Optimize OCB offset calculation

* cipher/cipher-internal.h (ocb_get_l): New.
* cipher/cipher-ocb.c (_gcry_cipher_ocb_authenticate)
(ocb_crypt): Use 'ocb_get_l' instead of '_gcry_cipher_ocb_get_l'.
* cipher/camellia-glue.c (get_l): Remove.
(_gcry_camellia_ocb_crypt, _gcry_camellia_ocb_auth): Precalculate
offset array when block count matches parallel operation size; Use
'ocb_get_l' instead of 'get_l'.
* cipher/rijndael-aesni.c (get_l): Add fast path for 75% most common
offsets.
(aesni_ocb_enc, aesni_ocb_dec, _gcry_aes_aesni_ocb_auth): Precalculate
offset array when block count matches parallel operation size.
* cipher/rijndael-ssse3-amd64.c (get_l): Add fast path for 75% most
common offsets.
* cipher/rijndael.c (_gcry_aes_ocb_crypt, _gcry_aes_ocb_auth): Use
'ocb_get_l' instead of '_gcry_cipher_ocb_get_l'.
* cipher/serpent.c (get_l): Remove.
(_gcry_serpent_ocb_crypt, _gcry_serpent_ocb_auth): Precalculate
offset array when block count matches parallel operation size; Use
'ocb_get_l' instead of 'get_l'.
* cipher/twofish.c (get_l): Remove.
(_gcry_twofish_ocb_crypt, _gcry_twofish_ocb_auth): Use 'ocb_get_l'
instead of 'get_l'.
--

Patch optimizes OCB offset calculation for generic code and
assembly implementations with parallel block processing.

Benchmark of OCB AES-NI on Intel Haswell:

 $ tests/bench-slope --cpu-mhz 3201 cipher aes

 Before:
  AES            |  nanosecs/byte   mebibytes/sec   cycles/byte
         CTR enc |     0.274 ns/B    3483.9 MiB/s     0.876 c/B
         CTR dec |     0.273 ns/B    3490.0 MiB/s     0.875 c/B
         OCB enc |     0.289 ns/B    3296.1 MiB/s     0.926 c/B
         OCB dec |     0.299 ns/B    3189.9 MiB/s     0.957 c/B
        OCB auth |     0.260 ns/B    3670.0 MiB/s     0.832 c/B

 After:
  AES            |  nanosecs/byte   mebibytes/sec   cycles/byte
         CTR enc |     0.273 ns/B    3489.4 MiB/s     0.875 c/B
         CTR dec |     0.273 ns/B    3487.5 MiB/s     0.875 c/B
         OCB enc |     0.248 ns/B    3852.8 MiB/s     0.792 c/B
         OCB dec |     0.261 ns/B    3659.5 MiB/s     0.834 c/B
        OCB auth |     0.227 ns/B    4205.5 MiB/s     0.726 c/B

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

1 files changed, 6 insertions, 19 deletions

diff --git a/cipher/twofish.c b/cipher/twofish.c
index 11e60a74..7f361c99 100644
--- a/cipher/twofish.c
+++ b/cipher/twofish.c
@@ -1247,19 +1247,6 @@ _gcry_twofish_cfb_dec(void *context, unsigned char *iv, void *outbuf_arg,
   _gcry_burn_stack(burn_stack_depth);
 }
 
-#ifdef USE_AMD64_ASM
-static inline const unsigned char *
-get_l (gcry_cipher_hd_t c, unsigned char *l_tmp, u64 i)
-{
-  unsigned int ntz = _gcry_ctz64 (i);
-
-  if (ntz < OCB_L_TABLE_SIZE)
-      return c->u_mode.ocb.L[ntz];
-  else
-      return _gcry_cipher_ocb_get_l (c, l_tmp, i);
-}
-#endif
-
 /* Bulk encryption/decryption of complete blocks in OCB mode. */
 size_t
 _gcry_twofish_ocb_crypt (gcry_cipher_hd_t c, void *outbuf_arg,
@@ -1280,9 +1267,9 @@ _gcry_twofish_ocb_crypt (gcry_cipher_hd_t c, void *outbuf_arg,
     while (nblocks >= 3)
       {
 	/* l_tmp will be used only every 65536-th block. */
-	Ls[0] = get_l(c, l_tmp, blkn + 1);
-	Ls[1] = get_l(c, l_tmp, blkn + 2);
-	Ls[2] = get_l(c, l_tmp, blkn + 3);
+	Ls[0] = ocb_get_l(c, l_tmp, blkn + 1);
+	Ls[1] = ocb_get_l(c, l_tmp, blkn + 2);
+	Ls[2] = ocb_get_l(c, l_tmp, blkn + 3);
 	blkn += 3;
 
 	if (encrypt)
@@ -1339,9 +1326,9 @@ _gcry_twofish_ocb_auth (gcry_cipher_hd_t c, const void *abuf_arg,
     while (nblocks >= 3)
       {
 	/* l_tmp will be used only every 65536-th block. */
-	Ls[0] = get_l(c, l_tmp, blkn + 1);
-	Ls[1] = get_l(c, l_tmp, blkn + 2);
-	Ls[2] = get_l(c, l_tmp, blkn + 3);
+	Ls[0] = ocb_get_l(c, l_tmp, blkn + 1);
+	Ls[1] = ocb_get_l(c, l_tmp, blkn + 2);
+	Ls[2] = ocb_get_l(c, l_tmp, blkn + 3);
 	blkn += 3;
 
 	twofish_amd64_ocb_auth(ctx, abuf, c->u_mode.ocb.aad_offset,