.gitignore

@@ -1 +1 @@
-SOURCES/v1.0.2.tar.gz
+SOURCES/runc-2abd837.tar.gz

.runc.metadata

@@ -1 +1 @@
-3a0bb2a9506981b5a2204fb1591afc827ecaeb45 SOURCES/v1.0.2.tar.gz
+cf7119a838db2963e7af6ecdba90a2cc95ec0d56 SOURCES/runc-2abd837.tar.gz

SOURCES/0001-Revert-Apply-cgroups-earlier.patch

@@ -0,0 +1,62 @@
+From dfb3496c174377b860b62872ce6af951364cc3ac Mon Sep 17 00:00:00 2001
+From: Lokesh Mandvekar <lsm5@fedoraproject.org>
+Date: Tue, 12 Dec 2017 13:22:42 +0530
+Subject: [PATCH] Revert "Apply cgroups earlier"
+
+This reverts commit 7062c7556b71188abc18d7516441ff4b03fbc1fc.
+---
+ libcontainer/process_linux.go | 31 ++++++++++++++-----------------
+ 1 file changed, 14 insertions(+), 17 deletions(-)
+
+diff --git a/libcontainer/process_linux.go b/libcontainer/process_linux.go
+index 149b1126..b8a395af 100644
+--- a/libcontainer/process_linux.go
++++ b/libcontainer/process_linux.go
+@@ -272,6 +272,20 @@ func (p *initProcess) start() error {
+ 		p.process.ops = nil
+ 		return newSystemErrorWithCause(err, "starting init process command")
+ 	}
++	if _, err := io.Copy(p.parentPipe, p.bootstrapData); err != nil {
++		return newSystemErrorWithCause(err, "copying bootstrap data to pipe")
++	}
++	if err := p.execSetns(); err != nil {
++		return newSystemErrorWithCause(err, "running exec setns process for init")
++	}
++	// Save the standard descriptor names before the container process
++	// can potentially move them (e.g., via dup2()).  If we don't do this now,
++	// we won't know at checkpoint time which file descriptor to look up.
++	fds, err := getPipeFds(p.pid())
++	if err != nil {
++		return newSystemErrorWithCausef(err, "getting pipe fds for pid %d", p.pid())
++	}
++	p.setExternalDescriptors(fds)
+ 	// Do this before syncing with child so that no children can escape the
+ 	// cgroup. We don't need to worry about not doing this and not being root
+ 	// because we'd be using the rootless cgroup manager in that case.
+@@ -292,23 +306,6 @@ func (p *initProcess) start() error {
+ 			}
+ 		}
+ 	}()
+-
+-	if _, err := io.Copy(p.parentPipe, p.bootstrapData); err != nil {
+-		return newSystemErrorWithCause(err, "copying bootstrap data to pipe")
+-	}
+-
+-	if err := p.execSetns(); err != nil {
+-		return newSystemErrorWithCause(err, "running exec setns process for init")
+-	}
+-
+-	// Save the standard descriptor names before the container process
+-	// can potentially move them (e.g., via dup2()).  If we don't do this now,
+-	// we won't know at checkpoint time which file descriptor to look up.
+-	fds, err := getPipeFds(p.pid())
+-	if err != nil {
+-		return newSystemErrorWithCausef(err, "getting pipe fds for pid %d", p.pid())
+-	}
+-	p.setExternalDescriptors(fds)
+ 	if err := p.createNetworkInterfaces(); err != nil {
+ 		return newSystemErrorWithCause(err, "creating network interfaces")
+ 	}
+-- 
+2.14.3
+

