vendor: update runc for helper packages

Signed-off-by: Tonis Tiigi <tonistiigi@gmail.com>

vendor.conf

@@ -75,8 +75,8 @@ github.com/pborman/uuid v1.0
 
 google.golang.org/grpc v1.12.0
 
-# When updating, also update RUNC_COMMIT in hack/dockerfile/install/runc accordingly
-github.com/opencontainers/runc 69663f0bd4b60df09991c08812a60108003fa340
+# This does not need to match RUNC_COMMIT as it is used for helper packages but should be newer or equal
+github.com/opencontainers/runc 0e561642f81e84ebd0b3afd6ec510c75a2ccb71b
 github.com/opencontainers/runtime-spec v1.0.1
 github.com/opencontainers/image-spec v1.0.1
 github.com/seccomp/libseccomp-golang 32f571b70023028bd57d9288c20efbcb237f3ce0

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

@@ -141,9 +141,10 @@ type Config struct {
 
 	// OomScoreAdj specifies the adjustment to be made by the kernel when calculating oom scores
 	// for a process. Valid values are between the range [-1000, '1000'], where processes with
-	// higher scores are preferred for being killed.
+	// higher scores are preferred for being killed. If it is unset then we don't touch the current
+	// value.
 	// More information about kernel oom score calculation here: https://lwn.net/Articles/317814/
-	OomScoreAdj int `json:"oom_score_adj"`
+	OomScoreAdj *int `json:"oom_score_adj,omitempty"`
 
 	// UidMappings is an array of User ID mappings for User Namespaces
 	UidMappings []IDMap `json:"uid_mappings"`

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

@@ -505,7 +505,8 @@ void join_namespaces(char *nslist)
 
 		ns->fd = fd;
 		ns->ns = nsflag(namespace);
-		strncpy(ns->path, path, PATH_MAX);
+		strncpy(ns->path, path, PATH_MAX - 1);
+		ns->path[PATH_MAX - 1] = '\0';
 	} while ((namespace = strtok_r(NULL, ",", &saveptr)) != NULL);
 
 	/*
@@ -678,17 +679,15 @@ void nsexec(void)
 					/*
 					 * Enable setgroups(2) if we've been asked to. But we also
 					 * have to explicitly disable setgroups(2) if we're
-					 * creating a rootless container (this is required since
-					 * Linux 3.19).
+					 * creating a rootless container for single-entry mapping.
+					 * i.e. config.is_setgroup == false.
+					 * (this is required since Linux 3.19).
+					 *
+					 * For rootless multi-entry mapping, config.is_setgroup shall be true and
+					 * newuidmap/newgidmap shall be used.
 					 */
-					if (config.is_rootless && config.is_setgroup) {
-						kill(child, SIGKILL);
-						bail("cannot allow setgroup in an unprivileged user namespace setup");
-					}
 
-					if (config.is_setgroup)
-						update_setgroups(child, SETGROUPS_ALLOW);
-					if (config.is_rootless)
+					if (config.is_rootless && !config.is_setgroup)
 						update_setgroups(child, SETGROUPS_DENY);
 
 					/* Set up mappings. */
@@ -809,25 +808,30 @@ void nsexec(void)
 			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.
+			 *
+			 * We don't unshare all namespaces in one go. The reason for this
+			 * is that, while the kernel documentation may claim otherwise,
+			 * there are certain cases where unsharing all namespaces at once
+			 * will result in namespace objects being owned incorrectly.
+			 * Ideally we should just fix these kernel bugs, but it's better to
+			 * be safe than sorry, and fix them separately.
+			 *
+			 * A specific case of this is that the SELinux label of the
+			 * internal kern-mount that mqueue uses will be incorrect if the
+			 * UTS namespace is cloned before the USER namespace is mapped.
+			 * I've also heard of similar problems with the network namespace
+			 * in some scenarios. This also mirrors how LXC deals with this
+			 * problem.
 			 */
 			if (config.cloneflags & CLONE_NEWUSER) {
+				if (unshare(CLONE_NEWUSER) < 0)
+					bail("failed to unshare user namespace");
+				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.
@@ -853,8 +857,21 @@ void nsexec(void)
 					if (prctl(PR_SET_DUMPABLE, 0, 0, 0, 0) < 0)
 						bail("failed to set process as dumpable");
 				}
+
+				/* Become root in the namespace proper. */
+				if (setresuid(0, 0, 0) < 0)
+					bail("failed to become root in user namespace");
 			}
 
