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.
(cherry picked from commit
02b78ff749f0c88771713368dbb2a09b1979814f)
+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.
+
2016-11-28 H.J. Lu <hongjiu.lu@intel.com>
[BZ #20750]
ENTRY (MEMSET_SYMBOL (__memset, erms))
# endif
L(stosb):
+ /* Issue vzeroupper before rep stosb. */
+ VZEROUPPER
movq %rdx, %rcx
movzbl %sil, %eax
movq %rdi, %rdx