Use runc version built without ambient capabilities

Until we can support existing behaviour with `sudo` disable
ambient capabilities in runc build.

Add tests that non root user cannot use default capabilities,
and that capabilities are working as expected.

Test for #27590

Update runc.

Signed-off-by: Justin Cormack <justin.cormack@docker.com>

contrib/syscall-test/Dockerfile

@@ -6,6 +6,10 @@ WORKDIR /usr/src/
 
 RUN gcc -g -Wall -static userns.c -o /usr/bin/userns-test \
 	&& gcc -g -Wall -static ns.c -o /usr/bin/ns-test \
-	&& gcc -g -Wall -static acct.c -o /usr/bin/acct-test
+	&& gcc -g -Wall -static acct.c -o /usr/bin/acct-test \
+	&& gcc -g -Wall -static setuid.c -o /usr/bin/setuid-test \
+	&& gcc -g -Wall -static setgid.c -o /usr/bin/setgid-test \
+	&& gcc -g -Wall -static socket.c -o /usr/bin/socket-test \
+	&& gcc -g -Wall -static raw.c -o /usr/bin/raw-test
 
 RUN [ "$(uname -m)" = "x86_64" ] && gcc -s -m32 -nostdlib exit32.s -o /usr/bin/exit32-test || true

contrib/syscall-test/raw.c

@@ -0,0 +1,14 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <netinet/ip.h>
+#include <netinet/udp.h>
+
+int main() {
+	if (socket(PF_INET, SOCK_RAW, IPPROTO_UDP) == -1) {
+		perror("socket");
+		return 1;
+	}
+
+	return 0;
+}

contrib/syscall-test/setgid.c

@@ -0,0 +1,11 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+
+int main() {
+	if (setgid(1) == -1) {
+		perror("setgid");
+		return 1;
+	}
+	return 0;
+}

contrib/syscall-test/setuid.c

@@ -0,0 +1,11 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+
+int main() {
+	if (setuid(1) == -1) {
+		perror("setuid");
+		return 1;
+	}
+	return 0;
+}

contrib/syscall-test/socket.c

@@ -0,0 +1,30 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+
+int main() {
+	int s;
+	struct sockaddr_in sin;
+
+	s = socket(AF_INET, SOCK_STREAM, 0);
+	if (s == -1) {
+		perror("socket");
+		return 1;
+	}
+
+	sin.sin_family = AF_INET;
+	sin.sin_addr.s_addr = INADDR_ANY;
+	sin.sin_port = htons(80);
+
+	if (bind(s, (struct sockaddr *)&sin, sizeof(sin)) == -1) {
+		perror("bind");
+		return 1;
+	}
+
+	close(s);
+
+	return 0;
+}

hack/dockerfile/install-binaries.sh

@@ -3,7 +3,7 @@ set -e
 set -x
 
 TOMLV_COMMIT=9baf8a8a9f2ed20a8e54160840c492f937eeaf9a
-RUNC_COMMIT=02f8fa7863dd3f82909a73e2061897828460d52f
+RUNC_COMMIT=ac031b5bf1cc92239461125f4c1ffb760522bbf2
 CONTAINERD_COMMIT=52ef1ceb4b660c42cf4ea9013180a5663968d4c7
 GRIMES_COMMIT=fe069a03affd2547fdb05e5b8b07202d2e41735b
 LIBNETWORK_COMMIT=0f534354b813003a754606689722fe253101bc4e
@@ -20,11 +20,12 @@ else
 	export GOPATH="$TMP_GOPATH"
 fi
 
+# Do not build with ambient capabilities support
 RUNC_BUILDTAGS="${RUNC_BUILDTAGS:-"seccomp apparmor selinux"}"
 
 install_runc() {
 	echo "Install runc version $RUNC_COMMIT"
-	git clone https://github.com/opencontainers/runc.git "$GOPATH/src/github.com/opencontainers/runc"
+	git clone https://github.com/docker/runc.git "$GOPATH/src/github.com/opencontainers/runc"
 	cd "$GOPATH/src/github.com/opencontainers/runc"
 	git checkout -q "$RUNC_COMMIT"
 	make BUILDTAGS="$RUNC_BUILDTAGS" $1

integration-cli/docker_cli_run_unix_test.go

@@ -1155,24 +1155,185 @@ func (s *DockerSuite) TestRunNoNewPrivSetuid(c *check.C) {
 	}
 }
 
-func (s *DockerSuite) TestRunAmbientCapabilities(c *check.C) {
-	testRequires(c, DaemonIsLinux, ambientCapabilities)
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesChown(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
 
-	// test that a non root user can gain capabilities
-	runCmd := exec.Command(dockerBinary, "run", "--user", "1000", "--cap-add", "chown", "busybox", "chown", "100", "/tmp")
+	// test that a root user has default capability CAP_CHOWN
+	runCmd := exec.Command(dockerBinary, "run", "busybox", "chown", "100", "/tmp")
 	_, _, err := runCommandWithOutput(runCmd)
 	c.Assert(err, check.IsNil)
-	// test that non root user has default capabilities
-	runCmd = exec.Command(dockerBinary, "run", "--user", "1000", "busybox", "chown", "100", "/tmp")
-	_, _, err = runCommandWithOutput(runCmd)
-	c.Assert(err, check.IsNil)
-	// test this fails without cap_chown
-	runCmd = exec.Command(dockerBinary, "run", "--user", "1000", "--cap-drop", "chown", "busybox", "chown", "100", "/tmp")
+	// test that non root user does not have default capability CAP_CHOWN
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "busybox", "chown", "100", "/tmp")
 	out, _, err := runCommandWithOutput(runCmd)
 	c.Assert(err, checker.NotNil, check.Commentf(out))
-	c.Assert(strings.TrimSpace(out), checker.Equals, "chown: /tmp: Operation not permitted")
+	c.Assert(out, checker.Contains, "Operation not permitted")
+	// test that root user can drop default capability CAP_CHOWN
+	runCmd = exec.Command(dockerBinary, "run", "--cap-drop", "chown", "busybox", "chown", "100", "/tmp")
+	out, _, err = runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
 }
 
