사용자 네임스페이스: 특정 프로그램에 대해서만 폴더를 마운트하는 방법

루트 액세스 없이 FHS가 아닌 시스템(NixO)에서 FHS 시스템을 가짜로 만들고 싶습니다. 이렇게 하려면 usernamespace를 사용하여 루트에 일부 폴더(예: install /tmp/mylibto )를 마운트해야 합니다 /lib(다른 솔루션은 보이지 않습니다).

불행히도 작동시키는 방법을 찾을 수 없습니다. 따라 하려고 했습니다.이 튜토리얼, 그러나 코드를 복사하면 실패합니다(bash를 시작할 수도 없습니다).

$ gcc userns_child_exec.c -lcap -o userns_child_exec
$ id
uid=1000(myname) gid=100(users) groups=100(users),1(wheel),17(audio),20(lp),57(networkmanager),59(scanner),131(docker),998(vboxusers),999(adbusers)

$ ./userns_child_exec -U -M '0 1000 1' -G '0 100 1' bash
write /proc/535313/gid_map: Operation not permitted
bash: initialize_job_control: no job control in background: Bad file descriptor

[nix-shell:~/Documents/Logiciels/Nix_bidouille/2022_04_26_-_nix_fake_FHS_user_namespace/demo]$ 
[root@bestos:~/Documents/Logiciels/Nix_bidouille/2022_04_26_-_nix_fake_FHS_user_namespace/demo]# 
exit

(bash 프롬프트가 표시되지만 그 이후에는 아무 것도 입력하고 바로 종료할 수 없습니다.)

어떻게 작동하게 만들 수 있는지 아시나요?

암호:

/* 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 */

    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);
}

편집하다

사실 이상합니다. 그룹을 작성할 때 오류가 발생하지만 uid에서는 작동합니다.

[leo@bestos:~]$ cat /proc/582197/gid_map 

[leo@bestos:~]$ cat /proc/582197/uid_map 
         0       1000          1

[leo@bestos:~]$ ll /proc/582197/gid_map 
-rw-r--r-- 1 leo users 0 mai   18 09:09 /proc/582197/gid_map

[leo@bestos:~]$ ll /proc/582197/uid_map 
-rw-r--r-- 1 leo users 0 mai   18 09:09 /proc/582197/uid_map