+			/*
+			 * Unshare all of the namespaces. 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.
+			 */
+			if (unshare(config.cloneflags) < 0)
+				bail("failed to unshare namespaces");
+
 			/*
 			 * TODO: What about non-namespace clone flags that we're dropping here?
 			 *

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

@@ -3,13 +3,12 @@
 package system
 
 import (
-	"bufio"
-	"fmt"
 	"os"
 	"os/exec"
 	"syscall" // only for exec
 	"unsafe"
 
+	"github.com/opencontainers/runc/libcontainer/user"
 	"golang.org/x/sys/unix"
 )
 
@@ -102,34 +101,43 @@ func Setctty() error {
 }
 
 // RunningInUserNS detects whether we are currently running in a user namespace.
-// Copied from github.com/lxc/lxd/shared/util.go
+// Originally copied from github.com/lxc/lxd/shared/util.go
 func RunningInUserNS() bool {
-	file, err := os.Open("/proc/self/uid_map")
+	uidmap, err := user.CurrentProcessUIDMap()
 	if err != nil {
 		// This kernel-provided file only exists if user namespaces are supported
 		return false
 	}
-	defer file.Close()
+	return UIDMapInUserNS(uidmap)
+}
 
-	buf := bufio.NewReader(file)
-	l, _, err := buf.ReadLine()
-	if err != nil {
-		return false
-	}
-
-	line := string(l)
-	var a, b, c int64
-	fmt.Sscanf(line, "%d %d %d", &a, &b, &c)
+func UIDMapInUserNS(uidmap []user.IDMap) bool {
 	/*
 	 * We assume we are in the initial user namespace if we have a full
 	 * range - 4294967295 uids starting at uid 0.
 	 */
-	if a == 0 && b == 0 && c == 4294967295 {
+	if len(uidmap) == 1 && uidmap[0].ID == 0 && uidmap[0].ParentID == 0 && uidmap[0].Count == 4294967295 {
 		return false
 	}
 	return true
 }
 
+// GetParentNSeuid returns the euid within the parent user namespace
+func GetParentNSeuid() int {
+	euid := os.Geteuid()
+	uidmap, err := user.CurrentProcessUIDMap()
+	if err != nil {
+		// This kernel-provided file only exists if user namespaces are supported
+		return euid
+	}
+	for _, um := range uidmap {
+		if um.ID <= euid && euid <= um.ID+um.Count-1 {
+			return um.ParentID + euid - um.ID
+		}
+	}
+	return euid
+}
+
 // SetSubreaper sets the value i as the subreaper setting for the calling process
 func SetSubreaper(i int) error {
 	return unix.Prctl(PR_SET_CHILD_SUBREAPER, uintptr(i), 0, 0, 0)

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

@@ -2,8 +2,26 @@
 
 package system
 
+import (
+	"os"
+
+	"github.com/opencontainers/runc/libcontainer/user"
+)
+
 // RunningInUserNS is a stub for non-Linux systems
 // Always returns false
 func RunningInUserNS() bool {
 	return false
 }
+
+// UIDMapInUserNS is a stub for non-Linux systems
+// Always returns false
+func UIDMapInUserNS(uidmap []user.IDMap) bool {
+	return false
+}
+
+// GetParentNSeuid returns the euid within the parent user namespace
+// Always returns os.Geteuid on non-linux
+func GetParentNSeuid() int {
+	return os.Geteuid()
+}

vendor/github.com/opencontainers/runc/libcontainer/user/lookup_unix.go

@@ -114,3 +114,29 @@ func CurrentUser() (User, error) {
 func CurrentGroup() (Group, error) {
 	return LookupGid(unix.Getgid())
 }
+
+func CurrentUserSubUIDs() ([]SubID, error) {
+	u, err := CurrentUser()
+	if err != nil {
+		return nil, err
+	}
+	return ParseSubIDFileFilter("/etc/subuid",
+		func(entry SubID) bool { return entry.Name == u.Name })
+}
+
+func CurrentGroupSubGIDs() ([]SubID, error) {
+	g, err := CurrentGroup()
+	if err != nil {
+		return nil, err
+	}
+	return ParseSubIDFileFilter("/etc/subgid",
+		func(entry SubID) bool { return entry.Name == g.Name })
+}
+
+func CurrentProcessUIDMap() ([]IDMap, error) {
+	return ParseIDMapFile("/proc/self/uid_map")
+}
+
+func CurrentProcessGIDMap() ([]IDMap, error) {
+	return ParseIDMapFile("/proc/self/gid_map")
+}

