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
  ...

19 files changed, 910 insertions, 441 deletions

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 block */
-	ld1		{v3.16b}, [x1], #16
+	ld1		{v3.16b}, [x20], #16
 	eor		v3.16b, v0.16b, v3.16b
-	st1		{v3.16b}, [x0], #16
+	st1		{v3.16b}, [x19], #16
 	bne		.Lctrloop
 
 .Lctrout:
-	st1		{v4.16b}, [x5]		/* return next CTR value */
-	ldp		x29, x30, [sp], #16
+	st1		{v4.16b}, [x24]		/* return next CTR value */
+.Lctrret:
+	frame_pop
 	ret
 
 .Lctrtailblock:
-	st1		{v0.16b}, [x0]
-	ldp		x29, x30, [sp], #16
-	ret
+	st1		{v0.16b}, [x19]
+	b		.Lctrret
 
 .Lctrcarry:
 	umov		x7, v4.d[0]		/* load upper word of ctr  */
@@ -274,10 +319,16 @@ CPU_LE(	.quad		1, 0x87		)
 CPU_BE(	.quad		0x87, 1		)
 
 AES_ENTRY(aes_xts_encrypt)
-	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, x6
 
-	ld1		{v4.16b}, [x6]
+	ld1		{v4.16b}, [x24]
 	cbz		w7, .Lxtsencnotfirst
 
 	enc_prepare	w3, x5, x8
@@ -286,15 +337,17 @@ AES_ENTRY(aes_xts_encrypt)
 	ldr		q7, .Lxts_mul_x
 	b		.LxtsencNx
 
+.Lxtsencrestart:
+	ld1		{v4.16b}, [x24]
 .Lxtsencnotfirst:
-	enc_prepare	w3, x2, x8
+	enc_prepare	w22, x21, x8
 .LxtsencloopNx:
 	ldr		q7, .Lxts_mul_x
 	next_tweak	v4, v4, v7, v8
 .LxtsencNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lxtsenc1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 pt blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 pt blocks */
 	next_tweak	v5, v4, v7, v8
 	eor		v0.16b, v0.16b, v4.16b
 	next_tweak	v6, v5, v7, v8
@@ -307,35 +360,43 @@ AES_ENTRY(aes_xts_encrypt)
 	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
+	st1		{v0.16b-v3.16b}, [x19], #64
 	mov		v4.16b, v7.16b
-	cbz		w4, .Lxtsencout
+	cbz		w23, .Lxtsencout
+	st1		{v4.16b}, [x24]
+	cond_yield_neon	.Lxtsencrestart
 	b		.LxtsencloopNx
 .Lxtsenc1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lxtsencout
 .Lxtsencloop:
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	eor		v0.16b, v1.16b, v4.16b
-	encrypt_block	v0, w3, x2, x8, w7
+	encrypt_block	v0, w22, x21, x8, w7
 	eor		v0.16b, v0.16b, v4.16b
-	st1		{v0.16b}, [x0], #16
-	subs		w4, w4, #1
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	beq		.Lxtsencout
 	next_tweak	v4, v4, v7, v8
 	b		.Lxtsencloop
 .Lxtsencout:
-	st1		{v4.16b}, [x6]
-	ldp		x29, x30, [sp], #16
+	st1		{v4.16b}, [x24]
+	frame_pop
 	ret
 AES_ENDPROC(aes_xts_encrypt)
 
 
 AES_ENTRY(aes_xts_decrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
+	frame_push	6
 
-	ld1		{v4.16b}, [x6]
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x6
+
+	ld1		{v4.16b}, [x24]
 	cbz		w7, .Lxtsdecnotfirst
 
 	enc_prepare	w3, x5, x8
@@ -344,15 +405,17 @@ AES_ENTRY(aes_xts_decrypt)
 	ldr		q7, .Lxts_mul_x
 	b		.LxtsdecNx
 
+.Lxtsdecrestart:
+	ld1		{v4.16b}, [x24]
 .Lxtsdecnotfirst:
-	dec_prepare	w3, x2, x8
+	dec_prepare	w22, x21, x8
 .LxtsdecloopNx:
 	ldr		q7, .Lxts_mul_x
 	next_tweak	v4, v4, v7, v8
 .LxtsdecNx:
-	subs		w4, w4, #4
+	subs		w23, w23, #4
 	bmi		.Lxtsdec1x
-	ld1		{v0.16b-v3.16b}, [x1], #64	/* get 4 ct blocks */
+	ld1		{v0.16b-v3.16b}, [x20], #64	/* get 4 ct blocks */
 	next_tweak	v5, v4, v7, v8
 	eor		v0.16b, v0.16b, v4.16b
 	next_tweak	v6, v5, v7, v8
@@ -365,26 +428,28 @@ AES_ENTRY(aes_xts_decrypt)
 	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
+	st1		{v0.16b-v3.16b}, [x19], #64
 	mov		v4.16b, v7.16b
-	cbz		w4, .Lxtsdecout
+	cbz		w23, .Lxtsdecout
+	st1		{v4.16b}, [x24]
+	cond_yield_neon	.Lxtsdecrestart
 	b		.LxtsdecloopNx
 .Lxtsdec1x:
-	adds		w4, w4, #4
+	adds		w23, w23, #4
 	beq		.Lxtsdecout
 .Lxtsdecloop:
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	eor		v0.16b, v1.16b, v4.16b
-	decrypt_block	v0, w3, x2, x8, w7
+	decrypt_block	v0, w22, x21, x8, w7
 	eor		v0.16b, v0.16b, v4.16b
-	st1		{v0.16b}, [x0], #16
-	subs		w4, w4, #1
+	st1		{v0.16b}, [x19], #16
+	subs		w23, w23, #1
 	beq		.Lxtsdecout
 	next_tweak	v4, v4, v7, v8
 	b		.Lxtsdecloop
 .Lxtsdecout:
-	st1		{v4.16b}, [x6]
-	ldp		x29, x30, [sp], #16
+	st1		{v4.16b}, [x24]
+	frame_pop
 	ret
 AES_ENDPROC(aes_xts_decrypt)
 
