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
  ...

24 files changed, 668 insertions, 294 deletions

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);
 
 	ret;
+ENDPROC(__cast5_enc_blk16)
 
 .align 16
-.type   __cast5_dec_blk16,@function;
-
 __cast5_dec_blk16:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -323,14 +322,14 @@ __cast5_dec_blk16:
 
 	movzbl rr(CTX), %eax;
 	testl %eax, %eax;
-	jnz __skip_dec;
+	jnz .L__skip_dec;
 
 	round(RL, RR, 15, 1);
 	round(RR, RL, 14, 3);
 	round(RL, RR, 13, 2);
 	round(RR, RL, 12, 1);
 
-__dec_tail:
+.L__dec_tail:
 	round(RL, RR, 11, 3);
 	round(RR, RL, 10, 2);
 	round(RL, RR, 9, 1);
@@ -355,15 +354,12 @@ __dec_tail:
 
 	ret;
 
-__skip_dec:
+.L__skip_dec:
 	vpsrldq $4, RKR, RKR;
-	jmp __dec_tail;
+	jmp .L__dec_tail;
+ENDPROC(__cast5_dec_blk16)
 
-.align 16
-.global cast5_ecb_enc_16way
-.type   cast5_ecb_enc_16way,@function;
-
-cast5_ecb_enc_16way:
+ENTRY(cast5_ecb_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -393,12 +389,9 @@ cast5_ecb_enc_16way:
 	vmovdqu RL4, (7*4*4)(%r11);
 
 	ret;
+ENDPROC(cast5_ecb_enc_16way)
 
-.align 16
-.global cast5_ecb_dec_16way
-.type   cast5_ecb_dec_16way,@function;
-
-cast5_ecb_dec_16way:
+ENTRY(cast5_ecb_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -428,12 +421,9 @@ cast5_ecb_dec_16way:
 	vmovdqu RL4, (7*4*4)(%r11);
 
 	ret;
+ENDPROC(cast5_ecb_dec_16way)
 
-.align 16
-.global cast5_cbc_dec_16way
-.type   cast5_cbc_dec_16way,@function;
-
-cast5_cbc_dec_16way:
+ENTRY(cast5_cbc_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -480,12 +470,9 @@ cast5_cbc_dec_16way:
 	popq %r12;
 
 	ret;
+ENDPROC(cast5_cbc_dec_16way)
 
-.align 16
-.global cast5_ctr_16way
-.type   cast5_ctr_16way,@function;
-
-cast5_ctr_16way:
+ENTRY(cast5_ctr_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -556,3 +543,4 @@ cast5_ctr_16way:
 	popq %r12;
 
 	ret;
+ENDPROC(cast5_ctr_16way)
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 2569d0da841f..f93b6105a0ce 100644
--- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -23,6 +23,7 @@
  *
  */
 
+#include <linux/linkage.h>
 #include "glue_helper-asm-avx.S"
 
 .file "cast6-avx-x86_64-asm_64.S"
@@ -250,8 +251,6 @@
 .text
 
 .align 8
-.type   __cast6_enc_blk8,@function;
-
 __cast6_enc_blk8:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -295,10 +294,9 @@ __cast6_enc_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
 	ret;
+ENDPROC(__cast6_enc_blk8)
 
 .align 8
-.type   __cast6_dec_blk8,@function;
-
 __cast6_dec_blk8:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -341,12 +339,9 @@ __cast6_dec_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
 
 	ret;
+ENDPROC(__cast6_dec_blk8)
 
-.align 8
-.global cast6_ecb_enc_8way
-.type   cast6_ecb_enc_8way,@function;
-
-cast6_ecb_enc_8way:
+ENTRY(cast6_ecb_enc_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -362,12 +357,9 @@ cast6_ecb_enc_8way:
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	ret;
+ENDPROC(cast6_ecb_enc_8way)
 
-.align 8
-.global cast6_ecb_dec_8way
-.type   cast6_ecb_dec_8way,@function;
-
-cast6_ecb_dec_8way:
+ENTRY(cast6_ecb_dec_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -383,12 +375,9 @@ cast6_ecb_dec_8way:
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	ret;
+ENDPROC(cast6_ecb_dec_8way)
 
-.align 8
-.global cast6_cbc_dec_8way
-.type   cast6_cbc_dec_8way,@function;
-
-cast6_cbc_dec_8way:
+ENTRY(cast6_cbc_dec_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -409,12 +398,9 @@ cast6_cbc_dec_8way:
 	popq %r12;
 
 	ret;
+ENDPROC(cast6_cbc_dec_8way)
 