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

@@ -75,12 +75,29 @@ func groupFromOS(g *user.Group) (Group, error) {
 	return newGroup, nil
 }
 
+// SubID represents an entry in /etc/sub{u,g}id
+type SubID struct {
+	Name  string
+	SubID int
+	Count int
+}
+
+// IDMap represents an entry in /proc/PID/{u,g}id_map
+type IDMap struct {
+	ID       int
+	ParentID int
+	Count    int
+}
+
 func parseLine(line string, v ...interface{}) {
-	if line == "" {
+	parseParts(strings.Split(line, ":"), v...)
+}
+
+func parseParts(parts []string, v ...interface{}) {
+	if len(parts) == 0 {
 		return
 	}
 
-	parts := strings.Split(line, ":")
 	for i, p := range parts {
 		// Ignore cases where we don't have enough fields to populate the arguments.
 		// Some configuration files like to misbehave.
@@ -479,3 +496,111 @@ func GetAdditionalGroupsPath(additionalGroups []string, groupPath string) ([]int
 	}
 	return GetAdditionalGroups(additionalGroups, group)
 }
+
+func ParseSubIDFile(path string) ([]SubID, error) {
+	subid, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer subid.Close()
+	return ParseSubID(subid)
+}
+
+func ParseSubID(subid io.Reader) ([]SubID, error) {
+	return ParseSubIDFilter(subid, nil)
+}
+
+func ParseSubIDFileFilter(path string, filter func(SubID) bool) ([]SubID, error) {
+	subid, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer subid.Close()
+	return ParseSubIDFilter(subid, filter)
+}
+
+func ParseSubIDFilter(r io.Reader, filter func(SubID) bool) ([]SubID, error) {
+	if r == nil {
+		return nil, fmt.Errorf("nil source for subid-formatted data")
+	}
+
+	var (
+		s   = bufio.NewScanner(r)
+		out = []SubID{}
+	)
+
+	for s.Scan() {
+		if err := s.Err(); err != nil {
+			return nil, err
+		}
+
+		line := strings.TrimSpace(s.Text())
+		if line == "" {
+			continue
+		}
+
+		// see: man 5 subuid
+		p := SubID{}
+		parseLine(line, &p.Name, &p.SubID, &p.Count)
+
+		if filter == nil || filter(p) {
+			out = append(out, p)
+		}
+	}
+
+	return out, nil
+}
+
+func ParseIDMapFile(path string) ([]IDMap, error) {
+	r, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer r.Close()
+	return ParseIDMap(r)
+}
+
+func ParseIDMap(r io.Reader) ([]IDMap, error) {
+	return ParseIDMapFilter(r, nil)
+}
+
+func ParseIDMapFileFilter(path string, filter func(IDMap) bool) ([]IDMap, error) {
+	r, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer r.Close()
+	return ParseIDMapFilter(r, filter)
+}
+
+func ParseIDMapFilter(r io.Reader, filter func(IDMap) bool) ([]IDMap, error) {
+	if r == nil {
+		return nil, fmt.Errorf("nil source for idmap-formatted data")
+	}
+
+	var (
+		s   = bufio.NewScanner(r)
+		out = []IDMap{}
+	)
+
+	for s.Scan() {
+		if err := s.Err(); err != nil {
+			return nil, err
+		}
+
+		line := strings.TrimSpace(s.Text())
+		if line == "" {
+			continue
+		}
+
+		// see: man 7 user_namespaces
+		p := IDMap{}
+		parseParts(strings.Fields(line), &p.ID, &p.ParentID, &p.Count)
+
+		if filter == nil || filter(p) {
+			out = append(out, p)
+		}
+	}
+
+	return out, nil
+}