[libvirt] [RFC PATCH 2/2] LXC: Create ro overlay mounts only if we're not within a user namespace
Daniel P. Berrange
berrange at redhat.com
Mon Jul 1 11:35:27 UTC 2013
On Mon, Jul 01, 2013 at 01:25:28PM +0200, Richard Weinberger wrote:
> Am 01.07.2013 13:22, schrieb Daniel P. Berrange:
> > On Mon, Jul 01, 2013 at 01:05:23PM +0200, Richard Weinberger wrote:
> >> Am 01.07.2013 12:33, schrieb Daniel P. Berrange:
> >>> On Mon, Jul 01, 2013 at 08:29:14AM +0200, Richard Weinberger wrote:
> >>>> Any ideas what's going on here?
> >>>
> >>> No, it is very odd. It smells like a kernel issue to me. What
> >>> version are you running ?
> >>
> >> I see this issue on all kernels.
> >> Currently I'm using vanilla v3.9.x and v3.10.
> >>
> >>> I've also tried running the demo programs shown on the LWN.net
> >>> article
> >>>
> >>> https://lwn.net/Articles/532593/
> >>>
> >>> and they don't operate in the way described by the article - the demo
> >>> programs continue to ru as 'nfsnobody' even after the mappings are
> >>> setup.
> >>>
> >>> I'm just using the Fedora 3.9.4-303 kernel, rebuilt with userns enabled
> >>> in KConfig. I'm wondering if there is still stuff missing in 3.9.x
> >>> that prevents this from working properly, or if the kernel behaviour
> >>> changed after those LWN articles were written.
> >>
> >> To me it looks like the capability system behaves odd.
> >> The mappings in /proc are fine as long I do not call capng_updatev().
> >> Also calling capng_updatev() with parameters that do not change the current cap set
> >> triggers the odd behavior too.
> >>
> >> So we see two (related?) issues:
> >> 1. If we try updating the capabilities of pid1 /proc/1/ has unmapped files till we exec().
> >> 2. Dropping capabilities does not work we always gain a fresh and full capability set.
> >>
> >> BTW: I'm sure the issues are not caused by Gau Feng's userns patches.
> >
> > Yeah, I've reproduced this problem with standalone code outside of
> > libvirt.
> >
> > Take the attached code and run
>
> -ENOATTACHMENT :-(
Now really attached.
I think I might know what is happening now though. When you start a new
namespace, you must mount a new instance of 'proc' filesystem. We are
not synchronizing this wrt setup of the uid/gid mappings though, so we
are racy. So I have a feeling we're creating the proc filesystem before
the mappings are setup. I'm going to add some synchronization in to see
if it makes a difference in this respect.
Daniel
--
|: http://berrange.com -o- http://www.flickr.com/photos/dberrange/ :|
|: http://libvirt.org -o- http://virt-manager.org :|
|: http://autobuild.org -o- http://search.cpan.org/~danberr/ :|
|: http://entangle-photo.org -o- http://live.gnome.org/gtk-vnc :|
-------------- next part --------------
/* userns_child_exec.c
Copyright 2013, Michael Kerrisk
Licensed under GNU General Public License v2 or later
Create a child process that executes a shell command in new
namespace(s); allow UID and GID mappings to be specified when
creating a user namespace.
*/
#define _GNU_SOURCE
#include <sched.h>
#include <unistd.h>
#include <stdlib.h>
#include <sys/wait.h>
#include <signal.h>
#include <fcntl.h>
#include <stdio.h>
#include <string.h>
#include <limits.h>
#include <errno.h>
/* A simple error-handling function: print an error message based
on the value in 'errno' and terminate the calling process */
#define errExit(msg) do { perror(msg); exit(EXIT_FAILURE); \
} while (0)
struct child_args {
char **argv; /* Command to be executed by child, with arguments */
int pipe_fd[2]; /* Pipe used to synchronize parent and child */
};
static int verbose;
static void
usage(char *pname)
{
fprintf(stderr, "Usage: %s [options] cmd [arg...]\n\n", pname);
fprintf(stderr, "Create a child process that executes a shell command "
"in a new user namespace,\n"
"and possibly also other new namespace(s).\n\n");
fprintf(stderr, "Options can be:\n\n");
#define fpe(str) fprintf(stderr, " %s", str);
fpe("-i New IPC namespace\n");
fpe("-m New mount namespace\n");
fpe("-n New network namespace\n");
fpe("-p New PID namespace\n");
fpe("-u New UTS namespace\n");
fpe("-U New user namespace\n");
fpe("-M uid_map Specify UID map for user namespace\n");
fpe("-G gid_map Specify GID map for user namespace\n");
fpe(" If -M or -G is specified, -U is required\n");
fpe("-v Display verbose messages\n");
fpe("\n");
fpe("Map strings for -M and -G consist of records of the form:\n");
fpe("\n");
fpe(" ID-inside-ns ID-outside-ns len\n");
fpe("\n");
fpe("A map string can contain multiple records, separated by commas;\n");
fpe("the commas are replaced by newlines before writing to map files.\n");