@@ -393,43 +458,61 @@ AES_ENDPROC(aes_xts_decrypt)
 	 *		  int blocks, u8 dg[], int enc_before, int enc_after)
 	 */
 AES_ENTRY(aes_mac_update)
-	ld1		{v0.16b}, [x4]			/* get dg */
+	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		w3, w3, #4
+	subs		w22, w22, #4
 	bmi		.Lmac1x
-	ld1		{v1.16b-v4.16b}, [x0], #64	/* get next pt block */
+	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, w2, x1, x7, w8
+	encrypt_block	v0, w21, x20, x7, w8
 	eor		v0.16b, v0.16b, v2.16b
-	encrypt_block	v0, w2, x1, x7, w8
+	encrypt_block	v0, w21, x20, x7, w8
 	eor		v0.16b, v0.16b, v3.16b
-	encrypt_block	v0, w2, x1, x7, w8
+	encrypt_block	v0, w21, x20, x7, w8
 	eor		v0.16b, v0.16b, v4.16b
-	cmp		w3, wzr
-	csinv		x5, x6, xzr, eq
+	cmp		w22, wzr
+	csinv		x5, x24, xzr, eq
 	cbz		w5, .Lmacout
-	encrypt_block	v0, w2, x1, x7, w8
+	encrypt_block	v0, w21, x20, x7, w8
+	st1		{v0.16b}, [x23]			/* return dg */
+	cond_yield_neon	.Lmacrestart
 	b		.Lmacloop4x
 .Lmac1x:
-	add		w3, w3, #4
+	add		w22, w22, #4
 .Lmacloop:
-	cbz		w3, .Lmacout
-	ld1		{v1.16b}, [x0], #16		/* get next pt block */
+	cbz		w22, .Lmacout
+	ld1		{v1.16b}, [x19], #16		/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with dg */
 
-	subs		w3, w3, #1
-	csinv		x5, x6, xzr, eq
+	subs		w22, w22, #1
+	csinv		x5, x24, xzr, eq
 	cbz		w5, .Lmacout
 
-	encrypt_block	v0, w2, x1, x7, w8
+.Lmacenc:
+	encrypt_block	v0, w21, x20, x7, w8
 	b		.Lmacloop
 
 .Lmacout:
-	st1		{v0.16b}, [x4]			/* return dg */
+	st1		{v0.16b}, [x23]			/* return dg */
+	frame_pop
 	ret
+
+.Lmacrestart:
+	ld1		{v0.16b}, [x23]			/* get dg */
+	enc_prepare	w21, x20, x0
+	b		.Lmacloop4x
 AES_ENDPROC(aes_mac_update)
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index ca0472500433..e613a87f8b53 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -565,54 +565,61 @@ ENDPROC(aesbs_decrypt8)
 	 *		     int blocks)
 	 */
 	.macro		__ecb_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
-	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
 
 99:	mov		x5, #1
-	lsl		x5, x5, x4
-	subs		w4, w4, #8
-	csel		x4, x4, xzr, pl
+	lsl		x5, x5, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
 	csel		x5, x5, xzr, mi
 
-	ld1		{v0.16b}, [x1], #16
+	ld1		{v0.16b}, [x20], #16
 	tbnz		x5, #1, 0f
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	tbnz		x5, #2, 0f
-	ld1		{v2.16b}, [x1], #16
+	ld1		{v2.16b}, [x20], #16
 	tbnz		x5, #3, 0f
-	ld1		{v3.16b}, [x1], #16
+	ld1		{v3.16b}, [x20], #16
 	tbnz		x5, #4, 0f
-	ld1		{v4.16b}, [x1], #16
+	ld1		{v4.16b}, [x20], #16
 	tbnz		x5, #5, 0f
-	ld1		{v5.16b}, [x1], #16
+	ld1		{v5.16b}, [x20], #16
 	tbnz		x5, #6, 0f
-	ld1		{v6.16b}, [x1], #16
+	ld1		{v6.16b}, [x20], #16
 	tbnz		x5, #7, 0f
-	ld1		{v7.16b}, [x1], #16
+	ld1		{v7.16b}, [x20], #16
 
-0:	mov		bskey, x2
-	mov		rounds, x3
+0:	mov		bskey, x21
+	mov		rounds, x22
 	bl		\do8
 
-	st1		{\o0\().16b}, [x0], #16
+	st1		{\o0\().16b}, [x19], #16
 	tbnz		x5, #1, 1f
-	st1		{\o1\().16b}, [x0], #16
+	st1		{\o1\().16b}, [x19], #16
 	tbnz		x5, #2, 1f
-	st1		{\o2\().16b}, [x0], #16
+	st1		{\o2\().16b}, [x19], #16
 	tbnz		x5, #3, 1f
-	st1		{\o3\().16b}, [x0], #16
+	st1		{\o3\().16b}, [x19], #16
 	tbnz		x5, #4, 1f
-	st1		{\o4\().16b}, [x0], #16
+	st1		{\o4\().16b}, [x19], #16
 	tbnz		x5, #5, 1f
-	st1		{\o5\().16b}, [x0], #16
+	st1		{\o5\().16b}, [x19], #16
 	tbnz		x5, #6, 1f
-	st1		{\o6\().16b}, [x0], #16
+	st1		{\o6\().16b}, [x19], #16
 	tbnz		x5, #7, 1f
-	st1		{\o7\().16b}, [x0], #16
+	st1		{\o7\().16b}, [x19], #16
 
-	cbnz		x4, 99b
+	cbz		x23, 1f
+	cond_yield_neon
+	b		99b
 
-1:	ldp		x29, x30, [sp], #16
+1:	frame_pop
 	ret
 	.endm
 
@@ -632,43 +639,49 @@ ENDPROC(aesbs_ecb_decrypt)
 	 */
 	.align		4
 ENTRY(aesbs_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
 
 99:	mov		x6, #1
-	lsl		x6, x6, x4
-	subs		w4, w4, #8
-	csel		x4, x4, xzr, pl
+	lsl		x6, x6, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
 	csel		x6, x6, xzr, mi
 
