Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:
 "API:
   - Add helper for simple skcipher modes.
   - Add helper to register multiple templates.
   - Set CRYPTO_TFM_NEED_KEY when setkey fails.
   - Require neither or both of export/import in shash.
   - AEAD decryption test vectors are now generated from encryption
     ones.
   - New option CONFIG_CRYPTO_MANAGER_EXTRA_TESTS that includes random
     fuzzing.

  Algorithms:
   - Conversions to skcipher and helper for many templates.
   - Add more test vectors for nhpoly1305 and adiantum.

  Drivers:
   - Add crypto4xx prng support.
   - Add xcbc/cmac/ecb support in caam.
   - Add AES support for Exynos5433 in s5p.
   - Remove sha384/sha512 from artpec7 as hardware cannot do partial
     hash"

[ There is a merge of the Freescale SoC tree in order to pull in changes
  required by patches to the caam/qi2 driver. ]

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (174 commits)
  crypto: s5p - add AES support for Exynos5433
  dt-bindings: crypto: document Exynos5433 SlimSSS
  crypto: crypto4xx - add missing of_node_put after of_device_is_available
  crypto: cavium/zip - fix collision with generic cra_driver_name
  crypto: af_alg - use struct_size() in sock_kfree_s()
  crypto: caam - remove redundant likely/unlikely annotation
  crypto: s5p - update iv after AES-CBC op end
  crypto: x86/poly1305 - Clear key material from stack in SSE2 variant
  crypto: caam - generate hash keys in-place
  crypto: caam - fix DMA mapping xcbc key twice
  crypto: caam - fix hash context DMA unmap size
  hwrng: bcm2835 - fix probe as platform device
  crypto: s5p-sss - Use AES_BLOCK_SIZE define instead of number
  crypto: stm32 - drop pointless static qualifier in stm32_hash_remove()
  crypto: chelsio - Fixed Traffic Stall
  crypto: marvell - Remove set but not used variable 'ivsize'
  crypto: ccp - Update driver messages to remove some confusion
  crypto: adiantum - add 1536 and 4096-byte test vectors
  crypto: nhpoly1305 - add a test vector with len % 16 != 0
  crypto: arm/aes-ce - update IV after partial final CTR block
  ...

1 files changed, 46 insertions, 29 deletions

diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index b461d62023f2..dd325829ee44 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -22,10 +22,8 @@
 
 #define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
 
-asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 buf[], u64 len);
-asmlinkage u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 buf[], u64 len);
-
-static u16 (*crc_t10dif_pmull)(u16 init_crc, const u8 buf[], u64 len);
+asmlinkage u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len);
+asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
 
 static int crct10dif_init(struct shash_desc *desc)
 {
@@ -35,30 +33,33 @@ static int crct10dif_init(struct shash_desc *desc)
 	return 0;
 }
 
-static int crct10dif_update(struct shash_desc *desc, const u8 *data,
+static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data,
 			    unsigned int length)
 {
 	u16 *crc = shash_desc_ctx(desc);
-	unsigned int l;
 
-	if (unlikely((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE)) {
-		l = min_t(u32, length, CRC_T10DIF_PMULL_CHUNK_SIZE -
-			  ((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE));
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+		kernel_neon_begin();
+		*crc = crc_t10dif_pmull_p8(*crc, data, length);
+		kernel_neon_end();
+	} else {
+		*crc = crc_t10dif_generic(*crc, data, length);
+	}
 
-		*crc = crc_t10dif_generic(*crc, data, l);
+	return 0;
+}
 
-		length -= l;
-		data += l;
-	}
+static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data,
+			    unsigned int length)
+{
+	u16 *crc = shash_desc_ctx(desc);
 
-	if (length > 0) {
-		if (may_use_simd()) {
-			kernel_neon_begin();
-			*crc = crc_t10dif_pmull(*crc, data, length);
-			kernel_neon_end();
-		} else {
-			*crc = crc_t10dif_generic(*crc, data, length);
-		}
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+		kernel_neon_begin();
+		*crc = crc_t10dif_pmull_p64(*crc, data, length);
+		kernel_neon_end();
+	} else {
+		*crc = crc_t10dif_generic(*crc, data, length);
 	}
 
 	return 0;
@@ -72,10 +73,22 @@ static int crct10dif_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static struct shash_alg crc_t10dif_alg = {
+static struct shash_alg crc_t10dif_alg[] = {{
 	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
 	.init			= crct10dif_init,
-	.update			= crct10dif_update,
+	.update			= crct10dif_update_pmull_p8,
+	.final			= crct10dif_final,
+	.descsize		= CRC_T10DIF_DIGEST_SIZE,
+
+	.base.cra_name		= "crct10dif",
+	.base.cra_driver_name	= "crct10dif-arm64-neon",
+	.base.cra_priority	= 100,
+	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
+	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
+	.init			= crct10dif_init,
+	.update			= crct10dif_update_pmull_p64,
 	.final			= crct10dif_final,
 	.descsize		= CRC_T10DIF_DIGEST_SIZE,
 
@@ -84,21 +97,25 @@ static struct shash_alg crc_t10dif_alg = {
 	.base.cra_priority	= 200,
 	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
-};
+}};
 
 static int __init crc_t10dif_mod_init(void)
 {
 	if (elf_hwcap & HWCAP_PMULL)
-		crc_t10dif_pmull = crc_t10dif_pmull_p64;
+		return crypto_register_shashes(crc_t10dif_alg,
+					       ARRAY_SIZE(crc_t10dif_alg));
 	else
-		crc_t10dif_pmull = crc_t10dif_pmull_p8;
-
-	return crypto_register_shash(&crc_t10dif_alg);
+		/* only register the first array element */
+		return crypto_register_shash(crc_t10dif_alg);
 }
 
 static void __exit crc_t10dif_mod_exit(void)
 {
-	crypto_unregister_shash(&crc_t10dif_alg);
+	if (elf_hwcap & HWCAP_PMULL)
+		crypto_unregister_shashes(crc_t10dif_alg,
+					  ARRAY_SIZE(crc_t10dif_alg));
+	else
+		crypto_unregister_shash(crc_t10dif_alg);
 }
 
 module_cpu_feature_match(ASIMD, crc_t10dif_mod_init);