linux/crypto
Tianjia Zhang 5b2efa2bb8 crypto: x86/sm4 - add AES-NI/AVX2/x86_64 implementation
Like the implementation of AESNI/AVX, this patch adds an accelerated
implementation of AESNI/AVX2. In terms of code implementation, by
reusing AESNI/AVX mode-related codes, the amount of code is greatly
reduced. From the benchmark data, it can be seen that when the block
size is 1024, compared to AVX acceleration, the performance achieved
by AVX2 has increased by about 70%, it is also 7.7 times of the pure
software implementation of sm4-generic.

The main algorithm implementation comes from SM4 AES-NI work by
libgcrypt and Markku-Juhani O. Saarinen at:
https://github.com/mjosaarinen/sm4ni

This optimization supports the four modes of SM4, ECB, CBC, CFB,
and CTR. Since CBC and CFB do not support multiple block parallel
encryption, the optimization effect is not obvious.

Benchmark on Intel i5-6200U 2.30GHz, performance data of three
implementation methods, pure software sm4-generic, aesni/avx
acceleration, and aesni/avx2 acceleration, the data comes from
the 218 mode and 518 mode of tcrypt. The abscissas are blocks of
different lengths. The data is tabulated and the unit is Mb/s:

block-size  |    16      64     128     256    1024    1420    4096
sm4-generic
    ECB enc | 60.94   70.41   72.27   73.02   73.87   73.58   73.59
    ECB dec | 61.87   70.53   72.15   73.09   73.89   73.92   73.86
    CBC enc | 56.71   66.31   68.05   69.84   70.02   70.12   70.24
    CBC dec | 54.54   65.91   68.22   69.51   70.63   70.79   70.82
    CFB enc | 57.21   67.24   69.10   70.25   70.73   70.52   71.42
    CFB dec | 57.22   64.74   66.31   67.24   67.40   67.64   67.58
    CTR enc | 59.47   68.64   69.91   71.02   71.86   71.61   71.95
    CTR dec | 59.94   68.77   69.95   71.00   71.84   71.55   71.95
sm4-aesni-avx
    ECB enc | 44.95  177.35  292.06  316.98  339.48  322.27  330.59
    ECB dec | 45.28  178.66  292.31  317.52  339.59  322.52  331.16
    CBC enc | 57.75   67.68   69.72   70.60   71.48   71.63   71.74
    CBC dec | 44.32  176.83  284.32  307.24  328.61  312.61  325.82
    CFB enc | 57.81   67.64   69.63   70.55   71.40   71.35   71.70
    CFB dec | 43.14  167.78  282.03  307.20  328.35  318.24  325.95
    CTR enc | 42.35  163.32  279.11  302.93  320.86  310.56  317.93
    CTR dec | 42.39  162.81  278.49  302.37  321.11  310.33  318.37
sm4-aesni-avx2
    ECB enc | 45.19  177.41  292.42  316.12  339.90  322.53  330.54
    ECB dec | 44.83  178.90  291.45  317.31  339.85  322.55  331.07
    CBC enc | 57.66   67.62   69.73   70.55   71.58   71.66   71.77
    CBC dec | 44.34  176.86  286.10  501.68  559.58  483.87  527.46
    CFB enc | 57.43   67.60   69.61   70.52   71.43   71.28   71.65
    CFB dec | 43.12  167.75  268.09  499.33  558.35  490.36  524.73
    CTR enc | 42.42  163.39  256.17  493.95  552.45  481.58  517.19
    CTR dec | 42.49  163.11  256.36  493.34  552.62  481.49  516.83

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2021-08-27 16:30:18 +08:00
..
