From b39d0d661752860633b67409d94e30525eba0ff3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 5 Apr 2024 20:26:10 -0400
Subject: [PATCH] crypto: x86/sha512-avx2 - add missing vzeroupper

[ Upstream commit 6a24fdfe1edbafacdacd53516654d99068f20eec ]

Since sha512_transform_rorx() uses ymm registers, execute vzeroupper
before returning from it.  This is necessary to avoid reducing the
performance of SSE code.

Fixes: e01d69cb0195 ("crypto: sha512 - Optimized SHA512 x86_64 assembly routine using AVX instructions.")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/crypto/sha512-avx2-asm.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index f08496cd6870..24973f42c43f 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -680,6 +680,7 @@ SYM_TYPED_FUNC_START(sha512_transform_rorx)
 	pop	%r12
 	pop	%rbx
 
+	vzeroupper
 	RET
 SYM_FUNC_END(sha512_transform_rorx)