From 57ce8a4e162599cf9adafef1f29763160a8e5564 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 5 Apr 2024 20:26:09 -0400 Subject: crypto: x86/sha256-avx2 - add missing vzeroupper Since sha256_transform_rorx() uses ymm registers, execute vzeroupper before returning from it. This is necessary to avoid reducing the performance of SSE code. Fixes: d34a460092d8 ("crypto: sha256 - Optimized sha256 x86_64 routine using AVX2's RORX instructions") Signed-off-by: Eric Biggers Acked-by: Tim Chen Signed-off-by: Herbert Xu --- arch/x86/crypto/sha256-avx2-asm.S | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/crypto') diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 9918212faf91..0ffb072be956 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -716,6 +716,7 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) popq %r13 popq %r12 popq %rbx + vzeroupper RET SYM_FUNC_END(sha256_transform_rorx) -- cgit v1.2.3