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

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (54 commits)
  crypto: gf128mul - remove leftover "(EXPERIMENTAL)" in Kconfig
  crypto: serpent-sse2 - remove unneeded LRW/XTS #ifdefs
  crypto: serpent-sse2 - select LRW and XTS
  crypto: twofish-x86_64-3way - remove unneeded LRW/XTS #ifdefs
  crypto: twofish-x86_64-3way - select LRW and XTS
  crypto: xts - remove dependency on EXPERIMENTAL
  crypto: lrw - remove dependency on EXPERIMENTAL
  crypto: picoxcell - fix boolean and / or confusion
  crypto: caam - remove DECO access initialization code
  crypto: caam - fix polarity of "propagate error" logic
  crypto: caam - more desc.h cleanups
  crypto: caam - desc.h - convert spaces to tabs
  crypto: talitos - convert talitos_error to struct device
  crypto: talitos - remove NO_IRQ references
  crypto: talitos - fix bad kfree
  crypto: convert drivers/crypto/* to use module_platform_driver()
  char: hw_random: convert drivers/char/hw_random/* to use module_platform_driver()
  crypto: serpent-sse2 - should select CRYPTO_CRYPTD
  crypto: serpent - rename serpent.c to serpent_generic.c
  crypto: serpent - cleanup checkpatch errors and warnings
  ...

arch/x86/crypto/Makefile

@@ -5,12 +5,14 @@
 obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
 obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
 obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
+obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
 
 obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
 obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
+obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 
@@ -20,12 +22,14 @@ obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
 aes-i586-y := aes-i586-asm_32.o aes_glue.o
 twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
 salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
+serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
 
 aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
 twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
 salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
+serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
 
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
 

arch/x86/crypto/serpent-sse2-i586-asm_32.S

+/*
+ * Serpent Cipher 4-way parallel algorithm (i586/SSE2)
+ *
+ * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on crypto/serpent.c by
+ *  Copyright (C) 2002 Dag Arne Osvik <osvik@ii.uib.no>
+ *                2003 Herbert Valerio Riedel <hvr@gnu.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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 for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+.file "serpent-sse2-i586-asm_32.S"
+.text
+
+#define arg_ctx 4
+#define arg_dst 8
+#define arg_src 12
+#define arg_xor 16
+
+/**********************************************************************
+  4-way SSE2 serpent
+ **********************************************************************/
+#define CTX %edx
+
+#define RA %xmm0
+#define RB %xmm1
+#define RC %xmm2
+#define RD %xmm3
+#define RE %xmm4
+
+#define RT0 %xmm5
+#define RT1 %xmm6
+
+#define RNOT %xmm7
+
+#define get_key(i, j, t) \
+	movd (4*(i)+(j))*4(CTX), t; \
+	pshufd $0, t, t;
+
+#define K(x0, x1, x2, x3, x4, i) \
+	get_key(i, 0, x4); \
+	get_key(i, 1, RT0); \
+	get_key(i, 2, RT1); \
+	pxor x4,		x0; \
+	pxor RT0,		x1; \
+	pxor RT1,		x2; \
+	get_key(i, 3, x4); \
+	pxor x4,		x3;
+
+#define LK(x0, x1, x2, x3, x4, i) \
+	movdqa x0,		x4; \
+	pslld $13,		x0; \
+	psrld $(32 - 13),	x4; \
+	por x4,			x0; \
+	pxor x0,		x1; \
+	movdqa x2,		x4; \
+	pslld $3,		x2; \
+	psrld $(32 - 3),	x4; \
+	por x4,			x2; \
+	pxor x2,		x1; \
+	movdqa x1,		x4; \
+	pslld $1,		x1; \
+	psrld $(32 - 1),	x4; \
+	por x4,			x1; \
+	movdqa x0,		x4; \
+	pslld $3,		x4; \
+	pxor x2,		x3; \
+	pxor x4,		x3; \
+	movdqa x3,		x4; \
+	pslld $7,		x3; \
+	psrld $(32 - 7),	x4; \
+	por x4,			x3; \
+	movdqa x1,		x4; \
+	pslld $7,		x4; \
+	pxor x1,		x0; \
+	pxor x3,		x0; \
+	pxor x3,		x2; \
+	pxor x4,		x2; \
+	movdqa x0,		x4; \
+	get_key(i, 1, RT0); \
+	pxor RT0,		x1; \
+	get_key(i, 3, RT0); \
+	pxor RT0,		x3; \
+	pslld $5,		x0; \
+	psrld $(32 - 5),	x4; \
+	por x4,			x0; \
+	movdqa x2,		x4; \
+	pslld $22,		x2; \
+	psrld $(32 - 22),	x4; \
+	por x4,			x2; \
+	get_key(i, 0, RT0); \
+	pxor RT0,		x0; \
+	get_key(i, 2, RT0); \
+	pxor RT0,		x2;
+
+#define KL(x0, x1, x2, x3, x4, i) \
+	K(x0, x1, x2, x3, x4, i); \
+	movdqa x0,		x4; \
+	psrld $5,		x0; \
+	pslld $(32 - 5),	x4; \
+	por x4,			x0; \
+	movdqa x2,		x4; \
+	psrld $22,		x2; \
+	pslld $(32 - 22),	x4; \
+	por x4,			x2; \
+	pxor x3,		x2; \
+	pxor x3,		x0; \
+	movdqa x1,		x4; \
+	pslld $7,		x4; \
+	pxor x1,		x0; \
+	pxor x4,		x2; \
+	movdqa x1,		x4; \
+	psrld $1,		x1; \
+	pslld $(32 - 1),	x4; \
+	por x4,			x1; \
+	movdqa x3,		x4; \
+	psrld $7,		x3; \
+	pslld $(32 - 7),	x4; \
+	por x4,			x3; \
+	pxor x0,		x1; \
+	movdqa x0,		x4; \
+	pslld $3,		x4; \
+	pxor x4,		x3; \
+	movdqa x0,		x4; \
+	psrld $13,		x0; \
+	pslld $(32 - 13),	x4; \
+	por x4,			x0; \
+	pxor x2,		x1; \
+	pxor x2,		x3; \
+	movdqa x2,		x4; \
+	psrld $3,		x2; \
+	pslld $(32 - 3),	x4; \
+	por x4,			x2;
+
+#define S0(x0, x1, x2, x3, x4) \
+	movdqa x3,		x4; \
+	por x0,			x3; \
+	pxor x4,		x0; \
+	pxor x2,		x4; \
+	pxor RNOT,		x4; \
+	pxor x1,		x3; \
+	pand x0,		x1; \
+	pxor x4,		x1; \
+	pxor x0,		x2; \
+	pxor x3,		x0; \
+	por x0,			x4; \
+	pxor x2,		x0; \
+	pand x1,		x2; \
+	pxor x2,		x3; \
+	pxor RNOT,		x1; \
+	pxor x4,		x2; \
+	pxor x2,		x1;
+
+#define S1(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	pxor x0,		x1; \
+	pxor x3,		x0; \
+	pxor RNOT,		x3; \
+	pand x1,		x4; \
+	por x1,			x0; \
+	pxor x2,		x3; \
+	pxor x3,		x0; \
+	pxor x3,		x1; \
+	pxor x4,		x3; \
+	por x4,			x1; \
+	pxor x2,		x4; \
+	pand x0,		x2; \
+	pxor x1,		x2; \
+	por x0,			x1; \
+	pxor RNOT,		x0; \
+	pxor x2,		x0; \
+	pxor x1,		x4;
+
+#define S2(x0, x1, x2, x3, x4) \
+	pxor RNOT,		x3; \
+	pxor x0,		x1; \
+	movdqa x0,		x4; \
+	pand x2,		x0; \
+	pxor x3,		x0; \
+	por x4,			x3; \
+	pxor x1,		x2; \
+	pxor x1,		x3; \
+	pand x0,		x1; \
+	pxor x2,		x0; \
+	pand x3,		x2; \
+	por x1,			x3; \
+	pxor RNOT,		x0; \
+	pxor x0,		x3; \
+	pxor x0,		x4; \
+	pxor x2,		x0; \
+	por x2,			x1;
+
+#define S3(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	pxor x3,		x1; \
+	por x0,			x3; \
+	pand x0,		x4; \
+	pxor x2,		x0; \
+	pxor x1,		x2; \
+	pand x3,		x1; \
+	pxor x3,		x2; \
+	por x4,			x0; \
+	pxor x3,		x4; \
+	pxor x0,		x1; \
+	pand x3,		x0; \
+	pand x4,		x3; \
+	pxor x2,		x3; \
+	por x1,			x4; \
+	pand x1,		x2; \
+	pxor x3,		x4; \
+	pxor x3,		x0; \
+	pxor x2,		x3;
+
+#define S4(x0, x1, x2, x3, x4) \
+	movdqa x3,		x4; \
+	pand x0,		x3; \
+	pxor x4,		x0; \
+	pxor x2,		x3; \
+	por x4,			x2; \
+	pxor x1,		x0; \
+	pxor x3,		x4; \
+	por x0,			x2; \
+	pxor x1,		x2; \
+	pand x0,		x1; \
+	pxor x4,		x1; \
+	pand x2,		x4; \
+	pxor x3,		x2; \
+	pxor x0,		x4; \
+	por x1,			x3; \
+	pxor RNOT,		x1; \
+	pxor x0,		x3;
+
+#define S5(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	por x0,			x1; \
+	pxor x1,		x2; \
+	pxor RNOT,		x3; \
+	pxor x0,		x4; \
+	pxor x2,		x0; \
+	pand x4,		x1; \
+	por x3,			x4; \
+	pxor x0,		x4; \
+	pand x3,		x0; \
+	pxor x3,		x1; \
+	pxor x2,		x3; \
+	pxor x1,		x0; \
+	pand x4,		x2; \
+	pxor x2,		x1; \
+	pand x0,		x2; \
+	pxor x2,		x3;
+
+#define S6(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	pxor x0,		x3; \
+	pxor x2,		x1; \
+	pxor x0,		x2; \
+	pand x3,		x0; \
+	por x3,			x1; \
+	pxor RNOT,		x4; \
+	pxor x1,		x0; \
+	pxor x2,		x1; \
+	pxor x4,		x3; \
+	pxor x0,		x4; \
+	pand x0,		x2; \
+	pxor x1,		x4; \
+	pxor x3,		x2; \
+	pand x1,		x3; \
+	pxor x0,		x3; \
+	pxor x2,		x1;
+
+#define S7(x0, x1, x2, x3, x4) \
+	pxor RNOT,		x1; \
+	movdqa x1,		x4; \
+	pxor RNOT,		x0; \
+	pand x2,		x1; \
+	pxor x3,		x1; \
+	por x4,			x3; \
+	pxor x2,		x4; \
+	pxor x3,		x2; \
+	pxor x0,		x3; \
+	por x1,			x0; \
+	pand x0,		x2; \
+	pxor x4,		x0; \
+	pxor x3,		x4; \
+	pand x0,		x3; \
+	pxor x1,		x4; \
+	pxor x4,		x2; \
+	pxor x1,		x3; \
+	por x0,			x4; \
+	pxor x1,		x4;
+
+#define SI0(x0, x1, x2, x3, x4) \
+	movdqa x3,		x4; \
+	pxor x0,		x1; \
+	por x1,			x3; \
+	pxor x1,		x4; \
+	pxor RNOT,		x0; \
+	pxor x3,		x2; \
+	pxor x0,		x3; \
+	pand x1,		x0; \
+	pxor x2,		x0; \
+	pand x3,		x2; \
+	pxor x4,		x3; \
+	pxor x3,		x2; \
+	pxor x3,		x1; \