-	ld1		{v0.16b}, [x1], #16
+	ld1		{v0.16b}, [x20], #16
 	mov		v25.16b, v0.16b
 	tbnz		x6, #1, 0f
-	ld1		{v1.16b}, [x1], #16
+	ld1		{v1.16b}, [x20], #16
 	mov		v26.16b, v1.16b
 	tbnz		x6, #2, 0f
-	ld1		{v2.16b}, [x1], #16
+	ld1		{v2.16b}, [x20], #16
 	mov		v27.16b, v2.16b
 	tbnz		x6, #3, 0f
-	ld1		{v3.16b}, [x1], #16
+	ld1		{v3.16b}, [x20], #16
 	mov		v28.16b, v3.16b
 	tbnz		x6, #4, 0f
-	ld1		{v4.16b}, [x1], #16
+	ld1		{v4.16b}, [x20], #16
 	mov		v29.16b, v4.16b
 	tbnz		x6, #5, 0f
-	ld1		{v5.16b}, [x1], #16
+	ld1		{v5.16b}, [x20], #16
 	mov		v30.16b, v5.16b
 	tbnz		x6, #6, 0f
-	ld1		{v6.16b}, [x1], #16
+	ld1		{v6.16b}, [x20], #16
 	mov		v31.16b, v6.16b
 	tbnz		x6, #7, 0f
-	ld1		{v7.16b}, [x1]
+	ld1		{v7.16b}, [x20]
 
-0:	mov		bskey, x2
-	mov		rounds, x3
+0:	mov		bskey, x21
+	mov		rounds, x22
 	bl		aesbs_decrypt8
 
-	ld1		{v24.16b}, [x5]			// load IV
+	ld1		{v24.16b}, [x24]		// load IV
 
 	eor		v1.16b, v1.16b, v25.16b
 	eor		v6.16b, v6.16b, v26.16b
@@ -679,34 +692,36 @@ ENTRY(aesbs_cbc_decrypt)
 	eor		v3.16b, v3.16b, v30.16b
 	eor		v5.16b, v5.16b, v31.16b
 
-	st1		{v0.16b}, [x0], #16
+	st1		{v0.16b}, [x19], #16
 	mov		v24.16b, v25.16b
 	tbnz		x6, #1, 1f
-	st1		{v1.16b}, [x0], #16
+	st1		{v1.16b}, [x19], #16
 	mov		v24.16b, v26.16b
 	tbnz		x6, #2, 1f
-	st1		{v6.16b}, [x0], #16
+	st1		{v6.16b}, [x19], #16
 	mov		v24.16b, v27.16b
 	tbnz		x6, #3, 1f
-	st1		{v4.16b}, [x0], #16
+	st1		{v4.16b}, [x19], #16
 	mov		v24.16b, v28.16b
 	tbnz		x6, #4, 1f
-	st1		{v2.16b}, [x0], #16
+	st1		{v2.16b}, [x19], #16
 	mov		v24.16b, v29.16b
 	tbnz		x6, #5, 1f
-	st1		{v7.16b}, [x0], #16
+	st1		{v7.16b}, [x19], #16
 	mov		v24.16b, v30.16b
 	tbnz		x6, #6, 1f
-	st1		{v3.16b}, [x0], #16
+	st1		{v3.16b}, [x19], #16
 	mov		v24.16b, v31.16b
 	tbnz		x6, #7, 1f
-	ld1		{v24.16b}, [x1], #16
-	st1		{v5.16b}, [x0], #16
-1:	st1		{v24.16b}, [x5]			// store IV
+	ld1		{v24.16b}, [x20], #16
+	st1		{v5.16b}, [x19], #16
+1:	st1		{v24.16b}, [x24]		// store IV
 
-	cbnz		x4, 99b
+	cbz		x23, 2f
+	cond_yield_neon
+	b		99b
 
-	ldp		x29, x30, [sp], #16
+2:	frame_pop
 	ret
 ENDPROC(aesbs_cbc_decrypt)
 
@@ -731,87 +746,93 @@ CPU_BE(	.quad		0x87, 1		)
 	 */
 __xts_crypt8:
 	mov		x6, #1
-	lsl		x6, x6, x4
-	subs		w4, w4, #8
-	csel		x4, x4, xzr, pl
+	lsl		x6, x6, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
 	csel		x6, x6, xzr, mi
 
-	ld1		{v0.16b}, [x1], #16
+	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}, [x1], #16
+	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}, [x1], #16
+	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}, [x1], #16
+	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}, [x1], #16
-	str		q29, [sp, #16]
+	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}, [x1], #16
-	str		q29, [sp, #32]
+	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}, [x1], #16
-	str		q29, [sp, #48]
+	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}, [x1], #16
-	str		q29, [sp, #64]
+	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, x2
-	mov		rounds, x3
+0:	mov		bskey, x21
+	mov		rounds, x22
 	br		x7
 ENDPROC(__xts_crypt8)
 
 	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
-	stp		x29, x30, [sp, #-80]!
-	mov		x29, sp
+	frame_push	6, 64
 
-	ldr		q30, .Lxts_mul_x
-	ld1		{v25.16b}, [x5]
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+
+0:	ldr		q30, .Lxts_mul_x
+	ld1		{v25.16b}, [x24]
 
 99:	adr		x7, \do8
 	bl		__xts_crypt8
 
-	ldp		q16, q17, [sp, #16]
-	ldp		q18, q19, [sp, #48]
+	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}, [x0], #16
+	st1		{\o0\().16b}, [x19], #16
 	mov		v25.16b, v26.16b
 	tbnz		x6, #1, 1f
-	st1		{\o1\().16b}, [x0], #16
+	st1		{\o1\().16b}, [x19], #16
 	mov		v25.16b, v27.16b
 	tbnz		x6, #2, 1f
-	st1		{\o2\().16b}, [x0], #16
+	st1		{\o2\().16b}, [x19], #16
 	mov		v25.16b, v28.16b
 	tbnz		x6, #3, 1f
-	st1		{\o3\().16b}, [x0], #16
+	st1		{\o3\().16b}, [x19], #16
 	mov		v25.16b, v29.16b
 	tbnz		x6, #4, 1f
 
