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

Pull crypto updates from Herbert Xu:
 "API:
   - Removed CRYPTO_TFM_RES flags
   - Extended spawn grabbing to all algorithm types
   - Moved hash descsize verification into API code

  Algorithms:
   - Fixed recursive pcrypt dead-lock
   - Added new 32 and 64-bit generic versions of poly1305
   - Added cryptogams implementation of x86/poly1305

  Drivers:
   - Added support for i.MX8M Mini in caam
   - Added support for i.MX8M Nano in caam
   - Added support for i.MX8M Plus in caam
   - Added support for A33 variant of SS in sun4i-ss
   - Added TEE support for Raven Ridge in ccp
   - Added in-kernel API to submit TEE commands in ccp
   - Added AMD-TEE driver
   - Added support for BCM2711 in iproc-rng200
   - Added support for AES256-GCM based ciphers for chtls
   - Added aead support on SEC2 in hisilicon"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (244 commits)
  crypto: arm/chacha - fix build failured when kernel mode NEON is disabled
  crypto: caam - add support for i.MX8M Plus
  crypto: x86/poly1305 - emit does base conversion itself
  crypto: hisilicon - fix spelling mistake "disgest" -> "digest"
  crypto: chacha20poly1305 - add back missing test vectors and test chunking
  crypto: x86/poly1305 - fix .gitignore typo
  tee: fix memory allocation failure checks on drv_data and amdtee
  crypto: ccree - erase unneeded inline funcs
  crypto: ccree - make cc_pm_put_suspend() void
  crypto: ccree - split overloaded usage of irq field
  crypto: ccree - fix PM race condition
  crypto: ccree - fix FDE descriptor sequence
  crypto: ccree - cc_do_send_request() is void func
  crypto: ccree - fix pm wrongful error reporting
  crypto: ccree - turn errors to debug msgs
  crypto: ccree - fix AEAD decrypt auth fail
  crypto: ccree - fix typo in comment
  crypto: ccree - fix typos in error msgs
  crypto: atmel-{aes,sha,tdes} - Retire crypto_platform_data
  crypto: x86/sha - Eliminate casts on asm implementations
  ...

27 files changed, 172 insertions, 195 deletions

diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index 9add9bbc48d8..99a028e298ed 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -15,7 +15,7 @@
 	 * void ce_aes_ccm_auth_data(u8 mac[], u8 const in[], u32 abytes,
 	 *			     u32 *macp, u8 const rk[], u32 rounds);
 	 */
-ENTRY(ce_aes_ccm_auth_data)
+SYM_FUNC_START(ce_aes_ccm_auth_data)
 	ldr	w8, [x3]			/* leftover from prev round? */
 	ld1	{v0.16b}, [x0]			/* load mac */
 	cbz	w8, 1f
@@ -81,13 +81,13 @@ ENTRY(ce_aes_ccm_auth_data)
 	st1	{v0.16b}, [x0]
 10:	str	w8, [x3]
 	ret
-ENDPROC(ce_aes_ccm_auth_data)
+SYM_FUNC_END(ce_aes_ccm_auth_data)
 
 	/*
 	 * void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u8 const rk[],
 	 * 			 u32 rounds);
 	 */
-ENTRY(ce_aes_ccm_final)
+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? */
@@ -121,7 +121,7 @@ ENTRY(ce_aes_ccm_final)
 	eor	v0.16b, v0.16b, v1.16b		/* en-/decrypt the mac */
 	st1	{v0.16b}, [x0]			/* store result */
 	ret
-ENDPROC(ce_aes_ccm_final)
+SYM_FUNC_END(ce_aes_ccm_final)
 
 	.macro	aes_ccm_do_crypt,enc
 	ldr	x8, [x6, #8]			/* load lower ctr */
@@ -212,10 +212,10 @@ CPU_LE(	rev	x8, x8			)
 	 * 			   u8 const rk[], u32 rounds, u8 mac[],
 	 * 			   u8 ctr[]);
 	 */
-ENTRY(ce_aes_ccm_encrypt)
+SYM_FUNC_START(ce_aes_ccm_encrypt)
 	aes_ccm_do_crypt	1
-ENDPROC(ce_aes_ccm_encrypt)
+SYM_FUNC_END(ce_aes_ccm_encrypt)
 
-ENTRY(ce_aes_ccm_decrypt)
+SYM_FUNC_START(ce_aes_ccm_decrypt)
 	aes_ccm_do_crypt	0
-ENDPROC(ce_aes_ccm_decrypt)
+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
index 541cf9165748..f6d19b0dc893 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -47,14 +47,8 @@ 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);
-	int ret;
 
-	ret = ce_aes_expandkey(ctx, in_key, key_len);
-	if (!ret)
-		return 0;
-
-	tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-	return -EINVAL;
+	return ce_aes_expandkey(ctx, in_key, key_len);
 }
 
 static int ccm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
diff --git a/arch/arm64/crypto/aes-ce-core.S b/arch/arm64/crypto/aes-ce-core.S
index 76a30fe4ba8b..e52e13eb8fdb 100644
--- a/arch/arm64/crypto/aes-ce-core.S
+++ b/arch/arm64/crypto/aes-ce-core.S
@@ -8,7 +8,7 @@
 
