Some applications want to write to /proc. For instance:
docker run -it centos groupadd foo
Gives: groupadd: failure while writing changes to /etc/group
And strace reveals why:
open("/proc/self/task/13/attr/fscreate", O_RDWR) = -1 EROFS (Read-only file system)
I've looked at what other systems do, and systemd-nspawn makes /proc read-write
and /proc/sys readonly, while lxc allows "proc:mixed" which does the same,
plus it makes /proc/sysrq-trigger also readonly.
The later seems like a prudent idea, so we follows lxc proc:mixed.
Additionally we make /proc/irq and /proc/bus, as these seem to let
you control various hardware things.
Docker-DCO-1.1-Signed-off-by: Alexander Larsson <alexl@redhat.com> (github: alexlarsson)
We don't have the flexibility to do extra things with lxc because it is
a black box and most fo the magic happens before we get a chance to
interact with it in dockerinit.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
There is not need for the remount hack, we use aa_change_onexec so the
apparmor profile is not applied until we exec the users app.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
This also cleans up some of the left over restriction paths code from
before.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
It has been pointed out that some files in /proc and /sys can be used
to break out of containers. However, if those filesystems are mounted
read-only, most of the known exploits are mitigated, since they rely
on writing some file in those filesystems.
This does not replace security modules (like SELinux or AppArmor), it
is just another layer of security. Likewise, it doesn't mean that the
other mitigations (shadowing parts of /proc or /sys with bind mounts)
are useless. Those measures are still useful. As such, the shadowing
of /proc/kcore is still enabled with both LXC and native drivers.
Special care has to be taken with /proc/1/attr, which still needs to
be mounted read-write in order to enable the AppArmor profile. It is
bind-mounted from a private read-write mount of procfs.
All that enforcement is done in dockerinit. The code doing the real
work is in libcontainer. The init function for the LXC driver calls
the function from libcontainer to avoid code duplication.
Docker-DCO-1.1-Signed-off-by: Jérôme Petazzoni <jerome@docker.com> (github: jpetazzo)
This duplicates some of the Exec code but I think it it worth it because
the native driver is more straight forward and does not have the
complexity have handling the type issues for now.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
This temp. expands the Exec method's signature but adds a more robust
way to know when the container's process is actually released and begins
to run. The network interfaces are not guaranteed to be up yet but this
provides a more accurate view with a single callback at this time.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
Without this patch, containers inherit the open file descriptors of the daemon, so my "exec 42>&2" allows us to "echo >&42 some nasty error with some bad advice" directly into the daemon log. :)
Also, "hack/dind" was already doing this due to issues caused by the inheritance, so I'm removing that hack too since this patch obsoletes it by generalizing it for all containers.
Docker-DCO-1.1-Signed-off-by: Andrew Page <admwiggin@gmail.com> (github: tianon)
This has every container using the docker daemon's pid for the processes
label so it does not work correctly.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
These are unnecessary since the user package handles these cases properly already (as evidenced by the LXC backend not having these special cases).
I also updated the errors returned to match the other libcontainer error messages in this same file.
Also, switching from Setresuid to Setuid directly isn't a problem, because the "setuid" system call will automatically do that if our own effective UID is root currently: (from `man 2 setuid`)
setuid() sets the effective user ID of the calling process. If the
effective UID of the caller is root, the real UID and saved set-user-
ID are also set.
Docker-DCO-1.1-Signed-off-by: Andrew Page <admwiggin@gmail.com> (github: tianon)
When the code attempts to set the ProcessLabel, it checks if SELinux Is
enabled. We have seen a case with some of our patches where the code
is fooled by the container to think that SELinux is not enabled. Calling
label.Init before setting up the rest of the container, tells the library that
SELinux is enabled and everything works fine.
Docker-DCO-1.1-Signed-off-by: Dan Walsh <dwalsh@redhat.com> (github: rhatdan)
This leaves only the generic cgroup helper functions in cgroups.go and
will allow easy implementations of other cgroup managers.
This also wires up the call to Cleanup the cgroup which was missing
before.
Docker-DCO-1.1-Signed-off-by: Alexander Larsson <alexl@redhat.com> (github: alexlarsson)
docker will run the process(es) within the container with an SELinux label and will label
all of the content within the container with mount label. Any temporary file systems
created within the container need to be mounted with the same mount label.
The user can override the process label by specifying
-Z With a string of space separated options.
-Z "user=unconfined_u role=unconfined_r type=unconfined_t level=s0"
Would cause the process label to run with unconfined_u:unconfined_r:unconfined_t:s0"
By default the processes will run execute within the container as svirt_lxc_net_t.
All of the content in the container as svirt_sandbox_file_t.
The process mcs level is based of the PID of the docker process that is creating the container.
If you run the container in --priv mode, the labeling will be disabled.
