diff mbox series

[v7,07/28] x86/asm/crypto: annotate local functions

Message ID 20190130124711.12463-8-jslaby@suse.cz (mailing list archive)
State Not Applicable
Delegated to: Herbert Xu
Headers show
Series None | expand

Commit Message

Jiri Slaby Jan. 30, 2019, 12:46 p.m. UTC 
Use the newly added SYM_FUNC_START_LOCAL to annotate starts of all
functions which do not have ".globl" annotation, but their ends are
annotated by ENDPROC. This is needed to balance ENDPROC for tools that
generate debuginfo.

To be symmetric, we also convert their ENDPROCs to the new SYM_FUNC_END.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <x86@kernel.org>
Cc: <linux-crypto@vger.kernel.org>
---
 arch/x86/crypto/aegis128-aesni-asm.S         |  8 ++--
 arch/x86/crypto/aegis128l-aesni-asm.S        |  8 ++--
 arch/x86/crypto/aegis256-aesni-asm.S         |  8 ++--
 arch/x86/crypto/aesni-intel_asm.S            | 49 ++++++++------------
 arch/x86/crypto/camellia-aesni-avx-asm_64.S  | 20 ++++----
 arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 20 ++++----
 arch/x86/crypto/cast5-avx-x86_64-asm_64.S    |  8 ++--
 arch/x86/crypto/cast6-avx-x86_64-asm_64.S    |  8 ++--
 arch/x86/crypto/chacha-ssse3-x86_64.S        |  4 +-
 arch/x86/crypto/ghash-clmulni-intel_asm.S    |  4 +-
 arch/x86/crypto/morus1280-avx2-asm.S         | 16 +++----
 arch/x86/crypto/morus1280-sse2-asm.S         | 16 +++----
 arch/x86/crypto/morus640-sse2-asm.S          | 16 +++----
 arch/x86/crypto/serpent-avx-x86_64-asm_64.S  |  8 ++--
 arch/x86/crypto/serpent-avx2-asm_64.S        |  8 ++--
 arch/x86/crypto/twofish-avx-x86_64-asm_64.S  |  8 ++--
 16 files changed, 100 insertions(+), 109 deletions(-)

Comments

Borislav Petkov Feb. 25, 2019, 10:13 a.m. UTC | #1 
On Wed, Jan 30, 2019 at 01:46:50PM +0100, Jiri Slaby wrote:
> Use the newly added SYM_FUNC_START_LOCAL to annotate starts of all
> functions which do not have ".globl" annotation, but their ends are
> annotated by ENDPROC. This is needed to balance ENDPROC for tools that
> generate debuginfo.
> 
> To be symmetric, we also convert their ENDPROCs to the new SYM_FUNC_END.
> 
> Signed-off-by: Jiri Slaby <jslaby@suse.cz>
> Cc: Herbert Xu <herbert@gondor.apana.org.au>
> Cc: "David S. Miller" <davem@davemloft.net>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: "H. Peter Anvin" <hpa@zytor.com>
> Cc: <x86@kernel.org>
> Cc: <linux-crypto@vger.kernel.org>
> ---
>  arch/x86/crypto/aegis128-aesni-asm.S         |  8 ++--
>  arch/x86/crypto/aegis128l-aesni-asm.S        |  8 ++--
>  arch/x86/crypto/aegis256-aesni-asm.S         |  8 ++--
>  arch/x86/crypto/aesni-intel_asm.S            | 49 ++++++++------------
>  arch/x86/crypto/camellia-aesni-avx-asm_64.S  | 20 ++++----
>  arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 20 ++++----
>  arch/x86/crypto/cast5-avx-x86_64-asm_64.S    |  8 ++--
>  arch/x86/crypto/cast6-avx-x86_64-asm_64.S    |  8 ++--
>  arch/x86/crypto/chacha-ssse3-x86_64.S        |  4 +-
>  arch/x86/crypto/ghash-clmulni-intel_asm.S    |  4 +-
>  arch/x86/crypto/morus1280-avx2-asm.S         | 16 +++----
>  arch/x86/crypto/morus1280-sse2-asm.S         | 16 +++----
>  arch/x86/crypto/morus640-sse2-asm.S          | 16 +++----
>  arch/x86/crypto/serpent-avx-x86_64-asm_64.S  |  8 ++--
>  arch/x86/crypto/serpent-avx2-asm_64.S        |  8 ++--
>  arch/x86/crypto/twofish-avx-x86_64-asm_64.S  |  8 ++--
>  16 files changed, 100 insertions(+), 109 deletions(-)
> 
> diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
> index 5f7e43d4f64a..87b94664296a 100644
> --- a/arch/x86/crypto/aegis128-aesni-asm.S
> +++ b/arch/x86/crypto/aegis128-aesni-asm.S
> @@ -74,7 +74,7 @@
>   *   %r8
>   *   %r9
>   */
> -__load_partial:
> +SYM_FUNC_START_LOCAL(__load_partial)