SOURCES/0001-nsenter-clone-proc-self-exe-to-avoid-exposing-host-b-runc.patch

@@ -0,0 +1,290 @@
+From bf6405284aa3870a39b402309003633a1c230ed9 Mon Sep 17 00:00:00 2001
+From: Aleksa Sarai <asarai@suse.de>
+Date: Wed, 9 Jan 2019 13:40:01 +1100
+Subject: [PATCH 1/1] nsenter: clone /proc/self/exe to avoid exposing host
+ binary to container
+
+There are quite a few circumstances where /proc/self/exe pointing to a
+pretty important container binary is a _bad_ thing, so to avoid this we
+have to make a copy (preferably doing self-clean-up and not being
+writeable).
+
+As a hotfix we require memfd_create(2), but we can always extend this to
+use a scratch MNT_DETACH overlayfs or tmpfs. The main downside to this
+approach is no page-cache sharing for the runc binary (which overlayfs
+would give us) but this is far less complicated.
+
+This is only done during nsenter so that it happens transparently to the
+Go code, and any libcontainer users benefit from it. This also makes
+ExtraFiles and --preserve-fds handling trivial (because we don't need to
+worry about it).
+
+Fixes: CVE-2019-5736
+Co-developed-by: Christian Brauner <christian.brauner@ubuntu.com>
+Signed-off-by: Aleksa Sarai <asarai@suse.de>
+Signed-off-by: Mrunal Patel <mrunalp@gmail.com>
+---
+ libcontainer/nsenter/cloned_binary.c | 221 +++++++++++++++++++++++++++
+ libcontainer/nsenter/nsexec.c        |  11 ++
+ 2 files changed, 232 insertions(+)
+ create mode 100644 libcontainer/nsenter/cloned_binary.c
+
+diff --git a/libcontainer/nsenter/cloned_binary.c b/libcontainer/nsenter/cloned_binary.c
+new file mode 100644
+index 00000000..d9f6093a
+--- /dev/null
++++ b/libcontainer/nsenter/cloned_binary.c
+@@ -0,0 +1,221 @@
++#define _GNU_SOURCE
++#include <unistd.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <stdbool.h>
++#include <string.h>
++#include <limits.h>
++#include <fcntl.h>
++#include <errno.h>
++
++#include <sys/types.h>
++#include <sys/stat.h>
++#include <sys/vfs.h>
++#include <sys/mman.h>
++#include <sys/sendfile.h>
++#include <sys/syscall.h>
++
++#include <linux/magic.h>
++#include <linux/memfd.h>
++
++/* Use our own wrapper for memfd_create. */
++#if !defined(SYS_memfd_create) && defined(__NR_memfd_create)
++#  define SYS_memfd_create __NR_memfd_create
++#endif
++#ifndef SYS_memfd_create
++#  error "memfd_create(2) syscall not supported by this glibc version"
++#endif
++int memfd_create(const char *name, unsigned int flags)
++{
++	return syscall(SYS_memfd_create, name, flags);
++}
++
++/* This comes directly from <linux/fcntl.h>. */
++#ifndef F_LINUX_SPECIFIC_BASE
++#  define F_LINUX_SPECIFIC_BASE 1024
++#endif
++#ifndef F_ADD_SEALS
++#  define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9)
++#  define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10)
++#endif
++#ifndef F_SEAL_SEAL
++#  define F_SEAL_SEAL   0x0001	/* prevent further seals from being set */
++#  define F_SEAL_SHRINK 0x0002	/* prevent file from shrinking */
++#  define F_SEAL_GROW   0x0004	/* prevent file from growing */
++#  define F_SEAL_WRITE  0x0008	/* prevent writes */
++#endif
++
++
++#define OUR_MEMFD_COMMENT "runc_cloned:/proc/self/exe"
++#define OUR_MEMFD_SEALS \
++	(F_SEAL_SEAL | F_SEAL_SHRINK | F_SEAL_GROW | F_SEAL_WRITE)
++
++static void *must_realloc(void *ptr, size_t size)
++{
++	void *old = ptr;
++	do {
++		ptr = realloc(old, size);
++	} while(!ptr);
++	return ptr;
++}
++
++/*
++ * Verify whether we are currently in a self-cloned program (namely, is
++ * /proc/self/exe a memfd). F_GET_SEALS will only succeed for memfds (or rather
++ * for shmem files), and we want to be sure it's actually sealed.
++ */
++static int is_self_cloned(void)
++{
++	int fd, seals;
++
++	fd = open("/proc/self/exe", O_RDONLY|O_CLOEXEC);
++	if (fd < 0)
++		return -ENOTRECOVERABLE;
++
++	seals = fcntl(fd, F_GET_SEALS);
++	close(fd);
++	return seals == OUR_MEMFD_SEALS;
++}
++
++/*
++ * Basic wrapper around mmap(2) that gives you the file length so you can
