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

Pull crypto updates from Herbert Xu:

 - Fixed algorithm construction hang when self-test fails.
 - Added SHA variants to talitos AEAD list.
 - New driver for Exynos random number generator.
 - Performance enhancements for arc4.
 - Added hwrng support to caam.
 - Added ahash support to caam.
 - Fixed bad kfree in aesni-intel.
 - Allow aesni-intel in FIPS mode.
 - Added atmel driver with support for AES/3DES/SHA.
 - Bug fixes for mv_cesa.
 - CRC hardware driver for BF60x family processors.

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (66 commits)
  crypto: twofish-avx - remove useless instruction
  crypto: testmgr - add aead cbc aes hmac sha1,256,512 test vectors
  crypto: talitos - add sha224, sha384 and sha512 to existing AEAD algorithms
  crypto: talitos - export the talitos_submit function
  crypto: talitos - move talitos structures to header file
  crypto: atmel - add new tests to tcrypt
  crypto: atmel - add Atmel SHA1/SHA256 driver
  crypto: atmel - add Atmel DES/TDES driver
  crypto: atmel - add Atmel AES driver
  ARM: AT91SAM9G45: add crypto peripherals
  crypto: testmgr - allow aesni-intel and ghash_clmulni-intel in fips mode
  hwrng: exynos - Add support for Exynos random number generator
  crypto: aesni-intel - fix wrong kfree pointer
  crypto: caam - ERA retrieval and printing for SEC device
  crypto: caam - Using alloc_coherent for caam job rings
  crypto: algapi - Fix hang on crypto allocation
  crypto: arc4 - now arc needs blockcipher support
  crypto: caam - one tasklet per job ring
  crypto: caam - consolidate memory barriers from job ring en/dequeue
  crypto: caam - only query h/w in job ring dequeue path
  ...