 	.arch		armv8-a+crypto
 
-ENTRY(__aes_ce_encrypt)
+SYM_FUNC_START(__aes_ce_encrypt)
 	sub		w3, w3, #2
 	ld1		{v0.16b}, [x2]
 	ld1		{v1.4s}, [x0], #16
@@ -34,9 +34,9 @@ ENTRY(__aes_ce_encrypt)
 	eor		v0.16b, v0.16b, v3.16b
 	st1		{v0.16b}, [x1]
 	ret
-ENDPROC(__aes_ce_encrypt)
+SYM_FUNC_END(__aes_ce_encrypt)
 
-ENTRY(__aes_ce_decrypt)
+SYM_FUNC_START(__aes_ce_decrypt)
 	sub		w3, w3, #2
 	ld1		{v0.16b}, [x2]
 	ld1		{v1.4s}, [x0], #16
@@ -62,23 +62,23 @@ ENTRY(__aes_ce_decrypt)
 	eor		v0.16b, v0.16b, v3.16b
 	st1		{v0.16b}, [x1]
 	ret
-ENDPROC(__aes_ce_decrypt)
+SYM_FUNC_END(__aes_ce_decrypt)
 
 /*
  * __aes_ce_sub() - use the aese instruction to perform the AES sbox
  *                  substitution on each byte in 'input'
  */
-ENTRY(__aes_ce_sub)
+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
-ENDPROC(__aes_ce_sub)
+SYM_FUNC_END(__aes_ce_sub)
 
-ENTRY(__aes_ce_invert)
+SYM_FUNC_START(__aes_ce_invert)
 	ld1		{v0.4s}, [x1]
 	aesimc		v1.16b, v0.16b
 	st1		{v1.4s}, [x0]
 	ret
-ENDPROC(__aes_ce_invert)
+SYM_FUNC_END(__aes_ce_invert)
diff --git a/arch/arm64/crypto/aes-ce-glue.c b/arch/arm64/crypto/aes-ce-glue.c
index 6d085dc56c51..56a5f6f0b0c1 100644
--- a/arch/arm64/crypto/aes-ce-glue.c
+++ b/arch/arm64/crypto/aes-ce-glue.c
@@ -143,14 +143,8 @@ int ce_aes_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 		  unsigned int key_len)
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	int ret;
 
-	ret = ce_aes_expandkey(ctx, in_key, key_len);
-	if (!ret)
-		return 0;
-
-	tfm->crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-	return -EINVAL;
+	return ce_aes_expandkey(ctx, in_key, key_len);
 }
 EXPORT_SYMBOL(ce_aes_setkey);
 
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index c132c49c89a8..45062553467f 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -9,8 +9,8 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-#define AES_ENTRY(func)		ENTRY(ce_ ## func)
-#define AES_ENDPROC(func)	ENDPROC(ce_ ## func)
+#define AES_ENTRY(func)		SYM_FUNC_START(ce_ ## func)
+#define AES_ENDPROC(func)	SYM_FUNC_END(ce_ ## func)
 
 	.arch		armv8-a+crypto
 
diff --git a/arch/arm64/crypto/aes-cipher-core.S b/arch/arm64/crypto/aes-cipher-core.S
index 423d0aebc570..c9d6955f8404 100644
--- a/arch/arm64/crypto/aes-cipher-core.S
+++ b/arch/arm64/crypto/aes-cipher-core.S
@@ -122,11 +122,11 @@ CPU_BE(	rev		w7, w7		)
 	ret
 	.endm
 
-ENTRY(__aes_arm64_encrypt)
+SYM_FUNC_START(__aes_arm64_encrypt)
 	do_crypt	fround, crypto_ft_tab, crypto_ft_tab + 1, 2
-ENDPROC(__aes_arm64_encrypt)
+SYM_FUNC_END(__aes_arm64_encrypt)
 
 	.align		5
-ENTRY(__aes_arm64_decrypt)
+SYM_FUNC_START(__aes_arm64_decrypt)
 	do_crypt	iround, crypto_it_tab, crypto_aes_inv_sbox, 0
-ENDPROC(__aes_arm64_decrypt)
+SYM_FUNC_END(__aes_arm64_decrypt)
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index aa57dc639f77..ed5409c6abf4 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -132,13 +132,8 @@ 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);
-	int ret;
-
-	ret = aes_expandkey(ctx, in_key, key_len);
-	if (ret)
-		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 
-	return ret;
+	return aes_expandkey(ctx, in_key, key_len);
 }
 
 static int __maybe_unused xts_set_key(struct crypto_skcipher *tfm,
@@ -155,11 +150,7 @@ static int __maybe_unused xts_set_key(struct crypto_skcipher *tfm,
 	if (!ret)
 		ret = aes_expandkey(&ctx->key2, &in_key[key_len / 2],
 				    key_len / 2);
-	if (!ret)
-		return 0;
-
-	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-	return -EINVAL;
+	return ret;
 }
 
 static int __maybe_unused essiv_cbc_set_key(struct crypto_skcipher *tfm,
@@ -173,19 +164,12 @@ static int __maybe_unused essiv_cbc_set_key(struct crypto_skcipher *tfm,
 
 	ret = aes_expandkey(&ctx->key1, in_key, key_len);
 	if (ret)
-		goto out;
+		return ret;
 
 	desc->tfm = ctx->hash;
 	crypto_shash_digest(desc, in_key, key_len, digest);
 