++ * safely treat it as an ordinary buffer. Only gives you read access.
++ */
++static char *read_file(char *path, size_t *length)
++{
++	int fd;
++	char buf[4096], *copy = NULL;
++
++	if (!length)
++		return NULL;
++
++	fd = open(path, O_RDONLY | O_CLOEXEC);
++	if (fd < 0)
++		return NULL;
++
++	*length = 0;
++	for (;;) {
++		int n;
++
++		n = read(fd, buf, sizeof(buf));
++		if (n < 0)
++			goto error;
++		if (!n)
++			break;
++
++		copy = must_realloc(copy, (*length + n) * sizeof(*copy));
++		memcpy(copy + *length, buf, n);
++		*length += n;
++	}
++	close(fd);
++	return copy;
++
++error:
++	close(fd);
++	free(copy);
++	return NULL;
++}
++
++/*
++ * A poor-man's version of "xargs -0". Basically parses a given block of
++ * NUL-delimited data, within the given length and adds a pointer to each entry
++ * to the array of pointers.
++ */
++static int parse_xargs(char *data, int data_length, char ***output)
++{
++	int num = 0;
++	char *cur = data;
++
++	if (!data || *output != NULL)
++		return -1;
++
++	while (cur < data + data_length) {
++		num++;
++		*output = must_realloc(*output, (num + 1) * sizeof(**output));
++		(*output)[num - 1] = cur;
++		cur += strlen(cur) + 1;
++	}
++	(*output)[num] = NULL;
++	return num;
++}
++
++/*
++ * "Parse" out argv and envp from /proc/self/cmdline and /proc/self/environ.
++ * This is necessary because we are running in a context where we don't have a
++ * main() that we can just get the arguments from.
++ */
++static int fetchve(char ***argv, char ***envp)
++{
++	char *cmdline = NULL, *environ = NULL;
++	size_t cmdline_size, environ_size;
++
++	cmdline = read_file("/proc/self/cmdline", &cmdline_size);
++	if (!cmdline)
++		goto error;
++	environ = read_file("/proc/self/environ", &environ_size);
++	if (!environ)
++		goto error;
++
++	if (parse_xargs(cmdline, cmdline_size, argv) <= 0)
++		goto error;
++	if (parse_xargs(environ, environ_size, envp) <= 0)
++		goto error;
++
++	return 0;
++
++error:
++	free(environ);
++	free(cmdline);
++	return -EINVAL;
++}
++
++#define SENDFILE_MAX 0x7FFFF000 /* sendfile(2) is limited to 2GB. */
++static int clone_binary(void)
++{
++	int binfd, memfd, err;
++	ssize_t sent = 0;
++
++	memfd = memfd_create(OUR_MEMFD_COMMENT, MFD_CLOEXEC | MFD_ALLOW_SEALING);
++	if (memfd < 0)
++		return -ENOTRECOVERABLE;
++
++	binfd = open("/proc/self/exe", O_RDONLY | O_CLOEXEC);
++	if (binfd < 0)
++		goto error;
++
++	sent = sendfile(memfd, binfd, NULL, SENDFILE_MAX);
++	close(binfd);
++	if (sent < 0)
++		goto error;
++
++	err = fcntl(memfd, F_ADD_SEALS, OUR_MEMFD_SEALS);
++	if (err < 0)
++		goto error;
++
++	return memfd;
++
++error:
++	close(memfd);
++	return -EIO;
++}
++
++int ensure_cloned_binary(void)
++{
++	int execfd;
++	char **argv = NULL, **envp = NULL;
++
++	/* Check that we're not self-cloned, and if we are then bail. */
++	int cloned = is_self_cloned();
++	if (cloned > 0 || cloned == -ENOTRECOVERABLE)
++		return cloned;
++
++	if (fetchve(&argv, &envp) < 0)
++		return -EINVAL;
++
++	execfd = clone_binary();
++	if (execfd < 0)
++		return -EIO;
++
++	fexecve(execfd, argv, envp);
++	return -ENOEXEC;
++}
+diff --git a/libcontainer/nsenter/nsexec.c b/libcontainer/nsenter/nsexec.c
+index cb224314..784fd9b0 100644
+--- a/libcontainer/nsenter/nsexec.c
++++ b/libcontainer/nsenter/nsexec.c
+@@ -528,6 +528,9 @@ void join_namespaces(char *nslist)
+ 	free(namespaces);
+ }
+ 
++/* Defined in cloned_binary.c. */
++int ensure_cloned_binary(void);
++
+ void nsexec(void)
+ {
+ 	int pipenum;
+@@ -543,6 +546,14 @@ void nsexec(void)
+ 	if (pipenum == -1)
+ 		return;
+ 
++	/*
++	 * We need to re-exec if we are not in a cloned binary. This is necessary
++	 * to ensure that containers won't be able to access the host binary
++	 * through /proc/self/exe. See CVE-2019-5736.
++	 */
++	if (ensure_cloned_binary() < 0)
++		bail("could not ensure we are a cloned binary");
++
+ 	/* Parse all of the netlink configuration. */
+ 	nl_parse(pipenum, &config);
+ 
+-- 
+2.20.1
+

