[PATCH 0/2] Add further ioctl() operations for namespace discovery

["Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com>]

Eric,

The code proposed in this patch series is pretty small. Is there any
chance we could make the 4.10 merge window, if the changes seem
acceptable to you?

I would like to write code that can answer the question: "what
capabilities does process X have in namespace Y"? (where Y is defined by
a file descriptor referring to one of the /proc/PID/ns/xxxx files). The
rules that determine the answer to this question are described in the
capabilities(7) manual page:

       The  rules for determining whether or not a process has a capabil‐
       ity in a particular user namespace are as follows:

       1. A process has a capability inside a user namespace if it  is  a
          member  of  that  namespace  and  it  has the capability in its
          effective capability set.  A process can gain  capabilities  in
          its  effective capability set in various ways.  For example, it
          may execute a set-user-ID program or an executable with associ‐
          ated  file capabilities.  In addition, a process may gain capa‐
          bilities via the effect of clone(2), unshare(2),  or  setns(2),
          as already described.

       2. If  a process has a capability in a user namespace, then it has
          that capability in all child (and further  removed  descendant)
          namespaces as well.

       3. When a user namespace is created, the kernel records the effec‐
          tive user ID of the creating process as being  the  "owner"  of
          the  namespace.   A  process  that resides in the parent of the
          user namespace and whose effective user ID matches the owner of
          the namespace has all capabilities in the namespace.  By virtue
          of the previous rule, this means that the process has all capa‐
          bilities  in  all further removed descendant user namespaces as
          well.

The NS_GET_PARENT and NS_GET_USERNS ioctl() operations added in Linux
4.9 provide much of what is needed, but AFAICT there are still a couple
of small pieces missing. Those pieces are added with this patch series.

Here's an example program that makes use of the new ioctl() operations.

8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---
/* ns_capable.c

   (C) 2016 Michael Kerrisk, <mtk.manpages@gmail.com>

   Licensed under the GNU General Public License v2 or later.
*/
#define _GNU_SOURCE
#include <sched.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdio.h>
#include <errno.h>
#include <fcntl.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/ioctl.h>
#include <limits.h>
#include <sys/capability.h>

#ifndef NS_GET_USERNS
#define NSIO    0xb7
#define NS_GET_USERNS           _IO(NSIO, 0x1)
#define NS_GET_PARENT           _IO(NSIO, 0x2)
#define NS_GET_NSTYPE           _IO(NSIO, 0x3)
#define NS_GET_CREATOR_UID      _IO(NSIO, 0x4)
#endif

#define errExit(msg)    do { perror(msg); exit(EXIT_FAILURE); \
                        } while (0)

#define fatal(msg)      do { fprintf(stderr, "%s\n", msg); \
                             exit(EXIT_FAILURE); } while (0)

/* Display capabilities sets of process with specified PID */

static void
show_cap(pid_t pid)
{
    cap_t caps;
    char *cap_string;

    caps = cap_get_pid(pid);
    if (caps == NULL)
        errExit("cap_get_proc");

    cap_string = cap_to_text(caps, NULL);
    if (cap_string == NULL)
        errExit("cap_to_text");

    printf("Capabilities: %s\n", cap_string);
}

/* Obtain the effective UID pf the process 'pid' by
   scanning its /proc/PID/file */

static uid_t
get_euid_of_process(pid_t pid)
{
    char path[PATH_MAX];
    char line[1024];
    int uid;

    snprintf(path, sizeof(path), "/proc/%ld/status", (long) pid);

    FILE *fp;
    fp = fopen(path, "r");
    if (fp == NULL)
        errExit("fopen-/proc/PID/status");

    for (;;) {
        if (fgets(line, sizeof(line), fp) == NULL) {

            /* Should never happen... */

            fprintf(stderr, "Failure scanning %s\n", path);
            exit(EXIT_FAILURE);
        }

        if (strstr(line, "Uid:") == line) {
            sscanf(line, "Uid: %*d %d %*d %*d", &uid);
            return uid;
        }
    }
}

int
main(int argc, char *argv[])
{
    int ns_fd, userns_fd, pid_userns_fd;
    int nstype;
    int next_fd;
    struct stat pid_stat;
    struct stat target_stat;
    char *pid_str;
    pid_t pid;
    char path[PATH_MAX];

    if (argc < 2) {
        fprintf(stderr, "Usage: %s PID [ns-file]\n", argv[0]);
        fprintf(stderr, "\t'ns-file' is a /proc/PID/ns/xxxx file; if omitted, "
                        "use the namespace\n"
                        "\treferred to by standard input "
                        "(file descriptor 0)\n");
        exit(EXIT_FAILURE);
    }

    pid_str = argv[1];
    pid = atoi(pid_str);

    if (argc <= 2) {
        ns_fd = STDIN_FILENO;
    } else {
        ns_fd = open(argv[2], O_RDONLY);
        if (ns_fd == -1)
            errExit("open-ns-file");
    }