-	ret = aes_expandkey(&ctx->key2, digest, sizeof(digest));
-	if (ret)
-		goto out;
-
-	return 0;
-out:
-	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-	return -EINVAL;
+	return aes_expandkey(&ctx->key2, digest, sizeof(digest));
 }
 
 static int __maybe_unused ecb_encrypt(struct skcipher_request *req)
@@ -791,13 +775,8 @@ 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);
-	int err;
 
-	err = aes_expandkey(&ctx->key, in_key, key_len);
-	if (err)
-		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-
-	return err;
+	return aes_expandkey(&ctx->key, in_key, key_len);
 }
 
 static void cmac_gf128_mul_by_x(be128 *y, const be128 *x)
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index 131618389f1f..8a2faa42b57e 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -22,26 +22,26 @@
 #define ST5(x...) x
 #endif
 
-aes_encrypt_block4x:
+SYM_FUNC_START_LOCAL(aes_encrypt_block4x)
 	encrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
 	ret
-ENDPROC(aes_encrypt_block4x)
+SYM_FUNC_END(aes_encrypt_block4x)
 
-aes_decrypt_block4x:
+SYM_FUNC_START_LOCAL(aes_decrypt_block4x)
 	decrypt_block4x	v0, v1, v2, v3, w3, x2, x8, w7
 	ret
-ENDPROC(aes_decrypt_block4x)
+SYM_FUNC_END(aes_decrypt_block4x)
 
 #if MAX_STRIDE == 5
-aes_encrypt_block5x:
+SYM_FUNC_START_LOCAL(aes_encrypt_block5x)
 	encrypt_block5x	v0, v1, v2, v3, v4, w3, x2, x8, w7
 	ret
-ENDPROC(aes_encrypt_block5x)
+SYM_FUNC_END(aes_encrypt_block5x)
 
-aes_decrypt_block5x:
+SYM_FUNC_START_LOCAL(aes_decrypt_block5x)
 	decrypt_block5x	v0, v1, v2, v3, v4, w3, x2, x8, w7
 	ret
-ENDPROC(aes_decrypt_block5x)
+SYM_FUNC_END(aes_decrypt_block5x)
 #endif
 
 	/*
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
index 22d9b110cf78..247d34ddaab0 100644
--- a/arch/arm64/crypto/aes-neon.S
+++ b/arch/arm64/crypto/aes-neon.S
@@ -8,8 +8,8 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 
-#define AES_ENTRY(func)		ENTRY(neon_ ## func)
-#define AES_ENDPROC(func)	ENDPROC(neon_ ## func)
+#define AES_ENTRY(func)		SYM_FUNC_START(neon_ ## func)
+#define AES_ENDPROC(func)	SYM_FUNC_END(neon_ ## func)
 
 	xtsmask		.req	v7
 	cbciv		.req	v7
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index 65982039fa36..b357164379f6 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -380,7 +380,7 @@ ISRM0:	.octa		0x0306090c00070a0d01040b0e0205080f
 	/*
 	 * void aesbs_convert_key(u8 out[], u32 const rk[], int rounds)
 	 */
-ENTRY(aesbs_convert_key)
+SYM_FUNC_START(aesbs_convert_key)
 	ld1		{v7.4s}, [x1], #16		// load round 0 key
 	ld1		{v17.4s}, [x1], #16		// load round 1 key
 
@@ -425,10 +425,10 @@ ENTRY(aesbs_convert_key)
 	eor		v17.16b, v17.16b, v7.16b
 	str		q17, [x0]
 	ret
-ENDPROC(aesbs_convert_key)
+SYM_FUNC_END(aesbs_convert_key)
 
 	.align		4
-aesbs_encrypt8:
+SYM_FUNC_START_LOCAL(aesbs_encrypt8)
 	ldr		q9, [bskey], #16		// round 0 key
 	ldr		q8, M0SR
 	ldr		q24, SR
@@ -488,10 +488,10 @@ aesbs_encrypt8:
 	eor		v2.16b, v2.16b, v12.16b
 	eor		v5.16b, v5.16b, v12.16b
 	ret
-ENDPROC(aesbs_encrypt8)
+SYM_FUNC_END(aesbs_encrypt8)
 
 	.align		4
-aesbs_decrypt8:
+SYM_FUNC_START_LOCAL(aesbs_decrypt8)
 	lsl		x9, rounds, #7
 	add		bskey, bskey, x9
 
