================================================================
 
 # SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped
index 555a1a8eec90..3b58300d611c 100644
--- a/arch/arm/crypto/sha256-core.S_shipped
+++ b/arch/arm/crypto/sha256-core.S_shipped
@@ -1,11 +1,18 @@
+@ 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.
 
 @ ====================================================================
 @ 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/.
-@
-@ Permission to use under GPL terms is granted.
 @ ====================================================================
 
 @ SHA256 block procedure for ARMv4. May 2007.
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
index a2b11a844357..fb5d15048c0b 100644
--- a/arch/arm/crypto/sha512-armv4.pl
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -1,12 +1,19 @@
 #!/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.
 
 # ====================================================================
 # 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/.
-#
-# Permission to use under GPL terms is granted.
 # ====================================================================
 
 # SHA512 block procedure for ARMv4. September 2007.
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
index 3694c4d4ca2b..b1c334a49cda 100644
--- a/arch/arm/crypto/sha512-core.S_shipped
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -1,11 +1,18 @@
+@ 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.
 
 @ ====================================================================
 @ 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/.
-@
-@ Permission to use under GPL terms is granted.
 @ ====================================================================
 
 @ SHA512 block procedure for ARMv4. September 2007.
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index cb5a243110c4..e3fdb0fd6f70 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -47,6 +47,12 @@ config CRYPTO_SM3_ARM64_CE
 	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
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index f35ac684b1c0..bcafd016618e 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -23,6 +23,9 @@ 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
 
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index e3a375c4cb83..88f5aef7934c 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -19,24 +19,33 @@
 	 *			     u32 *macp, u8 const rk[], u32 rounds);
 	 */
 ENTRY(ce_aes_ccm_auth_data)
-	ldr	w8, [x3]			/* leftover from prev round? */
+	frame_push	7
+
+	mov	x19, x0
+	mov	x20, x1
+	mov	x21, x2
+	mov	x22, x3
+	mov	x23, x4
+	mov	x24, x5
+
+	ldr	w25, [x22]			/* leftover from prev round? */
 	ld1	{v0.16b}, [x0]			/* load mac */
-	cbz	w8, 1f
-	sub	w8, w8, #16
+	cbz	w25, 1f
+	sub	w25, w25, #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
+0:	ldrb	w7, [x20], #1			/* get 1 byte of input */
+	subs	w21, w21, #1
+	add	w25, w25, #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
+	cbnz	w25, 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 */
+1:	ld1	{v3.4s}, [x23]			/* load first round key */
+	prfm	pldl1strm, [x20]
+	cmp	w24, #12			/* which key size? */
+	add	x6, x23, #16
+	sub	w7, w24, #2			/* modified # of rounds */
 	bmi	2f
 	bne	5f
 	mov	v5.16b, v3.16b
@@ -55,33 +64,43 @@ ENTRY(ce_aes_ccm_auth_data)
 	ld1	{v5.4s}, [x6], #16		/* load next round key */
 	bpl	3b
 	aese	v0.16b, v4.16b
-	subs	w2, w2, #16			/* last data? */
+	subs	w21, w21, #16			/* last data? */
 	eor	v0.16b, v0.16b, v5.16b		/* final round */
 	bmi	6f
-	ld1	{v1.16b}, [x1], #16		/* load next input block */
+	ld1	{v1.16b}, [x20], #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	6f
+
+	if_will_cond_yield_neon
+	st1	{v0.16b}, [x19]			/* store mac */
+	do_cond_yield_neon
+	ld1	{v0.16b}, [x19]			/* reload mac */
+	endif_yield_neon
+
+	b	1b
+6:	st1	{v0.16b}, [x19]			/* store mac */
 	beq	10f
-	adds	w2, w2, #16
+	adds	w21, w21, #16
 	beq	10f
-	mov	w8, w2
-7:	ldrb	w7, [x1], #1
+	mov	w25, w21
+7:	ldrb	w7, [x20], #1
 	umov	w6, v0.b[0]
 	eor	w6, w6, w7
-	strb	w6, [x0], #1
-	subs	w2, w2, #1
+	strb	w6, [x19], #1
+	subs	w21, w21, #1
 	beq	10f
 	ext	v0.16b, v0.16b, v0.16b, #1	/* rotate out the mac bytes */
 	b	7b
-8:	mov	w7, w8
-	add	w8, w8, #16
+8:	mov	w7, w25
+	add	w25, w25, #16
 9:	ext	v1.16b, v1.16b, v1.16b, #1
 	adds	w7, w7, #1
 	bne	9b
 	eor	v0.16b, v0.16b, v1.16b
-	st1	{v0.16b}, [x0]
-10:	str	w8, [x3]
+	st1	{v0.16b}, [x19]
+10:	str	w25, [x22]
+
+	frame_pop
 	ret
 ENDPROC(ce_aes_ccm_auth_data)
 