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesDacOverride(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
+
+	// test that a root user has default capability CAP_DAC_OVERRIDE
+	runCmd := exec.Command(dockerBinary, "run", "busybox", "sh", "-c", "echo test > /etc/passwd")
+	_, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, check.IsNil)
+	// test that non root user does not have default capability CAP_DAC_OVERRIDE
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "busybox", "sh", "-c", "echo test > /etc/passwd")
+	out, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Permission denied")
+	// TODO test that root user can drop default capability CAP_DAC_OVERRIDE
+}
+
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesFowner(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
+
+	// test that a root user has default capability CAP_FOWNER
+	runCmd := exec.Command(dockerBinary, "run", "busybox", "chmod", "777", "/etc/passwd")
+	_, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, check.IsNil)
+	// test that non root user does not have default capability CAP_FOWNER
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "busybox", "chmod", "777", "/etc/passwd")
+	out, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+	// TODO test that root user can drop default capability CAP_FOWNER
+}
+
+// TODO CAP_KILL
+
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesSetuid(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
+
+	// test that a root user has default capability CAP_SETUID
+	runCmd := exec.Command(dockerBinary, "run", "syscall-test", "setuid-test")
+	_, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, check.IsNil)
+	// test that non root user does not have default capability CAP_SETUID
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "syscall-test", "setuid-test")
+	out, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+	// test that root user can drop default capability CAP_SETUID
+	runCmd = exec.Command(dockerBinary, "run", "--cap-drop", "setuid", "syscall-test", "setuid-test")
+	out, _, err = runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+}
+
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesSetgid(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
+
+	// test that a root user has default capability CAP_SETGID
+	runCmd := exec.Command(dockerBinary, "run", "syscall-test", "setgid-test")
+	_, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, check.IsNil)
+	// test that non root user does not have default capability CAP_SETGID
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "syscall-test", "setgid-test")
+	out, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+	// test that root user can drop default capability CAP_SETGID
+	runCmd = exec.Command(dockerBinary, "run", "--cap-drop", "setgid", "syscall-test", "setgid-test")
+	out, _, err = runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+}
+
+// TODO CAP_SETPCAP
+
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesNetBindService(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
+
+	// test that a root user has default capability CAP_NET_BIND_SERVICE
+	runCmd := exec.Command(dockerBinary, "run", "syscall-test", "socket-test")
+	_, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, check.IsNil)
+	// test that non root user does not have default capability CAP_NET_BIND_SERVICE
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "syscall-test", "socket-test")
+	out, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Permission denied")
+	// test that root user can drop default capability CAP_NET_BIND_SERVICE
+	runCmd = exec.Command(dockerBinary, "run", "--cap-drop", "net_bind_service", "syscall-test", "socket-test")
+	out, _, err = runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Permission denied")
+}
+
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesNetRaw(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
+
+	// test that a root user has default capability CAP_NET_RAW
+	runCmd := exec.Command(dockerBinary, "run", "syscall-test", "raw-test")
+	_, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, check.IsNil)
+	// test that non root user does not have default capability CAP_NET_RAW
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "syscall-test", "raw-test")
+	out, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+	// test that root user can drop default capability CAP_NET_RAW
+	runCmd = exec.Command(dockerBinary, "run", "--cap-drop", "net_raw", "syscall-test", "raw-test")
+	out, _, err = runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+}
+
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesChroot(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
+
+	// test that a root user has default capability CAP_SYS_CHROOT
+	runCmd := exec.Command(dockerBinary, "run", "busybox", "chroot", "/", "/bin/true")
+	_, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, check.IsNil)
+	// test that non root user does not have default capability CAP_SYS_CHROOT
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "busybox", "chroot", "/", "/bin/true")
+	out, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+	// test that root user can drop default capability CAP_SYS_CHROOT
+	runCmd = exec.Command(dockerBinary, "run", "--cap-drop", "sys_chroot", "busybox", "chroot", "/", "/bin/true")
+	out, _, err = runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+}
+
+func (s *DockerSuite) TestUserNoEffectiveCapabilitiesMknod(c *check.C) {
+	testRequires(c, DaemonIsLinux)
+	ensureSyscallTest(c)
+
+	// test that a root user has default capability CAP_MKNOD
+	runCmd := exec.Command(dockerBinary, "run", "busybox", "mknod", "/tmp/node", "b", "1", "2")
+	_, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, check.IsNil)
+	// test that non root user does not have default capability CAP_MKNOD
+	runCmd = exec.Command(dockerBinary, "run", "--user", "1000:1000", "busybox", "mknod", "/tmp/node", "b", "1", "2")
+	out, _, err := runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+	// test that root user can drop default capability CAP_MKNOD
+	runCmd = exec.Command(dockerBinary, "run", "--cap-drop", "mknod", "busybox", "mknod", "/tmp/node", "b", "1", "2")
+	out, _, err = runCommandWithOutput(runCmd)
+	c.Assert(err, checker.NotNil, check.Commentf(out))
+	c.Assert(out, checker.Contains, "Operation not permitted")
+}
+
+// TODO CAP_AUDIT_WRITE
+// TODO CAP_SETFCAP
+
 func (s *DockerSuite) TestRunApparmorProcDirectory(c *check.C) {
 	testRequires(c, SameHostDaemon, Apparmor)
 

integration-cli/fixtures_linux_daemon.go

@@ -1,6 +1,7 @@
 package main
 
 import (
+	"fmt"
 	"io/ioutil"
 	"os"
 	"os/exec"
@@ -53,15 +54,14 @@ func ensureSyscallTest(c *check.C) {
 	gcc, err := exec.LookPath("gcc")
 	c.Assert(err, checker.IsNil, check.Commentf("could not find gcc"))
 
-	out, err := exec.Command(gcc, "-g", "-Wall", "-static", "../contrib/syscall-test/userns.c", "-o", tmp+"/"+"userns-test").CombinedOutput()
-	c.Assert(err, checker.IsNil, check.Commentf(string(out)))
-	out, err = exec.Command(gcc, "-g", "-Wall", "-static", "../contrib/syscall-test/ns.c", "-o", tmp+"/"+"ns-test").CombinedOutput()
-	c.Assert(err, checker.IsNil, check.Commentf(string(out)))
-	out, err = exec.Command(gcc, "-g", "-Wall", "-static", "../contrib/syscall-test/acct.c", "-o", tmp+"/"+"acct-test").CombinedOutput()
+	tests := []string{"userns", "ns", "acct", "setuid", "setgid", "socket", "raw"}
+	for _, test := range tests {
+		out, err := exec.Command(gcc, "-g", "-Wall", "-static", fmt.Sprintf("../contrib/syscall-test/%s.c", test), "-o", fmt.Sprintf("%s/%s-test", tmp, test)).CombinedOutput()
 		c.Assert(err, checker.IsNil, check.Commentf(string(out)))
+	}
 
 	if runtime.GOOS == "linux" && runtime.GOARCH == "amd64" {
-		out, err = exec.Command(gcc, "-s", "-m32", "-nostdlib", "../contrib/syscall-test/exit32.s", "-o", tmp+"/"+"exit32-test").CombinedOutput()
+		out, err := exec.Command(gcc, "-s", "-m32", "-nostdlib", "../contrib/syscall-test/exit32.s", "-o", tmp+"/"+"exit32-test").CombinedOutput()
 		c.Assert(err, checker.IsNil, check.Commentf(string(out)))
 	}
 

vendor.conf

@@ -59,7 +59,7 @@ github.com/miekg/pkcs11 df8ae6ca730422dba20c768ff38ef7d79077a59f
 github.com/docker/go v1.5.1-1-1-gbaf439e
 github.com/agl/ed25519 d2b94fd789ea21d12fac1a4443dd3a3f79cda72c
 
