Exemplo n.º 1
0
Arquivo: init.go Projeto: nhlfr/rkt
func getContainerSubCgroup(machineID string, canMachinedRegister, unified bool) (string, error) {
	var subcgroup string
	fromUnit, err := util.RunningFromSystemService()
	if err != nil {
		return "", errwrap.Wrap(errors.New("could not determine if we're running from a unit file"), err)
	}
	if fromUnit {
		slice, err := util.GetRunningSlice()
		if err != nil {
			return "", errwrap.Wrap(errors.New("could not get slice name"), err)
		}
		slicePath, err := common.SliceToPath(slice)
		if err != nil {
			return "", errwrap.Wrap(errors.New("could not convert slice name to path"), err)
		}
		unit, err := util.CurrentUnitName()
		if err != nil {
			return "", errwrap.Wrap(errors.New("could not get unit name"), err)
		}
		subcgroup = filepath.Join(slicePath, unit)

		if unified {
			subcgroup = filepath.Join(subcgroup, "payload")
		}
	} else {
		escapedmID := strings.Replace(machineID, "-", "\\x2d", -1)
		machineDir := "machine-" + escapedmID + ".scope"
		if canMachinedRegister {
			// we are not in the final cgroup yet: systemd-nspawn will move us
			// to the correct cgroup later during registration so we can't
			// look it up in /proc/self/cgroup
			subcgroup = filepath.Join("machine.slice", machineDir)
		} else {
			if unified {
				var err error
				subcgroup, err = v2.GetOwnCgroupPath()
				if err != nil {
					return "", errwrap.Wrap(errors.New("could not get own v2 cgroup path"), err)
				}
			} else {
				// when registration is disabled the container will be directly
				// under the current cgroup so we can look it up in /proc/self/cgroup
				ownV1CgroupPath, err := v1.GetOwnCgroupPath("name=systemd")
				if err != nil {
					return "", errwrap.Wrap(errors.New("could not get own v1 cgroup path"), err)
				}
				// systemd-nspawn won't work if we are in the root cgroup. In addition,
				// we want all rkt instances to be in distinct cgroups. Create a
				// subcgroup and add ourselves to it.
				subcgroup = filepath.Join(ownV1CgroupPath, machineDir)
				if err := v1.JoinSubcgroup("systemd", subcgroup); err != nil {
					return "", errwrap.Wrap(fmt.Errorf("error joining %s subcgroup", ownV1CgroupPath), err)
				}
			}
		}
	}

	return subcgroup, nil
}
Exemplo n.º 2
0
Arquivo: init.go Projeto: joshix/rkt
func stage1() int {
	uuid, err := types.NewUUID(flag.Arg(0))
	if err != nil {
		log.FatalE("UUID is missing or malformed", err)
	}

	root := "."
	p, err := stage1commontypes.LoadPod(root, uuid)
	if err != nil {
		log.FatalE("failed to load pod", err)
	}

	// set close-on-exec flag on RKT_LOCK_FD so it gets correctly closed when invoking
	// network plugins
	lfd, err := common.GetRktLockFD()
	if err != nil {
		log.FatalE("failed to get rkt lock fd", err)
	}

	if err := sys.CloseOnExec(lfd, true); err != nil {
		log.FatalE("failed to set FD_CLOEXEC on rkt lock", err)
	}

	mirrorLocalZoneInfo(p.Root)

	flavor, _, err := stage1initcommon.GetFlavor(p)
	if err != nil {
		log.FatalE("failed to get stage1 flavor", err)
	}

	var n *networking.Networking
	if netList.Contained() {
		fps, err := commonnet.ForwardedPorts(p.Manifest)
		if err != nil {
			log.FatalE("error initializing forwarding ports", err)
		}

		noDNS := dnsConfMode.Pairs["resolv"] != "default" // force ignore CNI DNS results
		n, err = networking.Setup(root, p.UUID, fps, netList, localConfig, flavor, noDNS, debug)
		if err != nil {
			log.FatalE("failed to setup network", err)
		}

		if err = n.Save(); err != nil {
			log.PrintE("failed to save networking state", err)
			n.Teardown(flavor, debug)
			return 254
		}

		if len(mdsToken) > 0 {
			hostIP, err := n.GetForwardableNetHostIP()
			if err != nil {
				log.FatalE("failed to get default Host IP", err)
			}

			p.MetadataServiceURL = common.MetadataServicePublicURL(hostIP, mdsToken)
		}
	} else {
		if flavor == "kvm" {
			log.Fatal("flavor kvm requires private network configuration (try --net)")
		}
		if len(mdsToken) > 0 {
			p.MetadataServiceURL = common.MetadataServicePublicURL(localhostIP, mdsToken)
		}
	}

	insecureOptions := stage1initcommon.Stage1InsecureOptions{
		DisablePaths:        disablePaths,
		DisableCapabilities: disableCapabilities,
		DisableSeccomp:      disableSeccomp,
	}

	mnt := fs.NewLoggingMounter(
		fs.MounterFunc(syscall.Mount),
		fs.UnmounterFunc(syscall.Unmount),
		diag.Printf,
	)

