system/linux
system/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux synced 2024-09-20 19:17:24 +00:00
Code Issues Packages Projects Releases Wiki Activity
1015148 commits 7 branches 853 tags 6.6 GiB
C 97.6%
Assembly 1%
Shell 0.5%
Python 0.3%
Makefile 0.3%
Find a file
Feng Tang 2e3025434a mm: relocate 'write_protect_seq' in struct mm_struct 
0day robot reported a 9.2% regression for will-it-scale mmap1 test
case[1], caused by commit 57efa1fe59 ("mm/gup: prevent gup_fast from
racing with COW during fork").

Further debug shows the regression is due to that commit changes the
offset of hot fields 'mmap_lock' inside structure 'mm_struct', thus some
cache alignment changes.

From the perf data, the contention for 'mmap_lock' is very severe and
takes around 95% cpu cycles, and it is a rw_semaphore

        struct rw_semaphore {
                atomic_long_t count;	/* 8 bytes */
                atomic_long_t owner;	/* 8 bytes */
                struct optimistic_spin_queue osq; /* spinner MCS lock */
                ...

Before commit 57efa1fe59 adds the 'write_protect_seq', it happens to
have a very optimal cache alignment layout, as Linus explained:

 "and before the addition of the 'write_protect_seq' field, the
  mmap_sem was at offset 120 in 'struct mm_struct'.

  Which meant that count and owner were in two different cachelines,
  and then when you have contention and spend time in
  rwsem_down_write_slowpath(), this is probably *exactly* the kind
  of layout you want.

  Because first the rwsem_write_trylock() will do a cmpxchg on the
  first cacheline (for the optimistic fast-path), and then in the
  case of contention, rwsem_down_write_slowpath() will just access
  the second cacheline.

  Which is probably just optimal for a load that spends a lot of
  time contended - new waiters touch that first cacheline, and then
  they queue themselves up on the second cacheline."

After the commit, the rw_semaphore is at offset 128, which means the
'count' and 'owner' fields are now in the same cacheline, and causes
more cache bouncing.

Currently there are 3 "#ifdef CONFIG_XXX" before 'mmap_lock' which will
affect its offset:

  CONFIG_MMU
  CONFIG_MEMBARRIER
  CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES

The layout above is on 64 bits system with 0day's default kernel config
(similar to RHEL-8.3's config), in which all these 3 options are 'y'.
And the layout can vary with different kernel configs.

Relayouting a structure is usually a double-edged sword, as sometimes it
can helps one case, but hurt other cases.  For this case, one solution
is, as the newly added 'write_protect_seq' is a 4 bytes long seqcount_t
(when CONFIG_DEBUG_LOCK_ALLOC=n), placing it into an existing 4 bytes
hole in 'mm_struct' will not change other fields' alignment, while
restoring the regression.

Link: https://lore.kernel.org/lkml/20210525031636.GB7744@xsang-OptiPlex-9020/ [1]
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-12 13:28:50 -07:00
arch Misc fixes: 2021-06-12 11:34:49 -07:00
block block-5.13-2021-05-22 2021-05-22 07:40:34 -10:00
certs Kbuild updates for v5.13 (2nd) 2021-05-08 10:00:11 -07:00
crypto async_xor: check src_offs is not NULL before updating it 2021-06-10 19:40:14 -07:00
Documentation USB fixes for 5.13-rc6 2021-06-12 12:34:49 -07:00
drivers USB fixes for 5.13-rc6 2021-06-12 12:34:49 -07:00
fs Driver core fix for 5.13-rc6 2021-06-12 12:18:49 -07:00
include mm: relocate 'write_protect_seq' in struct mm_struct 2021-06-12 13:28:50 -07:00
init pid: take a reference when initializing cad_pid 2021-06-05 08:58:11 -07:00
ipc ipc/mqueue, msg, sem: avoid relying on a stack reference past its expiry 2021-05-22 15:09:07 -10:00
kernel Misc fixes: 2021-06-12 11:41:28 -07:00
lib lib: crc64: fix kernel-doc warning 2021-06-05 08:58:12 -07:00
LICENSES LICENSES: Add the CC-BY-4.0 license 2020-12-08 10:33:27 -07:00
mm mm, hugetlb: fix simple resv_huge_pages underflow on UFFDIO_COPY 2021-06-05 08:58:12 -07:00
net Networking fixes for 5.13-rc5, including fixes from bpf, wireless, 2021-06-04 18:25:39 -07:00
samples VFIO fixes for v5.13-rc5 2021-06-03 11:52:24 -07:00
scripts kbuild: Quote OBJCOPY var to avoid a pahole call break the build 2021-05-27 11:32:56 -07:00
security trusted-keys: match tpm_get_ops on all return paths 2021-05-12 22:36:37 +03:00
sound sound fixes for 5.13-rc6 2021-06-11 10:47:10 -07:00
tools Two objtool fixes: 2021-06-12 11:10:28 -07:00
usr .gitignore: prefix local generated files with a slash 2021-05-02 00:43:35 +09:00
virt KVM: VMX: update vcpu posted-interrupt descriptor when assigning device 2021-05-27 07:58:23 -04:00
.clang-format clang-format: Update with the latest for_each macro list 2021-05-12 23:32:39 +02:00
.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 .gitignore: ignore only top-level modules.builtin 2021-05-02 00:43:35 +09:00
.mailmap mailmap: use private address for Michel Lespinasse 2021-06-05 08:58:12 -07:00
COPYING COPYING: state that all contributions really are covered by this file 2020-02-10 13:32:20 -08:00
CREDITS MAINTAINERS: move Murali Karicheri to credits 2021-04-29 15:47:30 -07:00
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 USB fixes for 5.13-rc6 2021-06-12 12:34:49 -07:00
Makefile Linux 5.13-rc5 2021-06-06 15:47:27 -07:00
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.