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

Pull crypto update from Herbert Xu:

 - XTS mode optimisation for twofish/cast6/camellia/aes on x86

 - AVX2/x86_64 implementation for blowfish/twofish/serpent/camellia

 - SSSE3/AVX/AVX2 optimisations for sha256/sha512

 - Added driver for SAHARA2 crypto accelerator

 - Fix for GMAC when used in non-IPsec secnarios

 - Added generic CMAC implementation (including IPsec glue)

 - IP update for crypto/atmel

 - Support for more than one device in hwrng/timeriomem

 - Added Broadcom BCM2835 RNG driver

 - Misc fixes

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (59 commits)
  crypto: caam - fix job ring cleanup code
  crypto: camellia - add AVX2/AES-NI/x86_64 assembler implementation of camellia cipher
  crypto: serpent - add AVX2/x86_64 assembler implementation of serpent cipher
  crypto: twofish - add AVX2/x86_64 assembler implementation of twofish cipher
  crypto: blowfish - add AVX2/x86_64 implementation of blowfish cipher
  crypto: tcrypt - add async cipher speed tests for blowfish
  crypto: testmgr - extend camellia test-vectors for camellia-aesni/avx2
  crypto: aesni_intel - fix Kconfig problem with CRYPTO_GLUE_HELPER_X86
  crypto: aesni_intel - add more optimized XTS mode for x86-64
  crypto: x86/camellia-aesni-avx - add more optimized XTS code
  crypto: cast6-avx: use new optimized XTS code
  crypto: x86/twofish-avx - use optimized XTS code
  crypto: x86 - add more optimized XTS-mode for serpent-avx
  xfrm: add rfc4494 AES-CMAC-96 support
  crypto: add CMAC support to CryptoAPI
  crypto: testmgr - add empty test vectors for null ciphers
  crypto: testmgr - add AES GMAC test vectors
  crypto: gcm - fix rfc4543 to handle async crypto correctly
  crypto: gcm - make GMAC work when dst and src are different
  hwrng: timeriomem - added devicetree hooks
  ...

1 files changed, 60 insertions, 1 deletions

diff --git a/arch/x86/crypto/glue_helper-asm-avx.S b/arch/x86/crypto/glue_helper-asm-avx.S
index f7b6ea2ddfd..02ee2308fb3 100644
--- a/arch/x86/crypto/glue_helper-asm-avx.S
+++ b/arch/x86/crypto/glue_helper-asm-avx.S
@@ -1,7 +1,7 @@
 /*
  * Shared glue code for 128bit block ciphers, AVX assembler macros
  *
- * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
  *
  * 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
@@ -89,3 +89,62 @@
 	vpxor (6*16)(src), x6, x6; \
 	vpxor (7*16)(src), x7, x7; \
 	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
+
+#define gf128mul_x_ble(iv, mask, tmp) \
+	vpsrad $31, iv, tmp; \
+	vpaddq iv, iv, iv; \
+	vpshufd $0x13, tmp, tmp; \
+	vpand mask, tmp, tmp; \
+	vpxor tmp, iv, iv;
+
+#define load_xts_8way(iv, src, dst, x0, x1, x2, x3, x4, x5, x6, x7, tiv, t0, \
+		      t1, xts_gf128mul_and_shl1_mask) \
+	vmovdqa xts_gf128mul_and_shl1_mask, t0; \
+	\
+	/* load IV */ \
+	vmovdqu (iv), tiv; \
+	vpxor (0*16)(src), tiv, x0; \
+	vmovdqu tiv, (0*16)(dst); \
+	\
+	/* construct and store IVs, also xor with source */ \
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (1*16)(src), tiv, x1; \
+	vmovdqu tiv, (1*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (2*16)(src), tiv, x2; \
+	vmovdqu tiv, (2*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (3*16)(src), tiv, x3; \
+	vmovdqu tiv, (3*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (4*16)(src), tiv, x4; \
+	vmovdqu tiv, (4*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (5*16)(src), tiv, x5; \
+	vmovdqu tiv, (5*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (6*16)(src), tiv, x6; \
+	vmovdqu tiv, (6*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (7*16)(src), tiv, x7; \
+	vmovdqu tiv, (7*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vmovdqu tiv, (iv);
+
+#define store_xts_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7) \
+	vpxor (0*16)(dst), x0, x0; \
+	vpxor (1*16)(dst), x1, x1; \
+	vpxor (2*16)(dst), x2, x2; \
+	vpxor (3*16)(dst), x3, x3; \
+	vpxor (4*16)(dst), x4, x4; \
+	vpxor (5*16)(dst), x5, x5; \
+	vpxor (6*16)(dst), x6, x6; \
+	vpxor (7*16)(dst), x7, x7; \
+	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);