+	pand x0,		x3; \
+	pxor x0,		x1; \
+	pxor x2,		x0; \
+	pxor x3,		x4;
+
+#define SI1(x0, x1, x2, x3, x4) \
+	pxor x3,		x1; \
+	movdqa x0,		x4; \
+	pxor x2,		x0; \
+	pxor RNOT,		x2; \
+	por x1,			x4; \
+	pxor x3,		x4; \
+	pand x1,		x3; \
+	pxor x2,		x1; \
+	pand x4,		x2; \
+	pxor x1,		x4; \
+	por x3,			x1; \
+	pxor x0,		x3; \
+	pxor x0,		x2; \
+	por x4,			x0; \
+	pxor x4,		x2; \
+	pxor x0,		x1; \
+	pxor x1,		x4;
+
+#define SI2(x0, x1, x2, x3, x4) \
+	pxor x1,		x2; \
+	movdqa x3,		x4; \
+	pxor RNOT,		x3; \
+	por x2,			x3; \
+	pxor x4,		x2; \
+	pxor x0,		x4; \
+	pxor x1,		x3; \
+	por x2,			x1; \
+	pxor x0,		x2; \
+	pxor x4,		x1; \
+	por x3,			x4; \
+	pxor x3,		x2; \
+	pxor x2,		x4; \
+	pand x1,		x2; \
+	pxor x3,		x2; \
+	pxor x4,		x3; \
+	pxor x0,		x4;
+
+#define SI3(x0, x1, x2, x3, x4) \
+	pxor x1,		x2; \
+	movdqa x1,		x4; \
+	pand x2,		x1; \
+	pxor x0,		x1; \
+	por x4,			x0; \
+	pxor x3,		x4; \
+	pxor x3,		x0; \
+	por x1,			x3; \
+	pxor x2,		x1; \
+	pxor x3,		x1; \
+	pxor x2,		x0; \
+	pxor x3,		x2; \
+	pand x1,		x3; \
+	pxor x0,		x1; \
+	pand x2,		x0; \
+	pxor x3,		x4; \
+	pxor x0,		x3; \
+	pxor x1,		x0;
+
+#define SI4(x0, x1, x2, x3, x4) \
+	pxor x3,		x2; \
+	movdqa x0,		x4; \
+	pand x1,		x0; \
+	pxor x2,		x0; \
+	por x3,			x2; \
+	pxor RNOT,		x4; \
+	pxor x0,		x1; \
+	pxor x2,		x0; \
+	pand x4,		x2; \
+	pxor x0,		x2; \
+	por x4,			x0; \
+	pxor x3,		x0; \
+	pand x2,		x3; \
+	pxor x3,		x4; \
+	pxor x1,		x3; \
+	pand x0,		x1; \
+	pxor x1,		x4; \
+	pxor x3,		x0;
+
+#define SI5(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	por x2,			x1; \
+	pxor x4,		x2; \
+	pxor x3,		x1; \
+	pand x4,		x3; \
+	pxor x3,		x2; \
+	por x0,			x3; \
+	pxor RNOT,		x0; \
+	pxor x2,		x3; \
+	por x0,			x2; \
+	pxor x1,		x4; \
+	pxor x4,		x2; \
+	pand x0,		x4; \
+	pxor x1,		x0; \
+	pxor x3,		x1; \
+	pand x2,		x0; \
+	pxor x3,		x2; \
+	pxor x2,		x0; \
+	pxor x4,		x2; \
+	pxor x3,		x4;
+
+#define SI6(x0, x1, x2, x3, x4) \
+	pxor x2,		x0; \
+	movdqa x0,		x4; \
+	pand x3,		x0; \
+	pxor x3,		x2; \
+	pxor x2,		x0; \
+	pxor x1,		x3; \
+	por x4,			x2; \
+	pxor x3,		x2; \
+	pand x0,		x3; \
+	pxor RNOT,		x0; \
+	pxor x1,		x3; \
+	pand x2,		x1; \
+	pxor x0,		x4; \
+	pxor x4,		x3; \
+	pxor x2,		x4; \
+	pxor x1,		x0; \
+	pxor x0,		x2;
+
+#define SI7(x0, x1, x2, x3, x4) \
+	movdqa x3,		x4; \
+	pand x0,		x3; \
+	pxor x2,		x0; \
+	por x4,			x2; \
+	pxor x1,		x4; \
+	pxor RNOT,		x0; \
+	por x3,			x1; \
+	pxor x0,		x4; \
+	pand x2,		x0; \
+	pxor x1,		x0; \
+	pand x2,		x1; \
+	pxor x2,		x3; \
+	pxor x3,		x4; \
+	pand x3,		x2; \
+	por x0,			x3; \
+	pxor x4,		x1; \
+	pxor x4,		x3; \
+	pand x0,		x4; \
+	pxor x2,		x4;
+
+#define transpose_4x4(x0, x1, x2, x3, t1, t2, t3) \
+	movdqa x2,		t3; \
+	movdqa x0,		t1; \
+	unpcklps x3,		t3; \
+	movdqa x0,		t2; \
+	unpcklps x1,		t1; \
+	unpckhps x1,		t2; \
+	movdqa t3,		x1; \
+	unpckhps x3,		x2; \
+	movdqa t1,		x0; \
+	movhlps t1,		x1; \
+	movdqa t2,		t1; \
+	movlhps t3,		x0; \
+	movlhps x2,		t1; \
+	movhlps t2,		x2; \
+	movdqa x2,		x3; \
+	movdqa t1,		x2;
+
+#define read_blocks(in, x0, x1, x2, x3, t0, t1, t2) \
+	movdqu (0*4*4)(in),	x0; \
+	movdqu (1*4*4)(in),	x1; \
+	movdqu (2*4*4)(in),	x2; \
+	movdqu (3*4*4)(in),	x3; \
+	\
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
+
+#define write_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	movdqu x0, (0*4*4)(out); \
+	movdqu x1, (1*4*4)(out); \
+	movdqu x2, (2*4*4)(out); \
+	movdqu x3, (3*4*4)(out);
+
+#define xor_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	movdqu (0*4*4)(out),	t0; \
+	pxor t0,		x0; \
+	movdqu x0,		(0*4*4)(out); \
+	movdqu (1*4*4)(out),	t0; \
+	pxor t0,		x1; \
+	movdqu x1,		(1*4*4)(out); \
+	movdqu (2*4*4)(out),	t0; \
+	pxor t0,		x2; \
+	movdqu x2,		(2*4*4)(out); \
+	movdqu (3*4*4)(out),	t0; \
+	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:
+	/* input:
+	 *	arg_ctx(%esp): ctx, CTX
+	 *	arg_dst(%esp): dst
+	 *	arg_src(%esp): src
+	 *	arg_xor(%esp): bool, if true: xor output
+	 */
+
+	pcmpeqd RNOT, RNOT;
+
+	movl arg_ctx(%esp), CTX;
+
+	movl arg_src(%esp), %eax;
+	read_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
+
+					 K(RA, RB, RC, RD, RE, 0);
+	S0(RA, RB, RC, RD, RE);		LK(RC, RB, RD, RA, RE, 1);
+	S1(RC, RB, RD, RA, RE);		LK(RE, RD, RA, RC, RB, 2);
+	S2(RE, RD, RA, RC, RB);		LK(RB, RD, RE, RC, RA, 3);
+	S3(RB, RD, RE, RC, RA);		LK(RC, RA, RD, RB, RE, 4);
+	S4(RC, RA, RD, RB, RE);		LK(RA, RD, RB, RE, RC, 5);
+	S5(RA, RD, RB, RE, RC);		LK(RC, RA, RD, RE, RB, 6);
+	S6(RC, RA, RD, RE, RB);		LK(RD, RB, RA, RE, RC, 7);
+	S7(RD, RB, RA, RE, RC);		LK(RC, RA, RE, RD, RB, 8);
+	S0(RC, RA, RE, RD, RB);		LK(RE, RA, RD, RC, RB, 9);
+	S1(RE, RA, RD, RC, RB);		LK(RB, RD, RC, RE, RA, 10);
+	S2(RB, RD, RC, RE, RA);		LK(RA, RD, RB, RE, RC, 11);
+	S3(RA, RD, RB, RE, RC);		LK(RE, RC, RD, RA, RB, 12);
+	S4(RE, RC, RD, RA, RB);		LK(RC, RD, RA, RB, RE, 13);
+	S5(RC, RD, RA, RB, RE);		LK(RE, RC, RD, RB, RA, 14);
+	S6(RE, RC, RD, RB, RA);		LK(RD, RA, RC, RB, RE, 15);
+	S7(RD, RA, RC, RB, RE);		LK(RE, RC, RB, RD, RA, 16);
+	S0(RE, RC, RB, RD, RA);		LK(RB, RC, RD, RE, RA, 17);
+	S1(RB, RC, RD, RE, RA);		LK(RA, RD, RE, RB, RC, 18);
+	S2(RA, RD, RE, RB, RC);		LK(RC, RD, RA, RB, RE, 19);
+	S3(RC, RD, RA, RB, RE);		LK(RB, RE, RD, RC, RA, 20);
+	S4(RB, RE, RD, RC, RA);		LK(RE, RD, RC, RA, RB, 21);
+	S5(RE, RD, RC, RA, RB);		LK(RB, RE, RD, RA, RC, 22);
+	S6(RB, RE, RD, RA, RC);		LK(RD, RC, RE, RA, RB, 23);
+	S7(RD, RC, RE, RA, RB);		LK(RB, RE, RA, RD, RC, 24);
+	S0(RB, RE, RA, RD, RC);		LK(RA, RE, RD, RB, RC, 25);
+	S1(RA, RE, RD, RB, RC);		LK(RC, RD, RB, RA, RE, 26);
+	S2(RC, RD, RB, RA, RE);		LK(RE, RD, RC, RA, RB, 27);
+	S3(RE, RD, RC, RA, RB);		LK(RA, RB, RD, RE, RC, 28);
+	S4(RA, RB, RD, RE, RC);		LK(RB, RD, RE, RC, RA, 29);
+	S5(RB, RD, RE, RC, RA);		LK(RA, RB, RD, RC, RE, 30);
+	S6(RA, RB, RD, RC, RE);		LK(RD, RE, RB, RC, RA, 31);
+	S7(RD, RE, RB, RC, RA);		 K(RA, RB, RC, RD, RE, 32);
+
+	movl arg_dst(%esp), %eax;
+
+	cmpb $0, arg_xor(%esp);
+	jnz __enc_xor4;
+
+	write_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
+
+	ret;
+
+__enc_xor4:
+	xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
+
+	ret;
+
+.align 8
+.global serpent_dec_blk_4way
+.type   serpent_dec_blk_4way,@function;
+
+serpent_dec_blk_4way:
+	/* input:
+	 *	arg_ctx(%esp): ctx, CTX
+	 *	arg_dst(%esp): dst
+	 *	arg_src(%esp): src
+	 */
+
+	pcmpeqd RNOT, RNOT;
+
+	movl arg_ctx(%esp), CTX;
+
+	movl arg_src(%esp), %eax;
+	read_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
+
+					 K(RA, RB, RC, RD, RE, 32);
+	SI7(RA, RB, RC, RD, RE);	KL(RB, RD, RA, RE, RC, 31);
+	SI6(RB, RD, RA, RE, RC);	KL(RA, RC, RE, RB, RD, 30);
+	SI5(RA, RC, RE, RB, RD);	KL(RC, RD, RA, RE, RB, 29);
+	SI4(RC, RD, RA, RE, RB);	KL(RC, RA, RB, RE, RD, 28);
+	SI3(RC, RA, RB, RE, RD);	KL(RB, RC, RD, RE, RA, 27);
+	SI2(RB, RC, RD, RE, RA);	KL(RC, RA, RE, RD, RB, 26);
+	SI1(RC, RA, RE, RD, RB);	KL(RB, RA, RE, RD, RC, 25);
+	SI0(RB, RA, RE, RD, RC);	KL(RE, RC, RA, RB, RD, 24);
+	SI7(RE, RC, RA, RB, RD);	KL(RC, RB, RE, RD, RA, 23);
+	SI6(RC, RB, RE, RD, RA);	KL(RE, RA, RD, RC, RB, 22);
+	SI5(RE, RA, RD, RC, RB);	KL(RA, RB, RE, RD, RC, 21);
+	SI4(RA, RB, RE, RD, RC);	KL(RA, RE, RC, RD, RB, 20);
+	SI3(RA, RE, RC, RD, RB);	KL(RC, RA, RB, RD, RE, 19);
+	SI2(RC, RA, RB, RD, RE);	KL(RA, RE, RD, RB, RC, 18);
+	SI1(RA, RE, RD, RB, RC);	KL(RC, RE, RD, RB, RA, 17);
+	SI0(RC, RE, RD, RB, RA);	KL(RD, RA, RE, RC, RB, 16);
+	SI7(RD, RA, RE, RC, RB);	KL(RA, RC, RD, RB, RE, 15);
+	SI6(RA, RC, RD, RB, RE);	KL(RD, RE, RB, RA, RC, 14);
+	SI5(RD, RE, RB, RA, RC);	KL(RE, RC, RD, RB, RA, 13);
+	SI4(RE, RC, RD, RB, RA);	KL(RE, RD, RA, RB, RC, 12);
+	SI3(RE, RD, RA, RB, RC);	KL(RA, RE, RC, RB, RD, 11);
+	SI2(RA, RE, RC, RB, RD);	KL(RE, RD, RB, RC, RA, 10);
+	SI1(RE, RD, RB, RC, RA);	KL(RA, RD, RB, RC, RE, 9);
+	SI0(RA, RD, RB, RC, RE);	KL(RB, RE, RD, RA, RC, 8);
+	SI7(RB, RE, RD, RA, RC);	KL(RE, RA, RB, RC, RD, 7);
+	SI6(RE, RA, RB, RC, RD);	KL(RB, RD, RC, RE, RA, 6);
+	SI5(RB, RD, RC, RE, RA);	KL(RD, RA, RB, RC, RE, 5);
+	SI4(RD, RA, RB, RC, RE);	KL(RD, RB, RE, RC, RA, 4);
+	SI3(RD, RB, RE, RC, RA);	KL(RE, RD, RA, RC, RB, 3);
+	SI2(RE, RD, RA, RC, RB);	KL(RD, RB, RC, RA, RE, 2);
+	SI1(RD, RB, RC, RA, RE);	KL(RE, RB, RC, RA, RD, 1);
+	SI0(RE, RB, RC, RA, RD);	 K(RC, RD, RB, RE, RA, 0);
+
+	movl arg_dst(%esp), %eax;
+	write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);
+
+	ret;

