Merge branch 'PR/unshare-binfmt_misc' of github.com:karelzak/util-lin…

…ux-work

* 'PR/unshare-binfmt_misc' of github.com:karelzak/util-linux-work:
  unshare: load binfmt_misc interpreter
  unshare: mount binfmt_misc

include/pathnames.h

@@ -204,6 +204,7 @@
 /* sysctl fs paths */
 #define _PATH_PROC_SYS_FS	"/proc/sys/fs"
 #define _PATH_PROC_PIPE_MAX_SIZE	_PATH_PROC_SYS_FS "/pipe-max-size"
+#define _PATH_PROC_BINFMT_MISC	_PATH_PROC_SYS_FS "/binfmt_misc"
 
 /* irqtop paths */
 #define _PATH_PROC_INTERRUPTS	"/proc/interrupts"

sys-utils/unshare.1.adoc

@@ -90,6 +90,9 @@ When *unshare* terminates, have _signame_ be sent to the forked child process. C
 *--mount-proc*[**=**__mountpoint__]::
 Just before running the program, mount the proc filesystem at _mountpoint_ (default is _/proc_). This is useful when creating a new PID namespace. It also implies creating a new mount namespace since the _/proc_ mount would otherwise mess up existing programs on the system. The new proc filesystem is explicitly mounted as private (with *MS_PRIVATE*|*MS_REC*).
 
+*--mount-binfmt*[**=**__mountpoint__]::
+Just before running the program, mount the binfmt_misc filesystem at _mountpoint_ (default is /proc/sys/fs/binfmt_misc).  It also implies creating a new mount namespace since the binfmt_misc mount would otherwise mess up existing programs on the system.  The new binfmt_misc filesystem is explicitly mounted as private (with *MS_PRIVATE*|*MS_REC*).
+
 **--map-user=**__uid|name__::
 Run the program only after the current effective user ID has been mapped to _uid_. If this option is specified multiple times, the last occurrence takes precedence. This option implies *--user*.
 
@@ -135,6 +138,10 @@ Set the user ID which will be used in the entered namespace.
 *-G*, *--setgid* _gid_::
 Set the group ID which will be used in the entered namespace and drop supplementary groups.
 
+*-l*, **--load-interp=**__string__::
+Load binfmt_misc definition in the namespace (implies *--mount-binfmt*). The __string__ argument is ``:name:type:offset:magic:mask:interpreter:flags``. For more details about new binary type registration see  https://www.kernel.org/doc/Documentation/admin-guide/binfmt-misc.rst.
+To manage the F flag in ``flags`` with **--root** parameter, binfmt_misc is mounted twice, once before the chroot to load the interpreter from the caller filesystem and once after to make it available from the chroot userspace.
+
 *--monotonic* _offset_::
 Set the offset of *CLOCK_MONOTONIC* which will be used in the entered time namespace. This option requires unsharing a time namespace with *--time*.
 
@@ -253,6 +260,20 @@ up 21 hours, 30 minutes
 up 9 years, 28 weeks, 1 day, 2 hours, 50 minutes
 ....
 
+The following example execute a chroot into the directory /chroot/powerpc/jessie and install the interpreter /bin/qemu-ppc-static to execute the powerpc binaries.
+
+....
+$  unshare --map-root-user --fork --pid --load-interp=":qemu-ppc:M::\\x7fELF\x01\\x02\\x01\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x02\\x00\\x14:\\xff\\xff\\xff\\xff\\xff\\xff\\xff\\x00\\xff\\xff\\xff\\xff\\xff\\xff\\xff\\xff\\xff\\xfe\\xff\\xff:/bin/qemu-ppc-static:OCF" --root=/chroot/powerpc/jessie /bin/bash -l
+....
+
+The ``load-interp`` parameter can be read as following::
+``qemu-ppc``::: is the name of the new file created below ``/proc/sys/fs/binfmt_misc`` to register the interpreter
+``M``::: defines the interpreter for a given type of magic number
+``\\x7fELF\x01\\x02\\x01\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x02\\x00\\x1``::: is the magic number to recognize the file to interpret (in this case, the ELF header for PPC32)
+``\\xff\\xff\\xff\\xff\\xff\\xff\\xff\\x00\\xff\\xff\\xff\\xff\\xff\\xff\\xff\\xff\\xff\\xfe\\xff\\xff``::: the mask to apply to the magic number
+``/bin/qemu-ppc-static``::: the interpreter to use with the file
+``OCF``::: the file is open by the kernel with credential and security tokens of the file itself and loaded as soon as we register it.
+
 == AUTHORS
 
 mailto:dottedmag@dottedmag.net[Mikhail Gusarov],

sys-utils/unshare.c

@@ -725,6 +725,35 @@ static pid_t map_ids_from_child(int *fd, uid_t mapuser,
 	exit(EXIT_SUCCESS);
 }
 
