diff options
| author | Andy Polyakov <appro@openssl.org> | 2015-11-04 23:57:06 +0100 |
|---|---|---|
| committer | Andy Polyakov <appro@openssl.org> | 2015-11-16 13:07:33 +0100 |
| commit | 817ddb9fb07e78b451e838a77b2b272b0dd23e5f (patch) | |
| tree | 3802d1403b82136ffbce77c905f6217bc42377b0 /crypto/evp | |
| parent | f236ef27bd2ca99b3367554aa3e2fc9ca345deb5 (diff) | |
aesni-sha256-x86_64.pl: fix crash on AMD Jaguar.
It was also found that stich performs suboptimally on AMD Jaguar, hence
execution is limited to XOP-capable and Intel processors.
Reviewed-by: Kurt Roeckx <kurt@openssl.org>
(cherry picked from commit a5fd24d19bbb586b1c6d235c2021e9bead22c9f5)
Diffstat (limited to 'crypto/evp')
| -rw-r--r-- | crypto/evp/e_aes_cbc_hmac_sha256.c | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/crypto/evp/e_aes_cbc_hmac_sha256.c b/crypto/evp/e_aes_cbc_hmac_sha256.c index 028658bf81..37800213c7 100644 --- a/crypto/evp/e_aes_cbc_hmac_sha256.c +++ b/crypto/evp/e_aes_cbc_hmac_sha256.c @@ -498,7 +498,18 @@ static int aesni_cbc_hmac_sha256_cipher(EVP_CIPHER_CTX *ctx, iv = AES_BLOCK_SIZE; # if defined(STITCHED_CALL) + /* + * Assembly stitch handles AVX-capable processors, but its + * performance is not optimal on AMD Jaguar, ~40% worse, for + * unknown reasons. Incidentally processor in question supports + * AVX, but not AMD-specific XOP extension, which can be used + * to identify it and avoid stitch invocation. So that after we + * establish that current CPU supports AVX, we even see if it's + * either even XOP-capable Bulldozer-based or GenuineIntel one. + */ if (OPENSSL_ia32cap_P[1] & (1 << (60 - 32)) && /* AVX? */ + ((OPENSSL_ia32cap_P[1] & (1 << (43 - 32))) /* XOP? */ + | (OPENSSL_ia32cap_P[0] & (1<<30))) && /* "Intel CPU"? */ plen > (sha_off + iv) && (blocks = (plen - (sha_off + iv)) / SHA256_CBLOCK)) { SHA256_Update(&key->md, in + iv, sha_off); |