lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20210319163821.20704-1-songmuchun@bytedance.com>
Date:   Sat, 20 Mar 2021 00:38:13 +0800
From:   Muchun Song <songmuchun@...edance.com>
To:     guro@...com, hannes@...xchg.org, mhocko@...nel.org,
        akpm@...ux-foundation.org, shakeelb@...gle.com,
        vdavydov.dev@...il.com
Cc:     linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        duanxiongchun@...edance.com, Muchun Song <songmuchun@...edance.com>
Subject: [PATCH v5 0/7] Use obj_cgroup APIs to charge kmem pages

Since Roman series "The new cgroup slab memory controller" applied. All
slab objects are charged with the new APIs of obj_cgroup. The new APIs
introduce a struct obj_cgroup to charge slab objects. It prevents
long-living objects from pinning the original memory cgroup in the memory.
But there are still some corner objects (e.g. allocations larger than
order-1 page on SLUB) which are not charged with the new APIs. Those
objects (include the pages which are allocated from buddy allocator
directly) are charged as kmem pages which still hold a reference to
the memory cgroup.

E.g. We know that the kernel stack is charged as kmem pages because the
size of the kernel stack can be greater than 2 pages (e.g. 16KB on x86_64
or arm64). If we create a thread (suppose the thread stack is charged to
memory cgroup A) and then move it from memory cgroup A to memory cgroup
B. Because the kernel stack of the thread hold a reference to the memory
cgroup A. The thread can pin the memory cgroup A in the memory even if
we remove the cgroup A. If we want to see this scenario by using the
following script. We can see that the system has added 500 dying cgroups
(This is not a real world issue, just a script to show that the large
kmallocs are charged as kmem pages which can pin the memory cgroup in the
memory).

	#!/bin/bash

	cat /proc/cgroups | grep memory

	cd /sys/fs/cgroup/memory
	echo 1 > memory.move_charge_at_immigrate

	for i in range{1..500}
	do
		mkdir kmem_test
		echo $$ > kmem_test/cgroup.procs
		sleep 3600 &
		echo $$ > cgroup.procs
		echo `cat kmem_test/cgroup.procs` > cgroup.procs
		rmdir kmem_test
	done

	cat /proc/cgroups | grep memory

This patchset aims to make those kmem pages to drop the reference to memory
cgroup by using the APIs of obj_cgroup. Finally, we can see that the number
of the dying cgroups will not increase if we run the above test script.

Changlogs in v5:
  1. Add a new patch (1st) to fix a potential issue.
  2. Rename get_obj_cgroup_memcg() to get_mem_cgroup_from_objcg().
  3. Remove get_mem_cgroup_from_current() and get_active_memcg().
  4. Add a comment to uncharge_page().
  5. Add a separate patch to inline __memcg_kmem_{un}charge() into
     obj_cgroup_{un}charge_pages().
  6. Collect Acked-by and Reviewed-by tags.

  Thanks to Johannes and Shakeel's review and suggestions.

Changlogs in v4:
  1. Do not change behavior of page_memcg() and page_memcg_rcu().
  2. Rework uncharge_page() and uncharge_batch().
  3. Add two patches (patch #2 and patch #3).

  Thanks to Johannes and Shakeel and Roman's review and suggestions.

Changlogs in v3:
  1. Drop "remote objcg charging APIs" patch.
  2. Rename obj_cgroup_{un}charge_page to obj_cgroup_{un}charge_pages.
  3. Make page_memcg/page_memcg_rcu safe for adding new memcg_data flags.
  4. Reuse the ug infrastructure to uncharge the kmem pages.
  5. Add a new patch to move PageMemcgKmem to the scope of CONFIG_MEMCG_KMEM.

  Thanks to Roman's review and suggestions.

Changlogs in v2:
  1. Fix some types in the commit log (Thanks Roman).
  2. Do not introduce page_memcg_kmem helper (Thanks to Johannes and Shakeel).
  3. Reduce the CC list to mm/memcg folks (Thanks to Johannes).
  4. Introduce remote objcg charging APIs instead of convert "remote memcg
     charging APIs" to "remote objcg charging APIs".

Muchun Song (7):
  mm: memcontrol: slab: fix obtain a reference to a freeing memcg
  mm: memcontrol: introduce obj_cgroup_{un}charge_pages
  mm: memcontrol: directly access page->memcg_data in mm/page_alloc.c
  mm: memcontrol: change ug->dummy_page only if memcg changed
  mm: memcontrol: use obj_cgroup APIs to charge kmem pages
  mm: memcontrol: inline __memcg_kmem_{un}charge() into
    obj_cgroup_{un}charge_pages()
  mm: memcontrol: move PageMemcgKmem to the scope of CONFIG_MEMCG_KMEM

 include/linux/memcontrol.h | 123 +++++++++++++++++++++------
 mm/memcontrol.c            | 206 +++++++++++++++++++++++----------------------
 mm/page_alloc.c            |   4 +-
 3 files changed, 207 insertions(+), 126 deletions(-)

-- 
2.11.0

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