@@ -126,19 +145,29 @@ ENTRY(ce_aes_ccm_final)
 ENDPROC(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 */
+	frame_push	8
+
+	mov	x19, x0
+	mov	x20, x1
+	mov	x21, x2
+	mov	x22, x3
+	mov	x23, x4
+	mov	x24, x5
+	mov	x25, x6
+
+	ldr	x26, [x25, #8]			/* load lower ctr */
+	ld1	{v0.16b}, [x24]			/* load mac */
+CPU_LE(	rev	x26, x26		)	/* 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 */
+	ld1	{v1.8b}, [x25]			/* load upper ctr */
+	prfm	pldl1strm, [x20]
+	add	x26, x26, #1
+	rev	x9, x26
+	cmp	w23, #12			/* which key size? */
+	sub	w7, w23, #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
+	ld1	{v3.4s}, [x22]			/* load first round key */
+	add	x10, x22, #16
 	bmi	1f
 	bne	4f
 	mov	v5.16b, v3.16b
@@ -165,9 +194,9 @@ CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 	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 */
+	subs	w21, w21, #16
+	bmi	7f				/* partial block? */
+	ld1	{v2.16b}, [x20], #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 */
@@ -176,18 +205,29 @@ CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
 	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 */
+	st1	{v1.16b}, [x19], #16		/* write output block */
+	beq	5f
+
+	if_will_cond_yield_neon
+	st1	{v0.16b}, [x24]			/* store mac */
+	do_cond_yield_neon
+	ld1	{v0.16b}, [x24]			/* reload mac */
+	endif_yield_neon
+
+	b	0b
+5:
+CPU_LE(	rev	x26, x26			)
+	st1	{v0.16b}, [x24]			/* store mac */
+	str	x26, [x25, #8]			/* store lsb end of ctr (BE) */
+
+6:	frame_pop
+	ret
+
+7:	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 */
+	st1	{v0.16b}, [x24]			/* store mac */
+	add	w21, w21, #16			/* process partial tail block */
+8:	ldrb	w9, [x20], #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
@@ -197,13 +237,13 @@ CPU_LE(	rev	x8, x8			)
 	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
+	strb	w9, [x19], #1			/* store out byte */
+	strb	w7, [x24], #1			/* store mac byte */
+	subs	w21, w21, #1
+	beq	6b
 	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
+	b	8b
 	.endm
 
 	/*
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index 50330f5c3adc..623e74ed1c67 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -30,18 +30,21 @@
 	.endm
 
 	/* prepare for encryption with key in rk[] */
-	.macro		enc_prepare, rounds, rk, ignore
-	load_round_keys	\rounds, \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, ignore
-	load_round_keys	\rounds, \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, ignore
-	load_round_keys	\rounds, \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
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index a68412e1e3a4..483a7130cf0e 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -14,12 +14,12 @@
 	.align		4
 
 aes_encrypt_block4x:
-	encrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
+	encrypt_block4x	v0, v1, v2, v3, w22, x21, x8, w7
 	ret
 ENDPROC(aes_encrypt_block4x)
 
 aes_decrypt_block4x:
-	decrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
+	decrypt_block4x	v0, v1, v2, v3, w22, x21, x8, w7
 	ret
 ENDPROC(aes_decrypt_block4x)
 
@@ -31,57 +31,71 @@ ENDPROC(aes_decrypt_block4x)
 	 */
 
 AES_ENTRY(aes_ecb_encrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	5
 
-	enc_prepare	w3, x2, x5
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+
+.Lecbencrestart:
+	enc_prepare	w22, x21, x5
 