@@ -553,7 +553,7 @@ aesbs_decrypt8:
 	eor		v3.16b, v3.16b, v12.16b
 	eor		v5.16b, v5.16b, v12.16b
 	ret
-ENDPROC(aesbs_decrypt8)
+SYM_FUNC_END(aesbs_decrypt8)
 
 	/*
 	 * aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
@@ -621,21 +621,21 @@ ENDPROC(aesbs_decrypt8)
 	.endm
 
 	.align		4
-ENTRY(aesbs_ecb_encrypt)
+SYM_FUNC_START(aesbs_ecb_encrypt)
 	__ecb_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
-ENDPROC(aesbs_ecb_encrypt)
+SYM_FUNC_END(aesbs_ecb_encrypt)
 
 	.align		4
-ENTRY(aesbs_ecb_decrypt)
+SYM_FUNC_START(aesbs_ecb_decrypt)
 	__ecb_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
-ENDPROC(aesbs_ecb_decrypt)
+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
-ENTRY(aesbs_cbc_decrypt)
+SYM_FUNC_START(aesbs_cbc_decrypt)
 	frame_push	6
 
 	mov		x19, x0
@@ -720,7 +720,7 @@ ENTRY(aesbs_cbc_decrypt)
 
 2:	frame_pop
 	ret
-ENDPROC(aesbs_cbc_decrypt)
+SYM_FUNC_END(aesbs_cbc_decrypt)
 
 	.macro		next_tweak, out, in, const, tmp
 	sshr		\tmp\().2d,  \in\().2d,   #63
@@ -736,7 +736,7 @@ ENDPROC(aesbs_cbc_decrypt)
 	 * aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
 	 *		     int blocks, u8 iv[])
 	 */
-__xts_crypt8:
+SYM_FUNC_START_LOCAL(__xts_crypt8)
 	mov		x6, #1
 	lsl		x6, x6, x23
 	subs		w23, w23, #8
@@ -789,7 +789,7 @@ __xts_crypt8:
 0:	mov		bskey, x21
 	mov		rounds, x22
 	br		x7
-ENDPROC(__xts_crypt8)
+SYM_FUNC_END(__xts_crypt8)
 
 	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
 	frame_push	6, 64
@@ -854,13 +854,13 @@ ENDPROC(__xts_crypt8)
 	ret
 	.endm
 
-ENTRY(aesbs_xts_encrypt)
+SYM_FUNC_START(aesbs_xts_encrypt)
 	__xts_crypt	aesbs_encrypt8, v0, v1, v4, v6, v3, v7, v2, v5
-ENDPROC(aesbs_xts_encrypt)
+SYM_FUNC_END(aesbs_xts_encrypt)
 
-ENTRY(aesbs_xts_decrypt)
+SYM_FUNC_START(aesbs_xts_decrypt)
 	__xts_crypt	aesbs_decrypt8, v0, v1, v6, v4, v2, v7, v3, v5
-ENDPROC(aesbs_xts_decrypt)
+SYM_FUNC_END(aesbs_xts_decrypt)
 
 	.macro		next_ctr, v
 	mov		\v\().d[1], x8
@@ -874,7 +874,7 @@ ENDPROC(aesbs_xts_decrypt)
 	 * aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
 	 *		     int rounds, int blocks, u8 iv[], u8 final[])
 	 */
-ENTRY(aesbs_ctr_encrypt)
+SYM_FUNC_START(aesbs_ctr_encrypt)
 	frame_push	8
 
 	mov		x19, x0
@@ -1002,4 +1002,4 @@ CPU_LE(	rev		x8, x8		)
 7:	cbz		x25, 8b
 	st1		{v5.16b}, [x25]
 	b		8b
-ENDPROC(aesbs_ctr_encrypt)
+SYM_FUNC_END(aesbs_ctr_encrypt)
diff --git a/arch/arm64/crypto/chacha-neon-core.S b/arch/arm64/crypto/chacha-neon-core.S
index 706c4e10e9e2..e90386a7db8e 100644
--- a/arch/arm64/crypto/chacha-neon-core.S
+++ b/arch/arm64/crypto/chacha-neon-core.S
@@ -36,7 +36,7 @@
  *
  * Clobbers: w3, x10, v4, v12
  */
-chacha_permute:
+SYM_FUNC_START_LOCAL(chacha_permute)
 
 	adr_l		x10, ROT8
 	ld1		{v12.4s}, [x10]
@@ -104,9 +104,9 @@ chacha_permute:
 	b.ne		.Ldoubleround
 
 	ret
-ENDPROC(chacha_permute)
+SYM_FUNC_END(chacha_permute)
 
-ENTRY(chacha_block_xor_neon)
+SYM_FUNC_START(chacha_block_xor_neon)
 	// x0: Input state matrix, s
 	// x1: 1 data block output, o
 	// x2: 1 data block input, i
@@ -143,9 +143,9 @@ ENTRY(chacha_block_xor_neon)
 
 	ldp		x29, x30, [sp], #16
 	ret
-ENDPROC(chacha_block_xor_neon)
+SYM_FUNC_END(chacha_block_xor_neon)
 