Btw, here's what I mean with it being problematic when the global symbol
names are not distinctive enough:

arch/x86/crypto/aegis128-aesni-asm.S:77:SYM_FUNC_START_LOCAL(__load_partial)
arch/x86/crypto/aegis128l-aesni-asm.S:68:SYM_FUNC_START_LOCAL(__load_partial)
arch/x86/crypto/aegis256-aesni-asm.S:61:SYM_FUNC_START_LOCAL(__load_partial)
arch/x86/crypto/morus1280-avx2-asm.S:115:SYM_FUNC_START_LOCAL(__load_partial)
arch/x86/crypto/morus1280-sse2-asm.S:237:SYM_FUNC_START_LOCAL(__load_partial)
arch/x86/crypto/morus640-sse2-asm.S:115:SYM_FUNC_START_LOCAL(__load_partial)

There are a bunch of those __{load,store}_partial labels and staring at
traces with them in it does not really help, unless you know which one
is it.

Should not be addressed by your patchset but those should be local
labels...
diff mbox series

Patch

diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
index 5f7e43d4f64a..87b94664296a 100644
--- a/arch/x86/crypto/aegis128-aesni-asm.S
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -74,7 +74,7 @@ 
  *   %r8
  *   %r9
  */
-__load_partial:
+SYM_FUNC_START_LOCAL(__load_partial)
 	xor %r9d, %r9d
 	pxor MSG, MSG
 
@@ -126,7 +126,7 @@  __load_partial:
 
 .Lld_partial_8:
 	ret
-ENDPROC(__load_partial)
+SYM_FUNC_END(__load_partial)
 
 /*
  * __store_partial: internal ABI
@@ -140,7 +140,7 @@  ENDPROC(__load_partial)
  *   %r9
  *   %r10
  */
-__store_partial:
+SYM_FUNC_START_LOCAL(__store_partial)
 	mov LEN, %r8
 	mov DST, %r9
 
@@ -184,7 +184,7 @@  __store_partial:
 
 .Lst_partial_1:
 	ret
-ENDPROC(__store_partial)
+SYM_FUNC_END(__store_partial)
 
 /*
  * void crypto_aegis128_aesni_init(void *state, const void *key, const void *iv);
diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S
index 491dd61c845c..9f79a2c6752a 100644
--- a/arch/x86/crypto/aegis128l-aesni-asm.S
+++ b/arch/x86/crypto/aegis128l-aesni-asm.S
@@ -65,7 +65,7 @@ 
  *   %r8
  *   %r9
  */
-__load_partial:
+SYM_FUNC_START_LOCAL(__load_partial)
 	xor %r9d, %r9d
 	pxor MSG0, MSG0
 	pxor MSG1, MSG1
@@ -126,7 +126,7 @@  __load_partial:
 
 .Lld_partial_16:
 	ret
-ENDPROC(__load_partial)
+SYM_FUNC_END(__load_partial)
 
 /*
  * __store_partial: internal ABI
@@ -141,7 +141,7 @@  ENDPROC(__load_partial)
  *   %r9
  *   %r10
  */
-__store_partial:
+SYM_FUNC_START_LOCAL(__store_partial)
 	mov LEN, %r8
 	mov DST, %r9
 
@@ -195,7 +195,7 @@  __store_partial:
 
 .Lst_partial_1:
 	ret
-ENDPROC(__store_partial)
+SYM_FUNC_END(__store_partial)
 
 .macro update
 	movdqa STATE7, T0
diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S
index 8870c7c5d9a4..e974a876c627 100644
--- a/arch/x86/crypto/aegis256-aesni-asm.S
+++ b/arch/x86/crypto/aegis256-aesni-asm.S
@@ -58,7 +58,7 @@ 
  *   %r8
  *   %r9
  */
-__load_partial:
+SYM_FUNC_START_LOCAL(__load_partial)
 	xor %r9d, %r9d
 	pxor MSG, MSG
 
@@ -110,7 +110,7 @@  __load_partial:
 