-github.com/opencontainers/runc 02f8fa7863dd3f82909a73e2061897828460d52f # libcontainer
+github.com/opencontainers/runc ac031b5bf1cc92239461125f4c1ffb760522bbf2 # libcontainer
 github.com/opencontainers/runtime-spec 1c7c27d043c2a5e513a44084d2b10d77d1402b8c # specs
 github.com/seccomp/libseccomp-golang 32f571b70023028bd57d9288c20efbcb237f3ce0
 # libcontainer deps (see src/github.com/opencontainers/runc/Godeps/Godeps.json)

vendor/github.com/opencontainers/runc/libcontainer/configs/cgroup_unix.go

@@ -22,7 +22,7 @@ type Cgroup struct {
 	// The path is assumed to be relative to the host system cgroup mountpoint.
 	Path string `json:"path"`
 
-	// ScopePrefix decribes prefix for the scope name
+	// ScopePrefix describes prefix for the scope name
 	ScopePrefix string `json:"scope_prefix"`
 
 	// Paths represent the absolute cgroups paths to join.
@@ -95,7 +95,7 @@ type Resources struct {
 	// IO read rate limit per cgroup per device, bytes per second.
 	BlkioThrottleReadBpsDevice []*ThrottleDevice `json:"blkio_throttle_read_bps_device"`
 
-	// IO write rate limit per cgroup per divice, bytes per second.
+	// IO write rate limit per cgroup per device, bytes per second.
 	BlkioThrottleWriteBpsDevice []*ThrottleDevice `json:"blkio_throttle_write_bps_device"`
 
 	// IO read rate limit per cgroup per device, IO per second.

vendor/github.com/opencontainers/runc/libcontainer/configs/config.go

@@ -85,11 +85,6 @@ type Config struct {
 	// that the parent process dies.
 	ParentDeathSignal int `json:"parent_death_signal"`
 
-	// PivotDir allows a custom directory inside the container's root filesystem to be used as pivot, when NoPivotRoot is not set.
-	// When a custom PivotDir not set, a temporary dir inside the root filesystem will be used. The pivot dir needs to be writeable.
-	// This is required when using read only root filesystems. In these cases, a read/writeable path can be (bind) mounted somewhere inside the root filesystem to act as pivot.
-	PivotDir string `json:"pivot_dir"`
-
 	// Path to a directory containing the container's root filesystem.
 	Rootfs string `json:"rootfs"`
 

vendor/github.com/opencontainers/runc/libcontainer/configs/mount.go

@@ -1,5 +1,11 @@
 package configs
 
+const (
+	// EXT_COPYUP is a directive to copy up the contents of a directory when
+	// a tmpfs is mounted over it.
+	EXT_COPYUP = 1 << iota
+)
+
 type Mount struct {
 	// Source path for the mount.
 	Source string `json:"source"`
@@ -22,6 +28,9 @@ type Mount struct {
 	// Relabel source if set, "z" indicates shared, "Z" indicates unshared.
 	Relabel string `json:"relabel"`
 
+	// Extensions are additional flags that are specific to runc.
+	Extensions int `json:"extensions"`
+
 	// Optional Command to be run before Source is mounted.
 	PremountCmds []Command `json:"premount_cmds"`
 

vendor/github.com/opencontainers/runc/libcontainer/configs/namespaces_unix.go

@@ -22,8 +22,8 @@ var (
 	supportedNamespaces = make(map[NamespaceType]bool)
 )
 
-// nsToFile converts the namespace type to its filename
-func nsToFile(ns NamespaceType) string {
+// NsName converts the namespace type to its filename
+func NsName(ns NamespaceType) string {
 	switch ns {
 	case NEWNET:
 		return "net"
@@ -50,7 +50,7 @@ func IsNamespaceSupported(ns NamespaceType) bool {
 	if ok {
 		return supported
 	}
-	nsFile := nsToFile(ns)
+	nsFile := NsName(ns)
 	// if the namespace type is unknown, just return false
 	if nsFile == "" {
 		return false
@@ -84,7 +84,7 @@ func (n *Namespace) GetPath(pid int) string {
 	if n.Path != "" {
 		return n.Path
 	}
-	return fmt.Sprintf("/proc/%d/ns/%s", pid, nsToFile(n.Type))
+	return fmt.Sprintf("/proc/%d/ns/%s", pid, NsName(n.Type))
 }
 
 func (n *Namespaces) Remove(t NamespaceType) bool {

vendor/github.com/opencontainers/runc/libcontainer/label/label.go

@@ -9,6 +9,10 @@ func InitLabels(options []string) (string, string, error) {
 	return "", "", nil
 }
 
+func GetROMountLabel() string {
+	return ""
+}
+
 func GenLabels(options string) (string, string, error) {
 	return "", "", nil
 }

vendor/github.com/opencontainers/runc/libcontainer/label/label_selinux.go

@@ -33,15 +33,19 @@ func InitLabels(options []string) (string, string, error) {
 		pcon := selinux.NewContext(processLabel)
 		mcon := selinux.NewContext(mountLabel)
 		for _, opt := range options {
-			if opt == "disable" {
+			val := strings.SplitN(opt, "=", 2)
+			if val[0] != "label" {
+				continue
+			}
+			if len(val) < 2 {
+				return "", "", fmt.Errorf("bad label option %q, valid options 'disable' or \n'user, role, level, type' followed by ':' and a value", opt)
+			}
+			if val[1] == "disable" {
 				return "", "", nil
 			}
-			if i := strings.Index(opt, ":"); i == -1 {
-				return "", "", fmt.Errorf("Bad label option %q, valid options 'disable' or \n'user, role, level, type' followed by ':' and a value", opt)
-			}
-			con := strings.SplitN(opt, ":", 2)
-			if !validOptions[con[0]] {
-				return "", "", fmt.Errorf("Bad label option %q, valid options 'disable, user, role, level, type'", con[0])
+			con := strings.SplitN(val[1], ":", 2)
+			if len(con) < 2 || !validOptions[con[0]] {
+				return "", "", fmt.Errorf("bad label option %q, valid options 'disable, user, role, level, type'", con[0])
 