SOURCES/1807.patch

@@ -0,0 +1,200 @@
+From ecf53c23545092019602578583031c28fde4d2a1 Mon Sep 17 00:00:00 2001
+From: Giuseppe Scrivano <gscrivan@redhat.com>
+Date: Fri, 25 May 2018 18:04:06 +0200
+Subject: [PATCH] sd-notify: do not hang when NOTIFY_SOCKET is used with create
+
+if NOTIFY_SOCKET is used, do not block the main runc process waiting
+for events on the notify socket.  Change the logic to create a new
+process that monitors exclusively the notify socket until an event is
+received.
+
+Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
+---
+ init.go          |  12 +++++++
+ notify_socket.go | 101 ++++++++++++++++++++++++++++++++++++++++++++++---------
+ signals.go       |   5 +--
+ 3 files changed, 99 insertions(+), 19 deletions(-)
+
+diff --git a/init.go b/init.go
+index c8f453192..6a3d9e91c 100644
+--- a/init.go
++++ b/init.go
+@@ -20,6 +20,18 @@ var initCommand = cli.Command{
+ 	Name:  "init",
+ 	Usage: `initialize the namespaces and launch the process (do not call it outside of runc)`,
+ 	Action: func(context *cli.Context) error {
++		// If NOTIFY_SOCKET is used create a new process that stays around
++		// so to not block "runc start".  It will automatically exits when the
++		// container notifies that it is ready, or when the container is deleted
++		if os.Getenv("_NOTIFY_SOCKET_FD") != "" {
++			fd := os.Getenv("_NOTIFY_SOCKET_FD")
++			pid := os.Getenv("_NOTIFY_SOCKET_PID")
++			hostNotifySocket := os.Getenv("_NOTIFY_SOCKET_HOST")
++			notifySocketPath := os.Getenv("_NOTIFY_SOCKET_PATH")
++			notifySocketInit(fd, pid, hostNotifySocket, notifySocketPath)
++			os.Exit(0)
++		}
++
+ 		factory, _ := libcontainer.New("")
+ 		if err := factory.StartInitialization(); err != nil {
+ 			// as the error is sent back to the parent there is no need to log
+diff --git a/notify_socket.go b/notify_socket.go
+index cd6c0a989..e04e9d660 100644
+--- a/notify_socket.go
++++ b/notify_socket.go
+@@ -6,10 +6,13 @@ import (
+ 	"bytes"
+ 	"fmt"
+ 	"net"
++	"os"
++	"os/exec"
+ 	"path/filepath"
++	"strconv"
++	"time"
+ 
+ 	"github.com/opencontainers/runtime-spec/specs-go"
+-
+ 	"github.com/sirupsen/logrus"
+ 	"github.com/urfave/cli"
+ )
+@@ -64,24 +67,94 @@ func (s *notifySocket) setupSocket() error {
+ 	return nil
+ }
+ 
++func (notifySocket *notifySocket) notifyNewPid(pid int) {
++	notifySocketHostAddr := net.UnixAddr{Name: notifySocket.host, Net: "unixgram"}
++	client, err := net.DialUnix("unixgram", nil, &notifySocketHostAddr)
++	if err != nil {
++		return
++	}
++	newPid := fmt.Sprintf("MAINPID=%d\n", pid)
++	client.Write([]byte(newPid))
++}
++
+ // pid1 must be set only with -d, as it is used to set the new process as the main process
+ // for the service in systemd
+ func (notifySocket *notifySocket) run(pid1 int) {
+-	buf := make([]byte, 512)
+-	notifySocketHostAddr := net.UnixAddr{Name: notifySocket.host, Net: "unixgram"}
+-	client, err := net.DialUnix("unixgram", nil, &notifySocketHostAddr)
++	file, err := notifySocket.socket.File()
+ 	if err != nil {
+ 		logrus.Error(err)
+ 		return
+ 	}
+-	for {