 .Lld_partial_8:
 	ret
-ENDPROC(__load_partial)
+SYM_FUNC_END(__load_partial)
 
 /*
  * __store_partial: internal ABI
@@ -124,7 +124,7 @@  ENDPROC(__load_partial)
  *   %r9
  *   %r10
  */
-__store_partial:
+SYM_FUNC_START_LOCAL(__store_partial)
 	mov LEN, %r8
 	mov DST, %r9
 
@@ -168,7 +168,7 @@  __store_partial:
 
 .Lst_partial_1:
 	ret
-ENDPROC(__store_partial)
+SYM_FUNC_END(__store_partial)
 
 .macro update
 	movdqa STATE5, T0
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index cb2deb61c5d9..6c349e844581 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -1763,7 +1763,7 @@  ENDPROC(aesni_gcm_finalize)
 
 .align 4
 _key_expansion_128:
-_key_expansion_256a:
+SYM_FUNC_START_LOCAL(_key_expansion_256a)
 	pshufd $0b11111111, %xmm1, %xmm1
 	shufps $0b00010000, %xmm0, %xmm4
 	pxor %xmm4, %xmm0
@@ -1774,10 +1774,9 @@  _key_expansion_256a:
 	add $0x10, TKEYP
 	ret
 ENDPROC(_key_expansion_128)
-ENDPROC(_key_expansion_256a)
+SYM_FUNC_END(_key_expansion_256a)
 
-.align 4
-_key_expansion_192a:
+SYM_FUNC_START_LOCAL(_key_expansion_192a)
 	pshufd $0b01010101, %xmm1, %xmm1
 	shufps $0b00010000, %xmm0, %xmm4
 	pxor %xmm4, %xmm0
@@ -1799,10 +1798,9 @@  _key_expansion_192a:
 	movaps %xmm1, 0x10(TKEYP)
 	add $0x20, TKEYP
 	ret
-ENDPROC(_key_expansion_192a)
+SYM_FUNC_END(_key_expansion_192a)
 
-.align 4
-_key_expansion_192b:
+SYM_FUNC_START_LOCAL(_key_expansion_192b)
 	pshufd $0b01010101, %xmm1, %xmm1
 	shufps $0b00010000, %xmm0, %xmm4
 	pxor %xmm4, %xmm0
@@ -1819,10 +1817,9 @@  _key_expansion_192b:
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
 	ret
-ENDPROC(_key_expansion_192b)
+SYM_FUNC_END(_key_expansion_192b)
 
-.align 4
-_key_expansion_256b:
+SYM_FUNC_START_LOCAL(_key_expansion_256b)
 	pshufd $0b10101010, %xmm1, %xmm1
 	shufps $0b00010000, %xmm2, %xmm4
 	pxor %xmm4, %xmm2
@@ -1832,7 +1829,7 @@  _key_expansion_256b:
 	movaps %xmm2, (TKEYP)
 	add $0x10, TKEYP
 	ret
-ENDPROC(_key_expansion_256b)
+SYM_FUNC_END(_key_expansion_256b)
 
 /*
  * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
@@ -1985,8 +1982,7 @@  ENDPROC(aesni_enc)
  *	KEY
  *	TKEYP (T1)
  */
-.align 4
-_aesni_enc1:
+SYM_FUNC_START_LOCAL(_aesni_enc1)
 	movaps (KEYP), KEY		# key
 	mov KEYP, TKEYP
 	pxor KEY, STATE		# round 0
@@ -2029,7 +2025,7 @@  _aesni_enc1:
 	movaps 0x70(TKEYP), KEY
 	AESENCLAST KEY STATE
 	ret
-ENDPROC(_aesni_enc1)
+SYM_FUNC_END(_aesni_enc1)
 
 /*
  * _aesni_enc4:	internal ABI
@@ -2049,8 +2045,7 @@  ENDPROC(_aesni_enc1)
  *	KEY
  *	TKEYP (T1)
  */
-.align 4
-_aesni_enc4:
+SYM_FUNC_START_LOCAL(_aesni_enc4)
 	movaps (KEYP), KEY		# key
 	mov KEYP, TKEYP
 	pxor KEY, STATE1		# round 0
@@ -2138,7 +2133,7 @@  _aesni_enc4:
 	AESENCLAST KEY STATE3
 	AESENCLAST KEY STATE4
 	ret
-ENDPROC(_aesni_enc4)
+SYM_FUNC_END(_aesni_enc4)
 
