Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:
 "Here is the crypto update for 3.9:

   - Added accelerated implementation of crc32 using pclmulqdq.

   - Added test vector for fcrypt.

   - Added support for OMAP4/AM33XX cipher and hash.

   - Fixed loose crypto_user input checks.

   - Misc fixes"

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (43 commits)
  crypto: user - ensure user supplied strings are nul-terminated
  crypto: user - fix empty string test in report API
  crypto: user - fix info leaks in report API
  crypto: caam - Added property fsl,sec-era in SEC4.0 device tree binding.
  crypto: use ERR_CAST
  crypto: atmel-aes - adjust duplicate test
  crypto: crc32-pclmul - Kill warning on x86-32
  crypto: x86/twofish - assembler clean-ups: use ENTRY/ENDPROC, localize jump labels
  crypto: x86/sha1 - assembler clean-ups: use ENTRY/ENDPROC
  crypto: x86/serpent - use ENTRY/ENDPROC for assember functions and localize jump targets
  crypto: x86/salsa20 - assembler cleanup, use ENTRY/ENDPROC for assember functions and rename ECRYPT_* to salsa20_*
  crypto: x86/ghash - assembler clean-up: use ENDPROC at end of assember functions
  crypto: x86/crc32c - assembler clean-up: use ENTRY/ENDPROC
  crypto: cast6-avx: use ENTRY()/ENDPROC() for assembler functions
  crypto: cast5-avx: use ENTRY()/ENDPROC() for assembler functions and localize jump targets
  crypto: camellia-x86_64/aes-ni: use ENTRY()/ENDPROC() for assembler functions and localize jump targets
  crypto: blowfish-x86_64: use ENTRY()/ENDPROC() for assembler functions and localize jump targets
  crypto: aesni-intel - add ENDPROC statements for assembler functions
  crypto: x86/aes - assembler clean-ups: use ENTRY/ENDPROC, localize jump targets
  crypto: testmgr - add test vector for fcrypt
  ...

51 files changed, 2146 insertions, 765 deletions

diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
index 6d21c0288e9e..e4022776ac6e 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
@@ -113,7 +113,7 @@ PROPERTIES
 EXAMPLE
 	crypto@300000 {
 		compatible = "fsl,sec-v4.0";
-		fsl,sec-era = <0x2>;
+		fsl,sec-era = <2>;
 		#address-cells = <1>;
 		#size-cells = <1>;
 		reg = <0x300000 0x10000>;
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index e0ca7c9ac383..63947a8f9f0f 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 
 obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
 obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
+obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
 
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
 twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
@@ -52,3 +53,4 @@ ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
 crc32c-intel-y := crc32c-intel_glue.o
 crc32c-intel-$(CONFIG_CRYPTO_CRC32C_X86_64) += crc32c-pcl-intel-asm_64.o
+crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
diff --git a/arch/x86/crypto/aes-i586-asm_32.S b/arch/x86/crypto/aes-i586-asm_32.S
index b949ec2f9af4..2849dbc59e11 100644
--- a/arch/x86/crypto/aes-i586-asm_32.S
+++ b/arch/x86/crypto/aes-i586-asm_32.S
@@ -36,6 +36,7 @@
 .file "aes-i586-asm.S"
 .text
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 #define tlen 1024   // length of each of 4 'xor' arrays (256 32-bit words)
@@ -219,14 +220,10 @@
 // AES (Rijndael) Encryption Subroutine
 /* void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */
 
-.global  aes_enc_blk
-
 .extern  crypto_ft_tab
 .extern  crypto_fl_tab
 
-.align 4
-
-aes_enc_blk:
+ENTRY(aes_enc_blk)
 	push    %ebp
 	mov     ctx(%esp),%ebp
 
@@ -290,18 +287,15 @@ aes_enc_blk:
 	mov     %r0,(%ebp)
 	pop     %ebp
 	ret
+ENDPROC(aes_enc_blk)
 
 // AES (Rijndael) Decryption Subroutine
 /* void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */
 
-.global  aes_dec_blk
-
 .extern  crypto_it_tab
 .extern  crypto_il_tab
 
-.align 4
-
-aes_dec_blk:
+ENTRY(aes_dec_blk)
 	push    %ebp
 	mov     ctx(%esp),%ebp
 
