Set init processes as non-dumpable

This sets the init processes that join and setup the container's
namespaces as non-dumpable before they setns to the container's pid (or
any other ) namespace.

This settings is automatically reset to the default after the Exec in
the container so that it does not change functionality for the
applications that are running inside, just our init processes.

This prevents parent processes, the pid 1 of the container, to ptrace
the init process before it drops caps and other sets LSMs.

This patch also ensures that the stateDirFD being used is still closed
prior to exec, even though it is set as O_CLOEXEC, because of the order
in the kernel.

https://github.com/torvalds/linux/blob/v4.9/fs/exec.c#L1290-L1318

The order during the exec syscall is that the process is set back to
dumpable before O_CLOEXEC are processed.

Signed-off-by: Michael Crosby <crosbymichael@gmail.com>

libcontainer/init_linux.go

@@ -77,8 +77,9 @@ func newContainerInit(t initType, pipe *os.File, stateDirFD int) (initer, error)
 	switch t {
 	case initSetns:
 		return &linuxSetnsInit{
-			pipe:   pipe,
-			config: config,
+			pipe:       pipe,
+			config:     config,
+			stateDirFD: stateDirFD,
 		}, nil
 	case initStandard:
 		return &linuxStandardInit{

libcontainer/nsenter/nsexec.c

@@ -424,6 +424,11 @@ void nsexec(void)
 	if (pipenum == -1)
 		return;
 
+	/* make the process non-dumpable */
+	if (prctl(PR_SET_DUMPABLE, 0, 0, 0, 0) != 0) {
+		bail("failed to set process as non-dumpable");
+	}
+
 	/* Parse all of the netlink configuration. */
 	nl_parse(pipenum, &config);
 

libcontainer/setns_init_linux.go

@@ -5,6 +5,7 @@ package libcontainer
 import (
 	"fmt"
 	"os"
+	"syscall"
 
 	"github.com/opencontainers/runc/libcontainer/apparmor"
 	"github.com/opencontainers/runc/libcontainer/keys"
@@ -16,8 +17,9 @@ import (
 // linuxSetnsInit performs the container's initialization for running a new process
 // inside an existing container.
 type linuxSetnsInit struct {
-	pipe   *os.File
-	config *initConfig
+	pipe       *os.File
+	config     *initConfig
+	stateDirFD int
 }
 
 func (l *linuxSetnsInit) getSessionRingName() string {
@@ -58,5 +60,8 @@ func (l *linuxSetnsInit) Init() error {
 	if err := label.SetProcessLabel(l.config.ProcessLabel); err != nil {
 		return err
 	}
+	// close the statedir fd before exec because the kernel resets dumpable in the wrong order
+	// https://github.com/torvalds/linux/blob/v4.9/fs/exec.c#L1290-L1318
+	syscall.Close(l.stateDirFD)
 	return system.Execv(l.config.Args[0], l.config.Args[0:], os.Environ())
 }

libcontainer/standard_init_linux.go

@@ -179,6 +179,9 @@ func (l *linuxStandardInit) Init() error {
 			return newSystemErrorWithCause(err, "init seccomp")
 		}
 	}
+	// close the statedir fd before exec because the kernel resets dumpable in the wrong order
+	// https://github.com/torvalds/linux/blob/v4.9/fs/exec.c#L1290-L1318
+	syscall.Close(l.stateDirFD)
 	if err := syscall.Exec(name, l.config.Args[0:], os.Environ()); err != nil {
 		return newSystemErrorWithCause(err, "exec user process")
 	}