exit(EXIT_FAILURE);
}
/* Update the mapping file 'map_file', with the value provided in
'mapping', a string that defines a UID or GID mapping. A UID or
GID mapping consists of one or more newline-delimited records
of the form:
ID_inside-ns ID-outside-ns length
Requiring the user to supply a string that contains newlines is
of course inconvenient for command-line use. Thus, we permit the
use of commas to delimit records in this string, and replace them
with newlines before writing the string to the file. */
static void
update_map(char *mapping, char *map_file)
{
int fd, j;
size_t map_len; /* Length of 'mapping' */
/* Replace commas in mapping string with newlines */
map_len = strlen(mapping);
for (j = 0; j < map_len; j++)
if (mapping[j] == ',')
mapping[j] = '\n';
fd = open(map_file, O_RDWR);
if (fd == -1) {
fprintf(stderr, "open %s: %s\n", map_file, strerror(errno));
exit(EXIT_FAILURE);
}
if (write(fd, mapping, map_len) != map_len) {
fprintf(stderr, "write %s: %s\n", map_file, strerror(errno));
exit(EXIT_FAILURE);
}
close(fd);
}
static int /* Start function for cloned child */
childFunc(void *arg)
{
struct child_args *args = (struct child_args *) arg;
char ch;
/* Wait until the parent has updated the UID and GID mappings. See
the comment in main(). We wait for end of file on a pipe that will
be closed by the parent process once it has updated the mappings. */
close(args->pipe_fd[1]); /* Close our descriptor for the write end
of the pipe so that we see EOF when
parent closes its descriptor */
if (read(args->pipe_fd[0], &ch, 1) != 0) {
fprintf(stderr, "Failure in child: read from pipe returned != 0\n");
exit(EXIT_FAILURE);
}
/* Execute a shell command */
if (setreuid(0, 0) < 0)
errExit("setreuid");
if (setregid(0, 0) < 0)
errExit("setregid");
fprintf(stderr, "Launching child init\n");
execvp(args->argv[0], args->argv);
errExit("execvp");
}
#define STACK_SIZE (1024 * 1024)
static char child_stack[STACK_SIZE]; /* Space for child's stack */
int
main(int argc, char *argv[])
{
int flags, opt;
pid_t child_pid;
struct child_args args;
char *uid_map, *gid_map;
char map_path[PATH_MAX];
/* Parse command-line options. The initial '+' character in
the final getopt() argument prevents GNU-style permutation
of command-line options. That's useful, since sometimes
the 'command' to be executed by this program itself
has command-line options. We don't want getopt() to treat
those as options to this program. */
flags = 0;
verbose = 0;
gid_map = NULL;
uid_map = NULL;
while ((opt = getopt(argc, argv, "+imnpuUM:G:v")) != -1) {
switch (opt) {
case 'i': flags |= CLONE_NEWIPC; break;
case 'm': flags |= CLONE_NEWNS; break;
case 'n': flags |= CLONE_NEWNET; break;
case 'p': flags |= CLONE_NEWPID; break;
case 'u': flags |= CLONE_NEWUTS; break;
case 'v': verbose = 1; break;
case 'M': uid_map = optarg; break;
case 'G': gid_map = optarg; break;
case 'U': flags |= CLONE_NEWUSER; break;
default: usage(argv[0]);
}
}
/* -M or -G without -U is nonsensical */
if ((uid_map != NULL || gid_map != NULL) &&
!(flags & CLONE_NEWUSER))
usage(argv[0]);
args.argv = &argv[optind];
/* We use a pipe to synchronize the parent and child, in order to
ensure that the parent sets the UID and GID maps before the child
calls execve(). This ensures that the child maintains its
capabilities during the execve() in the common case where we
want to map the child's effective user ID to 0 in the new user
namespace. Without this synchronization, the child would lose
its capabilities if it performed an execve() with nonzero
user IDs (see the capabilities(7) man page for details of the
transformation of a process's capabilities during execve()). */
if (pipe(args.pipe_fd) == -1)
errExit("pipe");
/* Create the child in new namespace(s) */
child_pid = clone(childFunc, child_stack + STACK_SIZE,
flags | SIGCHLD, &args);
if (child_pid == -1)
errExit("clone");
/* Parent falls through to here */
if (verbose)
printf("%s: PID of child created by clone() is %ld\n",
argv[0], (long) child_pid);
/* Update the UID and GID maps in the child */
if (uid_map != NULL) {
snprintf(map_path, PATH_MAX, "/proc/%ld/uid_map",
(long) child_pid);
update_map(uid_map, map_path);
}
if (gid_map != NULL) {
snprintf(map_path, PATH_MAX, "/proc/%ld/gid_map",
(long) child_pid);
update_map(gid_map, map_path);
}
/* Close the write end of the pipe, to signal to the child that we
have updated the UID and GID maps */
close(args.pipe_fd[1]);
if (waitpid(child_pid, NULL, 0) == -1) /* Wait for child */
errExit("waitpid");
if (verbose)
printf("%s: terminating\n", argv[0]);
exit(EXIT_SUCCESS);
}
More information about the libvir-list
mailing list