Optimize AES-ECB mode in OpenSSL for both aarch64 and aarch32

Aes-ecb mode can be optimized by inverleaving cipher operation on
several blocks and loop unrolling. Interleaving needs one ideal
unrolling factor, here we adopt the same factor with aes-cbc,
which is described as below:
    If blocks number > 5, select 5 blocks as one iteration,every
    loop, decrease the blocks number by 5.
    If 3 < left blocks < 5 select 3 blocks as one iteration, every
    loop, decrease the block number by 3.
    If left blocks < 3, treat them as tail blocks.
Detailed implementation will have a little adjustment for squeezing
code space.
With this way, for small size such as 16 bytes, the performance is
similar as before, but for big size such as 16k bytes, the performance
improves a lot, even reaches to 100%, for some arches such as A57,
the improvement  even exceeds 100%. The following table will list the
encryption performance data on aarch64, take a72 and a57 as examples.
Performance value takes the unit of cycles per byte, takes the format
as comparision of values. List them as below:

A72:
                            Before optimization     After optimization  Improve
evp-aes-128-ecb@16          17.26538237             16.82663866         2.61%
evp-aes-128-ecb@64          5.50528499              5.222637557         5.41%
evp-aes-128-ecb@256         2.632700213             1.908442892         37.95%
evp-aes-128-ecb@1024        1.876102047             1.078018868         74.03%
evp-aes-128-ecb@8192        1.6550392               0.853982929         93.80%
evp-aes-128-ecb@16384       1.636871283             0.847623957         93.11%
evp-aes-192-ecb@16          17.73104961             17.09692468         3.71%
evp-aes-192-ecb@64          5.78984398              5.418545192         6.85%
evp-aes-192-ecb@256         2.872005308             2.081815274         37.96%
evp-aes-192-ecb@1024        2.083226672             1.25095642          66.53%
evp-aes-192-ecb@8192        1.831992057             0.995916251         83.95%
evp-aes-192-ecb@16384       1.821590009             0.993820525         83.29%
evp-aes-256-ecb@16          18.0606306              17.96963317         0.51%
evp-aes-256-ecb@64          6.19651997              5.762465812         7.53%
evp-aes-256-ecb@256         3.176991394             2.24642538          41.42%
evp-aes-256-ecb@1024        2.385991919             1.396018192         70.91%
evp-aes-256-ecb@8192        2.147862636             1.142222597         88.04%
evp-aes-256-ecb@16384       2.131361787             1.135944617         87.63%

A57:
                            Before optimization     After optimization  Improve
evp-aes-128-ecb@16          18.61045121             18.36456218         1.34%
evp-aes-128-ecb@64          6.438628994             5.467959461         17.75%
evp-aes-128-ecb@256         2.957452881             1.97238604          49.94%
evp-aes-128-ecb@1024        2.117096219             1.099665054         92.52%
evp-aes-128-ecb@8192        1.868385973             0.837440804         123.11%
evp-aes-128-ecb@16384       1.853078526             0.822420027         125.32%
evp-aes-192-ecb@16          19.07021756             18.50018552         3.08%
evp-aes-192-ecb@64          6.672351486             5.696088921         17.14%
evp-aes-192-ecb@256         3.260427769             2.131449916         52.97%
evp-aes-192-ecb@1024        2.410522832             1.250529718         92.76%
evp-aes-192-ecb@8192        2.17921605              0.973225504         123.92%
evp-aes-192-ecb@16384       2.162250997             0.95919871          125.42%
evp-aes-256-ecb@16          19.3008384              19.12743654         0.91%
evp-aes-256-ecb@64          6.992950658             5.92149541          18.09%
evp-aes-256-ecb@256         3.576361743             2.287619504         56.34%
evp-aes-256-ecb@1024        2.726671027             1.381267599         97.40%
evp-aes-256-ecb@8192        2.493583657             1.110959913         124.45%
evp-aes-256-ecb@16384       2.473916816             1.099967073         124.91%

Change-Id: Iccd23d972e0d52d22dc093f4c208f69c9d5a0ca7

Reviewed-by: Shane Lontis <shane.lontis@oracle.com>
Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/10518)

2 files changed, 8 insertions, 0 deletions

diff --git a/include/crypto/ciphermode_platform.h b/include/crypto/ciphermode_platform.h
index b1868e1a6d..03afd719af 100644
--- a/include/crypto/ciphermode_platform.h
+++ b/include/crypto/ciphermode_platform.h
@@ -89,6 +89,7 @@ void AES_xts_decrypt(const unsigned char *inp, unsigned char *out, size_t len,
 #    define HWAES_encrypt aes_v8_encrypt
 #    define HWAES_decrypt aes_v8_decrypt
 #    define HWAES_cbc_encrypt aes_v8_cbc_encrypt
+#    define HWAES_ecb_encrypt aes_v8_ecb_encrypt
 #    define HWAES_ctr32_encrypt_blocks aes_v8_ctr32_encrypt_blocks
 #   endif
 #  endif
@@ -411,6 +412,9 @@ void HWAES_decrypt(const unsigned char *in, unsigned char *out,
 void HWAES_cbc_encrypt(const unsigned char *in, unsigned char *out,
                        size_t length, const AES_KEY *key,
                        unsigned char *ivec, const int enc);
+void HWAES_ecb_encrypt(const unsigned char *in, unsigned char *out,
+                       size_t length, const AES_KEY *key,
+                       const int enc);
 void HWAES_ctr32_encrypt_blocks(const unsigned char *in, unsigned char *out,
                                 size_t len, const AES_KEY *key,
                                 const unsigned char ivec[16]);
diff --git a/include/openssl/modes.h b/include/openssl/modes.h
index 1c672d2a46..e19079912b 100644
--- a/include/openssl/modes.h
+++ b/include/openssl/modes.h
@@ -29,6 +29,10 @@ typedef void (*cbc128_f) (const unsigned char *in, unsigned char *out,
                           size_t len, const void *key,
                           unsigned char ivec[16], int enc);
 
+typedef void (*ecb128_f) (const unsigned char *in, unsigned char *out,
+                          size_t len, const void *key,
+                          int enc);
+
 typedef void (*ctr128_f) (const unsigned char *in, unsigned char *out,
                           size_t blocks, const void *key,
                           const unsigned char ivec[16]);