@@ -820,18 +841,22 @@ ENDPROC(__xts_crypt8)
 	eor		\o6\().16b, \o6\().16b, v18.16b
 	eor		\o7\().16b, \o7\().16b, v19.16b
 
-	st1		{\o4\().16b}, [x0], #16
+	st1		{\o4\().16b}, [x19], #16
 	tbnz		x6, #5, 1f
-	st1		{\o5\().16b}, [x0], #16
+	st1		{\o5\().16b}, [x19], #16
 	tbnz		x6, #6, 1f
-	st1		{\o6\().16b}, [x0], #16
+	st1		{\o6\().16b}, [x19], #16
 	tbnz		x6, #7, 1f
-	st1		{\o7\().16b}, [x0], #16
+	st1		{\o7\().16b}, [x19], #16
+
+	cbz		x23, 1f
+	st1		{v25.16b}, [x24]
 
-	cbnz		x4, 99b
+	cond_yield_neon	0b
+	b		99b
 
-1:	st1		{v25.16b}, [x5]
-	ldp		x29, x30, [sp], #80
+1:	st1		{v25.16b}, [x24]
+	frame_pop
 	ret
 	.endm
 
@@ -856,24 +881,31 @@ ENDPROC(aesbs_xts_decrypt)
 	 *		     int rounds, int blocks, u8 iv[], u8 final[])
 	 */
 ENTRY(aesbs_ctr_encrypt)
-	stp		x29, x30, [sp, #-16]!
-	mov		x29, sp
-
-	cmp		x6, #0
-	cset		x10, ne
-	add		x4, x4, x10		// do one extra block if final
-
-	ldp		x7, x8, [x5]
-	ld1		{v0.16b}, [x5]
+	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, x4
-	subs		w4, w4, #8
-	csel		x4, x4, xzr, pl
+	lsl		x9, x9, x23
+	subs		w23, w23, #8
+	csel		x23, x23, xzr, pl
 	csel		x9, x9, xzr, le
 
 	tbnz		x9, #1, 0f
@@ -891,82 +923,85 @@ CPU_LE(	rev		x8, x8		)
 	tbnz		x9, #7, 0f
 	next_ctr	v7
 
-0:	mov		bskey, x2
-	mov		rounds, x3
+0:	mov		bskey, x21
+	mov		rounds, x22
 	bl		aesbs_encrypt8
 
-	lsr		x9, x9, x10		// disregard the extra block
+	lsr		x9, x9, x26		// disregard the extra block
 	tbnz		x9, #0, 0f
 
-	ld1		{v8.16b}, [x1], #16
+	ld1		{v8.16b}, [x20], #16
 	eor		v0.16b, v0.16b, v8.16b
-	st1		{v0.16b}, [x0], #16
+	st1		{v0.16b}, [x19], #16
 	tbnz		x9, #1, 1f
 
-	ld1		{v9.16b}, [x1], #16
+	ld1		{v9.16b}, [x20], #16
 	eor		v1.16b, v1.16b, v9.16b
-	st1		{v1.16b}, [x0], #16
+	st1		{v1.16b}, [x19], #16
 	tbnz		x9, #2, 2f
 
-	ld1		{v10.16b}, [x1], #16
+	ld1		{v10.16b}, [x20], #16
 	eor		v4.16b, v4.16b, v10.16b
-	st1		{v4.16b}, [x0], #16
+	st1		{v4.16b}, [x19], #16
 	tbnz		x9, #3, 3f
 
-	ld1		{v11.16b}, [x1], #16
+	ld1		{v11.16b}, [x20], #16
 	eor		v6.16b, v6.16b, v11.16b
-	st1		{v6.16b}, [x0], #16
+	st1		{v6.16b}, [x19], #16
 	tbnz		x9, #4, 4f
 
-	ld1		{v12.16b}, [x1], #16
+	ld1		{v12.16b}, [x20], #16
 	eor		v3.16b, v3.16b, v12.16b
-	st1		{v3.16b}, [x0], #16
+	st1		{v3.16b}, [x19], #16
 	tbnz		x9, #5, 5f
 
-	ld1		{v13.16b}, [x1], #16
+	ld1		{v13.16b}, [x20], #16
 	eor		v7.16b, v7.16b, v13.16b
-	st1		{v7.16b}, [x0], #16
+	st1		{v7.16b}, [x19], #16
 	tbnz		x9, #6, 6f
 
-	ld1		{v14.16b}, [x1], #16
+	ld1		{v14.16b}, [x20], #16
 	eor		v2.16b, v2.16b, v14.16b
-	st1		{v2.16b}, [x0], #16
+	st1		{v2.16b}, [x19], #16
 	tbnz		x9, #7, 7f
 
-	ld1		{v15.16b}, [x1], #16
+	ld1		{v15.16b}, [x20], #16
 	eor		v5.16b, v5.16b, v15.16b
-	st1		{v5.16b}, [x0], #16
+	st1		{v5.16b}, [x19], #16
 
 8:	next_ctr	v0
-	cbnz		x4, 99b
+	st1		{v0.16b}, [x24]
+	cbz		x23, 0f
+
+	cond_yield_neon	98b
+	b		99b
 
