Go to file
Linus Torvalds 254090925e mm: don't try to NUMA-migrate COW pages that have other uses
commit 80d47f5de5e311cbc0d01ebb6ee684e8f4c196c6 upstream.

Oded Gabbay reports that enabling NUMA balancing causes corruption with
his Gaudi accelerator test load:

 "All the details are in the bug, but the bottom line is that somehow,
  this patch causes corruption when the numa balancing feature is
  enabled AND we don't use process affinity AND we use GUP to pin pages
  so our accelerator can DMA to/from system memory.

  Either disabling numa balancing, using process affinity to bind to
  specific numa-node or reverting this patch causes the bug to
  disappear"

and Oded bisected the issue to commit 09854ba94c ("mm: do_wp_page()
simplification").

Now, the NUMA balancing shouldn't actually be changing the writability
of a page, and as such shouldn't matter for COW.  But it appears it
does.  Suspicious.

However, regardless of that, the condition for enabling NUMA faults in
change_pte_range() is nonsensical.  It uses "page_mapcount(page)" to
decide if a COW page should be NUMA-protected or not, and that makes
absolutely no sense.

The number of mappings a page has is irrelevant: not only does GUP get a
reference to a page as in Oded's case, but the other mappings migth be
paged out and the only reference to them would be in the page count.

Since we should never try to NUMA-balance a page that we can't move
anyway due to other references, just fix the code to use 'page_count()'.
Oded confirms that that fixes his issue.

Now, this does imply that something in NUMA balancing ends up changing
page protections (other than the obvious one of making the page
inaccessible to get the NUMA faulting information).  Otherwise the COW
simplification wouldn't matter - since doing the GUP on the page would
make sure it's writable.

The cause of that permission change would be good to figure out too,
since it clearly results in spurious COW events - but fixing the
nonsensical test that just happened to work before is obviously the
CorrectThing(tm) to do regardless.

Fixes: 09854ba94c ("mm: do_wp_page() simplification")
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215616
Link: https://lore.kernel.org/all/CAFCwf10eNmwq2wD71xjUhqkvv5+_pJMR1nPug2RqNDcFT4H86Q@mail.gmail.com/
Reported-and-tested-by: Oded Gabbay <oded.gabbay@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-02-23 12:00:57 +01:00
arch parisc: Drop __init from map_pages declaration 2022-02-23 12:00:57 +01:00
block block: bio-integrity: Advance seed correctly for larger interval sizes 2022-02-08 18:30:35 +01:00
certs certs: Trigger creation of RSA module signing key if it's not an RSA key 2021-09-15 09:50:29 +02:00
crypto crypto: api - Move cryptomgr soft dependency into algapi 2022-02-11 09:09:03 +01:00
Documentation ARM: dts: Fix timer regression for beagleboard revision c 2022-02-16 12:54:22 +01:00
drivers mmc: block: fix read single on recovery logic 2022-02-23 12:00:57 +01:00
fs fs/proc: task_mmu.c: don't read mapcount for migration entry 2022-02-23 12:00:56 +01:00
include can: isotp: add SF_BROADCAST support for functional addressing 2022-02-23 12:00:56 +01:00
init bpf: Add kconfig knob for disabling unpriv bpf by default 2022-01-05 12:40:34 +01:00
ipc shm: extend forced shm destroy to support objects from several IPC nses 2021-12-01 09:19:10 +01:00
kernel rcu: Do not report strict GPs for outgoing CPUs 2022-02-23 12:00:56 +01:00
lib lib/test_meminit: destroy cache in kmem_cache_alloc_bulk() test 2022-01-27 10:54:36 +01:00
LICENSES LICENSES/deprecated: add Zlib license text 2020-09-16 14:33:49 +02:00
mm mm: don't try to NUMA-migrate COW pages that have other uses 2022-02-23 12:00:57 +01:00
net can: isotp: add SF_BROADCAST support for functional addressing 2022-02-23 12:00:56 +01:00
samples ftrace/samples: Add missing prototypes direct functions 2022-01-11 15:25:00 +01:00
scripts Makefile.extrawarn: Move -Wunaligned-access to W=1 2022-02-16 12:54:30 +01:00
security ima: Do not print policy rule with inactive LSM labels 2022-02-16 12:54:16 +01:00
sound ASoC: max9759: fix underflow in speaker_gain_control_put() 2022-02-08 18:30:38 +01:00
tools selftests: nft_concat_range: add test for reload with no element add/del 2022-02-08 18:30:41 +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: eventfd: Fix false positive RCU usage warning 2022-02-16 12:54:20 +01:00
.clang-format RDMA 5.10 pull request 2020-10-17 11:18:18 -07:00
.cocciconfig scripts: add Linux .cocciconfig for coccinelle 2016-07-22 12:13:39 +02:00
.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 MAINTAINERS: adjust GCC PLUGINS after gcc-plugin.sh removal 2021-12-14 11:32:46 +01:00
Makefile Linux 5.10.101 2022-02-16 12:54:31 +01:00
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.