-.align 8
-.global cast6_ctr_8way
-.type   cast6_ctr_8way,@function;
-
-cast6_ctr_8way:
+ENTRY(cast6_ctr_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -437,3 +423,4 @@ cast6_ctr_8way:
 	popq %r12;
 
 	ret;
+ENDPROC(cast6_ctr_8way)
diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S
new file mode 100644
index 000000000000..c8335014a044
--- /dev/null
+++ b/arch/x86/crypto/crc32-pclmul_asm.S
@@ -0,0 +1,246 @@
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please  visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ *
+ * Using hardware provided PCLMULQDQ instruction to accelerate the CRC32
+ * calculation.
+ * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
+ * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
+ * at:
+ * http://www.intel.com/products/processor/manuals/
+ * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
+ * Volume 2B: Instruction Set Reference, N-Z
+ *
+ * Authors:   Gregory Prestas <Gregory_Prestas@us.xyratex.com>
+ *	      Alexander Boyko <Alexander_Boyko@xyratex.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/inst.h>
+
+
+.align 16
+/*
+ * [x4*128+32 mod P(x) << 32)]'  << 1   = 0x154442bd4
+ * #define CONSTANT_R1  0x154442bd4LL
+ *
+ * [(x4*128-32 mod P(x) << 32)]' << 1   = 0x1c6e41596
+ * #define CONSTANT_R2  0x1c6e41596LL
+ */
+.Lconstant_R2R1:
+	.octa 0x00000001c6e415960000000154442bd4
+/*
+ * [(x128+32 mod P(x) << 32)]'   << 1   = 0x1751997d0
+ * #define CONSTANT_R3  0x1751997d0LL
+ *
+ * [(x128-32 mod P(x) << 32)]'   << 1   = 0x0ccaa009e
+ * #define CONSTANT_R4  0x0ccaa009eLL
+ */
+.Lconstant_R4R3:
+	.octa 0x00000000ccaa009e00000001751997d0
+/*
+ * [(x64 mod P(x) << 32)]'       << 1   = 0x163cd6124
+ * #define CONSTANT_R5  0x163cd6124LL
+ */
+.Lconstant_R5:
+	.octa 0x00000000000000000000000163cd6124
+.Lconstant_mask32:
+	.octa 0x000000000000000000000000FFFFFFFF
+/*
+ * #define CRCPOLY_TRUE_LE_FULL 0x1DB710641LL
+ *
+ * Barrett Reduction constant (u64`) = u` = (x**64 / P(x))` = 0x1F7011641LL
+ * #define CONSTANT_RU  0x1F7011641LL
+ */
+.Lconstant_RUpoly:
+	.octa 0x00000001F701164100000001DB710641
+
+#define CONSTANT %xmm0
+
+#ifdef __x86_64__
+#define BUF     %rdi
+#define LEN     %rsi
+#define CRC     %edx
+#else
+#define BUF     %eax
+#define LEN     %edx
+#define CRC     %ecx
+#endif
+
+
+
+.text
+/**
+ *      Calculate crc32
+ *      BUF - buffer (16 bytes aligned)
+ *      LEN - sizeof buffer (16 bytes aligned), LEN should be grater than 63
+ *      CRC - initial crc32
+ *      return %eax crc32
+ *      uint crc32_pclmul_le_16(unsigned char const *buffer,
+ *	                     size_t len, uint crc32)
+ */
+.globl crc32_pclmul_le_16
+.align 4, 0x90
+crc32_pclmul_le_16:/* buffer and buffer size are 16 bytes aligned */
+	movdqa  (BUF), %xmm1
+	movdqa  0x10(BUF), %xmm2
+	movdqa  0x20(BUF), %xmm3
+	movdqa  0x30(BUF), %xmm4
+	movd    CRC, CONSTANT
+	pxor    CONSTANT, %xmm1
+	sub     $0x40, LEN
+	add     $0x40, BUF
+#ifndef __x86_64__
+	/* This is for position independent code(-fPIC) support for 32bit */
+	call    delta
+delta:
+	pop     %ecx
+#endif
+	cmp     $0x40, LEN
+	jb      less_64
+
+#ifdef __x86_64__
+	movdqa .Lconstant_R2R1(%rip), CONSTANT
+#else
+	movdqa .Lconstant_R2R1 - delta(%ecx), CONSTANT
+#endif
+
+loop_64:/*  64 bytes Full cache line folding */
+	prefetchnta    0x40(BUF)
+	movdqa  %xmm1, %xmm5
+	movdqa  %xmm2, %xmm6
+	movdqa  %xmm3, %xmm7
+#ifdef __x86_64__
+	movdqa  %xmm4, %xmm8
+#endif
+	PCLMULQDQ 00, CONSTANT, %xmm1
+	PCLMULQDQ 00, CONSTANT, %xmm2
+	PCLMULQDQ 00, CONSTANT, %xmm3