	if dnsConfMode.Pairs["resolv"] == "host" {
		stage1initcommon.UseHostResolv(mnt, root)
	}

	if dnsConfMode.Pairs["hosts"] == "host" {
		stage1initcommon.UseHostHosts(mnt, root)
	}

	if mutable {
		if err = stage1initcommon.MutableEnv(p); err != nil {
			log.FatalE("cannot initialize mutable environment", err)
		}
	} else {
		if err = stage1initcommon.ImmutableEnv(p, interactive, privateUsers, insecureOptions); err != nil {
			log.FatalE("cannot initialize immutable environment", err)
		}
	}

	if err := stage1initcommon.SetJournalPermissions(p); err != nil {
		log.PrintE("warning: error setting journal ACLs, you'll need root to read the pod journal", err)
	}

	if flavor == "kvm" {
		kvm.InitDebug(debug)
		if err := KvmNetworkingToSystemd(p, n); err != nil {
			log.FatalE("failed to configure systemd for kvm", err)
		}
	}

	canMachinedRegister := false
	if flavor != "kvm" {
		// kvm doesn't register with systemd right now, see #2664.
		canMachinedRegister = machinedRegister()
	}
	diag.Printf("canMachinedRegister %t", canMachinedRegister)

	args, env, err := getArgsEnv(p, flavor, canMachinedRegister, debug, n, insecureOptions)
	if err != nil {
		log.FatalE("cannot get environment", err)
	}
	diag.Printf("args %q", args)
	diag.Printf("env %q", env)

	// create a separate mount namespace so the cgroup filesystems
	// are unmounted when exiting the pod
	if err := syscall.Unshare(syscall.CLONE_NEWNS); err != nil {
		log.FatalE("error unsharing", err)
	}

	// we recursively make / a "shared and slave" so mount events from the
	// new namespace don't propagate to the host namespace but mount events
	// from the host propagate to the new namespace and are forwarded to
	// its peer group
	// See https://www.kernel.org/doc/Documentation/filesystems/sharedsubtree.txt
	if err := mnt.Mount("", "/", "none", syscall.MS_REC|syscall.MS_SLAVE, ""); err != nil {
		log.FatalE("error making / a slave mount", err)
	}
	if err := mnt.Mount("", "/", "none", syscall.MS_REC|syscall.MS_SHARED, ""); err != nil {
		log.FatalE("error making / a shared and slave mount", err)
	}

	unifiedCgroup, err := cgroup.IsCgroupUnified("/")
	if err != nil {
		log.FatalE("error determining cgroup version", err)
	}
	diag.Printf("unifiedCgroup %t", unifiedCgroup)

	s1Root := common.Stage1RootfsPath(p.Root)
	machineID := stage1initcommon.GetMachineID(p)

	subcgroup, err := getContainerSubCgroup(machineID, canMachinedRegister, unifiedCgroup)
	if err != nil {
		log.FatalE("error getting container subcgroup", err)
	}
	diag.Printf("subcgroup %q", subcgroup)

	if err := ioutil.WriteFile(filepath.Join(p.Root, "subcgroup"),
		[]byte(fmt.Sprintf("%s", subcgroup)), 0644); err != nil {
		log.FatalE("cannot write subcgroup file", err)
	}

	if !unifiedCgroup {
		enabledCgroups, err := v1.GetEnabledCgroups()
		if err != nil {
			log.FatalE("error getting v1 cgroups", err)
		}
		diag.Printf("enabledCgroups %q", enabledCgroups)

		if err := mountHostV1Cgroups(mnt, enabledCgroups); err != nil {
			log.FatalE("couldn't mount the host v1 cgroups", err)
		}

		if !canMachinedRegister {
			if err := v1.JoinSubcgroup("systemd", subcgroup); err != nil {
				log.FatalE(fmt.Sprintf("error joining subcgroup %q", subcgroup), err)
			}
		}

		var serviceNames []string
		for _, app := range p.Manifest.Apps {
			serviceNames = append(serviceNames, stage1initcommon.ServiceUnitName(app.Name))
		}
		diag.Printf("serviceNames %q", serviceNames)

		if err := mountContainerV1Cgroups(mnt, s1Root, enabledCgroups, subcgroup, serviceNames, insecureOptions); err != nil {
			log.FatalE("couldn't mount the container v1 cgroups", err)
		}

	}

	// KVM flavor has a bit different logic in handling pid vs ppid, for details look into #2389
	// it doesn't require the existence of a "ppid", instead it registers the current pid (which
	// will be reused by lkvm binary) as a pod process pid used during entering
	pid_filename := "ppid"
	if flavor == "kvm" {
		pid_filename = "pid"
	}

	if err = stage1common.WritePid(os.Getpid(), pid_filename); err != nil {
		log.FatalE("error writing pid", err)
	}

	if flavor == "kvm" {
		if err := KvmPrepareMounts(s1Root, p); err != nil {
			log.FatalE("error preparing mounts", err)
		}
	}

	err = stage1common.WithClearedCloExec(lfd, func() error {
		return syscall.Exec(args[0], args, env)
	})

	if err != nil {
		log.FatalE(fmt.Sprintf("failed to execute %q", args[0]), err)
	}

	return 0
}