    /* Get the relevant user namespace FD, which is 'ns_fd' if 'ns_fd' refers
       to a user namespace, otherwise the user namespace that owns 'ns_fd' */

    nstype = ioctl(ns_fd, NS_GET_NSTYPE);
    if (nstype == -1)
        errExit("ioctl-NS_GET_NSTYPE");

    if (nstype == CLONE_NEWUSER) {
        userns_fd = ns_fd;
    } else {
        userns_fd = ioctl(ns_fd, NS_GET_USERNS);
        if (userns_fd == -1)
            errExit("ioctl-NS_GET_USERNS");
    }

    /* Obtain 'stat' info for the user namespace of the specified PID */

    snprintf(path, sizeof(path), "/proc/%s/ns/user", pid_str);

    pid_userns_fd = open(path, O_RDONLY);
    if (pid_userns_fd == -1)
        errExit("open-PID");

    if (fstat(pid_userns_fd, &pid_stat) == -1)
        errExit("fstat-PID");

    /* Get 'stat' info for the target user namesapce */

    if (fstat(userns_fd, &target_stat) == -1)
        errExit("fstat-PID");

    /* If the PID is in the target user namespace, then it has
       whatever capabilities are in its sets. */

    if (pid_stat.st_dev == target_stat.st_dev &&
                pid_stat.st_ino == target_stat.st_ino) {
        printf("PID is in target namespace\n");

        show_cap(pid);

        exit(EXIT_SUCCESS);
    }

    /* Otherwise, we need to walk through the ancestors of the target
       user namespace to see if PID is in an ancestor namespace */

    for (;;) {
        int f;

        next_fd = ioctl(userns_fd, NS_GET_PARENT);

        if (next_fd == -1) {

            /* The error here should be EPERM... */

            if (errno != EPERM)
                errExit("ioctl-NS_GET_PARENT");

            printf("PID is not in an ancestor namespace\n");
            printf("It has no capabilities in the target namespace\n");

            exit(EXIT_SUCCESS);
        }

        if (fstat(next_fd, &target_stat) == -1)
            errExit("fstat-PID");

        /* If the 'stat' info for this user namespace matches the 'stat'
         * info for 'next_fd', then the PID is in an ancestor namespace */

        if (pid_stat.st_dev == target_stat.st_dev &&
                    pid_stat.st_ino == target_stat.st_ino)
            break;

        /* Next time round, get the next parent */

        f = userns_fd;
        userns_fd = next_fd;
        close(f);
    }

    /* At this point, we found that PID is in an ancestor of the target
       user namespace, and 'userns_fd' refers to the immediate descendant
       user namespace of PID in the chain of user namespaces from PID to
       the target user namespace. If the effective UID of PID matches the
       creator UID of descendant user namespace, then PID has all
       capabilities in the descendant namespace(s); otherwise, it just has
       the capabilities that are in its sets. */

    uid_t creator_uid, uid;

    creator_uid = ioctl(userns_fd, NS_GET_CREATOR_UID);
    if (creator_uid == -1)
        errExit("ioctl-NS_GET_CREATOR_UID");

    uid = get_euid_of_process(pid);

    printf("PID is in an ancestor namespace\n");
    if (creator_uid == uid) {
        printf("And its effective UID matches the creator "
                "of the namespace\n");
        printf("PID has all capabilities in that namespace!\n");
    } else {
        printf("But its effective UID does not match the creator "
                "of the namespace\n");
        show_cap(pid);
    }

    exit(EXIT_SUCCESS);
}
8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---8x---

Michael Kerrisk (2):
  nsfs: Add an ioctl() to return the namespace type
  nsfs: Add an ioctl() to return creator UID of a user namespace

 fs/nsfs.c                 | 8 ++++++++
 include/uapi/linux/nsfs.h | 9 +++++++--
 2 files changed, 15 insertions(+), 2 deletions(-)

-- 
2.5.5

-- 
Michael Kerrisk
Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/
Linux/UNIX System Programming Training: http://man7.org/training/