qiurui
/
glibc
mirror of git://sourceware.org/git/glibc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
glibc/sysdeps/x86_64
History
Jiamei Xie 96f1804a0d
x86: fix wmemset ifunc stray '!' (bug 33542) 
The ifunc selector for wmemset had a stray '!' in the
X86_ISA_CPU_FEATURES_ARCH_P(...) check:

  if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX2)
      && X86_ISA_CPU_FEATURES_ARCH_P (cpu_features,
                                      AVX_Fast_Unaligned_Load, !))

This effectively negated the predicate and caused the AVX2/AVX512
paths to be skipped, making the dispatcher fall back to the SSE2
implementation even on CPUs where AVX2/AVX512 are available. The
regression leads to noticeable throughput loss for wmemset.

Remove the stray '!' so the AVX_Fast_Unaligned_Load capability is
tested as intended and the correct AVX2/EVEX variants are selected.

Impact:
- On AVX2/AVX512-capable x86_64, wmemset no longer incorrectly
  falls back to SSE2; perf now shows __wmemset_evex/avx2 variants.

Testing:
- benchtests/bench-wmemset shows improved bandwidth across sizes.
- perf confirm the selected symbol is no longer SSE2.

Signed-off-by: xiejiamei <xiejiamei@hygon.com>
Signed-off-by: Li jing <lijing@hygon.cn>
Reviewed-by: Adhemerval Zanella  <adhemerval.zanella@linaro.org>
(cherry picked from commit 4d86b6cdd8)
 		2025-11-04 12:23:06 +00:00
..
64
…
fpu Apply the Makefile sorting fix 2025-08-20 06:11:54 -07:00
htl
…
multiarch x86: fix wmemset ifunc stray '!' (bug 33542) 2025-11-04 12:23:06 +00:00
nptl x86/cet: Sync with Linux kernel 6.6 shadow stack interface 2025-08-19 15:39:23 -07:00
sys
…
x32 x86-64: Remove sysdeps/x86_64/x32/dl-machine.h 2025-08-19 18:11:21 -07:00
Implies
…
Makefile i386: Also add GLIBC_ABI_GNU2_TLS version [BZ #33129] 2025-08-20 15:11:09 -07:00
Versions i386: Also add GLIBC_ABI_GNU2_TLS version [BZ #33129] 2025-08-20 15:11:09 -07:00
____longjmp_chk.S
…
__longjmp.S x86-64/cet: Check the restore token in longjmp 2025-08-19 15:39:23 -07:00
_mcount.S
…
abort-instr.h
…
add_n.S
…
addmul_1.S
…
bsd-_setjmp.S
…
bsd-setjmp.S
…
check-cet.awk x86-64/cet: Move check-cet.awk to x86_64 2025-08-19 15:39:23 -07:00
configure x86-64: Update _dl_tlsdesc_dynamic to preserve AMX registers 2025-08-19 18:22:00 -07:00
configure.ac x86-64: Update _dl_tlsdesc_dynamic to preserve AMX registers 2025-08-19 18:22:00 -07:00
crti.S
…
crtn.S
…
dl-cache.h
…
dl-cet.c x86-64/cet: Move dl-cet.[ch] to x86_64 directories 2025-08-19 15:39:23 -07:00
dl-hwcaps-subdirs.c
…
dl-irel.h
…
dl-machine.h x86: Update _dl_tlsdesc_dynamic to preserve caller-saved registers 2025-08-19 18:22:00 -07:00
dl-procinfo.c x86: Update _dl_tlsdesc_dynamic to preserve caller-saved registers 2025-08-19 18:22:00 -07:00
dl-procruntime.c i386: Remove CET support bits 2025-08-19 15:39:23 -07:00
dl-runtime.h
…
dl-tls.c elf: Support recursive use of dynamic TLS in interposed malloc 2025-01-10 16:49:38 -08:00
dl-tls.h
…
dl-tlsdesc-dynamic.h x86: Use separate variable for TLSDESC XSAVE/XSAVEC state size (bug 32810) 2025-08-20 06:14:48 -07:00
dl-tlsdesc.S x86-64: Don't use SSE resolvers for ISA level 3 or above 2025-10-17 08:04:28 +08:00
dl-tlsdesc.h
…
dl-trampoline-state.h x86: Update _dl_tlsdesc_dynamic to preserve caller-saved registers 2025-08-19 18:22:00 -07:00
dl-trampoline.S i386: Update ___tls_get_addr to preserve vector registers 2025-08-20 11:09:07 -07:00
dl-trampoline.h x86: Update _dl_tlsdesc_dynamic to preserve caller-saved registers 2025-08-19 18:22:00 -07:00
feature-control.h i386: Remove CET support bits 2025-08-19 15:39:23 -07:00
ffs.c
…
ffsll.c
…
ifuncmain8.c
…
ifuncmod8.c
…
isa-default-impl.h
…
isa.h
…
jmpbuf-offsets.h
…
jmpbuf-unwind.h
…
l10nflist.c
…
ldsodefs.h i386: Remove CET support bits 2025-08-19 15:39:23 -07:00
link-defines.sym
…
locale-defines.sym
…
localplt.data
…
lshift.S
…
machine-gmon.h
…
memchr.S
…
memcmp-isa-default-impl.h
…
memcmp.S
…
memcmpeq.S
…
memcpy.S
…
memcpy_chk.S
…
memmove.S
…
memmove_chk.S
…
mempcpy.S
…
mempcpy_chk.S
…
memrchr.S
…
memset.S
…
memset_chk.S
…
mp_clz_tab.c
…
mul_1.S
…
preconfigure
…
preconfigure.ac
…
rawmemchr.S
…
rshift.S
…
rtld-offsets.sym
…
setjmp.S
…
stackguard-macros.h
…
stackinfo.h
…
start.S
…
stpcpy.S
…
stpncpy.S
…
strcasecmp.S
…
strcasecmp_l-nonascii.c
…
strcasecmp_l.S
…
strcat.S
…
strchr-isa-default-impl.h
…
strchr.S
…
strchrnul.S
…
strcmp.S
…
strcpy.S
…
strcspn-generic.c
…
strcspn.c
…
strlen.S
…
strncase.S
…
strncase_l-nonascii.c
…
strncase_l.S
…
strncat.S
…
strncmp.S
…
strncpy.S
…
strnlen.S
…
strpbrk-generic.c
…
strpbrk.c
…
strrchr.S
…
strspn-generic.c
…
strspn.c
…
sub_n.S
…
submul_1.S
…
