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

Pull crypto updates from Herbert Xu:
 "Here is the crypto update for 4.10:

  API:
   - add skcipher walk interface
   - add asynchronous compression (acomp) interface
   - fix algif_aed AIO handling of zero buffer

  Algorithms:
   - fix unaligned access in poly1305
   - fix DRBG output to large buffers

  Drivers:
   - add support for iMX6UL to caam
   - fix givenc descriptors (used by IPsec) in caam
   - accelerated SHA256/SHA512 for ARM64 from OpenSSL
   - add SSE CRCT10DIF and CRC32 to ARM/ARM64
   - add AEAD support to Chelsio chcr
   - add Armada 8K support to omap-rng"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (148 commits)
  crypto: testmgr - fix overlap in chunked tests again
  crypto: arm/crc32 - accelerated support based on x86 SSE implementation
  crypto: arm64/crc32 - accelerated support based on x86 SSE implementation
  crypto: arm/crct10dif - port x86 SSE implementation to ARM
  crypto: arm64/crct10dif - port x86 SSE implementation to arm64
  crypto: testmgr - add/enhance test cases for CRC-T10DIF
  crypto: testmgr - avoid overlap in chunked tests
  crypto: chcr - checking for IS_ERR() instead of NULL
  crypto: caam - check caam_emi_slow instead of re-lookup platform
  crypto: algif_aead - fix AIO handling of zero buffer
  crypto: aes-ce - Make aes_simd_algs static
  crypto: algif_skcipher - set error code when kcalloc fails
  crypto: caam - make aamalg_desc a proper module
  crypto: caam - pass key buffers with typesafe pointers
  crypto: arm64/aes-ce-ccm - Fix AEAD decryption length
  MAINTAINERS: add crypto headers to crypto entry
  crypt: doc - remove misleading mention of async API
  crypto: doc - fix header file name
  crypto: api - fix comment typo
  crypto: skcipher - Add separate walker for AEAD decryption
  ..

1 files changed, 15 insertions, 19 deletions

diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index 2df9835dfbc0..b1c2d57dc734 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -17,6 +17,7 @@
 #include <linux/crypto.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <asm/unaligned.h>
 
 static inline u64 mlt(u64 a, u64 b)
 {
@@ -33,11 +34,6 @@ static inline u32 and(u32 v, u32 mask)
 	return v & mask;
 }
 
-static inline u32 le32_to_cpuvp(const void *p)
-{
-	return le32_to_cpup(p);
-}
-
 int crypto_poly1305_init(struct shash_desc *desc)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
@@ -65,19 +61,19 @@ EXPORT_SYMBOL_GPL(crypto_poly1305_setkey);
 static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
 	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
-	dctx->r[0] = (le32_to_cpuvp(key +  0) >> 0) & 0x3ffffff;
-	dctx->r[1] = (le32_to_cpuvp(key +  3) >> 2) & 0x3ffff03;
-	dctx->r[2] = (le32_to_cpuvp(key +  6) >> 4) & 0x3ffc0ff;
-	dctx->r[3] = (le32_to_cpuvp(key +  9) >> 6) & 0x3f03fff;
-	dctx->r[4] = (le32_to_cpuvp(key + 12) >> 8) & 0x00fffff;
+	dctx->r[0] = (get_unaligned_le32(key +  0) >> 0) & 0x3ffffff;
+	dctx->r[1] = (get_unaligned_le32(key +  3) >> 2) & 0x3ffff03;
+	dctx->r[2] = (get_unaligned_le32(key +  6) >> 4) & 0x3ffc0ff;
+	dctx->r[3] = (get_unaligned_le32(key +  9) >> 6) & 0x3f03fff;
+	dctx->r[4] = (get_unaligned_le32(key + 12) >> 8) & 0x00fffff;
 }
 
 static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
-	dctx->s[0] = le32_to_cpuvp(key +  0);
-	dctx->s[1] = le32_to_cpuvp(key +  4);
-	dctx->s[2] = le32_to_cpuvp(key +  8);
-	dctx->s[3] = le32_to_cpuvp(key + 12);
+	dctx->s[0] = get_unaligned_le32(key +  0);
+	dctx->s[1] = get_unaligned_le32(key +  4);
+	dctx->s[2] = get_unaligned_le32(key +  8);
+	dctx->s[3] = get_unaligned_le32(key + 12);
 }
 
 unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
@@ -137,11 +133,11 @@ static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
 	while (likely(srclen >= POLY1305_BLOCK_SIZE)) {
 
 		/* h += m[i] */
-		h0 += (le32_to_cpuvp(src +  0) >> 0) & 0x3ffffff;
-		h1 += (le32_to_cpuvp(src +  3) >> 2) & 0x3ffffff;
-		h2 += (le32_to_cpuvp(src +  6) >> 4) & 0x3ffffff;
-		h3 += (le32_to_cpuvp(src +  9) >> 6) & 0x3ffffff;
-		h4 += (le32_to_cpuvp(src + 12) >> 8) | hibit;
+		h0 += (get_unaligned_le32(src +  0) >> 0) & 0x3ffffff;
+		h1 += (get_unaligned_le32(src +  3) >> 2) & 0x3ffffff;
+		h2 += (get_unaligned_le32(src +  6) >> 4) & 0x3ffffff;
+		h3 += (get_unaligned_le32(src +  9) >> 6) & 0x3ffffff;
+		h4 += (get_unaligned_le32(src + 12) >> 8) | hibit;
 
 		/* h *= r */
 		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +