2004-11-03 13:51:07 +00:00
|
|
|
.\" Copyright (C) 2000 by Werner Almesberger
|
2019-07-27 06:54:02 +00:00
|
|
|
.\" and Copyright (C) 2019 Michael Kerrisk <mtk.manpages@gmail.com>
|
ldd.1, capget.2, clone.2, create_module.2, fallocate.2, futex.2, get_kernel_syms.2, get_thread_area.2, getcpu.2, getitimer.2, getpid.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl_list.2, mkdir.2, mknod.2, pciconfig_read.2, pivot_root.2, posix_fadvise.2, query_module.2, sendfile.2, set_thread_area.2, setns.2, unshare.2, __setfpucw.3, a64l.3, addseverity.3, argz_add.3, bindresvport.3, cabs.3, cacos.3, cacosh.3, canonicalize_file_name.3, carg.3, casin.3, casinh.3, catan.3, catanh.3, ccos.3, ccosh.3, cerf.3, cexp.3, cexp2.3, cimag.3, clog.3, clog10.3, clog2.3, cmsg.3, conj.3, cpow.3, cproj.3, creal.3, csin.3, csinh.3, csqrt.3, ctan.3, ctanh.3, des_crypt.3, envz_add.3, fdim.3, fma.3, fmax.3, fmemopen.3, fmin.3, fmtmsg.3, fpclassify.3, gamma.3, getpt.3, getrpcent.3, getrpcport.3, getttyent.3, isgreater.3, key_setsecret.3, lgamma.3, malloc_hook.3, mempcpy.3, nan.3, netlink.3, nextafter.3, putgrent.3, remove.3, remquo.3, rpc.3, rtime.3, rtnetlink.3, setaliasent.3, setnetgrent.3, signbit.3, significand.3, sincos.3, stdin.3, tgamma.3, xcrypt.3, xdr.3, cciss.4, hpsa.4, mouse.4, pts.4, sk98lin.4, tty_ioctl.4, wavelan.4, hosts.equiv.5, rpc.5, tzfile.5, boot.7, complex.7, ddp.7, fifo.7, futex.7, icmp.7, ip.7, ipv6.7, netdevice.7, netlink.7, packet.7, raw.7, rtnetlink.7, socket.7, tcp.7, udp.7, unix.7, x25.7, sync.8: Global fix: Put copyright info at top of page, followed by blank line and LICENSE
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-03-10 09:29:51 +00:00
|
|
|
.\"
|
2013-03-10 09:28:50 +00:00
|
|
|
.\" %%%LICENSE_START(GPL_NOVERSION_ONELINE)
|
2004-11-03 13:51:07 +00:00
|
|
|
.\" May be distributed under GPL
|
2013-03-10 09:28:50 +00:00
|
|
|
.\" %%%LICENSE_END
|
2004-11-03 13:51:07 +00:00
|
|
|
.\"
|
|
|
|
|
.\" Written 2000-02-23 by Werner Almesberger
|
2007-09-20 06:52:22 +00:00
|
|
|
.\" Modified 2004-06-17 Michael Kerrisk <mtk.manpages@gmail.com>
|
2004-11-03 13:51:07 +00:00
|
|
|
.\"
|
pldd.1, bpf.2, chdir.2, clone.2, fanotify_init.2, fanotify_mark.2, intro.2, ipc.2, mount.2, mprotect.2, msgctl.2, msgget.2, msgop.2, pivot_root.2, pkey_alloc.2, poll.2, prctl.2, semctl.2, semget.2, semop.2, setxattr.2, shmctl.2, shmget.2, shmop.2, tkill.2, dlopen.3, exec.3, ftok.3, getutent.3, on_exit.3, strcat.3, cpuid.4, proc.5, capabilities.7, cgroup_namespaces.7, credentials.7, fanotify.7, mount_namespaces.7, namespaces.7, sched.7, signal.7, socket.7, unix.7, user_namespaces.7, vdso.7, xattr.7, ld.so.8: tstamp
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2019-08-02 06:34:32 +00:00
|
|
|
.TH PIVOT_ROOT 2 2019-08-02 "Linux" "Linux Programmer's Manual"
|
2004-11-03 13:51:07 +00:00
|
|
|
.SH NAME
|
intro.1, time.1, access.2, acct.2, alloc_hugepages.2, bind.2, chdir.2, chmod.2, chown.2, chroot.2, clone.2, close.2, execve.2, fallocate.2, fcntl.2, getdents.2, getrusage.2, getxattr.2, init_module.2, inotify_add_watch.2, ioprio_set.2, kcmp.2, link.2, listxattr.2, lseek.2, madvise.2, mkdir.2, mknod.2, mmap.2, mount.2, move_pages.2, msgctl.2, nfsservctl.2, open.2, pivot_root.2, quotactl.2, read.2, readlink.2, removexattr.2, rename.2, rmdir.2, semctl.2, setfsgid.2, setfsuid.2, setresuid.2, setuid.2, setup.2, setxattr.2, shmctl.2, splice.2, spu_create.2, stat.2, statfs.2, swapon.2, symlink.2, sync.2, sync_file_range.2, sysfs.2, truncate.2, umount.2, unlink.2, unshare.2, ustat.2, utime.2, utimensat.2, write.2, btree.3, errno.3, fexecve.3, ftw.3, futimes.3, get_nprocs_conf.3, getcwd.3, getdirentries.3, getmntent.3, glob.3, mkfifo.3, mq_open.3, readdir.3, realpath.3, recno.3, remove.3, sem_open.3, shm_open.3, statvfs.3, sysconf.3, telldir.3, tmpfile.3, cciss.4, initrd.4, pts.4, sk98lin.4, vcs.4, core.5, filesystems.5, proc.5, boot.7, bootparam.7, capabilities.7, cpuset.7, credentials.7, feature_test_macros.7, fifo.7, hier.7, inotify.7, intro.7, mq_overview.7, path_resolution.7, pipe.7, sem_overview.7, shm_overview.7, spufs.7, symlink.7, unix.7, uri.7, sync.8: Global fix: s/file system/filesystem/
Notwithstanding 24d01c530c5a3f75217543d02bf6712395e5f90c,
"filesystem" is the form used by the great majority of man pages
outside the man-pages project and in a number of other sources,
so let's go with that.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-08-08 08:07:57 +00:00
|
|
|
pivot_root \- change the root filesystem
|
2004-11-03 13:51:07 +00:00
|
|
|
.SH SYNOPSIS
|
|
|
|
|
.BI "int pivot_root(const char *" new_root ", const char *" put_old );
|
_syscall.2, clock_getres.2, clone.2, copy_file_range.2, create_module.2, delete_module.2, fallocate.2, futex.2, get_kernel_syms.2, get_robust_list.2, getcpu.2, getdents.2, gettid.2, gettimeofday.2, getunwind.2, init_module.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl_userfaultfd.2, ioprio_set.2, kcmp.2, kexec_load.2, keyctl.2, link.2, llseek.2, memfd_create.2, mmap.2, mq_getsetattr.2, msgctl.2, msgget.2, open_by_handle_at.2, outb.2, perf_event_open.2, pivot_root.2, process_vm_readv.2, query_module.2, readdir.2, recvmmsg.2, rename.2, request_key.2, restart_syscall.2, rt_sigqueueinfo.2, s390_pci_mmio_write.2, s390_runtime_instr.2, sched_setattr.2, seccomp.2, select.2, select_tut.2, send.2, sendmmsg.2, set_thread_area.2, set_tid_address.2, sgetmask.2, shmop.2, sigaction.2, sigprocmask.2, splice.2, spu_create.2, spu_run.2, statx.2, subpage_prot.2, sync_file_range.2, syscall.2, sysctl.2, sysfs.2, tee.2, timer_create.2, timer_delete.2, timer_getoverrun.2, timer_settime.2, tkill.2, uselib.2, utimensat.2, vmsplice.2, wait.2, aio_init.3, asinh.3, atan2.3, atanh.3, backtrace.3, basename.3, bswap.3, bzero.3, catgets.3, catopen.3, dladdr.3, dlsym.3, endian.3, envz_add.3, erf.3, erfc.3, error.3, ferror.3, ffs.3, fgetc.3, fmemopen.3, fopen.3, fopencookie.3, fseek.3, ftw.3, futimes.3, getdate.3, getenv.3, getline.3, getlogin.3, getrpcent.3, getsubopt.3, getutmp.3, getw.3, gnu_get_libc_version.3, inet_net_pton.3, isalpha.3, lio_listio.3, makedev.3, malloc_get_state.3, malloc_stats.3, malloc_trim.3, malloc_usable_size.3, matherr.3, memchr.3, nextup.3, ntp_gettime.3, posix_madvise.3, program_invocation_name.3, pthread_atfork.3, pthread_attr_setaffinity_np.3, pthread_attr_setdetachstate.3, pthread_attr_setguardsize.3, pthread_attr_setinheritsched.3, pthread_attr_setschedparam.3, pthread_attr_setschedpolicy.3, pthread_attr_setscope.3, pthread_attr_setstack.3, pthread_attr_setstackaddr.3, pthread_attr_setstacksize.3, pthread_cleanup_push_defer_np.3, pthread_detach.3, pthread_equal.3, pthread_exit.3, pthread_join.3, pthread_kill.3, pthread_kill_other_threads_np.3, pthread_rwlockattr_setkind_np.3, pthread_self.3, pthread_setcancelstate.3, pthread_setconcurrency.3, pthread_setschedprio.3, pthread_testcancel.3, pthread_tryjoin_np.3, pthread_yield.3, puts.3, random.3, random_r.3, rpc.3, sched_getcpu.3, setnetgrent.3, sigwait.3, stdin.3, strerror.3, strfmon.3, timeradd.3, tmpnam.3, toupper.3, towlower.3, towupper.3, ttyname.3, uselocale.3, xdr.3, dsp56k.4, sigevent.7, vdso.7: ffix
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2017-08-15 17:26:11 +00:00
|
|
|
.PP
|
get_robust_list.2, get_thread_area.2, getcpu.2, getdents.2, gettid.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioprio_set.2, kexec_load.2, llseek.2, modify_ldt.2, mq_getsetattr.2, pivot_root.2, readdir.2, rt_sigqueueinfo.2, set_thread_area.2, sgetmask.2, spu_create.2, spu_run.2, subpage_prot.2, sysctl.2, tkill.2: Add note to SYNOPSIS that there is no glibc wrapper for system call
Reduce the chance that the reader may be misled into thinking
that there is a wrapper function for this system call by noting
explicitly in the SYNOPSIS that there is no glibc wrapper and
pointing the reader to NOTES for further details.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2012-07-13 06:48:20 +00:00
|
|
|
.IR Note :
|
|
|
|
|
There is no glibc wrapper for this system call; see NOTES.
|
2004-11-03 13:51:07 +00:00
|
|
|
.SH DESCRIPTION
|
2007-05-12 09:06:04 +00:00
|
|
|
.BR pivot_root ()
|
2019-07-27 16:50:09 +00:00
|
|
|
changes the root filesystem in the mount namespace of the calling process.