 .LecbencloopNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lecbenc1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 pt blocks */
 	bl		aes_encrypt_block4x
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
+	cond_yield_neon	.Lecbencrestart
 	b		.LecbencloopNx
 .Lecbenc1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	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
+	ld1		{v0.16b}, [x20], #16		/* get next pt block */
+	encrypt_block	v0, w22, x21, x5, w6
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	bne		.Lecbencloop
 .Lecbencout:
-	ldp		x29, x30, [sp], #16
+	frame_pop
 	ret
 AES_ENDPROC(aes_ecb_encrypt)
 
 
 AES_ENTRY(aes_ecb_decrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	5
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
 
-	dec_prepare	w3, x2, x5
+.Lecbdecrestart:
+	dec_prepare	w22, x21, x5
 
 .LecbdecloopNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lecbdec1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 ct blocks */
 	bl		aes_decrypt_block4x
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
+	cond_yield_neon	.Lecbdecrestart
 	b		.LecbdecloopNx
 .Lecbdec1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	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
+	ld1		{v0.16b}, [x20], #16		/* get next ct block */
+	decrypt_block	v0, w22, x21, x5, w6
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	bne		.Lecbdecloop
 .Lecbdecout:
-	ldp		x29, x30, [sp], #16
+	frame_pop
 	ret
 AES_ENDPROC(aes_ecb_decrypt)
 
@@ -94,78 +108,100 @@ AES_ENDPROC(aes_ecb_decrypt)
 	 */
 
 AES_ENTRY(aes_cbc_encrypt)
-	ld1		{v4.16b}, [x5]			/* get iv */
-	enc_prepare	w3, x2, x6
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+
+.Lcbcencrestart:
+	ld1		{v4.16b}, [x24]			/* get iv */
+	enc_prepare	w22, x21, x6
 
 .Lcbcencloop4x:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lcbcenc1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 pt blocks */
 	eor		v0.16b, v0.16b, v4.16b		/* ..and xor with iv */
-	encrypt_block	v0, w3, x2, x6, w7
+	encrypt_block	v0, w22, x21, x6, w7
 	eor		v1.16b, v1.16b, v0.16b
-	encrypt_block	v1, w3, x2, x6, w7
+	encrypt_block	v1, w22, x21, x6, w7
 	eor		v2.16b, v2.16b, v1.16b
-	encrypt_block	v2, w3, x2, x6, w7
+	encrypt_block	v2, w22, x21, x6, w7
 	eor		v3.16b, v3.16b, v2.16b
-	encrypt_block	v3, w3, x2, x6, w7
-	st1		{v0.16b-v3.16b}, [x0], #64
+	encrypt_block	v3, w22, x21, x6, w7
+	st1		{v0.16b-v3.16b}, [x19], #64
 	mov		v4.16b, v3.16b
+	st1		{v4.16b}, [x24]			/* return iv */
+	cond_yield_neon	.Lcbcencrestart
 	b		.Lcbcencloop4x
 .Lcbcenc1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lcbcencout
 .Lcbcencloop:
-	ld1		{v0.16b}, [x1], #16		/* get next pt block */
+	ld1		{v0.16b}, [x20], #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
+	encrypt_block	v4, w22, x21, x6, w7
+	st1		{v4.16b}, [x19], #16
+	subs		w23, w23, #1
 	bne		.Lcbcencloop
 .Lcbcencout:
-	st1		{v4.16b}, [x5]			/* return iv */
+	st1		{v4.16b}, [x24]			/* return iv */
+	frame_pop
 	ret
 AES_ENDPROC(aes_cbc_encrypt)
 
 
 AES_ENTRY(aes_cbc_decrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	6
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
 
-	ld1		{v7.16b}, [x5]			/* get iv */
-	dec_prepare	w3, x2, x6
+.Lcbcdecrestart:
+	ld1		{v7.16b}, [x24]			/* get iv */
+	dec_prepare	w22, x21, x6
 