sysdep.h i386: Remove CET support 2025-08-19 06:29:04 -07:00
tls_get_addr.S
…
tlsdesc.c
…
tlsdesc.sym
…
tst-audit.h
…
tst-audit3.c
…
tst-audit4-aux.c
…
tst-audit4.c
…
tst-audit5.c
…
tst-audit6.c
…
tst-audit7.c
…
tst-audit10-aux.c
…
tst-audit10.c
…
tst-auditmod3a.c
…
tst-auditmod3b.c
…
tst-auditmod4a.c
…
tst-auditmod4b.c
…
tst-auditmod5a.c
…
tst-auditmod5b.c
…
tst-auditmod6a.c
…
tst-auditmod6b.c
…
tst-auditmod6c.c
…
tst-auditmod7a.c
…
tst-auditmod7b.c
…
tst-auditmod10a.c
…
tst-auditmod10b.c
…
tst-avx-aux.c
…
tst-avx.c
…
tst-avx512-aux.c
…
tst-avx512.c
…
tst-avx512mod.c
…
tst-avxmod.c
…
tst-cet-legacy-1.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-1a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-2.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-2a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-3.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-4.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-4a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-4b.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-4c.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-5.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-5a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-5b.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-6.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-6a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-6b.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-7.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-8.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-9-static.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-9.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-10-static.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-10.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-10a-static.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-10a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-1.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-2.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-4.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-5.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-5a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-5b.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-5c.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-6.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-6a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-6b.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-6c.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-cet-legacy-mod-6d.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-glibc-hwcaps.c
…
tst-gnu2-tls2mod1.S x86-64: Allocate state buffer space for RDI, RSI and RBX 2025-08-19 18:22:00 -07:00
tst-platform-1.c
…
tst-platformmod-1.c
…
tst-platformmod-2.c
…
tst-quad1.c
…
tst-quad1pie.c
…
tst-quad2.c
…
tst-quad2pie.c
…
tst-quadmod1.S
…
tst-quadmod1pie.S
…
tst-quadmod2.S
…
tst-quadmod2pie.S
…
tst-rsi-strlen.c
…
tst-rsi-wcslen.c
…
tst-shstk-legacy-1-extra.S x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1a-static.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1a.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1b-static.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1b.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1c-static.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1c.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1d-static.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1d.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1e-static.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1e-static.sh x86/cet: fix shadow stack test scripts 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1e.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1e.sh x86/cet: fix shadow stack test scripts 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1f.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1g.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-1g.sh x86/cet: fix shadow stack test scripts 2025-08-19 15:39:23 -07:00
tst-shstk-legacy-mod-1.c x86: Move CET infrastructure to x86_64 2025-08-19 15:39:23 -07:00
tst-split-dynreloc.c
…
tst-split-dynreloc.lds
…
tst-sse.c
…
tst-ssemod.c
…
varshift.c
…
wcpcpy-generic.c
…
wcpcpy.S
…
wcpncpy-generic.c
…
wcpncpy.S
…
wcscat-generic.c
…
wcscat.S
…
wcschr.S
…
wcscmp.S
…
wcscpy-generic.c
…
wcscpy.S
…
wcslen.S
…
wcsncat-generic.c
…
wcsncat.S
…
wcsncmp-generic.c
…
wcsncmp.S
…
wcsncpy-generic.c
…
wcsncpy.S
…
wcsnlen-generic.c
…
wcsnlen.S
…
wcsrchr.S
…
wmemchr.S
…
wmemcmp.S
…
wmemset.S
…
wmemset_chk.S
…
wordcopy.c
…
x86-lp_size.h
…