|
|
|
|
|
More precisely, it moves the root filesystem to the
|
|
|
|
|
directory \fIput_old\fP and makes \fInew_root\fP the new root filesystem.
|
2019-07-27 07:15:03 +00:00
|
|
|
The calling process must have the
|
|
|
|
|
.B CAP_SYS_ADMIN
|
|
|
|
|
capability in the user namespace that owns the caller's mount namespace.
|
_syscall.2, bpf.2, cacheflush.2, capget.2, chdir.2, chmod.2, chroot.2, clock_getres.2, clock_nanosleep.2, clone.2, close.2, connect.2, copy_file_range.2, create_module.2, delete_module.2, dup.2, epoll_create.2, epoll_ctl.2, epoll_wait.2, eventfd.2, execve.2, execveat.2, fallocate.2, flock.2, fork.2, fsync.2, futex.2, futimesat.2, get_kernel_syms.2, get_mempolicy.2, get_robust_list.2, getcpu.2, getdents.2, getdomainname.2, getgid.2, getgroups.2, gethostname.2, getitimer.2, getpagesize.2, getpeername.2, getpriority.2, getrandom.2, getresuid.2, getrlimit.2, getrusage.2, getsid.2, getsockname.2, getsockopt.2, gettid.2, gettimeofday.2, getuid.2, getunwind.2, init_module.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, intro.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl_fat.2, ioctl_ficlonerange.2, ioctl_fideduperange.2, ioctl_tty.2, ioctl_userfaultfd.2, ioperm.2, iopl.2, ioprio_set.2, kcmp.2, kexec_load.2, keyctl.2, kill.2, link.2, listen.2, listxattr.2, llseek.2, lookup_dcookie.2, lseek.2, madvise.2, mbind.2, membarrier.2, memfd_create.2, migrate_pages.2, mincore.2, mkdir.2, mknod.2, mlock.2, mmap.2, mmap2.2, modify_ldt.2, move_pages.2, mprotect.2, mq_getsetattr.2, mremap.2, msgctl.2, msgget.2, msgop.2, msync.2, nanosleep.2, nfsservctl.2, nice.2, open_by_handle_at.2, outb.2, perf_event_open.2, perfmonctl.2, personality.2, pivot_root.2, pkey_alloc.2, poll.2, posix_fadvise.2, prctl.2, pread.2, process_vm_readv.2, ptrace.2, query_module.2, quotactl.2, read.2, readahead.2, readdir.2, readv.2, reboot.2, recv.2, recvmmsg.2, remap_file_pages.2, rename.2, request_key.2, restart_syscall.2, rt_sigqueueinfo.2, s390_pci_mmio_write.2, s390_runtime_instr.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setattr.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, seccomp.2, select.2, select_tut.2, semctl.2, semget.2, semop.2, send.2, sendfile.2, sendmmsg.2, set_mempolicy.2, set_thread_area.2, set_tid_address.2, seteuid.2, setfsgid.2, setfsuid.2, setgid.2, setns.2, setpgid.2, setresuid.2, setreuid.2, setsid.2, setuid.2, sgetmask.2, shmctl.2, shmget.2, shmop.2, sigaction.2, sigaltstack.2, sigpending.2, sigprocmask.2, sigreturn.2, sigsuspend.2, sigwaitinfo.2, socket.2, socketcall.2, socketpair.2, splice.2, spu_create.2, spu_run.2, stat.2, statfs.2, statx.2, subpage_prot.2, swapon.2, symlink.2, sync.2, sync_file_range.2, syscalls.2, sysctl.2, sysinfo.2, syslog.2, tee.2, time.2, timer_create.2, timer_getoverrun.2, timer_settime.2, timerfd_create.2, times.2, tkill.2, truncate.2, umask.2, umount.2, unimplemented.2, unlink.2, unshare.2, uselib.2, userfaultfd.2, utime.2, utimensat.2, vfork.2, vmsplice.2, wait.2, wait4.2, write.2: Formatting fix: replace blank lines with .PP/.IP
Blank lines shouldn't generally appear in *roff source (other
than in code examples), since they create large vertical
spaces between text blocks.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2017-08-16 07:30:51 +00:00
|
|
|
.PP
|
2007-05-12 09:06:04 +00:00
|
|
|
.BR pivot_root ()
|
|
|
|
|
may or may not change the current root and the current
|
2019-07-27 05:43:58 +00:00
|
|
|
working directory of any processes or threads that
|
|
|
|
|
use the old root directory and which are in
|
|
|
|
|
the same mount namespace as the caller of
|
|
|
|
|
.BR pivot_root ().
|
2007-05-12 09:06:04 +00:00
|
|
|
The caller of
|
|
|
|
|
.BR pivot_root ()
|
2019-09-10 09:35:37 +00:00
|
|
|
should ensure that processes with root or current working directory
|
2007-12-27 16:01:37 +00:00
|
|
|
at the old root operate correctly in either case.
|
2007-04-12 22:42:49 +00:00
|
|
|
An easy way to ensure this is to change their
|
2007-12-27 16:01:37 +00:00
|
|
|
root and current working directory to \fInew_root\fP before invoking
|
2007-05-12 09:06:04 +00:00
|
|
|
.BR pivot_root ().
|
2019-09-10 08:42:22 +00:00
|
|
|
Note also that
|
|
|
|
|
.BR pivot_root ()
|
|
|
|
|
may or may not affect the calling process's current working directory.
|
|
|
|
|
It is therefore recommended to call
|
|
|
|
|
\fBchdir("/")\fP immediately after
|
|
|
|
|
.BR pivot_root ().
|
_syscall.2, bpf.2, cacheflush.2, capget.2, chdir.2, chmod.2, chroot.2, clock_getres.2, clock_nanosleep.2, clone.2, close.2, connect.2, copy_file_range.2, create_module.2, delete_module.2, dup.2, epoll_create.2, epoll_ctl.2, epoll_wait.2, eventfd.2, execve.2, execveat.2, fallocate.2, flock.2, fork.2, fsync.2, futex.2, futimesat.2, get_kernel_syms.2, get_mempolicy.2, get_robust_list.2, getcpu.2, getdents.2, getdomainname.2, getgid.2, getgroups.2, gethostname.2, getitimer.2, getpagesize.2, getpeername.2, getpriority.2, getrandom.2, getresuid.2, getrlimit.2, getrusage.2, getsid.2, getsockname.2, getsockopt.2, gettid.2, gettimeofday.2, getuid.2, getunwind.2, init_module.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, intro.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl_fat.2, ioctl_ficlonerange.2, ioctl_fideduperange.2, ioctl_tty.2, ioctl_userfaultfd.2, ioperm.2, iopl.2, ioprio_set.2, kcmp.2, kexec_load.2, keyctl.2, kill.2, link.2, listen.2, listxattr.2, llseek.2, lookup_dcookie.2, lseek.2, madvise.2, mbind.2, membarrier.2, memfd_create.2, migrate_pages.2, mincore.2, mkdir.2, mknod.2, mlock.2, mmap.2, mmap2.2, modify_ldt.2, move_pages.2, mprotect.2, mq_getsetattr.2, mremap.2, msgctl.2, msgget.2, msgop.2, msync.2, nanosleep.2, nfsservctl.2, nice.2, open_by_handle_at.2, outb.2, perf_event_open.2, perfmonctl.2, personality.2, pivot_root.2, pkey_alloc.2, poll.2, posix_fadvise.2, prctl.2, pread.2, process_vm_readv.2, ptrace.2, query_module.2, quotactl.2, read.2, readahead.2, readdir.2, readv.2, reboot.2, recv.2, recvmmsg.2, remap_file_pages.2, rename.2, request_key.2, restart_syscall.2, rt_sigqueueinfo.2, s390_pci_mmio_write.2, s390_runtime_instr.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setattr.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, seccomp.2, select.2, select_tut.2, semctl.2, semget.2, semop.2, send.2, sendfile.2, sendmmsg.2, set_mempolicy.2, set_thread_area.2, set_tid_address.2, seteuid.2, setfsgid.2, setfsuid.2, setgid.2, setns.2, setpgid.2, setresuid.2, setreuid.2, setsid.2, setuid.2, sgetmask.2, shmctl.2, shmget.2, shmop.2, sigaction.2, sigaltstack.2, sigpending.2, sigprocmask.2, sigreturn.2, sigsuspend.2, sigwaitinfo.2, socket.2, socketcall.2, socketpair.2, splice.2, spu_create.2, spu_run.2, stat.2, statfs.2, statx.2, subpage_prot.2, swapon.2, symlink.2, sync.2, sync_file_range.2, syscalls.2, sysctl.2, sysinfo.2, syslog.2, tee.2, time.2, timer_create.2, timer_getoverrun.2, timer_settime.2, timerfd_create.2, times.2, tkill.2, truncate.2, umask.2, umount.2, unimplemented.2, unlink.2, unshare.2, uselib.2, userfaultfd.2, utime.2, utimensat.2, vfork.2, vmsplice.2, wait.2, wait4.2, write.2: Formatting fix: replace blank lines with .PP/.IP
Blank lines shouldn't generally appear in *roff source (other
than in code examples), since they create large vertical
spaces between text blocks.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2017-08-16 07:30:51 +00:00
|
|
|
.PP
|
2019-09-10 09:35:37 +00:00
|
|
|
The paragraph above is intentionally vague because at the time when
|
2019-07-27 07:40:34 +00:00
|
|
|
.BR pivot_root ()
|
2019-09-10 09:35:37 +00:00
|
|
|
was first implemented, it was unclear whether its affect
|
|
|
|
|
on other process's root and current working directories\(emand
|
|
|
|
|
the caller's current working directory\(emmight change in the future.
|
|
|
|
|
However, the behavior has remained consistent since this system call
|
2019-07-27 07:40:34 +00:00
|
|
|
was first implemented:
|
2007-05-12 09:06:04 +00:00
|
|
|
.BR pivot_root ()
|
2019-07-27 05:52:00 +00:00
|
|
|
changes the root directory and the current working directory
|
|
|
|
|
of each process or thread in the same mount namespace to
|
|
|
|
|
.I new_root
|
|
|
|
|
if they point to the old root directory.
|
2019-09-10 09:35:37 +00:00
|
|
|
(See also NOTES.)
|
|
|
|
|
On the other hand,
|
|
|
|
|
.BR pivot_root ()
|
|
|
|
|
does not change the caller's current working directory
|
|
|
|
|
(unless it is on the old root directory),
|
|
|
|
|
and thus it should be followed by a
|
|
|
|
|
\fBchdir("/")\fP call.