 			}
 			pcon[con[0]] = con[1]
@@ -55,6 +59,10 @@ func InitLabels(options []string) (string, string, error) {
 	return processLabel, mountLabel, nil
 }
 
+func GetROMountLabel() string {
+	return selinux.GetROFileLabel()
+}
+
 // DEPRECATED: The GenLabels function is only to be used during the transition to the official API.
 func GenLabels(options string) (string, string, error) {
 	return InitLabels(strings.Fields(options))

vendor/github.com/opencontainers/runc/libcontainer/nsenter/namespace.h

@@ -0,0 +1,32 @@
+#ifndef NSENTER_NAMESPACE_H
+#define NSENTER_NAMESPACE_H
+
+#ifndef _GNU_SOURCE
+#	define _GNU_SOURCE
+#endif
+#include <sched.h>
+
+/* All of these are taken from include/uapi/linux/sched.h */
+#ifndef CLONE_NEWNS
+#	define CLONE_NEWNS 0x00020000 /* New mount namespace group */
+#endif
+#ifndef CLONE_NEWCGROUP
+#	define CLONE_NEWCGROUP 0x02000000 /* New cgroup namespace */
+#endif
+#ifndef CLONE_NEWUTS
+#	define CLONE_NEWUTS 0x04000000 /* New utsname namespace */
+#endif
+#ifndef CLONE_NEWIPC
+#	define CLONE_NEWIPC 0x08000000 /* New ipc namespace */
+#endif
+#ifndef CLONE_NEWUSER
+#	define CLONE_NEWUSER 0x10000000 /* New user namespace */
+#endif
+#ifndef CLONE_NEWPID
+#	define CLONE_NEWPID 0x20000000 /* New pid namespace */
+#endif
+#ifndef CLONE_NEWNET
+#	define CLONE_NEWNET 0x40000000 /* New network namespace */
+#endif
+
+#endif /* NSENTER_NAMESPACE_H */

vendor/github.com/opencontainers/runc/libcontainer/nsenter/nsenter.go

@@ -0,0 +1,12 @@
+// +build linux,!gccgo
+
+package nsenter
+
+/*
+#cgo CFLAGS: -Wall
+extern void nsexec();
+void __attribute__((constructor)) init(void) {
+	nsexec();
+}
+*/
+import "C"

vendor/github.com/opencontainers/runc/libcontainer/nsenter/nsenter_gccgo.go

@@ -0,0 +1,25 @@
+// +build linux,gccgo
+
+package nsenter
+
+/*
+#cgo CFLAGS: -Wall
+extern void nsexec();
+void __attribute__((constructor)) init(void) {
+	nsexec();
+}
+*/
+import "C"
+
+// AlwaysFalse is here to stay false
+// (and be exported so the compiler doesn't optimize out its reference)
+var AlwaysFalse bool
+
+func init() {
+	if AlwaysFalse {
+		// by referencing this C init() in a noop test, it will ensure the compiler
+		// links in the C function.
+		// https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65134
+		C.init()
+	}
+}

vendor/github.com/opencontainers/runc/libcontainer/nsenter/nsenter_unsupported.go

@@ -0,0 +1,5 @@
+// +build !linux !cgo
+
+package nsenter
+
+import "C"

