linux-stable.git/include/linux/cgroup-defs.h, branch v5.16.2

bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode

2021-09-13T23:35:58+00:00

Fix cgroup v1 interference when non-root cgroup v2 BPF programs are used.
Back in the days, commit bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup")
embedded per-socket cgroup information into sock->sk_cgrp_data and in order
to save 8 bytes in struct sock made both mutually exclusive, that is, when
cgroup v1 socket tagging (e.g. net_cls/net_prio) is used, then cgroup v2
falls back to the root cgroup in sock_cgroup_ptr() (&cgrp_dfl_root.cgrp).

The assumption made was "there is no reason to mix the two and this is in line
with how legacy and v2 compatibility is handled" as stated in bd1060a1d671.
However, with Kubernetes more widely supporting cgroups v2 as well nowadays,
this assumption no longer holds, and the possibility of the v1/v2 mixed mode
with the v2 root fallback being hit becomes a real security issue.

Many of the cgroup v2 BPF programs are also used for policy enforcement, just
to pick _one_ example, that is, to programmatically deny socket related system
calls like connect(2) or bind(2). A v2 root fallback would implicitly cause
a policy bypass for the affected Pods.

In production environments, we have recently seen this case due to various
circumstances: i) a different 3rd party agent and/or ii) a container runtime
such as [0] in the user's environment configuring legacy cgroup v1 net_cls
tags, which triggered implicitly mentioned root fallback. Another case is
Kubernetes projects like kind [1] which create Kubernetes nodes in a container
and also add cgroup namespaces to the mix, meaning programs which are attached
to the cgroup v2 root of the cgroup namespace get attached to a non-root
cgroup v2 path from init namespace point of view. And the latter's root is
out of reach for agents on a kind Kubernetes node to configure. Meaning, any
entity on the node setting cgroup v1 net_cls tag will trigger the bypass
despite cgroup v2 BPF programs attached to the namespace root.

Generally, this mutual exclusiveness does not hold anymore in today's user
environments and makes cgroup v2 usage from BPF side fragile and unreliable.
This fix adds proper struct cgroup pointer for the cgroup v2 case to struct
sock_cgroup_data in order to address these issues; this implicitly also fixes
the tradeoffs being made back then with regards to races and refcount leaks
as stated in bd1060a1d671, and removes the fallback, so that cgroup v2 BPF
programs always operate as expected.

  [0] https://github.com/nestybox/sysbox/
  [1] https://kind.sigs.k8s.io/

Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup")
Signed-off-by: Daniel Borkmann 
Signed-off-by: Alexei Starovoitov 
Acked-by: Stanislav Fomichev 
Acked-by: Tejun Heo 
Link: https://lore.kernel.org/bpf/20210913230759.2313-1-daniel@iogearbox.net

cgroup: make per-cgroup pressure stall tracking configurable

2021-06-08T18:59:02+00:00

PSI accounts stalls for each cgroup separately and aggregates it at each
level of the hierarchy. This causes additional overhead with psi_avgs_work
being called for each cgroup in the hierarchy. psi_avgs_work has been
highly optimized, however on systems with large number of cgroups the
overhead becomes noticeable.
Systems which use PSI only at the system level could avoid this overhead
if PSI can be configured to skip per-cgroup stall accounting.
Add "cgroup_disable=pressure" kernel command-line option to allow
requesting system-wide only pressure stall accounting. When set, it
keeps system-wide accounting under /proc/pressure/ but skips accounting
for individual cgroups and does not expose PSI nodes in cgroup hierarchy.

Signed-off-by: Suren Baghdasaryan 
Acked-by: Peter Zijlstra (Intel) 
Acked-by: Johannes Weiner 
Signed-off-by: Tejun Heo

Merge branch 'for-5.13-fixes' into for-5.14

2021-05-24T17:43:56+00:00

cgroup: fix spelling mistakes

2021-05-24T16:45:26+00:00

Fix some spelling mistakes in comments:
hierarhcy ==> hierarchy
automtically ==> automatically
overriden ==> overridden
In absense of .. or ==> In absence of .. and
assocaited ==> associated
taget ==> target
initate ==> initiate
succeded ==> succeeded
curremt ==> current
udpated ==> updated

Signed-off-by: Zhen Lei 
Signed-off-by: Tejun Heo

cgroup: introduce cgroup.kill

2021-05-10T14:41:10+00:00

Introduce the cgroup.kill file. It does what it says on the tin and
allows a caller to kill a cgroup by writing "1" into cgroup.kill.
The file is available in non-root cgroups.