+#ifdef __x86_64__
+	PCLMULQDQ 00, CONSTANT, %xmm4
+#endif
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	PCLMULQDQ 0x11, CONSTANT, %xmm6
+	PCLMULQDQ 0x11, CONSTANT, %xmm7
+#ifdef __x86_64__
+	PCLMULQDQ 0x11, CONSTANT, %xmm8
+#endif
+	pxor    %xmm5, %xmm1
+	pxor    %xmm6, %xmm2
+	pxor    %xmm7, %xmm3
+#ifdef __x86_64__
+	pxor    %xmm8, %xmm4
+#else
+	/* xmm8 unsupported for x32 */
+	movdqa  %xmm4, %xmm5
+	PCLMULQDQ 00, CONSTANT, %xmm4
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm4
+#endif
+
+	pxor    (BUF), %xmm1
+	pxor    0x10(BUF), %xmm2
+	pxor    0x20(BUF), %xmm3
+	pxor    0x30(BUF), %xmm4
+
+	sub     $0x40, LEN
+	add     $0x40, BUF
+	cmp     $0x40, LEN
+	jge     loop_64
+less_64:/*  Folding cache line into 128bit */
+#ifdef __x86_64__
+	movdqa  .Lconstant_R4R3(%rip), CONSTANT
+#else
+	movdqa  .Lconstant_R4R3 - delta(%ecx), CONSTANT
+#endif
+	prefetchnta     (BUF)
+
+	movdqa  %xmm1, %xmm5
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm1
+	pxor    %xmm2, %xmm1
+
+	movdqa  %xmm1, %xmm5
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm1
+	pxor    %xmm3, %xmm1
+
+	movdqa  %xmm1, %xmm5
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm1
+	pxor    %xmm4, %xmm1
+
+	cmp     $0x10, LEN
+	jb      fold_64
+loop_16:/* Folding rest buffer into 128bit */
+	movdqa  %xmm1, %xmm5
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm1
+	pxor    (BUF), %xmm1
+	sub     $0x10, LEN
+	add     $0x10, BUF
+	cmp     $0x10, LEN
+	jge     loop_16
+
+fold_64:
+	/* perform the last 64 bit fold, also adds 32 zeroes
+	 * to the input stream */
+	PCLMULQDQ 0x01, %xmm1, CONSTANT /* R4 * xmm1.low */
+	psrldq  $0x08, %xmm1
+	pxor    CONSTANT, %xmm1
+
+	/* final 32-bit fold */
+	movdqa  %xmm1, %xmm2
+#ifdef __x86_64__
+	movdqa  .Lconstant_R5(%rip), CONSTANT
+	movdqa  .Lconstant_mask32(%rip), %xmm3
+#else
+	movdqa  .Lconstant_R5 - delta(%ecx), CONSTANT
+	movdqa  .Lconstant_mask32 - delta(%ecx), %xmm3
+#endif
+	psrldq  $0x04, %xmm2
+	pand    %xmm3, %xmm1
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	pxor    %xmm2, %xmm1
+
+	/* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
+#ifdef __x86_64__
+	movdqa  .Lconstant_RUpoly(%rip), CONSTANT
+#else
+	movdqa  .Lconstant_RUpoly - delta(%ecx), CONSTANT
+#endif
+	movdqa  %xmm1, %xmm2
+	pand    %xmm3, %xmm1
+	PCLMULQDQ 0x10, CONSTANT, %xmm1
+	pand    %xmm3, %xmm1
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	pxor    %xmm2, %xmm1
+	pextrd  $0x01, %xmm1, %eax
+
+	ret
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
new file mode 100644
index 000000000000..9d014a74ef96
--- /dev/null
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -0,0 +1,201 @@
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please  visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ *
+ * Wrappers for kernel crypto shash api to pclmulqdq crc32 imlementation.
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+
+#include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
+#include <asm/i387.h>
+
+#define CHKSUM_BLOCK_SIZE	1
+#define CHKSUM_DIGEST_SIZE	4
+
+#define PCLMUL_MIN_LEN		64L     /* minimum size of buffer
+					 * for crc32_pclmul_le_16 */
+#define SCALE_F			16L	/* size of xmm register */
+#define SCALE_F_MASK		(SCALE_F - 1)
+
+u32 crc32_pclmul_le_16(unsigned char const *buffer, size_t len, u32 crc32);
+
+static u32 __attribute__((pure))
+	crc32_pclmul_le(u32 crc, unsigned char const *p, size_t len)
+{
+	unsigned int iquotient;
+	unsigned int iremainder;
+	unsigned int prealign;
+