-ENTRY(hchacha_block_neon)
+SYM_FUNC_START(hchacha_block_neon)
 	// x0: Input state matrix, s
 	// x1: output (8 32-bit words)
 	// w2: nrounds
@@ -163,7 +163,7 @@ ENTRY(hchacha_block_neon)
 
 	ldp		x29, x30, [sp], #16
 	ret
-ENDPROC(hchacha_block_neon)
+SYM_FUNC_END(hchacha_block_neon)
 
 	a0		.req	w12
 	a1		.req	w13
@@ -183,7 +183,7 @@ ENDPROC(hchacha_block_neon)
 	a15		.req	w28
 
 	.align		6
-ENTRY(chacha_4block_xor_neon)
+SYM_FUNC_START(chacha_4block_xor_neon)
 	frame_push	10
 
 	// x0: Input state matrix, s
@@ -845,7 +845,7 @@ CPU_BE(	  rev		a15, a15	)
 	eor		v31.16b, v31.16b, v3.16b
 	st1		{v28.16b-v31.16b}, [x1]
 	b		.Lout
-ENDPROC(chacha_4block_xor_neon)
+SYM_FUNC_END(chacha_4block_xor_neon)
 
 	.section	".rodata", "a", %progbits
 	.align		L1_CACHE_SHIFT
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index e545b42e6a46..5a95c2628fbf 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -131,7 +131,7 @@
 	tbl		bd4.16b, {\bd\().16b}, perm4.16b
 	.endm
 
-__pmull_p8_core:
+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
@@ -194,7 +194,7 @@ __pmull_p8_core:
 	eor		t4.16b, t4.16b, t5.16b
 	eor		t6.16b, t6.16b, t3.16b
 	ret
-ENDPROC(__pmull_p8_core)
+SYM_FUNC_END(__pmull_p8_core)
 
 	.macro		__pmull_p8, rq, ad, bd, i
 	.ifnc		\bd, fold_consts
@@ -488,9 +488,9 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 //
 // Assumes len >= 16.
 //
-ENTRY(crc_t10dif_pmull_p8)
+SYM_FUNC_START(crc_t10dif_pmull_p8)
 	crc_t10dif_pmull	p8
-ENDPROC(crc_t10dif_pmull_p8)
+SYM_FUNC_END(crc_t10dif_pmull_p8)
 
 	.align		5
 //
@@ -498,9 +498,9 @@ ENDPROC(crc_t10dif_pmull_p8)
 //
 // Assumes len >= 16.
 //
-ENTRY(crc_t10dif_pmull_p64)
+SYM_FUNC_START(crc_t10dif_pmull_p64)
 	crc_t10dif_pmull	p64
-ENDPROC(crc_t10dif_pmull_p64)
+SYM_FUNC_END(crc_t10dif_pmull_p64)
 
 	.section	".rodata", "a"
 	.align		4
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index a791c4adf8e6..084c6a30b03a 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -350,13 +350,13 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 	 * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
 	 *			   struct ghash_key const *k, const char *head)
 	 */
-ENTRY(pmull_ghash_update_p64)
+SYM_FUNC_START(pmull_ghash_update_p64)
 	__pmull_ghash	p64
-ENDPROC(pmull_ghash_update_p64)
+SYM_FUNC_END(pmull_ghash_update_p64)
 
-ENTRY(pmull_ghash_update_p8)
+SYM_FUNC_START(pmull_ghash_update_p8)
 	__pmull_ghash	p8
-ENDPROC(pmull_ghash_update_p8)
+SYM_FUNC_END(pmull_ghash_update_p8)
 
 	KS0		.req	v8
 	KS1		.req	v9
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 522cf004ce65..22831d3b7f62 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -248,10 +248,8 @@ static int ghash_setkey(struct crypto_shash *tfm,
 {
 	struct ghash_key *key = crypto_shash_ctx(tfm);
 
-	if (keylen != GHASH_BLOCK_SIZE) {
-		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	if (keylen != GHASH_BLOCK_SIZE)
 		return -EINVAL;
-	}
 
 	return __ghash_setkey(key, inkey, keylen);
 }
@@ -259,7 +257,7 @@ static int ghash_setkey(struct crypto_shash *tfm,
 static struct shash_alg ghash_alg[] = {{
 	.base.cra_name		= "ghash",
 	.base.cra_driver_name	= "ghash-neon",
-	.base.cra_priority	= 100,
+	.base.cra_priority	= 150,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct ghash_key),
 	.base.cra_module	= THIS_MODULE,
@@ -306,10 +304,8 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 	int ret;
 
 	ret = aes_expandkey(&ctx->aes_key, inkey, keylen);
-	if (ret) {
-		tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+	if (ret)
 		return -EINVAL;
-	}
 
 	aes_encrypt(&ctx->aes_key, key, (u8[AES_BLOCK_SIZE]){});
 