vendor/github.com/opencontainers/runc/libcontainer/nsenter/nsexec.c

@@ -0,0 +1,753 @@
+#define _GNU_SOURCE
+#include <endian.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <grp.h>
+#include <sched.h>
+#include <setjmp.h>
+#include <signal.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/ioctl.h>
+#include <sys/prctl.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+#include <linux/limits.h>
+#include <linux/netlink.h>
+#include <linux/types.h>
+
+/* Get all of the CLONE_NEW* flags. */
+#include "namespace.h"
+
+/* Synchronisation values. */
+enum sync_t {
+	SYNC_USERMAP_PLS = 0x40, /* Request parent to map our users. */
+	SYNC_USERMAP_ACK = 0x41, /* Mapping finished by the parent. */
+	SYNC_RECVPID_PLS = 0x42, /* Tell parent we're sending the PID. */
+	SYNC_RECVPID_ACK = 0x43, /* PID was correctly received by parent. */
+
+	/* XXX: This doesn't help with segfaults and other such issues. */
+	SYNC_ERR = 0xFF, /* Fatal error, no turning back. The error code follows. */
+};
+
+/* longjmp() arguments. */
+#define JUMP_PARENT 0x00
+#define JUMP_CHILD  0xA0
+#define JUMP_INIT   0xA1
+
+/* JSON buffer. */
+#define JSON_MAX 4096
+
+/* Assume the stack grows down, so arguments should be above it. */
+struct clone_t {
+	/*
+	 * Reserve some space for clone() to locate arguments
+	 * and retcode in this place
+	 */
+	char stack[4096] __attribute__ ((aligned(16)));
+	char stack_ptr[0];
+
+	/* There's two children. This is used to execute the different code. */
+	jmp_buf *env;
+	int jmpval;
+};
+
+struct nlconfig_t {
+	char *data;
+	uint32_t cloneflags;
+	char *uidmap;
+	size_t uidmap_len;
+	char *gidmap;
+	size_t gidmap_len;
+	char *namespaces;
+	size_t namespaces_len;
+	uint8_t is_setgroup;
+	int consolefd;
+};
+
+/*
+ * List of netlink message types sent to us as part of bootstrapping the init.
+ * These constants are defined in libcontainer/message_linux.go.
+ */
+#define INIT_MSG		62000
+#define CLONE_FLAGS_ATTR	27281
+#define CONSOLE_PATH_ATTR	27282
+#define NS_PATHS_ATTR		27283
+#define UIDMAP_ATTR		27284
+#define GIDMAP_ATTR		27285
+#define SETGROUP_ATTR		27286
+
+/*
+ * Use the raw syscall for versions of glibc which don't include a function for
+ * it, namely (glibc 2.12).
+ */
+#if __GLIBC__ == 2 && __GLIBC_MINOR__ < 14
+#	define _GNU_SOURCE
+#	include "syscall.h"
+#	if !defined(SYS_setns) && defined(__NR_setns)
+#		define SYS_setns __NR_setns
+#	endif
+
+#ifndef SYS_setns
+#	error "setns(2) syscall not supported by glibc version"
+#endif
+
+int setns(int fd, int nstype)
+{
+	return syscall(SYS_setns, fd, nstype);
+}
+#endif
+
+/* XXX: This is ugly. */
+static int syncfd = -1;
+
+/* TODO(cyphar): Fix this so it correctly deals with syncT. */
+#define bail(fmt, ...)								\
+	do {									\
+		int ret = __COUNTER__ + 1;					\
+		fprintf(stderr, "nsenter: " fmt ": %m\n", ##__VA_ARGS__);	\
+		if (syncfd >= 0) {						\
+			enum sync_t s = SYNC_ERR;				\
+			if (write(syncfd, &s, sizeof(s)) != sizeof(s))		\
+				fprintf(stderr, "nsenter: failed: write(s)");	\
+			if (write(syncfd, &ret, sizeof(ret)) != sizeof(ret))	\
+				fprintf(stderr, "nsenter: failed: write(ret)");	\
+		}								\
+		exit(ret);							\
+	} while(0)
+
+static int write_file(char *data, size_t data_len, char *pathfmt, ...)
+{
+	int fd, len, ret = 0;
+	char path[PATH_MAX];
+
+	va_list ap;
+	va_start(ap, pathfmt);
+	len = vsnprintf(path, PATH_MAX, pathfmt, ap);
+	va_end(ap);
+	if (len < 0)
+		return -1;
+
+	fd = open(path, O_RDWR);
+	if (fd < 0) {
+		ret = -1;
+		goto out;
+	}
+
+	len = write(fd, data, data_len);
+	if (len != data_len) {
+		ret = -1;
+		goto out;
+	}
+
+out:
+	close(fd);
+	return ret;
+}
+
+enum policy_t {
+	SETGROUPS_DEFAULT = 0,
+	SETGROUPS_ALLOW,
+	SETGROUPS_DENY,
+};
+
+/* This *must* be called before we touch gid_map. */
+static void update_setgroups(int pid, enum policy_t setgroup)
+{
+	char *policy;
+
+	switch (setgroup) {
+		case SETGROUPS_ALLOW:
+			policy = "allow";
+			break;
+		case SETGROUPS_DENY:
+			policy = "deny";
+			break;
+		case SETGROUPS_DEFAULT:
+			/* Nothing to do. */
+			return;
+	}
+
+	if (write_file(policy, strlen(policy), "/proc/%d/setgroups", pid) < 0) {
+		/*
+		 * If the kernel is too old to support /proc/pid/setgroups,
+		 * open(2) or write(2) will return ENOENT. This is fine.
+		 */
+		if (errno != ENOENT)
+			bail("failed to write '%s' to /proc/%d/setgroups", policy, pid);
+	}
+}
+
+static void update_uidmap(int pid, char *map, int map_len)
+{
+	if (map == NULL || map_len <= 0)
+		return;
+
+	if (write_file(map, map_len, "/proc/%d/uid_map", pid) < 0)
+		bail("failed to update /proc/%d/uid_map", pid);
+}
+
+static void update_gidmap(int pid, char *map, int map_len)
+{
+	if (map == NULL || map_len <= 0)
+		return;
+
+	if (write_file(map, map_len, "/proc/%d/gid_map", pid) < 0)
+		bail("failed to update /proc/%d/gid_map", pid);
+}
+
+/* A dummy function that just jumps to the given jumpval. */
+static int child_func(void *arg) __attribute__ ((noinline));
+static int child_func(void *arg)
+{
+	struct clone_t *ca = (struct clone_t *)arg;
+	longjmp(*ca->env, ca->jmpval);
+}
+
+static int clone_parent(jmp_buf *env, int jmpval) __attribute__ ((noinline));
+static int clone_parent(jmp_buf *env, int jmpval)
+{
+	struct clone_t ca = {
+		.env    = env,
+		.jmpval = jmpval,
+	};
+
+	return clone(child_func, ca.stack_ptr, CLONE_PARENT | SIGCHLD, &ca);
+}
+
+/*
+ * Gets the init pipe fd from the environment, which is used to read the
+ * bootstrap data and tell the parent what the new pid is after we finish
+ * setting up the environment.
+ */
+static int initpipe(void)
+{
+	int pipenum;
+	char *initpipe, *endptr;
+
+	initpipe = getenv("_LIBCONTAINER_INITPIPE");
+	if (initpipe == NULL || *initpipe == '\0')
+		return -1;
+
+	pipenum = strtol(initpipe, &endptr, 10);
+	if (*endptr != '\0')
+		bail("unable to parse _LIBCONTAINER_INITPIPE");
+
+	return pipenum;
+}
+
+/* Returns the clone(2) flag for a namespace, given the name of a namespace. */
+static int nsflag(char *name)
+{
+	if (!strcmp(name, "cgroup"))
+		return CLONE_NEWCGROUP;
+	else if (!strcmp(name, "ipc"))
+		return CLONE_NEWIPC;
+	else if (!strcmp(name, "mnt"))
+		return CLONE_NEWNS;
+	else if (!strcmp(name, "net"))
+		return CLONE_NEWNET;
+	else if (!strcmp(name, "pid"))
+		return CLONE_NEWPID;
+	else if (!strcmp(name, "user"))
+		return CLONE_NEWUSER;
+	else if (!strcmp(name, "uts"))
+		return CLONE_NEWUTS;
+
+	/* If we don't recognise a name, fallback to 0. */
+	return 0;
+}
+
+static uint32_t readint32(char *buf)
+{
+	return *(uint32_t *) buf;
+}
+
+static uint8_t readint8(char *buf)
+{
+	return *(uint8_t *) buf;
+}
+
+static void nl_parse(int fd, struct nlconfig_t *config)
+{
+	size_t len, size;
+	struct nlmsghdr hdr;
+	char *data, *current;
+
+	/* Retrieve the netlink header. */
+	len = read(fd, &hdr, NLMSG_HDRLEN);
+	if (len != NLMSG_HDRLEN)
+		bail("invalid netlink header length %lu", len);
+
+	if (hdr.nlmsg_type == NLMSG_ERROR)
+		bail("failed to read netlink message");
+
+	if (hdr.nlmsg_type != INIT_MSG)
+		bail("unexpected msg type %d", hdr.nlmsg_type);
+
+	/* Retrieve data. */
+	size = NLMSG_PAYLOAD(&hdr, 0);
+	current = data = malloc(size);
+	if (!data)
+		bail("failed to allocate %zu bytes of memory for nl_payload", size);
+