 /*
  * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
@@ -2177,8 +2172,7 @@  ENDPROC(aesni_dec)
  *	KEY
  *	TKEYP (T1)
  */
-.align 4
-_aesni_dec1:
+SYM_FUNC_START_LOCAL(_aesni_dec1)
 	movaps (KEYP), KEY		# key
 	mov KEYP, TKEYP
 	pxor KEY, STATE		# round 0
@@ -2221,7 +2215,7 @@  _aesni_dec1:
 	movaps 0x70(TKEYP), KEY
 	AESDECLAST KEY STATE
 	ret
-ENDPROC(_aesni_dec1)
+SYM_FUNC_END(_aesni_dec1)
 
 /*
  * _aesni_dec4:	internal ABI
@@ -2241,8 +2235,7 @@  ENDPROC(_aesni_dec1)
  *	KEY
  *	TKEYP (T1)
  */
-.align 4
-_aesni_dec4:
+SYM_FUNC_START_LOCAL(_aesni_dec4)
 	movaps (KEYP), KEY		# key
 	mov KEYP, TKEYP
 	pxor KEY, STATE1		# round 0
@@ -2330,7 +2323,7 @@  _aesni_dec4:
 	AESDECLAST KEY STATE3
 	AESDECLAST KEY STATE4
 	ret
-ENDPROC(_aesni_dec4)
+SYM_FUNC_END(_aesni_dec4)
 
 /*
  * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2608,8 +2601,7 @@  ENDPROC(aesni_cbc_dec)
  *	INC:	== 1, in little endian
  *	BSWAP_MASK == endian swapping mask
  */
-.align 4
-_aesni_inc_init:
+SYM_FUNC_START_LOCAL(_aesni_inc_init)
 	movaps .Lbswap_mask, BSWAP_MASK
 	movaps IV, CTR
 	PSHUFB_XMM BSWAP_MASK CTR
@@ -2617,7 +2609,7 @@  _aesni_inc_init:
 	MOVQ_R64_XMM TCTR_LOW INC
 	MOVQ_R64_XMM CTR TCTR_LOW
 	ret
-ENDPROC(_aesni_inc_init)
+SYM_FUNC_END(_aesni_inc_init)
 
 /*
  * _aesni_inc:		internal ABI
@@ -2634,8 +2626,7 @@  ENDPROC(_aesni_inc_init)
  *	CTR:	== output IV, in little endian
  *	TCTR_LOW: == lower qword of CTR
  */
-.align 4
-_aesni_inc:
+SYM_FUNC_START_LOCAL(_aesni_inc)
 	paddq INC, CTR
 	add $1, TCTR_LOW
 	jnc .Linc_low
@@ -2646,7 +2637,7 @@  _aesni_inc:
 	movaps CTR, IV
 	PSHUFB_XMM BSWAP_MASK IV
 	ret
-ENDPROC(_aesni_inc)
+SYM_FUNC_END(_aesni_inc)
 
 /*
  * void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index a14af6eb09cb..f4408ca55fdb 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -189,20 +189,20 @@ 
  * larger and would only be 0.5% faster (on sandy-bridge).
  */
 .align 8
-roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd:
+SYM_FUNC_START_LOCAL(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 	roundsm16(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
 		  %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15,
 		  %rcx, (%r9));
 	ret;
-ENDPROC(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
+SYM_FUNC_END(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
 .align 8
-roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
+SYM_FUNC_START_LOCAL(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	roundsm16(%xmm4, %xmm5, %xmm6, %xmm7, %xmm0, %xmm1, %xmm2, %xmm3,
 		  %xmm12, %xmm13, %xmm14, %xmm15, %xmm8, %xmm9, %xmm10, %xmm11,
 		  %rax, (%r9));
 	ret;
-ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
+SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 /*
  * IN/OUT:
@@ -722,7 +722,7 @@  ENDPROC(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 .text
 
 .align 8
-__camellia_enc_blk16:
+SYM_FUNC_START_LOCAL(__camellia_enc_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rax: temporary storage, 256 bytes
@@ -806,10 +806,10 @@  __camellia_enc_blk16:
 		     %xmm15, %rax, %rcx, 24);
 
 	jmp .Lenc_done;
-ENDPROC(__camellia_enc_blk16)
+SYM_FUNC_END(__camellia_enc_blk16)
 
 .align 8
-__camellia_dec_blk16:
+SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rax: temporary storage, 256 bytes
@@ -891,7 +891,7 @@  __camellia_dec_blk16:
 	      ((key_table + (24) * 8) + 4)(CTX));
 
 	jmp .Ldec_max24;
-ENDPROC(__camellia_dec_blk16)
+SYM_FUNC_END(__camellia_dec_blk16)
 
 ENTRY(camellia_ecb_enc_16way)
 	/* input:
@@ -1120,7 +1120,7 @@  ENDPROC(camellia_ctr_16way)
 	vpxor tmp, iv, iv;
 
 .align 8
-camellia_xts_crypt_16way:
+SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -1254,7 +1254,7 @@  camellia_xts_crypt_16way:
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_xts_crypt_16way)
+SYM_FUNC_END(camellia_xts_crypt_16way)
 
 ENTRY(camellia_xts_enc_16way)
 	/* input:
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index b66bbfa62f50..916a3e2b8ea4 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -228,20 +228,20 @@ 
  * larger and would only marginally faster.
  */
 .align 8
-roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd:
+SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 	roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7,
 		  %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15,
 		  %rcx, (%r9));
 	ret;
-ENDPROC(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
+SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)
 
 .align 8
-roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
+SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 	roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3,
 		  %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11,
 		  %rax, (%r9));
 	ret;
-ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
+SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 
 /*
  * IN/OUT:
@@ -765,7 +765,7 @@  ENDPROC(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)
 .text
 
 .align 8
-__camellia_enc_blk32:
+SYM_FUNC_START_LOCAL(__camellia_enc_blk32)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rax: temporary storage, 512 bytes
@@ -849,10 +849,10 @@  __camellia_enc_blk32:
 		     %ymm15, %rax, %rcx, 24);
 
 	jmp .Lenc_done;
-ENDPROC(__camellia_enc_blk32)
+SYM_FUNC_END(__camellia_enc_blk32)
 
 .align 8
-__camellia_dec_blk32:
+SYM_FUNC_START_LOCAL(__camellia_dec_blk32)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rax: temporary storage, 512 bytes
@@ -934,7 +934,7 @@  __camellia_dec_blk32:
 	      ((key_table + (24) * 8) + 4)(CTX));
 
 	jmp .Ldec_max24;
-ENDPROC(__camellia_dec_blk32)
+SYM_FUNC_END(__camellia_dec_blk32)
 
 ENTRY(camellia_ecb_enc_32way)
 	/* input:
@@ -1227,7 +1227,7 @@  ENDPROC(camellia_ctr_32way)
 	vpxor tmp1, iv, iv;
 
 .align 8
-camellia_xts_crypt_32way:
+SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (32 blocks)
@@ -1372,7 +1372,7 @@  camellia_xts_crypt_32way:
 
 	FRAME_END
 	ret;
-ENDPROC(camellia_xts_crypt_32way)
+SYM_FUNC_END(camellia_xts_crypt_32way)
 
 ENTRY(camellia_xts_enc_32way)
 	/* input:
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
index 86107c961bb4..b26df120413c 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -224,7 +224,7 @@ 
 .text
 
 .align 16
-__cast5_enc_blk16:
+SYM_FUNC_START_LOCAL(__cast5_enc_blk16)
 	/* input:
 	 *	%rdi: ctx
 	 *	RL1: blocks 1 and 2
@@ -295,10 +295,10 @@  __cast5_enc_blk16:
 	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
 
 	ret;
-ENDPROC(__cast5_enc_blk16)
+SYM_FUNC_END(__cast5_enc_blk16)
 
 .align 16
-__cast5_dec_blk16:
+SYM_FUNC_START_LOCAL(__cast5_dec_blk16)
 	/* input:
 	 *	%rdi: ctx
 	 *	RL1: encrypted blocks 1 and 2
@@ -372,7 +372,7 @@  __cast5_dec_blk16:
 .L__skip_dec:
 	vpsrldq $4, RKR, RKR;
 	jmp .L__dec_tail;
-ENDPROC(__cast5_dec_blk16)
+SYM_FUNC_END(__cast5_dec_blk16)
 
 ENTRY(cast5_ecb_enc_16way)
 	/* input:
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
index 7f30b6f0d72c..0a68e42a00f9 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -262,7 +262,7 @@ 
 .text
 
 .align 8
-__cast6_enc_blk8:
+SYM_FUNC_START_LOCAL(__cast6_enc_blk8)
 	/* input:
 	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -307,10 +307,10 @@  __cast6_enc_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
 	ret;
-ENDPROC(__cast6_enc_blk8)
+SYM_FUNC_END(__cast6_enc_blk8)
 
