If we pass a file descriptor to the host filesystem while joining a
container, there is a race condition where a process inside the
container can ptrace(2) the joining process and stop it from closing its
file descriptor to the stateDirFd. Then the process can access the
*host* filesystem from that file descriptor. This was fixed in part by
5d93fed3d2 ("Set init processes as non-dumpable"), but that fix is
more of a hail-mary than an actual fix for the underlying issue.
To fix this, don't open or pass the stateDirFd to the init process
unless we're creating a new container. A proper fix for this would be to
remove the need for even passing around directory file descriptors
(which are quite dangerous in the context of mount namespaces).
There is still an issue with containers that have CAP_SYS_PTRACE and are
using the setns(2)-style of joining a container namespace. Currently I'm
not really sure how to fix it without rampant layer violation.
Fixes: CVE-2016-9962
Fixes: 5d93fed3d2 ("Set init processes as non-dumpable")
Signed-off-by: Aleksa Sarai <asarai@suse.de>
`HookState` struct should follow definition of `State` in runtime-spec:
* modify json name of `version` to `ociVersion`.
* Remove redundant `Rootfs` field as rootfs can be retrived from
`bundlePath/config.json`.
Signed-off-by: Zhang Wei <zhangwei555@huawei.com>
This implements {createTTY, detach} and all of the combinations and
negations of the two that were previously implemented. There are some
valid questions about out-of-OCI-scope topics like !createTTY and how
things should be handled (why do we dup the current stdio to the
process, and how is that not a security issue). However, these will be
dealt with in a separate patchset.
In order to allow for late console setup, split setupRootfs into the
"preparation" section where all of the mounts are created and the
"finalize" section where we pivot_root and set things as ro. In between
the two we can set up all of the console mountpoints and symlinks we
need.
We use two-stage synchronisation to ensures that when the syscalls are
reordered in a suboptimal way, an out-of-place read() on the parentPipe
will not gobble the ancilliary information.
This patch is part of the console rewrite patchset.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
This allows a user to send a signal to all the processes in the
container within a single atomic action to avoid new processes being
forked off before the signal can be sent.
This is basically taking functionality that we already use being
`delete` and exposing it ok the `kill` command by adding a flag.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
In user namespaces devices are bind-mounted from the host, so
we need to add them as external mounts for CRIU.
Reported-by: Ross Boucher <boucher@gmail.com>
Signed-off-by: Andrei Vagin <avagin@virtuozzo.com>
Depending on your SELinux setup, the order in which you join namespaces
can be important. In general, user namespaces should *always* be joined
and unshared first because then the other namespaces are correctly
pinned and you have the right priviliges within them. This also is very
useful for rootless containers, as well as older kernels that had
essentially broken unshare(2) and clone(2) implementations.
This also includes huge refactorings in how we spawn processes for
complicated reasons that I don't want to get into because it will make
me spiral into a cloud of rage. The reasoning is in the giant comment in
clone_parent. Have fun.
In addition, because we now create multiple children with CLONE_PARENT,
we cannot wait for them to SIGCHLD us in the case of a death. Thus, we
have to resort to having a child kindly send us their exit code before
they die. Hopefully this all works okay, but at this point there's not
much more than we can do.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
This avoids us from running into cases where libcontainer thinks that a
particular namespace file is a different type, and makes it a fatal
error rather than causing broken functionality.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
if a container state is running or created, the container.Pause()
method can set the state to pausing, and then paused.
this patch update the comment, so it can be consistent with the code.
Signed-off-by: Wang Long <long.wanglong@huawei.com>
1. According to docs of Cmd.Path and Cmd.Args from package "os/exec":
Path is the path of the command to run. Args holds command line
arguments, including the command as Args[0]. We have mixed usage
of args. In InitPath(), InitArgs only take arguments, in InitArgs(),
InitArgs including the command as Args[0]. This is confusing.
2. InitArgs() already have the ability to configure a LinuxFactory
with the provided absolute path to the init binary and arguements as
InitPath() does.
3. exec.Command() will take care of serching executable path.
4. The default "/proc/self/exe" instead of os.Args[0] is passed to
InitArgs in order to allow relative path for the runC binary.
Signed-off-by: Yang Hongyang <imhy.yang@gmail.com>
This removes the use of a signal handler and SIGCONT to signal the init
process to exec the users process.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
This is the inital port of the libcontainer.Error to added a cause to
all the existing error messages. Going forward, when an error can be
wrapped because it is not being checked at the higher levels for
something like `os.IsNotExist` we can add more information to the error
message like cause and stack file/line information. This will help
higher level tools to know what cause a container start or operation to
fail.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
No substantial code change.
Note that some style errors reported by `golint` are not fixed due to possible compatibility issues.
Signed-off-by: Akihiro Suda <suda.kyoto@gmail.com>
This updates runc and libcontainer to handle rlimits per process and set
them correctly for the container.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
This commit adds support to libcontainer to allow caps, no new privs,
apparmor, and selinux process label to the process struct so that it can
be used together of override the base settings on the container config
per individual process.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
currentState() always adds all possible namespaces to the state,
regardless of whether they are supported.
If orderNamespacePaths detects an unsupported namespace, an error is
returned that results in initialization failure.
Fix this by only adding paths of supported namespaces to the state.
Signed-off-by: Ido Yariv <ido@wizery.com>
An init process can join other namespaces (pidns, ipc etc.). This leverages
C code defined in nsenter package to spawn a process with correct namespaces
and clone if necessary.
This moves all setns and cloneflags related code to nsenter layer, which mean
that we dont use Go os/exec to create process with cloneflags and set
uid/gid_map or setgroups anymore. The necessary data is passed from Go to C
using a netlink binary-encoding format.
With this change, setns and init processes are almost the same, which brings
some opportunity for refactoring.
Signed-off-by: Daniel, Dao Quang Minh <dqminh89@gmail.com>
[mickael.laventure@docker.com: adapted to apply on master @ d97d5e]
Signed-off-by: Kenfe-Mickael Laventure <mickael.laventure@docker.com>
This adds orderNamespacePaths to get correct order of namespaces for the
bootstrap program to join.
Signed-off-by: Daniel, Dao Quang Minh <dqminh89@gmail.com>
Create a unique session key name for every container. Use the pattern
_ses.<postfix> with postfix being the container's Id.
This patch does not prevent containers from joining each other's session
keyring.
Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Docker uses Prestart hooks to call a libnetwork hook to create
network devices and set addesses and routes.
Signed-off-by: Andrew Vagin <avagin@virtuozzo.com>
This options is set a namespace mask which will not be dumped and restored.
For example, we are going to use this option to restore network
for docker containers. CRIU will create a network namespace and
call a libnetwork hook to restore network devices, addresses and routes.
Signed-off-by: Andrew Vagin <avagin@virtuozzo.com>
We don't need a CreatedTime method on the container because it's not
part of the interface and can be received via the state. We also do not
need to call it CreateTime because the type of this field is time.Time
so we know its time.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
Aleksa Sarai
Qiang Huang
Zhang Wei
Mrunal Patel
Xianlu Bird
Michael Crosby
Andrei Vagin
Wang Long
rajasec
Phil Estes
Yang Hongyang
Petar Petrov
Akihiro Suda
George Lestaris
Peng Gao
Jessica Frazelle
Ido Yariv
Daniel, Dao Quang Minh
Stefan Berger