+	len = read(fd, data, size);
+	if (len != size)
+		bail("failed to read netlink payload, %lu != %lu", len, size);
+
+	/* Parse the netlink payload. */
+	config->data = data;
+	config->consolefd = -1;
+	while (current < data + size) {
+		struct nlattr *nlattr = (struct nlattr *)current;
+		size_t payload_len = nlattr->nla_len - NLA_HDRLEN;
+
+		/* Advance to payload. */
+		current += NLA_HDRLEN;
+
+		/* Handle payload. */
+		switch (nlattr->nla_type) {
+		case CLONE_FLAGS_ATTR:
+			config->cloneflags = readint32(current);
+			break;
+		case CONSOLE_PATH_ATTR:
+			/*
+			 * We open the console here because we currently evaluate console
+			 * paths from the *host* namespaces.
+			 */
+			config->consolefd = open(current, O_RDWR);
+			if (config->consolefd < 0)
+				bail("failed to open console %s", current);
+			break;
+		case NS_PATHS_ATTR:
+			config->namespaces = current;
+			config->namespaces_len = payload_len;
+			break;
+		case UIDMAP_ATTR:
+			config->uidmap = current;
+			config->uidmap_len = payload_len;
+			break;
+		case GIDMAP_ATTR:
+			config->gidmap = current;
+			config->gidmap_len = payload_len;
+			break;
+		case SETGROUP_ATTR:
+			config->is_setgroup = readint8(current);
+			break;
+		default:
+			bail("unknown netlink message type %d", nlattr->nla_type);
+		}
+
+		current += NLA_ALIGN(payload_len);
+	}
+}
+
+void nl_free(struct nlconfig_t *config)
+{
+	free(config->data);
+}
+
+void join_namespaces(char *nslist)
+{
+	int num = 0, i;
+	char *saveptr = NULL;
+	char *namespace = strtok_r(nslist, ",", &saveptr);
+	struct namespace_t {
+		int fd;
+		int ns;
+		char type[PATH_MAX];
+		char path[PATH_MAX];
+	} *namespaces = NULL;
+
+	if (!namespace || !strlen(namespace) || !strlen(nslist))
+		bail("ns paths are empty");
+
+	/*
+	 * We have to open the file descriptors first, since after
+	 * we join the mnt namespace we might no longer be able to
+	 * access the paths.
+	 */
+	do {
+		int fd;
+		char *path;
+		struct namespace_t *ns;
+
+		/* Resize the namespace array. */
+		namespaces = realloc(namespaces, ++num * sizeof(struct namespace_t));
+		if (!namespaces)
+			bail("failed to reallocate namespace array");
+		ns = &namespaces[num - 1];
+
+		/* Split 'ns:path'. */
+		path = strstr(namespace, ":");
+		if (!path)
+			bail("failed to parse %s", namespace);
+		*path++ = '\0';
+
+		fd = open(path, O_RDONLY);
+		if (fd < 0)
+			bail("failed to open %s", namespace);
+
+		ns->fd = fd;
+		ns->ns = nsflag(namespace);
+		strncpy(ns->path, path, PATH_MAX);
+	} while ((namespace = strtok_r(NULL, ",", &saveptr)) != NULL);
+
+	/*
+	 * The ordering in which we join namespaces is important. We should
+	 * always join the user namespace *first*. This is all guaranteed
+	 * from the container_linux.go side of this, so we're just going to
+	 * follow the order given to us.
+	 */
+
+	for (i = 0; i < num; i++) {
+		struct namespace_t ns = namespaces[i];
+
+		if (setns(ns.fd, ns.ns) < 0)
+			bail("failed to setns to %s", ns.path);
+
+		close(ns.fd);
+	}
+
+	free(namespaces);
+}
+
+void nsexec(void)
+{
+	int pipenum;
+	jmp_buf env;
+	int syncpipe[2];
+	struct nlconfig_t config = {0};
+
+	/*
+	 * If we don't have an init pipe, just return to the go routine.
+	 * We'll only get an init pipe for start or exec.
+	 */
+	pipenum = initpipe();
+	if (pipenum == -1)
+		return;
+
+	/* Parse all of the netlink configuration. */
+	nl_parse(pipenum, &config);
+
+	/* Pipe so we can tell the child when we've finished setting up. */
+	if (socketpair(AF_LOCAL, SOCK_STREAM, 0, syncpipe) < 0)
+		bail("failed to setup sync pipe between parent and child");
+
+	/* TODO: Currently we aren't dealing with child deaths properly. */
+
+	/*
+	 * Okay, so this is quite annoying.
+	 *
+	 * In order for this unsharing code to be more extensible we need to split
+	 * up unshare(CLONE_NEWUSER) and clone() in various ways. The ideal case
+	 * would be if we did clone(CLONE_NEWUSER) and the other namespaces
+	 * separately, but because of SELinux issues we cannot really do that. But
+	 * we cannot just dump the namespace flags into clone(...) because several
+	 * usecases (such as rootless containers) require more granularity around
+	 * the namespace setup. In addition, some older kernels had issues where
+	 * CLONE_NEWUSER wasn't handled before other namespaces (but we cannot
+	 * handle this while also dealing with SELinux so we choose SELinux support
+	 * over broken kernel support).
+	 *
+	 * However, if we unshare(2) the user namespace *before* we clone(2), then
+	 * all hell breaks loose.
+	 *
+	 * The parent no longer has permissions to do many things (unshare(2) drops
+	 * all capabilities in your old namespace), and the container cannot be set
+	 * up to have more than one {uid,gid} mapping. This is obviously less than
+	 * ideal. In order to fix this, we have to first clone(2) and then unshare.
+	 *
+	 * Unfortunately, it's not as simple as that. We have to fork to enter the
+	 * PID namespace (the PID namespace only applies to children). Since we'll
+	 * have to double-fork, this clone_parent() call won't be able to get the
+	 * PID of the _actual_ init process (without doing more synchronisation than
+	 * I can deal with at the moment). So we'll just get the parent to send it
+	 * for us, the only job of this process is to update
+	 * /proc/pid/{setgroups,uid_map,gid_map}.
+	 *
+	 * And as a result of the above, we also need to setns(2) in the first child
+	 * because if we join a PID namespace in the topmost parent then our child
+	 * will be in that namespace (and it will not be able to give us a PID value
+	 * that makes sense without resorting to sending things with cmsg).
+	 *
+	 * This also deals with an older issue caused by dumping cloneflags into
+	 * clone(2): On old kernels, CLONE_PARENT didn't work with CLONE_NEWPID, so
+	 * we have to unshare(2) before clone(2) in order to do this. This was fixed
+	 * in upstream commit 1f7f4dde5c945f41a7abc2285be43d918029ecc5, and was
+	 * introduced by 40a0d32d1eaffe6aac7324ca92604b6b3977eb0e. As far as we're
+	 * aware, the last mainline kernel which had this bug was Linux 3.12.
+	 * However, we cannot comment on which kernels the broken patch was
+	 * backported to.
+	 *
+	 * -- Aleksa "what has my life come to?" Sarai
+	 */
+
+	switch (setjmp(env)) {
+	/*
+	 * Stage 0: We're in the parent. Our job is just to create a new child
+	 *          (stage 1: JUMP_CHILD) process and write its uid_map and
+	 *          gid_map. That process will go on to create a new process, then
+	 *          it will send us its PID which we will send to the bootstrap
+	 *          process.
+	 */
+	case JUMP_PARENT: {
+			int len;
+			pid_t child;
+			char buf[JSON_MAX];
+
+			/* For debugging. */
+			prctl(PR_SET_NAME, (unsigned long) "runc:[0:PARENT]", 0, 0, 0);
+
+			/* Start the process of getting a container. */
+			child = clone_parent(&env, JUMP_CHILD);
+			if (child < 0)
+				bail("unable to fork: child_func");
+
+			/* State machine for synchronisation with the children. */
+			while (true) {
+				enum sync_t s;
+
+				/* This doesn't need to be global, we're in the parent. */
+				int syncfd = syncpipe[1];
+
+				if (read(syncfd, &s, sizeof(s)) != sizeof(s))
+					bail("failed to sync with child: next state");
+