 .align 8
-__cast6_dec_blk8:
+SYM_FUNC_START_LOCAL(__cast6_dec_blk8)
 	/* input:
 	 *	%rdi: ctx
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
@@ -354,7 +354,7 @@  __cast6_dec_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
 	ret;
-ENDPROC(__cast6_dec_blk8)
+SYM_FUNC_END(__cast6_dec_blk8)
 
 ENTRY(cast6_ecb_enc_8way)
 	/* input:
diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S
index c05a7a963dc3..eb5f7517d28c 100644
--- a/arch/x86/crypto/chacha-ssse3-x86_64.S
+++ b/arch/x86/crypto/chacha-ssse3-x86_64.S
@@ -37,7 +37,7 @@  CTRINC:	.octa 0x00000003000000020000000100000000
  *
  * Clobbers: %r8d, %xmm4-%xmm7
  */
-chacha_permute:
+SYM_FUNC_START_LOCAL(chacha_permute)
 
 	movdqa		ROT8(%rip),%xmm4
 	movdqa		ROT16(%rip),%xmm5
@@ -113,7 +113,7 @@  chacha_permute:
 	jnz		.Ldoubleround
 
 	ret
-ENDPROC(chacha_permute)
+SYM_FUNC_END(chacha_permute)
 
 ENTRY(chacha_block_xor_ssse3)
 	# %rdi: Input state matrix, s
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index f94375a8dcd1..c3db86842578 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -47,7 +47,7 @@ 
  *	T2
  *	T3
  */
-__clmul_gf128mul_ble:
+SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble)
 	movaps DATA, T1
 	pshufd $0b01001110, DATA, T2
 	pshufd $0b01001110, SHASH, T3
@@ -90,7 +90,7 @@  __clmul_gf128mul_ble:
 	pxor T2, T1
 	pxor T1, DATA
 	ret
-ENDPROC(__clmul_gf128mul_ble)
+SYM_FUNC_END(__clmul_gf128mul_ble)
 
 /* void clmul_ghash_mul(char *dst, const u128 *shash) */
 ENTRY(clmul_ghash_mul)
diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S
index de182c460f82..61916af30d94 100644
--- a/arch/x86/crypto/morus1280-avx2-asm.S
+++ b/arch/x86/crypto/morus1280-avx2-asm.S
@@ -70,7 +70,7 @@ 
  * changed:
  *   T0
  */
-__morus1280_update:
+SYM_FUNC_START_LOCAL(__morus1280_update)
 	morus1280_round STATE0, STATE1, STATE2, STATE3, STATE4, 13, MASK1
 	vpxor MSG, STATE1, STATE1
 	morus1280_round STATE1, STATE2, STATE3, STATE4, STATE0, 46, MASK2
@@ -81,7 +81,7 @@  __morus1280_update:
 	vpxor MSG, STATE4, STATE4
 	morus1280_round STATE4, STATE0, STATE1, STATE2, STATE3,  4, MASK1
 	ret
-ENDPROC(__morus1280_update)
+SYM_FUNC_END(__morus1280_update)
 
 /*
  * __morus1280_update_zero: internal ABI
@@ -92,14 +92,14 @@  ENDPROC(__morus1280_update)
  * changed:
  *   T0
  */
-__morus1280_update_zero:
+SYM_FUNC_START_LOCAL(__morus1280_update_zero)
 	morus1280_round STATE0, STATE1, STATE2, STATE3, STATE4, 13, MASK1
 	morus1280_round STATE1, STATE2, STATE3, STATE4, STATE0, 46, MASK2
 	morus1280_round STATE2, STATE3, STATE4, STATE0, STATE1, 38, MASK3
 	morus1280_round STATE3, STATE4, STATE0, STATE1, STATE2,  7, MASK2
 	morus1280_round STATE4, STATE0, STATE1, STATE2, STATE3,  4, MASK1
 	ret
-ENDPROC(__morus1280_update_zero)
+SYM_FUNC_END(__morus1280_update_zero)
 
 /*
  * __load_partial: internal ABI
@@ -112,7 +112,7 @@  ENDPROC(__morus1280_update_zero)
  *   %r8
  *   %r9
  */
-__load_partial:
+SYM_FUNC_START_LOCAL(__load_partial)
 	xor %r9d, %r9d
 	vpxor MSG, MSG, MSG
 