Killing cgroups is a process directed operation, i.e. the whole
thread-group is affected. Consequently trying to write to cgroup.kill in
threaded cgroups will be rejected and EOPNOTSUPP returned. This behavior
aligns with cgroup.procs where reads in threaded-cgroups are rejected
with EOPNOTSUPP.

The cgroup.kill file is write-only since killing a cgroup is an event
not which makes it different from e.g. freezer where a cgroup
transitions between the two states.

As with all new cgroup features cgroup.kill is recursive by default.

Killing a cgroup is protected against concurrent migrations through the
cgroup mutex. To protect against forkbombs and to mitigate the effect of
racing forks a new CGRP_KILL css set lock protected flag is introduced
that is set prior to killing a cgroup and unset after the cgroup has
been killed. We can then check in cgroup_post_fork() where we hold the
css set lock already whether the cgroup is currently being killed. If so
we send the child a SIGKILL signal immediately taking it down as soon as
it returns to userspace. To make the killing of the child semantically
clean it is killed after all cgroup attachment operations have been
finalized.

There are various use-cases of this interface:
- Containers usually have a conservative layout where each container
  usually has a delegated cgroup. For such layouts there is a 1:1
  mapping between container and cgroup. If the container in addition
  uses a separate pid namespace then killing a container usually becomes
  a simple kill -9  from an ancestor pid namespace.
  However, there are quite a few scenarios where that isn't true. For
  example, there are containers that share the cgroup with other
  processes on purpose that are supposed to be bound to the lifetime of
  the container but are not in the same pidns of the container.
  Containers that are in a delegated cgroup but share the pid namespace
  with the host or other containers.
- Service managers such as systemd use cgroups to group and organize
  processes belonging to a service. They usually rely on a recursive
  algorithm now to kill a service. With cgroup.kill this becomes a
  simple write to cgroup.kill.
- Userspace OOM implementations can make good use of this feature to
  efficiently take down whole cgroups quickly.
- The kill program can gain a new
  kill --cgroup /sys/fs/cgroup/delegated
  flag to take down cgroups.

A few observations about the semantics:
- If parent and child are in the same cgroup and CLONE_INTO_CGROUP is
  not specified we are not taking cgroup mutex meaning the cgroup can be
  killed while a process in that cgroup is forking.
  If the kill request happens right before cgroup_can_fork() and before
  the parent grabs its siglock the parent is guaranteed to see the
  pending SIGKILL. In addition we perform another check in
  cgroup_post_fork() whether the cgroup is being killed and is so take
  down the child (see above). This is robust enough and protects gainst
  forkbombs. If userspace really really wants to have stricter
  protection the simple solution would be to grab the write side of the
  cgroup threadgroup rwsem which will force all ongoing forks to
  complete before killing starts. We concluded that this is not
  necessary as the semantics for concurrent forking should simply align
  with freezer where a similar check as cgroup_post_fork() is performed.

  For all other cases CLONE_INTO_CGROUP is required. In this case we
  will grab the cgroup mutex so the cgroup can't be killed while we
  fork. Once we're done with the fork and have dropped cgroup mutex we
  are visible and will be found by any subsequent kill request.
- We obviously don't kill kthreads. This means a cgroup that has a
  kthread will not become empty after killing and consequently no
  unpopulated event will be generated. The assumption is that kthreads
  should be in the root cgroup only anyway so this is not an issue.
- We skip killing tasks that already have pending fatal signals.
- Freezer doesn't care about tasks in different pid namespaces, i.e. if
  you have two tasks in different pid namespaces the cgroup would still
  be frozen. The cgroup.kill mechanism consequently behaves the same
  way, i.e. we kill all processes and ignore in which pid namespace they
  exist.
- If the caller is located in a cgroup that is killed the caller will
  obviously be killed as well.

Link: https://lore.kernel.org/r/20210503143922.3093755-1-brauner@kernel.org
Cc: Shakeel Butt 
Cc: Roman Gushchin 
Cc: Tejun Heo 
Cc: cgroups@vger.kernel.org
Reviewed-by: Shakeel Butt 
Reviewed-by: Serge Hallyn 
Acked-by: Roman Gushchin 
Signed-off-by: Christian Brauner 
Signed-off-by: Tejun Heo

cgroup: remove obsoleted broken_hierarchy and warned_broken_hierarchy

2020-12-15T20:13:40+00:00

With the deprecation of the non-hierarchical mode of the memory controller
there are no more examples of broken hierarchies left.

