@@ -146,17 +146,21 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
bytes <= CHACHA_BLOCK_SIZE)
return chacha_crypt_generic(state, dst, src, bytes, nrounds);
- do {
- unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+ kernel_fpu_begin();
+ for (;;) {
+ const unsigned int chunk = min(bytes, 4096U);
- kernel_fpu_begin();
- chacha_dosimd(state, dst, src, todo, nrounds);
- kernel_fpu_end();
+ chacha_dosimd(state, dst, src, chunk, nrounds);
- bytes -= todo;
- src += todo;
- dst += todo;
- } while (bytes);
+ bytes -= chunk;
+ if (!bytes)
+ break;
+
+ src += chunk;
+ dst += chunk;
+ kernel_fpu_yield();
+ }
+ kernel_fpu_end();
}
EXPORT_SYMBOL(chacha_crypt_arch);
The x86 assembly language implementations using SIMD process data between kernel_fpu_begin() and kernel_fpu_end() calls. That disables scheduler preemption, so prevents the CPU core from being used by other threads. Rather than break the processing into 4 KiB passes, each of which unilaterally calls kernel_fpu_begin() and kernel_fpu_end(), periodically check if the kernel scheduler wants to run something else on the CPU. If so, yield the kernel FPU context and let the scheduler intervene. Suggested-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Robert Elliott <elliott@hpe.com> --- arch/x86/crypto/chacha_glue.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-)