@@ -365,3 +359,4 @@ aes_dec_blk:
 	mov     %r0,(%ebp)
 	pop     %ebp
 	ret
+ENDPROC(aes_dec_blk)
diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S
index 5b577d5a059b..910565547163 100644
--- a/arch/x86/crypto/aes-x86_64-asm_64.S
+++ b/arch/x86/crypto/aes-x86_64-asm_64.S
@@ -15,6 +15,7 @@
 
 .text
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 #define R1	%rax
@@ -49,10 +50,8 @@
 #define R11	%r11
 
 #define prologue(FUNC,KEY,B128,B192,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11) \
-	.global	FUNC;			\
-	.type	FUNC,@function;		\
-	.align	8;			\
-FUNC:	movq	r1,r2;			\
+	ENTRY(FUNC);			\
+	movq	r1,r2;			\
 	movq	r3,r4;			\
 	leaq	KEY+48(r8),r9;		\
 	movq	r10,r11;		\
@@ -71,14 +70,15 @@ FUNC:	movq	r1,r2;			\
 	je	B192;			\
 	leaq	32(r9),r9;
 
-#define epilogue(r1,r2,r3,r4,r5,r6,r7,r8,r9) \
+#define epilogue(FUNC,r1,r2,r3,r4,r5,r6,r7,r8,r9) \
 	movq	r1,r2;			\
 	movq	r3,r4;			\
 	movl	r5 ## E,(r9);		\
 	movl	r6 ## E,4(r9);		\
 	movl	r7 ## E,8(r9);		\
 	movl	r8 ## E,12(r9);		\
-	ret;
+	ret;				\
+	ENDPROC(FUNC);
 
 #define round(TAB,OFFSET,r1,r2,r3,r4,r5,r6,r7,r8,ra,rb,rc,rd) \
 	movzbl	r2 ## H,r5 ## E;	\
@@ -133,7 +133,7 @@ FUNC:	movq	r1,r2;			\
 #define entry(FUNC,KEY,B128,B192) \
 	prologue(FUNC,KEY,B128,B192,R2,R8,R7,R9,R1,R3,R4,R6,R10,R5,R11)
 
-#define return epilogue(R8,R2,R9,R7,R5,R6,R3,R4,R11)
+#define return(FUNC) epilogue(FUNC,R8,R2,R9,R7,R5,R6,R3,R4,R11)
 
 #define encrypt_round(TAB,OFFSET) \
 	round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) \
@@ -151,12 +151,12 @@ FUNC:	movq	r1,r2;			\
 
 /* void aes_enc_blk(stuct crypto_tfm *tfm, u8 *out, const u8 *in) */
 
-	entry(aes_enc_blk,0,enc128,enc192)
+	entry(aes_enc_blk,0,.Le128,.Le192)
 	encrypt_round(crypto_ft_tab,-96)
 	encrypt_round(crypto_ft_tab,-80)
-enc192:	encrypt_round(crypto_ft_tab,-64)
+.Le192:	encrypt_round(crypto_ft_tab,-64)
 	encrypt_round(crypto_ft_tab,-48)
-enc128:	encrypt_round(crypto_ft_tab,-32)
+.Le128:	encrypt_round(crypto_ft_tab,-32)
 	encrypt_round(crypto_ft_tab,-16)
 	encrypt_round(crypto_ft_tab,  0)
 	encrypt_round(crypto_ft_tab, 16)
@@ -166,16 +166,16 @@ enc128:	encrypt_round(crypto_ft_tab,-32)
 	encrypt_round(crypto_ft_tab, 80)
 	encrypt_round(crypto_ft_tab, 96)
 	encrypt_final(crypto_fl_tab,112)
-	return
+	return(aes_enc_blk)
 