+-		r, err := notifySocket.socket.Read(buf)
+-		if err != nil {
+-			break
++	defer file.Close()
++	defer notifySocket.socket.Close()
++
++	cmd := exec.Command("/proc/self/exe", "init")
++	cmd.ExtraFiles = []*os.File{file}
++	cmd.Env = append(cmd.Env, "_NOTIFY_SOCKET_FD=3",
++		fmt.Sprintf("_NOTIFY_SOCKET_PID=%d", pid1),
++		fmt.Sprintf("_NOTIFY_SOCKET_HOST=%s", notifySocket.host),
++		fmt.Sprintf("_NOTIFY_SOCKET_PATH=%s", notifySocket.socketPath))
++
++	if err := cmd.Start(); err != nil {
++		logrus.Fatal(err)
++	}
++	notifySocket.notifyNewPid(cmd.Process.Pid)
++	cmd.Process.Release()
++}
++
++func notifySocketInit(envFd string, envPid string, notifySocketHost string, notifySocketPath string) {
++	intFd, err := strconv.Atoi(envFd)
++	if err != nil {
++		return
++	}
++	pid1, err := strconv.Atoi(envPid)
++	if err != nil {
++		return
++	}
++
++	file := os.NewFile(uintptr(intFd), "unixgram")
++	defer file.Close()
++
++	fileChan := make(chan []byte)
++	exitChan := make(chan bool)
++
++	go func() {
++		for {
++			buf := make([]byte, 512)
++			r, err := file.Read(buf)
++			if err != nil {
++				return
++			}
++			fileChan <- buf[0:r]
+ 		}
+-		var out bytes.Buffer
+-		for _, line := range bytes.Split(buf[0:r], []byte{'\n'}) {
+-			if bytes.HasPrefix(line, []byte("READY=")) {
++	}()
++	go func() {
++		for {
++			if _, err := os.Stat(notifySocketPath); os.IsNotExist(err) {
++				exitChan <- true
++				return
++			}
++			time.Sleep(time.Second)
++		}
++	}()
++
++	notifySocketHostAddr := net.UnixAddr{Name: notifySocketHost, Net: "unixgram"}
++	client, err := net.DialUnix("unixgram", nil, &notifySocketHostAddr)
++	if err != nil {
++		return
++	}
++
++	for {
++		select {
++		case <-exitChan:
++			return
++		case b := <-fileChan:
++			for _, line := range bytes.Split(b, []byte{'\n'}) {
++				if !bytes.HasPrefix(line, []byte("READY=")) {
++					continue
++				}
++
++				var out bytes.Buffer
+ 				_, err = out.Write(line)
+ 				if err != nil {
+ 					return
+@@ -98,10 +171,8 @@ func (notifySocket *notifySocket) run(pid1 int) {
+ 				}
+ 
+ 				// now we can inform systemd to use pid1 as the pid to monitor
+-				if pid1 > 0 {
+-					newPid := fmt.Sprintf("MAINPID=%d\n", pid1)
+-					client.Write([]byte(newPid))
+-				}
++				newPid := fmt.Sprintf("MAINPID=%d\n", pid1)
++				client.Write([]byte(newPid))
+ 				return
+ 			}
+ 		}
+diff --git a/signals.go b/signals.go
+index 1811de837..d0988cb39 100644
+--- a/signals.go
++++ b/signals.go
+@@ -70,7 +70,7 @@ func (h *signalHandler) forward(process *libcontainer.Process, tty *tty, detach
+ 			h.notifySocket.run(pid1)
+ 			return 0, nil
+ 		} else {
+-			go h.notifySocket.run(0)
++			h.notifySocket.run(os.Getpid())
+ 		}
+ 	}
+ 
+@@ -98,9 +98,6 @@ func (h *signalHandler) forward(process *libcontainer.Process, tty *tty, detach
+ 					// status because we must ensure that any of the go specific process
+ 					// fun such as flushing pipes are complete before we return.
+ 					process.Wait()
+-					if h.notifySocket != nil {
+-						h.notifySocket.Close()
+-					}
+ 					return e.status, nil
+ 				}
+ 			}