+	if (len < PCLMUL_MIN_LEN + SCALE_F_MASK || !irq_fpu_usable())
+		return crc32_le(crc, p, len);
+
+	if ((long)p & SCALE_F_MASK) {
+		/* align p to 16 byte */
+		prealign = SCALE_F - ((long)p & SCALE_F_MASK);
+
+		crc = crc32_le(crc, p, prealign);
+		len -= prealign;
+		p = (unsigned char *)(((unsigned long)p + SCALE_F_MASK) &
+				     ~SCALE_F_MASK);
+	}
+	iquotient = len & (~SCALE_F_MASK);
+	iremainder = len & SCALE_F_MASK;
+
+	kernel_fpu_begin();
+	crc = crc32_pclmul_le_16(p, iquotient, crc);
+	kernel_fpu_end();
+
+	if (iremainder)
+		crc = crc32_le(crc, p + iquotient, iremainder);
+
+	return crc;
+}
+
+static int crc32_pclmul_cra_init(struct crypto_tfm *tfm)
+{
+	u32 *key = crypto_tfm_ctx(tfm);
+
+	*key = 0;
+
+	return 0;
+}
+
+static int crc32_pclmul_setkey(struct crypto_shash *hash, const u8 *key,
+			unsigned int keylen)
+{
+	u32 *mctx = crypto_shash_ctx(hash);
+
+	if (keylen != sizeof(u32)) {
+		crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	*mctx = le32_to_cpup((__le32 *)key);
+	return 0;
+}
+
+static int crc32_pclmul_init(struct shash_desc *desc)
+{
+	u32 *mctx = crypto_shash_ctx(desc->tfm);
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = *mctx;
+
+	return 0;
+}
+
+static int crc32_pclmul_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = crc32_pclmul_le(*crcp, data, len);
+	return 0;
+}
+
+/* No final XOR 0xFFFFFFFF, like crc32_le */
+static int __crc32_pclmul_finup(u32 *crcp, const u8 *data, unsigned int len,
+				u8 *out)
+{
+	*(__le32 *)out = cpu_to_le32(crc32_pclmul_le(*crcp, data, len));
+	return 0;
+}
+
+static int crc32_pclmul_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return __crc32_pclmul_finup(shash_desc_ctx(desc), data, len, out);
+}
+
+static int crc32_pclmul_final(struct shash_desc *desc, u8 *out)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*(__le32 *)out = cpu_to_le32p(crcp);
+	return 0;
+}
+
+static int crc32_pclmul_digest(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *out)
+{
+	return __crc32_pclmul_finup(crypto_shash_ctx(desc->tfm), data, len,
+				    out);
+}
+
+static struct shash_alg alg = {
+	.setkey		= crc32_pclmul_setkey,
+	.init		= crc32_pclmul_init,
+	.update		= crc32_pclmul_update,
+	.final		= crc32_pclmul_final,
+	.finup		= crc32_pclmul_finup,
+	.digest		= crc32_pclmul_digest,
+	.descsize	= sizeof(u32),
+	.digestsize	= CHKSUM_DIGEST_SIZE,
+	.base		= {
+			.cra_name		= "crc32",
+			.cra_driver_name	= "crc32-pclmul",
+			.cra_priority		= 200,
+			.cra_blocksize		= CHKSUM_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(u32),
+			.cra_module		= THIS_MODULE,
+			.cra_init		= crc32_pclmul_cra_init,
+	}
+};
+
+static const struct x86_cpu_id crc32pclmul_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, crc32pclmul_cpu_id);
+
+
+static int __init crc32_pclmul_mod_init(void)
+{
+
+	if (!x86_match_cpu(crc32pclmul_cpu_id)) {
+		pr_info("PCLMULQDQ-NI instructions are not detected.\n");
+		return -ENODEV;
+	}
+	return crypto_register_shash(&alg);
+}
+
+static void __exit crc32_pclmul_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crc32_pclmul_mod_init);
+module_exit(crc32_pclmul_mod_fini);
+
+MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
+MODULE_LICENSE("GPL");
+
+MODULE_ALIAS("crc32");
+MODULE_ALIAS("crc32-pclmul");
diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
index 93c6d39237ac..cf1a7ec4cc3a 100644
--- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
+++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S
@@ -42,6 +42,8 @@
  * SOFTWARE.
  */
 
