android/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
987,946 Commits 2 Branches 0 Tags 2.3 GiB
C 97.8%
Assembly 1.2%
Shell 0.3%
Makefile 0.3%
Python 0.2%
Other 0.1%
20a02bc845
Go to file
Mateusz Guzik 20a02bc845 lockref: stop doing cpu_relax in the cmpxchg loop 
[ Upstream commit f5fe24ef17b5fbe6db49534163e77499fb10ae8c ]

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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-02-01 08:23:18 +01:00
arch KVM: s390: interrupt: use READ_ONCE() before cmpxchg() 2023-02-01 08:23:17 +01:00
block blk-mq: fix possible memleak when register 'hctx' failed 2023-01-14 10:16:19 +01:00
certs certs/blacklist_hashes.c: fix const confusion in certs blacklist 2022-06-22 14:13:17 +02:00
crypto crypto: tcrypt - Fix multibuffer skcipher speed test mem leak 2023-01-14 10:15:50 +01:00
Documentation dt-bindings: phy: g12a-usb3-pcie-phy: fix compatible string documentation 2023-01-24 07:20:00 +01:00
drivers platform/x86: asus-nb-wmi: Add alternate mapping for KEY_SCREENLOCK 2023-02-01 08:23:17 +01:00
fs affs: initialize fsdata in affs_truncate() 2023-02-01 08:23:11 +01:00
include scsi: iscsi: Fix multiple iSCSI session unbind events sent to userspace 2023-02-01 08:23:16 +01:00
init init/Kconfig: fix CC_HAS_ASM_GOTO_TIED_OUTPUT test with dash 2022-12-02 17:40:03 +01:00
io_uring io_uring/rw: remove leftover debug statement 2023-01-24 07:20:02 +01:00
ipc ipc/sem: Fix dangling sem_array access in semtimedop race 2022-12-08 11:24:00 +01:00
kernel kcsan: test: don't put the expect array on the stack 2023-02-01 08:23:16 +01:00
lib lockref: stop doing cpu_relax in the cmpxchg loop 2023-02-01 08:23:18 +01:00
LICENSES LICENSES/deprecated: add Zlib license text 2020-09-16 14:33:49 +02:00
mm mm/khugepaged: fix collapse_pte_mapped_thp() to allow anon_vma 2023-01-24 07:20:01 +01:00
net tcp: fix rate_app_limited to default to 1 2023-02-01 08:23:16 +01:00
samples samples: vfio-mdev: Fix missing pci_disable_device() in mdpy_fb_probe() 2023-01-14 10:16:01 +01:00
scripts scripts/faddr2line: Fix regression in name resolution on ppc64le 2022-12-08 11:23:54 +01:00
security tomoyo: fix broken dependency on *.conf.default 2023-02-01 08:23:10 +01:00
sound ASoC: fsl-asoc-card: Fix naming of AC'97 CODEC widgets 2023-02-01 08:23:17 +01:00
tools tools/virtio: initialize spinlocks in vring_test.c 2023-01-24 07:19:55 +01:00
usr usr/include/Makefile: add linux/nfc.h to the compile-test coverage 2022-02-01 17:25:48 +01:00
virt kvm: Add support for arch compat vm ioctls 2022-10-30 09:41:15 +01:00
.clang-format RDMA 5.10 pull request 2020-10-17 11:18:18 -07:00
.cocciconfig
.get_maintainer.ignore Opt out of scripts/get_maintainer.pl 2019-05-16 10:53:40 -07:00
.gitattributes .gitattributes: use 'dts' diff driver for dts files 2019-12-04 19:44:11 -08:00
.gitignore kbuild: generate Module.symvers only when vmlinux exists 2021-05-19 10:12:59 +02:00
.mailmap mailmap: add two more addresses of Uwe Kleine-König 2020-12-06 10:19:07 -08:00
COPYING COPYING: state that all contributions really are covered by this file 2020-02-10 13:32:20 -08:00
CREDITS MAINTAINERS: Move Jason Cooper to CREDITS 2020-11-30 10:20:34 +01:00
Kbuild kbuild: rename hostprogs-y/always to hostprogs/always-y 2020-02-04 01:53:07 +09:00
Kconfig kbuild: ensure full rebuild when the compiler is updated 2020-05-12 13:28:33 +09:00
MAINTAINERS futex: Move to kernel/futex/ 2023-01-14 10:15:20 +01:00
Makefile Linux 5.10.165 2023-01-24 07:20:02 +01:00
README Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00

README 

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.