-0:	st1		{v0.16b}, [x5]
-	ldp		x29, x30, [sp], #16
+0:	frame_pop
 	ret
 
 	/*
 	 * If we are handling the tail of the input (x6 != NULL), return the
 	 * final keystream block back to the caller.
 	 */
-1:	cbz		x6, 8b
-	st1		{v1.16b}, [x6]
+1:	cbz		x25, 8b
+	st1		{v1.16b}, [x25]
 	b		8b
-2:	cbz		x6, 8b
-	st1		{v4.16b}, [x6]
+2:	cbz		x25, 8b
+	st1		{v4.16b}, [x25]
 	b		8b
-3:	cbz		x6, 8b
-	st1		{v6.16b}, [x6]
+3:	cbz		x25, 8b
+	st1		{v6.16b}, [x25]
 	b		8b
-4:	cbz		x6, 8b
-	st1		{v3.16b}, [x6]
+4:	cbz		x25, 8b
+	st1		{v3.16b}, [x25]
 	b		8b
-5:	cbz		x6, 8b
-	st1		{v7.16b}, [x6]
+5:	cbz		x25, 8b
+	st1		{v7.16b}, [x25]
 	b		8b
-6:	cbz		x6, 8b
-	st1		{v2.16b}, [x6]
+6:	cbz		x25, 8b
+	st1		{v2.16b}, [x25]
 	b		8b
-7:	cbz		x6, 8b
-	st1		{v5.16b}, [x6]
+7:	cbz		x25, 8b
+	st1		{v5.16b}, [x25]
 	b		8b
 ENDPROC(aesbs_ctr_encrypt)
diff --git a/arch/arm64/crypto/crc32-ce-core.S b/arch/arm64/crypto/crc32-ce-core.S
index 16ed3c7ebd37..8061bf0f9c66 100644
--- a/arch/arm64/crypto/crc32-ce-core.S
+++ b/arch/arm64/crypto/crc32-ce-core.S
@@ -100,9 +100,10 @@
 	dCONSTANT	.req	d0
 	qCONSTANT	.req	q0
 
-	BUF		.req	x0
-	LEN		.req	x1
-	CRC		.req	x2
+	BUF		.req	x19
+	LEN		.req	x20
+	CRC		.req	x21
+	CONST		.req	x22
 
 	vzr		.req	v9
 
@@ -123,7 +124,14 @@ ENTRY(crc32_pmull_le)
 ENTRY(crc32c_pmull_le)
 	adr_l		x3, .Lcrc32c_constants
 
-0:	bic		LEN, LEN, #15
+0:	frame_push	4, 64
+
+	mov		BUF, x0
+	mov		LEN, x1
+	mov		CRC, x2
+	mov		CONST, x3
+
+	bic		LEN, LEN, #15
 	ld1		{v1.16b-v4.16b}, [BUF], #0x40
 	movi		vzr.16b, #0
 	fmov		dCONSTANT, CRC
@@ -132,7 +140,7 @@ ENTRY(crc32c_pmull_le)
 	cmp		LEN, #0x40
 	b.lt		less_64
 
-	ldr		qCONSTANT, [x3]
+	ldr		qCONSTANT, [CONST]
 
 loop_64:		/* 64 bytes Full cache line folding */
 	sub		LEN, LEN, #0x40
@@ -162,10 +170,21 @@ loop_64:		/* 64 bytes Full cache line folding */
 	eor		v4.16b, v4.16b, v8.16b
 
 	cmp		LEN, #0x40
-	b.ge		loop_64
+	b.lt		less_64
+
+	if_will_cond_yield_neon
+	stp		q1, q2, [sp, #.Lframe_local_offset]
+	stp		q3, q4, [sp, #.Lframe_local_offset + 32]
+	do_cond_yield_neon
+	ldp		q1, q2, [sp, #.Lframe_local_offset]
+	ldp		q3, q4, [sp, #.Lframe_local_offset + 32]
+	ldr		qCONSTANT, [CONST]
+	movi		vzr.16b, #0
+	endif_yield_neon
+	b		loop_64
 
 less_64:		/* Folding cache line into 128bit */
-	ldr		qCONSTANT, [x3, #16]
+	ldr		qCONSTANT, [CONST, #16]
 
 	pmull2		v5.1q, v1.2d, vCONSTANT.2d
 	pmull		v1.1q, v1.1d, vCONSTANT.1d
@@ -204,8 +223,8 @@ fold_64:
 	eor		v1.16b, v1.16b, v2.16b
 
 	/* final 32-bit fold */
-	ldr		dCONSTANT, [x3, #32]
-	ldr		d3, [x3, #40]
+	ldr		dCONSTANT, [CONST, #32]
+	ldr		d3, [CONST, #40]
 
 	ext		v2.16b, v1.16b, vzr.16b, #4
 	and		v1.16b, v1.16b, v3.16b
@@ -213,7 +232,7 @@ fold_64:
 	eor		v1.16b, v1.16b, v2.16b
 
 	/* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
-	ldr		qCONSTANT, [x3, #48]
+	ldr		qCONSTANT, [CONST, #48]
 
 	and		v2.16b, v1.16b, v3.16b
 	ext		v2.16b, vzr.16b, v2.16b, #8
@@ -223,6 +242,7 @@ fold_64:
 	eor		v1.16b, v1.16b, v2.16b
 	mov		w0, v1.s[1]
 
+	frame_pop
 	ret
 ENDPROC(crc32_pmull_le)
 ENDPROC(crc32c_pmull_le)
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index f179c01bd55c..663ea71cdb38 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -74,13 +74,19 @@
 	.text
 	.cpu		generic+crypto
 
-	arg1_low32	.req	w0
-	arg2		.req	x1
-	arg3		.req	x2
+	arg1_low32	.req	w19
+	arg2		.req	x20
+	arg3		.req	x21
 
 	vzr		.req	v13
 
 ENTRY(crc_t10dif_pmull)
+	frame_push	3, 128
+
+	mov		arg1_low32, w0
+	mov		arg2, x1
+	mov		arg3, x2
+
 	movi		vzr.16b, #0		// init zero register
 
 	// adjust the 16-bit initial_crc value, scale it to 32 bits
@@ -175,8 +181,25 @@ CPU_LE(	ext		v12.16b, v12.16b, v12.16b, #8	)
 	subs		arg3, arg3, #128
 
 	// check if there is another 64B in the buffer to be able to fold
-	b.ge		_fold_64_B_loop
+	b.lt		_fold_64_B_end
+
+	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]
+	ldr_l		q10, rk3, x8
+	movi		vzr.16b, #0		// init zero register
+	endif_yield_neon
+
+	b		_fold_64_B_loop
 
+_fold_64_B_end:
 	// at this point, the buffer pointer is pointing at the last y Bytes
 	// of the buffer the 64B of folded data is in 4 of the vector
 	// registers: v0, v1, v2, v3
@@ -304,6 +327,7 @@ _barrett:
 _cleanup:
 	// scale the result back to 16 bits
 	lsr		x0, x0, #16
+	frame_pop
 	ret
 