|
_syscall.2, bpf.2, cacheflush.2, capget.2, chdir.2, chmod.2, chroot.2, clock_getres.2, clock_nanosleep.2, clone.2, close.2, connect.2, copy_file_range.2, create_module.2, delete_module.2, dup.2, epoll_create.2, epoll_ctl.2, epoll_wait.2, eventfd.2, execve.2, execveat.2, fallocate.2, flock.2, fork.2, fsync.2, futex.2, futimesat.2, get_kernel_syms.2, get_mempolicy.2, get_robust_list.2, getcpu.2, getdents.2, getdomainname.2, getgid.2, getgroups.2, gethostname.2, getitimer.2, getpagesize.2, getpeername.2, getpriority.2, getrandom.2, getresuid.2, getrlimit.2, getrusage.2, getsid.2, getsockname.2, getsockopt.2, gettid.2, gettimeofday.2, getuid.2, getunwind.2, init_module.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, intro.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl_fat.2, ioctl_ficlonerange.2, ioctl_fideduperange.2, ioctl_tty.2, ioctl_userfaultfd.2, ioperm.2, iopl.2, ioprio_set.2, kcmp.2, kexec_load.2, keyctl.2, kill.2, link.2, listen.2, listxattr.2, llseek.2, lookup_dcookie.2, lseek.2, madvise.2, mbind.2, membarrier.2, memfd_create.2, migrate_pages.2, mincore.2, mkdir.2, mknod.2, mlock.2, mmap.2, mmap2.2, modify_ldt.2, move_pages.2, mprotect.2, mq_getsetattr.2, mremap.2, msgctl.2, msgget.2, msgop.2, msync.2, nanosleep.2, nfsservctl.2, nice.2, open_by_handle_at.2, outb.2, perf_event_open.2, perfmonctl.2, personality.2, pivot_root.2, pkey_alloc.2, poll.2, posix_fadvise.2, prctl.2, pread.2, process_vm_readv.2, ptrace.2, query_module.2, quotactl.2, read.2, readahead.2, readdir.2, readv.2, reboot.2, recv.2, recvmmsg.2, remap_file_pages.2, rename.2, request_key.2, restart_syscall.2, rt_sigqueueinfo.2, s390_pci_mmio_write.2, s390_runtime_instr.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setattr.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, seccomp.2, select.2, select_tut.2, semctl.2, semget.2, semop.2, send.2, sendfile.2, sendmmsg.2, set_mempolicy.2, set_thread_area.2, set_tid_address.2, seteuid.2, setfsgid.2, setfsuid.2, setgid.2, setns.2, setpgid.2, setresuid.2, setreuid.2, setsid.2, setuid.2, sgetmask.2, shmctl.2, shmget.2, shmop.2, sigaction.2, sigaltstack.2, sigpending.2, sigprocmask.2, sigreturn.2, sigsuspend.2, sigwaitinfo.2, socket.2, socketcall.2, socketpair.2, splice.2, spu_create.2, spu_run.2, stat.2, statfs.2, statx.2, subpage_prot.2, swapon.2, symlink.2, sync.2, sync_file_range.2, syscalls.2, sysctl.2, sysinfo.2, syslog.2, tee.2, time.2, timer_create.2, timer_getoverrun.2, timer_settime.2, timerfd_create.2, times.2, tkill.2, truncate.2, umask.2, umount.2, unimplemented.2, unlink.2, unshare.2, uselib.2, userfaultfd.2, utime.2, utimensat.2, vfork.2, vmsplice.2, wait.2, wait4.2, write.2: Formatting fix: replace blank lines with .PP/.IP
Blank lines shouldn't generally appear in *roff source (other
than in code examples), since they create large vertical
spaces between text blocks.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2017-08-16 07:30:51 +00:00
|
|
|
.PP
|
2019-07-30 11:56:47 +00:00
|
|
|
The following restrictions apply:
|
2004-11-03 13:51:07 +00:00
|
|
|
.IP \- 3
|
2019-07-30 11:56:47 +00:00
|
|
|
.IR new_root
|
|
|
|
|
and
|
|
|
|
|
.IR put_old
|
|
|
|
|
must be directories.
|
2019-07-27 07:11:28 +00:00
|
|
|
.IP \-
|
intro.1, time.1, access.2, acct.2, alloc_hugepages.2, bind.2, chdir.2, chmod.2, chown.2, chroot.2, clone.2, close.2, execve.2, fallocate.2, fcntl.2, getdents.2, getrusage.2, getxattr.2, init_module.2, inotify_add_watch.2, ioprio_set.2, kcmp.2, link.2, listxattr.2, lseek.2, madvise.2, mkdir.2, mknod.2, mmap.2, mount.2, move_pages.2, msgctl.2, nfsservctl.2, open.2, pivot_root.2, quotactl.2, read.2, readlink.2, removexattr.2, rename.2, rmdir.2, semctl.2, setfsgid.2, setfsuid.2, setresuid.2, setuid.2, setup.2, setxattr.2, shmctl.2, splice.2, spu_create.2, stat.2, statfs.2, swapon.2, symlink.2, sync.2, sync_file_range.2, sysfs.2, truncate.2, umount.2, unlink.2, unshare.2, ustat.2, utime.2, utimensat.2, write.2, btree.3, errno.3, fexecve.3, ftw.3, futimes.3, get_nprocs_conf.3, getcwd.3, getdirentries.3, getmntent.3, glob.3, mkfifo.3, mq_open.3, readdir.3, realpath.3, recno.3, remove.3, sem_open.3, shm_open.3, statvfs.3, sysconf.3, telldir.3, tmpfile.3, cciss.4, initrd.4, pts.4, sk98lin.4, vcs.4, core.5, filesystems.5, proc.5, boot.7, bootparam.7, capabilities.7, cpuset.7, credentials.7, feature_test_macros.7, fifo.7, hier.7, inotify.7, intro.7, mq_overview.7, path_resolution.7, pipe.7, sem_overview.7, shm_overview.7, spufs.7, symlink.7, unix.7, uri.7, sync.8: Global fix: s/file system/filesystem/
Notwithstanding 24d01c530c5a3f75217543d02bf6712395e5f90c,
"filesystem" is the form used by the great majority of man pages
outside the man-pages project and in a number of other sources,
so let's go with that.
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-08-08 08:07:57 +00:00
|
|
|
\fInew_root\fP and \fIput_old\fP must not be on the same filesystem as
|
2004-11-03 13:51:07 +00:00
|
|
|
the current root.
|
2019-07-30 12:14:10 +00:00
|
|
|
In particular,
|
|
|
|
|
.IR new_root
|
|
|
|
|
can't be
|
|
|
|
|
.IR """/"""
|
|
|
|
|
(but can be a bind mounted directory on the current root filesystem).
|
2019-07-27 07:11:28 +00:00
|
|
|
.IP \-
|
2019-07-31 21:51:39 +00:00
|
|
|
\fIput_old\fP must be at or underneath \fInew_root\fP;
|
|
|
|
|
that is, adding a nonnegative
|
2005-11-02 13:55:25 +00:00
|
|
|
number of \fI/..\fP to the string pointed to by \fIput_old\fP must yield
|
2004-11-03 13:51:07 +00:00
|
|
|
the same directory as \fInew_root\fP.
|
2019-07-27 07:11:28 +00:00
|
|
|
.IP \-
|
pivot_root.2: 'new_root' must be a mount point
It appears that 'new_root' may not have needed to be a mount
point on ancient kernels, but already in Linux 2.4.5, there
was the diff shown below. Verified also by testing.
@@ -1631,8 +1605,9 @@
* - we don't move root/cwd if they are not at the root (reason: if something
* cared enough to change them, it's probably wrong to force them elsewhere)
* - it's okay to pick a root that isn't the root of a file system, e.g.
- * /nfs/my_root where /nfs is the mount point. Better avoid creating
- * unreachable mount points this way, though.
+ * /nfs/my_root where /nfs is the mount point. It must be a mountpoint,
+ * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
+ * first.
*/
asmlinkage long sys_pivot_root(const char *new_root, const char *put_old)
@@ -1640,7 +1615,7 @@
struct dentry *root;
struct vfsmount *root_mnt;
struct vfsmount *tmp;
- struct nameidata new_nd, old_nd;
+ struct nameidata new_nd, old_nd, parent_nd, root_parent;
char *name;
int error;
@@ -1688,6 +1663,10 @@
if (new_nd.mnt == root_mnt || old_nd.mnt == root_mnt)
goto out2; /* loop */
error = -EINVAL;
+ if (root_mnt->mnt_root != root)
+ goto out2;
+ if (new_nd.mnt->mnt_root != new_nd.dentry)
+ goto out2; /* not a mountpoint */
tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */
spin_lock(&dcache_lock);
if (tmp != new_nd.mnt) {
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2019-07-26 14:54:16 +00:00
|
|
|
.I new_root
|
|
|
|
|
must be a mount point.
|
|
|
|
|
(If it is not otherwise a mount point, it suffices to bind mount
|
|
|
|
|
.I new_root
|
|
|
|
|
on top of itself.)
|
2019-07-27 07:11:28 +00:00
|
|
|
.IP \-
|
2019-09-23 10:26:37 +00:00
|
|
|
The propagation type of the parent mount of
|
|
|
|
|
.IR new_root
|
|
|
|
|
and the parent mount of the current root directory must not be
|
2019-07-26 21:22:59 +00:00
|
|
|
.BR MS_SHARED ;
|
|
|
|
|
similarly, if
|
|
|
|
|
.I put_old
|
|
|
|
|
is an existing mount point, its propagation type must not be
|
2019-07-26 15:10:06 +00:00
|
|
|
.BR MS_SHARED .
|
2019-09-23 10:43:14 +00:00
|
|
|
These restrictions ensure that
|
|
|
|
|
.BR pivot_root ()
|
|
|
|
|
never propagates any changes to another mount namespace.
|
2019-07-30 20:59:17 +00:00
|
|
|
.IP \-
|
|
|
|
|
The current root directory must be a mount point.
