crypto: x86/sm4 - fix crash with CFI enabled

sm4_aesni_avx_ctr_enc_blk8(), sm4_aesni_avx_cbc_dec_blk8(),
sm4_aesni_avx_cfb_dec_blk8(), sm4_aesni_avx2_ctr_enc_blk16(),
sm4_aesni_avx2_cbc_dec_blk16(), and sm4_aesni_avx2_cfb_dec_blk16() are
called via indirect function calls.  Therefore they need to use
SYM_TYPED_FUNC_START instead of SYM_FUNC_START to cause their type
hashes to be emitted when the kernel is built with CONFIG_CFI_CLANG=y.
Otherwise, the code crashes with a CFI failure.

(Or at least that should be the case.  For some reason the CFI checks in
sm4_avx_cbc_decrypt(), sm4_avx_cfb_decrypt(), and sm4_avx_ctr_crypt()
are not always being generated, using current tip-of-tree clang.
Anyway, this patch is a good idea anyway.)

Fixes: ccace936 ("x86: Add types to indirectly called assembly functions")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/sm4-aesni-avx-asm_64.S

@@ -14,6 +14,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 
 #define rRIP         (%rip)
@@ -420,7 +421,7 @@ SYM_FUNC_END(sm4_aesni_avx_crypt8)
  *                                 const u8 *src, u8 *iv)
  */
 .align 8
-SYM_FUNC_START(sm4_aesni_avx_ctr_enc_blk8)
+SYM_TYPED_FUNC_START(sm4_aesni_avx_ctr_enc_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
 	 *	%rsi: dst (8 blocks)
@@ -495,7 +496,7 @@ SYM_FUNC_END(sm4_aesni_avx_ctr_enc_blk8)
  *                                 const u8 *src, u8 *iv)
  */
 .align 8
-SYM_FUNC_START(sm4_aesni_avx_cbc_dec_blk8)
+SYM_TYPED_FUNC_START(sm4_aesni_avx_cbc_dec_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
 	 *	%rsi: dst (8 blocks)
@@ -545,7 +546,7 @@ SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8)
  *                                 const u8 *src, u8 *iv)
  */
 .align 8
-SYM_FUNC_START(sm4_aesni_avx_cfb_dec_blk8)
+SYM_TYPED_FUNC_START(sm4_aesni_avx_cfb_dec_blk8)
 	/* input:
 	 *	%rdi: round key array, CTX
 	 *	%rsi: dst (8 blocks)

arch/x86/crypto/sm4-aesni-avx2-asm_64.S

@@ -14,6 +14,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 
 #define rRIP         (%rip)
@@ -282,7 +283,7 @@ SYM_FUNC_END(__sm4_crypt_blk16)
  *                                   const u8 *src, u8 *iv)
  */
 .align 8
-SYM_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16)
+SYM_TYPED_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
 	 *	%rsi: dst (16 blocks)
@@ -395,7 +396,7 @@ SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16)
  *                                   const u8 *src, u8 *iv)
  */
 .align 8
-SYM_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
+SYM_TYPED_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
 	 *	%rsi: dst (16 blocks)
@@ -449,7 +450,7 @@ SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16)
  *                                   const u8 *src, u8 *iv)
  */
 .align 8
-SYM_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
+SYM_TYPED_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16)
 	/* input:
 	 *	%rdi: round key array, CTX
 	 *	%rsi: dst (16 blocks)