Let's remove the cgroup core code which was supposed to print warnings
about creating of broken hierarchies.

Link: https://lkml.kernel.org/r/20201110220800.929549-4-guro@fb.com
Signed-off-by: Roman Gushchin 
Reviewed-by: Shakeel Butt 
Acked-by: David Rientjes 
Acked-by: Johannes Weiner 
Cc: Michal Hocko 
Cc: Tejun Heo 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

cgroup: Fix sock_cgroup_data on big-endian.

2020-07-09T23:28:44+00:00

In order for no_refcnt and is_data to be the lowest order two
bits in the 'val' we have to pad out the bitfield of the u8.

Fixes: ad0f75e5f57c ("cgroup: fix cgroup_sk_alloc() for sk_clone_lock()")
Reported-by: Guenter Roeck 
Signed-off-by: David S. Miller

cgroup: fix cgroup_sk_alloc() for sk_clone_lock()

2020-07-07T20:34:11+00:00

When we clone a socket in sk_clone_lock(), its sk_cgrp_data is
copied, so the cgroup refcnt must be taken too. And, unlike the
sk_alloc() path, sock_update_netprioidx() is not called here.
Therefore, it is safe and necessary to grab the cgroup refcnt
even when cgroup_sk_alloc is disabled.

sk_clone_lock() is in BH context anyway, the in_interrupt()
would terminate this function if called there. And for sk_alloc()
skcd->val is always zero. So it's safe to factor out the code
to make it more readable.

The global variable 'cgroup_sk_alloc_disabled' is used to determine
whether to take these reference counts. It is impossible to make
the reference counting correct unless we save this bit of information
in skcd->val. So, add a new bit there to record whether the socket
has already taken the reference counts. This obviously relies on
kmalloc() to align cgroup pointers to at least 4 bytes,
ARCH_KMALLOC_MINALIGN is certainly larger than that.

This bug seems to be introduced since the beginning, commit
d979a39d7242 ("cgroup: duplicate cgroup reference when cloning sockets")
tried to fix it but not compeletely. It seems not easy to trigger until
the recent commit 090e28b229af
("netprio_cgroup: Fix unlimited memory leak of v2 cgroups") was merged.

Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup")
Reported-by: Cameron Berkenpas 
Reported-by: Peter Geis 
Reported-by: Lu Fengqi 
Reported-by: Daniël Sonck 
Reported-by: Zhang Qiang 
Tested-by: Cameron Berkenpas 
Tested-by: Peter Geis 
Tested-by: Thomas Lamprecht 
Cc: Daniel Borkmann 
Cc: Zefan Li 
Cc: Tejun Heo 
Cc: Roman Gushchin 
Signed-off-by: Cong Wang 
Signed-off-by: David S. Miller

Merge branch 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

2020-04-03T18:30:20+00:00

Pull cgroup updates from Tejun Heo:

 - Christian extended clone3 so that processes can be spawned into
   cgroups directly.

   This is not only neat in terms of semantics but also avoids grabbing
   the global cgroup_threadgroup_rwsem for migration.

 - Daniel added !root xattr support to cgroupfs.

   Userland already uses xattrs on cgroupfs for bookkeeping. This will
   allow delegated cgroups to support such usages.

 - Prateek tried to make cpuset hotplug handling synchronous but that
   led to possible deadlock scenarios. Reverted.

 - Other minor changes including release_agent_path handling cleanup.

* 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  docs: cgroup-v1: Document the cpuset_v2_mode mount option
  Revert "cpuset: Make cpuset hotplug synchronous"
  cgroupfs: Support user xattrs
  kernfs: Add option to enable user xattrs
  kernfs: Add removed_size out param for simple_xattr_set
  kernfs: kvmalloc xattr value instead of kmalloc
  cgroup: Restructure release_agent_path handling
  selftests/cgroup: add tests for cloning into cgroups
  clone3: allow spawning processes into cgroups
  cgroup: add cgroup_may_write() helper
  cgroup: refactor fork helpers
  cgroup: add cgroup_get_from_file() helper
  cgroup: unify attach permission checking
  cpuset: Make cpuset hotplug synchronous
  cgroup.c: Use built-in RCU list checking
  kselftest/cgroup: add cgroup destruction test
  cgroup: Clean up css_set task traversal

mm: memcontrol: recursive memory.low protection

2020-04-02T16:35:28+00:00

Right now, the effective protection of any given cgroup is capped by its
own explicit memory.low setting, regardless of what the parent says.  The
reasons for this are mostly historical and ease of implementation: to make
delegation of memory.low safe, effective protection is the min() of all
memory.low up the tree.