SOURCES/99-containers.conf

@@ -0,0 +1 @@
+fs.may_detach_mounts=1

SOURCES/change-default-root.patch

@@ -0,0 +1,61 @@
+diff --git a/list.go b/list.go
+index 0313d8c..328798b 100644
+--- a/list.go
++++ b/list.go
+@@ -50,7 +50,7 @@ var listCommand = cli.Command{
+ 	ArgsUsage: `
+ 
+ Where the given root is specified via the global option "--root"
+-(default: "/run/runc").
++(default: "/run/runc-ctrs").
+ 
+ EXAMPLE 1:
+ To list containers created via the default "--root":
+diff --git a/main.go b/main.go
+index 278399a..0f49fce 100644
+--- a/main.go
++++ b/main.go
+@@ -62,7 +62,7 @@ func main() {
+ 	v = append(v, fmt.Sprintf("spec: %s", specs.Version))
+ 	app.Version = strings.Join(v, "\n")
+ 
+-	root := "/run/runc"
++	root := "/run/runc-ctrs"
+ 	rootless, err := isRootless(nil)
+ 	if err != nil {
+ 		fatal(err)
+@@ -70,7 +70,7 @@ func main() {
+ 	if rootless {
+ 		runtimeDir := os.Getenv("XDG_RUNTIME_DIR")
+ 		if runtimeDir != "" {
+-			root = runtimeDir + "/runc"
++			root = runtimeDir + "/runc-ctrs"
+ 			// According to the XDG specification, we need to set anything in
+ 			// XDG_RUNTIME_DIR to have a sticky bit if we don't want it to get
+ 			// auto-pruned.
+diff --git a/man/runc-list.8.md b/man/runc-list.8.md
+index f737424..107220e 100644
+--- a/man/runc-list.8.md
++++ b/man/runc-list.8.md
+@@ -6,7 +6,7 @@
+ 
+ # EXAMPLE
+ Where the given root is specified via the global option "--root"
+-(default: "/run/runc").
++(default: "/run/runc-ctrs").
+ 
+ To list containers created via the default "--root":
+        # runc list
+diff --git a/man/runc.8.md b/man/runc.8.md
+index 6d0ddff..337bc73 100644
+--- a/man/runc.8.md
++++ b/man/runc.8.md
+@@ -51,7 +51,7 @@ value for "bundle" is the current directory.
+    --debug              enable debug output for logging
+    --log value          set the log file path where internal debug information is written (default: "/dev/null")
+    --log-format value   set the format used by logs ('text' (default), or 'json') (default: "text")
+-   --root value         root directory for storage of container state (this should be located in tmpfs) (default: "/run/runc" or $XDG_RUNTIME_DIR/runc for rootless containers)
++   --root value         root directory for storage of container state (this should be located in tmpfs) (default: "/run/runc-ctrs" or $XDG_RUNTIME_DIR/runc-ctrs for rootless containers)
+    --criu value         path to the criu binary used for checkpoint and restore (default: "criu")
+    --systemd-cgroup     enable systemd cgroup support, expects cgroupsPath to be of form "slice:prefix:name" for e.g. "system.slice:runc:434234"
+    --rootless value    enable rootless mode ('true', 'false', or 'auto') (default: "auto")

