crypto: arm64 - Use modern annotations for assembly functions

In an effort to clarify and simplify the annotation of assembly functions
in the kernel new macros have been introduced. These replace ENTRY and
ENDPROC and also add a new annotation for static functions which previously
had no ENTRY equivalent. Update the annotations in the crypto code to the
new macros.

There are a small number of files imported from OpenSSL where the assembly
is generated using perl programs, these are not currently annotated at all
and have not been modified.

Signed-off-by: Mark Brown <[e-mail]>
Acked-by: Ard Biesheuvel <[e-mail]>
Signed-off-by: Herbert Xu <[e-mail]>

arch/arm64/crypto/aes-ce-ccm-core.S

···
 	 * 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
···
 	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? */
···
 	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 */
···
 	 * 			   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)

arch/arm64/crypto/aes-ce-core.S

···
 
 	.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
···
 	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
···
 	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)

arch/arm64/crypto/aes-ce.S

···
 #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
 

arch/arm64/crypto/aes-cipher-core.S

···
 	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)

arch/arm64/crypto/aes-modes.S

···
 #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
 
 	/*

arch/arm64/crypto/aes-neon.S

···
 #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

arch/arm64/crypto/aes-neonbs-core.S

···
 	/*
 	 * 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
 
···
 	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
···
 	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
 
···
 	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,
···
 	.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
···
 
 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
···
 	 * 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
···
 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
···
 	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
···
 	 * 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
···
 7:	cbz		x25, 8b
 	st1		{v5.16b}, [x25]
 	b		8b
-ENDPROC(aesbs_ctr_encrypt)
+SYM_FUNC_END(aesbs_ctr_encrypt)

arch/arm64/crypto/chacha-neon-core.S

···
  *
  * Clobbers: w3, x10, v4, v12
  */
-chacha_permute:
+SYM_FUNC_START_LOCAL(chacha_permute)
 
 	adr_l		x10, ROT8
 	ld1		{v12.4s}, [x10]
···
 	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
···
 
 	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
···
 
 	ldp		x29, x30, [sp], #16
 	ret
-ENDPROC(hchacha_block_neon)
+SYM_FUNC_END(hchacha_block_neon)
 
 	a0		.req	w12
 	a1		.req	w13
···
 	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
···
 	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

arch/arm64/crypto/crct10dif-ce-core.S

···
 	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
···
 	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
···
 //
 // 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
 //
···
 //
 // 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

arch/arm64/crypto/ghash-ce-core.S

···
 	 * 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

arch/arm64/crypto/nh-neon-core.S

···
  *
  * 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
···
 	addp		T1.2d, PASS2_SUMS.2d, PASS3_SUMS.2d
 	st1		{T0.16b,T1.16b}, [HASH]
 	ret
-ENDPROC(nh_neon)
+SYM_FUNC_END(nh_neon)

arch/arm64/crypto/sha1-ce-core.S

···
 	 * 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
···
 	str		dgb, [x19, #16]
 	frame_pop
 	ret
-ENDPROC(sha1_ce_transform)
+SYM_FUNC_END(sha1_ce_transform)

arch/arm64/crypto/sha2-ce-core.S

···
 	 *			  int blocks)
 	 */
 	.text
-ENTRY(sha2_ce_transform)
+SYM_FUNC_START(sha2_ce_transform)
 	frame_push	3
 
 	mov		x19, x0
···
 4:	st1		{dgav.4s, dgbv.4s}, [x19]
 	frame_pop
 	ret
-ENDPROC(sha2_ce_transform)
+SYM_FUNC_END(sha2_ce_transform)

arch/arm64/crypto/sha3-ce-core.S

···
 	 * 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
···
 	st1	{v24.1d}, [x19]
 	frame_pop
 	ret
-ENDPROC(sha3_ce_transform)
+SYM_FUNC_END(sha3_ce_transform)
 
 	.section	".rodata", "a"
 	.align		8

arch/arm64/crypto/sha512-ce-core.S

···
 	 *			  int blocks)
 	 */
 	.text
-ENTRY(sha512_ce_transform)
+SYM_FUNC_START(sha512_ce_transform)
 	frame_push	3
 
 	mov		x19, x0
···
 3:	st1		{v8.2d-v11.2d}, [x19]
 	frame_pop
 	ret
-ENDPROC(sha512_ce_transform)
+SYM_FUNC_END(sha512_ce_transform)

arch/arm64/crypto/sm3-ce-core.S

···
 	 *                       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
···
 	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

arch/arm64/crypto/sm4-ce-core.S

···
 	 * 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		)
···
 CPU_LE(	rev32		v8.16b, v8.16b		)
 	st1		{v8.4s}, [x1]
 	ret
-ENDPROC(sm4_ce_do_crypt)
+SYM_FUNC_END(sm4_ce_do_crypt)