Commit 4ad096cc authored by Eric Biggers's avatar Eric Biggers Committed by Herbert Xu
Browse files

crypto: x86/nh-avx2 - add missing vzeroupper



Since nh_avx2() uses ymm registers, execute vzeroupper before returning
from it.  This is necessary to avoid reducing the performance of SSE
code.

Fixes: 0f961f9f ("crypto: x86/nhpoly1305 - add AVX2 accelerated NHPoly1305")
Signed-off-by: default avatarEric Biggers <ebiggers@google.com>
Acked-by: default avatarTim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: default avatarHerbert Xu <herbert@gondor.apana.org.au>
parent 8f0e0cf7
Loading
Loading
Loading
Loading
+1 −0
Original line number Diff line number Diff line
@@ -154,5 +154,6 @@ SYM_TYPED_FUNC_START(nh_avx2)
	vpaddq		T1, T0, T0
	vpaddq		T4, T0, T0
	vmovdqu		T0, (HASH)
	vzeroupper
	RET
SYM_FUNC_END(nh_avx2)