diff options
| author |   Ard Biesheuvel <ardb@kernel.org> | 2021-02-03 12:36:25 +0100 |
|---|---|---|
| committer |   Herbert Xu <herbert@gondor.apana.org.au> | 2021-02-10 17:55:58 +1100 |
| commit | fc754c024a343b836cfbb794afd3c7a87f625dbb (patch) | |
| tree | b8ac74fbba399721a116d8be67033e28bcfe8c45 /arch/arm64/crypto/crct10dif-ce-glue.c | |
| parent | crypto: arm64/aes-ce-mac - simplify NEON yield (diff) | |
| download | linux-dev-fc754c024a343b836cfbb794afd3c7a87f625dbb.tar.xz linux-dev-fc754c024a343b836cfbb794afd3c7a87f625dbb.zip | |
crypto: arm64/crc-t10dif - move NEON yield to C code
Instead of yielding from the bowels of the asm routine if a reschedule
is needed, divide up the input into 4 KB chunks in the C glue. This
simplifies the code substantially, and avoids scheduling out the task
with the asm routine on the call stack, which is undesirable from a
CFI/instrumentation point of view.
Signed-off-by: Ard Biesheuvel <ardb@kernel.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 | 30 |
1 files changed, 24 insertions, 6 deletions
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c index ccc3f6067742..09eb1456aed4 100644 --- a/arch/arm64/crypto/crct10dif-ce-glue.c +++ b/arch/arm64/crypto/crct10dif-ce-glue.c @@ -37,9 +37,18 @@ static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data, u16 *crc = shash_desc_ctx(desc); if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) { - kernel_neon_begin(); - *crc = crc_t10dif_pmull_p8(*crc, data, length); - kernel_neon_end(); + do { + unsigned int chunk = length; + + if (chunk > SZ_4K + CRC_T10DIF_PMULL_CHUNK_SIZE) + chunk = SZ_4K; + + kernel_neon_begin(); + *crc = crc_t10dif_pmull_p8(*crc, data, chunk); + kernel_neon_end(); + data += chunk; + length -= chunk; + } while (length); } else { *crc = crc_t10dif_generic(*crc, data, length); } @@ -53,9 +62,18 @@ static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data, u16 *crc = shash_desc_ctx(desc); if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) { - kernel_neon_begin(); - *crc = crc_t10dif_pmull_p64(*crc, data, length); - kernel_neon_end(); + do { + unsigned int chunk = length; + + if (chunk > SZ_4K + CRC_T10DIF_PMULL_CHUNK_SIZE) + chunk = SZ_4K; + + kernel_neon_begin(); + *crc = crc_t10dif_pmull_p64(*crc, data, chunk); + kernel_neon_end(); + data += chunk; + length -= chunk; + } while (length); } else { *crc = crc_t10dif_generic(*crc, data, length); } |