diff --git a/arch/arm64/crypto/nh-neon-core.S b/arch/arm64/crypto/nh-neon-core.S
index e05570c38de7..51c0a534ef87 100644
--- a/arch/arm64/crypto/nh-neon-core.S
+++ b/arch/arm64/crypto/nh-neon-core.S
@@ -62,7 +62,7 @@
  *
  * It's guaranteed that message_len % 16 == 0.
  */
-ENTRY(nh_neon)
+SYM_FUNC_START(nh_neon)
 
 	ld1		{K0.4s,K1.4s}, [KEY], #32
 	  movi		PASS0_SUMS.2d, #0
@@ -100,4 +100,4 @@ ENTRY(nh_neon)
 	addp		T1.2d, PASS2_SUMS.2d, PASS3_SUMS.2d
 	st1		{T0.16b,T1.16b}, [HASH]
 	ret
-ENDPROC(nh_neon)
+SYM_FUNC_END(nh_neon)
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
index 83a2338a8826..e97b092f56b8 100644
--- a/arch/arm64/crypto/poly1305-glue.c
+++ b/arch/arm64/crypto/poly1305-glue.c
@@ -21,7 +21,7 @@
 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, __le32 *digest, const u32 *nonce);
+asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce);
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
 
@@ -162,9 +162,6 @@ EXPORT_SYMBOL(poly1305_update_arch);
 
 void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 {
-	__le32 digest[4];
-	u64 f = 0;
-
 	if (unlikely(dctx->buflen)) {
 		dctx->buf[dctx->buflen++] = 1;
 		memset(dctx->buf + dctx->buflen, 0,
@@ -172,18 +169,7 @@ void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
 		poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
 	}
 
-	poly1305_emit(&dctx->h, digest, dctx->s);
-
-	/* mac = (h + s) % (2^128) */
-	f = (f >> 32) + le32_to_cpu(digest[0]);
-	put_unaligned_le32(f, dst);
-	f = (f >> 32) + le32_to_cpu(digest[1]);
-	put_unaligned_le32(f, dst + 4);
-	f = (f >> 32) + le32_to_cpu(digest[2]);
-	put_unaligned_le32(f, dst + 8);
-	f = (f >> 32) + le32_to_cpu(digest[3]);
-	put_unaligned_le32(f, dst + 12);
-
+	poly1305_emit(&dctx->h, dst, dctx->s);
 	*dctx = (struct poly1305_desc_ctx){};
 }
 EXPORT_SYMBOL(poly1305_final_arch);
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index c2ce1f820706..92d0d2753e81 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -65,7 +65,7 @@
 	 * void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src,
 	 *			  int blocks)
 	 */
-ENTRY(sha1_ce_transform)
+SYM_FUNC_START(sha1_ce_transform)
 	frame_push	3
 
 	mov		x19, x0
@@ -160,4 +160,4 @@ CPU_LE(	rev32		v11.16b, v11.16b	)
 	str		dgb, [x19, #16]
 	frame_pop
 	ret
-ENDPROC(sha1_ce_transform)
+SYM_FUNC_END(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index bdc1b6d7aff7..63c875d3314b 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -28,6 +28,13 @@ struct sha1_ce_state {
 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);
 
@@ -41,8 +48,7 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 
 	sctx->finalize = 0;
 	kernel_neon_begin();
-	sha1_base_do_update(desc, data, len,
-			    (sha1_block_fn *)sha1_ce_transform);
+	sha1_base_do_update(desc, data, len, __sha1_ce_transform);
 	kernel_neon_end();
 
 	return 0;
@@ -64,10 +70,9 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 	sctx->finalize = finalize;
 
 	kernel_neon_begin();
-	sha1_base_do_update(desc, data, len,
-			    (sha1_block_fn *)sha1_ce_transform);
+	sha1_base_do_update(desc, data, len, __sha1_ce_transform);
 	if (!finalize)
-		sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform);
+		sha1_base_do_finalize(desc, __sha1_ce_transform);
 	kernel_neon_end();
 	return sha1_base_finish(desc, out);
 }
@@ -81,7 +86,7 @@ static int sha1_ce_final(struct shash_desc *desc, u8 *out)
 
 	sctx->finalize = 0;
 	kernel_neon_begin();
-	sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform);
+	sha1_base_do_finalize(desc, __sha1_ce_transform);
 	kernel_neon_end();
 	return sha1_base_finish(desc, out);
 }
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 6f728a419009..3f9d0f326987 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -75,7 +75,7 @@
 	 *			  int blocks)
 	 */
 	.text
-ENTRY(sha2_ce_transform)
+SYM_FUNC_START(sha2_ce_transform)
 	frame_push	3
 
 	mov		x19, x0
@@ -166,4 +166,4 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 4:	st1		{dgav.4s, dgbv.4s}, [x19]
 	frame_pop
 	ret
-ENDPROC(sha2_ce_transform)
+SYM_FUNC_END(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 604a01a4ede6..a8e67bafba3d 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -28,6 +28,13 @@ struct sha256_ce_state {
 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,
@@ -35,6 +42,12 @@ const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
 