arch/x86/crypto/serpent-sse2-x86_64-asm_64.S

+/*
+ * Serpent Cipher 8-way parallel algorithm (x86_64/SSE2)
+ *
+ * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on crypto/serpent.c by
+ *  Copyright (C) 2002 Dag Arne Osvik <osvik@ii.uib.no>
+ *                2003 Herbert Valerio Riedel <hvr@gnu.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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 for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+.file "serpent-sse2-x86_64-asm_64.S"
+.text
+
+#define CTX %rdi
+
+/**********************************************************************
+  8-way SSE2 serpent
+ **********************************************************************/
+#define RA1 %xmm0
+#define RB1 %xmm1
+#define RC1 %xmm2
+#define RD1 %xmm3
+#define RE1 %xmm4
+
+#define RA2 %xmm5
+#define RB2 %xmm6
+#define RC2 %xmm7
+#define RD2 %xmm8
+#define RE2 %xmm9
+
+#define RNOT %xmm10
+
+#define RK0 %xmm11
+#define RK1 %xmm12
+#define RK2 %xmm13
+#define RK3 %xmm14
+
+#define S0_1(x0, x1, x2, x3, x4) \
+	movdqa x3,		x4; \
+	por x0,			x3; \
+	pxor x4,		x0; \
+	pxor x2,		x4; \
+	pxor RNOT,		x4; \
+	pxor x1,		x3; \
+	pand x0,		x1; \
+	pxor x4,		x1; \
+	pxor x0,		x2;
+#define S0_2(x0, x1, x2, x3, x4) \
+	pxor x3,		x0; \
+	por x0,			x4; \
+	pxor x2,		x0; \
+	pand x1,		x2; \
+	pxor x2,		x3; \
+	pxor RNOT,		x1; \
+	pxor x4,		x2; \
+	pxor x2,		x1;
+
+#define S1_1(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	pxor x0,		x1; \
+	pxor x3,		x0; \
+	pxor RNOT,		x3; \
+	pand x1,		x4; \
+	por x1,			x0; \
+	pxor x2,		x3; \
+	pxor x3,		x0; \
+	pxor x3,		x1;
+#define S1_2(x0, x1, x2, x3, x4) \
+	pxor x4,		x3; \
+	por x4,			x1; \
+	pxor x2,		x4; \
+	pand x0,		x2; \
+	pxor x1,		x2; \
+	por x0,			x1; \
+	pxor RNOT,		x0; \
+	pxor x2,		x0; \
+	pxor x1,		x4;
+
+#define S2_1(x0, x1, x2, x3, x4) \
+	pxor RNOT,		x3; \
+	pxor x0,		x1; \
+	movdqa x0,		x4; \
+	pand x2,		x0; \
+	pxor x3,		x0; \
+	por x4,			x3; \
+	pxor x1,		x2; \
+	pxor x1,		x3; \
+	pand x0,		x1;
+#define S2_2(x0, x1, x2, x3, x4) \
+	pxor x2,		x0; \
+	pand x3,		x2; \
+	por x1,			x3; \
+	pxor RNOT,		x0; \
+	pxor x0,		x3; \
+	pxor x0,		x4; \
+	pxor x2,		x0; \
+	por x2,			x1;
+
+#define S3_1(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	pxor x3,		x1; \
+	por x0,			x3; \
+	pand x0,		x4; \
+	pxor x2,		x0; \
+	pxor x1,		x2; \
+	pand x3,		x1; \
+	pxor x3,		x2; \
+	por x4,			x0; \
+	pxor x3,		x4;
+#define S3_2(x0, x1, x2, x3, x4) \
+	pxor x0,		x1; \
+	pand x3,		x0; \
+	pand x4,		x3; \
+	pxor x2,		x3; \
+	por x1,			x4; \
+	pand x1,		x2; \
+	pxor x3,		x4; \
+	pxor x3,		x0; \
+	pxor x2,		x3;
+
+#define S4_1(x0, x1, x2, x3, x4) \
+	movdqa x3,		x4; \
+	pand x0,		x3; \
+	pxor x4,		x0; \
+	pxor x2,		x3; \
+	por x4,			x2; \
+	pxor x1,		x0; \
+	pxor x3,		x4; \
+	por x0,			x2; \
+	pxor x1,		x2;
+#define S4_2(x0, x1, x2, x3, x4) \
+	pand x0,		x1; \
+	pxor x4,		x1; \
+	pand x2,		x4; \
+	pxor x3,		x2; \
+	pxor x0,		x4; \
+	por x1,			x3; \
+	pxor RNOT,		x1; \
+	pxor x0,		x3;
+
+#define S5_1(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	por x0,			x1; \
+	pxor x1,		x2; \
+	pxor RNOT,		x3; \
+	pxor x0,		x4; \
+	pxor x2,		x0; \
+	pand x4,		x1; \
+	por x3,			x4; \
+	pxor x0,		x4;
+#define S5_2(x0, x1, x2, x3, x4) \
+	pand x3,		x0; \
+	pxor x3,		x1; \
+	pxor x2,		x3; \
+	pxor x1,		x0; \
+	pand x4,		x2; \
+	pxor x2,		x1; \
+	pand x0,		x2; \
+	pxor x2,		x3;
+
+#define S6_1(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	pxor x0,		x3; \
+	pxor x2,		x1; \
+	pxor x0,		x2; \
+	pand x3,		x0; \
+	por x3,			x1; \
+	pxor RNOT,		x4; \
+	pxor x1,		x0; \
+	pxor x2,		x1;
+#define S6_2(x0, x1, x2, x3, x4) \
+	pxor x4,		x3; \
+	pxor x0,		x4; \
+	pand x0,		x2; \
+	pxor x1,		x4; \
+	pxor x3,		x2; \
+	pand x1,		x3; \
+	pxor x0,		x3; \
+	pxor x2,		x1;
+
+#define S7_1(x0, x1, x2, x3, x4) \
+	pxor RNOT,		x1; \
+	movdqa x1,		x4; \
+	pxor RNOT,		x0; \
+	pand x2,		x1; \
+	pxor x3,		x1; \
+	por x4,			x3; \
+	pxor x2,		x4; \
+	pxor x3,		x2; \
+	pxor x0,		x3; \
+	por x1,			x0;
+#define S7_2(x0, x1, x2, x3, x4) \
+	pand x0,		x2; \
+	pxor x4,		x0; \
+	pxor x3,		x4; \
+	pand x0,		x3; \
+	pxor x1,		x4; \
+	pxor x4,		x2; \
+	pxor x1,		x3; \
+	por x0,			x4; \
+	pxor x1,		x4;
+
+#define SI0_1(x0, x1, x2, x3, x4) \
+	movdqa x3,		x4; \
+	pxor x0,		x1; \
+	por x1,			x3; \
+	pxor x1,		x4; \
+	pxor RNOT,		x0; \
+	pxor x3,		x2; \
+	pxor x0,		x3; \
+	pand x1,		x0; \
+	pxor x2,		x0;
+#define SI0_2(x0, x1, x2, x3, x4) \
+	pand x3,		x2; \
+	pxor x4,		x3; \
+	pxor x3,		x2; \
+	pxor x3,		x1; \
+	pand x0,		x3; \
+	pxor x0,		x1; \
+	pxor x2,		x0; \
+	pxor x3,		x4;
+
+#define SI1_1(x0, x1, x2, x3, x4) \
+	pxor x3,		x1; \
+	movdqa x0,		x4; \
+	pxor x2,		x0; \
+	pxor RNOT,		x2; \
+	por x1,			x4; \
+	pxor x3,		x4; \
+	pand x1,		x3; \
+	pxor x2,		x1; \
+	pand x4,		x2;
+#define SI1_2(x0, x1, x2, x3, x4) \
+	pxor x1,		x4; \
+	por x3,			x1; \
+	pxor x0,		x3; \
+	pxor x0,		x2; \
+	por x4,			x0; \
+	pxor x4,		x2; \
+	pxor x0,		x1; \
+	pxor x1,		x4;
+
+#define SI2_1(x0, x1, x2, x3, x4) \
+	pxor x1,		x2; \
+	movdqa x3,		x4; \
+	pxor RNOT,		x3; \
+	por x2,			x3; \
+	pxor x4,		x2; \
+	pxor x0,		x4; \
+	pxor x1,		x3; \
+	por x2,			x1; \
+	pxor x0,		x2;
+#define SI2_2(x0, x1, x2, x3, x4) \
+	pxor x4,		x1; \
+	por x3,			x4; \
+	pxor x3,		x2; \
+	pxor x2,		x4; \
+	pand x1,		x2; \
+	pxor x3,		x2; \
+	pxor x4,		x3; \
+	pxor x0,		x4;
+
+#define SI3_1(x0, x1, x2, x3, x4) \
+	pxor x1,		x2; \
+	movdqa x1,		x4; \
+	pand x2,		x1; \
+	pxor x0,		x1; \
+	por x4,			x0; \
+	pxor x3,		x4; \
+	pxor x3,		x0; \
+	por x1,			x3; \
+	pxor x2,		x1;
+#define SI3_2(x0, x1, x2, x3, x4) \
+	pxor x3,		x1; \
+	pxor x2,		x0; \
+	pxor x3,		x2; \
+	pand x1,		x3; \
+	pxor x0,		x1; \
+	pand x2,		x0; \
+	pxor x3,		x4; \
+	pxor x0,		x3; \
+	pxor x1,		x0;
+
+#define SI4_1(x0, x1, x2, x3, x4) \
+	pxor x3,		x2; \
+	movdqa x0,		x4; \
+	pand x1,		x0; \
+	pxor x2,		x0; \
+	por x3,			x2; \
+	pxor RNOT,		x4; \
+	pxor x0,		x1; \
+	pxor x2,		x0; \
+	pand x4,		x2;
+#define SI4_2(x0, x1, x2, x3, x4) \
+	pxor x0,		x2; \
+	por x4,			x0; \
+	pxor x3,		x0; \
+	pand x2,		x3; \
+	pxor x3,		x4; \
+	pxor x1,		x3; \
+	pand x0,		x1; \
+	pxor x1,		x4; \
+	pxor x3,		x0;
+
+#define SI5_1(x0, x1, x2, x3, x4) \
+	movdqa x1,		x4; \
+	por x2,			x1; \
+	pxor x4,		x2; \
+	pxor x3,		x1; \
+	pand x4,		x3; \
+	pxor x3,		x2; \
+	por x0,			x3; \
+	pxor RNOT,		x0; \
+	pxor x2,		x3; \
+	por x0,			x2;
+#define SI5_2(x0, x1, x2, x3, x4) \
+	pxor x1,		x4; \
+	pxor x4,		x2; \
+	pand x0,		x4; \
+	pxor x1,		x0; \
+	pxor x3,		x1; \
+	pand x2,		x0; \
+	pxor x3,		x2; \
+	pxor x2,		x0; \
+	pxor x4,		x2; \
+	pxor x3,		x4;
+
+#define SI6_1(x0, x1, x2, x3, x4) \
+	pxor x2,		x0; \
+	movdqa x0,		x4; \
+	pand x3,		x0; \
+	pxor x3,		x2; \
+	pxor x2,		x0; \
+	pxor x1,		x3; \
+	por x4,			x2; \
+	pxor x3,		x2; \
+	pand x0,		x3;
+#define SI6_2(x0, x1, x2, x3, x4) \
+	pxor RNOT,		x0; \
+	pxor x1,		x3; \
+	pand x2,		x1; \
+	pxor x0,		x4; \
+	pxor x4,		x3; \
+	pxor x2,		x4; \
+	pxor x1,		x0; \
+	pxor x0,		x2;
+
+#define SI7_1(x0, x1, x2, x3, x4) \
+	movdqa x3,		x4; \
+	pand x0,		x3; \
+	pxor x2,		x0; \
+	por x4,			x2; \
+	pxor x1,		x4; \
+	pxor RNOT,		x0; \
+	por x3,			x1; \
+	pxor x0,		x4; \
+	pand x2,		x0; \
+	pxor x1,		x0;
+#define SI7_2(x0, x1, x2, x3, x4) \
+	pand x2,		x1; \
+	pxor x2,		x3; \
+	pxor x3,		x4; \
+	pand x3,		x2; \
+	por x0,			x3; \
+	pxor x4,		x1; \
+	pxor x4,		x3; \
+	pand x0,		x4; \
+	pxor x2,		x4;
+
+#define get_key(i, j, t) \
+	movd (4*(i)+(j))*4(CTX), t; \
+	pshufd $0, t, t;
+
+#define K2(x0, x1, x2, x3, x4, i) \
+	get_key(i, 0, RK0); \
+	get_key(i, 1, RK1); \
+	get_key(i, 2, RK2); \
+	get_key(i, 3, RK3); \
+	pxor RK0,		x0 ## 1; \
+	pxor RK1,		x1 ## 1; \
+	pxor RK2,		x2 ## 1; \
+	pxor RK3,		x3 ## 1; \
+		pxor RK0,		x0 ## 2; \
+		pxor RK1,		x1 ## 2; \
+		pxor RK2,		x2 ## 2; \
+		pxor RK3,		x3 ## 2;
+
+#define LK2(x0, x1, x2, x3, x4, i) \
+	movdqa x0 ## 1,		x4 ## 1; \
+	pslld $13,		x0 ## 1; \
+	psrld $(32 - 13),	x4 ## 1; \
+	por x4 ## 1,		x0 ## 1; \
+	pxor x0 ## 1,		x1 ## 1; \
+	movdqa x2 ## 1,		x4 ## 1; \
+	pslld $3,		x2 ## 1; \
+	psrld $(32 - 3),	x4 ## 1; \
+	por x4 ## 1,		x2 ## 1; \
+	pxor x2 ## 1,		x1 ## 1; \
+		movdqa x0 ## 2,		x4 ## 2; \
+		pslld $13,		x0 ## 2; \
+		psrld $(32 - 13),	x4 ## 2; \
+		por x4 ## 2,		x0 ## 2; \
+		pxor x0 ## 2,		x1 ## 2; \
+		movdqa x2 ## 2,		x4 ## 2; \
+		pslld $3,		x2 ## 2; \
+		psrld $(32 - 3),	x4 ## 2; \
+		por x4 ## 2,		x2 ## 2; \
+		pxor x2 ## 2,		x1 ## 2; \
+	movdqa x1 ## 1,		x4 ## 1; \
+	pslld $1,		x1 ## 1; \
+	psrld $(32 - 1),	x4 ## 1; \
+	por x4 ## 1,		x1 ## 1; \
+	movdqa x0 ## 1,		x4 ## 1; \
+	pslld $3,		x4 ## 1; \
+	pxor x2 ## 1,		x3 ## 1; \
+	pxor x4 ## 1,		x3 ## 1; \
+	movdqa x3 ## 1,		x4 ## 1; \
+	get_key(i, 1, RK1); \
+		movdqa x1 ## 2,		x4 ## 2; \
+		pslld $1,		x1 ## 2; \
+		psrld $(32 - 1),	x4 ## 2; \
+		por x4 ## 2,		x1 ## 2; \
+		movdqa x0 ## 2,		x4 ## 2; \
+		pslld $3,		x4 ## 2; \
+		pxor x2 ## 2,		x3 ## 2; \
+		pxor x4 ## 2,		x3 ## 2; \
+		movdqa x3 ## 2,		x4 ## 2; \
+		get_key(i, 3, RK3); \
+	pslld $7,		x3 ## 1; \
+	psrld $(32 - 7),	x4 ## 1; \
+	por x4 ## 1,		x3 ## 1; \
+	movdqa x1 ## 1,		x4 ## 1; \
+	pslld $7,		x4 ## 1; \
+	pxor x1 ## 1,		x0 ## 1; \
+	pxor x3 ## 1,		x0 ## 1; \
+	pxor x3 ## 1,		x2 ## 1; \
+	pxor x4 ## 1,		x2 ## 1; \
+	get_key(i, 0, RK0); \
+		pslld $7,		x3 ## 2; \
+		psrld $(32 - 7),	x4 ## 2; \
+		por x4 ## 2,		x3 ## 2; \
+		movdqa x1 ## 2,		x4 ## 2; \
+		pslld $7,		x4 ## 2; \
+		pxor x1 ## 2,		x0 ## 2; \
+		pxor x3 ## 2,		x0 ## 2; \
+		pxor x3 ## 2,		x2 ## 2; \
+		pxor x4 ## 2,		x2 ## 2; \
+		get_key(i, 2, RK2); \
+	pxor RK1,		x1 ## 1; \
+	pxor RK3,		x3 ## 1; \
+	movdqa x0 ## 1,		x4 ## 1; \
+	pslld $5,		x0 ## 1; \
+	psrld $(32 - 5),	x4 ## 1; \
+	por x4 ## 1,		x0 ## 1; \