 /* void aes_dec_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in) */
 
-	entry(aes_dec_blk,240,dec128,dec192)
+	entry(aes_dec_blk,240,.Ld128,.Ld192)
 	decrypt_round(crypto_it_tab,-96)
 	decrypt_round(crypto_it_tab,-80)
-dec192:	decrypt_round(crypto_it_tab,-64)
+.Ld192:	decrypt_round(crypto_it_tab,-64)
 	decrypt_round(crypto_it_tab,-48)
-dec128:	decrypt_round(crypto_it_tab,-32)
+.Ld128:	decrypt_round(crypto_it_tab,-32)
 	decrypt_round(crypto_it_tab,-16)
 	decrypt_round(crypto_it_tab,  0)
 	decrypt_round(crypto_it_tab, 16)
@@ -185,4 +185,4 @@ dec128:	decrypt_round(crypto_it_tab,-32)
 	decrypt_round(crypto_it_tab, 80)
 	decrypt_round(crypto_it_tab, 96)
 	decrypt_final(crypto_il_tab,112)
-	return
+	return(aes_dec_blk)
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 3470624d7835..04b797767b9e 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -1262,7 +1262,6 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
 * poly = x^128 + x^127 + x^126 + x^121 + 1
 *
 *****************************************************************************/
-
 ENTRY(aesni_gcm_dec)
 	push	%r12
 	push	%r13
@@ -1437,6 +1436,7 @@ _return_T_done_decrypt:
 	pop	%r13
 	pop	%r12
 	ret
+ENDPROC(aesni_gcm_dec)
 
 
 /*****************************************************************************
@@ -1700,10 +1700,12 @@ _return_T_done_encrypt:
 	pop	%r13
 	pop	%r12
 	ret
+ENDPROC(aesni_gcm_enc)
 
 #endif
 
 
+.align 4
 _key_expansion_128:
 _key_expansion_256a:
 	pshufd $0b11111111, %xmm1, %xmm1
@@ -1715,6 +1717,8 @@ _key_expansion_256a:
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
 	ret
+ENDPROC(_key_expansion_128)
+ENDPROC(_key_expansion_256a)
 
 .align 4
 _key_expansion_192a:
@@ -1739,6 +1743,7 @@ _key_expansion_192a:
 	movaps %xmm1, 0x10(TKEYP)
 	add $0x20, TKEYP
 	ret
+ENDPROC(_key_expansion_192a)
 
 .align 4
 _key_expansion_192b:
@@ -1758,6 +1763,7 @@ _key_expansion_192b:
 	movaps %xmm0, (TKEYP)
 	add $0x10, TKEYP
 	ret
+ENDPROC(_key_expansion_192b)
 
 .align 4
 _key_expansion_256b:
@@ -1770,6 +1776,7 @@ _key_expansion_256b:
 	movaps %xmm2, (TKEYP)
 	add $0x10, TKEYP
 	ret
+ENDPROC(_key_expansion_256b)
 
 /*
  * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
@@ -1882,6 +1889,7 @@ ENTRY(aesni_set_key)
 	popl KEYP
 #endif
 	ret
+ENDPROC(aesni_set_key)
 
 /*
  * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
@@ -1903,6 +1911,7 @@ ENTRY(aesni_enc)
 	popl KEYP
 #endif
 	ret
+ENDPROC(aesni_enc)
 
 /*
  * _aesni_enc1:		internal ABI
@@ -1960,6 +1969,7 @@ _aesni_enc1:
 	movaps 0x70(TKEYP), KEY
 	AESENCLAST KEY STATE
 	ret
+ENDPROC(_aesni_enc1)
 
 /*
  * _aesni_enc4:	internal ABI
@@ -2068,6 +2078,7 @@ _aesni_enc4:
 	AESENCLAST KEY STATE3
 	AESENCLAST KEY STATE4
 	ret
+ENDPROC(_aesni_enc4)
 
 /*
  * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
@@ -2090,6 +2101,7 @@ ENTRY(aesni_dec)
 	popl KEYP
 #endif
 	ret
+ENDPROC(aesni_dec)
 
 /*
  * _aesni_dec1:		internal ABI
@@ -2147,6 +2159,7 @@ _aesni_dec1:
 	movaps 0x70(TKEYP), KEY
 	AESDECLAST KEY STATE
 	ret
+ENDPROC(_aesni_dec1)
 
 /*
  * _aesni_dec4:	internal ABI
@@ -2255,6 +2268,7 @@ _aesni_dec4:
 	AESDECLAST KEY STATE3
 	AESDECLAST KEY STATE4
 	ret
+ENDPROC(_aesni_dec4)
 