 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)
 {
@@ -42,12 +55,11 @@ static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
 
 	if (!crypto_simd_usable())
 		return sha256_base_do_update(desc, data, len,
-				(sha256_block_fn *)sha256_block_data_order);
+				__sha256_block_data_order);
 
 	sctx->finalize = 0;
 	kernel_neon_begin();
-	sha256_base_do_update(desc, data, len,
-			      (sha256_block_fn *)sha2_ce_transform);
+	sha256_base_do_update(desc, data, len, __sha2_ce_transform);
 	kernel_neon_end();
 
 	return 0;
@@ -62,9 +74,8 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 	if (!crypto_simd_usable()) {
 		if (len)
 			sha256_base_do_update(desc, data, len,
-				(sha256_block_fn *)sha256_block_data_order);
-		sha256_base_do_finalize(desc,
-				(sha256_block_fn *)sha256_block_data_order);
+				__sha256_block_data_order);
+		sha256_base_do_finalize(desc, __sha256_block_data_order);
 		return sha256_base_finish(desc, out);
 	}
 
@@ -75,11 +86,9 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 	sctx->finalize = finalize;
 
 	kernel_neon_begin();
-	sha256_base_do_update(desc, data, len,
-			      (sha256_block_fn *)sha2_ce_transform);
+	sha256_base_do_update(desc, data, len, __sha2_ce_transform);
 	if (!finalize)
-		sha256_base_do_finalize(desc,
-					(sha256_block_fn *)sha2_ce_transform);
+		sha256_base_do_finalize(desc, __sha2_ce_transform);
 	kernel_neon_end();
 	return sha256_base_finish(desc, out);
 }
@@ -89,14 +98,13 @@ 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_fn *)sha256_block_data_order);
+		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, (sha256_block_fn *)sha2_ce_transform);
+	sha256_base_do_finalize(desc, __sha2_ce_transform);
 	kernel_neon_end();
 	return sha256_base_finish(desc, out);
 }
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index 999da59f03a9..ddf4a0d85c1c 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -27,14 +27,26 @@ 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_fn *)sha256_block_data_order);
+				     __sha256_block_data_order);
 }
 
 static int crypto_sha256_arm64_finup(struct shash_desc *desc, const u8 *data,
@@ -42,9 +54,8 @@ static int crypto_sha256_arm64_finup(struct shash_desc *desc, const u8 *data,
 {
 	if (len)
 		sha256_base_do_update(desc, data, len,
-				(sha256_block_fn *)sha256_block_data_order);
-	sha256_base_do_finalize(desc,
-				(sha256_block_fn *)sha256_block_data_order);
+				      __sha256_block_data_order);
+	sha256_base_do_finalize(desc, __sha256_block_data_order);
 
 	return sha256_base_finish(desc, out);
 }
@@ -87,7 +98,7 @@ static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
 
 	if (!crypto_simd_usable())
 		return sha256_base_do_update(desc, data, len,
-				(sha256_block_fn *)sha256_block_data_order);
+				__sha256_block_data_order);
 
 	while (len > 0) {
 		unsigned int chunk = len;
@@ -103,8 +114,7 @@ static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
 				sctx->count % SHA256_BLOCK_SIZE;
 
 		kernel_neon_begin();
-		sha256_base_do_update(desc, data, chunk,
-				      (sha256_block_fn *)sha256_block_neon);
+		sha256_base_do_update(desc, data, chunk, __sha256_block_neon);
 		kernel_neon_end();
 		data += chunk;
 		len -= chunk;
@@ -118,15 +128,13 @@ static int sha256_finup_neon(struct shash_desc *desc, const u8 *data,
 	if (!crypto_simd_usable()) {
 		if (len)
 			sha256_base_do_update(desc, data, len,
-				(sha256_block_fn *)sha256_block_data_order);
-		sha256_base_do_finalize(desc,
-				(sha256_block_fn *)sha256_block_data_order);
+				__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_fn *)sha256_block_neon);
+		sha256_base_do_finalize(desc, __sha256_block_neon);
 		kernel_neon_end();
 	}
 	return sha256_base_finish(desc, out);
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
index a7d587fa54f6..1cfb768df350 100644
--- a/arch/arm64/crypto/sha3-ce-core.S
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -40,7 +40,7 @@
 	 * sha3_ce_transform(u64 *st, const u8 *data, int blocks, int dg_size)
 	 */
 	.text
-ENTRY(sha3_ce_transform)
+SYM_FUNC_START(sha3_ce_transform)
 	frame_push	4
 
 	mov	x19, x0
@@ -218,7 +218,7 @@ ENTRY(sha3_ce_transform)
 	st1	{v24.1d}, [x19]
 	frame_pop
 	ret
-ENDPROC(sha3_ce_transform)
+SYM_FUNC_END(sha3_ce_transform)
 
