Without this patch applied, RHEL's SELinux policies cause container
creation to not really work. Unfortunately this might be an issue for
rootless containers (opencontainers/runc#774) but we'll cross that
bridge when we come to it.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
Print the error message to stderr if we are unable to return it back via
the pipe to the parent process. Also, don't panic here as it is most
likely a system or user error and not a programmer error.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
We need support for read/only mounts in SELinux to allow a bunch of
containers to share the same read/only image. In order to do this
we need a new label which allows container processes to read/execute
all files but not write them.
Existing mount label is either shared write or private write. This
label is shared read/execute.
Signed-off-by: Dan Walsh <dwalsh@redhat.com>
At some point InitLabels was changed to look for SecuritOptions
separated by a ":" rather then an "=", but DupSecOpt was never
changed to match this default.
Signed-off-by: Dan Walsh <dwalsh@redhat.com>
If copyup is specified for a tmpfs mount, then the contents of the
underlying directory are copied into the tmpfs mounted over it.
Signed-off-by: Mrunal Patel <mrunalp@gmail.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>
In order to mount root filesystems inside the container's mount
namespace as part of the spec we need to have the ability to do a bind
mount to / as the destination.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
Since Linux 4.3 ambient capabilities are available. If set these allow unprivileged child
processes to inherit capabilities, while at present there is no means to set capabilities
on non root processes, other than via filesystem capabilities which are not usually
supported in image formats.
With ambient capabilities non root processes can be given capabilities as well, and so
the main reason to use root in containers goes away, and capabilities work as expected.
The code falls back to the existing behaviour if ambient capabilities are not supported.
Signed-off-by: Justin Cormack <justin.cormack@docker.com>
grep -r "range map" showw 3 parts use map to
range enum types, use slice instead can get
better performance and less memory usage.
Signed-off-by: Peng Gao <peng.gao.dut@gmail.com>
For example, the /sys/firmware directory should be masked because it can contain some sensitive files:
- /sys/firmware/acpi/tables/{SLIC,MSDM}: Windows license information:
- /sys/firmware/ibft/target0/chap-secret: iSCSI CHAP secret
Signed-off-by: Akihiro Suda <suda.akihiro@lab.ntt.co.jp>
cgroupData.join method using `WriteCgroupProc` to place the pid into
the proc file, it can avoid attach any pid to the cgroup if -1 is
specified as a pid.
so, replace `writeFile` with `WriteCgroupProc` like `cpuset.go`'s
ApplyDir method.
Signed-off-by: Wang Long <long.wanglong@huawei.com>
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>
Currently if a user does a command like
docker: Error response from daemon: operation not supported.
With this fix they should see a much more informative error message.
docker run -ti -v /proc:/proc:Z fedora sh
docker: Error response from daemon: SELinux Relabeling of /proc is not allowed: operation not supported.
Signed-off-by: Dan Walsh <dwalsh@redhat.com>
Error sent from child process is already genericError, if
we don't allow recrusive generic error, we won't get any
cause infomation from parent process.
Before, we got:
WARN[0000] exit status 1
ERRO[0000] operation not permitted
After, we got:
WARN[0000] exit status 1
ERRO[0000] container_linux.go:247: starting container process caused "process_linux.go:359: container init caused \"operation not permitted\""
it's not pretty but useful for detecting root causes.
Signed-off-by: Qiang Huang <h.huangqiang@huawei.com>
This allows older state files to be loaded without the unmarshal error
of the string to int conversion.
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
After #1009, we don't always set `cgroup.Paths`, so
`getCgroupPath()` will return wrong cgroup path because
it'll take current process's cgroup as the parent, which
would be wrong when we try to find the cgroup path in
`runc ps` and `runc kill`.
Fix it by using `m.GetPath()` to get the true cgroup
paths.
Reported-by: Yang Shukui <yangshukui@huawei.com>
Signed-off-by: Qiang Huang <h.huangqiang@huawei.com>
Alternative of #895 , part of #892
The intension of current behavior if to create cgroup in
parent cgroup of current process, but we did this in a
wrong way, we used devices cgroup path of current process
as the default parent path for all subsystems, this is
wrong because we don't always have the same cgroup path
for all subsystems.
Signed-off-by: Qiang Huang <h.huangqiang@huawei.com>
Signed-off-by: rajasec <rajasec79@gmail.com>
Error handling when container not exists
Signed-off-by: rajasec <rajasec79@gmail.com>
Error handling when container not exists
Signed-off-by: rajasec <rajasec79@gmail.com>
Error handling when container not exists
Signed-off-by: rajasec <rajasec79@gmail.com>
This just moves everything to one function so we don't have to pass a
bunch of things to functions when there's no real benefit. It also makes
the API nicer.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
The original SETUID takes a 16 bit UID. Linux 2.4 introduced a new
syscall, SETUID32, with support for 32 bit UIDs. The setgid wrapper
already uses SETGID32.