 /*
  * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2312,6 +2326,7 @@ ENTRY(aesni_ecb_enc)
 	popl LEN
 #endif
 	ret
+ENDPROC(aesni_ecb_enc)
 
 /*
  * void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2370,6 +2385,7 @@ ENTRY(aesni_ecb_dec)
 	popl LEN
 #endif
 	ret
+ENDPROC(aesni_ecb_dec)
 
 /*
  * void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2411,6 +2427,7 @@ ENTRY(aesni_cbc_enc)
 	popl IVP
 #endif
 	ret
+ENDPROC(aesni_cbc_enc)
 
 /*
  * void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2501,6 +2518,7 @@ ENTRY(aesni_cbc_dec)
 	popl IVP
 #endif
 	ret
+ENDPROC(aesni_cbc_dec)
 
 #ifdef __x86_64__
 .align 16
@@ -2527,6 +2545,7 @@ _aesni_inc_init:
 	MOVQ_R64_XMM TCTR_LOW INC
 	MOVQ_R64_XMM CTR TCTR_LOW
 	ret
+ENDPROC(_aesni_inc_init)
 
 /*
  * _aesni_inc:		internal ABI
@@ -2555,6 +2574,7 @@ _aesni_inc:
 	movaps CTR, IV
 	PSHUFB_XMM BSWAP_MASK IV
 	ret
+ENDPROC(_aesni_inc)
 
 /*
  * void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
@@ -2615,4 +2635,5 @@ ENTRY(aesni_ctr_enc)
 	movups IV, (IVP)
 .Lctr_enc_just_ret:
 	ret
+ENDPROC(aesni_ctr_enc)
 #endif
diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S
index 391d245dc086..246c67006ed0 100644
--- a/arch/x86/crypto/blowfish-x86_64-asm_64.S
+++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S
@@ -20,6 +20,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 .file "blowfish-x86_64-asm.S"
 .text
 
@@ -116,11 +118,7 @@
 	bswapq 			RX0; \
 	xorq RX0, 		(RIO);
 
-.align 8
-.global __blowfish_enc_blk
-.type   __blowfish_enc_blk,@function;
-
-__blowfish_enc_blk:
+ENTRY(__blowfish_enc_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -148,19 +146,16 @@ __blowfish_enc_blk:
 
 	movq %r10, RIO;
 	test %cl, %cl;
-	jnz __enc_xor;
+	jnz .L__enc_xor;
 
 	write_block();
 	ret;
-__enc_xor:
+.L__enc_xor:
 	xor_block();
 	ret;
+ENDPROC(__blowfish_enc_blk)
 
-.align 8
-.global blowfish_dec_blk
-.type   blowfish_dec_blk,@function;
-
-blowfish_dec_blk:
+ENTRY(blowfish_dec_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -189,6 +184,7 @@ blowfish_dec_blk:
 	movq %r11, %rbp;
 
 	ret;
+ENDPROC(blowfish_dec_blk)
 
 /**********************************************************************
   4-way blowfish, four blocks parallel
@@ -300,11 +296,7 @@ blowfish_dec_blk:
 	bswapq 			RX3; \
 	xorq RX3,		24(RIO);
 
-.align 8
-.global __blowfish_enc_blk_4way
-.type   __blowfish_enc_blk_4way,@function;
-
-__blowfish_enc_blk_4way:
+ENTRY(__blowfish_enc_blk_4way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -336,7 +328,7 @@ __blowfish_enc_blk_4way:
 	movq %r11, RIO;
 
 	test %bpl, %bpl;
-	jnz __enc_xor4;
+	jnz .L__enc_xor4;
 
 	write_block4();
 
@@ -344,18 +336,15 @@ __blowfish_enc_blk_4way:
 	popq %rbp;
 	ret;
 
-__enc_xor4:
+.L__enc_xor4:
 	xor_block4();
 
 	popq %rbx;
 	popq %rbp;
 	ret;
+ENDPROC(__blowfish_enc_blk_4way)
 