@@ -171,7 +171,7 @@  __load_partial:
 
 .Lld_partial_16:
 	ret
-ENDPROC(__load_partial)
+SYM_FUNC_END(__load_partial)
 
 /*
  * __store_partial: internal ABI
@@ -185,7 +185,7 @@  ENDPROC(__load_partial)
  *   %r9
  *   %r10
  */
-__store_partial:
+SYM_FUNC_START_LOCAL(__store_partial)
 	mov %rcx, %r8
 	mov %rdx, %r9
 
@@ -238,7 +238,7 @@  __store_partial:
 
 .Lst_partial_1:
 	ret
-ENDPROC(__store_partial)
+SYM_FUNC_END(__store_partial)
 
 /*
  * void crypto_morus1280_avx2_init(void *state, const void *key,
diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S
index da5d2905db60..927bb362fa98 100644
--- a/arch/x86/crypto/morus1280-sse2-asm.S
+++ b/arch/x86/crypto/morus1280-sse2-asm.S
@@ -128,7 +128,7 @@ 
  * changed:
  *   T0
  */
-__morus1280_update:
+SYM_FUNC_START_LOCAL(__morus1280_update)
 	morus1280_round \
 		STATE0_LO, STATE0_HI, \
 		STATE1_LO, STATE1_HI, \
@@ -173,7 +173,7 @@  __morus1280_update:
 		STATE3_LO, STATE3_HI, \
 		4, rol1
 	ret
-ENDPROC(__morus1280_update)
+SYM_FUNC_END(__morus1280_update)
 
 /*
  * __morus1280_update_zero: internal ABI
@@ -184,7 +184,7 @@  ENDPROC(__morus1280_update)
  * changed:
  *   T0
  */
-__morus1280_update_zero:
+SYM_FUNC_START_LOCAL(__morus1280_update_zero)
 	morus1280_round \
 		STATE0_LO, STATE0_HI, \
 		STATE1_LO, STATE1_HI, \
@@ -221,7 +221,7 @@  __morus1280_update_zero:
 		STATE3_LO, STATE3_HI, \
 		4, rol1
 	ret
-ENDPROC(__morus1280_update_zero)
+SYM_FUNC_END(__morus1280_update_zero)
 
 /*
  * __load_partial: internal ABI
@@ -234,7 +234,7 @@  ENDPROC(__morus1280_update_zero)
  *   %r8
  *   %r9
  */
-__load_partial:
+SYM_FUNC_START_LOCAL(__load_partial)
 	xor %r9d, %r9d
 	pxor MSG_LO, MSG_LO
 	pxor MSG_HI, MSG_HI
@@ -295,7 +295,7 @@  __load_partial:
 
 .Lld_partial_16:
 	ret
-ENDPROC(__load_partial)
+SYM_FUNC_END(__load_partial)
 
 /*
  * __store_partial: internal ABI
@@ -309,7 +309,7 @@  ENDPROC(__load_partial)
  *   %r9
  *   %r10
  */
-__store_partial:
+SYM_FUNC_START_LOCAL(__store_partial)
 	mov %rcx, %r8
 	mov %rdx, %r9
 
@@ -363,7 +363,7 @@  __store_partial:
 
 .Lst_partial_1:
 	ret
-ENDPROC(__store_partial)
+SYM_FUNC_END(__store_partial)
 
 /*
  * void crypto_morus1280_sse2_init(void *state, const void *key,
diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S
index 414db480250e..4bdd3da7f66c 100644
--- a/arch/x86/crypto/morus640-sse2-asm.S
+++ b/arch/x86/crypto/morus640-sse2-asm.S
@@ -68,7 +68,7 @@ 
  * changed:
  *   T0
  */
-__morus640_update:
+SYM_FUNC_START_LOCAL(__morus640_update)
 	morus640_round STATE0, STATE1, STATE2, STATE3, STATE4,  5, MASK1
 	pxor MSG, STATE1
 	morus640_round STATE1, STATE2, STATE3, STATE4, STATE0, 31, MASK2
@@ -79,7 +79,7 @@  __morus640_update:
 	pxor MSG, STATE4
 	morus640_round STATE4, STATE0, STATE1, STATE2, STATE3, 13, MASK1
 	ret
-ENDPROC(__morus640_update)
+SYM_FUNC_END(__morus640_update)
 