asymmetric_keys x509: Add OID for NIST P384 and extend parser for it 2021-03-26 19:41:59 +11:00
async_tx async_xor: check src_offs is not NULL before updating it 2021-06-10 19:40:14 -07:00
842.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 157 2019-05-30 11:26:37 -07:00
acompress.c crypto: api - permit users to specify numa node of acomp hardware 2020-07-09 18:25:23 +10:00
adiantum.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
aead.c crypto: algapi - enforce that all instances have a ->free() method 2020-01-09 11:30:58 +08:00
aegis128-core.c crypto: aegis128 - Move simd prototypes into aegis.h 2021-03-19 21:59:45 +11:00
aegis128-neon-inner.c crypto: aegis128/neon - move final tag check to SIMD domain 2020-11-27 17:13:40 +11:00
aegis128-neon.c crypto: aegis128 - Move simd prototypes into aegis.h 2021-03-19 21:59:45 +11:00
aegis.h crypto: aegis128 - Move simd prototypes into aegis.h 2021-03-19 21:59:45 +11:00
aes_generic.c crypto: remove CRYPTO_TFM_RES_BAD_KEY_LEN 2020-01-09 11:30:53 +08:00
aes_ti.c crypto: aes - create AES library based on the fixed time AES code 2019-07-26 14:55:33 +10:00
af_alg.c crypto: af_alg - use DIV_ROUND_UP helper macro for calculations 2021-06-03 20:24:04 +08:00
ahash.c crypto: ahash - Add init_tfm/exit_tfm 2020-08-28 16:58:28 +10:00
akcipher.c crypto: algapi - enforce that all instances have a ->free() method 2020-01-09 11:30:58 +08:00
algapi.c crypto: api - remove CRYPTOA_U32 and related functions 2021-06-17 15:07:31 +08:00
algboss.c crypto: api - remove CRYPTOA_U32 and related functions 2021-06-17 15:07:31 +08:00
algif_aead.c crypto: algif_aead - Do not set MAY_BACKLOG on the async path 2020-08-21 14:45:27 +10:00
algif_hash.c net: make ->{get,set}sockopt in proto_ops optional 2020-07-19 18:16:41 -07:00
algif_rng.c crypto: af_alg - add extra parameters for DRBG interface 2020-09-25 17:48:52 +10:00
algif_skcipher.c crypto: algif_skcipher - EBUSY on aio should be an error 2020-08-21 14:45:26 +10:00
ansi_cprng.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
anubis.c crypto: remove CRYPTO_TFM_RES_BAD_KEY_LEN 2020-01-09 11:30:53 +08:00
api.c crypto: api - check for ERR pointers in crypto_destroy_tfm() 2021-03-13 00:04:01 +11:00
arc4.c crypto: arc4 - mark ecb(arc4) skcipher as obsolete 2020-09-11 14:39:16 +10:00
authenc.c crypto: algapi - use common mechanism for inheriting flags 2020-07-16 21:49:08 +10:00
authencesn.c crypto: algapi - use common mechanism for inheriting flags 2020-07-16 21:49:08 +10:00
blake2b_generic.c crypto: blake2b - update file comment 2021-01-03 08:41:39 +11:00
blake2s_generic.c crypto: blake2s - share the "shash" API boilerplate code 2021-01-03 08:41:38 +11:00
blowfish_common.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
blowfish_generic.c crypto: blowfish - use unaligned accessors instead of alignmask 2021-02-10 17:55:56 +11:00
camellia_generic.c crypto: camellia - use unaligned accessors instead of alignmask 2021-02-10 17:55:56 +11:00
cast5_generic.c crypto: cast5 - use unaligned accessors instead of alignmask 2021-02-10 17:55:56 +11:00
cast6_generic.c crypto: cast6 - use unaligned accessors instead of alignmask 2021-02-10 17:55:56 +11:00
cast_common.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 44 2019-05-24 17:27:12 +02:00
cbc.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
ccm.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
cfb.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
chacha20poly1305.c crypto: algapi - use common mechanism for inheriting flags 2020-07-16 21:49:08 +10:00
chacha_generic.c crypto: chacha_generic - remove unnecessary setkey() functions 2019-11-22 18:48:39 +08:00
cipher.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
cmac.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
compress.c crypto: compress - remove crt_u.compress (struct compress_tfm) 2019-12-11 16:37:01 +08:00
crc32_generic.c crypto: crc32-generic - Use SPDX-License-Identifier 2021-04-16 21:24:27 +10:00
crc32c_generic.c crypto: crc32c_generic - delete and fix duplicated words 2020-08-21 14:45:25 +10:00
crct10dif_common.c
crct10dif_generic.c crypto: crct10dif_generic - fix duplicated words 2020-08-21 14:45:25 +10:00