+				switch (s) {
+				case SYNC_ERR: {
+						/* We have to mirror the error code of the child. */
+						int ret;
+
+						if (read(syncfd, &ret, sizeof(ret)) != sizeof(ret))
+							bail("failed to sync with child: read(error code)");
+
+						exit(ret);
+					}
+					break;
+				case SYNC_USERMAP_PLS:
+					/* Enable setgroups(2) if we've been asked to. */
+					if (config.is_setgroup)
+						update_setgroups(child, SETGROUPS_ALLOW);
+
+					/* Set up mappings. */
+					update_uidmap(child, config.uidmap, config.uidmap_len);
+					update_gidmap(child, config.gidmap, config.gidmap_len);
+
+					s = SYNC_USERMAP_ACK;
+					if (write(syncfd, &s, sizeof(s)) != sizeof(s)) {
+						kill(child, SIGKILL);
+						bail("failed to sync with child: write(SYNC_USERMAP_ACK)");
+					}
+					break;
+				case SYNC_USERMAP_ACK:
+					/* We should _never_ receive acks. */
+					kill(child, SIGKILL);
+					bail("failed to sync with child: unexpected SYNC_USERMAP_ACK");
+					break;
+				case SYNC_RECVPID_PLS: {
+						pid_t old = child;
+
+						/* Get the init_func pid. */
+						if (read(syncfd, &child, sizeof(child)) != sizeof(child)) {
+							kill(old, SIGKILL);
+							bail("failed to sync with child: read(childpid)");
+						}
+
+						/* Send ACK. */
+						s = SYNC_RECVPID_ACK;
+						if (write(syncfd, &s, sizeof(s)) != sizeof(s)) {
+							kill(old, SIGKILL);
+							kill(child, SIGKILL);
+							bail("failed to sync with child: write(SYNC_RECVPID_ACK)");
+						}
+					}
+
+					/* Leave the loop. */
+					goto out;
+				case SYNC_RECVPID_ACK:
+					/* We should _never_ receive acks. */
+					kill(child, SIGKILL);
+					bail("failed to sync with child: unexpected SYNC_RECVPID_ACK");
+					break;
+				}
+			}
+
+		out:
+			/* Send the init_func pid back to our parent. */
+			len = snprintf(buf, JSON_MAX, "{\"pid\": %d}\n", child);
+			if (len < 0) {
+				kill(child, SIGKILL);
+				bail("unable to generate JSON for child pid");
+			}
+			if (write(pipenum, buf, len) != len) {
+				kill(child, SIGKILL);
+				bail("unable to send child pid to bootstrapper");
+			}
+
+			exit(0);
+		}
+
+	/*
+	 * Stage 1: We're in the first child process. Our job is to join any
+	 *          provided user namespaces in the netlink payload. If we've been
+	 *          asked to CLONE_NEWUSER, we will unshare the user namespace and
+	 *          ask our parent (stage 0) to set up our user mappings for us.
+	 *          Then, we unshare the rest of the requested namespaces and
+	 *          create a new child (stage 2: JUMP_INIT).  We then send the
+	 *          child's PID to our parent (stage 0).
+	 */
+	case JUMP_CHILD: {
+			pid_t child;
+			enum sync_t s;
+
+			/* We're in a child and thus need to tell the parent if we die. */
+			syncfd = syncpipe[0];
+
+			/* For debugging. */
+			prctl(PR_SET_NAME, (unsigned long) "runc:[1:CHILD]", 0, 0, 0);
+
+			/*
+			 * We need to setns first. We cannot do this earlier (in stage 0)
+			 * because of the fact that we forked to get here (the PID of
+			 * [stage 2: JUMP_INIT]) would be meaningless). We could send it
+			 * using cmsg(3) but that's just annoying.
+			 */
+			if (config.namespaces)
+				join_namespaces(config.namespaces);
+
+			/*
+			 * Unshare all of the namespaces. Now, it should be noted that this
+			 * ordering might break in the future (especially with rootless
+			 * containers). But for now, it's not possible to split this into
+			 * CLONE_NEWUSER + [the rest] because of some RHEL SELinux issues.
+			 *
+			 * Note that we don't merge this with clone() because there were
+			 * some old kernel versions where clone(CLONE_PARENT | CLONE_NEWPID)
+			 * was broken, so we'll just do it the long way anyway.
+			 */
+			if (unshare(config.cloneflags) < 0)
+				bail("failed to unshare namespaces");
+
+			/*
+			 * Deal with user namespaces first. They are quite special, as they
+			 * affect our ability to unshare other namespaces and are used as
+			 * context for privilege checks.
+			 */
+			if (config.cloneflags & CLONE_NEWUSER) {
+				/*
+				 * We don't have the privileges to do any mapping here (see the
+				 * clone_parent rant). So signal our parent to hook us up.
+				 */
+
+				s = SYNC_USERMAP_PLS;
+				if (write(syncfd, &s, sizeof(s)) != sizeof(s))
+					bail("failed to sync with parent: write(SYNC_USERMAP_PLS)");
+
+				/* ... wait for mapping ... */
+
+				if (read(syncfd, &s, sizeof(s)) != sizeof(s))
+					bail("failed to sync with parent: read(SYNC_USERMAP_ACK)");
+				if (s != SYNC_USERMAP_ACK)
+					bail("failed to sync with parent: SYNC_USERMAP_ACK: got %u", s);
+			}
+
+			/* TODO: What about non-namespace clone flags that we're dropping here? */
+			child = clone_parent(&env, JUMP_INIT);
+			if (child < 0)
+				bail("unable to fork: init_func");
+
+			/* Send the child to our parent, which knows what it's doing. */
+			s = SYNC_RECVPID_PLS;
+			if (write(syncfd, &s, sizeof(s)) != sizeof(s)) {
+				kill(child, SIGKILL);
+				bail("failed to sync with parent: write(SYNC_RECVPID_PLS)");
+			}
+			if (write(syncfd, &child, sizeof(child)) != sizeof(child)) {
+				kill(child, SIGKILL);
+				bail("failed to sync with parent: write(childpid)");
+			}
+
+			/* ... wait for parent to get the pid ... */
+
+			if (read(syncfd, &s, sizeof(s)) != sizeof(s)) {
+				kill(child, SIGKILL);
+				bail("failed to sync with parent: read(SYNC_RECVPID_ACK)");
+			}
+			if (s != SYNC_RECVPID_ACK) {
+				kill(child, SIGKILL);
+				bail("failed to sync with parent: SYNC_RECVPID_ACK: got %u", s);
+			}
+
+			/* Our work is done. [Stage 2: JUMP_INIT] is doing the rest of the work. */
+			exit(0);
+		}
+
+	/*
+	 * Stage 2: We're the final child process, and the only process that will
+	 *          actually return to the Go runtime. Our job is to just do the
+	 *          final cleanup steps and then return to the Go runtime to allow
+	 *          init_linux.go to run.
+	 */
+	case JUMP_INIT: {
+			/*
+			 * We're inside the child now, having jumped from the
+			 * start_child() code after forking in the parent.
+			 */
+			int consolefd = config.consolefd;
+
+			/* We're in a child and thus need to tell the parent if we die. */
+			syncfd = syncpipe[0];
+
+			/* For debugging. */
+			prctl(PR_SET_NAME, (unsigned long) "runc:[2:INIT]", 0, 0, 0);
+
+			if (setsid() < 0)
+				bail("setsid failed");
+
+			if (setuid(0) < 0)
+				bail("setuid failed");
+
+			if (setgid(0) < 0)
+				bail("setgid failed");
+
+			if (setgroups(0, NULL) < 0)
+				bail("setgroups failed");
+
+			if (consolefd != -1) {
+				if (ioctl(consolefd, TIOCSCTTY, 0) < 0)
+					bail("ioctl TIOCSCTTY failed");
+				if (dup3(consolefd, STDIN_FILENO, 0) != STDIN_FILENO)
+					bail("failed to dup stdin");
+				if (dup3(consolefd, STDOUT_FILENO, 0) != STDOUT_FILENO)
+					bail("failed to dup stdout");
+				if (dup3(consolefd, STDERR_FILENO, 0) != STDERR_FILENO)
+					bail("failed to dup stderr");
+			}
+
+			/* Close sync pipes. */
+			close(syncpipe[0]);
+			close(syncpipe[1]);
+
+			/* Free netlink data. */
+			nl_free(&config);
+
+			/* Finish executing, let the Go runtime take over. */
+			return;
+		}
+	default:
+		bail("unexpected jump value");
+		break;
+	}
+
+	/* Should never be reached. */
+	bail("should never be reached");
+}