+#include <linux/linkage.h>
+
 ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
 
 .macro LABEL prefix n
@@ -68,8 +70,7 @@
 
 # unsigned int crc_pcl(u8 *buffer, int len, unsigned int crc_init);
 
-.global crc_pcl
-crc_pcl:
+ENTRY(crc_pcl)
 #define    bufp		%rdi
 #define    bufp_dw	%edi
 #define    bufp_w	%di
@@ -323,6 +324,9 @@ JMPTBL_ENTRY %i
 .noaltmacro
 	i=i+1
 .endr
+
+ENDPROC(crc_pcl)
+
 	################################################################
 	## PCLMULQDQ tables
 	## Table is 128 entries x 2 quad words each
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 1eb7f90cb7b9..586f41aac361 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -94,6 +94,7 @@ __clmul_gf128mul_ble:
 	pxor T2, T1
 	pxor T1, DATA
 	ret
+ENDPROC(__clmul_gf128mul_ble)
 
 /* void clmul_ghash_mul(char *dst, const be128 *shash) */
 ENTRY(clmul_ghash_mul)
@@ -105,6 +106,7 @@ ENTRY(clmul_ghash_mul)
 	PSHUFB_XMM BSWAP DATA
 	movups DATA, (%rdi)
 	ret
+ENDPROC(clmul_ghash_mul)
 
 /*
  * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
@@ -131,6 +133,7 @@ ENTRY(clmul_ghash_update)
 	movups DATA, (%rdi)
 .Lupdate_just_ret:
 	ret
+ENDPROC(clmul_ghash_update)
 
 /*
  * void clmul_ghash_setkey(be128 *shash, const u8 *key);
@@ -155,3 +158,4 @@ ENTRY(clmul_ghash_setkey)
 	pxor %xmm1, %xmm0
 	movups %xmm0, (%rdi)
 	ret
+ENDPROC(clmul_ghash_setkey)
diff --git a/arch/x86/crypto/salsa20-i586-asm_32.S b/arch/x86/crypto/salsa20-i586-asm_32.S
index 72eb306680b2..329452b8f794 100644
--- a/arch/x86/crypto/salsa20-i586-asm_32.S
+++ b/arch/x86/crypto/salsa20-i586-asm_32.S
@@ -2,11 +2,12 @@
 # D. J. Bernstein
 # Public domain.
 
-# enter ECRYPT_encrypt_bytes
+#include <linux/linkage.h>
+
 .text
-.p2align 5
-.globl ECRYPT_encrypt_bytes
-ECRYPT_encrypt_bytes:
+
+# enter salsa20_encrypt_bytes
+ENTRY(salsa20_encrypt_bytes)
 	mov	%esp,%eax
 	and	$31,%eax
 	add	$256,%eax
@@ -933,11 +934,10 @@ ECRYPT_encrypt_bytes:
 	add	$64,%esi
 	# goto bytesatleast1
 	jmp	._bytesatleast1
-# enter ECRYPT_keysetup
-.text
-.p2align 5
-.globl ECRYPT_keysetup
-ECRYPT_keysetup:
+ENDPROC(salsa20_encrypt_bytes)
+
+# enter salsa20_keysetup
+ENTRY(salsa20_keysetup)
 	mov	%esp,%eax
 	and	$31,%eax
 	add	$256,%eax
@@ -1060,11 +1060,10 @@ ECRYPT_keysetup:
 	# leave
 	add	%eax,%esp
 	ret
-# enter ECRYPT_ivsetup
-.text
-.p2align 5
-.globl ECRYPT_ivsetup
-ECRYPT_ivsetup:
+ENDPROC(salsa20_keysetup)
+
+# enter salsa20_ivsetup
+ENTRY(salsa20_ivsetup)
 	mov	%esp,%eax
 	and	$31,%eax
 	add	$256,%eax
@@ -1112,3 +1111,4 @@ ECRYPT_ivsetup:
 	# leave
 	add	%eax,%esp
 	ret
+ENDPROC(salsa20_ivsetup)
diff --git a/arch/x86/crypto/salsa20-x86_64-asm_64.S b/arch/x86/crypto/salsa20-x86_64-asm_64.S
index 6214a9b09706..9279e0b2d60e 100644
--- a/arch/x86/crypto/salsa20-x86_64-asm_64.S
+++ b/arch/x86/crypto/salsa20-x86_64-asm_64.S
@@ -1,8 +1,7 @@
-# enter ECRYPT_encrypt_bytes
-.text
-.p2align 5
-.globl ECRYPT_encrypt_bytes
-ECRYPT_encrypt_bytes:
+#include <linux/linkage.h>
+
+# enter salsa20_encrypt_bytes
+ENTRY(salsa20_encrypt_bytes)
 	mov	%rsp,%r11
 	and	$31,%r11
 	add	$256,%r11
@@ -802,11 +801,10 @@ ECRYPT_encrypt_bytes:
 	# comment:fp stack unchanged by jump
 	# goto bytesatleast1
 	jmp	._bytesatleast1
-# enter ECRYPT_keysetup
-.text
-.p2align 5
-.globl ECRYPT_keysetup
-ECRYPT_keysetup:
+ENDPROC(salsa20_encrypt_bytes)
+
+# enter salsa20_keysetup
+ENTRY(salsa20_keysetup)
 	mov	%rsp,%r11
 	and	$31,%r11
 	add	$256,%r11
@@ -892,11 +890,10 @@ ECRYPT_keysetup:
 	mov	%rdi,%rax
 	mov	%rsi,%rdx
 	ret
-# enter ECRYPT_ivsetup
-.text
-.p2align 5
-.globl ECRYPT_ivsetup
-ECRYPT_ivsetup:
+ENDPROC(salsa20_keysetup)
+
+# enter salsa20_ivsetup
+ENTRY(salsa20_ivsetup)
 	mov	%rsp,%r11
 	and	$31,%r11
 	add	$256,%r11
@@ -918,3 +915,4 @@ ECRYPT_ivsetup:
 	mov	%rdi,%rax
 	mov	%rsi,%rdx
 	ret
+ENDPROC(salsa20_ivsetup)
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index a3a3c0205c16..5e8e67739bb5 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -26,11 +26,6 @@
 #define SALSA20_MIN_KEY_SIZE  16U
 #define SALSA20_MAX_KEY_SIZE  32U
 