+	movdqa x2 ## 1,		x4 ## 1; \
+	pslld $22,		x2 ## 1; \
+	psrld $(32 - 22),	x4 ## 1; \
+	por x4 ## 1,		x2 ## 1; \
+	pxor RK0,		x0 ## 1; \
+	pxor RK2,		x2 ## 1; \
+		pxor RK1,		x1 ## 2; \
+		pxor RK3,		x3 ## 2; \
+		movdqa x0 ## 2,		x4 ## 2; \
+		pslld $5,		x0 ## 2; \
+		psrld $(32 - 5),	x4 ## 2; \
+		por x4 ## 2,		x0 ## 2; \
+		movdqa x2 ## 2,		x4 ## 2; \
+		pslld $22,		x2 ## 2; \
+		psrld $(32 - 22),	x4 ## 2; \
+		por x4 ## 2,		x2 ## 2; \
+		pxor RK0,		x0 ## 2; \
+		pxor RK2,		x2 ## 2;
+
+#define KL2(x0, x1, x2, x3, x4, i) \
+	pxor RK0,		x0 ## 1; \
+	pxor RK2,		x2 ## 1; \
+	movdqa x0 ## 1,		x4 ## 1; \
+	psrld $5,		x0 ## 1; \
+	pslld $(32 - 5),	x4 ## 1; \
+	por x4 ## 1,		x0 ## 1; \
+	pxor RK3,		x3 ## 1; \
+	pxor RK1,		x1 ## 1; \
+	movdqa x2 ## 1,		x4 ## 1; \
+	psrld $22,		x2 ## 1; \
+	pslld $(32 - 22),	x4 ## 1; \
+	por x4 ## 1,		x2 ## 1; \
+	pxor x3 ## 1,		x2 ## 1; \
+		pxor RK0,		x0 ## 2; \
+		pxor RK2,		x2 ## 2; \
+		movdqa x0 ## 2,		x4 ## 2; \
+		psrld $5,		x0 ## 2; \
+		pslld $(32 - 5),	x4 ## 2; \
+		por x4 ## 2,		x0 ## 2; \
+		pxor RK3,		x3 ## 2; \
+		pxor RK1,		x1 ## 2; \
+		movdqa x2 ## 2,		x4 ## 2; \
+		psrld $22,		x2 ## 2; \
+		pslld $(32 - 22),	x4 ## 2; \
+		por x4 ## 2,		x2 ## 2; \
+		pxor x3 ## 2,		x2 ## 2; \
+	pxor x3 ## 1,		x0 ## 1; \
+	movdqa x1 ## 1,		x4 ## 1; \
+	pslld $7,		x4 ## 1; \
+	pxor x1 ## 1,		x0 ## 1; \
+	pxor x4 ## 1,		x2 ## 1; \
+	movdqa x1 ## 1,		x4 ## 1; \
+	psrld $1,		x1 ## 1; \
+	pslld $(32 - 1),	x4 ## 1; \
+	por x4 ## 1,		x1 ## 1; \
+		pxor x3 ## 2,		x0 ## 2; \
+		movdqa x1 ## 2,		x4 ## 2; \
+		pslld $7,		x4 ## 2; \
+		pxor x1 ## 2,		x0 ## 2; \
+		pxor x4 ## 2,		x2 ## 2; \
+		movdqa x1 ## 2,		x4 ## 2; \
+		psrld $1,		x1 ## 2; \
+		pslld $(32 - 1),	x4 ## 2; \
+		por x4 ## 2,		x1 ## 2; \
+	movdqa x3 ## 1,		x4 ## 1; \
+	psrld $7,		x3 ## 1; \
+	pslld $(32 - 7),	x4 ## 1; \
+	por x4 ## 1,		x3 ## 1; \
+	pxor x0 ## 1,		x1 ## 1; \
+	movdqa x0 ## 1,		x4 ## 1; \
+	pslld $3,		x4 ## 1; \
+	pxor x4 ## 1,		x3 ## 1; \
+	movdqa x0 ## 1,		x4 ## 1; \
+		movdqa x3 ## 2,		x4 ## 2; \
+		psrld $7,		x3 ## 2; \
+		pslld $(32 - 7),	x4 ## 2; \
+		por x4 ## 2,		x3 ## 2; \
+		pxor x0 ## 2,		x1 ## 2; \
+		movdqa x0 ## 2,		x4 ## 2; \
+		pslld $3,		x4 ## 2; \
+		pxor x4 ## 2,		x3 ## 2; \
+		movdqa x0 ## 2,		x4 ## 2; \
+	psrld $13,		x0 ## 1; \
+	pslld $(32 - 13),	x4 ## 1; \
+	por x4 ## 1,		x0 ## 1; \
+	pxor x2 ## 1,		x1 ## 1; \
+	pxor x2 ## 1,		x3 ## 1; \
+	movdqa x2 ## 1,		x4 ## 1; \
+	psrld $3,		x2 ## 1; \
+	pslld $(32 - 3),	x4 ## 1; \
+	por x4 ## 1,		x2 ## 1; \
+		psrld $13,		x0 ## 2; \
+		pslld $(32 - 13),	x4 ## 2; \
+		por x4 ## 2,		x0 ## 2; \
+		pxor x2 ## 2,		x1 ## 2; \
+		pxor x2 ## 2,		x3 ## 2; \
+		movdqa x2 ## 2,		x4 ## 2; \
+		psrld $3,		x2 ## 2; \
+		pslld $(32 - 3),	x4 ## 2; \
+		por x4 ## 2,		x2 ## 2;
+
+#define S(SBOX, x0, x1, x2, x3, x4) \
+	SBOX ## _1(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+	SBOX ## _2(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+	SBOX ## _1(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+	SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2);
+
+#define SP(SBOX, x0, x1, x2, x3, x4, i) \
+	get_key(i, 0, RK0); \
+	SBOX ## _1(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+	get_key(i, 2, RK2); \
+	SBOX ## _1(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+	get_key(i, 3, RK3); \
+	SBOX ## _2(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+	get_key(i, 1, RK1); \
+	SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+
+#define transpose_4x4(x0, x1, x2, x3, t1, t2, t3) \
+	movdqa x2,		t3; \
+	movdqa x0,		t1; \
+	unpcklps x3,		t3; \
+	movdqa x0,		t2; \
+	unpcklps x1,		t1; \
+	unpckhps x1,		t2; \
+	movdqa t3,		x1; \
+	unpckhps x3,		x2; \
+	movdqa t1,		x0; \
+	movhlps t1,		x1; \
+	movdqa t2,		t1; \
+	movlhps t3,		x0; \
+	movlhps x2,		t1; \
+	movhlps t2,		x2; \
+	movdqa x2,		x3; \
+	movdqa t1,		x2;
+
+#define read_blocks(in, x0, x1, x2, x3, t0, t1, t2) \
+	movdqu (0*4*4)(in),	x0; \
+	movdqu (1*4*4)(in),	x1; \
+	movdqu (2*4*4)(in),	x2; \
+	movdqu (3*4*4)(in),	x3; \
+	\
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
+
+#define write_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	movdqu x0,		(0*4*4)(out); \
+	movdqu x1,		(1*4*4)(out); \
+	movdqu x2,		(2*4*4)(out); \
+	movdqu x3,		(3*4*4)(out);
+
+#define xor_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	movdqu (0*4*4)(out),	t0; \
+	pxor t0,		x0; \
+	movdqu x0,		(0*4*4)(out); \
+	movdqu (1*4*4)(out),	t0; \
+	pxor t0,		x1; \
+	movdqu x1,		(1*4*4)(out); \
+	movdqu (2*4*4)(out),	t0; \
+	pxor t0,		x2; \
+	movdqu x2,		(2*4*4)(out); \
+	movdqu (3*4*4)(out),	t0; \
+	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:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: bool, if true: xor output
+	 */
+
+	pcmpeqd RNOT, RNOT;
+
+	leaq (4*4*4)(%rdx), %rax;
+	read_blocks(%rdx, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+	read_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+						 K2(RA, RB, RC, RD, RE, 0);
+	S(S0, RA, RB, RC, RD, RE);		LK2(RC, RB, RD, RA, RE, 1);
+	S(S1, RC, RB, RD, RA, RE);		LK2(RE, RD, RA, RC, RB, 2);
+	S(S2, RE, RD, RA, RC, RB);		LK2(RB, RD, RE, RC, RA, 3);
+	S(S3, RB, RD, RE, RC, RA);		LK2(RC, RA, RD, RB, RE, 4);
+	S(S4, RC, RA, RD, RB, RE);		LK2(RA, RD, RB, RE, RC, 5);
+	S(S5, RA, RD, RB, RE, RC);		LK2(RC, RA, RD, RE, RB, 6);
+	S(S6, RC, RA, RD, RE, RB);		LK2(RD, RB, RA, RE, RC, 7);
+	S(S7, RD, RB, RA, RE, RC);		LK2(RC, RA, RE, RD, RB, 8);
+	S(S0, RC, RA, RE, RD, RB);		LK2(RE, RA, RD, RC, RB, 9);
+	S(S1, RE, RA, RD, RC, RB);		LK2(RB, RD, RC, RE, RA, 10);
+	S(S2, RB, RD, RC, RE, RA);		LK2(RA, RD, RB, RE, RC, 11);
+	S(S3, RA, RD, RB, RE, RC);		LK2(RE, RC, RD, RA, RB, 12);
+	S(S4, RE, RC, RD, RA, RB);		LK2(RC, RD, RA, RB, RE, 13);
+	S(S5, RC, RD, RA, RB, RE);		LK2(RE, RC, RD, RB, RA, 14);
+	S(S6, RE, RC, RD, RB, RA);		LK2(RD, RA, RC, RB, RE, 15);
+	S(S7, RD, RA, RC, RB, RE);		LK2(RE, RC, RB, RD, RA, 16);
+	S(S0, RE, RC, RB, RD, RA);		LK2(RB, RC, RD, RE, RA, 17);
+	S(S1, RB, RC, RD, RE, RA);		LK2(RA, RD, RE, RB, RC, 18);
+	S(S2, RA, RD, RE, RB, RC);		LK2(RC, RD, RA, RB, RE, 19);
+	S(S3, RC, RD, RA, RB, RE);		LK2(RB, RE, RD, RC, RA, 20);
+	S(S4, RB, RE, RD, RC, RA);		LK2(RE, RD, RC, RA, RB, 21);
+	S(S5, RE, RD, RC, RA, RB);		LK2(RB, RE, RD, RA, RC, 22);
+	S(S6, RB, RE, RD, RA, RC);		LK2(RD, RC, RE, RA, RB, 23);
+	S(S7, RD, RC, RE, RA, RB);		LK2(RB, RE, RA, RD, RC, 24);
+	S(S0, RB, RE, RA, RD, RC);		LK2(RA, RE, RD, RB, RC, 25);
+	S(S1, RA, RE, RD, RB, RC);		LK2(RC, RD, RB, RA, RE, 26);
+	S(S2, RC, RD, RB, RA, RE);		LK2(RE, RD, RC, RA, RB, 27);
+	S(S3, RE, RD, RC, RA, RB);		LK2(RA, RB, RD, RE, RC, 28);
+	S(S4, RA, RB, RD, RE, RC);		LK2(RB, RD, RE, RC, RA, 29);
+	S(S5, RB, RD, RE, RC, RA);		LK2(RA, RB, RD, RC, RE, 30);
+	S(S6, RA, RB, RD, RC, RE);		LK2(RD, RE, RB, RC, RA, 31);
+	S(S7, RD, RE, RB, RC, RA);		 K2(RA, RB, RC, RD, RE, 32);
+
+	leaq (4*4*4)(%rsi), %rax;
+
+	testb %cl, %cl;
+	jnz __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:
+	xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+	xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+	ret;
+
+.align 8
+.global serpent_dec_blk_8way
+.type   serpent_dec_blk_8way,@function;
+
+serpent_dec_blk_8way:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	pcmpeqd RNOT, RNOT;
+
+	leaq (4*4*4)(%rdx), %rax;
+	read_blocks(%rdx, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+	read_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+						 K2(RA, RB, RC, RD, RE, 32);
+	SP(SI7, RA, RB, RC, RD, RE, 31);	KL2(RB, RD, RA, RE, RC, 31);
+	SP(SI6, RB, RD, RA, RE, RC, 30);	KL2(RA, RC, RE, RB, RD, 30);
+	SP(SI5, RA, RC, RE, RB, RD, 29);	KL2(RC, RD, RA, RE, RB, 29);
+	SP(SI4, RC, RD, RA, RE, RB, 28);	KL2(RC, RA, RB, RE, RD, 28);
+	SP(SI3, RC, RA, RB, RE, RD, 27);	KL2(RB, RC, RD, RE, RA, 27);
+	SP(SI2, RB, RC, RD, RE, RA, 26);	KL2(RC, RA, RE, RD, RB, 26);
+	SP(SI1, RC, RA, RE, RD, RB, 25);	KL2(RB, RA, RE, RD, RC, 25);
+	SP(SI0, RB, RA, RE, RD, RC, 24);	KL2(RE, RC, RA, RB, RD, 24);
+	SP(SI7, RE, RC, RA, RB, RD, 23);	KL2(RC, RB, RE, RD, RA, 23);
+	SP(SI6, RC, RB, RE, RD, RA, 22);	KL2(RE, RA, RD, RC, RB, 22);
+	SP(SI5, RE, RA, RD, RC, RB, 21);	KL2(RA, RB, RE, RD, RC, 21);
+	SP(SI4, RA, RB, RE, RD, RC, 20);	KL2(RA, RE, RC, RD, RB, 20);
+	SP(SI3, RA, RE, RC, RD, RB, 19);	KL2(RC, RA, RB, RD, RE, 19);
+	SP(SI2, RC, RA, RB, RD, RE, 18);	KL2(RA, RE, RD, RB, RC, 18);
+	SP(SI1, RA, RE, RD, RB, RC, 17);	KL2(RC, RE, RD, RB, RA, 17);
+	SP(SI0, RC, RE, RD, RB, RA, 16);	KL2(RD, RA, RE, RC, RB, 16);
+	SP(SI7, RD, RA, RE, RC, RB, 15);	KL2(RA, RC, RD, RB, RE, 15);
+	SP(SI6, RA, RC, RD, RB, RE, 14);	KL2(RD, RE, RB, RA, RC, 14);
+	SP(SI5, RD, RE, RB, RA, RC, 13);	KL2(RE, RC, RD, RB, RA, 13);
+	SP(SI4, RE, RC, RD, RB, RA, 12);	KL2(RE, RD, RA, RB, RC, 12);
+	SP(SI3, RE, RD, RA, RB, RC, 11);	KL2(RA, RE, RC, RB, RD, 11);
+	SP(SI2, RA, RE, RC, RB, RD, 10);	KL2(RE, RD, RB, RC, RA, 10);
+	SP(SI1, RE, RD, RB, RC, RA, 9);		KL2(RA, RD, RB, RC, RE, 9);
+	SP(SI0, RA, RD, RB, RC, RE, 8);		KL2(RB, RE, RD, RA, RC, 8);
+	SP(SI7, RB, RE, RD, RA, RC, 7);		KL2(RE, RA, RB, RC, RD, 7);
+	SP(SI6, RE, RA, RB, RC, RD, 6);		KL2(RB, RD, RC, RE, RA, 6);
+	SP(SI5, RB, RD, RC, RE, RA, 5);		KL2(RD, RA, RB, RC, RE, 5);
+	SP(SI4, RD, RA, RB, RC, RE, 4);		KL2(RD, RB, RE, RC, RA, 4);
+	SP(SI3, RD, RB, RE, RC, RA, 3);		KL2(RE, RD, RA, RC, RB, 3);
+	SP(SI2, RE, RD, RA, RC, RB, 2);		KL2(RD, RB, RC, RA, RE, 2);
+	SP(SI1, RD, RB, RC, RA, RE, 1);		KL2(RE, RB, RC, RA, RD, 1);
+	S(SI0, RE, RB, RC, RA, RD);		 K2(RC, RD, RB, RE, RA, 0);
+
+	leaq (4*4*4)(%rsi), %rax;
+	write_blocks(%rsi, RC1, RD1, RB1, RE1, RK0, RK1, RK2);
+	write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
+
+	ret;

