Re: [RCF] [PATCH] unprivileged mount/umount

From: Miklos Szeredi
Date: Thu May 12 2005 - 13:56:03 EST



> > I'm not sure passing directory file descriptors is the right semantic
> > we want - but at least it provides a point of explicit control (in
> > much the same way as a bind). Are you sure the clone + open("/") +
> > pass-to-parent scenario you allows the parent to traverse the child's
> > private name space through that fd?
>
> Pretty sure.

Yup. Attached a little program that can be used to try this out. It
creates a new namespace in the child, does a bind mount (so the
namespaces can be differentiated), then sends the file descriptor of
"/" to the parent. The parent does fchdir(fd), then starts a shell.

So the result is that CWD is under the child namespace, while root is
under the initial namespace.

I also tried bind mounting from the child's namespace to the parent's,
and that works too. But the new mount's mnt_namespace is copied from
the old, which makes the mount un-removable. This is most likely not
intentional, IOW a bug.

Miklos

=== newns.c =========================================================
#define _GNU_SOURCE

#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <signal.h>
#include <sched.h>
#include <errno.h>
#include <fcntl.h>
#include <unistd.h>
#include <sys/un.h>
#include <sys/socket.h>

static int socks[2];

static int send_fd(int sock_fd, int fd)
{
int retval;
struct msghdr msg;
struct cmsghdr *p_cmsg;
struct iovec vec;
char cmsgbuf[CMSG_SPACE(sizeof(fd))];
int *p_fds;
char sendchar = 0;

msg.msg_control = cmsgbuf;
msg.msg_controllen = sizeof(cmsgbuf);
p_cmsg = CMSG_FIRSTHDR(&msg);
p_cmsg->cmsg_level = SOL_SOCKET;
p_cmsg->cmsg_type = SCM_RIGHTS;
p_cmsg->cmsg_len = CMSG_LEN(sizeof(fd));
p_fds = (int *) CMSG_DATA(p_cmsg);
*p_fds = fd;
msg.msg_controllen = p_cmsg->cmsg_len;
msg.msg_name = NULL;
msg.msg_namelen = 0;
msg.msg_iov = &vec;
msg.msg_iovlen = 1;
msg.msg_flags = 0;
/* "To pass file descriptors or credentials you need to send/read at
* least one byte" (man 7 unix) */
vec.iov_base = &sendchar;
vec.iov_len = sizeof(sendchar);
while ((retval = sendmsg(sock_fd, &msg, 0)) == -1 && errno == EINTR);
if (retval != 1) {
perror("sending file descriptor");
return -1;
}
return 0;
}

static int receive_fd(int fd)
{
struct msghdr msg;
struct iovec iov;
char buf[1];
int rv;
int connfd = -1;
char ccmsg[CMSG_SPACE(sizeof(connfd))];
struct cmsghdr *cmsg;

iov.iov_base = buf;
iov.iov_len = 1;

msg.msg_name = 0;
msg.msg_namelen = 0;
msg.msg_iov = &iov;
msg.msg_iovlen = 1;
/* old BSD implementations should use msg_accrights instead of
* msg_control; the interface is different. */
msg.msg_control = ccmsg;
msg.msg_controllen = sizeof(ccmsg);

while(((rv = recvmsg(fd, &msg, 0)) == -1) && errno == EINTR);
if (rv == -1) {
perror("recvmsg");
return -1;
}
if(!rv) {
/* EOF */
return -1;
}

cmsg = CMSG_FIRSTHDR(&msg);
if (!cmsg->cmsg_type == SCM_RIGHTS) {
fprintf(stderr, "got control message of unknown type %d\n",
cmsg->cmsg_type);
return -1;
}
return *(int*)CMSG_DATA(cmsg);
}

int childfn(void *p)
{
int fd;

(void) p;
mkdir("/tmp/clonetest", 755);
mkdir("/tmp/clonetest/dir1", 755);
mkdir("/tmp/clonetest/dir1/subdir1", 755);
mkdir("/tmp/clonetest/mnt", 755);
system("mount --bind /tmp/clonetest/dir1 /tmp/clonetest/mnt");
fd = open("/", O_RDONLY | O_DIRECTORY);
send_fd(socks[0], fd);
sleep(1000);
return 1;
}

int main()
{
char buf[10000];
pid_t pid;
int res;
int childfd;

res = socketpair(AF_UNIX, SOCK_STREAM, 0, socks);
if (res == -1) {
perror("socketpair");
return 1;
}

pid = clone(childfn, buf+5000, CLONE_NEWNS | SIGCHLD, NULL);
if ((int) pid == -1) {
perror("clone");
exit(1);
}

childfd = receive_fd(socks[1]);
res = fchdir(childfd);
if (res == -1) {
perror("fchdir");
return 1;
}
execl("/bin/bash", "/bin/bash", NULL);

return 0;
}
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/