-.align 8
-.global blowfish_dec_blk_4way
-.type   blowfish_dec_blk_4way,@function;
-
-blowfish_dec_blk_4way:
+ENTRY(blowfish_dec_blk_4way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -387,4 +376,4 @@ blowfish_dec_blk_4way:
 	popq %rbp;
 
 	ret;
-
+ENDPROC(blowfish_dec_blk_4way)
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index 2306d2e4816f..cfc163469c71 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -15,6 +15,8 @@
  *	http://koti.mbnet.fi/axh/crypto/camellia-BSD-1.2.0-aesni1.tar.xz
  */
 
+#include <linux/linkage.h>
+
 #define CAMELLIA_TABLE_BYTE_LEN 272
 
 /* struct camellia_ctx: */
@@ -190,6 +192,7 @@ roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd:
 		  %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)
 
 .align 8
 roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
@@ -197,6 +200,7 @@ roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
 		  %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)
 
 /*
  * IN/OUT:
@@ -709,8 +713,6 @@ roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab:
 .text
 
 .align 8
-.type   __camellia_enc_blk16,@function;
-
 __camellia_enc_blk16:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -793,10 +795,9 @@ __camellia_enc_blk16:
 		     %xmm15, %rax, %rcx, 24);
 
 	jmp .Lenc_done;
+ENDPROC(__camellia_enc_blk16)
 
 .align 8
-.type   __camellia_dec_blk16,@function;
-
 __camellia_dec_blk16:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -877,12 +878,9 @@ __camellia_dec_blk16:
 	      ((key_table + (24) * 8) + 4)(CTX));
 
 	jmp .Ldec_max24;
+ENDPROC(__camellia_dec_blk16)
 
-.align 8
-.global camellia_ecb_enc_16way
-.type   camellia_ecb_enc_16way,@function;
-
-camellia_ecb_enc_16way:
+ENTRY(camellia_ecb_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -903,12 +901,9 @@ camellia_ecb_enc_16way:
 		     %xmm8, %rsi);
 
 	ret;
+ENDPROC(camellia_ecb_enc_16way)
 
-.align 8
-.global camellia_ecb_dec_16way
-.type   camellia_ecb_dec_16way,@function;
-
-camellia_ecb_dec_16way:
+ENTRY(camellia_ecb_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -934,12 +929,9 @@ camellia_ecb_dec_16way:
 		     %xmm8, %rsi);
 
 	ret;
+ENDPROC(camellia_ecb_dec_16way)
 
-.align 8
-.global camellia_cbc_dec_16way
-.type   camellia_cbc_dec_16way,@function;
-
-camellia_cbc_dec_16way:
+ENTRY(camellia_cbc_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -986,6 +978,7 @@ camellia_cbc_dec_16way:
 		     %xmm8, %rsi);
 
 	ret;
+ENDPROC(camellia_cbc_dec_16way)
 
 #define inc_le128(x, minus_one, tmp) \
 	vpcmpeqq minus_one, x, tmp; \
@@ -993,11 +986,7 @@ camellia_cbc_dec_16way:
 	vpslldq $8, tmp, tmp; \
 	vpsubq tmp, x, x;
 
-.align 8
-.global camellia_ctr_16way
-.type   camellia_ctr_16way,@function;
-
-camellia_ctr_16way:
+ENTRY(camellia_ctr_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -1100,3 +1089,4 @@ camellia_ctr_16way:
 		     %xmm8, %rsi);
 
 	ret;
+ENDPROC(camellia_ctr_16way)
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 0b3374335fdc..310319c601ed 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -20,6 +20,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 .file "camellia-x86_64-asm_64.S"
 .text
 
@@ -188,10 +190,7 @@
 	bswapq				RAB0; \
 	movq RAB0,			4*2(RIO);
 
-.global __camellia_enc_blk;
-.type   __camellia_enc_blk,@function;
-
-__camellia_enc_blk:
+ENTRY(__camellia_enc_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -214,33 +213,31 @@ __camellia_enc_blk:
 	movl $24, RT1d; /* max */
 
 	cmpb $16, key_length(CTX);
-	je __enc_done;
+	je .L__enc_done;
 
 	enc_fls(24);
 	enc_rounds(24);
 	movl $32, RT1d; /* max */
 
-__enc_done:
+.L__enc_done:
 	testb RXORbl, RXORbl;
 	movq RDST, RIO;
 