-// use the ECRYPT_* function names
-#define salsa20_keysetup        ECRYPT_keysetup
-#define salsa20_ivsetup         ECRYPT_ivsetup
-#define salsa20_encrypt_bytes   ECRYPT_encrypt_bytes
-
 struct salsa20_ctx
 {
 	u32 input[16];
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 02b0e9fe997c..43c938612b74 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -24,6 +24,7 @@
  *
  */
 
+#include <linux/linkage.h>
 #include "glue_helper-asm-avx.S"
 
 .file "serpent-avx-x86_64-asm_64.S"
@@ -566,8 +567,6 @@
 	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
 
 .align 8
-.type   __serpent_enc_blk8_avx,@function;
-
 __serpent_enc_blk8_avx:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -619,10 +618,9 @@ __serpent_enc_blk8_avx:
 	write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
 	ret;
+ENDPROC(__serpent_enc_blk8_avx)
 
 .align 8
-.type   __serpent_dec_blk8_avx,@function;
-
 __serpent_dec_blk8_avx:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -674,12 +672,9 @@ __serpent_dec_blk8_avx:
 	write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
 	ret;
+ENDPROC(__serpent_dec_blk8_avx)
 
-.align 8
-.global serpent_ecb_enc_8way_avx
-.type   serpent_ecb_enc_8way_avx,@function;
-
-serpent_ecb_enc_8way_avx:
+ENTRY(serpent_ecb_enc_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -693,12 +688,9 @@ serpent_ecb_enc_8way_avx:
 	store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	ret;
+ENDPROC(serpent_ecb_enc_8way_avx)
 
-.align 8
-.global serpent_ecb_dec_8way_avx
-.type   serpent_ecb_dec_8way_avx,@function;
-
-serpent_ecb_dec_8way_avx:
+ENTRY(serpent_ecb_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -712,12 +704,9 @@ serpent_ecb_dec_8way_avx:
 	store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
 	ret;
+ENDPROC(serpent_ecb_dec_8way_avx)
 
-.align 8
-.global serpent_cbc_dec_8way_avx
-.type   serpent_cbc_dec_8way_avx,@function;
-
-serpent_cbc_dec_8way_avx:
+ENTRY(serpent_cbc_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -731,12 +720,9 @@ serpent_cbc_dec_8way_avx:
 	store_cbc_8way(%rdx, %rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);
 
 	ret;
+ENDPROC(serpent_cbc_dec_8way_avx)
 
-.align 8
-.global serpent_ctr_8way_avx
-.type   serpent_ctr_8way_avx,@function;
-
-serpent_ctr_8way_avx:
+ENTRY(serpent_ctr_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -752,3 +738,4 @@ serpent_ctr_8way_avx:
 	store_ctr_8way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	ret;
+ENDPROC(serpent_ctr_8way_avx)
diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
index c00053d42f99..d348f1553a79 100644
--- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S
+++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
@@ -24,6 +24,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 .file "serpent-sse2-i586-asm_32.S"
 .text
 
@@ -510,11 +512,7 @@
 	pxor t0,		x3; \
 	movdqu x3,		(3*4*4)(out);
 
-.align 8
-.global __serpent_enc_blk_4way
-.type   __serpent_enc_blk_4way,@function;
-
-__serpent_enc_blk_4way:
+ENTRY(__serpent_enc_blk_4way)
 	/* input:
 	 *	arg_ctx(%esp): ctx, CTX
 	 *	arg_dst(%esp): dst
@@ -566,22 +564,19 @@ __serpent_enc_blk_4way:
 	movl arg_dst(%esp), %eax;
 
 	cmpb $0, arg_xor(%esp);
-	jnz __enc_xor4;
+	jnz .L__enc_xor4;
 
 	write_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
 
 	ret;
 
-__enc_xor4:
+.L__enc_xor4:
 	xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
 
 	ret;
+ENDPROC(__serpent_enc_blk_4way)
 
-.align 8
-.global serpent_dec_blk_4way
-.type   serpent_dec_blk_4way,@function;
-
-serpent_dec_blk_4way:
+ENTRY(serpent_dec_blk_4way)
 	/* input:
 	 *	arg_ctx(%esp): ctx, CTX
 	 *	arg_dst(%esp): dst
@@ -633,3 +628,4 @@ serpent_dec_blk_4way:
 	write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);
 
 	ret;
+ENDPROC(serpent_dec_blk_4way)
diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
index 3ee1ff04d3e9..acc066c7c6b2 100644
--- a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
@@ -24,6 +24,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 .file "serpent-sse2-x86_64-asm_64.S"
 .text
 
@@ -632,11 +634,7 @@
 	pxor t0,		x3; \
 	movdqu x3,		(3*4*4)(out);
 
-.align 8
-.global __serpent_enc_blk_8way
-.type   __serpent_enc_blk_8way,@function;
-
-__serpent_enc_blk_8way:
+ENTRY(__serpent_enc_blk_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -687,24 +685,21 @@ __serpent_enc_blk_8way:
 	leaq (4*4*4)(%rsi), %rax;
 
 	testb %cl, %cl;
-	jnz __enc_xor8;
+	jnz .L__enc_xor8;
 
 	write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
 	ret;
 
-__enc_xor8:
+.L__enc_xor8:
 	xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
 	xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
 
 	ret;
+ENDPROC(__serpent_enc_blk_8way)
 
-.align 8
-.global serpent_dec_blk_8way
-.type   serpent_dec_blk_8way,@function;
-
-serpent_dec_blk_8way:
+ENTRY(serpent_dec_blk_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -756,3 +751,4 @@ serpent_dec_blk_8way:
 	write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
 
 	ret;
+ENDPROC(serpent_dec_blk_8way)
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index 49d6987a73d9..a4109506a5e8 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -28,6 +28,8 @@
  * (at your option) any later version.
  */
 
+#include <linux/linkage.h>
+
 #define CTX	%rdi	// arg1
 #define BUF	%rsi	// arg2
 #define CNT	%rdx	// arg3
@@ -69,10 +71,8 @@
  * param: function's name
  */
 .macro SHA1_VECTOR_ASM  name
-	.global	\name
-	.type	\name, @function
-	.align 32
-\name:
+	ENTRY(\name)
+
 	push	%rbx
 	push	%rbp
 	push	%r12
@@ -106,7 +106,7 @@
 	pop	%rbx
 	ret
 
-	.size	\name, .-\name
+	ENDPROC(\name)
 .endm
 
 /*
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 ebac16bfa830..8d3e113b2c95 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -23,6 +23,7 @@
  *
  */
 
+#include <linux/linkage.h>
 #include "glue_helper-asm-avx.S"
 
 .file "twofish-avx-x86_64-asm_64.S"
@@ -243,8 +244,6 @@
 	vpxor		x3, wkey, x3;
 
 .align 8
-.type	__twofish_enc_blk8,@function;
-
 __twofish_enc_blk8:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -284,10 +283,9 @@ __twofish_enc_blk8:
 	outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
 
 	ret;
+ENDPROC(__twofish_enc_blk8)
 
 .align 8
-.type	__twofish_dec_blk8,@function;
-
 __twofish_dec_blk8:
 	/* input:
 	 *	%rdi: ctx, CTX
@@ -325,12 +323,9 @@ __twofish_dec_blk8:
 	outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
 
 	ret;
+ENDPROC(__twofish_dec_blk8)
 
-.align 8
-.global twofish_ecb_enc_8way
-.type   twofish_ecb_enc_8way,@function;
-
-twofish_ecb_enc_8way:
+ENTRY(twofish_ecb_enc_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -346,12 +341,9 @@ twofish_ecb_enc_8way:
 	store_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);
 
 	ret;
+ENDPROC(twofish_ecb_enc_8way)
 
-.align 8
-.global twofish_ecb_dec_8way
-.type   twofish_ecb_dec_8way,@function;
-
-twofish_ecb_dec_8way:
+ENTRY(twofish_ecb_dec_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -367,12 +359,9 @@ twofish_ecb_dec_8way:
 	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
 
 	ret;
+ENDPROC(twofish_ecb_dec_8way)
 