+static int is_fixed(const char *interp)
+{
+	const char *flags;
+
+	flags = strrchr(interp, ':');
+
+	return strchr(flags, 'F') != NULL;
+}
+
+static void load_interp(const char *binfmt_mnt, const char *interp)
+{
+	int dirfd, fd;
+
+	dirfd = open(binfmt_mnt, O_PATH | O_DIRECTORY);
+	if (dirfd < 0)
+		err(EXIT_FAILURE, _("cannot open %s"), binfmt_mnt);
+
+	fd = openat(dirfd, "register", O_WRONLY);
+	if (fd < 0)
+		err(EXIT_FAILURE, _("cannot open %s/register"), binfmt_mnt);
+
+	if (write_all(fd, interp, strlen(interp)))
+		err(EXIT_FAILURE, _("write failed %s/register"), binfmt_mnt);
+
+	close(fd);
+
+	close(dirfd);
+}
+
 static void __attribute__((__noreturn__)) usage(void)
 {
 	FILE *out = stdout;
@@ -760,6 +789,7 @@ static void __attribute__((__noreturn__)) usage(void)
 	fputs(_(" --kill-child[=<signame>]  when dying, kill the forked child (implies --fork)\n"
 		"                             defaults to SIGKILL\n"), out);
 	fputs(_(" --mount-proc[=<dir>]      mount proc filesystem first (implies --mount)\n"), out);
+	fputs(_(" --mount-binfmt[=<dir>]    mount binfmt filesystem first (implies --user and --mount)\n"), out);
 	fputs(_(" --propagation slave|shared|private|unchanged\n"
 	        "                           modify mount propagation in mount namespace\n"), out);
 	fputs(_(" --setgroups allow|deny    control the setgroups syscall in user namespaces\n"), out);
@@ -771,6 +801,7 @@ static void __attribute__((__noreturn__)) usage(void)
 	fputs(_(" -G, --setgid <gid>        set gid in entered namespace\n"), out);
 	fputs(_(" --monotonic <offset>      set clock monotonic offset (seconds) in time namespaces\n"), out);
 	fputs(_(" --boottime <offset>       set clock boottime offset (seconds) in time namespaces\n"), out);
+	fputs(_(" -l, --load-interp <file>  load binfmt definition in the namespace (implies --mount-binfmt)\n"), out);
 
 	fputs(USAGE_SEPARATOR, out);
 	fprintf(out, USAGE_HELP_OPTIONS(27));
@@ -783,6 +814,7 @@ int main(int argc, char *argv[])
 {
 	enum {
 		OPT_MOUNTPROC = CHAR_MAX + 1,
+		OPT_MOUNTBINFMT,
 		OPT_PROPAGATION,
 		OPT_SETGROUPS,
 		OPT_KILLCHILD,
@@ -811,6 +843,7 @@ int main(int argc, char *argv[])
 		{ "fork",          no_argument,       NULL, 'f'             },
 		{ "kill-child",    optional_argument, NULL, OPT_KILLCHILD   },
 		{ "mount-proc",    optional_argument, NULL, OPT_MOUNTPROC   },
+		{ "mount-binfmt",  optional_argument, NULL, OPT_MOUNTBINFMT },
 		{ "map-user",      required_argument, NULL, OPT_MAPUSER     },
 		{ "map-users",     required_argument, NULL, OPT_MAPUSERS    },
 		{ "map-group",     required_argument, NULL, OPT_MAPGROUP    },
@@ -827,6 +860,7 @@ int main(int argc, char *argv[])
 		{ "wd",		   required_argument, NULL, 'w'		    },
 		{ "monotonic",     required_argument, NULL, OPT_MONOTONIC   },
 		{ "boottime",      required_argument, NULL, OPT_BOOTTIME    },
+		{ "load-interp",   required_argument, NULL, 'l'		    },
 		{ NULL, 0, NULL, 0 }
 	};
 