 _less_than_128:
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 11ebf1ae248a..dcffb9e77589 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -213,22 +213,31 @@
 	.endm
 
 	.macro		__pmull_ghash, pn
-	ld1		{SHASH.2d}, [x3]
-	ld1		{XL.2d}, [x1]
+	frame_push	5
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+
+0:	ld1		{SHASH.2d}, [x22]
+	ld1		{XL.2d}, [x20]
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
 	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	__pmull_pre_\pn
 
 	/* do the head block first, if supplied */
-	cbz		x4, 0f
-	ld1		{T1.2d}, [x4]
-	b		1f
+	cbz		x23, 1f
+	ld1		{T1.2d}, [x23]
+	mov		x23, xzr
+	b		2f
 
-0:	ld1		{T1.2d}, [x2], #16
-	sub		w0, w0, #1
+1:	ld1		{T1.2d}, [x21], #16
+	sub		w19, w19, #1
 
-1:	/* multiply XL by SHASH in GF(2^128) */
+2:	/* multiply XL by SHASH in GF(2^128) */
 CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	ext		T2.16b, XL.16b, XL.16b, #8
@@ -250,9 +259,18 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 	eor		T2.16b, T2.16b, XH.16b
 	eor		XL.16b, XL.16b, T2.16b
 
-	cbnz		w0, 0b
+	cbz		w19, 3f
+
+	if_will_cond_yield_neon
+	st1		{XL.2d}, [x20]
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
+
+	b		1b
 
-	st1		{XL.2d}, [x1]
+3:	st1		{XL.2d}, [x20]
+	frame_pop
 	ret
 	.endm
 
@@ -304,38 +322,55 @@ ENDPROC(pmull_ghash_update_p8)
 	.endm
 
 	.macro		pmull_gcm_do_crypt, enc
-	ld1		{SHASH.2d}, [x4]
-	ld1		{XL.2d}, [x1]
-	ldr		x8, [x5, #8]			// load lower counter
+	frame_push	10
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+	mov		x22, x3
+	mov		x23, x4
+	mov		x24, x5
+	mov		x25, x6
+	mov		x26, x7
+	.if		\enc == 1
+	ldr		x27, [sp, #96]			// first stacked arg
+	.endif
+
+	ldr		x28, [x24, #8]			// load lower counter
+CPU_LE(	rev		x28, x28	)
+
+0:	mov		x0, x25
+	load_round_keys	w26, x0
+	ld1		{SHASH.2d}, [x23]
+	ld1		{XL.2d}, [x20]
 
 	movi		MASK.16b, #0xe1
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
-CPU_LE(	rev		x8, x8		)
 	shl		MASK.2d, MASK.2d, #57
 	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	.if		\enc == 1
-	ld1		{KS.16b}, [x7]
+	ld1		{KS.16b}, [x27]
 	.endif
 
-0:	ld1		{CTR.8b}, [x5]			// load upper counter
-	ld1		{INP.16b}, [x3], #16
-	rev		x9, x8
-	add		x8, x8, #1
-	sub		w0, w0, #1
+1:	ld1		{CTR.8b}, [x24]			// load upper counter
+	ld1		{INP.16b}, [x22], #16
+	rev		x9, x28
+	add		x28, x28, #1
+	sub		w19, w19, #1
 	ins		CTR.d[1], x9			// set lower counter
 
 	.if		\enc == 1
 	eor		INP.16b, INP.16b, KS.16b	// encrypt input
-	st1		{INP.16b}, [x2], #16
+	st1		{INP.16b}, [x21], #16
 	.endif
 
 	rev64		T1.16b, INP.16b
 
-	cmp		w6, #12
-	b.ge		2f				// AES-192/256?
+	cmp		w26, #12
+	b.ge		4f				// AES-192/256?
 
-1:	enc_round	CTR, v21
+2:	enc_round	CTR, v21
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 	ext		IN1.16b, T1.16b, T1.16b, #8
@@ -390,27 +425,39 @@ CPU_LE(	rev		x8, x8		)
 
 	.if		\enc == 0
 	eor		INP.16b, INP.16b, KS.16b
-	st1		{INP.16b}, [x2], #16
+	st1		{INP.16b}, [x21], #16
 	.endif
 
-	cbnz		w0, 0b
+	cbz		w19, 3f
 
-CPU_LE(	rev		x8, x8		)
-	st1		{XL.2d}, [x1]
-	str		x8, [x5, #8]			// store lower counter
+	if_will_cond_yield_neon
+	st1		{XL.2d}, [x20]
+	.if		\enc == 1
+	st1		{KS.16b}, [x27]
+	.endif
+	do_cond_yield_neon
+	b		0b
+	endif_yield_neon
 
+	b		1b
+
+3:	st1		{XL.2d}, [x20]
 	.if		\enc == 1
-	st1		{KS.16b}, [x7]
+	st1		{KS.16b}, [x27]
 	.endif
 
+CPU_LE(	rev		x28, x28	)
+	str		x28, [x24, #8]			// store lower counter
+
+	frame_pop
 	ret
 
-2:	b.eq		3f				// AES-192?
+4:	b.eq		5f				// AES-192?
 	enc_round	CTR, v17
 	enc_round	CTR, v18
-3:	enc_round	CTR, v19
+5:	enc_round	CTR, v19
 	enc_round	CTR, v20
-	b		1b
+	b		2b
 	.endm
 
 	/*
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index cfc9c92814fd..7cf0b1aa6ea8 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -63,11 +63,12 @@ static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
 
 asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[],
 				  const u8 src[], struct ghash_key const *k,
-				  u8 ctr[], int rounds, u8 ks[]);
+				  u8 ctr[], u32 const rk[], int rounds,
+				  u8 ks[]);
 
 asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[],
 				  const u8 src[], struct ghash_key const *k,
-				  u8 ctr[], int rounds);
+				  u8 ctr[], u32 const rk[], int rounds);
 
 asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[],
 					u32 const rk[], int rounds);
@@ -368,26 +369,29 @@ static int gcm_encrypt(struct aead_request *req)
 		pmull_gcm_encrypt_block(ks, iv, NULL,
 					num_rounds(&ctx->aes_key));
 		put_unaligned_be32(3, iv + GCM_IV_SIZE);
+		kernel_neon_end();
 