-.align 8
-.global twofish_cbc_dec_8way
-.type   twofish_cbc_dec_8way,@function;
-
-twofish_cbc_dec_8way:
+ENTRY(twofish_cbc_dec_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -393,12 +382,9 @@ twofish_cbc_dec_8way:
 	popq %r12;
 
 	ret;
+ENDPROC(twofish_cbc_dec_8way)
 
-.align 8
-.global twofish_ctr_8way
-.type   twofish_ctr_8way,@function;
-
-twofish_ctr_8way:
+ENTRY(twofish_ctr_8way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -421,3 +407,4 @@ twofish_ctr_8way:
 	popq %r12;
 
 	ret;
+ENDPROC(twofish_ctr_8way)
diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S
index 658af4bb35c9..694ea4587ba7 100644
--- a/arch/x86/crypto/twofish-i586-asm_32.S
+++ b/arch/x86/crypto/twofish-i586-asm_32.S
@@ -20,6 +20,7 @@
 .file "twofish-i586-asm.S"
 .text
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 /* return address at 0 */
@@ -219,11 +220,7 @@
 	xor	%esi,		d ## D;\
 	ror	$1,		d ## D;
 
-.align 4
-.global twofish_enc_blk
-.global twofish_dec_blk
-
-twofish_enc_blk:
+ENTRY(twofish_enc_blk)
 	push	%ebp			/* save registers according to calling convention*/
 	push    %ebx
 	push    %esi
@@ -277,8 +274,9 @@ twofish_enc_blk:
 	pop	%ebp
 	mov	$1,	%eax
 	ret
+ENDPROC(twofish_enc_blk)
 
-twofish_dec_blk:
+ENTRY(twofish_dec_blk)
 	push	%ebp			/* save registers according to calling convention*/
 	push    %ebx
 	push    %esi
@@ -333,3 +331,4 @@ twofish_dec_blk:
 	pop	%ebp
 	mov	$1,	%eax
 	ret
+ENDPROC(twofish_dec_blk)
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index 5b012a2c5119..1c3b7ceb36d2 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -20,6 +20,8 @@
  *
  */
 
+#include <linux/linkage.h>
+
 .file "twofish-x86_64-asm-3way.S"
 .text
 
@@ -214,11 +216,7 @@
 	rorq $32,			RAB2; \
 	outunpack3(mov, RIO, 2, RAB, 2);
 
-.align 8
-.global __twofish_enc_blk_3way
-.type   __twofish_enc_blk_3way,@function;
-
-__twofish_enc_blk_3way:
+ENTRY(__twofish_enc_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -250,7 +248,7 @@ __twofish_enc_blk_3way:
 	popq %rbp; /* bool xor */
 
 	testb %bpl, %bpl;
-	jnz __enc_xor3;
+	jnz .L__enc_xor3;
 
 	outunpack_enc3(mov);
 
@@ -262,7 +260,7 @@ __twofish_enc_blk_3way:
 	popq %r15;
 	ret;
 
-__enc_xor3:
+.L__enc_xor3:
 	outunpack_enc3(xor);
 
 	popq %rbx;
@@ -272,11 +270,9 @@ __enc_xor3:
 	popq %r14;
 	popq %r15;
 	ret;
+ENDPROC(__twofish_enc_blk_3way)
 
-.global twofish_dec_blk_3way
-.type   twofish_dec_blk_3way,@function;
-
-twofish_dec_blk_3way:
+ENTRY(twofish_dec_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -313,4 +309,4 @@ twofish_dec_blk_3way:
 	popq %r14;
 	popq %r15;
 	ret;
-
+ENDPROC(twofish_dec_blk_3way)
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S
index 7bcf3fcc3668..a039d21986a2 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64.S
@@ -20,6 +20,7 @@
 .file "twofish-x86_64-asm.S"
 .text
 
+#include <linux/linkage.h>
 #include <asm/asm-offsets.h>
 
 #define a_offset	0
@@ -214,11 +215,7 @@
 	xor	%r8d,		d ## D;\
 	ror	$1,		d ## D;
 
-.align 8
-.global twofish_enc_blk
-.global twofish_dec_blk
-
-twofish_enc_blk:
+ENTRY(twofish_enc_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
@@ -269,8 +266,9 @@ twofish_enc_blk:
 	popq	R1
 	movq	$1,%rax
 	ret
+ENDPROC(twofish_enc_blk)
 
-twofish_dec_blk:
+ENTRY(twofish_dec_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
@@ -320,3 +318,4 @@ twofish_dec_blk:
 	popq	R1
 	movq	$1,%rax
 	ret
+ENDPROC(twofish_dec_blk)