Skip to content

Introduce cmpxchg128() -- aka. the demise of cmpxchg_double()

Peter Zijlstra linux-arch linux-crypto linux-doc linux-iommu linux-mm linux-parisc linux-s390 lkml llvm 1 version Applied

Status from this message: The following commit has been merged into the locking/core branch of tip:

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest12 patches 6 repliesApplied

Since v3 from the cover letter

- unbreak everything that does *NOT* have cmpxchg128()

Patches in v1 Applied

#Subject and filesSizeRepliesApplied
1/12cyrpto/b128ops: Remove struct u128include/crypto/b128ops.h+3 -110 replies
2/12types: Introduce [us]128include/linux/types.h include/uapi/linux/types.h lib/crypto/curve25519-hacl64.c +1 more+9 -40 replies
3/12arch: Introduce arch_{,try_}_cmpxchg128{,_local}()arch/arm64/include/asm/atomic_ll_sc.h arch/arm64/include/asm/atomic_lse.h arch/arm64/include/asm/cmpxchg.h +3 more+177 -20 replies
4/12instrumentation: Wire up cmpxchg128()include/linux/atomic/atomic-arch-fallback.h include/linux/atomic/atomic-instrumented.h scripts/atomic/gen-atomic-fallback.sh +1 more+183 -60 replies
5/12percpu: Add {raw,this}_cpu_try_cmpxchg()include/asm-generic/percpu.h include/linux/percpu-defs.h+128 -43 replies
6/12percpu: Wire up cmpxchg128arch/arm64/include/asm/percpu.h arch/s390/include/asm/percpu.h arch/x86/include/asm/percpu.h +4 more+240 -390 replies
7/12percpu: #ifndef __SIZEOF_INT128__include/asm-generic/percpu.h include/linux/types.h+63 -017 replies
8/12x86,amd_iommu: Replace cmpxchg_double()drivers/iommu/amd/amd_iommu_types.h drivers/iommu/amd/iommu.c+11 -80 replies
9/12x86,intel_iommu: Replace cmpxchg_double()drivers/iommu/intel/irq_remapping.c include/linux/dmar.h+68 -650 replies
10/12slub: Replace cmpxchg_double()include/linux/slub_def.h mm/slab.h mm/slub.c+137 -670 replies
11/12arch: Remove cmpxchg_doubleDocumentation/core-api/this_cpu_ops.rst arch/arm64/include/asm/atomic_ll_sc.h arch/arm64/include/asm/atomic_lse.h +12 more+5 -3710 replies
12/12s390/cpum_sf: Convert to cmpxchg128()arch/s390/include/asm/cpu_mf.h arch/s390/kernel/perf_cpum_sf.c+4 -140 replies

Reviews trailers per patch

10 of 12 patches have a Reviewed-by or Acked-by of their own; the series has one for all of them.

PatchArnd BergmannHeiko CarstensHerbert XuMark RutlandVlastimil BabkaHyeonggon YooLu BaoluVasant HegdeHelge Deller
SeriesR-b T-b
1/12R-b A-b
2/12R-b A-b
3/12R-b A-b A-b
4/12R-b A-b
5/12
6/12
7/12T-b A-b
8/12R-b T-b
9/12R-b R-b
10/12R-b A-b A-b
11/12R-b A-b
12/12R-b A-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 9 reviewers.

Read the v1 thread

Cover letter [PATCH 00/12] Introduce cmpxchg128() -- aka. the demise of cmpxchg_double()

Hi!

After much breaking of things, find here the improved version.

Since v3:

- unbreak everything that does *NOT* have cmpxchg128()

Notably this_cpu_cmpxchg_double() is used unconditionally by SLUB which means that this_cpu_try_cmpxchg128() needs to be unconditionally available on all 64bit architectures.

- fixed up x86/x86_64 cmpxchg{8,16}b emulation for this_cpu_cmpxchg{64,128}()

- introduce {raw,this}_cpu_try_cmpxchg*()

- add fallback for !__SIZEOF_INT128__ 64bit architectures

Sadly there are supported 64bit architecture/compiler combinations that do not have __SIZEOF_INT128__, specifically it was found that HPPA64 only added this with GCC-11.

this is yuck, and ideally we'd simply raise compiler requirements, but this 'works'.

My plan is to re-add this to tip/locking/core and thus -next later this week.

Also available at:

git://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git locking/core

---
 Documentation/core-api/this_cpu_ops.rst     |   2 -
 arch/arm64/include/asm/atomic_ll_sc.h       |  56 +++---
 arch/arm64/include/asm/atomic_lse.h         |  39 ++---
 arch/arm64/include/asm/cmpxchg.h            |  48 ++----
 arch/arm64/include/asm/percpu.h             |  30 ++--
 arch/s390/include/asm/cmpxchg.h             |  32 +---
 arch/s390/include/asm/cpu_mf.h              |   2 +-
 arch/s390/include/asm/percpu.h              |  34 ++--
 arch/s390/kernel/perf_cpum_sf.c             |  16 +-
 arch/x86/include/asm/cmpxchg.h              |  25 ---
 arch/x86/include/asm/cmpxchg_32.h           |   2 +-
 arch/x86/include/asm/cmpxchg_64.h           |  63 ++++++-
 arch/x86/include/asm/percpu.h               | 102 ++++++-----
 arch/x86/lib/Makefile                       |   3 +-
 arch/x86/lib/cmpxchg16b_emu.S               |  43 +++--
 arch/x86/lib/cmpxchg8b_emu.S                |  67 ++++++--
 drivers/iommu/amd/amd_iommu_types.h         |   9 +-
 drivers/iommu/amd/iommu.c                   |  10 +-
 drivers/iommu/intel/irq_remapping.c         |   8 +-
 include/asm-generic/percpu.h                | 257 ++++++++++++++++++++++------
 include/crypto/b128ops.h                    |  14 +-
 include/linux/atomic/atomic-arch-fallback.h |  95 +++++++++-
 include/linux/atomic/atomic-instrumented.h  |  93 ++++++++--
 include/linux/dmar.h                        | 125 +++++++-------
 include/linux/percpu-defs.h                 |  45 ++---
 include/linux/slub_def.h                    |  12 +-
 include/linux/types.h                       |  12 ++
 include/uapi/linux/types.h                  |   4 +
 lib/crypto/curve25519-hacl64.c              |   2 -
 lib/crypto/poly1305-donna64.c               |   2 -
 mm/slab.h                                   |  53 +++++-
 mm/slub.c                                   | 139 +++++++++------
 scripts/atomic/gen-atomic-fallback.sh       |   4 +-
 scripts/atomic/gen-atomic-instrumented.sh   |  19 +-
 34 files changed, 952 insertions(+), 515 deletions(-)