arch/x86/crypto/twofish_glue_3way.c

@@ -32,6 +32,8 @@
 #include <crypto/algapi.h>
 #include <crypto/twofish.h>
 #include <crypto/b128ops.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
 
 /* regular block cipher functions from twofish_x86_64 module */
 asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst,
@@ -432,6 +434,209 @@ static struct crypto_alg blk_ctr_alg = {
 	},
 };
 
+static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = TF_BLOCK_SIZE;
+	struct twofish_ctx *ctx = priv;
+	int i;
+
+	if (nbytes == 3 * bsize) {
+		twofish_enc_blk_3way(ctx, srcdst, srcdst);
+		return;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		twofish_enc_blk(ctx, srcdst, srcdst);
+}
+
+static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = TF_BLOCK_SIZE;
+	struct twofish_ctx *ctx = priv;
+	int i;
+
+	if (nbytes == 3 * bsize) {
+		twofish_dec_blk_3way(ctx, srcdst, srcdst);
+		return;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		twofish_dec_blk(ctx, srcdst, srcdst);
+}
+
+struct twofish_lrw_ctx {
+	struct lrw_table_ctx lrw_table;
+	struct twofish_ctx twofish_ctx;
+};
+
+static int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct twofish_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+	int err;
+
+	err = __twofish_setkey(&ctx->twofish_ctx, key, keylen - TF_BLOCK_SIZE,
+			       &tfm->crt_flags);
+	if (err)
+		return err;
+
+	return lrw_init_table(&ctx->lrw_table, key + keylen - TF_BLOCK_SIZE);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[3];
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &ctx->twofish_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+
+	return lrw_crypt(desc, dst, src, nbytes, &req);
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[3];
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &ctx->twofish_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+
+	return lrw_crypt(desc, dst, src, nbytes, &req);
+}
+
+static void lrw_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct twofish_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	lrw_free_table(&ctx->lrw_table);
+}
+
+static struct crypto_alg blk_lrw_alg = {
+	.cra_name		= "lrw(twofish)",
+	.cra_driver_name	= "lrw-twofish-3way",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct twofish_lrw_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(blk_lrw_alg.cra_list),
+	.cra_exit		= lrw_exit_tfm,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE + TF_BLOCK_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE + TF_BLOCK_SIZE,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= lrw_twofish_setkey,
+			.encrypt	= lrw_encrypt,
+			.decrypt	= lrw_decrypt,
+		},
+	},
+};
+
+struct twofish_xts_ctx {
+	struct twofish_ctx tweak_ctx;
+	struct twofish_ctx crypt_ctx;
+};
+
+static int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct twofish_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 *flags = &tfm->crt_flags;
+	int err;
+
+	/* key consists of keys of equal size concatenated, therefore
+	 * the length must be even
+	 */
+	if (keylen % 2) {
+		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+
+	/* first half of xts-key is for crypt */
+	err = __twofish_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
+	if (err)
+		return err;
+
+	/* second half of xts-key is for tweak */
+	return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2,
+				flags);
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[3];
+	struct xts_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.tweak_ctx = &ctx->tweak_ctx,
+		.tweak_fn = XTS_TWEAK_CAST(twofish_enc_blk),
+		.crypt_ctx = &ctx->crypt_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+
+	return xts_crypt(desc, dst, src, nbytes, &req);
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[3];
+	struct xts_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.tweak_ctx = &ctx->tweak_ctx,
+		.tweak_fn = XTS_TWEAK_CAST(twofish_enc_blk),
+		.crypt_ctx = &ctx->crypt_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+
+	return xts_crypt(desc, dst, src, nbytes, &req);
+}
+
+static struct crypto_alg blk_xts_alg = {
+	.cra_name		= "xts(twofish)",
+	.cra_driver_name	= "xts-twofish-3way",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct twofish_xts_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(blk_xts_alg.cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE * 2,
+			.max_keysize	= TF_MAX_KEY_SIZE * 2,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= xts_twofish_setkey,
+			.encrypt	= xts_encrypt,
+			.decrypt	= xts_decrypt,
+		},
+	},
+};
+
 int __init init(void)
 {
 	int err;
@@ -445,9 +650,20 @@ int __init init(void)
 	err = crypto_register_alg(&blk_ctr_alg);
 	if (err)
 		goto ctr_err;
+	err = crypto_register_alg(&blk_lrw_alg);
+	if (err)
+		goto blk_lrw_err;
+	err = crypto_register_alg(&blk_xts_alg);
+	if (err)
+		goto blk_xts_err;
 
 	return 0;
 
+	crypto_unregister_alg(&blk_xts_alg);
+blk_xts_err:
+	crypto_unregister_alg(&blk_lrw_alg);
+blk_lrw_err:
+	crypto_unregister_alg(&blk_ctr_alg);
 ctr_err:
 	crypto_unregister_alg(&blk_cbc_alg);
 cbc_err:
@@ -458,6 +674,8 @@ int __init init(void)
 
 void __exit fini(void)
 {
+	crypto_unregister_alg(&blk_xts_alg);
+	crypto_unregister_alg(&blk_lrw_alg);
 	crypto_unregister_alg(&blk_ctr_alg);
 	crypto_unregister_alg(&blk_cbc_alg);
 	crypto_unregister_alg(&blk_ecb_alg);

arch/x86/include/asm/serpent.h

+#ifndef ASM_X86_SERPENT_H
+#define ASM_X86_SERPENT_H
+
+#include <linux/crypto.h>
+#include <crypto/serpent.h>
+
+#ifdef CONFIG_X86_32
+
+#define SERPENT_PARALLEL_BLOCKS 4
+
+asmlinkage void __serpent_enc_blk_4way(struct serpent_ctx *ctx, u8 *dst,
+				       const u8 *src, bool xor);
+asmlinkage void serpent_dec_blk_4way(struct serpent_ctx *ctx, u8 *dst,
+				     const u8 *src);
+
+static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+					const u8 *src)
+{
+	__serpent_enc_blk_4way(ctx, dst, src, false);
+}
+
+static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
+					    const u8 *src)
+{
+	__serpent_enc_blk_4way(ctx, dst, src, true);
+}
+
+static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+					const u8 *src)
+{
+	serpent_dec_blk_4way(ctx, dst, src);
+}
+
+#else
+
+#define SERPENT_PARALLEL_BLOCKS 8
+
+asmlinkage void __serpent_enc_blk_8way(struct serpent_ctx *ctx, u8 *dst,
+				       const u8 *src, bool xor);
+asmlinkage void serpent_dec_blk_8way(struct serpent_ctx *ctx, u8 *dst,
+				     const u8 *src);
+
+static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+				   const u8 *src)
+{
+	__serpent_enc_blk_8way(ctx, dst, src, false);
+}
+
+static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
+				       const u8 *src)
+{
+	__serpent_enc_blk_8way(ctx, dst, src, true);
+}
+
+static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+				   const u8 *src)
+{
+	serpent_dec_blk_8way(ctx, dst, src);
+}
+
+#endif
+
+#endif

crypto/Kconfig

@@ -105,7 +105,7 @@ config CRYPTO_USER
 	depends on NET
 	select CRYPTO_MANAGER
 	help
-	  Userapace configuration for cryptographic instantiations such as
+	  Userspace configuration for cryptographic instantiations such as
 	  cbc(aes).
 
 config CRYPTO_MANAGER_DISABLE_TESTS
@@ -117,7 +117,7 @@ config CRYPTO_MANAGER_DISABLE_TESTS
 	  algorithm registration.
 
 config CRYPTO_GF128MUL
-	tristate "GF(2^128) multiplication functions (EXPERIMENTAL)"
+	tristate "GF(2^128) multiplication functions"
 	help
 	  Efficient table driven implementation of multiplications in the
 	  field GF(2^128).  This is needed by some cypher modes. This
@@ -241,8 +241,7 @@ config CRYPTO_ECB
 	  the input block by block.
 
 config CRYPTO_LRW
-	tristate "LRW support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	tristate "LRW support"
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_GF128MUL
@@ -262,8 +261,7 @@ config CRYPTO_PCBC
 	  This block cipher algorithm is required for RxRPC.
 
 config CRYPTO_XTS
-	tristate "XTS support (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	tristate "XTS support"
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_MANAGER
 	select CRYPTO_GF128MUL
@@ -764,6 +762,46 @@ config CRYPTO_SERPENT
 	  See also:
 	  <http://www.cl.cam.ac.uk/~rja14/serpent.html>
 
+config CRYPTO_SERPENT_SSE2_X86_64
+	tristate "Serpent cipher algorithm (x86_64/SSE2)"
+	depends on X86 && 64BIT
+	select CRYPTO_ALGAPI
+	select CRYPTO_CRYPTD
+	select CRYPTO_SERPENT
+	select CRYPTO_LRW
+	select CRYPTO_XTS
+	help
+	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
+
+	  Keys are allowed to be from 0 to 256 bits in length, in steps
+	  of 8 bits.
+
+	  This module provides Serpent cipher algorithm that processes eigth
+	  blocks parallel using SSE2 instruction set.
+
+	  See also:
+	  <http://www.cl.cam.ac.uk/~rja14/serpent.html>
+
+config CRYPTO_SERPENT_SSE2_586
+	tristate "Serpent cipher algorithm (i586/SSE2)"
+	depends on X86 && !64BIT
+	select CRYPTO_ALGAPI
+	select CRYPTO_CRYPTD
+	select CRYPTO_SERPENT
+	select CRYPTO_LRW
+	select CRYPTO_XTS
+	help
+	  Serpent cipher algorithm, by Anderson, Biham & Knudsen.
+
+	  Keys are allowed to be from 0 to 256 bits in length, in steps
+	  of 8 bits.
+
+	  This module provides Serpent cipher algorithm that processes four
+	  blocks parallel using SSE2 instruction set.
+
+	  See also:
+	  <http://www.cl.cam.ac.uk/~rja14/serpent.html>
+
 config CRYPTO_TEA
 	tristate "TEA, XTEA and XETA cipher algorithms"
 	select CRYPTO_ALGAPI
@@ -840,6 +878,8 @@ config CRYPTO_TWOFISH_X86_64_3WAY
 	select CRYPTO_ALGAPI
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
+	select CRYPTO_LRW
+	select CRYPTO_XTS
 	help
 	  Twofish cipher algorithm (x86_64, 3-way parallel).
 

crypto/Makefile

@@ -65,7 +65,7 @@ obj-$(CONFIG_CRYPTO_BLOWFISH) += blowfish_generic.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_COMMON) += blowfish_common.o
 obj-$(CONFIG_CRYPTO_TWOFISH) += twofish_generic.o
 obj-$(CONFIG_CRYPTO_TWOFISH_COMMON) += twofish_common.o
-obj-$(CONFIG_CRYPTO_SERPENT) += serpent.o
+obj-$(CONFIG_CRYPTO_SERPENT) += serpent_generic.o
 obj-$(CONFIG_CRYPTO_AES) += aes_generic.o
 obj-$(CONFIG_CRYPTO_CAMELLIA) += camellia.o
 obj-$(CONFIG_CRYPTO_CAST5) += cast5.o

crypto/algapi.c

@@ -518,6 +518,35 @@ int crypto_register_instance(struct crypto_template *tmpl,
 }
 EXPORT_SYMBOL_GPL(crypto_register_instance);
 
