moby--moby/oci/defaults.go

227 lines
4.9 KiB
Go
Raw Normal View History

package oci
import (
"os"
"runtime"
"github.com/opencontainers/runtime-spec/specs-go"
)
func iPtr(i int64) *int64 { return &i }
func u32Ptr(i int64) *uint32 { u := uint32(i); return &u }
func fmPtr(i int64) *os.FileMode { fm := os.FileMode(i); return &fm }
func defaultCapabilities() []string {
return []string{
"CAP_CHOWN",
"CAP_DAC_OVERRIDE",
"CAP_FSETID",
"CAP_FOWNER",
"CAP_MKNOD",
"CAP_NET_RAW",
"CAP_SETGID",
"CAP_SETUID",
"CAP_SETFCAP",
"CAP_SETPCAP",
"CAP_NET_BIND_SERVICE",
"CAP_SYS_CHROOT",
"CAP_KILL",
"CAP_AUDIT_WRITE",
}
}
// DefaultSpec returns the default spec used by docker for the current Platform
func DefaultSpec() specs.Spec {
return DefaultOSSpec(runtime.GOOS)
}
// DefaultOSSpec returns the spec for a given OS
func DefaultOSSpec(osName string) specs.Spec {
if osName == "windows" {
return DefaultWindowsSpec()
} else if osName == "solaris" {
return DefaultSolarisSpec()
} else {
return DefaultLinuxSpec()
}
}
// DefaultWindowsSpec create a default spec for running Windows containers
func DefaultWindowsSpec() specs.Spec {
return specs.Spec{
Version: specs.Version,
Windows: &specs.Windows{},
Process: &specs.Process{},
Root: &specs.Root{},
}
}
// DefaultSolarisSpec create a default spec for running Solaris containers
func DefaultSolarisSpec() specs.Spec {
s := specs.Spec{
Version: "0.6.0",
}
s.Solaris = &specs.Solaris{}
return s
}
// DefaultLinuxSpec create a default spec for running Linux containers
func DefaultLinuxSpec() specs.Spec {
s := specs.Spec{
Version: specs.Version,
Process: &specs.Process{},
Root: &specs.Root{},
}
s.Mounts = []specs.Mount{
{
Destination: "/proc",
Type: "proc",
Source: "proc",
Options: []string{"nosuid", "noexec", "nodev"},
},
{
Destination: "/dev",
Type: "tmpfs",
Source: "tmpfs",
Options: []string{"nosuid", "strictatime", "mode=755", "size=65536k"},
},
{
Destination: "/dev/pts",
Type: "devpts",
Source: "devpts",
Options: []string{"nosuid", "noexec", "newinstance", "ptmxmode=0666", "mode=0620", "gid=5"},
},
{
Destination: "/sys",
Type: "sysfs",
Source: "sysfs",
Options: []string{"nosuid", "noexec", "nodev", "ro"},
},
{
Destination: "/sys/fs/cgroup",
Type: "cgroup",
Source: "cgroup",
Options: []string{"ro", "nosuid", "noexec", "nodev"},
},
{
Destination: "/dev/mqueue",
Type: "mqueue",
Source: "mqueue",
Options: []string{"nosuid", "noexec", "nodev"},
},
Implement none, private, and shareable ipc modes Since the commit d88fe447df0e8 ("Add support for sharing /dev/shm/ and /dev/mqueue between containers") container's /dev/shm is mounted on the host first, then bind-mounted inside the container. This is done that way in order to be able to share this container's IPC namespace (and the /dev/shm mount point) with another container. Unfortunately, this functionality breaks container checkpoint/restore (even if IPC is not shared). Since /dev/shm is an external mount, its contents is not saved by `criu checkpoint`, and so upon restore any application that tries to access data under /dev/shm is severily disappointed (which usually results in a fatal crash). This commit solves the issue by introducing new IPC modes for containers (in addition to 'host' and 'container:ID'). The new modes are: - 'shareable': enables sharing this container's IPC with others (this used to be the implicit default); - 'private': disables sharing this container's IPC. In 'private' mode, container's /dev/shm is truly mounted inside the container, without any bind-mounting from the host, which solves the issue. While at it, let's also implement 'none' mode. The motivation, as eloquently put by Justin Cormack, is: > I wondered a while back about having a none shm mode, as currently it is > not possible to have a totally unwriteable container as there is always > a /dev/shm writeable mount. It is a bit of a niche case (and clearly > should never be allowed to be daemon default) but it would be trivial to > add now so maybe we should... ...so here's