vendor/github.com/opencontainers/runc/libcontainer/selinux/selinux.go

@@ -355,6 +355,12 @@ func FreeLxcContexts(scon string) {
 	}
 }
 
+var roFileLabel string
+
+func GetROFileLabel() (fileLabel string) {
+	return roFileLabel
+}
+
 func GetLxcContexts() (processLabel string, fileLabel string) {
 	var (
 		val, key string
@@ -399,6 +405,9 @@ func GetLxcContexts() (processLabel string, fileLabel string) {
 			if key == "file" {
 				fileLabel = strings.Trim(val, "\"")
 			}
+			if key == "ro_file" {
+				roFileLabel = strings.Trim(val, "\"")
+			}
 		}
 	}
 
@@ -406,6 +415,9 @@ func GetLxcContexts() (processLabel string, fileLabel string) {
 		return "", ""
 	}
 
+	if roFileLabel == "" {
+		roFileLabel = fileLabel
+	}
 exit:
 	//	mcs := IntToMcs(os.Getpid(), 1024)
 	mcs := uniqMcs(1024)

vendor/github.com/opencontainers/runc/libcontainer/system/proc.go

@@ -14,8 +14,10 @@ func GetProcessStartTime(pid int) (string, error) {
 	if err != nil {
 		return "", err
 	}
+	return parseStartTime(string(data))
+}
 
-	parts := strings.Split(string(data), " ")
+func parseStartTime(stat string) (string, error) {
 	// the starttime is located at pos 22
 	// from the man page
 	//
@@ -23,5 +25,19 @@ func GetProcessStartTime(pid int) (string, error) {
 	// (22)  The  time the process started after system boot.  In kernels before Linux 2.6, this
 	// value was expressed in jiffies.  Since Linux 2.6, the value is expressed in  clock  ticks
 	// (divide by sysconf(_SC_CLK_TCK)).
-	return parts[22-1], nil // starts at 1
+	//
+	// NOTE:
+	// pos 2 could contain space and is inside `(` and `)`:
+	// (2) comm  %s
+	// The filename of the executable, in parentheses.
+	// This is visible whether or not the executable is
+	// swapped out.
+	//
+	// the following is an example:
+	// 89653 (gunicorn: maste) S 89630 89653 89653 0 -1 4194560 29689 28896 0 3 146 32 76 19 20 0 1 0 2971844 52965376 3920 18446744073709551615 1 1 0 0 0 0 0 16781312 137447943 0 0 0 17 1 0 0 0 0 0 0 0 0 0 0 0 0 0
+
+	// get parts after last `)`:
+	s := strings.Split(stat, ")")
+	parts := strings.Split(strings.TrimSpace(s[len(s)-1]), " ")
+	return parts[22-3], nil // starts at 3 (after the filename pos `2`)
 }