Linux kernel stable tree
Go to file
Mateusz Guzik f5fe24ef17 lockref: stop doing cpu_relax in the cmpxchg loop
On the x86-64 architecture even a failing cmpxchg grants exclusive
access to the cacheline, making it preferable to retry the failed op
immediately instead of stalling with the pause instruction.

To illustrate the impact, below are benchmark results obtained by
running various will-it-scale tests on top of the 6.2-rc3 kernel and
Cascade Lake (2 sockets * 24 cores * 2 threads) CPU.

All results in ops/s.  Note there is some variance in re-runs, but the
code is consistently faster when contention is present.

  open3 ("Same file open/close"):
  proc          stock       no-pause
     1         805603         814942       (+%1)
     2        1054980        1054781       (-0%)
     8        1544802        1822858      (+18%)
    24        1191064        2199665      (+84%)
    48         851582        1469860      (+72%)
    96         609481        1427170     (+134%)

  fstat2 ("Same file fstat"):
  proc          stock       no-pause
     1        3013872        3047636       (+1%)
     2        4284687        4400421       (+2%)
     8        3257721        5530156      (+69%)
    24        2239819        5466127     (+144%)
    48        1701072        5256609     (+209%)
    96        1269157        6649326     (+423%)

Additionally, a kernel with a private patch to help access() scalability:
access2 ("Same file access"):

  proc          stock        patched      patched
                                         +nopause
    24        2378041        2005501      5370335  (-15% / +125%)

That is, fixing the problems in access itself *reduces* scalability
after the cacheline ping-pong only happens in lockref with the pause
instruction.

Note that fstat and access benchmarks are not currently integrated into
will-it-scale, but interested parties can find them in pull requests to
said project.

Code at hand has a rather tortured history.  First modification showed
up in commit d472d9d98b ("lockref: Relax in cmpxchg loop"), written
with Itanium in mind.  Later it got patched up to use an arch-dependent
macro to stop doing it on s390 where it caused a significant regression.
Said macro had undergone revisions and was ultimately eliminated later,
going back to cpu_relax.

While I intended to only remove cpu_relax for x86-64, I got the
following comment from Linus:

    I would actually prefer just removing it entirely and see if
    somebody else hollers. You have the numbers to prove it hurts on
    real hardware, and I don't think we have any numbers to the
    contrary.

    So I think it's better to trust the numbers and remove it as a
    failure, than say "let's just remove it on x86-64 and leave
    everybody else with the potentially broken code"

Additionally, Will Deacon (maintainer of the arm64 port, one of the
architectures previously benchmarked):

    So, from the arm64 side of the fence, I'm perfectly happy just
    removing the cpu_relax() calls from lockref.

As such, come back full circle in history and whack it altogether.

Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://lore.kernel.org/all/CAGudoHHx0Nqg6DE70zAVA75eV-HXfWyhVMWZ-aSeOofkA_=WdA@mail.gmail.com/
Acked-by: Tony Luck <tony.luck@intel.com> # ia64
Acked-by: Nicholas Piggin <npiggin@gmail.com> # powerpc
Acked-by: Will Deacon <will@kernel.org> # arm64
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2023-01-13 14:35:38 -06:00
arch First batch of EFI fixes for v6.2: 2023-01-13 10:37:10 -06:00
block block-2023-01-06 2023-01-06 13:12:42 -08:00
certs certs: make system keyring depend on built-in x509 parser 2022-09-24 04:31:18 +09:00
crypto This update includes the following changes: 2022-12-14 12:31:09 -08:00
Documentation Three documentation fixes (or rather two and one warning): 2023-01-13 10:35:26 -06:00
drivers First batch of EFI fixes for v6.2: 2023-01-13 10:37:10 -06:00
fs arm64 fixes for -rc4 2023-01-13 07:11:45 -06:00
include First batch of EFI fixes for v6.2: 2023-01-13 10:37:10 -06:00
init gcc: disable -Warray-bounds for gcc-11 too 2023-01-09 17:04:49 -06:00
io_uring io_uring: fix CQ waiting timeout handling 2023-01-05 08:04:47 -07:00
ipc Non-MM patches for 6.2-rc1. 2022-12-12 17:28:58 -08:00
kernel - Fix various DocBook formatting errors in kernel/time/ that 2023-01-12 16:53:39 -06:00
lib lockref: stop doing cpu_relax in the cmpxchg loop 2023-01-13 14:35:38 -06:00
LICENSES LICENSES: Add the copyleft-next-0.3.1 license 2022-11-08 15:44:01 +01:00
mm memblock: Fix doc for memblock_phys_free 2023-01-04 12:31:22 +02:00
net Including fixes from rxrpc. 2023-01-12 18:20:44 -06:00
rust rust: types: add Opaque type 2022-12-04 01:59:16 +01:00
samples Char/Misc driver changes for 6.2-rc1 2022-12-16 03:49:24 -08:00
scripts kbuild: readd -w option when vmlinux.o or Module.symver is missing 2023-01-05 16:53:48 +09:00
security kernel hardening fixes for v6.2-rc1 2022-12-23 12:00:24 -08:00
sound sound fixes for 6.2-rc4 2023-01-13 08:20:29 -06:00
tools Including fixes from rxrpc. 2023-01-12 18:20:44 -06:00
usr usr/gen_init_cpio.c: remove unnecessary -1 values from int file 2022-10-03 14:21:44 -07:00
virt Merge branch 'kvm-late-6.1-fixes' into HEAD 2022-12-28 07:19:14 -05:00
.clang-format iommufd for 6.2 2022-12-14 09:15:43 -08:00
.cocciconfig scripts: add Linux .cocciconfig for coccinelle 2016-07-22 12:13:39 +02:00
.get_maintainer.ignore get_maintainer: add Alan to .get_maintainer.ignore 2022-08-20 15:17:44 -07:00
.gitattributes .gitattributes: use 'dts' diff driver for dts files 2019-12-04 19:44:11 -08:00
.gitignore .gitignore: ignore *.rpm 2022-12-30 17:22:14 +09:00
.mailmap MAINTAINERS: Update email of Tudor Ambarus 2023-01-07 15:18:44 +01:00
.rustfmt.toml rust: add .rustfmt.toml 2022-09-28 09:02:20 +02:00
COPYING COPYING: state that all contributions really are covered by this file 2020-02-10 13:32:20 -08:00
CREDITS MAINTAINERS: zram: zsmalloc: Add an additional co-maintainer 2022-12-15 16:37:49 -08:00
Kbuild Kbuild updates for v6.1 2022-10-10 12:00:45 -07:00
Kconfig kbuild: ensure full rebuild when the compiler is updated 2020-05-12 13:28:33 +09:00
MAINTAINERS MTD changes: 2023-01-12 05:56:06 -06:00
Makefile Linux 6.2-rc3 2023-01-08 11:49:43 -06:00
README Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00

Linux kernel
============

There are several guides for kernel developers and users. These guides can
be rendered in a number of formats, like HTML and PDF. Please read
Documentation/admin-guide/README.rst first.

In order to build the documentation, use ``make htmldocs`` or
``make pdfdocs``.  The formatted documentation can also be read online at:

    https://www.kernel.org/doc/html/latest/

There are various text files in the Documentation/ subdirectory,
several of them using the Restructured Text markup notation.

Please read the Documentation/process/changes.rst file, as it contains the
requirements for building and running the kernel, and information about
the problems which may result by upgrading your kernel.