cryptd.c crypto: algapi - use common mechanism for inheriting flags 2020-07-16 21:49:08 +10:00
crypto_engine.c crypto: engine - delete duplicated word 2020-08-21 14:45:26 +10:00
crypto_null.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2019-07-08 20:57:08 -07:00
crypto_user_base.c crypto: algapi - make unregistration functions return void 2019-12-20 14:58:35 +08:00
crypto_user_stat.c crypto: skcipher - remove the "blkcipher" algorithm type 2019-11-01 13:38:32 +08:00
ctr.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
cts.c crypto: algapi - use common mechanism for inheriting flags 2020-07-16 21:49:08 +10:00
curve25519-generic.c crypto: curve25519 - implement generic KPP driver 2019-11-17 09:02:43 +08:00
deflate.c mm, treewide: rename kzfree() to kfree_sensitive() 2020-08-07 11:33:22 -07:00
des_generic.c crypto: remove CRYPTO_TFM_RES_WEAK_KEY 2020-01-09 11:30:53 +08:00
dh_helper.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
dh.c crypto: dh - SP800-56A rev 3 local public key validation 2020-07-31 18:08:59 +10:00
drbg.c crypto: DRBG - switch to HMAC SHA512 DRBG as default DRBG 2021-05-28 15:11:45 +08:00
ecb.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
ecc_curve_defs.h Merge branch 'ecc' 2021-03-26 19:55:55 +11:00
ecc.c crypto: ecc - Correct an error in the comments 2021-03-26 20:15:56 +11:00
ecc.h crypto: ecc - handle unaligned input buffer in ecc_swap_digits 2021-07-30 10:58:36 +08:00
ecdh_helper.c crypto: ecdh - move curve_id of ECDH from the key to algorithm name 2021-03-13 00:04:03 +11:00
ecdh.c crypto: ecdh - register NIST P384 tfm 2021-05-28 15:11:47 +08:00
ecdsa.c crypto: ecdsa - Register NIST P384 and extend test suite 2021-03-26 19:41:58 +11:00
ecdsasignature.asn1 crypto: ecdsa - Add support for ECDSA signature verification 2021-03-26 19:41:58 +11:00
echainiv.c crypto: geniv - remove unneeded arguments from aead_geniv_alloc() 2020-07-16 21:49:07 +10:00
ecrdsa_defs.h crypto: ecrdsa - add EC-RDSA (GOST 34.10) algorithm 2019-04-18 22:15:02 +08:00
ecrdsa_params.asn1 crypto: ecrdsa - add EC-RDSA (GOST 34.10) algorithm 2019-04-18 22:15:02 +08:00
ecrdsa_pub_key.asn1 crypto: ecrdsa - add EC-RDSA (GOST 34.10) algorithm 2019-04-18 22:15:02 +08:00
ecrdsa.c crypto: algapi - Remove skbuff.h inclusion 2020-08-20 14:04:28 +10:00
essiv.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
fcrypt.c crypto: fcrypt - Remove 'do while(0)' loop for single statement macro 2021-04-02 18:28:13 +11:00
fips.c crypto: fips - add FIPS test failure notification chain 2019-07-26 14:51:57 +10:00
gcm.c mm, treewide: rename kzfree() to kfree_sensitive() 2020-08-07 11:33:22 -07:00
geniv.c crypto: algapi - use common mechanism for inheriting flags 2020-07-16 21:49:08 +10:00
gf128mul.c mm, treewide: rename kzfree() to kfree_sensitive() 2020-08-07 11:33:22 -07:00
ghash-generic.c crypto: remove CRYPTO_TFM_RES_BAD_KEY_LEN 2020-01-09 11:30:53 +08:00
hash_info.c crypto: rename sm3-256 to sm3 in hash_algo_name 2020-02-18 07:35:49 -05:00
hmac.c crypto: algapi - use common mechanism for inheriting flags 2020-07-16 21:49:08 +10:00
internal.h crypto: api - Move crypto attr definitions out of crypto.h 2021-06-24 14:51:35 +08:00
jitterentropy-kcapi.c crypto: algapi - Remove skbuff.h inclusion 2020-08-20 14:04:28 +10:00
jitterentropy.c crypto: jitterentropy - Put constants on the right side of the expression 2021-03-26 20:02:35 +11:00
jitterentropy.h crypto: jitter - add header to fix buildwarnings 2019-10-18 18:49:40 +11:00
Kconfig crypto: x86/sm4 - add AES-NI/AVX2/x86_64 implementation 2021-08-27 16:30:18 +08:00
keywrap.c crypto: keywrap - Remove else after break statement 2021-04-02 18:28:13 +11:00
khazad.c crypto: khazad,wp512 - remove leading spaces before tabs 2021-05-28 15:11:44 +08:00
kpp.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
lrw.c crypto: Replace HTTP links with HTTPS ones 2020-07-23 17:34:20 +10:00
lz4.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2019-07-08 20:57:08 -07:00
lz4hc.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2019-07-08 20:57:08 -07:00
lzo-rle.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2019-07-08 20:57:08 -07:00
lzo.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2019-07-08 20:57:08 -07:00
