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

Pull crypto update from Herbert Xu:

 - Added aesni/avx/x86_64 implementations for camellia.

 - Optimised AVX code for cast5/serpent/twofish/cast6.

 - Fixed vmac bug with unaligned input.

 - Allow compression algorithms in FIPS mode.

 - Optimised crc32c implementation for Intel.

 - Misc fixes.

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (32 commits)
  crypto: caam - Updated SEC-4.0 device tree binding for ERA information.
  crypto: testmgr - remove superfluous initializers for xts(aes)
  crypto: testmgr - allow compression algs in fips mode
  crypto: testmgr - add larger crc32c test vector to test FPU path in crc32c_intel
  crypto: testmgr - clean alg_test_null entries in alg_test_descs[]
  crypto: testmgr - remove fips_allowed flag from camellia-aesni null-tests
  crypto: cast5/cast6 - move lookup tables to shared module
  padata: use __this_cpu_read per-cpu helper
  crypto: s5p-sss - Fix compilation error
  crypto: picoxcell - Add terminating entry for platform_device_id table
  crypto: omap-aes - select BLKCIPHER2
  crypto: camellia - add AES-NI/AVX/x86_64 assembler implementation of camellia cipher
  crypto: camellia-x86_64 - share common functions and move structures and function definitions to header file
  crypto: tcrypt - add async speed test for camellia cipher
  crypto: tegra-aes - fix error-valued pointer dereference
  crypto: tegra - fix missing unlock on error case
  crypto: cast5/avx - avoid using temporary stack buffers
  crypto: serpent/avx - avoid using temporary stack buffers
  crypto: twofish/avx - avoid using temporary stack buffers
  crypto: cast6/avx - avoid using temporary stack buffers
  ...

arch/x86/include/asm/crypto/camellia.h

@@ -0,0 +1,82 @@
+#ifndef ASM_X86_CAMELLIA_H
+#define ASM_X86_CAMELLIA_H
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+
+#define CAMELLIA_MIN_KEY_SIZE	16
+#define CAMELLIA_MAX_KEY_SIZE	32
+#define CAMELLIA_BLOCK_SIZE	16
+#define CAMELLIA_TABLE_BYTE_LEN	272
+#define CAMELLIA_PARALLEL_BLOCKS 2
+
+struct camellia_ctx {
+	u64 key_table[CAMELLIA_TABLE_BYTE_LEN / sizeof(u64)];
+	u32 key_length;
+};
+
+struct camellia_lrw_ctx {
+	struct lrw_table_ctx lrw_table;
+	struct camellia_ctx camellia_ctx;
+};
+
+struct camellia_xts_ctx {
+	struct camellia_ctx tweak_ctx;
+	struct camellia_ctx crypt_ctx;
+};
+
+extern int __camellia_setkey(struct camellia_ctx *cctx,
+			     const unsigned char *key,
+			     unsigned int key_len, u32 *flags);
+
+extern int lrw_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
+			       unsigned int keylen);
+extern void lrw_camellia_exit_tfm(struct crypto_tfm *tfm);
+
+extern int xts_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
+			       unsigned int keylen);
+
+/* regular block cipher functions */
+asmlinkage void __camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst,
+				   const u8 *src, bool xor);
+asmlinkage void camellia_dec_blk(struct camellia_ctx *ctx, u8 *dst,
+				 const u8 *src);
+
+/* 2-way parallel cipher functions */
+asmlinkage void __camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst,
+					const u8 *src, bool xor);
+asmlinkage void camellia_dec_blk_2way(struct camellia_ctx *ctx, u8 *dst,
+				      const u8 *src);
+
+static inline void camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst,
+				    const u8 *src)
+{
+	__camellia_enc_blk(ctx, dst, src, false);
+}
+
+static inline void camellia_enc_blk_xor(struct camellia_ctx *ctx, u8 *dst,
+					const u8 *src)
+{
+	__camellia_enc_blk(ctx, dst, src, true);
+}
+
+static inline void camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst,
+					 const u8 *src)
+{
+	__camellia_enc_blk_2way(ctx, dst, src, false);
+}
+
+static inline void camellia_enc_blk_xor_2way(struct camellia_ctx *ctx, u8 *dst,
+					     const u8 *src)
+{
+	__camellia_enc_blk_2way(ctx, dst, src, true);
+}
+
+/* glue helpers */
+extern void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src);
+extern void camellia_crypt_ctr(void *ctx, u128 *dst, const u128 *src,
+			       le128 *iv);
+extern void camellia_crypt_ctr_2way(void *ctx, u128 *dst, const u128 *src,
+				    le128 *iv);
+
+#endif /* ASM_X86_CAMELLIA_H */