|
getent.1, intro.1, time.1, _exit.2, _syscall.2, accept.2, access.2, acct.2, adjtimex.2, alarm.2, alloc_hugepages.2, arch_prctl.2, bdflush.2, bind.2, brk.2, cacheflush.2, capget.2, chdir.2, chmod.2, chown.2, chroot.2, clock_getres.2, clock_nanosleep.2, clone.2, close.2, connect.2, create_module.2, delete_module.2, dup.2, epoll_create.2, epoll_ctl.2, epoll_wait.2, eventfd.2, execve.2, exit_group.2, faccessat.2, fchmodat.2, fchownat.2, fcntl.2, flock.2, fork.2, fstatat.2, fsync.2, futex.2, futimesat.2, get_kernel_syms.2, get_robust_list.2, get_thread_area.2, getcpu.2, getdents.2, getdomainname.2, getgid.2, getgroups.2, gethostname.2, getitimer.2, getpagesize.2, getpeername.2, getpid.2, getpriority.2, getresuid.2, getrlimit.2, getrusage.2, getsid.2, getsockname.2, getsockopt.2, gettid.2, gettimeofday.2, getuid.2, getunwind.2, getxattr.2, idle.2, init_module.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, intro.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl.2, ioctl_list.2, ioperm.2, iopl.2, ioprio_set.2, ipc.2, kcmp.2, kill.2, killpg.2, link.2, linkat.2, listen.2, listxattr.2, llseek.2, lookup_dcookie.2, lseek.2, madvise.2, migrate_pages.2, mincore.2, mkdir.2, mkdirat.2, mknod.2, mknodat.2, mlock.2, mmap.2, mmap2.2, modify_ldt.2, mount.2, move_pages.2, mprotect.2, mq_getsetattr.2, mremap.2, msgctl.2, msgget.2, msgop.2, msync.2, nanosleep.2, nfsservctl.2, nice.2, open.2, openat.2, outb.2, pause.2, pciconfig_read.2, perf_event_open.2, perfmonctl.2, personality.2, pipe.2, pivot_root.2, poll.2, posix_fadvise.2, prctl.2, pread.2, process_vm_readv.2, ptrace.2, query_module.2, quotactl.2, read.2, readahead.2, readdir.2, readlink.2, readlinkat.2, readv.2, reboot.2, recv.2, remap_file_pages.2, removexattr.2, rename.2, renameat.2, rmdir.2, rt_sigqueueinfo.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, select.2, semctl.2, semget.2, semop.2, send.2, sendfile.2, set_thread_area.2, set_tid_address.2, seteuid.2, setfsgid.2, setfsuid.2, setgid.2, setpgid.2, setresuid.2, setreuid.2, setsid.2, setuid.2, setup.2, setxattr.2, shmctl.2, shmget.2, shmop.2, shutdown.2, sigaction.2, sigaltstack.2, signal.2, signalfd.2, sigpending.2, sigprocmask.2, sigreturn.2, sigsuspend.2, sigwaitinfo.2, socket.2, socketcall.2, socketpair.2, splice.2, stat.2, statfs.2, stime.2, swapon.2, symlink.2, symlinkat.2, sync.2, sync_file_range.2, sysctl.2, sysfs.2, sysinfo.2, syslog.2, tee.2, time.2, timerfd_create.2, times.2, tkill.2, truncate.2, umask.2, umount.2, uname.2, unimplemented.2, unlink.2, unlinkat.2, uselib.2, ustat.2, utime.2, utimensat.2, vfork.2, vhangup.2, vm86.2, vmsplice.2, wait.2, wait4.2, write.2, CPU_SET.3, INFINITY.3, MB_CUR_MAX.3, MB_LEN_MAX.3, __setfpucw.3, a64l.3, abort.3, abs.3, acos.3, acosh.3, addseverity.3, adjtime.3, aio_cancel.3, aio_error.3, aio_fsync.3, aio_read.3, aio_return.3, aio_suspend.3, aio_write.3, alloca.3, argz_add.3, asin.3, asinh.3, asprintf.3, assert.3, assert_perror.3, atan.3, atan2.3, atanh.3, atexit.3, atof.3, atoi.3, backtrace.3, basename.3, bcmp.3, bcopy.3, bindresvport.3, bsd_signal.3, bsearch.3, bstring.3, btowc.3, btree.3, byteorder.3, bzero.3, cabs.3, cacos.3, cacosh.3, canonicalize_file_name.3, carg.3, casin.3, casinh.3, catan.3, catanh.3, catgets.3, catopen.3, cbrt.3, ccos.3, ccosh.3, ceil.3, cerf.3, cexp.3, cexp2.3, cfree.3, cimag.3, clearenv.3, clock.3, clock_getcpuclockid.3, clog.3, clog10.3, clog2.3, closedir.3, cmsg.3, confstr.3, conj.3, copysign.3, cos.3, cosh.3, cpow.3, cproj.3, creal.3, crypt.3, csin.3, csinh.3, csqrt.3, ctan.3, ctanh.3, ctermid.3, ctime.3, daemon.3, dbopen.3, des_crypt.3, difftime.3, dirfd.3, div.3, dl_iterate_phdr.3, dlopen.3, dprintf.3, drand48.3, drand48_r.3, dysize.3, ecvt.3, ecvt_r.3, encrypt.3, end.3, endian.3, envz_add.3, erf.3, erfc.3, err.3, errno.3, error.3, ether_aton.3, euidaccess.3, exec.3, exit.3, exp.3, exp10.3, exp2.3, expm1.3, fabs.3, fclose.3, fcloseall.3, fdim.3, fenv.3, ferror.3, fexecve.3, fflush.3, ffs.3, fgetgrent.3, fgetpwent.3, fgetwc.3, fgetws.3, finite.3, flockfile.3, floor.3, fma.3, fmax.3, fmemopen.3, fmin.3, fmod.3, fmtmsg.3, fnmatch.3, fopen.3, fpathconf.3, fpclassify.3, fpurge.3, fputwc.3, fputws.3, fread.3, frexp.3, fseek.3, fseeko.3, ftime.3, ftok.3, fts.3, ftw.3, futimes.3, fwide.3, gamma.3, gcvt.3, getaddrinfo.3, getaddrinfo_a.3, getauxval.3, getcontext.3, getcwd.3, getdate.3, getdirentries.3, getdtablesize.3, getenv.3, getfsent.3, getgrent.3, getgrent_r.3, getgrnam.3, getgrouplist.3, gethostbyname.3, gethostid.3, getipnodebyname.3, getline.3, getloadavg.3, getlogin.3, getmntent.3, getnameinfo.3, getnetent.3, getnetent_r.3, getopt.3, getpass.3, getprotoent.3, getprotoent_r.3, getpt.3, getpw.3, getpwent.3, getpwent_r.3, getpwnam.3, getrpcent.3, getrpcent_r.3, getrpcport.3, gets.3, getservent.3, getservent_r.3, getspnam.3, getttyent.3, getumask.3, getusershell.3, getutent.3, getw.3, getwchar.3, glob.3, grantpt.3, gsignal.3, hash.3, hsearch.3, hypot.3, iconv.3, iconv_close.3, iconv_open.3, ilogb.3, index.3, inet.3, inet_ntop.3, inet_pton.3, infnan.3, initgroups.3, insque.3, intro.3, isalpha.3, isatty.3, isgreater.3, iswalnum.3, iswalpha.3, iswblank.3, iswcntrl.3, iswctype.3, iswdigit.3, iswgraph.3, iswlower.3, iswprint.3, iswpunct.3, iswspace.3, iswupper.3, iswxdigit.3, j0.3, key_setsecret.3, ldexp.3, lgamma.3, lio_listio.3, localeconv.3, lockf.3, log.3, log10.3, log1p.3, log2.3, logb.3, login.3, longjmp.3, lrint.3, lround.3, lsearch.3, lseek64.3, makecontext.3, makedev.3, malloc.3, malloc_hook.3, mblen.3, mbrlen.3, mbrtowc.3, mbsinit.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, memccpy.3, memchr.3, memcmp.3, memcpy.3, memfrob.3, memmem.3, memmove.3, mempcpy.3, memset.3, mkdtemp.3, mkfifo.3, mkfifoat.3, mkstemp.3, mktemp.3, modf.3, mpool.3, mq_close.3, mq_getattr.3, mq_notify.3, mq_open.3, mq_receive.3, mq_send.3, mq_unlink.3, mtrace.3, nan.3, netlink.3, nextafter.3, nl_langinfo.3, offsetof.3, on_exit.3, opendir.3, openpty.3, perror.3, popen.3, posix_fallocate.3, posix_memalign.3, posix_openpt.3, pow.3, pow10.3, printf.3, profil.3, program_invocation_name.3, psignal.3, pthread_kill_other_threads_np.3, ptsname.3, putenv.3, putgrent.3, putpwent.3, puts.3, putwchar.3, qecvt.3, qsort.3, queue.3, raise.3, rand.3, random.3, random_r.3, rcmd.3, re_comp.3, readdir.3, realpath.3, recno.3, regex.3, remainder.3, remove.3, remquo.3, resolver.3, rewinddir.3, rexec.3, rint.3, round.3, rpc.3, rpmatch.3, rtime.3, rtnetlink.3, scalb.3, scalbln.3, scandir.3, scandirat.3, scanf.3, seekdir.3, sem_close.3, sem_destroy.3, sem_getvalue.3, sem_init.3, sem_open.3, sem_post.3, sem_unlink.3, sem_wait.3, setaliasent.3, setbuf.3, setenv.3, setjmp.3, setlocale.3, setlogmask.3, setnetgrent.3, shm_open.3, siginterrupt.3, signbit.3, significand.3, sigpause.3, sigqueue.3, sigset.3, sigsetops.3, sigvec.3, sin.3, sincos.3, sinh.3, sleep.3, sockatmark.3, sqrt.3, statvfs.3, stdarg.3, stdin.3, stdio.3, stdio_ext.3, stpcpy.3, stpncpy.3, strcasecmp.3, strcat.3, strchr.3, strcmp.3, strcoll.3, strcpy.3, strdup.3, strerror.3, strfmon.3, strfry.3, strftime.3, string.3, strlen.3, strnlen.3, strpbrk.3, strptime.3, strsep.3, strsignal.3, strspn.3, strstr.3, strtod.3, strtoimax.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, swab.3, sysconf.3, syslog.3, system.3, sysv_signal.3, tan.3, tanh.3, tcgetpgrp.3, tcgetsid.3, telldir.3, tempnam.3, termios.3, tgamma.3, timegm.3, timeradd.3, tmpfile.3, tmpnam.3, toascii.3, toupper.3, towctrans.3, towlower.3, towupper.3, trunc.3, tsearch.3, ttyname.3, ttyslot.3, tzset.3, ualarm.3, ulimit.3, ungetwc.3, unlocked_stdio.3, unlockpt.3, updwtmp.3, usleep.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscasecmp.3, wcscat.3, wcschr.3, wcscmp.3, wcscpy.3, wcscspn.3, wcsdup.3, wcslen.3, wcsncasecmp.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcspbrk.3, wcsrchr.3, wcsrtombs.3, wcsspn.3, wcsstr.3, wcstoimax.3, wcstok.3, wcstombs.3, wcswidth.3, wctob.3, wctomb.3, wctrans.3, wctype.3, wcwidth.3, wmemchr.3, wmemcmp.3, wmemcpy.3, wmemmove.3, wmemset.3, wordexp.3, wprintf.3, xcrypt.3, xdr.3, y0.3, cciss.4, console.4, console_codes.4, console_ioctl.4, dsp56k.4, fd.4, full.4, hd.4, hpsa.4, initrd.4, intro.4, lp.4, mem.4, mouse.4, null.4, pts.4, ram.4, random.4, rtc.4, sk98lin.4, st.4, tty.4, ttyS.4, tty_ioctl.4, vcs.4, wavelan.4, acct.5, charmap.5, dir_colors.5, filesystems.5, ftpusers.5, group.5, host.conf.5, hosts.5, hosts.equiv.5, intro.5, issue.5, locale.5, motd.5, networks.5, nologin.5, nscd.conf.5, passwd.5, proc.5, protocols.5, resolv.conf.5, rpc.5, securetty.5, services.5, shells.5, termcap.5, ttytype.5, utmp.5, armscii-8.7, arp.7, ascii.7, bootparam.7, capabilities.7, charsets.7, complex.7, cp1251.7, credentials.7, ddp.7, environ.7, epoll.7, fifo.7, futex.7, glob.7, hier.7, icmp.7, inotify.7, intro.7, ip.7, ipv6.7, iso_8859-1.7, iso_8859-10.7, iso_8859-11.7, iso_8859-13.7, iso_8859-14.7, iso_8859-15.7, iso_8859-16.7, iso_8859-2.7, iso_8859-3.7, iso_8859-4.7, iso_8859-5.7, iso_8859-6.7, iso_8859-7.7, iso_8859-8.7, iso_8859-9.7, koi8-r.7, koi8-u.7, locale.7, mailaddr.7, man.7, mq_overview.7, netdevice.7, netlink.7, numa.7, packet.7, path_resolution.7, pipe.7, posixoptions.7, pthreads.7, pty.7, raw.7, regex.7, rtld-audit.7, rtnetlink.7, sem_overview.7, shm_overview.7, sigevent.7, signal.7, socket.7, standards.7, suffixes.7, svipc.7, tcp.7, termio.7, time.7, udp.7, udplite.7, unicode.7, unix.7, uri.7, utf-8.7, x25.7, nscd.8, sync.8, tzselect.8, zdump.8, zic.8: Global fix: remove unneeded double quotes in .SH headings
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-02-24 18:01:36 +00:00
|
|
|
.SH RETURN VALUE
|
2007-04-12 22:42:49 +00:00
|
|
|
On success, zero is returned.