Signed-off-by: Carl Henrik Lunde <chlunde@ifi.uio.no>
TestCaptureTestFunc failed in localunittest:
# make localunittest
=== RUN TestCaptureTestFunc
--- FAIL: TestCaptureTestFunc (0.00s)
capture_test.go:26: expected package "github.com/opencontainers/runc/libcontainer/stacktrace" but received "_/root/runc/libcontainer/stacktrace"
#
Reason: the path for stacktrace is a fixed string which
only valid for container environment.
And we can switch to relative path to make both in-container
and out-of-container test works.
After patch:
# make localunittest
=== RUN TestCaptureTestFunc
--- PASS: TestCaptureTestFunc (0.00s)
#
Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Removed a lot of clutter, improved the style of the code, removed
unnecessary complexity. In addition, made errors unique by making bail()
exit with a unique error code. Most of this code comes from the current
state of the rootless containers branch.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
This device is not required by the OCI spec.
The rationale for this was linked to https://github.com/docker/docker/issues/2393
So a non functional /dev/fuse was created, and actual fuse use still is
required to add the device explicitly. However even old versions of the JVM
on Ubuntu 12.04 no longer require the fuse package, and this is all not
needed.
Signed-off-by: Justin Cormack <justin.cormack@docker.com>
It's possible that `cmd.Process` is still nil when we reach timeout.
Start creates `Process` field synchronously, and there is no way to such
race.
Signed-off-by: Alexander Morozov <lk4d4math@gmail.com>
This avoid the goimports tool from remove the libcontainer/keys import line due the package name is diferent from folder name
Signed-off-by: Guilherme Rezende <guilhermebr@gmail.com>
Revert: #935Fixes: #946
I can reproduce #946 on some machines, the problem is on
some machines, it could be very fast that modify time
of `memory.kmem.limit_in_bytes` could be the same as
before it's modified.
And now we'll call `SetKernelMemory` twice on container
creation which cause the second time failure.
Revert this before we find a better solution.
Signed-off-by: Qiang Huang <h.huangqiang@huawei.com>
Previously we used the same JSON tag name for the regular and realtime
versions of the CpuRt* fields, which causes issues when you want to use
two different values for the fields.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
Setting classid of net_cls cgroup failed:
ERRO[0000] process_linux.go:291: setting cgroup config for ready process caused "failed to write 𐀁 to net_cls.classid: write /sys/fs/cgroup/net_cls,net_prio/user.slice/abc/net_cls.classid: invalid argument"
process_linux.go:291: setting cgroup config for ready process caused "failed to write 𐀁 to net_cls.classid: write /sys/fs/cgroup/net_cls,net_prio/user.slice/abc/net_cls.classid: invalid argument"
The spec has classid as a *uint32, the libcontainer configs should match the type.
Signed-off-by: Hushan Jia <hushan.jia@gmail.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>
Added a unit test to verify that 'cpu.rt_runtime_us' and 'cpu.rt_runtime_us'
cgroup values are set when the cgroup is applied to a process.
Signed-off-by: Ben Gray <ben.r.gray@gmail.com>
before trying to move the process into the cgroup.
This is required if runc itself is running in SCHED_RR mode, as it is not
possible to add a process in SCHED_RR mode to a cgroup which hasn't been
assigned any RT bandwidth. And RT bandwidth is not inherited, each new
cgroup starts with 0 b/w.
Signed-off-by: Ben Gray <ben.r.gray@gmail.com>
There's no point in changing directory here. Syscalls are resolved local
to the linkpath, not to the current directory that the process was in
when creating the symlink. Changing directories just confuses people who
are trying to debug things.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
Comparisons with paths aren't really a good idea unless you're
guaranteed that the comparison will work will all paths that resolve to
the same lexical path as the compared path.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
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>
Prior to this change a cgroup with a `:` character in it's path was not
parsed correctly (as occurs on some instances of systemd cgroups under
some versions of systemd, e.g. 225 with accounting).
This fixes that issue and adds a test.
Signed-off-by: Euan Kemp <euank@coreos.com>
This adds an `--no-new-keyring` flag to run and create so that a new
session keyring is not created for the container and the calling
processes keyring is inherited.
Fixes#818
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
Delegate is only available in systemd >218, applying it for older systemd will
result in an error. Therefore we should check for it when testing systemd
properties.