@@ -839,9 +873,11 @@ int main(int argc, char *argv[])
 	struct map_range *groupmap = NULL;
 	int kill_child_signo = 0; /* 0 means --kill-child was not used */
 	const char *procmnt = NULL;
+	const char *binfmt_mnt = NULL;
 	const char *newroot = NULL;
 	const char *newdir = NULL;
 	pid_t pid_bind = 0, pid_idmap = 0;
+	const char *newinterp = NULL;
 	pid_t pid = 0;
 #ifdef UL_HAVE_PIDFD
 	int fd_parent_pid = -1;
@@ -864,7 +900,7 @@ int main(int argc, char *argv[])
 	textdomain(PACKAGE);
 	close_stdout_atexit();
 
-	while ((c = getopt_long(argc, argv, "+fhVmuinpCTUrR:w:S:G:c", longopts, NULL)) != -1) {
+	while ((c = getopt_long(argc, argv, "+fhVmuinpCTUrR:w:S:G:cl:", longopts, NULL)) != -1) {
 		switch (c) {
 		case 'f':
 			forkit = 1;
@@ -913,6 +949,15 @@ int main(int argc, char *argv[])
 			unshare_flags |= CLONE_NEWNS;
 			procmnt = optarg ? optarg : "/proc";
 			break;
+		case OPT_MOUNTBINFMT:
+			unshare_flags |= CLONE_NEWNS | CLONE_NEWUSER;
+			binfmt_mnt = optarg;
+			if (!binfmt_mnt) {
+				if (!procmnt)
+					procmnt = "/proc";
+				binfmt_mnt = _PATH_PROC_BINFMT_MISC;
+			}
+			break;
 		case OPT_MAPUSER:
 			unshare_flags |= CLONE_NEWUSER;
 			mapuser = get_user(optarg, _("failed to parse uid"));
@@ -998,6 +1043,15 @@ int main(int argc, char *argv[])
 			boottime = strtos64_or_err(optarg, _("failed to parse boottime offset"));
 			force_boottime = 1;
 			break;
+		case 'l':
+			unshare_flags |= CLONE_NEWNS | CLONE_NEWUSER;
+			if (!binfmt_mnt) {
+				if (!procmnt)
+					procmnt = "/proc";
+				binfmt_mnt = _PATH_PROC_BINFMT_MISC;
+			}
+			newinterp = optarg;
+			break;
 
 		case 'h':
 			usage();
@@ -1152,6 +1206,13 @@ int main(int argc, char *argv[])
 	if ((unshare_flags & CLONE_NEWNS) && propagation)
 		set_propagation(propagation);
 
+	if (newinterp && is_fixed(newinterp) && newroot) {
+		if (mount("binfmt_misc", _PATH_PROC_BINFMT_MISC, "binfmt_misc",
+			  MS_NOSUID|MS_NOEXEC|MS_NODEV, NULL) != 0)
+			err(EXIT_FAILURE, _("mount %s failed"), _PATH_PROC_BINFMT_MISC);
+		load_interp(_PATH_PROC_BINFMT_MISC, newinterp);
+	}
+
 	if (newroot) {
 		if (chroot(newroot) != 0)
 			err(EXIT_FAILURE,
@@ -1178,6 +1239,14 @@ int main(int argc, char *argv[])
 			err(EXIT_FAILURE, _("mount %s failed"), procmnt);
 	}
 
+	if (binfmt_mnt) {
+		if (mount("binfmt_misc", binfmt_mnt, "binfmt_misc",
+			  MS_NOSUID|MS_NOEXEC|MS_NODEV, NULL) != 0)
+			err(EXIT_FAILURE, _("mount %s failed"), binfmt_mnt);
+	}
+	if (newinterp && !(is_fixed(newinterp) && newroot))
+		load_interp(binfmt_mnt, newinterp);
+
 	if (force_gid) {
 		if (setgroups(0, NULL) != 0)	/* drop supplementary groups */
 			err(EXIT_FAILURE, _("setgroups failed"));