SOURCES/pivot-root.patch

@@ -0,0 +1,72 @@
+From 28a697cce3e4f905dca700eda81d681a30eef9cd Mon Sep 17 00:00:00 2001
+From: Giuseppe Scrivano <gscrivan@redhat.com>
+Date: Fri, 11 Jan 2019 21:53:45 +0100
+Subject: [PATCH] rootfs: umount all procfs and sysfs with --no-pivot
+
+When creating a new user namespace, the kernel doesn't allow to mount
+a new procfs or sysfs file system if there is not already one instance
+fully visible in the current mount namespace.
+
+When using --no-pivot we were effectively inhibiting this protection
+from the kernel, as /proc and /sys from the host are still present in
+the container mount namespace.
+
+A container without full access to /proc could then create a new user
+namespace, and from there able to mount a fully visible /proc, bypassing
+the limitations in the container.
+
+A simple reproducer for this issue is:
+
+unshare -mrfp sh -c "mount -t proc none /proc && echo c > /proc/sysrq-trigger"
+
+Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
+---
+ libcontainer/rootfs_linux.go | 35 +++++++++++++++++++++++++++++++++++
+ 1 file changed, 35 insertions(+)
+
+diff --git a/libcontainer/rootfs_linux.go b/libcontainer/rootfs_linux.go
+index e7c2f8ada..6bd6da74a 100644
+--- a/libcontainer/rootfs_linux.go
++++ b/libcontainer/rootfs_linux.go
+@@ -748,6 +748,41 @@ func pivotRoot(rootfs string) error {
+ }
+ 
+ func msMoveRoot(rootfs string) error {
++	mountinfos, err := mount.GetMounts()
++	if err != nil {
++		return err
++	}
++
++	absRootfs, err := filepath.Abs(rootfs)
++	if err != nil {
++		return err
++	}
++
++	for _, info := range mountinfos {
++		p, err := filepath.Abs(info.Mountpoint)
++		if err != nil {
++			return err
++		}
++		// Umount every syfs and proc file systems, except those under the container rootfs
++		if (info.Fstype != "proc" && info.Fstype != "sysfs") || filepath.HasPrefix(p, absRootfs) {
++			continue
++		}
++		// Be sure umount events are not propagated to the host.
++		if err := unix.Mount("", p, "", unix.MS_SLAVE|unix.MS_REC, ""); err != nil {
++			return err
++		}
++		if err := unix.Unmount(p, unix.MNT_DETACH); err != nil {
++			if err != unix.EINVAL && err != unix.EPERM {
++				return err
++			} else {
++				// If we have not privileges for umounting (e.g. rootless), then
++				// cover the path.
++				if err := unix.Mount("tmpfs", p, "tmpfs", 0, ""); err != nil {
++					return err
++				}
++			}
++		}
++	}
+ 	if err := unix.Mount(rootfs, "/", "", unix.MS_MOVE, ""); err != nil {
+ 		return err
+ 	}