|
|
|
|
|
On error, \-1 is returned, and
|
2004-11-03 13:51:07 +00:00
|
|
|
\fIerrno\fP is set appropriately.
|
|
|
|
|
.SH ERRORS
|
2007-05-12 09:06:04 +00:00
|
|
|
.BR pivot_root ()
|
2019-07-27 05:09:03 +00:00
|
|
|
may fail with any of the same errors as
|
2007-05-12 09:06:04 +00:00
|
|
|
.BR stat (2).
|
2019-07-27 05:09:03 +00:00
|
|
|
Additionally, it may fail with the following errors:
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP
|
|
|
|
|
.B EBUSY
|
2019-07-30 10:37:26 +00:00
|
|
|
.\" Reconfirmed that the following error occurs on Linux 5.0 by
|
|
|
|
|
.\" specifying 'new_root' as "/rootfs" and 'put_old' as
|
|
|
|
|
.\" "/rootfs/oldrootfs", and *not* bind mounting "/rootfs" on top of
|
|
|
|
|
.\" itself. Of course, this is an odd situation, since a later check
|
|
|
|
|
.\" in the kernel code will in any case yield EINVAL if 'new_root' is
|
|
|
|
|
.\" not a mount point. However, when the system call was first added,
|
2019-09-25 15:58:46 +00:00
|
|
|
.\" 'new_root' was not required to be a mount point. So, this
|
2019-07-30 10:37:26 +00:00
|
|
|
.\" error is nowadays probably just the result of crufty accumulation.
|
|
|
|
|
.\" This error can also occur if we bind mount "/" on top of itself
|
|
|
|
|
.\" and try to specify "/" as the 'new' (again, an odd situation). So,
|
|
|
|
|
.\" the EBUSY check in the kernel does still seem necessary to prevent
|
|
|
|
|
.\" that case. Furthermore, the "or put_old" piece is probably
|
|
|
|
|
.\" redundant text (although the check is in the kernel), since,
|
|
|
|
|
.\" in another check, 'put_old' is required to be under 'new_root'.
|
|
|
|
|
.I new_root
|
|
|
|
|
or
|
|
|
|
|
.I put_old
|
|
|
|
|
is on the current root filesystem.
|
|
|
|
|
(This error covers the pathological case where
|
|
|
|
|
.I new_root
|
|
|
|
|
is
|
|
|
|
|
.IR """/""" .)
|
2004-11-03 13:51:07 +00:00
|
|
|
.TP
|
|
|
|
|
.B EINVAL
|
pivot_root.2: 'new_root' must be a mount point
It appears that 'new_root' may not have needed to be a mount
point on ancient kernels, but already in Linux 2.4.5, there
was the diff shown below. Verified also by testing.
@@ -1631,8 +1605,9 @@
* - we don't move root/cwd if they are not at the root (reason: if something
* cared enough to change them, it's probably wrong to force them elsewhere)
* - it's okay to pick a root that isn't the root of a file system, e.g.
- * /nfs/my_root where /nfs is the mount point. Better avoid creating
- * unreachable mount points this way, though.
+ * /nfs/my_root where /nfs is the mount point. It must be a mountpoint,
+ * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
+ * first.
*/
asmlinkage long sys_pivot_root(const char *new_root, const char *put_old)
@@ -1640,7 +1615,7 @@
struct dentry *root;
struct vfsmount *root_mnt;
struct vfsmount *tmp;
- struct nameidata new_nd, old_nd;
+ struct nameidata new_nd, old_nd, parent_nd, root_parent;
char *name;
int error;
@@ -1688,6 +1663,10 @@
if (new_nd.mnt == root_mnt || old_nd.mnt == root_mnt)
goto out2; /* loop */
error = -EINVAL;
+ if (root_mnt->mnt_root != root)
+ goto out2;
+ if (new_nd.mnt->mnt_root != new_nd.dentry)
+ goto out2; /* not a mountpoint */
tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */
spin_lock(&dcache_lock);
if (tmp != new_nd.mnt) {
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2019-07-26 14:54:16 +00:00
|
|
|
.I new_root
|
|
|
|
|
is not a mount point.
|
|
|
|
|
.TP
|
|
|
|
|
.B EINVAL
|
2004-11-03 13:51:07 +00:00
|
|
|
\fIput_old\fP is not underneath \fInew_root\fP.
|
|
|
|
|
.TP
|
2018-08-09 04:23:13 +00:00
|
|
|
.B EINVAL
|
2019-07-30 20:59:17 +00:00
|
|
|
The current root directory is not a mount point
|
|
|
|
|
(because of an earlier
|
|
|
|
|
.BR chroot (2)).
|
|
|
|
|
.TP
|
|
|
|
|
.B EINVAL
|
2019-07-27 17:13:29 +00:00
|
|
|
The current root is on the rootfs (initial ramfs) filesystem; see NOTES.
|
2018-08-09 04:23:13 +00:00
|
|
|
.TP
|
2019-07-26 15:10:06 +00:00
|
|
|
.B EINVAL
|
|
|
|
|
Either the mount point at
|
|
|
|
|
.IR new_root ,
|
|
|
|
|
or the parent mount of that mount point,
|
|
|
|
|
has propagation type
|
|
|
|
|
.BR MS_SHARED .
|
|
|
|
|
.TP
|
2019-07-26 21:22:59 +00:00
|
|
|
.B EINVAL
|
|
|
|
|
.I put_old
|
|
|
|
|
is a mount point and has the propagation type
|
|
|
|
|
.BR MS_SHARED .
|
|
|
|
|
.TP
|
2004-11-03 13:51:07 +00:00
|
|
|
.B ENOTDIR
|
|
|
|
|
\fInew_root\fP or \fIput_old\fP is not a directory.
|
|
|
|
|
.TP
|
|
|
|
|
.B EPERM
|
2007-12-27 16:01:37 +00:00
|
|
|
The calling process does not have the
|
2004-11-03 13:51:07 +00:00
|
|
|
.B CAP_SYS_ADMIN
|
|
|
|
|
capability.
|
2007-05-18 16:06:42 +00:00
|
|
|
.SH VERSIONS
|
|
|
|
|
.BR pivot_root ()
|
|
|
|
|
was introduced in Linux 2.3.41.
