Optimize buffer xoring.

* cipher/Makefile.am (libcipher_la_SOURCES): Add 'bufhelp.h'.
* cipher/bufhelp.h: New.
* cipher/cipher-aeswrap.c (_gcry_cipher_aeswrap_encrypt)
(_gcry_cipher_aeswrap_decrypt): Use 'buf_xor' for buffer xoring.
* cipher/cipher-cbc.c (_gcry_cipher_cbc_encrypt)
(_gcry_cipher_cbc_decrypt): Use 'buf_xor' for buffer xoring and remove
resulting unused variables.
* cipher/cipher-cfb.c (_gcry_cipher_cfb_encrypt) Use 'buf_xor_2dst'
for buffer xoring and remove resulting unused variables.
(_gcry_cipher_cfb_decrypt): Use 'buf_xor_n_copy' for buffer xoring and
remove resulting unused variables.
* cipher/cipher-ctr.c (_gcry_cipher_ctr_encrypt): Use 'buf_xor' for
buffer xoring and remove resulting unused variables.
* cipher/cipher-ofb.c (_gcry_cipher_ofb_encrypt)
(_gcry_cipher_ofb_decrypt): Use 'buf_xor' for buffer xoring and remove
resulting used variables.
* cipher/rijndael.c (_gry_aes_cfb_enc): Use 'buf_xor_2dst' for buffer
xoring and remove resulting unused variables.
(_gry_aes_cfb_dev): Use 'buf_xor_n_copy' for buffer xoring and remove
resulting unused variables.
(_gry_aes_cbc_enc, _gry_aes_ctr_enc, _gry_aes_cbc_dec): Use 'buf_xor'
for buffer xoring and remove resulting unused variables.
--

Add faster helper functions for buffer xoring and replace byte buffer xor
loops. This give following speed up. Note that CTR speed up is from refactoring
code to use buf_xor() and removal of integer division/modulo operations issued
per each processed byte. This removal of div/mod most likely gives even greater
speed increase on CPU architechtures that do not have hardware division unit.

Benchmark ratios (old-vs-new, AMD Phenom II, x86-64):

                ECB/Stream         CBC             CFB             OFB             CTR
             --------------- --------------- --------------- --------------- ---------------
IDEA            0.99x   1.01x   1.06x   1.02x   1.03x   1.06x   1.04x   1.02x   1.58x   1.58x
3DES            1.00x   1.00x   1.01x   1.01x   1.02x   1.02x   1.02x   1.01x   1.22x   1.23x
CAST5           0.98x   1.00x   1.09x   1.03x   1.09x   1.09x   1.07x   1.07x   1.98x   1.95x
BLOWFISH        1.00x   1.00x   1.18x   1.05x   1.07x   1.07x   1.05x   1.05x   1.93x   1.91x
AES             1.00x   0.98x   1.18x   1.14x   1.13x   1.13x   1.14x   1.14x   1.18x   1.18x
AES192          0.98x   1.00x   1.13x   1.14x   1.13x   1.10x   1.14x   1.16x   1.15x   1.15x
AES256          0.97x   1.02x   1.09x   1.13x   1.13x   1.09x   1.10x   1.14x   1.11x   1.13x
TWOFISH         1.00x   1.00x   1.15x   1.17x   1.18x   1.16x   1.18x   1.13x   2.37x   2.31x
ARCFOUR         1.03x   0.97x
DES             1.01x   1.00x   1.04x   1.04x   1.04x   1.05x   1.05x   1.02x   1.56x   1.55x
TWOFISH128      0.97x   1.03x   1.18x   1.17x   1.18x   1.15x   1.15x   1.15x   2.37x   2.31x
SERPENT128      1.00x   1.00x   1.10x   1.11x   1.08x   1.09x   1.08x   1.06x   1.66x   1.67x
SERPENT192      1.00x   1.00x   1.07x   1.08x   1.08x   1.09x   1.08x   1.08x   1.65x   1.66x
SERPENT256      1.00x   1.00x   1.09x   1.09x   1.08x   1.09x   1.08x   1.06x   1.66x   1.67x
RFC2268_40      1.03x   0.99x   1.05x   1.02x   1.03x   1.03x   1.04x   1.03x   1.46x   1.46x
SEED            1.00x   1.00x   1.10x   1.10x   1.09x   1.09x   1.10x   1.07x   1.80x   1.76x
CAMELLIA128     1.00x   1.00x   1.23x   1.12x   1.15x   1.17x   1.15x   1.12x   2.15x   2.13x
CAMELLIA192     1.05x   1.03x   1.23x   1.21x   1.21x   1.16x   1.12x   1.25x   1.90x   1.90x
CAMELLIA256     1.03x   1.07x   1.10x   1.19x   1.08x   1.14x   1.12x   1.10x   1.90x   1.92x

Benchmark ratios (old-vs-new, AMD Phenom II, i386):