+int crypto_unregister_instance(struct crypto_alg *alg)
+{
+	int err;
+	struct crypto_instance *inst = (void *)alg;
+	struct crypto_template *tmpl = inst->tmpl;
+	LIST_HEAD(users);
+
+	if (!(alg->cra_flags & CRYPTO_ALG_INSTANCE))
+		return -EINVAL;
+
+	BUG_ON(atomic_read(&alg->cra_refcnt) != 1);
+
+	down_write(&crypto_alg_sem);
+
+	hlist_del_init(&inst->list);
+	err = crypto_remove_alg(alg, &users);
+
+	up_write(&crypto_alg_sem);
+
+	if (err)
+		return err;
+
+	tmpl->free(inst);
+	crypto_remove_final(&users);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(crypto_unregister_instance);
+
 int crypto_init_spawn(struct crypto_spawn *spawn, struct crypto_alg *alg,
 		      struct crypto_instance *inst, u32 mask)
 {

crypto/ansi_cprng.c

@@ -414,10 +414,18 @@ static int fips_cprng_get_random(struct crypto_rng *tfm, u8 *rdata,
 static int fips_cprng_reset(struct crypto_rng *tfm, u8 *seed, unsigned int slen)
 {
 	u8 rdata[DEFAULT_BLK_SZ];
+	u8 *key = seed + DEFAULT_BLK_SZ;
 	int rc;
 
 	struct prng_context *prng = crypto_rng_ctx(tfm);
 
+	if (slen < DEFAULT_PRNG_KSZ + DEFAULT_BLK_SZ)
+		return -EINVAL;
+
+	/* fips strictly requires seed != key */
+	if (!memcmp(seed, key, DEFAULT_PRNG_KSZ))
+		return -EINVAL;
+
 	rc = cprng_reset(tfm, seed, slen);
 
 	if (!rc)

crypto/crypto_user.c

@@ -298,7 +298,7 @@ static int crypto_del_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (atomic_read(&alg->cra_refcnt) != 1)
 		return -EBUSY;
 
-	return crypto_unregister_alg(alg);
+	return crypto_unregister_instance(alg);
 }
 
 static int crypto_add_alg(struct sk_buff *skb, struct nlmsghdr *nlh,

crypto/lrw.c

@@ -3,7 +3,7 @@
  *
  * Copyright (c) 2006 Rik Snel <rsnel@cube.dyndns.org>
  *
- * Based om ecb.c
+ * Based on ecb.c
  * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
  *
  * This program is free software; you can redistribute it and/or modify it
@@ -16,6 +16,7 @@
  * http://www.mail-archive.com/stds-p1619@listserv.ieee.org/msg00173.html
  *
  * The test vectors are included in the testing module tcrypt.[ch] */
+
 #include <crypto/algapi.h>
 #include <linux/err.h>
 #include <linux/init.h>
@@ -26,21 +27,11 @@
 
 #include <crypto/b128ops.h>
 #include <crypto/gf128mul.h>
+#include <crypto/lrw.h>
 
 struct priv {
 	struct crypto_cipher *child;
-	/* optimizes multiplying a random (non incrementing, as at the
-	 * start of a new sector) value with key2, we could also have
-	 * used 4k optimization tables or no optimization at all. In the
-	 * latter case we would have to store key2 here */
-	struct gf128mul_64k *table;
-	/* stores:
-	 *  key2*{ 0,0,...0,0,0,0,1 }, key2*{ 0,0,...0,0,0,1,1 },
-	 *  key2*{ 0,0,...0,0,1,1,1 }, key2*{ 0,0,...0,1,1,1,1 }
-	 *  key2*{ 0,0,...1,1,1,1,1 }, etc
-	 * needed for optimized multiplication of incrementing values
-	 * with key2 */
-	be128 mulinc[128];
+	struct lrw_table_ctx table;
 };
 
 static inline void setbit128_bbe(void *b, int bit)
@@ -54,28 +45,16 @@ static inline void setbit128_bbe(void *b, int bit)
 			), b);
 }
 
-static int setkey(struct crypto_tfm *parent, const u8 *key,
-		  unsigned int keylen)
+int lrw_init_table(struct lrw_table_ctx *ctx, const u8 *tweak)
 {
-	struct priv *ctx = crypto_tfm_ctx(parent);
-	struct crypto_cipher *child = ctx->child;
-	int err, i;
 	be128 tmp = { 0 };
-	int bsize = crypto_cipher_blocksize(child);
-
-	crypto_cipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_cipher_set_flags(child, crypto_tfm_get_flags(parent) &
-				       CRYPTO_TFM_REQ_MASK);
-	if ((err = crypto_cipher_setkey(child, key, keylen - bsize)))
-		return err;
-	crypto_tfm_set_flags(parent, crypto_cipher_get_flags(child) &
-				     CRYPTO_TFM_RES_MASK);
+	int i;
 
 	if (ctx->table)
 		gf128mul_free_64k(ctx->table);
 
 	/* initialize multiplication table for Key2 */
-	ctx->table = gf128mul_init_64k_bbe((be128 *)(key + keylen - bsize));
+	ctx->table = gf128mul_init_64k_bbe((be128 *)tweak);
 	if (!ctx->table)
 		return -ENOMEM;
 
@@ -88,6 +67,34 @@ static int setkey(struct crypto_tfm *parent, const u8 *key,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(lrw_init_table);
+
+void lrw_free_table(struct lrw_table_ctx *ctx)
+{
+	if (ctx->table)
+		gf128mul_free_64k(ctx->table);
+}
+EXPORT_SYMBOL_GPL(lrw_free_table);
+
+static int setkey(struct crypto_tfm *parent, const u8 *key,
+		  unsigned int keylen)
+{
+	struct priv *ctx = crypto_tfm_ctx(parent);
+	struct crypto_cipher *child = ctx->child;
+	int err, bsize = LRW_BLOCK_SIZE;
+	const u8 *tweak = key + keylen - bsize;
+
+	crypto_cipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_cipher_set_flags(child, crypto_tfm_get_flags(parent) &
+				       CRYPTO_TFM_REQ_MASK);
+	err = crypto_cipher_setkey(child, key, keylen - bsize);
+	if (err)
+		return err;
+	crypto_tfm_set_flags(parent, crypto_cipher_get_flags(child) &
+				     CRYPTO_TFM_RES_MASK);
+
+	return lrw_init_table(&ctx->table, tweak);
+}
 
 struct sinfo {
 	be128 t;
@@ -134,7 +141,7 @@ static int crypt(struct blkcipher_desc *d,
 {
 	int err;
 	unsigned int avail;
-	const int bs = crypto_cipher_blocksize(ctx->child);
+	const int bs = LRW_BLOCK_SIZE;
 	struct sinfo s = {
 		.tfm = crypto_cipher_tfm(ctx->child),
 		.fn = fn
@@ -155,7 +162,7 @@ static int crypt(struct blkcipher_desc *d,
 	s.t = *iv;
 
 	/* T <- I*Key2 */
-	gf128mul_64k_bbe(&s.t, ctx->table);
+	gf128mul_64k_bbe(&s.t, ctx->table.table);
 
 	goto first;
 
@@ -163,7 +170,8 @@ static int crypt(struct blkcipher_desc *d,
 		do {
 			/* T <- I*Key2, using the optimization
 			 * discussed in the specification */
-			be128_xor(&s.t, &s.t, &ctx->mulinc[get_index128(iv)]);
+			be128_xor(&s.t, &s.t,
+				  &ctx->table.mulinc[get_index128(iv)]);
 			inc(iv);
 
 first:
@@ -206,6 +214,85 @@ static int decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		     crypto_cipher_alg(ctx->child)->cia_decrypt);
 }
 
+int lrw_crypt(struct blkcipher_desc *desc, struct scatterlist *sdst,
+	      struct scatterlist *ssrc, unsigned int nbytes,
+	      struct lrw_crypt_req *req)
+{
+	const unsigned int bsize = LRW_BLOCK_SIZE;
+	const unsigned int max_blks = req->tbuflen / bsize;
+	struct lrw_table_ctx *ctx = req->table_ctx;
+	struct blkcipher_walk walk;
+	unsigned int nblocks;
+	be128 *iv, *src, *dst, *t;
+	be128 *t_buf = req->tbuf;
+	int err, i;
+
+	BUG_ON(max_blks < 1);
+
+	blkcipher_walk_init(&walk, sdst, ssrc, nbytes);
+
+	err = blkcipher_walk_virt(desc, &walk);
+	nbytes = walk.nbytes;
+	if (!nbytes)
+		return err;
+
+	nblocks = min(walk.nbytes / bsize, max_blks);
+	src = (be128 *)walk.src.virt.addr;
+	dst = (be128 *)walk.dst.virt.addr;
+
+	/* calculate first value of T */
+	iv = (be128 *)walk.iv;
+	t_buf[0] = *iv;
+
+	/* T <- I*Key2 */
+	gf128mul_64k_bbe(&t_buf[0], ctx->table);
+
+	i = 0;
+	goto first;
+
+	for (;;) {
+		do {
+			for (i = 0; i < nblocks; i++) {
+				/* T <- I*Key2, using the optimization
+				 * discussed in the specification */
+				be128_xor(&t_buf[i], t,
+						&ctx->mulinc[get_index128(iv)]);
+				inc(iv);
+first:
+				t = &t_buf[i];
+
+				/* PP <- T xor P */
+				be128_xor(dst + i, t, src + i);
+			}
+
+			/* CC <- E(Key2,PP) */
+			req->crypt_fn(req->crypt_ctx, (u8 *)dst,
+				      nblocks * bsize);
+
+			/* C <- T xor CC */
+			for (i = 0; i < nblocks; i++)
+				be128_xor(dst + i, dst + i, &t_buf[i]);
+
+			src += nblocks;
+			dst += nblocks;
+			nbytes -= nblocks * bsize;
+			nblocks = min(nbytes / bsize, max_blks);
+		} while (nblocks > 0);
+
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = walk.nbytes;
+		if (!nbytes)
+			break;
+
+		nblocks = min(nbytes / bsize, max_blks);
+		src = (be128 *)walk.src.virt.addr;
+		dst = (be128 *)walk.dst.virt.addr;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(lrw_crypt);
+
 static int init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_cipher *cipher;
@@ -218,8 +305,9 @@ static int init_tfm(struct crypto_tfm *tfm)
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
-	if (crypto_cipher_blocksize(cipher) != 16) {
+	if (crypto_cipher_blocksize(cipher) != LRW_BLOCK_SIZE) {
 		*flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
+		crypto_free_cipher(cipher);
 		return -EINVAL;
 	}
 
@@ -230,8 +318,8 @@ static int init_tfm(struct crypto_tfm *tfm)
 static void exit_tfm(struct crypto_tfm *tfm)
 {
 	struct priv *ctx = crypto_tfm_ctx(tfm);
-	if (ctx->table)
-		gf128mul_free_64k(ctx->table);
+
+	lrw_free_table(&ctx->table);
 	crypto_free_cipher(ctx->child);
 }
 

crypto/tcrypt.c

@@ -719,6 +719,207 @@ static void test_ahash_speed(const char *algo, unsigned int sec,
 	crypto_free_ahash(tfm);
 }
 
+static inline int do_one_acipher_op(struct ablkcipher_request *req, int ret)
+{
+	if (ret == -EINPROGRESS || ret == -EBUSY) {
+		struct tcrypt_result *tr = req->base.data;
+
+		ret = wait_for_completion_interruptible(&tr->completion);
+		if (!ret)
+			ret = tr->err;
+		INIT_COMPLETION(tr->completion);
+	}
+
+	return ret;
+}
+
+static int test_acipher_jiffies(struct ablkcipher_request *req, int enc,
+				int blen, int sec)
+{
+	unsigned long start, end;
+	int bcount;
+	int ret;
+
+	for (start = jiffies, end = start + sec * HZ, bcount = 0;
+	     time_before(jiffies, end); bcount++) {
+		if (enc)
+			ret = do_one_acipher_op(req,
+						crypto_ablkcipher_encrypt(req));
+		else
+			ret = do_one_acipher_op(req,
+						crypto_ablkcipher_decrypt(req));
+
+		if (ret)
+			return ret;
+	}
+
+	pr_cont("%d operations in %d seconds (%ld bytes)\n",
+		bcount, sec, (long)bcount * blen);
+	return 0;
+}
+
+static int test_acipher_cycles(struct ablkcipher_request *req, int enc,
+			       int blen)
+{
+	unsigned long cycles = 0;
+	int ret = 0;
+	int i;
+
+	/* Warm-up run. */
+	for (i = 0; i < 4; i++) {
+		if (enc)
+			ret = do_one_acipher_op(req,
+						crypto_ablkcipher_encrypt(req));
+		else
+			ret = do_one_acipher_op(req,
+						crypto_ablkcipher_decrypt(req));
+
+		if (ret)
+			goto out;
+	}
+
+	/* The real thing. */
+	for (i = 0; i < 8; i++) {
+		cycles_t start, end;
+
+		start = get_cycles();
+		if (enc)
+			ret = do_one_acipher_op(req,
+						crypto_ablkcipher_encrypt(req));
+		else
+			ret = do_one_acipher_op(req,
+						crypto_ablkcipher_decrypt(req));
+		end = get_cycles();
+
+		if (ret)
+			goto out;
+
+		cycles += end - start;
+	}
+
+out:
+	if (ret == 0)
+		pr_cont("1 operation in %lu cycles (%d bytes)\n",
+			(cycles + 4) / 8, blen);
+
+	return ret;
+}
+
+static void test_acipher_speed(const char *algo, int enc, unsigned int sec,
+			       struct cipher_speed_template *template,
+			       unsigned int tcount, u8 *keysize)
+{
+	unsigned int ret, i, j, iv_len;
+	struct tcrypt_result tresult;
+	const char *key;
+	char iv[128];
+	struct ablkcipher_request *req;
+	struct crypto_ablkcipher *tfm;
+	const char *e;
+	u32 *b_size;
+
+	if (enc == ENCRYPT)
+		e = "encryption";
+	else
+		e = "decryption";
+
+	pr_info("\ntesting speed of async %s %s\n", algo, e);
+
+	init_completion(&tresult.completion);
+
+	tfm = crypto_alloc_ablkcipher(algo, 0, 0);
+
+	if (IS_ERR(tfm)) {
+		pr_err("failed to load transform for %s: %ld\n", algo,
+		       PTR_ERR(tfm));
+		return;
+	}
+
+	req = ablkcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		pr_err("tcrypt: skcipher: Failed to allocate request for %s\n",
+		       algo);
+		goto out;
+	}
+
+	ablkcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					tcrypt_complete, &tresult);
+
+	i = 0;
+	do {
+		b_size = block_sizes;
+
+		do {
+			struct scatterlist sg[TVMEMSIZE];
+
+			if ((*keysize + *b_size) > TVMEMSIZE * PAGE_SIZE) {
+				pr_err("template (%u) too big for "
+				       "tvmem (%lu)\n", *keysize + *b_size,
+				       TVMEMSIZE * PAGE_SIZE);
+				goto out_free_req;
+			}
+
+			pr_info("test %u (%d bit key, %d byte blocks): ", i,
+				*keysize * 8, *b_size);
+
+			memset(tvmem[0], 0xff, PAGE_SIZE);
+
+			/* set key, plain text and IV */
+			key = tvmem[0];
+			for (j = 0; j < tcount; j++) {
+				if (template[j].klen == *keysize) {
+					key = template[j].key;
+					break;
+				}
+			}
+
+			crypto_ablkcipher_clear_flags(tfm, ~0);
+
+			ret = crypto_ablkcipher_setkey(tfm, key, *keysize);
+			if (ret) {
+				pr_err("setkey() failed flags=%x\n",
+					crypto_ablkcipher_get_flags(tfm));
+				goto out_free_req;
+			}
+
+			sg_init_table(sg, TVMEMSIZE);
+			sg_set_buf(sg, tvmem[0] + *keysize,
+				   PAGE_SIZE - *keysize);
+			for (j = 1; j < TVMEMSIZE; j++) {
+				sg_set_buf(sg + j, tvmem[j], PAGE_SIZE);
+				memset(tvmem[j], 0xff, PAGE_SIZE);
+			}
+
+			iv_len = crypto_ablkcipher_ivsize(tfm);
+			if (iv_len)
+				memset(&iv, 0xff, iv_len);
+
+			ablkcipher_request_set_crypt(req, sg, sg, *b_size, iv);
+
+			if (sec)
+				ret = test_acipher_jiffies(req, enc,
+							   *b_size, sec);
+			else
+				ret = test_acipher_cycles(req, enc,
+							  *b_size);
+
+			if (ret) {
+				pr_err("%s() failed flags=%x\n", e,
+					crypto_ablkcipher_get_flags(tfm));
+				break;
+			}
+			b_size++;
+			i++;
+		} while (*b_size);
+		keysize++;
+	} while (*keysize);
+
+out_free_req:
+	ablkcipher_request_free(req);
+out:
+	crypto_free_ablkcipher(tfm);
+}
+
 static void test_available(void)
 {
 	char **name = check;
@@ -789,10 +990,16 @@ static int do_test(int m)
 		ret += tcrypt_test("ecb(twofish)");
 		ret += tcrypt_test("cbc(twofish)");
 		ret += tcrypt_test("ctr(twofish)");
+		ret += tcrypt_test("lrw(twofish)");
+		ret += tcrypt_test("xts(twofish)");
 		break;
 