-		err = skcipher_walk_aead_encrypt(&walk, req, true);
+		err = skcipher_walk_aead_encrypt(&walk, req, false);
 
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
+			kernel_neon_begin();
 			pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
 					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, num_rounds(&ctx->aes_key), ks);
+					  iv, ctx->aes_key.key_enc,
+					  num_rounds(&ctx->aes_key), ks);
+			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
 		}
-		kernel_neon_end();
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
 				    num_rounds(&ctx->aes_key));
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
-		err = skcipher_walk_aead_encrypt(&walk, req, true);
+		err = skcipher_walk_aead_encrypt(&walk, req, false);
 
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -467,15 +471,19 @@ static int gcm_decrypt(struct aead_request *req)
 		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc,
 					num_rounds(&ctx->aes_key));
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
+		kernel_neon_end();
 
-		err = skcipher_walk_aead_decrypt(&walk, req, true);
+		err = skcipher_walk_aead_decrypt(&walk, req, false);
 
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
+			kernel_neon_begin();
 			pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
 					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, num_rounds(&ctx->aes_key));
+					  iv, ctx->aes_key.key_enc,
+					  num_rounds(&ctx->aes_key));
+			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
 						 walk.nbytes % AES_BLOCK_SIZE);
@@ -483,14 +491,12 @@ static int gcm_decrypt(struct aead_request *req)
 		if (walk.nbytes)
 			pmull_gcm_encrypt_block(iv, iv, NULL,
 						num_rounds(&ctx->aes_key));
-
-		kernel_neon_end();
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
 				    num_rounds(&ctx->aes_key));
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
-		err = skcipher_walk_aead_decrypt(&walk, req, true);
+		err = skcipher_walk_aead_decrypt(&walk, req, false);
 
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 46049850727d..78eb35fb5056 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -69,30 +69,36 @@
 	 *			  int blocks)
 	 */
 ENTRY(sha1_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
 	/* load round constants */
-	loadrc		k0.4s, 0x5a827999, w6
+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}, [x0]
-	ldr		dgb, [x0, #16]
+	ld1		{dgav.4s}, [x19]
+	ldr		dgb, [x19, #16]
 
 	/* load sha1_ce_state::finalize */
 	ldr_l		w4, sha1_ce_offsetof_finalize, x4
-	ldr		w4, [x0, x4]
+	ldr		w4, [x19, x4]
 
 	/* load input */
-0:	ld1		{v8.4s-v11.4s}, [x1], #64
-	sub		w2, w2, #1
+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	)
 
-1:	add		t0.4s, v8.4s, k0.4s
+2:	add		t0.4s, v8.4s, k0.4s
 	mov		dg0v.16b, dgav.16b
 
 	add_update	c, ev, k0,  8,  9, 10, 11, dgb
@@ -123,16 +129,25 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	add		dgbv.2s, dgbv.2s, dg1v.2s
 	add		dgav.4s, dgav.4s, dg0v.4s
 
-	cbnz		w2, 0b
+	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.
 	 */
-	cbz		x4, 3f
+3:	cbz		x4, 4f
 	ldr_l		w4, sha1_ce_offsetof_count, x4
-	ldr		x4, [x0, x4]
+	ldr		x4, [x19, x4]
 	movi		v9.2d, #0
 	mov		x8, #0x80000000
 	movi		v10.2d, #0
@@ -141,10 +156,11 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	mov		x4, #0
 	mov		v11.d[0], xzr
 	mov		v11.d[1], x7
-	b		1b
+	b		2b
 
 	/* store new state */
-3:	st1		{dgav.4s}, [x0]
-	str		dgb, [x0, #16]
+4:	st1		{dgav.4s}, [x19]
+	str		dgb, [x19, #16]
+	frame_pop
 	ret
 ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 4c3c89b812ce..cd8b36412469 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -79,30 +79,36 @@
 	 */
 	.text
 ENTRY(sha2_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
 	/* load round constants */
-	adr_l		x8, .Lsha2_rcon
+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}, [x0]
+	ld1		{dgav.4s, dgbv.4s}, [x19]
 
 	/* load sha256_ce_state::finalize */
 	ldr_l		w4, sha256_ce_offsetof_finalize, x4
-	ldr		w4, [x0, x4]
+	ldr		w4, [x19, x4]
 
 	/* load input */
-0:	ld1		{v16.4s-v19.4s}, [x1], #64
-	sub		w2, w2, #1
+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	)
 
-1:	add		t0.4s, v16.4s, v0.4s
+2:	add		t0.4s, v16.4s, v0.4s
 	mov		dg0v.16b, dgav.16b
 	mov		dg1v.16b, dgbv.16b
 
@@ -131,16 +137,24 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	add		dgbv.4s, dgbv.4s, dg1v.4s
 
 	/* handled all input blocks? */
-	cbnz		w2, 0b
+	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.
 	 */
-	cbz		x4, 3f
+3:	cbz		x4, 4f
 	ldr_l		w4, sha256_ce_offsetof_count, x4
-	ldr		x4, [x0, x4]
+	ldr		x4, [x19, x4]
 	movi		v17.2d, #0
 	mov		x8, #0x80000000
 	movi		v18.2d, #0
@@ -149,9 +163,10 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 	mov		x4, #0
 	mov		v19.d[0], xzr
 	mov		v19.d[1], x7
-	b		1b
+	b		2b
 
 	/* store new state */
-3:	st1		{dgav.4s, dgbv.4s}, [x0]
+4:	st1		{dgav.4s, dgbv.4s}, [x19]
+	frame_pop
 	ret
 ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha256-core.S_shipped b/arch/arm64/crypto/sha256-core.S_shipped
index 3ce82cc860bc..7c7ce2e3bad6 100644
--- a/arch/arm64/crypto/sha256-core.S_shipped
+++ b/arch/arm64/crypto/sha256-core.S_shipped
@@ -1,3 +1,13 @@
+// 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
@@ -10,8 +20,6 @@
 // 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 GPLv2 terms is granted.
 // ====================================================================
 //
 // SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
index 332ad7530690..a7d587fa54f6 100644
--- a/arch/arm64/crypto/sha3-ce-core.S
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -41,9 +41,16 @@
 	 */
 	.text
 ENTRY(sha3_ce_transform)
-	/* load state */
-	add	x8, x0, #32
-	ld1	{ v0.1d- v3.1d}, [x0]
+	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
@@ -51,13 +58,13 @@ ENTRY(sha3_ce_transform)
 	ld1	{v20.1d-v23.1d}, [x8], #32
 	ld1	{v24.1d}, [x8]
 