                ECB/Stream         CBC             CFB             OFB             CTR
             --------------- --------------- --------------- --------------- ---------------
IDEA            1.00x   1.00x   1.04x   1.05x   1.04x   1.02x   1.02x   1.02x   1.38x   1.40x
3DES            1.01x   1.00x   1.02x   1.04x   1.03x   1.01x   1.00x   1.02x   1.20x   1.20x
CAST5           1.00x   1.00x   1.03x   1.09x   1.07x   1.04x   1.13x   1.00x   1.74x   1.74x
BLOWFISH        1.04x   1.08x   1.03x   1.13x   1.07x   1.12x   1.03x   1.00x   1.78x   1.74x
AES             0.96x   1.00x   1.09x   1.08x   1.14x   1.13x   1.07x   1.03x   1.14x   1.09x
AES192          1.00x   1.03x   1.07x   1.03x   1.07x   1.07x   1.06x   1.03x   1.08x   1.11x
AES256          1.00x   1.00x   1.06x   1.06x   1.10x   1.06x   1.05x   1.03x   1.10x   1.10x
TWOFISH         0.95x   1.10x   1.13x   1.23x   1.05x   1.14x   1.09x   1.13x   1.95x   1.86x
ARCFOUR         1.00x   1.00x
DES             1.02x   0.98x   1.04x   1.04x   1.05x   1.02x   1.04x   1.00x   1.45x   1.48x
TWOFISH128      0.95x   1.10x   1.26x   1.19x   1.09x   1.14x   1.17x   1.00x   2.00x   1.91x
SERPENT128      1.02x   1.00x   1.08x   1.04x   1.10x   1.06x   1.08x   1.04x   1.42x   1.42x
SERPENT192      1.02x   1.02x   1.06x   1.06x   1.10x   1.08x   1.04x   1.06x   1.42x   1.42x
SERPENT256      1.02x   0.98x   1.06x   1.06x   1.10x   1.06x   1.04x   1.06x   1.42x   1.40x
RFC2268_40      1.00x   1.00x   1.02x   1.06x   1.04x   1.02x   1.02x   1.02x   1.35x   1.35x
SEED            1.00x   0.97x   1.11x   1.05x   1.06x   1.08x   1.08x   1.05x   1.56x   1.57x
CAMELLIA128     1.03x   0.97x   1.12x   1.14x   1.06x   1.10x   1.06x   1.06x   1.73x   1.59x
CAMELLIA192     1.06x   1.00x   1.13x   1.10x   1.11x   1.11x   1.15x   1.08x   1.57x   1.58x
CAMELLIA256     1.06x   1.03x   1.10x   1.10x   1.11x   1.11x   1.13x   1.08x   1.57x   1.62x

[v2]:
 - include stdint.h only when it's available
 - use uintptr_t instead of long and intptr_t