 	case 9:
 		ret += tcrypt_test("ecb(serpent)");
+		ret += tcrypt_test("cbc(serpent)");
+		ret += tcrypt_test("ctr(serpent)");
+		ret += tcrypt_test("lrw(serpent)");
+		ret += tcrypt_test("xts(serpent)");
 		break;
 
 	case 10:
@@ -1045,6 +1252,14 @@ static int do_test(int m)
 				speed_template_16_24_32);
 		test_cipher_speed("ctr(twofish)", DECRYPT, sec, NULL, 0,
 				speed_template_16_24_32);
+		test_cipher_speed("lrw(twofish)", ENCRYPT, sec, NULL, 0,
+				speed_template_32_40_48);
+		test_cipher_speed("lrw(twofish)", DECRYPT, sec, NULL, 0,
+				speed_template_32_40_48);
+		test_cipher_speed("xts(twofish)", ENCRYPT, sec, NULL, 0,
+				speed_template_32_48_64);
+		test_cipher_speed("xts(twofish)", DECRYPT, sec, NULL, 0,
+				speed_template_32_48_64);
 		break;
 
 	case 203:
@@ -1089,6 +1304,29 @@ static int do_test(int m)
 				  speed_template_16_32);
 		break;
 
+	case 207:
+		test_cipher_speed("ecb(serpent)", ENCRYPT, sec, NULL, 0,
+				  speed_template_16_32);
+		test_cipher_speed("ecb(serpent)", DECRYPT, sec, NULL, 0,
+				  speed_template_16_32);
+		test_cipher_speed("cbc(serpent)", ENCRYPT, sec, NULL, 0,
+				  speed_template_16_32);
+		test_cipher_speed("cbc(serpent)", DECRYPT, sec, NULL, 0,
+				  speed_template_16_32);
+		test_cipher_speed("ctr(serpent)", ENCRYPT, sec, NULL, 0,
+				  speed_template_16_32);
+		test_cipher_speed("ctr(serpent)", DECRYPT, sec, NULL, 0,
+				  speed_template_16_32);
+		test_cipher_speed("lrw(serpent)", ENCRYPT, sec, NULL, 0,
+				  speed_template_32_48);
+		test_cipher_speed("lrw(serpent)", DECRYPT, sec, NULL, 0,
+				  speed_template_32_48);
+		test_cipher_speed("xts(serpent)", ENCRYPT, sec, NULL, 0,
+				  speed_template_32_64);
+		test_cipher_speed("xts(serpent)", DECRYPT, sec, NULL, 0,
+				  speed_template_32_64);
+		break;
+
 	case 300:
 		/* fall through */
 
@@ -1241,6 +1479,78 @@ static int do_test(int m)
 	case 499:
 		break;
 
+	case 500:
+		test_acipher_speed("ecb(aes)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("ecb(aes)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("cbc(aes)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("cbc(aes)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("lrw(aes)", ENCRYPT, sec, NULL, 0,
+				   speed_template_32_40_48);
+		test_acipher_speed("lrw(aes)", DECRYPT, sec, NULL, 0,
+				   speed_template_32_40_48);
+		test_acipher_speed("xts(aes)", ENCRYPT, sec, NULL, 0,
+				   speed_template_32_48_64);
+		test_acipher_speed("xts(aes)", DECRYPT, sec, NULL, 0,
+				   speed_template_32_48_64);
+		test_acipher_speed("ctr(aes)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		test_acipher_speed("ctr(aes)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_24_32);
+		break;
+
+	case 501:
+		test_acipher_speed("ecb(des3_ede)", ENCRYPT, sec,
+				   des3_speed_template, DES3_SPEED_VECTORS,
+				   speed_template_24);
+		test_acipher_speed("ecb(des3_ede)", DECRYPT, sec,
+				   des3_speed_template, DES3_SPEED_VECTORS,
+				   speed_template_24);
+		test_acipher_speed("cbc(des3_ede)", ENCRYPT, sec,
+				   des3_speed_template, DES3_SPEED_VECTORS,
+				   speed_template_24);
+		test_acipher_speed("cbc(des3_ede)", DECRYPT, sec,
+				   des3_speed_template, DES3_SPEED_VECTORS,
+				   speed_template_24);
+		break;
+
+	case 502:
+		test_acipher_speed("ecb(des)", ENCRYPT, sec, NULL, 0,
+				   speed_template_8);
+		test_acipher_speed("ecb(des)", DECRYPT, sec, NULL, 0,
+				   speed_template_8);
+		test_acipher_speed("cbc(des)", ENCRYPT, sec, NULL, 0,
+				   speed_template_8);
+		test_acipher_speed("cbc(des)", DECRYPT, sec, NULL, 0,
+				   speed_template_8);
+		break;
+
+	case 503:
+		test_acipher_speed("ecb(serpent)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_32);
+		test_acipher_speed("ecb(serpent)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_32);
+		test_acipher_speed("cbc(serpent)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_32);
+		test_acipher_speed("cbc(serpent)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_32);
+		test_acipher_speed("ctr(serpent)", ENCRYPT, sec, NULL, 0,
+				   speed_template_16_32);
+		test_acipher_speed("ctr(serpent)", DECRYPT, sec, NULL, 0,
+				   speed_template_16_32);
+		test_acipher_speed("lrw(serpent)", ENCRYPT, sec, NULL, 0,
+				   speed_template_32_48);
+		test_acipher_speed("lrw(serpent)", DECRYPT, sec, NULL, 0,
+				   speed_template_32_48);
+		test_acipher_speed("xts(serpent)", ENCRYPT, sec, NULL, 0,
+				   speed_template_32_64);
+		test_acipher_speed("xts(serpent)", DECRYPT, sec, NULL, 0,
+				   speed_template_32_64);
+		break;
+
 	case 1000:
 		test_available();
 		break;

crypto/tcrypt.h

@@ -51,7 +51,9 @@ static u8 speed_template_8_32[] = {8, 32, 0};
 static u8 speed_template_16_32[] = {16, 32, 0};
 static u8 speed_template_16_24_32[] = {16, 24, 32, 0};
 static u8 speed_template_32_40_48[] = {32, 40, 48, 0};
+static u8 speed_template_32_48[] = {32, 48, 0};
 static u8 speed_template_32_48_64[] = {32, 48, 64, 0};
+static u8 speed_template_32_64[] = {32, 64, 0};
 
 /*
  * Digest speed tests

crypto/testmgr.c

@@ -1534,6 +1534,21 @@ static int alg_test_null(const struct alg_test_desc *desc,
 /* Please keep this list sorted by algorithm name. */
 static const struct alg_test_desc alg_test_descs[] = {
 	{
+		.alg = "__cbc-serpent-sse2",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
+	}, {
 		.alg = "__driver-cbc-aes-aesni",
 		.test = alg_test_null,
 		.suite = {
@@ -1548,6 +1563,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "__driver-cbc-serpent-sse2",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
 	}, {
 		.alg = "__driver-ecb-aes-aesni",
 		.test = alg_test_null,
@@ -1563,6 +1593,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "__driver-ecb-serpent-sse2",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
 	}, {
 		.alg = "__ghash-pclmulqdqni",
 		.test = alg_test_null,
@@ -1674,6 +1719,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "cbc(serpent)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = serpent_cbc_enc_tv_template,
+					.count = SERPENT_CBC_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = serpent_cbc_dec_tv_template,
+					.count = SERPENT_CBC_DEC_TEST_VECTORS
+				}
+			}
+		}
 	}, {
 		.alg = "cbc(twofish)",
 		.test = alg_test_skcipher,
@@ -1730,6 +1790,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "cryptd(__driver-ecb-serpent-sse2)",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
 	}, {
 		.alg = "cryptd(__ghash-pclmulqdqni)",
 		.test = alg_test_null,
@@ -1770,6 +1845,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "ctr(serpent)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = serpent_ctr_enc_tv_template,
+					.count = SERPENT_CTR_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = serpent_ctr_dec_tv_template,
+					.count = SERPENT_CTR_DEC_TEST_VECTORS
+				}
+			}
+		}
 	}, {
 		.alg = "ctr(twofish)",
 		.test = alg_test_skcipher,
@@ -2206,6 +2296,36 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "lrw(serpent)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = serpent_lrw_enc_tv_template,
+					.count = SERPENT_LRW_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = serpent_lrw_dec_tv_template,
+					.count = SERPENT_LRW_DEC_TEST_VECTORS
+				}
+			}
+		}
+	}, {
+		.alg = "lrw(twofish)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = tf_lrw_enc_tv_template,
+					.count = TF_LRW_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = tf_lrw_dec_tv_template,
+					.count = TF_LRW_DEC_TEST_VECTORS
+				}
+			}
+		}
 	}, {
 		.alg = "lzo",
 		.test = alg_test_comp,
@@ -2513,6 +2633,36 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "xts(serpent)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = serpent_xts_enc_tv_template,
+					.count = SERPENT_XTS_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = serpent_xts_dec_tv_template,
+					.count = SERPENT_XTS_DEC_TEST_VECTORS
+				}
+			}
+		}
+	}, {
+		.alg = "xts(twofish)",
+		.test = alg_test_skcipher,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = tf_xts_enc_tv_template,
+					.count = TF_XTS_ENC_TEST_VECTORS
+				},
+				.dec = {
+					.vecs = tf_xts_dec_tv_template,
+					.count = TF_XTS_DEC_TEST_VECTORS
+				}
+			}
+		}
 	}, {
 		.alg = "zlib",
 		.test = alg_test_pcomp,

crypto/twofish_common.c

@@ -580,12 +580,9 @@ static const u8 calc_sb_tbl[512] = {
    ctx->a[(j) + 1] = rol32(y, 9)
 
 /* Perform the key setup. */
-int twofish_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len)
+int __twofish_setkey(struct twofish_ctx *ctx, const u8 *key,
+		     unsigned int key_len, u32 *flags)
 {
-
-	struct twofish_ctx *ctx = crypto_tfm_ctx(tfm);
-	u32 *flags = &tfm->crt_flags;
-
 	int i, j, k;
 
 	/* Temporaries for CALC_K. */
@@ -701,7 +698,13 @@ int twofish_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__twofish_setkey);
 
+int twofish_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int key_len)
+{
+	return __twofish_setkey(crypto_tfm_ctx(tfm), key, key_len,
+				&tfm->crt_flags);
+}
 EXPORT_SYMBOL_GPL(twofish_setkey);
 
 MODULE_LICENSE("GPL");

crypto/xts.c

@@ -21,6 +21,7 @@
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 
+#include <crypto/xts.h>
 #include <crypto/b128ops.h>
 #include <crypto/gf128mul.h>
 
@@ -96,7 +97,7 @@ static int crypt(struct blkcipher_desc *d,
 {
 	int err;
 	unsigned int avail;
-	const int bs = crypto_cipher_blocksize(ctx->child);
+	const int bs = XTS_BLOCK_SIZE;
 	struct sinfo s = {
 		.tfm = crypto_cipher_tfm(ctx->child),
 		.fn = fn
@@ -165,6 +166,78 @@ static int decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		     crypto_cipher_alg(ctx->child)->cia_decrypt);
 }
 