Unfortunately, this limitation makes it impossible to protect an entire
subtree from another without forcing the user to make explicit protection
allocations all the way to the leaf cgroups - something that is highly
undesirable in real life scenarios.

Consider memory in a data center host.  At the cgroup top level, we have a
distinction between system management software and the actual workload the
system is executing.  Both branches are further subdivided into individual
services, job components etc.

We want to protect the workload as a whole from the system management
software, but that doesn't mean we want to protect and prioritize
individual workload wrt each other.  Their memory demand can vary over
time, and we'd want the VM to simply cache the hottest data within the
workload subtree.  Yet, the current memory.low limitations force us to
allocate a fixed amount of protection to each workload component in order
to get protection from system management software in general.  This
results in very inefficient resource distribution.

Another concern with mandating downward allocation is that, as the
complexity of the cgroup tree grows, it gets harder for the lower levels
to be informed about decisions made at the host-level.  Consider a
container inside a namespace that in turn creates its own nested tree of
cgroups to run multiple workloads.  It'd be extremely difficult to
configure memory.low parameters in those leaf cgroups that on one hand
balance pressure among siblings as the container desires, while also
reflecting the host-level protection from e.g.  rpm upgrades, that lie
beyond one or more delegation and namespacing points in the tree.

It's highly unusual from a cgroup interface POV that nested levels have to
be aware of and reflect decisions made at higher levels for them to be
effective.

To enable such use cases and scale configurability for complex trees, this
patch implements a resource inheritance model for memory that is similar
to how the CPU and the IO controller implement work-conserving resource
allocations: a share of a resource allocated to a subree always applies to
the entire subtree recursively, while allowing, but not mandating,
children to further specify distribution rules.

That means that if protection is explicitly allocated among siblings,
those configured shares are being followed during page reclaim just like
they are now.  However, if the memory.low set at a higher level is not
fully claimed by the children in that subtree, the "floating" remainder is
applied to each cgroup in the tree in proportion to its size.  Since
reclaim pressure is applied in proportion to size as well, each child in
that tree gets the same boost, and the effect is neutral among siblings -
with respect to each other, they behave as if no memory control was
enabled at all, and the VM simply balances the memory demands optimally
within the subtree.  But collectively those cgroups enjoy a boost over the
cgroups in neighboring trees.

E.g.  a leaf cgroup with a memory.low setting of 0 no longer means that
it's not getting a share of the hierarchically assigned resource, just
that it doesn't claim a fixed amount of it to protect from its siblings.

This allows us to recursively protect one subtree (workload) from another
(system management), while letting subgroups compete freely among each
other - without having to assign fixed shares to each leaf, and without
nested groups having to echo higher-level settings.

The floating protection composes naturally with fixed protection.
Consider the following example tree:

		A            A: low = 2G
               / \          A1: low = 1G
              A1 A2         A2: low = 0G

As outside pressure is applied to this tree, A1 will enjoy a fixed
protection from A2 of 1G, but the remaining, unclaimed 1G from A is split
evenly among A1 and A2, coming out to 1.5G and 0.5G.

There is a slight risk of regressing theoretical setups where the
top-level cgroups don't know about the true budgeting and set bogusly high
"bypass" values that are meaningfully allocated down the tree.  Such
setups would rely on unclaimed protection to be discarded, and
distributing it would change the intended behavior.  Be safe and hide the
new behavior behind a mount option, 'memory_recursiveprot'.

Signed-off-by: Johannes Weiner 
Signed-off-by: Andrew Morton 
Acked-by: Tejun Heo 
Acked-by: Roman Gushchin 
Acked-by: Chris Down 
Cc: Michal Hocko 
Cc: Michal Koutný 
Link: http://lkml.kernel.org/r/20200227195606.46212-4-hannes@cmpxchg.org
Signed-off-by: Linus Torvalds