From 02b78ff749f0c88771713368dbb2a09b1979814f Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Mon, 30 Jan 2017 10:59:15 -0800 Subject: Add VZEROUPPER to memset-vec-unaligned-erms.S [BZ #21081] Since memset-vec-unaligned-erms.S has VDUP_TO_VEC0_AND_SET_RETURN at function entry, memset optimized for AVX2 and AVX512 will always use ymm/zmm register. VZEROUPPER should be placed before ret in L(stosb): movq %rdx, %rcx movzbl %sil, %eax movq %rdi, %rdx rep stosb movq %rdx, %rax ret since it can be reached from L(stosb_more_2x_vec): cmpq $REP_STOSB_THRESHOLD, %rdx ja L(stosb) [BZ #21081] * sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S (L(stosb)): Add VZEROUPPER before ret. --- ChangeLog | 6 ++++++ sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S | 2 ++ 2 files changed, 8 insertions(+) diff --git a/ChangeLog b/ChangeLog index 4e0d78851c..a7f0434e35 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +2017-01-30 H.J. Lu + + [BZ #21081] + * sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S + (L(stosb)): Add VZEROUPPER before ret. + 2016-01-28 Carlos O'Donell Alexey Makhalov Florian Weimer diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S index ff214f0243..704eed9a3f 100644 --- a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S +++ b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S @@ -110,6 +110,8 @@ ENTRY (__memset_erms) ENTRY (MEMSET_SYMBOL (__memset, erms)) # endif L(stosb): + /* Issue vzeroupper before rep stosb. */ + VZEROUPPER movq %rdx, %rcx movzbl %sil, %eax movq %rdi, %rdx -- cgit 1.4.1