Docker-DCO-1.1-Signed-off-by: Dan Walsh <dwalsh@redhat.com> (github: rhatdan)
We need to change it to read only at the very end so that bound,
copy dev nodes and other ops do not fail.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
Docker-DCO-1.1-Signed-off-by: Timothy Hobbs <timothyhobbs@seznam.cz> (github: https://github.com/timthelion)
Remove loopback code from veth strategy
Docker-DCO-1.1-Signed-off-by: Timothy Hobbs <timothyhobbs@seznam.cz> (github: https://github.com/timthelion)
Looback strategy: Get rid of uneeded code in Create
Docker-DCO-1.1-Signed-off-by: Timothy Hobbs <timothyhobbs@seznam.cz> (github: https://github.com/timthelion)
Use append when building network strategy list
Docker-DCO-1.1-Signed-off-by: Timothy Hobbs <timothyhobbs@seznam.cz> (github: https://github.com/timthelion)
Swap loopback and veth strategies in Networks list
Docker-DCO-1.1-Signed-off-by: Timothy Hobbs <timothyhobbs@seznam.cz> (github: https://github.com/timthelion)
Revert "Swap loopback and veth strategies in Networks list"
This reverts commit 3b8b2c8454171d79bed5e9a80165172617e92fc7.
Docker-DCO-1.1-Signed-off-by: Timothy Hobbs <timothyhobbs@seznam.cz> (github: https://github.com/timthelion)
When initializing networks, only return from the loop if there is an error
Docker-DCO-1.1-Signed-off-by: Timothy Hobbs <timothyhobbs@seznam.cz> (github: https://github.com/timthelion)
This moves the bind mounts like /.dockerinit, /etc/hostname, volumes,
etc into the container namespace, by setting them up using lxc.
This is useful to avoid littering the global namespace with a lot of
mounts that are internal to each container and are not generally
needed on the outside. In particular, it seems that having a lot of
mounts is problematic wrt scaling to a lot of containers on systems
where the root filesystem is mounted --rshared.
Note that the "private" option is only supported by the native driver, as
lxc doesn't support setting this. This is not a huge problem, but it does
mean that some mounts are unnecessarily shared inside the container if you're
using the lxc driver.
Docker-DCO-1.1-Signed-off-by: Alexander Larsson <alexl@redhat.com> (github: alexlarsson)
Use the DOCKER_RAMDISK env var to tell the native driver not to use
a pivot root when setting up the rootfs of a container.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
This reverts commit 82f797f14096430c3edbace1cd30e04a483ec41f.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
This reverts commit bd263f5b15b51747e3429179fef7fcb425ccbe4a.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
This reverts commit 757b5775725fb90262cee1fa6068fa9dcbbff59f.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
This reverts commit 5b5c884cc8266d0c2a56da0bc2df14cc9d5d85e8.
Docker-DCO-1.1-Signed-off-by: Michael Crosby <michael@crosbymichael.com> (github: crosbymichael)
We can't keep file descriptors without close-on-exec except with
syscall.ForkLock held, as otherwise they could leak by accident into
other children from forks in other threads.
Instead we just use Cmd.ExtraFiles which handles all this for us.
This fixes https://github.com/dotcloud/docker/issues/4493
Docker-DCO-1.1-Signed-off-by: Alexander Larsson <alexl@redhat.com> (github: alexlarsson)
Now that we unmount all the mounts from the global namespace we can
use a private namespace rather than a slave one (as we have no need
for unmounts of inherited global mounts to propagate into the
container).
Docker-DCO-1.1-Signed-off-by: Alexander Larsson <alexl@redhat.com> (github: alexlarsson)
Instead of keeping all the old mounts in the container namespace and
just using subtree as root we pivot_root so that the actual root in
the namespace is the root we want, and then we unmount the previous
mounts.
This has multiple advantages:
* The namespace mount tree is smaller (in the kernel)
* If you break out of the chroot you could previously access the host
filesystem. Now the host filesystem is fully invisible to the namespace.
* We get rid of all unrelated mounts from the parent namespace, which means
we don't hog these. This is important if we later switch to MS_PRIVATE instead
of MS_SLAVE as otherwise these mounts would be impossible to unmount from the
parent namespace.
Docker-DCO-1.1-Signed-off-by: Alexander Larsson <alexl@redhat.com> (github: alexlarsson)
Erik Hollensbe
Victor Marmol
Alexander Larsson
Sridhar Ratnakumar
Bernerd Schaefer
Michael Crosby
Michael Crosby
Rohit Jnagal
Jérôme Petazzoni
Guillaume J. Charmes
Tianon Gravi
Victor Vieux
unclejack
Dan Walsh
Johan Euphrosine
Timothy Hobbs
Guillaume J. Charmes