diff options
| author | Ard Biesheuvel <ard.biesheuvel@linaro.org> | 2018-08-27 18:38:12 +0300 |
|---|---|---|
| committer | Herbert Xu <herbert@gondor.apana.org.au> | 2018-09-04 06:37:04 +0300 |
| commit | 2fffee536c6875bdf546cee0045fed8faa5ea51f (patch) | |
| tree | 6d98c7294ece7fbcb26770da27c236f179c12f05 /arch/arm64/crypto/crct10dif-ce-glue.c | |
| parent | 6c1b0da13e521fa5cb4a3541b991efb100aced35 (diff) | |
| download | linux-2fffee536c6875bdf546cee0045fed8faa5ea51f.tar.xz | |
crypto: arm64/crct10dif - implement non-Crypto Extensions alternative
The arm64 implementation of the CRC-T10DIF algorithm uses the 64x64 bit
polynomial multiplication instructions, which are optional in the
architecture, and if these instructions are not available, we fall back
to the C routine which is slow and inefficient.
So let's reuse the 64x64 bit PMULL alternative from the GHASH driver that
uses a sequence of ~40 instructions involving 8x8 bit PMULL and some
shifting and masking. This is a lot slower than the original, but it is
still twice as fast as the current [unoptimized] C code on Cortex-A53,
and it is time invariant and much easier on the D-cache.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/arm64/crypto/crct10dif-ce-glue.c')
| -rw-r--r-- | arch/arm64/crypto/crct10dif-ce-glue.c | 10 |
1 files changed, 8 insertions, 2 deletions
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c index 343a1e95b11a..b461d62023f2 100644 --- a/arch/arm64/crypto/crct10dif-ce-glue.c +++ b/arch/arm64/crypto/crct10dif-ce-glue.c @@ -23,6 +23,7 @@ #define CRC_T10DIF_PMULL_CHUNK_SIZE 16U asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 buf[], u64 len); +asmlinkage u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 buf[], u64 len); static u16 (*crc_t10dif_pmull)(u16 init_crc, const u8 buf[], u64 len); @@ -87,7 +88,10 @@ static struct shash_alg crc_t10dif_alg = { static int __init crc_t10dif_mod_init(void) { - crc_t10dif_pmull = crc_t10dif_pmull_p64; + if (elf_hwcap & HWCAP_PMULL) + crc_t10dif_pmull = crc_t10dif_pmull_p64; + else + crc_t10dif_pmull = crc_t10dif_pmull_p8; return crypto_register_shash(&crc_t10dif_alg); } @@ -97,8 +101,10 @@ static void __exit crc_t10dif_mod_exit(void) crypto_unregister_shash(&crc_t10dif_alg); } -module_cpu_feature_match(PMULL, crc_t10dif_mod_init); +module_cpu_feature_match(ASIMD, crc_t10dif_mod_init); module_exit(crc_t10dif_mod_exit); MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("crct10dif"); +MODULE_ALIAS_CRYPTO("crct10dif-arm64-ce"); |