arch/x86/include/asm/crypto/glue_helper.h

@@ -13,7 +13,7 @@
 typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
 typedef void (*common_glue_cbc_func_t)(void *ctx, u128 *dst, const u128 *src);
 typedef void (*common_glue_ctr_func_t)(void *ctx, u128 *dst, const u128 *src,
-				       u128 *iv);
+				       le128 *iv);
 
 #define GLUE_FUNC_CAST(fn) ((common_glue_func_t)(fn))
 #define GLUE_CBC_FUNC_CAST(fn) ((common_glue_cbc_func_t)(fn))
@@ -71,23 +71,29 @@ static inline void glue_fpu_end(bool fpu_enabled)
 		kernel_fpu_end();
 }
 
-static inline void u128_to_be128(be128 *dst, const u128 *src)
+static inline void le128_to_be128(be128 *dst, const le128 *src)
 {
-	dst->a = cpu_to_be64(src->a);
-	dst->b = cpu_to_be64(src->b);
+	dst->a = cpu_to_be64(le64_to_cpu(src->a));
+	dst->b = cpu_to_be64(le64_to_cpu(src->b));
 }
 
-static inline void be128_to_u128(u128 *dst, const be128 *src)
+static inline void be128_to_le128(le128 *dst, const be128 *src)
 {
-	dst->a = be64_to_cpu(src->a);
-	dst->b = be64_to_cpu(src->b);
+	dst->a = cpu_to_le64(be64_to_cpu(src->a));
+	dst->b = cpu_to_le64(be64_to_cpu(src->b));
 }
 
-static inline void u128_inc(u128 *i)
+static inline void le128_inc(le128 *i)
 {
-	i->b++;
-	if (!i->b)
-		i->a++;
+	u64 a = le64_to_cpu(i->a);
+	u64 b = le64_to_cpu(i->b);
+
+	b++;
+	if (!b)
+		a++;
+
+	i->a = cpu_to_le64(a);
+	i->b = cpu_to_le64(b);
 }
 
 extern int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,

arch/x86/include/asm/crypto/serpent-avx.h

@@ -6,27 +6,14 @@
 
 #define SERPENT_PARALLEL_BLOCKS 8
 
-asmlinkage void __serpent_enc_blk_8way_avx(struct serpent_ctx *ctx, u8 *dst,
-					   const u8 *src, bool xor);
-asmlinkage void serpent_dec_blk_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+asmlinkage void serpent_ecb_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+					 const u8 *src);
+asmlinkage void serpent_ecb_dec_8way_avx(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_avx(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_avx(ctx, dst, src, true);
-}
-
-static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
-				   const u8 *src)
-{
-	serpent_dec_blk_8way_avx(ctx, dst, src);
-}
+asmlinkage void serpent_cbc_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+					 const u8 *src);
+asmlinkage void serpent_ctr_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+				     const u8 *src, le128 *iv);
 
 #endif

arch/x86/include/asm/crypto/twofish.h

@@ -31,9 +31,9 @@ asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst,
 /* helpers from twofish_x86_64-3way module */
 extern void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src);
 extern void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src,
-				u128 *iv);
+				le128 *iv);
 extern void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src,
-				     u128 *iv);
+				     le128 *iv);
 
 extern int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
 			      unsigned int keylen);