 
 /*
@@ -91,14 +91,14 @@  ENDPROC(__morus640_update)
  * changed:
  *   T0
  */
-__morus640_update_zero:
+SYM_FUNC_START_LOCAL(__morus640_update_zero)
 	morus640_round STATE0, STATE1, STATE2, STATE3, STATE4,  5, MASK1
 	morus640_round STATE1, STATE2, STATE3, STATE4, STATE0, 31, MASK2
 	morus640_round STATE2, STATE3, STATE4, STATE0, STATE1,  7, MASK3
 	morus640_round STATE3, STATE4, STATE0, STATE1, STATE2, 22, MASK2
 	morus640_round STATE4, STATE0, STATE1, STATE2, STATE3, 13, MASK1
 	ret
-ENDPROC(__morus640_update_zero)
+SYM_FUNC_END(__morus640_update_zero)
 
 /*
  * __load_partial: internal ABI
@@ -112,7 +112,7 @@  ENDPROC(__morus640_update_zero)
  *   %r8
  *   %r9
  */
-__load_partial:
+SYM_FUNC_START_LOCAL(__load_partial)
 	xor %r9d, %r9d
 	pxor MSG, MSG
 
@@ -164,7 +164,7 @@  __load_partial:
 
 .Lld_partial_8:
 	ret
-ENDPROC(__load_partial)
+SYM_FUNC_END(__load_partial)
 
 /*
  * __store_partial: internal ABI
@@ -178,7 +178,7 @@  ENDPROC(__load_partial)
  *   %r9
  *   %r10
  */
-__store_partial:
+SYM_FUNC_START_LOCAL(__store_partial)
 	mov %rcx, %r8
 	mov %rdx, %r9
 
@@ -222,7 +222,7 @@  __store_partial:
 
 .Lst_partial_1:
 	ret
-ENDPROC(__store_partial)
+SYM_FUNC_END(__store_partial)
 
 /*
  * void crypto_morus640_sse2_init(void *state, const void *key, const void *iv);
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index 2925077f8c6a..c2d4a1fc9ee8 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -570,7 +570,7 @@ 
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
 .align 8
-__serpent_enc_blk8_avx:
+SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -621,10 +621,10 @@  __serpent_enc_blk8_avx:
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_enc_blk8_avx)
+SYM_FUNC_END(__serpent_enc_blk8_avx)
 
 .align 8
-__serpent_dec_blk8_avx:
+SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
@@ -675,7 +675,7 @@  __serpent_dec_blk8_avx:
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_dec_blk8_avx)
+SYM_FUNC_END(__serpent_dec_blk8_avx)
 
 ENTRY(serpent_ecb_enc_8way_avx)
 	/* input:
diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S
index d67888f2a52a..52c527ce4b18 100644
--- a/arch/x86/crypto/serpent-avx2-asm_64.S
+++ b/arch/x86/crypto/serpent-avx2-asm_64.S
@@ -566,7 +566,7 @@ 
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
 .align 8
-__serpent_enc_blk16:
+SYM_FUNC_START_LOCAL(__serpent_enc_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: plaintext
@@ -617,10 +617,10 @@  __serpent_enc_blk16:
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_enc_blk16)
+SYM_FUNC_END(__serpent_enc_blk16)
 
 .align 8
-__serpent_dec_blk16:
+SYM_FUNC_START_LOCAL(__serpent_dec_blk16)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: ciphertext
@@ -671,7 +671,7 @@  __serpent_dec_blk16:
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
 	ret;
-ENDPROC(__serpent_dec_blk16)
+SYM_FUNC_END(__serpent_dec_blk16)
 
 ENTRY(serpent_ecb_enc_16way)
 	/* input:
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index 73b471da3622..96ddfda4d7b2 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -249,7 +249,7 @@ 
 	vpxor		x3, wkey, x3;
 
 .align 8
-__twofish_enc_blk8:
+SYM_FUNC_START_LOCAL(__twofish_enc_blk8)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
@@ -288,10 +288,10 @@  __twofish_enc_blk8:
 	outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
 
 	ret;
-ENDPROC(__twofish_enc_blk8)
+SYM_FUNC_END(__twofish_enc_blk8)
 
 .align 8
-__twofish_dec_blk8:
+SYM_FUNC_START_LOCAL(__twofish_dec_blk8)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2: encrypted blocks
@@ -328,7 +328,7 @@  __twofish_dec_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
 
 	ret;
-ENDPROC(__twofish_dec_blk8)
+SYM_FUNC_END(__twofish_dec_blk8)
 
 ENTRY(twofish_ecb_enc_8way)
 	/* input: