autodev: adapt to changes in Linux 4.18

Starting with commit 55956b59df33 ("vfs: Allow userns root to call mknod on owned filesystems.") Linux will allow mknod() in user namespaces for userns root if CAP_MKNOD is available. However, these device nodes are useless since static struct super_block *alloc_super(struct file_system_type *type, int flags, struct user_namespace *user_ns) { /* <snip> */ if (s->s_user_ns != &init_user_ns) s->s_iflags |= SB_I_NODEV; /* <snip> */ } will set the SB_I_NODEV flag on the filesystem. When a device node created in non-init userns is open()ed the call chain will hit: bool may_open_dev(const struct path *path) { return !(path->mnt->mnt_flags & MNT_NODEV) && !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } which will cause an EPERM because the device node is located on an fs owned by non-init-userns and thus doesn't grant access to device nodes due to SB_I_NODEV. The solution is straightforward. Unless you're real root you should bind-mount device nodes. Signed-off-by: 's avatarChristian Brauner <christian.brauner@ubuntu.com>
parent 4c08bd46
...@@ -1238,6 +1238,7 @@ struct lxc_device_node { ...@@ -1238,6 +1238,7 @@ struct lxc_device_node {
}; };
static const struct lxc_device_node lxc_devices[] = { static const struct lxc_device_node lxc_devices[] = {
{ "console", S_IFCHR | S_IRWXU | S_IRWXG | S_IRWXO, 1, 5 },
{ "full", S_IFCHR | S_IRWXU | S_IRWXG | S_IRWXO, 1, 7 }, { "full", S_IFCHR | S_IRWXU | S_IRWXG | S_IRWXO, 1, 7 },
{ "null", S_IFCHR | S_IRWXU | S_IRWXG | S_IRWXO, 1, 3 }, { "null", S_IFCHR | S_IRWXU | S_IRWXG | S_IRWXO, 1, 3 },
{ "random", S_IFCHR | S_IRWXU | S_IRWXG | S_IRWXO, 1, 8 }, { "random", S_IFCHR | S_IRWXU | S_IRWXG | S_IRWXO, 1, 8 },
...@@ -1251,7 +1252,7 @@ static int lxc_fill_autodev(const struct lxc_rootfs *rootfs) ...@@ -1251,7 +1252,7 @@ static int lxc_fill_autodev(const struct lxc_rootfs *rootfs)
int i, ret; int i, ret;
char path[MAXPATHLEN]; char path[MAXPATHLEN];
mode_t cmask; mode_t cmask;
bool can_mknod = true; int can_mknod = 1;
ret = snprintf(path, MAXPATHLEN, "%s/dev", ret = snprintf(path, MAXPATHLEN, "%s/dev",
rootfs->path ? rootfs->mount : ""); rootfs->path ? rootfs->mount : "");
...@@ -1274,7 +1275,11 @@ static int lxc_fill_autodev(const struct lxc_rootfs *rootfs) ...@@ -1274,7 +1275,11 @@ static int lxc_fill_autodev(const struct lxc_rootfs *rootfs)
if (ret < 0 || ret >= MAXPATHLEN) if (ret < 0 || ret >= MAXPATHLEN)
return -1; return -1;
if (can_mknod) { /* See
* - https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=55956b59df336f6738da916dbb520b6e37df9fbd
* - https://lists.linuxfoundation.org/pipermail/containers/2018-June/039176.html
*/
if (can_mknod == 2 || (can_mknod == 1 && !am_host_unpriv())) {
ret = mknod(path, device->mode, makedev(device->maj, device->min)); ret = mknod(path, device->mode, makedev(device->maj, device->min));
if (ret == 0 || (ret < 0 && errno == EEXIST)) { if (ret == 0 || (ret < 0 && errno == EEXIST)) {
DEBUG("Created device node \"%s\"", path); DEBUG("Created device node \"%s\"", path);
...@@ -1289,7 +1294,9 @@ static int lxc_fill_autodev(const struct lxc_rootfs *rootfs) ...@@ -1289,7 +1294,9 @@ static int lxc_fill_autodev(const struct lxc_rootfs *rootfs)
/* This can e.g. happen when the container is /* This can e.g. happen when the container is
* unprivileged or CAP_MKNOD has been dropped. * unprivileged or CAP_MKNOD has been dropped.
*/ */
can_mknod = false; can_mknod = 2;
} else {
can_mknod = 0;
} }
ret = mknod(path, S_IFREG, 0); ret = mknod(path, S_IFREG, 0);
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment