Merge 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 4.3:

  API:

   - the AEAD interface transition is now complete.
   - add top-level skcipher interface.

  Drivers:

   - x86-64 acceleration for chacha20/poly1305.
   - add sunxi-ss Allwinner Security System crypto accelerator.
   - add RSA algorithm to qat driver.
   - add SRIOV support to qat driver.
   - add LS1021A support to caam.
   - add i.MX6 support to caam"

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (163 commits)
  crypto: algif_aead - fix for multiple operations on AF_ALG sockets
  crypto: qat - enable legacy VFs
  MPI: Fix mpi_read_buffer
  crypto: qat - silence a static checker warning
  crypto: vmx - Fixing opcode issue
  crypto: caam - Use the preferred style for memory allocations
  crypto: caam - Propagate the real error code in caam_probe
  crypto: caam - Fix the error handling in caam_probe
  crypto: caam - fix writing to JQCR_MS when using service interface
  crypto: hash - Add AHASH_REQUEST_ON_STACK
  crypto: testmgr - Use new skcipher interface
  crypto: skcipher - Add top-level skcipher interface
  crypto: cmac - allow usage in FIPS mode
  crypto: sahara - Use dmam_alloc_coherent
  crypto: caam - Add support for LS1021A
  crypto: qat - Don't move data inside output buffer
  crypto: vmx - Fixing GHASH Key issue on little endian
  crypto: vmx - Fixing AES-CTR counter bug
  crypto: null - Add missing Kconfig tristate for NULL2
  crypto: nx - Add forward declaration for struct crypto_aead
  ...

lib/mpi/mpicoder.c

@@ -146,18 +146,25 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 	uint8_t *p;
 	mpi_limb_t alimb;
 	unsigned int n = mpi_get_size(a);
-	int i;
+	int i, lzeros = 0;
 
-	if (buf_len < n || !buf)
+	if (buf_len < n || !buf || !nbytes)
 		return -EINVAL;
 
 	if (sign)
 		*sign = a->sign;
 
-	if (nbytes)
-		*nbytes = n;
+	p = (void *)&a->d[a->nlimbs] - 1;
+
+	for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) {
+		if (!*p)
+			lzeros++;
+		else
+			break;
+	}
 
 	p = buf;
+	*nbytes = n - lzeros;
 
 	for (i = a->nlimbs - 1; i >= 0; i--) {
 		alimb = a->d[i];
@@ -178,6 +185,19 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 #else
 #error please implement for this limb size.
 #endif
+
+		if (lzeros > 0) {
+			if (lzeros >= sizeof(alimb)) {
+				p -= sizeof(alimb);
+			} else {
+				mpi_limb_t *limb1 = (void *)p - sizeof(alimb);
+				mpi_limb_t *limb2 = (void *)p - sizeof(alimb)
+							+ lzeros;
+				*limb1 = *limb2;
+				p -= lzeros;
+			}
+			lzeros -= sizeof(alimb);
+		}
 	}
 	return 0;
 }
@@ -197,7 +217,7 @@ EXPORT_SYMBOL_GPL(mpi_read_buffer);
  */
 void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 {
-	uint8_t *buf, *p;
+	uint8_t *buf;
 	unsigned int n;
 	int ret;
 
@@ -220,14 +240,6 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 		kfree(buf);
 		return NULL;
 	}
-
-	/* this is sub-optimal but we need to do the shift operation
-	 * because the caller has to free the returned buffer */
-	for (p = buf; !*p && *nbytes; p++, --*nbytes)
-		;
-	if (p != buf)
-		memmove(buf, p, *nbytes);
-
 	return buf;
 }
 EXPORT_SYMBOL_GPL(mpi_get_buffer);