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@mbnet.fi>

1 files changed, 179 insertions, 0 deletions

diff --git a/cipher/bufhelp.h b/cipher/bufhelp.h
new file mode 100644
index 00000000..a3be24a1
--- /dev/null
+++ b/cipher/bufhelp.h
@@ -0,0 +1,179 @@
+/* bufhelp.h  -  Some buffer manipulation helpers
+ *	Copyright © 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Libgcrypt is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser general Public License as
+ * published by the Free Software Foundation; either version 2.1 of
+ * the License, or (at your option) any later version.
+ *
+ * Libgcrypt is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ */
+#ifndef G10_BUFHELP_H
+#define G10_BUFHELP_H
+
+#ifdef HAVE_STDINT_H
+# include <stdint.h> /* uintptr_t */
+#else
+/* In this case, uintptr_t is provided by config.h. */
+#endif
+
+
+#if defined(__i386__) || defined(__x86_64__)
+/* These architechtures are able of unaligned memory accesses and can
+   handle those fast.
+ */
+# define BUFHELP_FAST_UNALIGNED_ACCESS 1
+#endif
+
+
+/* Optimized function for buffer xoring */
+static inline void
+buf_xor(void *_dst, const void *_src1, const void *_src2, size_t len)
+{
+  byte *dst = _dst;
+  const byte *src1 = _src1;
+  const byte *src2 = _src2;
+  uintptr_t *ldst;
+  const uintptr_t *lsrc1, *lsrc2;
+#ifndef BUFHELP_FAST_UNALIGNED_ACCESS
+  const unsigned int longmask = sizeof(uintptr_t) - 1;
+
+  /* Skip fast processing if alignment of buffers do not match.  */
+  if ((((uintptr_t)dst ^ (uintptr_t)src1) |
+       ((uintptr_t)dst ^ (uintptr_t)src2)) & longmask)
+    goto do_bytes;
+
+  /* Handle unaligned head.  */
+  for (; len && ((uintptr_t)dst & longmask); len--)
+      *dst++ = *src1++ ^ *src2++;
+#endif
+
+  ldst = (uintptr_t *)dst;
+  lsrc1 = (const uintptr_t *)src1;
+  lsrc2 = (const uintptr_t *)src2;
+
+  for (; len >= sizeof(uintptr_t); len -= sizeof(uintptr_t))
+    *ldst++ = *lsrc1++ ^ *lsrc2++;
+
+  dst = (byte *)ldst;
+  src1 = (const byte *)lsrc1;
+  src2 = (const byte *)lsrc2;
+
+#ifndef BUFHELP_FAST_UNALIGNED_ACCESS
+do_bytes:
+#endif
+  /* Handle tail.  */
+  for (; len; len--)
+    *dst++ = *src1++ ^ *src2++;
+}
+
+
+/* Optimized function for buffer xoring with two destination buffers.  Used
+   mainly by CFB mode encryption.  */
+static inline void
+buf_xor_2dst(void *_dst1, void *_dst2, const void *_src, size_t len)
+{
+  byte *dst1 = _dst1;
+  byte *dst2 = _dst2;
+  const byte *src = _src;
+  uintptr_t *ldst1, *ldst2;
+  const uintptr_t *lsrc;
+#ifndef BUFHELP_FAST_UNALIGNED_ACCESS
+  const unsigned int longmask = sizeof(uintptr_t) - 1;
+
+  /* Skip fast processing if alignment of buffers do not match.  */
+  if ((((uintptr_t)src ^ (uintptr_t)dst1) |
+       ((uintptr_t)src ^ (uintptr_t)dst2)) & longmask)
+    goto do_bytes;
+
+  /* Handle unaligned head.  */
+  for (; len && ((uintptr_t)src & longmask); len--)
+    *dst1++ = (*dst2++ ^= *src++);
+#endif
+
+  ldst1 = (uintptr_t *)dst1;
+  ldst2 = (uintptr_t *)dst2;
+  lsrc = (const uintptr_t *)src;
+
+  for (; len >= sizeof(uintptr_t); len -= sizeof(uintptr_t))
+    *ldst1++ = (*ldst2++ ^= *lsrc++);
+
+  dst1 = (byte *)ldst1;
+  dst2 = (byte *)ldst2;
+  src = (const byte *)lsrc;
+
+#ifndef BUFHELP_FAST_UNALIGNED_ACCESS
+do_bytes:
+#endif
+  /* Handle tail.  */
+  for (; len; len--)
+    *dst1++ = (*dst2++ ^= *src++);
+}
+
+
+/* Optimized function for combined buffer xoring and copying.  Used by mainly
+   CFB mode decryption.  */
+static inline void
+buf_xor_n_copy(void *_dst_xor, void *_srcdst_cpy, const void *_src, size_t len)
+{
+  byte *dst_xor = _dst_xor;
+  byte *srcdst_cpy = _srcdst_cpy;
+  byte temp;
+  const byte *src = _src;
+  uintptr_t *ldst_xor, *lsrcdst_cpy;
+  const uintptr_t *lsrc;
+  uintptr_t ltemp;
+#ifndef BUFHELP_FAST_UNALIGNED_ACCESS
+  const unsigned int longmask = sizeof(uintptr_t) - 1;
+
+  /* Skip fast processing if alignment of buffers do not match.  */
+  if ((((uintptr_t)src ^ (uintptr_t)dst_xor) |
+       ((uintptr_t)src ^ (uintptr_t)srcdst_cpy)) & longmask)
+    goto do_bytes;
+
+  /* Handle unaligned head.  */
+  for (; len && ((uintptr_t)src & longmask); len--)
+    {
+      temp = *src++;
+      *dst_xor++ = *srcdst_cpy ^ temp;
+      *srcdst_cpy++ = temp;
+    }
+#endif
+
+  ldst_xor = (uintptr_t *)dst_xor;
+  lsrcdst_cpy = (uintptr_t *)srcdst_cpy;
+  lsrc = (const uintptr_t *)src;
+
+  for (; len >= sizeof(uintptr_t); len -= sizeof(uintptr_t))
+    {
+      ltemp = *lsrc++;
+      *ldst_xor++ = *lsrcdst_cpy ^ ltemp;
+      *lsrcdst_cpy++ = ltemp;
+    }
+
+  dst_xor = (byte *)ldst_xor;
+  srcdst_cpy = (byte *)lsrcdst_cpy;
+  src = (const byte *)lsrc;
+
+#ifndef BUFHELP_FAST_UNALIGNED_ACCESS
+do_bytes:
+#endif
+  /* Handle tail.  */
+  for (; len; len--)
+    {
+      temp = *src++;
+      *dst_xor++ = *srcdst_cpy ^ temp;
+      *srcdst_cpy++ = temp;
+    }
+}
+
+#endif /*G10_BITHELP_H*/