+int xts_crypt(struct blkcipher_desc *desc, struct scatterlist *sdst,
+	      struct scatterlist *ssrc, unsigned int nbytes,
+	      struct xts_crypt_req *req)
+{
+	const unsigned int bsize = XTS_BLOCK_SIZE;
+	const unsigned int max_blks = req->tbuflen / bsize;
+	struct blkcipher_walk walk;
+	unsigned int nblocks;
+	be128 *src, *dst, *t;
+	be128 *t_buf = req->tbuf;
+	int err, i;
+
+	BUG_ON(max_blks < 1);
+
+	blkcipher_walk_init(&walk, sdst, ssrc, nbytes);
+
+	err = blkcipher_walk_virt(desc, &walk);
+	nbytes = walk.nbytes;
+	if (!nbytes)
+		return err;
+
+	nblocks = min(nbytes / bsize, max_blks);
+	src = (be128 *)walk.src.virt.addr;
+	dst = (be128 *)walk.dst.virt.addr;
+
+	/* calculate first value of T */
+	req->tweak_fn(req->tweak_ctx, (u8 *)&t_buf[0], walk.iv);
+
+	i = 0;
+	goto first;
+
+	for (;;) {
+		do {
+			for (i = 0; i < nblocks; i++) {
+				gf128mul_x_ble(&t_buf[i], t);
+first:
+				t = &t_buf[i];
+
+				/* PP <- T xor P */
+				be128_xor(dst + i, t, src + i);
+			}
+
+			/* CC <- E(Key2,PP) */
+			req->crypt_fn(req->crypt_ctx, (u8 *)dst,
+				      nblocks * bsize);
+
+			/* C <- T xor CC */
+			for (i = 0; i < nblocks; i++)
+				be128_xor(dst + i, dst + i, &t_buf[i]);
+
+			src += nblocks;
+			dst += nblocks;
+			nbytes -= nblocks * bsize;
+			nblocks = min(nbytes / bsize, max_blks);
+		} while (nblocks > 0);
+
+		*(be128 *)walk.iv = *t;
+
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+		nbytes = walk.nbytes;
+		if (!nbytes)
+			break;
+
+		nblocks = min(nbytes / bsize, max_blks);
+		src = (be128 *)walk.src.virt.addr;
+		dst = (be128 *)walk.dst.virt.addr;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xts_crypt);
+
 static int init_tfm(struct crypto_tfm *tfm)
 {
 	struct crypto_cipher *cipher;
@@ -177,7 +250,7 @@ static int init_tfm(struct crypto_tfm *tfm)
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
-	if (crypto_cipher_blocksize(cipher) != 16) {
+	if (crypto_cipher_blocksize(cipher) != XTS_BLOCK_SIZE) {
 		*flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;
 		crypto_free_cipher(cipher);
 		return -EINVAL;
@@ -192,7 +265,7 @@ static int init_tfm(struct crypto_tfm *tfm)
 	}
 
 	/* this check isn't really needed, leave it here just in case */
-	if (crypto_cipher_blocksize(cipher) != 16) {
+	if (crypto_cipher_blocksize(cipher) != XTS_BLOCK_SIZE) {
 		crypto_free_cipher(cipher);
 		crypto_free_cipher(ctx->child);
 		*flags |= CRYPTO_TFM_RES_BAD_BLOCK_LEN;

drivers/char/hw_random/atmel-rng.c

@@ -141,17 +141,7 @@ static struct platform_driver atmel_trng_driver = {
 	},
 };
 
-static int __init atmel_trng_init(void)
-{
-	return platform_driver_register(&atmel_trng_driver);
-}
-module_init(atmel_trng_init);
-
-static void __exit atmel_trng_exit(void)
-{
-	platform_driver_unregister(&atmel_trng_driver);
-}
-module_exit(atmel_trng_exit);
+module_platform_driver(atmel_trng_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Peter Korsgaard <jacmet@sunsite.dk>");

drivers/char/hw_random/n2-drv.c

@@ -770,15 +770,4 @@ static struct platform_driver n2rng_driver = {
 	.remove		= __devexit_p(n2rng_remove),
 };
 
-static int __init n2rng_init(void)
-{
-	return platform_driver_register(&n2rng_driver);
-}
-
-static void __exit n2rng_exit(void)
-{
-	platform_driver_unregister(&n2rng_driver);
-}
-
-module_init(n2rng_init);
-module_exit(n2rng_exit);
+module_platform_driver(n2rng_driver);

drivers/char/hw_random/octeon-rng.c

@@ -131,18 +131,7 @@ static struct platform_driver octeon_rng_driver = {
 	.remove		= __exit_p(octeon_rng_remove),
 };
 
-static int __init octeon_rng_mod_init(void)
-{
-	return platform_driver_register(&octeon_rng_driver);
-}
-
-static void __exit octeon_rng_mod_exit(void)
-{
-	platform_driver_unregister(&octeon_rng_driver);
-}
-
-module_init(octeon_rng_mod_init);
-module_exit(octeon_rng_mod_exit);
+module_platform_driver(octeon_rng_driver);
 
 MODULE_AUTHOR("David Daney");
 MODULE_LICENSE("GPL");

drivers/char/hw_random/pasemi-rng.c

@@ -148,17 +148,7 @@ static struct platform_driver rng_driver = {
 	.remove		= rng_remove,
 };
 
-static int __init rng_init(void)
-{
-	return platform_driver_register(&rng_driver);
-}
-module_init(rng_init);
-
-static void __exit rng_exit(void)
-{
-	platform_driver_unregister(&rng_driver);
-}
-module_exit(rng_exit);
+module_platform_driver(rng_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Egor Martovetsky <egor@pasemi.com>");

drivers/char/hw_random/picoxcell-rng.c

@@ -191,17 +191,7 @@ static struct platform_driver picoxcell_trng_driver = {
 	},
 };
 
-static int __init picoxcell_trng_init(void)
-{
-	return platform_driver_register(&picoxcell_trng_driver);
-}
-module_init(picoxcell_trng_init);
-
-static void __exit picoxcell_trng_exit(void)
-{
-	platform_driver_unregister(&picoxcell_trng_driver);
-}
-module_exit(picoxcell_trng_exit);
+module_platform_driver(picoxcell_trng_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jamie Iles");

drivers/char/hw_random/ppc4xx-rng.c

@@ -139,17 +139,7 @@ static struct platform_driver ppc4xx_rng_driver = {
 	.remove = ppc4xx_rng_remove,
 };
 
-static int __init ppc4xx_rng_init(void)
-{
-	return platform_driver_register(&ppc4xx_rng_driver);
-}
-module_init(ppc4xx_rng_init);
-
-static void __exit ppc4xx_rng_exit(void)
-{
-	platform_driver_unregister(&ppc4xx_rng_driver);
-}
-module_exit(ppc4xx_rng_exit);
+module_platform_driver(ppc4xx_rng_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Josh Boyer <jwboyer@linux.vnet.ibm.com>");

drivers/char/hw_random/timeriomem-rng.c

@@ -149,18 +149,7 @@ static struct platform_driver timeriomem_rng_driver = {
 	.remove		= __devexit_p(timeriomem_rng_remove),
 };
 
-static int __init timeriomem_rng_init(void)
-{
-	return platform_driver_register(&timeriomem_rng_driver);
-}
-
-static void __exit timeriomem_rng_exit(void)
-{
-	platform_driver_unregister(&timeriomem_rng_driver);
-}
-
-module_init(timeriomem_rng_init);
-module_exit(timeriomem_rng_exit);
+module_platform_driver(timeriomem_rng_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>");

drivers/crypto/amcc/crypto4xx_core.c

@@ -1292,18 +1292,7 @@ static struct platform_driver crypto4xx_driver = {
 	.remove		= crypto4xx_remove,
 };
 
-static int __init crypto4xx_init(void)
-{
-	return platform_driver_register(&crypto4xx_driver);
-}
-
-static void __exit crypto4xx_exit(void)
-{
-	platform_driver_unregister(&crypto4xx_driver);
-}
-
-module_init(crypto4xx_init);
-module_exit(crypto4xx_exit);
+module_platform_driver(crypto4xx_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("James Hsiao <jhsiao@amcc.com>");

drivers/crypto/caam/caamalg.c

@@ -113,7 +113,7 @@ static inline void append_dec_shr_done(u32 *desc)
 
 	jump_cmd = append_jump(desc, JUMP_CLASS_CLASS1 | JUMP_TEST_ALL);
 	set_jump_tgt_here(desc, jump_cmd);
-	append_cmd(desc, SET_OK_PROP_ERRORS | CMD_LOAD);
+	append_cmd(desc, SET_OK_NO_PROP_ERRORS | CMD_LOAD);
 }
 
 /*
@@ -213,7 +213,7 @@ static void init_sh_desc_key_aead(u32 *desc, struct caam_ctx *ctx,
 	set_jump_tgt_here(desc, key_jump_cmd);
 
 	/* Propagate errors from shared to job descriptor */
-	append_cmd(desc, SET_OK_PROP_ERRORS | CMD_LOAD);
+	append_cmd(desc, SET_OK_NO_PROP_ERRORS | CMD_LOAD);
 }
 
 static int aead_set_sh_desc(struct crypto_aead *aead)
@@ -310,7 +310,7 @@ static int aead_set_sh_desc(struct crypto_aead *aead)
 	/* Only propagate error immediately if shared */
 	jump_cmd = append_jump(desc, JUMP_TEST_ALL);
 	set_jump_tgt_here(desc, key_jump_cmd);
-	append_cmd(desc, SET_OK_PROP_ERRORS | CMD_LOAD);
+	append_cmd(desc, SET_OK_NO_PROP_ERRORS | CMD_LOAD);
 	set_jump_tgt_here(desc, jump_cmd);
 
 	/* Class 2 operation */
@@ -683,7 +683,7 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	set_jump_tgt_here(desc, key_jump_cmd);
 
 	/* Propagate errors from shared to job descriptor */
-	append_cmd(desc, SET_OK_PROP_ERRORS | CMD_LOAD);
+	append_cmd(desc, SET_OK_NO_PROP_ERRORS | CMD_LOAD);
 
 	/* Load iv */
 	append_cmd(desc, CMD_SEQ_LOAD | LDST_SRCDST_BYTE_CONTEXT |
@@ -724,7 +724,7 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher,
 	/* For aead, only propagate error immediately if shared */
 	jump_cmd = append_jump(desc, JUMP_TEST_ALL);
 	set_jump_tgt_here(desc, key_jump_cmd);
-	append_cmd(desc, SET_OK_PROP_ERRORS | CMD_LOAD);
+	append_cmd(desc, SET_OK_NO_PROP_ERRORS | CMD_LOAD);
 	set_jump_tgt_here(desc, jump_cmd);
 
 	/* load IV */
@@ -1805,6 +1805,25 @@ struct caam_alg_template {
 
 static struct caam_alg_template driver_algs[] = {
 	/* single-pass ipsec_esp descriptor */
+	{
+		.name = "authenc(hmac(md5),cbc(aes))",
+		.driver_name = "authenc-hmac-md5-cbc-aes-caam",
+		.blocksize = AES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.givencrypt = aead_givencrypt,
+			.geniv = "<built-in>",
+			.ivsize = AES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+			},
+		.class1_alg_type = OP_ALG_ALGSEL_AES | OP_ALG_AAI_CBC,
+		.class2_alg_type = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC_PRECOMP,
+		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+	},
 	{
 		.name = "authenc(hmac(sha1),cbc(aes))",
 		.driver_name = "authenc-hmac-sha1-cbc-aes-caam",
@@ -1864,6 +1883,25 @@ static struct caam_alg_template driver_algs[] = {
 				   OP_ALG_AAI_HMAC_PRECOMP,
 		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
 	},
+	{
+		.name = "authenc(hmac(md5),cbc(des3_ede))",
+		.driver_name = "authenc-hmac-md5-cbc-des3_ede-caam",
+		.blocksize = DES3_EDE_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.givencrypt = aead_givencrypt,
+			.geniv = "<built-in>",
+			.ivsize = DES3_EDE_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+			},
+		.class1_alg_type = OP_ALG_ALGSEL_3DES | OP_ALG_AAI_CBC,
+		.class2_alg_type = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC_PRECOMP,
+		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+	},
 	{
 		.name = "authenc(hmac(sha1),cbc(des3_ede))",
 		.driver_name = "authenc-hmac-sha1-cbc-des3_ede-caam",
@@ -1923,6 +1961,25 @@ static struct caam_alg_template driver_algs[] = {
 				   OP_ALG_AAI_HMAC_PRECOMP,
 		.alg_op = OP_ALG_ALGSEL_SHA512 | OP_ALG_AAI_HMAC,
 	},
+	{
+		.name = "authenc(hmac(md5),cbc(des))",
+		.driver_name = "authenc-hmac-md5-cbc-des-caam",
+		.blocksize = DES_BLOCK_SIZE,
+		.type = CRYPTO_ALG_TYPE_AEAD,
+		.template_aead = {
+			.setkey = aead_setkey,
+			.setauthsize = aead_setauthsize,
+			.encrypt = aead_encrypt,
+			.decrypt = aead_decrypt,
+			.givencrypt = aead_givencrypt,
+			.geniv = "<built-in>",
+			.ivsize = DES_BLOCK_SIZE,
+			.maxauthsize = MD5_DIGEST_SIZE,
+			},
+		.class1_alg_type = OP_ALG_ALGSEL_DES | OP_ALG_AAI_CBC,
+		.class2_alg_type = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC_PRECOMP,
+		.alg_op = OP_ALG_ALGSEL_MD5 | OP_ALG_AAI_HMAC,
+	},
 	{
 		.name = "authenc(hmac(sha1),cbc(des))",
 		.driver_name = "authenc-hmac-sha1-cbc-des-caam",

drivers/crypto/caam/compat.h

@@ -28,6 +28,7 @@
 #include <crypto/aes.h>
 #include <crypto/des.h>
 #include <crypto/sha.h>
+#include <crypto/md5.h>
 #include <crypto/aead.h>
 #include <crypto/authenc.h>
 #include <crypto/scatterwalk.h>