[0/8] x86-64: Avoid RTM abort inside a RTM region

Message ID 20210305165316.323467-1-hjl.tools@gmail.com
Headers
Series x86-64: Avoid RTM abort inside a RTM region |

Message

H.J. Lu March 5, 2021, 4:53 p.m. UTC
  Since VZEROUPPER triggers RTM abort inside a transactionally executing
RTM region, avoid VZEROUPPER inside a RTM region in string/memory
functions:

1. Turn on Prefer_No_VZEROUPPER for processors with RTM.
2. Select functions optimized with 256-bit EVEX instructions using
YMM16-YMM31 registers, which don't need VZEROUPPER at function exit.
3. Select AVX optimized string/memory functions with

	xtest
	jz	1f
	vzeroall
	ret
1:
	vzeroupper
	ret

at function exit on processors with RTM, but without 256-bit EVEX
instructions.
4. Since to compare 2 32-byte strings, 256-bit EVEX strcmp requires 2
loads, 3 VPCMPs and 2 KORDs while AVX2 strcmp requires 1 load, 2 VPCMPEQs,
1 VPMINU and 1 VPMOVMSKB, AVX2 strcmp is faster than EVEX strcmp.  Add
Prefer_AVX2_STRCMP to prefer AVX2 strcmp family functions.
5. Add tests to verify that string/memory functions won't cause RTM abort
in RTM region.

H.J. Lu (8):
  x86: Set Prefer_No_VZEROUPPER and add Prefer_AVX2_STRCMP
  x86-64: Add ifunc-avx2.h functions with 256-bit EVEX
  x86-64: Add strcpy family functions with 256-bit EVEX
  x86-64: Add memmove family functions with 256-bit EVEX
  x86-64: Add memset family functions with 256-bit EVEX
  x86-64: Add memcmp family functions with 256-bit EVEX
  x86-64: Add AVX optimized string/memory functions for RTM
  x86: Add string/memory function tests in RTM region