|
getent.1, intro.1, time.1, _exit.2, _syscall.2, accept.2, access.2, acct.2, adjtimex.2, alarm.2, alloc_hugepages.2, arch_prctl.2, bdflush.2, bind.2, brk.2, cacheflush.2, capget.2, chdir.2, chmod.2, chown.2, chroot.2, clock_getres.2, clock_nanosleep.2, clone.2, close.2, connect.2, create_module.2, delete_module.2, dup.2, epoll_create.2, epoll_ctl.2, epoll_wait.2, eventfd.2, execve.2, exit_group.2, faccessat.2, fchmodat.2, fchownat.2, fcntl.2, flock.2, fork.2, fstatat.2, fsync.2, futex.2, futimesat.2, get_kernel_syms.2, get_robust_list.2, get_thread_area.2, getcpu.2, getdents.2, getdomainname.2, getgid.2, getgroups.2, gethostname.2, getitimer.2, getpagesize.2, getpeername.2, getpid.2, getpriority.2, getresuid.2, getrlimit.2, getrusage.2, getsid.2, getsockname.2, getsockopt.2, gettid.2, gettimeofday.2, getuid.2, getunwind.2, getxattr.2, idle.2, init_module.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, intro.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl.2, ioctl_list.2, ioperm.2, iopl.2, ioprio_set.2, ipc.2, kcmp.2, kill.2, killpg.2, link.2, linkat.2, listen.2, listxattr.2, llseek.2, lookup_dcookie.2, lseek.2, madvise.2, migrate_pages.2, mincore.2, mkdir.2, mkdirat.2, mknod.2, mknodat.2, mlock.2, mmap.2, mmap2.2, modify_ldt.2, mount.2, move_pages.2, mprotect.2, mq_getsetattr.2, mremap.2, msgctl.2, msgget.2, msgop.2, msync.2, nanosleep.2, nfsservctl.2, nice.2, open.2, openat.2, outb.2, pause.2, pciconfig_read.2, perf_event_open.2, perfmonctl.2, personality.2, pipe.2, pivot_root.2, poll.2, posix_fadvise.2, prctl.2, pread.2, process_vm_readv.2, ptrace.2, query_module.2, quotactl.2, read.2, readahead.2, readdir.2, readlink.2, readlinkat.2, readv.2, reboot.2, recv.2, remap_file_pages.2, removexattr.2, rename.2, renameat.2, rmdir.2, rt_sigqueueinfo.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, select.2, semctl.2, semget.2, semop.2, send.2, sendfile.2, set_thread_area.2, set_tid_address.2, seteuid.2, setfsgid.2, setfsuid.2, setgid.2, setpgid.2, setresuid.2, setreuid.2, setsid.2, setuid.2, setup.2, setxattr.2, shmctl.2, shmget.2, shmop.2, shutdown.2, sigaction.2, sigaltstack.2, signal.2, signalfd.2, sigpending.2, sigprocmask.2, sigreturn.2, sigsuspend.2, sigwaitinfo.2, socket.2, socketcall.2, socketpair.2, splice.2, stat.2, statfs.2, stime.2, swapon.2, symlink.2, symlinkat.2, sync.2, sync_file_range.2, sysctl.2, sysfs.2, sysinfo.2, syslog.2, tee.2, time.2, timerfd_create.2, times.2, tkill.2, truncate.2, umask.2, umount.2, uname.2, unimplemented.2, unlink.2, unlinkat.2, uselib.2, ustat.2, utime.2, utimensat.2, vfork.2, vhangup.2, vm86.2, vmsplice.2, wait.2, wait4.2, write.2, CPU_SET.3, INFINITY.3, MB_CUR_MAX.3, MB_LEN_MAX.3, __setfpucw.3, a64l.3, abort.3, abs.3, acos.3, acosh.3, addseverity.3, adjtime.3, aio_cancel.3, aio_error.3, aio_fsync.3, aio_read.3, aio_return.3, aio_suspend.3, aio_write.3, alloca.3, argz_add.3, asin.3, asinh.3, asprintf.3, assert.3, assert_perror.3, atan.3, atan2.3, atanh.3, atexit.3, atof.3, atoi.3, backtrace.3, basename.3, bcmp.3, bcopy.3, bindresvport.3, bsd_signal.3, bsearch.3, bstring.3, btowc.3, btree.3, byteorder.3, bzero.3, cabs.3, cacos.3, cacosh.3, canonicalize_file_name.3, carg.3, casin.3, casinh.3, catan.3, catanh.3, catgets.3, catopen.3, cbrt.3, ccos.3, ccosh.3, ceil.3, cerf.3, cexp.3, cexp2.3, cfree.3, cimag.3, clearenv.3, clock.3, clock_getcpuclockid.3, clog.3, clog10.3, clog2.3, closedir.3, cmsg.3, confstr.3, conj.3, copysign.3, cos.3, cosh.3, cpow.3, cproj.3, creal.3, crypt.3, csin.3, csinh.3, csqrt.3, ctan.3, ctanh.3, ctermid.3, ctime.3, daemon.3, dbopen.3, des_crypt.3, difftime.3, dirfd.3, div.3, dl_iterate_phdr.3, dlopen.3, dprintf.3, drand48.3, drand48_r.3, dysize.3, ecvt.3, ecvt_r.3, encrypt.3, end.3, endian.3, envz_add.3, erf.3, erfc.3, err.3, errno.3, error.3, ether_aton.3, euidaccess.3, exec.3, exit.3, exp.3, exp10.3, exp2.3, expm1.3, fabs.3, fclose.3, fcloseall.3, fdim.3, fenv.3, ferror.3, fexecve.3, fflush.3, ffs.3, fgetgrent.3, fgetpwent.3, fgetwc.3, fgetws.3, finite.3, flockfile.3, floor.3, fma.3, fmax.3, fmemopen.3, fmin.3, fmod.3, fmtmsg.3, fnmatch.3, fopen.3, fpathconf.3, fpclassify.3, fpurge.3, fputwc.3, fputws.3, fread.3, frexp.3, fseek.3, fseeko.3, ftime.3, ftok.3, fts.3, ftw.3, futimes.3, fwide.3, gamma.3, gcvt.3, getaddrinfo.3, getaddrinfo_a.3, getauxval.3, getcontext.3, getcwd.3, getdate.3, getdirentries.3, getdtablesize.3, getenv.3, getfsent.3, getgrent.3, getgrent_r.3, getgrnam.3, getgrouplist.3, gethostbyname.3, gethostid.3, getipnodebyname.3, getline.3, getloadavg.3, getlogin.3, getmntent.3, getnameinfo.3, getnetent.3, getnetent_r.3, getopt.3, getpass.3, getprotoent.3, getprotoent_r.3, getpt.3, getpw.3, getpwent.3, getpwent_r.3, getpwnam.3, getrpcent.3, getrpcent_r.3, getrpcport.3, gets.3, getservent.3, getservent_r.3, getspnam.3, getttyent.3, getumask.3, getusershell.3, getutent.3, getw.3, getwchar.3, glob.3, grantpt.3, gsignal.3, hash.3, hsearch.3, hypot.3, iconv.3, iconv_close.3, iconv_open.3, ilogb.3, index.3, inet.3, inet_ntop.3, inet_pton.3, infnan.3, initgroups.3, insque.3, intro.3, isalpha.3, isatty.3, isgreater.3, iswalnum.3, iswalpha.3, iswblank.3, iswcntrl.3, iswctype.3, iswdigit.3, iswgraph.3, iswlower.3, iswprint.3, iswpunct.3, iswspace.3, iswupper.3, iswxdigit.3, j0.3, key_setsecret.3, ldexp.3, lgamma.3, lio_listio.3, localeconv.3, lockf.3, log.3, log10.3, log1p.3, log2.3, logb.3, login.3, longjmp.3, lrint.3, lround.3, lsearch.3, lseek64.3, makecontext.3, makedev.3, malloc.3, malloc_hook.3, mblen.3, mbrlen.3, mbrtowc.3, mbsinit.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, memccpy.3, memchr.3, memcmp.3, memcpy.3, memfrob.3, memmem.3, memmove.3, mempcpy.3, memset.3, mkdtemp.3, mkfifo.3, mkfifoat.3, mkstemp.3, mktemp.3, modf.3, mpool.3, mq_close.3, mq_getattr.3, mq_notify.3, mq_open.3, mq_receive.3, mq_send.3, mq_unlink.3, mtrace.3, nan.3, netlink.3, nextafter.3, nl_langinfo.3, offsetof.3, on_exit.3, opendir.3, openpty.3, perror.3, popen.3, posix_fallocate.3, posix_memalign.3, posix_openpt.3, pow.3, pow10.3, printf.3, profil.3, program_invocation_name.3, psignal.3, pthread_kill_other_threads_np.3, ptsname.3, putenv.3, putgrent.3, putpwent.3, puts.3, putwchar.3, qecvt.3, qsort.3, queue.3, raise.3, rand.3, random.3, random_r.3, rcmd.3, re_comp.3, readdir.3, realpath.3, recno.3, regex.3, remainder.3, remove.3, remquo.3, resolver.3, rewinddir.3, rexec.3, rint.3, round.3, rpc.3, rpmatch.3, rtime.3, rtnetlink.3, scalb.3, scalbln.3, scandir.3, scandirat.3, scanf.3, seekdir.3, sem_close.3, sem_destroy.3, sem_getvalue.3, sem_init.3, sem_open.3, sem_post.3, sem_unlink.3, sem_wait.3, setaliasent.3, setbuf.3, setenv.3, setjmp.3, setlocale.3, setlogmask.3, setnetgrent.3, shm_open.3, siginterrupt.3, signbit.3, significand.3, sigpause.3, sigqueue.3, sigset.3, sigsetops.3, sigvec.3, sin.3, sincos.3, sinh.3, sleep.3, sockatmark.3, sqrt.3, statvfs.3, stdarg.3, stdin.3, stdio.3, stdio_ext.3, stpcpy.3, stpncpy.3, strcasecmp.3, strcat.3, strchr.3, strcmp.3, strcoll.3, strcpy.3, strdup.3, strerror.3, strfmon.3, strfry.3, strftime.3, string.3, strlen.3, strnlen.3, strpbrk.3, strptime.3, strsep.3, strsignal.3, strspn.3, strstr.3, strtod.3, strtoimax.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, swab.3, sysconf.3, syslog.3, system.3, sysv_signal.3, tan.3, tanh.3, tcgetpgrp.3, tcgetsid.3, telldir.3, tempnam.3, termios.3, tgamma.3, timegm.3, timeradd.3, tmpfile.3, tmpnam.3, toascii.3, toupper.3, towctrans.3, towlower.3, towupper.3, trunc.3, tsearch.3, ttyname.3, ttyslot.3, tzset.3, ualarm.3, ulimit.3, ungetwc.3, unlocked_stdio.3, unlockpt.3, updwtmp.3, usleep.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscasecmp.3, wcscat.3, wcschr.3, wcscmp.3, wcscpy.3, wcscspn.3, wcsdup.3, wcslen.3, wcsncasecmp.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcspbrk.3, wcsrchr.3, wcsrtombs.3, wcsspn.3, wcsstr.3, wcstoimax.3, wcstok.3, wcstombs.3, wcswidth.3, wctob.3, wctomb.3, wctrans.3, wctype.3, wcwidth.3, wmemchr.3, wmemcmp.3, wmemcpy.3, wmemmove.3, wmemset.3, wordexp.3, wprintf.3, xcrypt.3, xdr.3, y0.3, cciss.4, console.4, console_codes.4, console_ioctl.4, dsp56k.4, fd.4, full.4, hd.4, hpsa.4, initrd.4, intro.4, lp.4, mem.4, mouse.4, null.4, pts.4, ram.4, random.4, rtc.4, sk98lin.4, st.4, tty.4, ttyS.4, tty_ioctl.4, vcs.4, wavelan.4, acct.5, charmap.5, dir_colors.5, filesystems.5, ftpusers.5, group.5, host.conf.5, hosts.5, hosts.equiv.5, intro.5, issue.5, locale.5, motd.5, networks.5, nologin.5, nscd.conf.5, passwd.5, proc.5, protocols.5, resolv.conf.5, rpc.5, securetty.5, services.5, shells.5, termcap.5, ttytype.5, utmp.5, armscii-8.7, arp.7, ascii.7, bootparam.7, capabilities.7, charsets.7, complex.7, cp1251.7, credentials.7, ddp.7, environ.7, epoll.7, fifo.7, futex.7, glob.7, hier.7, icmp.7, inotify.7, intro.7, ip.7, ipv6.7, iso_8859-1.7, iso_8859-10.7, iso_8859-11.7, iso_8859-13.7, iso_8859-14.7, iso_8859-15.7, iso_8859-16.7, iso_8859-2.7, iso_8859-3.7, iso_8859-4.7, iso_8859-5.7, iso_8859-6.7, iso_8859-7.7, iso_8859-8.7, iso_8859-9.7, koi8-r.7, koi8-u.7, locale.7, mailaddr.7, man.7, mq_overview.7, netdevice.7, netlink.7, numa.7, packet.7, path_resolution.7, pipe.7, posixoptions.7, pthreads.7, pty.7, raw.7, regex.7, rtld-audit.7, rtnetlink.7, sem_overview.7, shm_overview.7, sigevent.7, signal.7, socket.7, standards.7, suffixes.7, svipc.7, tcp.7, termio.7, time.7, udp.7, udplite.7, unicode.7, unix.7, uri.7, utf-8.7, x25.7, nscd.8, sync.8, tzselect.8, zdump.8, zic.8: Global fix: remove unneeded double quotes in .SH headings
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-02-24 18:01:36 +00:00
|
|
|
.SH CONFORMING TO
|
2007-05-18 16:06:42 +00:00
|
|
|
.BR pivot_root ()
|
2007-12-25 21:28:09 +00:00
|
|
|
is Linux-specific and hence is not portable.