6 files changed, 226 insertions, 2 deletions

diff --git a/arch/x86/include/asm/crypto/ablk_helper.h b/arch/x86/include/asm/crypto/ablk_helper.h
new file mode 100644
index 000000000000..4f93df50c23e
--- /dev/null
+++ b/arch/x86/include/asm/crypto/ablk_helper.h
@@ -0,0 +1,31 @@
+/*
+ * Shared async block cipher helpers
+ */
+
+#ifndef _CRYPTO_ABLK_HELPER_H
+#define _CRYPTO_ABLK_HELPER_H
+
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <crypto/cryptd.h>
+
+struct async_helper_ctx {
+	struct cryptd_ablkcipher *cryptd_tfm;
+};
+
+extern int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+			unsigned int key_len);
+
+extern int __ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_decrypt(struct ablkcipher_request *req);
+
+extern void ablk_exit(struct crypto_tfm *tfm);
+
+extern int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name);
+
+extern int ablk_init(struct crypto_tfm *tfm);
+
+#endif /* _CRYPTO_ABLK_HELPER_H */
diff --git a/arch/x86/include/asm/aes.h b/arch/x86/include/asm/crypto/aes.h
index 80545a1cbe39..80545a1cbe39 100644
--- a/arch/x86/include/asm/aes.h
+++ b/arch/x86/include/asm/crypto/aes.h
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
new file mode 100644
index 000000000000..3e408bddc96f
--- /dev/null
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -0,0 +1,115 @@
+/*
+ * Shared glue code for 128bit block ciphers
+ */
+
+#ifndef _CRYPTO_GLUE_HELPER_H
+#define _CRYPTO_GLUE_HELPER_H
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <asm/i387.h>
+#include <crypto/b128ops.h>
+
+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);
+
+#define GLUE_FUNC_CAST(fn) ((common_glue_func_t)(fn))
+#define GLUE_CBC_FUNC_CAST(fn) ((common_glue_cbc_func_t)(fn))
+#define GLUE_CTR_FUNC_CAST(fn) ((common_glue_ctr_func_t)(fn))
+
+struct common_glue_func_entry {
+	unsigned int num_blocks; /* number of blocks that @fn will process */
+	union {
+		common_glue_func_t ecb;
+		common_glue_cbc_func_t cbc;
+		common_glue_ctr_func_t ctr;
+	} fn_u;
+};
+
+struct common_glue_ctx {
+	unsigned int num_funcs;
+	int fpu_blocks_limit; /* -1 means fpu not needed at all */
+
+	/*
+	 * First funcs entry must have largest num_blocks and last funcs entry
+	 * must have num_blocks == 1!
+	 */
+	struct common_glue_func_entry funcs[];
+};
+
+static inline bool glue_fpu_begin(unsigned int bsize, int fpu_blocks_limit,
+				  struct blkcipher_desc *desc,
+				  bool fpu_enabled, unsigned int nbytes)
+{
+	if (likely(fpu_blocks_limit < 0))
+		return false;
+
+	if (fpu_enabled)
+		return true;
+
+	/*
+	 * Vector-registers are only used when chunk to be processed is large
+	 * enough, so do not enable FPU until it is necessary.
+	 */
+	if (nbytes < bsize * (unsigned int)fpu_blocks_limit)
+		return false;
+
+	if (desc) {
+		/* prevent sleeping if FPU is in use */
+		desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	}
+
+	kernel_fpu_begin();
+	return true;
+}
+
+static inline void glue_fpu_end(bool fpu_enabled)
+{
+	if (fpu_enabled)
+		kernel_fpu_end();
+}
+
+static inline void u128_to_be128(be128 *dst, const u128 *src)
+{
+	dst->a = cpu_to_be64(src->a);
+	dst->b = cpu_to_be64(src->b);
+}
+
+static inline void be128_to_u128(u128 *dst, const be128 *src)
+{
+	dst->a = be64_to_cpu(src->a);
+	dst->b = be64_to_cpu(src->b);
+}
+
+static inline void u128_inc(u128 *i)
+{
+	i->b++;
+	if (!i->b)
+		i->a++;
+}
+
+extern int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
+				 struct blkcipher_desc *desc,
+				 struct scatterlist *dst,
+				 struct scatterlist *src, unsigned int nbytes);
+
+extern int glue_cbc_encrypt_128bit(const common_glue_func_t fn,
+				   struct blkcipher_desc *desc,
+				   struct scatterlist *dst,
+				   struct scatterlist *src,
+				   unsigned int nbytes);
+
+extern int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
+				   struct blkcipher_desc *desc,
+				   struct scatterlist *dst,
+				   struct scatterlist *src,
+				   unsigned int nbytes);
+
+extern int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
+				 struct blkcipher_desc *desc,
+				 struct scatterlist *dst,
+				 struct scatterlist *src, unsigned int nbytes);
+
+#endif /* _CRYPTO_GLUE_HELPER_H */
diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h
new file mode 100644
index 000000000000..432deedd2945
--- /dev/null
+++ b/arch/x86/include/asm/crypto/serpent-avx.h
@@ -0,0 +1,32 @@
+#ifndef ASM_X86_SERPENT_AVX_H
+#define ASM_X86_SERPENT_AVX_H
+
+#include <linux/crypto.h>
+#include <crypto/serpent.h>
+
+#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,
+					 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);
+}
+
+#endif
diff --git a/arch/x86/include/asm/serpent.h b/arch/x86/include/asm/crypto/serpent-sse2.h
index d3ef63fe0c81..e6e77dffbdab 100644
--- a/arch/x86/include/asm/serpent.h
+++ b/arch/x86/include/asm/crypto/serpent-sse2.h
@@ -1,5 +1,5 @@
-#ifndef ASM_X86_SERPENT_H
-#define ASM_X86_SERPENT_H
+#ifndef ASM_X86_SERPENT_SSE2_H
+#define ASM_X86_SERPENT_SSE2_H
 
 #include <linux/crypto.h>
 #include <crypto/serpent.h>
diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/include/asm/crypto/twofish.h
new file mode 100644
index 000000000000..9d2c514bd5f9
--- /dev/null
+++ b/arch/x86/include/asm/crypto/twofish.h
@@ -0,0 +1,46 @@
+#ifndef ASM_X86_TWOFISH_H
+#define ASM_X86_TWOFISH_H
+
+#include <linux/crypto.h>
+#include <crypto/twofish.h>
+#include <crypto/lrw.h>
+#include <crypto/b128ops.h>
+
+struct twofish_lrw_ctx {
+	struct lrw_table_ctx lrw_table;
+	struct twofish_ctx twofish_ctx;
+};
+
+struct twofish_xts_ctx {
+	struct twofish_ctx tweak_ctx;
+	struct twofish_ctx crypt_ctx;
+};
+
+/* regular block cipher functions from twofish_x86_64 module */
+asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst,
+				const u8 *src);
+asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst,
+				const u8 *src);
+
+/* 3-way parallel cipher functions */
+asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
+				       const u8 *src, bool xor);
+asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst,
+				     const u8 *src);
+
+/* 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);
+extern void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src,
+				     u128 *iv);
+
+extern int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen);
+
+extern void lrw_twofish_exit_tfm(struct crypto_tfm *tfm);
+
+extern int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen);
+
+#endif /* ASM_X86_TWOFISH_H */