diff options
| author | Allan Jude <allanjude@FreeBSD.org> | 2021-11-19 15:14:30 +0000 |
|---|---|---|
| committer | Allan Jude <allanjude@FreeBSD.org> | 2021-11-22 18:12:20 +0000 |
| commit | 32a2fed6e71f896266d4c695754104d82a72c60d (patch) | |
| tree | bb7390fa6d2befcb41792e1f6c2499ef59f8a3c6 | |
| parent | d16fbc488e604d5bad295c2951aa67da885a62f5 (diff) | |
| download | src-32a2fed6e71f896266d4c695754104d82a72c60d.tar.gz src-32a2fed6e71f896266d4c695754104d82a72c60d.zip | |
openssl: Fix detection of ARMv7 and ARM64 CPU features
OpenSSL assumes the same value for AT_HWCAP=16 (Linux)
So it ends up calling elf_auxv_info() with AT_CANARY which
returns ENOENT, and all acceleration features are disabled.
With this, my ARM64 test machine runs the benchmark
`openssl speed -evp aes-256-gcm` nearly 20x faster
going from 100 MB/sec to 2000 MB/sec
It also improves sha256 from 300 MB/sec to 1800 MB/sec
This fix has been accepted but not yet merged upstream:
https://github.com/openssl/openssl/pull/17082
PR: 259937
Reviewed by: manu, imp
MFC after: immediate
Relnotes: yes
Fixes: 88e852c0b5c872b1a ("OpenSSL: Merge OpenSSL 1.1.1j")
Sponsored by: Ampere Computing LLC
Sponsored by: Klara Inc.
Differential Revision: https://reviews.freebsd.org/D33060
(cherry picked from commit d9bb798725cfce9c72b80440659b48e8668eb10d)
| -rw-r--r-- | crypto/openssl/crypto/armcap.c | 15 |
1 files changed, 9 insertions, 6 deletions
diff --git a/crypto/openssl/crypto/armcap.c b/crypto/openssl/crypto/armcap.c index c5685bde5891..48c5d4d64e32 100644 --- a/crypto/openssl/crypto/armcap.c +++ b/crypto/openssl/crypto/armcap.c @@ -106,20 +106,23 @@ static unsigned long getauxval(unsigned long key) * ARM puts the feature bits for Crypto Extensions in AT_HWCAP2, whereas * AArch64 used AT_HWCAP. */ +# ifndef AT_HWCAP +# define AT_HWCAP 16 +# endif +# ifndef AT_HWCAP2 +# define AT_HWCAP2 26 +# endif # if defined(__arm__) || defined (__arm) -# define HWCAP 16 - /* AT_HWCAP */ +# define HWCAP AT_HWCAP # define HWCAP_NEON (1 << 12) -# define HWCAP_CE 26 - /* AT_HWCAP2 */ +# define HWCAP_CE AT_HWCAP2 # define HWCAP_CE_AES (1 << 0) # define HWCAP_CE_PMULL (1 << 1) # define HWCAP_CE_SHA1 (1 << 2) # define HWCAP_CE_SHA256 (1 << 3) # elif defined(__aarch64__) -# define HWCAP 16 - /* AT_HWCAP */ +# define HWCAP AT_HWCAP # define HWCAP_NEON (1 << 1) # define HWCAP_CE HWCAP |