[PATCH 13/13] crypto: x86/aria - yield FPU context only when needed

[Robert Elliott]

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.

During ctr mode, rather than break the processing into 256 byte
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.

Signed-off-by: Robert Elliott <elliott@xxxxxxx>
---
 arch/x86/crypto/aria_aesni_avx_glue.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/crypto/aria_aesni_avx_glue.c b/arch/x86/crypto/aria_aesni_avx_glue.c
index c561ea4fefa5..6657ce576e6c 100644
--- a/arch/x86/crypto/aria_aesni_avx_glue.c
+++ b/arch/x86/crypto/aria_aesni_avx_glue.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2022 Taehee Yoo <ap420073@xxxxxxxxx>
  */
 
+#include <asm/simd.h>
 #include <crypto/algapi.h>
 #include <crypto/internal/simd.h>
 #include <crypto/aria.h>
@@ -85,17 +86,19 @@ static int aria_avx_ctr_encrypt(struct skcipher_request *req)
 		const u8 *src = walk.src.virt.addr;
 		u8 *dst = walk.dst.virt.addr;
 
+		kernel_fpu_begin();
 		while (nbytes >= ARIA_AESNI_PARALLEL_BLOCK_SIZE) {
 			u8 keystream[ARIA_AESNI_PARALLEL_BLOCK_SIZE];
 
-			kernel_fpu_begin();
 			aria_ops.aria_ctr_crypt_16way(ctx, dst, src, keystream,
 						      walk.iv);
-			kernel_fpu_end();
 			dst += ARIA_AESNI_PARALLEL_BLOCK_SIZE;
 			src += ARIA_AESNI_PARALLEL_BLOCK_SIZE;
 			nbytes -= ARIA_AESNI_PARALLEL_BLOCK_SIZE;
+
+			kernel_fpu_yield();
 		}
+		kernel_fpu_end();
 
 		while (nbytes >= ARIA_BLOCK_SIZE) {
 			u8 keystream[ARIA_BLOCK_SIZE];
-- 
2.38.1