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.

diff --git a/ChangeLog b/ChangeLog
index 4e0d78851cb976de887d76452b5cb53ba99353ff..a7f0434e35e421c2c68e8a20cb8a927b2e50fb4e 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2017-01-30  H.J. Lu  <hongjiu.lu@intel.com>
+
+       [BZ #21081]
+       * sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S
+       (L(stosb)): Add VZEROUPPER before ret.
+
 2016-01-28  Carlos O'Donell  <carlos@redhat.com>
            Alexey Makhalov <amakhalov@vmware.com>
            Florian Weimer <fweimer@redhat.com>

diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S
index ff214f024376cd363f3a38b133789ff9f771a0c1..704eed9a3f400e9e0cd155ef9c9431e3515326b2 100644 (file)
--- 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