This removes vndr, and swiches to native Go Modules instead. All modules
are kept on the old version.
Keeps the vendor/ dir, so everything is backwards compatible.
Signed-off-by: Odin Ugedal <odin@ugedal.com>
I'm nominating Akihiro to be added as a maintainer for runc. Akihiro has been a
frequent contributor to this project, bringing expertise in important areas, such
as cgroups v2 and rootless containers.
Akihiro has experience with collaborating on, and maintaining various mainstream
open source projects in the container ecosystem, and as such would be a great
addition to the list of maintainers to help this project moving forward.
With this pull request, I invite the maintainers to vote on this PR, as described
in the maintainers guide;
602c85fdc6/MAINTAINERS_GUIDE.md (how-are-maintainers-added)
> The final vote to add a new maintainer should be approved by over 66% of the
> current maintainers with the chief maintainer having veto power. In case of a
> veto, conflict resolution rules expressed above apply. The voting period is
> five business days on the Pull Request to add the new maintainer.
Signed-off-by: Sebastiaan van Stijn <github@gone.nl>
Some systemd properties are documented as having "Sec" suffix
(e.g. "TimeoutStopSec") but are expected to have "USec" suffix
when passed over dbus, so let's provide appropriate conversion
to improve compatibility.
This means, one can specify TimeoutStopSec with a numeric argument,
in seconds, and it will be properly converted to TimeoutStopUsec
with the argument in microseconds. As a side bonus, even float
values are converted, so e.g. TimeoutStopSec=1.5 is possible.
This turned out a bit more tricky to implement when I was
originally expected, since there are a handful of numeric
types in dbus and each one requires explicit conversion.
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
In case systemd is used to set cgroups for the container,
it creates a scope unit dedicated to it (usually named
`runc-$ID.scope`).
This patch adds an ability to set arbitrary systemd properties
for the systemd unit via runtime spec annotations.
Initially this was developed as an ability to specify the
`TimeoutStopUSec` property, but later generalized to work with
arbitrary ones.
Example usage: add the following to runtime spec (config.json):
```
"annotations": {
"org.systemd.property.TimeoutStopUSec": "uint64 123456789",
"org.systemd.property.CollectMode":"'inactive-or-failed'"
},
```
and start the container (e.g. `runc --systemd-cgroup run $ID`).
The above will set the following systemd parameters:
* `TimeoutStopSec` to 2 minutes and 3 seconds,
* `CollectMode` to "inactive-or-failed".
The values are in the gvariant format (see [1]). To figure out
which type systemd expects for a particular parameter, see
systemd sources.
In particular, parameters with `USec` suffix require an `uint64`
typed argument, while gvariant assumes int32 for a numeric values,
therefore the explicit type is required.
NOTE that systemd receives the time-typed parameters as *USec
but shows them (in `systemctl show`) as *Sec. For example,
the stop timeout should be set as `TimeoutStopUSec` but
is shown as `TimeoutStopSec`.
[1] https://developer.gnome.org/glib/stable/gvariant-text.html
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
Adrian reported that the checkpoint test stated failing:
=== RUN TestCheckpoint
--- FAIL: TestCheckpoint (0.38s)
checkpoint_test.go:297: Did not restore the pipe correctly:
The problem here is when we start exec.Cmd, we don't call its wait
method. This means that we don't wait cmd.goroutines ans so we don't
know when all data will be read from process pipes.
Signed-off-by: Andrei Vagin <avagin@gmail.com>
Update the set of Go versions (and use 1.x to always test the latest
release), as well as making the cgroupv2 tests allowable failures (the
vagrant setup seems to break pretty often, causing flaky failures).
Signed-off-by: Aleksa Sarai <asarai@suse.de>
mount(2) will blindly follow symlinks, which is a problem because it
allows a malicious container to trick runc into mounting /proc to an
entirely different location (and thus within the attacker's control for
a rename-exchange attack).
This is just a hotfix (to "stop the bleeding"), and the more complete
fix would be finish libpathrs and port runc to it (to avoid these types
of attacks entirely, and defend against a variety of other /proc-related
attacks). It can be bypased by someone having "/" be a volume controlled
by another container.
Fixes: CVE-2019-19921
Signed-off-by: Aleksa Sarai <asarai@suse.de>
A new method was added to the cgroup interface when #2177 was merged.
After #2177 got merged, #2169 was merged without rebase (sorry!) and compilation was failing:
libcontainer/cgroups/fs2/fs2.go:208:22: container.Cgroup undefined (type *configs.Config has no field or method Cgroup)
Signed-off-by: Akihiro Suda <akihiro.suda.cz@hco.ntt.co.jp>
Odin Ugedal
Michael Crosby
Kenta Tada
Akihiro Suda
Brian Goff
Aleksa Sarai
Sebastiaan van Stijn
Qiang Huang
Boris Popovschi
Kir Kolyshkin
Mrunal Patel
Andrei Vagin
wanghuaiqing
Amye Scavarda Perrin
Kohei Ota