 .LcbcdecloopNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lcbcdec1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 ct blocks */
 	mov		v4.16b, v0.16b
 	mov		v5.16b, v1.16b
 	mov		v6.16b, v2.16b
 	bl		aes_decrypt_block4x
-	sub		x1, x1, #16
+	sub		x20, x20, #16
 	eor		v0.16b, v0.16b, v7.16b
 	eor		v1.16b, v1.16b, v4.16b
-	ld1		{v7.16b}, [x1], #16		/* reload 1 ct block */
+	ld1		{v7.16b}, [x20], #16		/* reload 1 ct block */
 	eor		v2.16b, v2.16b, v5.16b
 	eor		v3.16b, v3.16b, v6.16b
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
+	st1		{v7.16b}, [x24]			/* return iv */
+	cond_yield_neon	.Lcbcdecrestart
 	b		.LcbcdecloopNx
 .Lcbcdec1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lcbcdecout
 .Lcbcdecloop:
-	ld1		{v1.16b}, [x1], #16		/* get next ct block */
+	ld1		{v1.16b}, [x20], #16		/* get next ct block */
 	mov		v0.16b, v1.16b			/* ...and copy to v0 */
-	decrypt_block	v0, w3, x2, x6, w7
+	decrypt_block	v0, w22, x21, x6, w7
 	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
 	mov		v7.16b, v1.16b			/* ct is next iv */
-	st1		{v0.16b}, [x0], #16
-	subs		w4, w4, #1
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	bne		.Lcbcdecloop
 .Lcbcdecout:
-	st1		{v7.16b}, [x5]			/* return iv */
-	ldp		x29, x30, [sp], #16
+	st1		{v7.16b}, [x24]			/* return iv */
+	frame_pop
 	ret
 AES_ENDPROC(aes_cbc_decrypt)
 
@@ -176,19 +212,26 @@ AES_ENDPROC(aes_cbc_decrypt)
 	 */
 
 AES_ENTRY(aes_ctr_encrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	6
 
-	enc_prepare	w3, x2, x6
-	ld1		{v4.16b}, [x5]
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+
+.Lctrrestart:
+	enc_prepare	w22, x21, x6
+	ld1		{v4.16b}, [x24]
 
 	umov		x6, v4.d[1]		/* keep swabbed ctr in reg */
 	rev		x6, x6
-	cmn		w6, w4			/* 32 bit overflow? */
-	bcs		.Lctrloop
 .LctrloopNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lctr1x
+	cmn		w6, #4			/* 32 bit overflow? */
+	bcs		.Lctr1x
 	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
 	dup		v7.4s, w6
 	mov		v0.16b, v4.16b
@@ -200,25 +243,27 @@ AES_ENTRY(aes_ctr_encrypt)
 	mov		v1.s[3], v8.s[0]
 	mov		v2.s[3], v8.s[1]
 	mov		v3.s[3], v8.s[2]
-	ld1		{v5.16b-v7.16b}, [x1], #48	/* get 3 input blocks */
+	ld1		{v5.16b-v7.16b}, [x20], #48	/* get 3 input blocks */
 	bl		aes_encrypt_block4x
 	eor		v0.16b, v5.16b, v0.16b
-	ld1		{v5.16b}, [x1], #16		/* get 1 input block  */
+	ld1		{v5.16b}, [x20], #16		/* get 1 input block  */
 	eor		v1.16b, v6.16b, v1.16b
 	eor		v2.16b, v7.16b, v2.16b
 	eor		v3.16b, v5.16b, v3.16b
-	st1		{v0.16b-v3.16b}, [x0], #64
+	st1		{v0.16b-v3.16b}, [x19], #64
 	add		x6, x6, #4
 	rev		x7, x6
 	ins		v4.d[1], x7
-	cbz		w4, .Lctrout
+	cbz		w23, .Lctrout
+	st1		{v4.16b}, [x24]		/* return next CTR value */
+	cond_yield_neon	.Lctrrestart
 	b		.LctrloopNx
 .Lctr1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lctrout
 .Lctrloop:
 	mov		v0.16b, v4.16b
-	encrypt_block	v0, w3, x2, x8, w7
+	encrypt_block	v0, w22, x21, x8, w7
 
 	adds		x6, x6, #1		/* increment BE ctr */
 	rev		x7, x6
@@ -226,22 +271,22 @@ AES_ENTRY(aes_ctr_encrypt)
 	bcs		.Lctrcarry		/* overflow? */
 
 .Lctrcarrydone:
-	subs		w4, w4, #1
+	subs		w23, w23, #1
 	bmi		.Lctrtailblock		/* blocks <0 means tail