 sysdeps/x86/Makefile                          |   23 +
 sysdeps/x86/cpu-features.c                    |   20 +-
 sysdeps/x86/cpu-tunables.c                    |    2 +
 ...cpu-features-preferred_feature_index_1.def |    1 +
 sysdeps/x86/tst-memchr-rtm.c                  |   54 +
 sysdeps/x86/tst-memcmp-rtm.c                  |   52 +
 sysdeps/x86/tst-memmove-rtm.c                 |   53 +
 sysdeps/x86/tst-memrchr-rtm.c                 |   54 +
 sysdeps/x86/tst-memset-rtm.c                  |   45 +
 sysdeps/x86/tst-strchr-rtm.c                  |   54 +
 sysdeps/x86/tst-strcpy-rtm.c                  |   53 +
 sysdeps/x86/tst-string-rtm.h                  |   72 ++
 sysdeps/x86/tst-strlen-rtm.c                  |   53 +
 sysdeps/x86/tst-strncmp-rtm.c                 |   52 +
 sysdeps/x86/tst-strrchr-rtm.c                 |   53 +
 sysdeps/x86_64/multiarch/Makefile             |   58 +-
 sysdeps/x86_64/multiarch/ifunc-avx2.h         |   18 +-
 sysdeps/x86_64/multiarch/ifunc-impl-list.c    |  339 ++++++
 sysdeps/x86_64/multiarch/ifunc-memcmp.h       |   17 +-
 sysdeps/x86_64/multiarch/ifunc-memmove.h      |   33 +-
 sysdeps/x86_64/multiarch/ifunc-memset.h       |   35 +-
 sysdeps/x86_64/multiarch/ifunc-strcpy.h       |   17 +-
 sysdeps/x86_64/multiarch/ifunc-wmemset.h      |   18 +-
 sysdeps/x86_64/multiarch/memchr-avx2-rtm.S    |   12 +
 sysdeps/x86_64/multiarch/memchr-avx2.S        |   45 +-
 sysdeps/x86_64/multiarch/memchr-evex.S        |  381 ++++++
 .../x86_64/multiarch/memcmp-avx2-movbe-rtm.S  |   12 +
 sysdeps/x86_64/multiarch/memcmp-avx2-movbe.S  |   28 +-
 sysdeps/x86_64/multiarch/memcmp-evex-movbe.S  |  440 +++++++
 .../memmove-avx-unaligned-erms-rtm.S          |   17 +
 .../multiarch/memmove-evex-unaligned-erms.S   |   26 +
 .../multiarch/memmove-vec-unaligned-erms.S    |   57 +-
 sysdeps/x86_64/multiarch/memrchr-avx2-rtm.S   |   12 +
 sysdeps/x86_64/multiarch/memrchr-avx2.S       |   53 +-
 sysdeps/x86_64/multiarch/memrchr-evex.S       |  337 ++++++
 .../memset-avx2-unaligned-erms-rtm.S          |   10 +
 .../multiarch/memset-avx2-unaligned-erms.S    |   12 +-
 .../multiarch/memset-evex-unaligned-erms.S    |   24 +
 .../multiarch/memset-vec-unaligned-erms.S     |   61 +-
 sysdeps/x86_64/multiarch/rawmemchr-avx2-rtm.S |    4 +
 sysdeps/x86_64/multiarch/rawmemchr-evex.S     |    4 +
 sysdeps/x86_64/multiarch/stpcpy-avx2-rtm.S    |    3 +
 sysdeps/x86_64/multiarch/stpcpy-evex.S        |    3 +
 sysdeps/x86_64/multiarch/stpncpy-avx2-rtm.S   |    4 +
 sysdeps/x86_64/multiarch/stpncpy-evex.S       |    4 +
 sysdeps/x86_64/multiarch/strcat-avx2-rtm.S    |   12 +
 sysdeps/x86_64/multiarch/strcat-avx2.S        |    6 +-
 sysdeps/x86_64/multiarch/strcat-evex.S        |  283 +++++
 sysdeps/x86_64/multiarch/strchr-avx2-rtm.S    |   12 +
 sysdeps/x86_64/multiarch/strchr-avx2.S        |   28 +-
 sysdeps/x86_64/multiarch/strchr-evex.S        |  335 ++++++
 sysdeps/x86_64/multiarch/strchr.c             |   17 +-
 sysdeps/x86_64/multiarch/strchrnul-avx2-rtm.S |    3 +
 sysdeps/x86_64/multiarch/strchrnul-evex.S     |    3 +
 sysdeps/x86_64/multiarch/strcmp-avx2-rtm.S    |   12 +
 sysdeps/x86_64/multiarch/strcmp-avx2.S        |   55 +-
 sysdeps/x86_64/multiarch/strcmp-evex.S        | 1043 +++++++++++++++++
 sysdeps/x86_64/multiarch/strcmp.c             |   19 +-
 sysdeps/x86_64/multiarch/strcpy-avx2-rtm.S    |   12 +
 sysdeps/x86_64/multiarch/strcpy-avx2.S        |   85 +-
 sysdeps/x86_64/multiarch/strcpy-evex.S        | 1007 ++++++++++++++++
 sysdeps/x86_64/multiarch/strlen-avx2-rtm.S    |   12 +
 sysdeps/x86_64/multiarch/strlen-avx2.S        |   43 +-
 sysdeps/x86_64/multiarch/strlen-evex.S        |  436 +++++++
 sysdeps/x86_64/multiarch/strncat-avx2-rtm.S   |    3 +
 sysdeps/x86_64/multiarch/strncat-evex.S       |    3 +
 sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S   |    3 +
 sysdeps/x86_64/multiarch/strncmp-evex.S       |    3 +
 sysdeps/x86_64/multiarch/strncmp.c            |   19 +-
 sysdeps/x86_64/multiarch/strncpy-avx2-rtm.S   |    3 +
 sysdeps/x86_64/multiarch/strncpy-evex.S       |    3 +
 sysdeps/x86_64/multiarch/strnlen-avx2-rtm.S   |    4 +
 sysdeps/x86_64/multiarch/strnlen-evex.S       |    4 +
 sysdeps/x86_64/multiarch/strrchr-avx2-rtm.S   |   12 +
 sysdeps/x86_64/multiarch/strrchr-avx2.S       |   19 +-
 sysdeps/x86_64/multiarch/strrchr-evex.S       |  265 +++++
 sysdeps/x86_64/multiarch/wcschr-avx2-rtm.S    |    3 +
 sysdeps/x86_64/multiarch/wcschr-evex.S        |    3 +
 sysdeps/x86_64/multiarch/wcscmp-avx2-rtm.S    |    4 +
 sysdeps/x86_64/multiarch/wcscmp-evex.S        |    4 +
 sysdeps/x86_64/multiarch/wcslen-avx2-rtm.S    |    4 +
 sysdeps/x86_64/multiarch/wcslen-evex.S        |    4 +
 sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S   |    5 +
 sysdeps/x86_64/multiarch/wcsncmp-evex.S       |    5 +
 sysdeps/x86_64/multiarch/wcsnlen-avx2-rtm.S   |    5 +
 sysdeps/x86_64/multiarch/wcsnlen-evex.S       |    5 +
 sysdeps/x86_64/multiarch/wcsnlen.c            |   18 +-
 sysdeps/x86_64/multiarch/wcsrchr-avx2-rtm.S   |    3 +
 sysdeps/x86_64/multiarch/wcsrchr-evex.S       |    3 +
 sysdeps/x86_64/multiarch/wmemchr-avx2-rtm.S   |    4 +
 sysdeps/x86_64/multiarch/wmemchr-evex.S       |    4 +
 .../x86_64/multiarch/wmemcmp-avx2-movbe-rtm.S |    4 +
 sysdeps/x86_64/multiarch/wmemcmp-evex-movbe.S |    4 +
 sysdeps/x86_64/sysdep.h                       |   22 +
 94 files changed, 6295 insertions(+), 298 deletions(-)
 create mode 100644 sysdeps/x86/tst-memchr-rtm.c
 create mode 100644 sysdeps/x86/tst-memcmp-rtm.c
 create mode 100644 sysdeps/x86/tst-memmove-rtm.c
 create mode 100644 sysdeps/x86/tst-memrchr-rtm.c
 create mode 100644 sysdeps/x86/tst-memset-rtm.c
 create mode 100644 sysdeps/x86/tst-strchr-rtm.c
 create mode 100644 sysdeps/x86/tst-strcpy-rtm.c
 create mode 100644 sysdeps/x86/tst-string-rtm.h
 create mode 100644 sysdeps/x86/tst-strlen-rtm.c
 create mode 100644 sysdeps/x86/tst-strncmp-rtm.c
 create mode 100644 sysdeps/x86/tst-strrchr-rtm.c
 create mode 100644 sysdeps/x86_64/multiarch/memchr-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/memchr-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/memcmp-avx2-movbe-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/memcmp-evex-movbe.S
 create mode 100644 sysdeps/x86_64/multiarch/memmove-avx-unaligned-erms-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/memmove-evex-unaligned-erms.S
 create mode 100644 sysdeps/x86_64/multiarch/memrchr-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/memrchr-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/memset-avx2-unaligned-erms-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/memset-evex-unaligned-erms.S
 create mode 100644 sysdeps/x86_64/multiarch/rawmemchr-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/rawmemchr-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/stpcpy-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/stpcpy-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/stpncpy-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/stpncpy-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strcat-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strcat-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strchr-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strchr-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strchrnul-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strchrnul-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strcmp-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strcmp-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strcpy-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strcpy-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strlen-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strlen-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strncat-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strncat-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strncmp-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strncmp-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strncpy-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strncpy-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strnlen-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strnlen-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/strrchr-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/strrchr-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/wcschr-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/wcschr-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/wcscmp-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/wcscmp-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/wcslen-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/wcslen-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/wcsncmp-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/wcsncmp-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/wcsnlen-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/wcsnlen-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/wcsrchr-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/wcsrchr-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/wmemchr-avx2-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/wmemchr-evex.S
 create mode 100644 sysdeps/x86_64/multiarch/wmemcmp-avx2-movbe-rtm.S
 create mode 100644 sysdeps/x86_64/multiarch/wmemcmp-evex-movbe.S