yet yet another mode: - 'none': no /dev/shm mount inside the container (though it still has its own private IPC namespace). Now, to ultimately solve the abovementioned checkpoint/restore issue, we'd need to make 'private' the default mode, but unfortunately it breaks the backward compatibility. So, let's make the default container IPC mode per-daemon configurable (with the built-in default set to 'shareable' for now). The default can be changed either via a daemon CLI option (--default-shm-mode) or a daemon.json configuration file parameter of the same name. Note one can only set either 'shareable' or 'private' IPC modes as a daemon default (i.e. in this context 'host', 'container', or 'none' do not make much sense). Some other changes this patch introduces are: 1. A mount for /dev/shm is added to default OCI Linux spec. 2. IpcMode.Valid() is simplified to remove duplicated code that parsed 'container:ID' form. Note the old version used to check that ID does not contain a semicolon -- this is no longer the case (tests are modified accordingly). The motivation is we should either do a proper check for container ID validity, or don't check it at all (since it is checked in other places anyway). I chose the latter. 3. IpcMode.Container() is modified to not return container ID if the mode value does not start with "container:", unifying the check to be the same as in IpcMode.IsContainer(). 3. IPC mode unit tests (runconfig/hostconfig_test.go) are modified to add checks for newly added values. [v2: addressed review at https://github.com/moby/moby/pull/34087#pullrequestreview-51345997] [v3: addressed review at https://github.com/moby/moby/pull/34087#pullrequestreview-53902833] [v4: addressed the case of upgrading from older daemon, in this case container.HostConfig.IpcMode is unset and this is valid] [v5: document old and new IpcMode values in api/swagger.yaml] [v6: add the 'none' mode, changelog entry to docs/api/version-history.md] Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
2017-06-27 21:58:50 +00:00
{
Destination: "/dev/shm",
Type: "tmpfs",
Source: "shm",
Options: []string{"nosuid", "noexec", "nodev", "mode=1777"},
},
}
s.Process = &specs.Process{
Capabilities: &specs.LinuxCapabilities{
Bounding: defaultCapabilities(),
Permitted: defaultCapabilities(),
Inheritable: defaultCapabilities(),
Effective: defaultCapabilities(),
},
}
s.Linux = &specs.Linux{
MaskedPaths: []string{
"/proc/kcore",
"/proc/latency_stats",
"/proc/timer_list",
"/proc/timer_stats",
"/proc/sched_debug",
},
ReadonlyPaths: []string{
"/proc/asound",
"/proc/bus",
"/proc/fs",
"/proc/irq",
"/proc/sys",
"/proc/sysrq-trigger",
},
Namespaces: []specs.LinuxNamespace{
{Type: "mount"},
{Type: "network"},
{Type: "uts"},
{Type: "pid"},
{Type: "ipc"},
},
// Devices implicitly contains the following devices:
// null, zero, full, random, urandom, tty, console, and ptmx.
// ptmx is a bind mount or symlink of the container's ptmx.
// See also: https://github.com/opencontainers/runtime-spec/blob/master/config-linux.md#default-devices
Devices: []specs.LinuxDevice{},
Resources: &specs.LinuxResources{
Devices: []specs.LinuxDeviceCgroup{
{
Allow: false,
Access: "rwm",
},
{
Allow: true,
Type: "c",
Major: iPtr(1),
Minor: iPtr(5),
Access: "rwm",
},
{
Allow: true,
Type: "c",
Major: iPtr(1),
Minor: iPtr(3),
Access: "rwm",
},
{
Allow: true,
Type: "c",
Major: iPtr(1),
Minor: iPtr(9),
Access: "rwm",
},
{
Allow: true,
Type: "c",
Major: iPtr(1),
Minor: iPtr(8),
Access: "rwm",
},
{
Allow: true,
Type: "c",
Major: iPtr(5),
Minor: iPtr(0),
Access: "rwm",
},
{
Allow: true,
Type: "c",
Major: iPtr(5),
Minor: iPtr(1),
Access: "rwm",
},
{
Allow: false,
Type: "c",
Major: iPtr(10),
Minor: iPtr(229),
Access: "rwm",
},
},
},
}
// For LCOW support, populate a blank Windows spec
if runtime.GOOS == "windows" {
s.Windows = &specs.Windows{}
}
// For LCOW support, don't mask /sys/firmware
if runtime.GOOS != "windows" {
s.Linux.MaskedPaths = append(s.Linux.MaskedPaths, "/sys/firmware")
}
return s
}