|
2007-06-14 06:31:39 +00:00
|
|
|
.SH NOTES
|
|
|
|
|
Glibc does not provide a wrapper for this system call; call it using
|
|
|
|
|
.BR syscall (2).
|
2018-09-30 15:24:23 +00:00
|
|
|
.PP
|
2019-07-30 12:18:41 +00:00
|
|
|
A command-line interface for this system call is provided by
|
|
|
|
|
.BR pivot_root (8).
|
|
|
|
|
.PP
|
2019-07-27 17:07:39 +00:00
|
|
|
.BR pivot_root ()
|
|
|
|
|
allows the caller to switch to a new root filesystem while at the same time
|
|
|
|
|
placing the old root mount at a location under
|
|
|
|
|
.I new_root
|
|
|
|
|
from where it can subsequently be unmounted.
|
|
|
|
|
(The fact that it moves all processes that have a root directory
|
|
|
|
|
or current working directory on the old root filesystem to the
|
|
|
|
|
new root filesystem frees the old root filesystem of users,
|
|
|
|
|
allowing it to be unmounted more easily.)
|
2019-09-10 08:33:24 +00:00
|
|
|
.PP
|
2019-07-27 17:07:39 +00:00
|
|
|
A typical use of
|
|
|
|
|
.BR pivot_root ()
|
|
|
|
|
is during system startup, when the
|
|
|
|
|
system mounts a temporary root filesystem (e.g., an \fBinitrd\fP), then
|
|
|
|
|
mounts the real root filesystem, and eventually turns the latter into
|
|
|
|
|
the current root of all relevant processes or threads.
|
|
|
|
|
A modern use is to set up a root filesystem during
|
|
|
|
|
the creation of a container.
|
|
|
|
|
.PP
|
2019-07-30 11:47:12 +00:00
|
|
|
The fact that
|
|
|
|
|
.BR pivot_root ()
|
|
|
|
|
modifies process root and current working directories in the
|
|
|
|
|
manner noted in DESCRIPTION
|
|
|
|
|
is necessary in order to prevent kernel threads from keeping the old
|
|
|
|
|
root directory busy with their root and current working directory,
|
|
|
|
|
even if they never access
|
|
|
|
|
the filesystem in any way.
|
|
|
|
|
.PP
|
2019-07-31 21:51:39 +00:00
|
|
|
.I new_root
|
|
|
|
|
and
|
|
|
|
|
.I put_old
|
|
|
|
|
may be the same directory.
|
|
|
|
|
In particular, the following sequence allows a pivot-root operation
|
|
|
|
|
without needing to create and remove a temporary directory:
|
|
|
|
|
.PP
|
|
|
|
|
.in +4n
|
|
|
|
|
.EX
|
|
|
|
|
chdir(new_root);
|
|
|
|
|
pivot_root(".", ".");
|
|
|
|
|
umount2(".", MNT_DETACH);
|
|
|
|
|
.EE
|
|
|
|
|
.in
|
|
|
|
|
.PP
|
|
|
|
|
This sequence succeeds because the
|
|
|
|
|
.BR pivot_root ()
|
|
|
|
|
call stacks the old root mount point
|
|
|
|
|
on top of the new root mount point at
|
|
|
|
|
.IR / .
|
|
|
|
|
At that point, the calling process's root directory and current
|
|
|
|
|
working directory refer to the new root mount point
|
|
|
|
|
.RI ( new_root ).
|
|
|
|
|
During the subsequent
|
|
|
|
|
.BR umount ()
|
|
|
|
|
call, resolution of
|
|
|
|
|
.IR """."""
|
|
|
|
|
starts with
|
|
|
|
|
.I new_root
|
|
|
|
|
and then moves up the list of mounts stacked at
|
|
|
|
|
.IR / ,
|
2019-10-08 18:57:55 +00:00
|
|
|
with the result that old root mount point is unmounted.
|
2019-07-31 21:51:39 +00:00
|
|
|
.PP
|
2018-09-30 15:24:23 +00:00
|
|
|
The rootfs (initial ramfs) cannot be
|
|
|
|
|
.BR pivot_root ()ed.
|
2018-11-09 07:54:20 +00:00
|
|
|
The recommended method of changing the root filesystem in this case is
|
|
|
|
|
to delete everything in rootfs, overmount rootfs with the new root, attach
|
2018-09-30 15:24:23 +00:00
|
|
|
.IR stdin / stdout / stderr
|
|
|
|
|
to the new
|
|
|
|
|
.IR /dev/console ,
|
2018-11-09 07:54:20 +00:00
|
|
|
and exec the new
|
|
|
|
|
.BR init (1).
|
|
|
|
|
Helper programs for this process exist; see
|
2018-09-30 15:24:23 +00:00
|
|
|
.BR switch_root (8).
|
2019-07-28 07:11:29 +00:00
|
|
|
.SH EXAMPLE
|
|
|
|
|
.PP
|
|
|
|
|
The program below demonstrates the use of
|
|
|
|
|
.BR pivot_root ()
|
|
|
|
|
inside a mount namespace that is created using
|
|
|
|
|
.BR clone (2).
|
|
|
|
|
After pivoting to the root directory named in the program's
|
|
|
|
|
first command-line argument, the child created by
|
|
|
|
|
.BR clone (2)
|
|
|
|
|
then executes the program named in the remaining command-line arguments.
|
|
|
|
|
.PP
|
|
|
|
|
We demonstrate the program by creating a directory that will serve as
|
|
|
|
|
the new root filesystem and placing a copy of the (statically linked)
|
|
|
|
|
.BR busybox (1)
|
|
|
|
|
executable in that directory.
|
|
|
|
|
.PP
|
|
|
|
|
.in +4n
|
|
|
|
|
.EX
|
|
|
|
|
$ \fBmkdir /tmp/rootfs\fP
|
|
|
|
|
$ \fBls \-id /tmp/rootfs\fP # Show inode number of new root directory
|
|
|
|
|
319459 /tmp/rootfs
|
|
|
|
|
$ \fBcp $(which busybox) /tmp/rootfs\fP
|
|
|
|
|
$ \fBPS1='bbsh$ ' sudo ./pivot_root_demo /tmp/rootfs /busybox sh\fP
|
|
|
|
|
bbsh$ \fBPATH=/\fP
|
|
|
|
|
bbsh$ \fBbusybox ln busybox ln\fP
|
|
|
|
|
bbsh$ \fBln busybox echo\fP
|
|
|
|
|
bbsh$ \fBln busybox ls\fP
|
|
|
|
|
bbsh$ \fBls\fP
|
|
|
|
|
busybox echo ln ls
|
|
|
|
|
bbsh$ \fBls \-id /\fP # Compare with inode number above
|
|
|
|
|
319459 /
|
|
|
|
|
bbsh$ \fBecho \(aqhello world\(aq\fP
|
|
|
|
|
hello world
|
|
|
|
|
.EE
|
|
|
|
|
.in
|
|
|
|
|
.SS Program source
|
|
|
|
|
\&
|
|
|
|
|
.PP
|
|
|
|
|
.EX
|
|
|
|
|
/* pivot_root_demo.c */
|
|
|
|
|
|
|
|
|
|
#define _GNU_SOURCE
|
|
|
|
|
#include <sched.h>
|
|
|
|
|
#include <stdio.h>
|
|
|
|
|
#include <stdlib.h>
|
|
|
|
|
#include <unistd.h>
|
|
|
|
|
#include <sys/wait.h>
|
|
|
|
|
#include <sys/syscall.h>
|
|
|
|
|
#include <sys/mount.h>
|
|
|
|
|
#include <sys/stat.h>
|
|
|
|
|
#include <limits.h>
|
|
|
|
|
|
|
|
|
|
#define errExit(msg) do { perror(msg); exit(EXIT_FAILURE); \e
|
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
|
|
static int
|
|
|
|
|
pivot_root(const char *new_root, const char *put_old)
|
|
|
|
|
{
|
|
|
|
|
return syscall(SYS_pivot_root, new_root, put_old);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define STACK_SIZE (1024 * 1024)
|
|
|
|
|
|
|
|
|
|
static int /* Startup function for cloned child */
|
|
|
|
|
child(void *arg)
|
|
|
|
|
{
|
|
|
|
|
char **args = arg;
|
|
|
|
|
char *new_root = args[0];
|
|
|
|
|
const char *put_old = "/oldrootfs";
|
|
|
|
|
char path[PATH_MAX];
|
|
|
|
|
|
|
|
|
|
/* Ensure that \(aqnew_root\(aq and its parent mount don\(aqt have
|
|
|
|
|
shared propagation (which would cause pivot_root() to
|
|
|
|
|
return an error), and prevent propagation of mount
|
|
|
|
|
events to the initial mount namespace */
|
|
|
|
|
|
|
|
|
|
if (mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, NULL) == 1)
|
|
|
|
|
errExit("mount\-MS_PRIVATE");
|
|
|
|
|
|
|
|
|
|
/* Ensure that \(aqnew_root\(aq is a mount point */
|
|
|
|
|
|
|
|
|
|
if (mount(new_root, new_root, NULL, MS_BIND, NULL) == \-1)
|
|
|
|
|
errExit("mount\-MS_BIND");
|
|
|
|
|
|
|
|
|
|
/* Create directory to which old root will be pivoted */
|
|
|
|
|
|
|
|
|
|
snprintf(path, sizeof(path), "%s/%s", new_root, put_old);
|
|
|
|
|
if (mkdir(path, 0777) == \-1)
|
|
|
|
|
errExit("mkdir");
|
|
|
|
|
|
|
|
|
|
/* And pivot the root filesystem */
|
|
|
|
|
|
|
|
|
|
if (pivot_root(new_root, path) == \-1)
|
|
|
|
|
errExit("pivot_root");
|
|
|
|
|
|
2019-09-25 15:58:46 +00:00
|
|
|
/* Switch the current working directory to "/" */
|
2019-07-28 07:11:29 +00:00
|
|
|
|
|
|
|
|
if (chdir("/") == \-1)
|
|
|
|
|
errExit("chdir");
|
|
|
|
|
|
|
|
|
|
/* Unmount old root and remove mount point */
|
|
|
|
|
|
|
|
|
|
if (umount2(put_old, MNT_DETACH) == \-1)
|
|
|
|
|
perror("umount2");
|
|
|
|
|
if (rmdir(put_old) == \-1)
|
|
|
|
|
perror("rmdir");
|
|
|
|
|
|
|
|
|
|
/* Execute the command specified in argv[1]... */
|
|
|
|
|
|
|
|
|
|
execv(args[1], &args[1]);
|
|
|
|
|