-0:	sub	w2, w2, #1
+1:	sub	w21, w21, #1
 	mov	w8, #24
 	adr_l	x9, .Lsha3_rcon
 
 	/* load input */
-	ld1	{v25.8b-v28.8b}, [x1], #32
-	ld1	{v29.8b-v31.8b}, [x1], #24
+	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
@@ -66,10 +73,10 @@ ENTRY(sha3_ce_transform)
 	eor	v5.8b, v5.8b, v30.8b
 	eor	v6.8b, v6.8b, v31.8b
 
-	tbnz	x3, #6, 2f		// SHA3-512
+	tbnz	x22, #6, 3f		// SHA3-512
 
-	ld1	{v25.8b-v28.8b}, [x1], #32
-	ld1	{v29.8b-v30.8b}, [x1], #16
+	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
@@ -77,34 +84,34 @@ ENTRY(sha3_ce_transform)
 	eor	v11.8b, v11.8b, v29.8b
 	eor	v12.8b, v12.8b, v30.8b
 
-	tbnz	x3, #4, 1f		// SHA3-384 or SHA3-224
+	tbnz	x22, #4, 2f		// SHA3-384 or SHA3-224
 
 	// SHA3-256
-	ld1	{v25.8b-v28.8b}, [x1], #32
+	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	3f
+	b	4f
 
-1:	tbz	x3, #2, 3f		// bit 2 cleared? SHA-384
+2:	tbz	x22, #2, 4f		// bit 2 cleared? SHA-384
 
 	// SHA3-224
-	ld1	{v25.8b-v28.8b}, [x1], #32
-	ld1	{v29.8b}, [x1], #8
+	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	3f
+	b	4f
 
 	// SHA3-512
-2:	ld1	{v25.8b-v26.8b}, [x1], #16
+3:	ld1	{v25.8b-v26.8b}, [x20], #16
 	eor	 v7.8b,  v7.8b, v25.8b
 	eor	 v8.8b,  v8.8b, v26.8b
 
-3:	sub	w8, w8, #1
+4:	sub	w8, w8, #1
 
 	eor3	v29.16b,  v4.16b,  v9.16b, v14.16b
 	eor3	v26.16b,  v1.16b,  v6.16b, v11.16b
@@ -183,17 +190,33 @@ ENTRY(sha3_ce_transform)
 
 	eor	 v0.16b,  v0.16b, v31.16b
 
-	cbnz	w8, 3b
-	cbnz	w2, 0b
+	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 */
-	st1	{ v0.1d- v3.1d}, [x0], #32
-	st1	{ v4.1d- v7.1d}, [x0], #32
-	st1	{ v8.1d-v11.1d}, [x0], #32
-	st1	{v12.1d-v15.1d}, [x0], #32
-	st1	{v16.1d-v19.1d}, [x0], #32
-	st1	{v20.1d-v23.1d}, [x0], #32
-	st1	{v24.1d}, [x0]
+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
 ENDPROC(sha3_ce_transform)
 
diff --git a/arch/arm64/crypto/sha512-armv8.pl b/arch/arm64/crypto/sha512-armv8.pl
index c55efb308544..2d8655d5b1af 100644
--- a/arch/arm64/crypto/sha512-armv8.pl
+++ b/arch/arm64/crypto/sha512-armv8.pl
@@ -1,4 +1,14 @@
 #! /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
@@ -11,8 +21,6 @@
 # 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 GPLv2 terms is granted.
 # ====================================================================
 #
 # SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S
index 7f3bca5c59a2..ce65e3abe4f2 100644
--- a/arch/arm64/crypto/sha512-ce-core.S
+++ b/arch/arm64/crypto/sha512-ce-core.S
@@ -107,17 +107,23 @@
 	 */
 	.text
 ENTRY(sha512_ce_transform)
+	frame_push	3
+
+	mov		x19, x0
+	mov		x20, x1
+	mov		x21, x2
+
 	/* load state */
-	ld1		{v8.2d-v11.2d}, [x0]
+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 */
-0:	ld1		{v12.2d-v15.2d}, [x1], #64
-	ld1		{v16.2d-v19.2d}, [x1], #64
-	sub		w2, w2, #1
+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	)
@@ -196,9 +202,18 @@ CPU_LE(	rev64		v19.16b, v19.16b	)
 	add		v11.2d, v11.2d, v3.2d
 
 	/* handled all input blocks? */
-	cbnz		w2, 0b
+	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}, [x0]
+3:	st1		{v8.2d-v11.2d}, [x19]
+	frame_pop
 	ret
 ENDPROC(sha512_ce_transform)
diff --git a/arch/arm64/crypto/sha512-core.S_shipped b/arch/arm64/crypto/sha512-core.S_shipped
index bd0f59f06c9d..e063a6106720 100644
--- a/arch/arm64/crypto/sha512-core.S_shipped
+++ b/arch/arm64/crypto/sha512-core.S_shipped
@@ -1,3 +1,13 @@
+// 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
@@ -10,8 +20,6 @@
 // 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 GPLv2 terms is granted.
 // ====================================================================
 //
 // SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sm4-ce-core.S b/arch/arm64/crypto/sm4-ce-core.S
new file mode 100644
index 000000000000..af3bfbc3f4d4
--- /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
+ENTRY(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
+ENDPROC(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 000000000000..b7fb5274b250
--- /dev/null
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/sm4.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 (!may_use_simd()) {
+		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 (!may_use_simd()) {
+		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(SM3, sm4_ce_mod_init);
+module_exit(sm4_ce_mod_fini);