 	.section	".rodata", "a"
 	.align		8
diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S
index ce65e3abe4f2..cde606c0323e 100644
--- a/arch/arm64/crypto/sha512-ce-core.S
+++ b/arch/arm64/crypto/sha512-ce-core.S
@@ -106,7 +106,7 @@
 	 *			  int blocks)
 	 */
 	.text
-ENTRY(sha512_ce_transform)
+SYM_FUNC_START(sha512_ce_transform)
 	frame_push	3
 
 	mov		x19, x0
@@ -216,4 +216,4 @@ CPU_LE(	rev64		v19.16b, v19.16b	)
 3:	st1		{v8.2d-v11.2d}, [x19]
 	frame_pop
 	ret
-ENDPROC(sha512_ce_transform)
+SYM_FUNC_END(sha512_ce_transform)
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
index 2369540040aa..dc890a719f54 100644
--- a/arch/arm64/crypto/sha512-ce-glue.c
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -29,16 +29,21 @@ asmlinkage void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
 
 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_fn *)sha512_block_data_order);
+					     __sha512_block_data_order);
 
 	kernel_neon_begin();
-	sha512_base_do_update(desc, data, len,
-			      (sha512_block_fn *)sha512_ce_transform);
+	sha512_base_do_update(desc, data, len, sha512_ce_transform);
 	kernel_neon_end();
 
 	return 0;
@@ -50,16 +55,14 @@ static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
 	if (!crypto_simd_usable()) {
 		if (len)
 			sha512_base_do_update(desc, data, len,
-				(sha512_block_fn *)sha512_block_data_order);
-		sha512_base_do_finalize(desc,
-				(sha512_block_fn *)sha512_block_data_order);
+					      __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_block_fn *)sha512_ce_transform);
-	sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_ce_transform);
+	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);
 }
@@ -67,13 +70,12 @@ static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
 static int sha512_ce_final(struct shash_desc *desc, u8 *out)
 {
 	if (!crypto_simd_usable()) {
-		sha512_base_do_finalize(desc,
-				(sha512_block_fn *)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_finalize(desc, (sha512_block_fn *)sha512_ce_transform);
+	sha512_base_do_finalize(desc, sha512_ce_transform);
 	kernel_neon_end();
 	return sha512_base_finish(desc, out);
 }
diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c
index d915c656e5fe..78d3083de6b7 100644
--- a/arch/arm64/crypto/sha512-glue.c
+++ b/arch/arm64/crypto/sha512-glue.c
@@ -20,15 +20,21 @@ MODULE_LICENSE("GPL v2");
 MODULE_ALIAS_CRYPTO("sha384");
 MODULE_ALIAS_CRYPTO("sha512");
 
-asmlinkage void sha512_block_data_order(u32 *digest, const void *data,
+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_fn *)sha512_block_data_order);
+				     __sha512_block_data_order);
 }
 
 static int sha512_finup(struct shash_desc *desc, const u8 *data,
@@ -36,9 +42,8 @@ static int sha512_finup(struct shash_desc *desc, const u8 *data,
 {
 	if (len)
 		sha512_base_do_update(desc, data, len,
-			(sha512_block_fn *)sha512_block_data_order);
-	sha512_base_do_finalize(desc,
-			(sha512_block_fn *)sha512_block_data_order);
+				      __sha512_block_data_order);
+	sha512_base_do_finalize(desc, __sha512_block_data_order);
 
 	return sha512_base_finish(desc, out);
 }
diff --git a/arch/arm64/crypto/sm3-ce-core.S b/arch/arm64/crypto/sm3-ce-core.S
index d50d187906cb..ef97d3187cb7 100644
--- a/arch/arm64/crypto/sm3-ce-core.S
+++ b/arch/arm64/crypto/sm3-ce-core.S
@@ -73,7 +73,7 @@
 	 *                       int blocks)
 	 */
 	.text
-ENTRY(sm3_ce_transform)
+SYM_FUNC_START(sm3_ce_transform)
 	/* load state */
 	ld1		{v8.4s-v9.4s}, [x0]
 	rev64		v8.4s, v8.4s
@@ -131,7 +131,7 @@ CPU_LE(	rev32		v3.16b, v3.16b		)
 	ext		v9.16b, v9.16b, v9.16b, #8
 	st1		{v8.4s-v9.4s}, [x0]
 	ret
-ENDPROC(sm3_ce_transform)
+SYM_FUNC_END(sm3_ce_transform)
 
 	.section	".rodata", "a"
 	.align		3
diff --git a/arch/arm64/crypto/sm4-ce-core.S b/arch/arm64/crypto/sm4-ce-core.S
index af3bfbc3f4d4..4ac6cfbc5797 100644
--- a/arch/arm64/crypto/sm4-ce-core.S
+++ b/arch/arm64/crypto/sm4-ce-core.S
@@ -15,7 +15,7 @@
 	 * void sm4_ce_do_crypt(const u32 *rk, u32 *out, const u32 *in);
 	 */
 	.text
-ENTRY(sm4_ce_do_crypt)
+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		)
@@ -33,4 +33,4 @@ CPU_LE(	rev32		v8.16b, v8.16b		)
 CPU_LE(	rev32		v8.16b, v8.16b		)
 	st1		{v8.4s}, [x1]
 	ret
-ENDPROC(sm4_ce_do_crypt)
+SYM_FUNC_END(sm4_ce_do_crypt)