Signed-off-by: Daniel, Dao Quang Minh <dqminh89@gmail.com>
Kernel memory cannot be set in these circumstances (before kernel 4.6):
1. kernel memory is not initialized, and there are tasks in cgroup
2. kernel memory is not initialized, and use_hierarchy is enabled,
and there are sub-cgroups
While we don't need to cover case 2 because when we set kernel
memory in runC, it's either:
- in Apply phase when we create the container, and in this case,
set kernel memory would definitely be valid;
- or in update operation, and in this case, there would be tasks
in cgroup, we only need to check if kernel memory is initialized
or not.
Even if we want to check use_hierarchy, we need to check sub-cgroups
as well, but for here, we can just leave it aside.
Signed-off-by: Qiang Huang <h.huangqiang@huawei.com>
In user namespaces, we need to make sure we don't chown() the console to
unmapped users. This means we need to get both the UID and GID of the
root user in the container when changing the owner.
Signed-off-by: Aleksa Sarai <asarai@suse.de>
Fix the following warnings when building runc with gcc 6+:
Godeps/_workspace/src/github.com/opencontainers/runc/libcontainer/nsenter/nsexec.c:
In function ‘nsexec’:
Godeps/_workspace/src/github.com/opencontainers/runc/libcontainer/nsenter/nsexec.c:322:6:
warning: ‘__s’ may be used uninitialized in this function
[-Wmaybe-uninitialized]
pr_perror("Failed to open %s", ns);
Godeps/_workspace/src/github.com/opencontainers/runc/libcontainer/nsenter/nsexec.c:273:30:
note: ‘__s’ was declared here
static struct nsenter_config process_nl_attributes(int pipenum, char
*data, int data_size)
^~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Antonio Murdaca <runcom@redhat.com>
`libcontainer/cgroups/utils.go` uses an incorrect path to the
documentation for cgroups. This updates the comment to use the correct
URL. Fixes#794.
Signed-off-by: Jim Berlage <james.berlage@gmail.com>
See https://github.com/docker/docker/issues/22252
Previously we would apply seccomp rules before applying
capabilities, because it requires CAP_SYS_ADMIN. This
however means that a seccomp profile needs to allow
operations such as setcap() and setuid() which you
might reasonably want to disallow.
If prctl(PR_SET_NO_NEW_PRIVS) has been applied however
setting a seccomp filter is an unprivileged operation.
Therefore if this has been set, apply the seccomp
filter as late as possible, after capabilities have
been dropped and the uid set.
Note a small number of syscalls will take place
after the filter is applied, such as `futex`,
`stat` and `execve`, so these still need to be allowed
in addition to any the program itself needs.
Signed-off-by: Justin Cormack <justin.cormack@docker.com>
Avoid parsing the whole lines of mountinfo after all mountpoints
of the target subsytems are found, or when the target subsystem
is not enabled.
Signed-off-by: Tatsushi Inagaki <e29253@jp.ibm.com>
Remove a wrongly added include which was added in commit 3c2e77ee (Add a
compatibility header for CentOS/RHEL 6, 2016-01-29) apparently to
fix this compile error on centos 6:
> In file included from
> Godeps/_workspace/src/github.com/opencontainers/runc/libcontainer/nsenter/nsexec.c:20:
> /usr/include/linux/netlink.h:35: error: expected specifier-qualifier-list before 'sa_family_t'
The glibc bits/sockaddr.h says that this header should never be included
directly[1]. Instead, sys/socket.h should be used.
The problem was correctly fixed later, in commit 394fb55 (Fix build
error on centos6, 2016-03-02) so the incorrect bits/sockaddr.h can
safely be removed.
This is needed to build musl libc.
Fixes#761
[1]: 20003c4988/bits/sockaddr.h (L20)
Signed-off-by: Natanael Copa <natanael.copa@docker.com>
Derek Carr
Aleksa Sarai
Michael Crosby
Mrunal Patel
Dan Walsh
rajasec
Daniel, Dao Quang Minh
Shukui Yang
Wang Long
Xianglin Gao
Mrunal Patel
Qiang Huang
William Martin
Justin Cormack
Peng Gao
Akihiro Suda
Yuanhong Peng
Adam Thomason
Zhang Wei
Alexander Morozov
xiekeyang
Phil Estes
Carl Henrik Lunde
Zhao Lei
Serge Hallyn
Aleksa Sarai
Haiyan Meng
Buddha Prakash
Seth Jennings
Guilherme Rezende
Haiyan Meng
Yen-Lin Chen
Hushan Jia
Yang Hongyang
Vishnu kannan
Ben
ben
Petar Petrov
Euan Kemp
Christian Brauner
Joe Farrell
Michael Holzheu
Andrew Vagin
Bhanu Valasa
Antonio Murdaca
Kenfe-Mickael Laventure
Jim Berlage
Bryan Boreham
Tatsushi Inagaki
Natanael Copa