-	jnz __enc_xor;
+	jnz .L__enc_xor;
 
 	enc_outunpack(mov, RT1);
 
 	movq RRBP, %rbp;
 	ret;
 
-__enc_xor:
+.L__enc_xor:
 	enc_outunpack(xor, RT1);
 
 	movq RRBP, %rbp;
 	ret;
+ENDPROC(__camellia_enc_blk)
 
-.global camellia_dec_blk;
-.type   camellia_dec_blk,@function;
-
-camellia_dec_blk:
+ENTRY(camellia_dec_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -258,12 +255,12 @@ camellia_dec_blk:
 	dec_inpack(RT2);
 
 	cmpb $24, RT2bl;
-	je __dec_rounds16;
+	je .L__dec_rounds16;
 
 	dec_rounds(24);
 	dec_fls(24);
 
-__dec_rounds16:
+.L__dec_rounds16:
 	dec_rounds(16);
 	dec_fls(16);
 	dec_rounds(8);
@@ -276,6 +273,7 @@ __dec_rounds16:
 
 	movq RRBP, %rbp;
 	ret;
+ENDPROC(camellia_dec_blk)
 
 /**********************************************************************
   2-way camellia
@@ -426,10 +424,7 @@ __dec_rounds16:
 		bswapq				RAB1; \
 		movq RAB1,			12*2(RIO);
 
-.global __camellia_enc_blk_2way;
-.type   __camellia_enc_blk_2way,@function;
-
-__camellia_enc_blk_2way:
+ENTRY(__camellia_enc_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -453,16 +448,16 @@ __camellia_enc_blk_2way:
 	movl $24, RT2d; /* max */
 
 	cmpb $16, key_length(CTX);
-	je __enc2_done;
+	je .L__enc2_done;
 
 	enc_fls2(24);
 	enc_rounds2(24);
 	movl $32, RT2d; /* max */
 
-__enc2_done:
+.L__enc2_done:
 	test RXORbl, RXORbl;
 	movq RDST, RIO;
-	jnz __enc2_xor;
+	jnz .L__enc2_xor;
 
 	enc_outunpack2(mov, RT2);
 
@@ -470,17 +465,15 @@ __enc2_done:
 	popq %rbx;
 	ret;
 
-__enc2_xor:
+.L__enc2_xor:
 	enc_outunpack2(xor, RT2);
 
 	movq RRBP, %rbp;
 	popq %rbx;
 	ret;
+ENDPROC(__camellia_enc_blk_2way)
 
-.global camellia_dec_blk_2way;
-.type   camellia_dec_blk_2way,@function;
-
-camellia_dec_blk_2way:
+ENTRY(camellia_dec_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -499,12 +492,12 @@ camellia_dec_blk_2way:
 	dec_inpack2(RT2);
 
 	cmpb $24, RT2bl;
-	je __dec2_rounds16;
+	je .L__dec2_rounds16;
 
 	dec_rounds2(24);
 	dec_fls2(24);
 
-__dec2_rounds16:
+.L__dec2_rounds16:
 	dec_rounds2(16);
 	dec_fls2(16);
 	dec_rounds2(8);
@@ -518,3 +511,4 @@ __dec2_rounds16:
 	movq RRBP, %rbp;
 	movq RXOR, %rbx;
 	ret;
+ENDPROC(camellia_dec_blk_2way)
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 15b00ac7cbd3..c35fd5d6ecd2 100644
--- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -23,6 +23,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 .file "cast5-avx-x86_64-asm_64.S"
 
 .extern cast_s1
@@ -211,8 +213,6 @@
 .text
 
 .align 16
-.type   __cast5_enc_blk16,@function;
-
 __cast5_enc_blk16:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -263,14 +263,14 @@ __cast5_enc_blk16:
 
 	movzbl rr(CTX), %eax;
 	testl %eax, %eax;
-	jnz __skip_enc;
+	jnz .L__skip_enc;
 
 	round(RL, RR, 12, 1);
 	round(RR, RL, 13, 2);
 	round(RL, RR, 14, 3);
 	round(RR, RL, 15, 1);
 
-__skip_enc:
+.L__skip_enc:
 	popq %rbx;
 	popq %rbp;
 
@@ -282,10 +282,9 @@ __skip_enc:
 	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);