diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S
index 6a0b15e7196a..ef73a3ab8726 100644
--- a/arch/x86/crypto/nh-avx2-x86_64.S
+++ b/arch/x86/crypto/nh-avx2-x86_64.S
@@ -8,6 +8,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 #define		PASS0_SUMS	%ymm0
 #define		PASS1_SUMS	%ymm1
@@ -65,11 +66,11 @@
 
 /*
  * void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
- *		u8 hash[NH_HASH_BYTES])
+ *		__le64 hash[NH_NUM_PASSES])
  *
  * It's guaranteed that message_len % 16 == 0.
  */
-SYM_FUNC_START(nh_avx2)
+SYM_TYPED_FUNC_START(nh_avx2)
 
 	vmovdqu		0x00(KEY), K0
 	vmovdqu		0x10(KEY), K1
diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S
index 34c567bbcb4f..75fb994b6d17 100644
--- a/arch/x86/crypto/nh-sse2-x86_64.S
+++ b/arch/x86/crypto/nh-sse2-x86_64.S
@@ -8,6 +8,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 #define		PASS0_SUMS	%xmm0
 #define		PASS1_SUMS	%xmm1
@@ -67,11 +68,11 @@
 
 /*
  * void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
- *		u8 hash[NH_HASH_BYTES])
+ *		__le64 hash[NH_NUM_PASSES])
  *
  * It's guaranteed that message_len % 16 == 0.
  */
-SYM_FUNC_START(nh_sse2)
+SYM_TYPED_FUNC_START(nh_sse2)
 
 	movdqu		0x00(KEY), K0
 	movdqu		0x10(KEY), K1
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index 8ea5ab0f1ca7..46b036204ed9 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -14,14 +14,7 @@
 #include <asm/simd.h>
 
 asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
-			u8 hash[NH_HASH_BYTES]);
-
-/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */
-static void _nh_avx2(const u32 *key, const u8 *message, size_t message_len,
-		     __le64 hash[NH_NUM_PASSES])
-{
-	nh_avx2(key, message, message_len, (u8 *)hash);
-}
+			__le64 hash[NH_NUM_PASSES]);
 
 static int nhpoly1305_avx2_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
@@ -33,7 +26,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc,
 		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_fpu_begin();
-		crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2);
+		crypto_nhpoly1305_update_helper(desc, src, n, nh_avx2);
 		kernel_fpu_end();
 		src += n;
 		srclen -= n;
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index 2b353d42ed13..4a4970d75107 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -14,14 +14,7 @@
 #include <asm/simd.h>
 
 asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
-			u8 hash[NH_HASH_BYTES]);
-
-/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */
-static void _nh_sse2(const u32 *key, const u8 *message, size_t message_len,
-		     __le64 hash[NH_NUM_PASSES])
-{
-	nh_sse2(key, message, message_len, (u8 *)hash);
-}
+			__le64 hash[NH_NUM_PASSES]);
 
 static int nhpoly1305_sse2_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
@@ -33,7 +26,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc,
 		unsigned int n = min_t(unsigned int, srclen, SZ_4K);
 
 		kernel_fpu_begin();
-		crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2);
+		crypto_nhpoly1305_update_helper(desc, src, n, nh_sse2);
 		kernel_fpu_end();
 		src += n;
 		srclen -= n;