Makefile crypto: rmd320 - remove rmd320 in Makefile 2021-08-27 16:30:18 +08:00
md4.c crypto: make all generic algorithms set cra_driver_name 2019-06-13 14:31:39 +08:00
md5.c crypto: md5 - remove unused macros 2020-02-28 08:43:21 +08:00
memneq.c
michael_mic.c crypto: michael_mic - fix broken misalignment handling 2021-02-10 17:55:55 +11:00
nhpoly1305.c crypto: poly1305 - add new 32 and 64-bit generic versions 2020-01-16 15:18:12 +08:00
ofb.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
pcbc.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
pcrypt.c padata: fold padata_alloc_possible() into padata_alloc() 2020-07-23 17:34:18 +10:00
poly1305_generic.c crypto: poly1305 - add new 32 and 64-bit generic versions 2020-01-16 15:18:12 +08:00
proc.c crypto: proc - Removing some useless only space lines 2020-09-25 17:48:15 +10:00
ripemd.h crypto: rmd320 - remove RIPE-MD 320 hash algorithm 2021-01-29 16:07:04 +11:00
rmd160.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2019-07-08 20:57:08 -07:00
rng.c crypto: rng - fix crypto_rng_reset() refcounting when !CRYPTO_STATS 2021-04-02 18:28:12 +11:00
rsa_helper.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
rsa-pkcs1pad.c crypto: algapi - Remove skbuff.h inclusion 2020-08-20 14:04:28 +10:00
rsa.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 36 2019-05-24 17:27:11 +02:00
rsaprivkey.asn1
rsapubkey.asn1
scatterwalk.c treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
scompress.c crypto: algapi - make unregistration functions return void 2019-12-20 14:58:35 +08:00
seed.c crypto: seed - remove trailing semicolon in macro definition 2020-12-04 18:13:16 +11:00
seqiv.c mm, treewide: rename kzfree() to kfree_sensitive() 2020-08-07 11:33:22 -07:00
serpent_generic.c crypto: serpent - Fix sparse byte order warnings 2021-03-07 15:13:15 +11:00
sha1_generic.c crypto: sha - split sha.h into sha1.h and sha2.h 2020-11-20 14:45:33 +11:00
sha3_generic.c crypto: Replace HTTP links with HTTPS ones 2020-07-23 17:34:20 +10:00
sha256_generic.c crypto: sha - split sha.h into sha1.h and sha2.h 2020-11-20 14:45:33 +11:00
sha512_generic.c crypto: sha - split sha.h into sha1.h and sha2.h 2020-11-20 14:45:33 +11:00
shash.c crypto: shash - avoid comparing pointers to exported functions under CFI 2021-06-17 15:07:31 +08:00
simd.c crypto: algapi - use common mechanism for inheriting flags 2020-07-16 21:49:08 +10:00
skcipher.c crypto: skcipher - in_irq() cleanup 2021-08-21 15:44:58 +08:00
sm2.c crypto: sm2 - fix a memory leak in sm2 2021-06-11 15:03:30 +08:00
sm2signature.asn1 crypto: sm2 - introduce OSCCA SM2 asymmetric cipher algorithm 2020-09-25 17:48:54 +10:00
sm3_generic.c crypto: sm3 - export crypto_sm3_final function 2020-09-25 17:48:53 +10:00
sm4_generic.c crypto: arm64/sm4-ce - Make dependent on sm4 library instead of sm4-generic 2021-07-30 10:58:30 +08:00
streebog_generic.c crypto: streebog - remove two unused variables 2019-08-15 21:52:14 +10:00
tcrypt.c crypto: tcrypt - add GCM/CCM mode test for SM4 algorithm 2021-08-21 15:44:57 +08:00
tcrypt.h crypto: tcrypt - Add support for hash speed testing with keys 2020-08-21 14:45:27 +10:00
tea.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2019-07-08 20:57:08 -07:00
testmgr.c crypto: testmgr - Add GCM/CCM mode test of SM4 algorithm 2021-08-21 15:44:57 +08:00
testmgr.h crypto: testmgr - Add GCM/CCM mode test of SM4 algorithm 2021-08-21 15:44:57 +08:00
twofish_common.c crypto: remove CRYPTO_TFM_RES_BAD_KEY_LEN 2020-01-09 11:30:53 +08:00
twofish_generic.c crypto: twofish - use unaligned accessors instead of alignmask 2021-02-10 17:55:57 +11:00
vmac.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
wp512.c crypto: wp512 - correct a non-kernel-doc comment 2021-08-12 19:32:17 +08:00
xcbc.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
xor.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2021-02-21 17:23:56 -08:00
xts.c crypto: remove cipher routines from public crypto API 2021-01-03 08:41:35 +11:00
xxhash_generic.c crypto: remove CRYPTO_TFM_RES_BAD_KEY_LEN 2020-01-09 11:30:53 +08:00
zstd.c mm, treewide: rename kzfree() to kfree_sensitive() 2020-08-07 11:33:22 -07:00