errExit("execv");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
int
|
|
|
|
|
main(int argc, char *argv[])
|
|
|
|
|
{
|
|
|
|
|
/* Create a child process in a new mount namespace */
|
|
|
|
|
|
|
|
|
|
char *stack = malloc(STACK_SIZE);
|
|
|
|
|
if (stack == NULL)
|
|
|
|
|
errExit("malloc");
|
|
|
|
|
|
|
|
|
|
if (clone(child, stack + STACK_SIZE,
|
|
|
|
|
CLONE_NEWNS | SIGCHLD, &argv[1]) == \-1)
|
|
|
|
|
errExit("clone");
|
|
|
|
|
|
|
|
|
|
/* Parent falls through to here; wait for child */
|
|
|
|
|
|
|
|
|
|
if (wait(NULL) == \-1)
|
|
|
|
|
errExit("wait");
|
|
|
|
|
|
|
|
|
|
exit(EXIT_SUCCESS);
|
|
|
|
|
}
|
|
|
|
|
.EE
|
getent.1, intro.1, time.1, _exit.2, _syscall.2, accept.2, access.2, acct.2, adjtimex.2, alarm.2, alloc_hugepages.2, arch_prctl.2, bdflush.2, bind.2, brk.2, cacheflush.2, capget.2, chdir.2, chmod.2, chown.2, chroot.2, clock_getres.2, clock_nanosleep.2, clone.2, close.2, connect.2, create_module.2, delete_module.2, dup.2, epoll_create.2, epoll_ctl.2, epoll_wait.2, eventfd.2, execve.2, exit_group.2, faccessat.2, fchmodat.2, fchownat.2, fcntl.2, flock.2, fork.2, fstatat.2, fsync.2, futex.2, futimesat.2, get_kernel_syms.2, get_robust_list.2, get_thread_area.2, getcpu.2, getdents.2, getdomainname.2, getgid.2, getgroups.2, gethostname.2, getitimer.2, getpagesize.2, getpeername.2, getpid.2, getpriority.2, getresuid.2, getrlimit.2, getrusage.2, getsid.2, getsockname.2, getsockopt.2, gettid.2, gettimeofday.2, getuid.2, getunwind.2, getxattr.2, idle.2, init_module.2, inotify_add_watch.2, inotify_init.2, inotify_rm_watch.2, intro.2, io_cancel.2, io_destroy.2, io_getevents.2, io_setup.2, io_submit.2, ioctl.2, ioctl_list.2, ioperm.2, iopl.2, ioprio_set.2, ipc.2, kcmp.2, kill.2, killpg.2, link.2, linkat.2, listen.2, listxattr.2, llseek.2, lookup_dcookie.2, lseek.2, madvise.2, migrate_pages.2, mincore.2, mkdir.2, mkdirat.2, mknod.2, mknodat.2, mlock.2, mmap.2, mmap2.2, modify_ldt.2, mount.2, move_pages.2, mprotect.2, mq_getsetattr.2, mremap.2, msgctl.2, msgget.2, msgop.2, msync.2, nanosleep.2, nfsservctl.2, nice.2, open.2, openat.2, outb.2, pause.2, pciconfig_read.2, perf_event_open.2, perfmonctl.2, personality.2, pipe.2, pivot_root.2, poll.2, posix_fadvise.2, prctl.2, pread.2, process_vm_readv.2, ptrace.2, query_module.2, quotactl.2, read.2, readahead.2, readdir.2, readlink.2, readlinkat.2, readv.2, reboot.2, recv.2, remap_file_pages.2, removexattr.2, rename.2, renameat.2, rmdir.2, rt_sigqueueinfo.2, sched_get_priority_max.2, sched_rr_get_interval.2, sched_setaffinity.2, sched_setparam.2, sched_setscheduler.2, sched_yield.2, select.2, semctl.2, semget.2, semop.2, send.2, sendfile.2, set_thread_area.2, set_tid_address.2, seteuid.2, setfsgid.2, setfsuid.2, setgid.2, setpgid.2, setresuid.2, setreuid.2, setsid.2, setuid.2, setup.2, setxattr.2, shmctl.2, shmget.2, shmop.2, shutdown.2, sigaction.2, sigaltstack.2, signal.2, signalfd.2, sigpending.2, sigprocmask.2, sigreturn.2, sigsuspend.2, sigwaitinfo.2, socket.2, socketcall.2, socketpair.2, splice.2, stat.2, statfs.2, stime.2, swapon.2, symlink.2, symlinkat.2, sync.2, sync_file_range.2, sysctl.2, sysfs.2, sysinfo.2, syslog.2, tee.2, time.2, timerfd_create.2, times.2, tkill.2, truncate.2, umask.2, umount.2, uname.2, unimplemented.2, unlink.2, unlinkat.2, uselib.2, ustat.2, utime.2, utimensat.2, vfork.2, vhangup.2, vm86.2, vmsplice.2, wait.2, wait4.2, write.2, CPU_SET.3, INFINITY.3, MB_CUR_MAX.3, MB_LEN_MAX.3, __setfpucw.3, a64l.3, abort.3, abs.3, acos.3, acosh.3, addseverity.3, adjtime.3, aio_cancel.3, aio_error.3, aio_fsync.3, aio_read.3, aio_return.3, aio_suspend.3, aio_write.3, alloca.3, argz_add.3, asin.3, asinh.3, asprintf.3, assert.3, assert_perror.3, atan.3, atan2.3, atanh.3, atexit.3, atof.3, atoi.3, backtrace.3, basename.3, bcmp.3, bcopy.3, bindresvport.3, bsd_signal.3, bsearch.3, bstring.3, btowc.3, btree.3, byteorder.3, bzero.3, cabs.3, cacos.3, cacosh.3, canonicalize_file_name.3, carg.3, casin.3, casinh.3, catan.3, catanh.3, catgets.3, catopen.3, cbrt.3, ccos.3, ccosh.3, ceil.3, cerf.3, cexp.3, cexp2.3, cfree.3, cimag.3, clearenv.3, clock.3, clock_getcpuclockid.3, clog.3, clog10.3, clog2.3, closedir.3, cmsg.3, confstr.3, conj.3, copysign.3, cos.3, cosh.3, cpow.3, cproj.3, creal.3, crypt.3, csin.3, csinh.3, csqrt.3, ctan.3, ctanh.3, ctermid.3, ctime.3, daemon.3, dbopen.3, des_crypt.3, difftime.3, dirfd.3, div.3, dl_iterate_phdr.3, dlopen.3, dprintf.3, drand48.3, drand48_r.3, dysize.3, ecvt.3, ecvt_r.3, encrypt.3, end.3, endian.3, envz_add.3, erf.3, erfc.3, err.3, errno.3, error.3, ether_aton.3, euidaccess.3, exec.3, exit.3, exp.3, exp10.3, exp2.3, expm1.3, fabs.3, fclose.3, fcloseall.3, fdim.3, fenv.3, ferror.3, fexecve.3, fflush.3, ffs.3, fgetgrent.3, fgetpwent.3, fgetwc.3, fgetws.3, finite.3, flockfile.3, floor.3, fma.3, fmax.3, fmemopen.3, fmin.3, fmod.3, fmtmsg.3, fnmatch.3, fopen.3, fpathconf.3, fpclassify.3, fpurge.3, fputwc.3, fputws.3, fread.3, frexp.3, fseek.3, fseeko.3, ftime.3, ftok.3, fts.3, ftw.3, futimes.3, fwide.3, gamma.3, gcvt.3, getaddrinfo.3, getaddrinfo_a.3, getauxval.3, getcontext.3, getcwd.3, getdate.3, getdirentries.3, getdtablesize.3, getenv.3, getfsent.3, getgrent.3, getgrent_r.3, getgrnam.3, getgrouplist.3, gethostbyname.3, gethostid.3, getipnodebyname.3, getline.3, getloadavg.3, getlogin.3, getmntent.3, getnameinfo.3, getnetent.3, getnetent_r.3, getopt.3, getpass.3, getprotoent.3, getprotoent_r.3, getpt.3, getpw.3, getpwent.3, getpwent_r.3, getpwnam.3, getrpcent.3, getrpcent_r.3, getrpcport.3, gets.3, getservent.3, getservent_r.3, getspnam.3, getttyent.3, getumask.3, getusershell.3, getutent.3, getw.3, getwchar.3, glob.3, grantpt.3, gsignal.3, hash.3, hsearch.3, hypot.3, iconv.3, iconv_close.3, iconv_open.3, ilogb.3, index.3, inet.3, inet_ntop.3, inet_pton.3, infnan.3, initgroups.3, insque.3, intro.3, isalpha.3, isatty.3, isgreater.3, iswalnum.3, iswalpha.3, iswblank.3, iswcntrl.3, iswctype.3, iswdigit.3, iswgraph.3, iswlower.3, iswprint.3, iswpunct.3, iswspace.3, iswupper.3, iswxdigit.3, j0.3, key_setsecret.3, ldexp.3, lgamma.3, lio_listio.3, localeconv.3, lockf.3, log.3, log10.3, log1p.3, log2.3, logb.3, login.3, longjmp.3, lrint.3, lround.3, lsearch.3, lseek64.3, makecontext.3, makedev.3, malloc.3, malloc_hook.3, mblen.3, mbrlen.3, mbrtowc.3, mbsinit.3, mbsnrtowcs.3, mbsrtowcs.3, mbstowcs.3, mbtowc.3, memccpy.3, memchr.3, memcmp.3, memcpy.3, memfrob.3, memmem.3, memmove.3, mempcpy.3, memset.3, mkdtemp.3, mkfifo.3, mkfifoat.3, mkstemp.3, mktemp.3, modf.3, mpool.3, mq_close.3, mq_getattr.3, mq_notify.3, mq_open.3, mq_receive.3, mq_send.3, mq_unlink.3, mtrace.3, nan.3, netlink.3, nextafter.3, nl_langinfo.3, offsetof.3, on_exit.3, opendir.3, openpty.3, perror.3, popen.3, posix_fallocate.3, posix_memalign.3, posix_openpt.3, pow.3, pow10.3, printf.3, profil.3, program_invocation_name.3, psignal.3, pthread_kill_other_threads_np.3, ptsname.3, putenv.3, putgrent.3, putpwent.3, puts.3, putwchar.3, qecvt.3, qsort.3, queue.3, raise.3, rand.3, random.3, random_r.3, rcmd.3, re_comp.3, readdir.3, realpath.3, recno.3, regex.3, remainder.3, remove.3, remquo.3, resolver.3, rewinddir.3, rexec.3, rint.3, round.3, rpc.3, rpmatch.3, rtime.3, rtnetlink.3, scalb.3, scalbln.3, scandir.3, scandirat.3, scanf.3, seekdir.3, sem_close.3, sem_destroy.3, sem_getvalue.3, sem_init.3, sem_open.3, sem_post.3, sem_unlink.3, sem_wait.3, setaliasent.3, setbuf.3, setenv.3, setjmp.3, setlocale.3, setlogmask.3, setnetgrent.3, shm_open.3, siginterrupt.3, signbit.3, significand.3, sigpause.3, sigqueue.3, sigset.3, sigsetops.3, sigvec.3, sin.3, sincos.3, sinh.3, sleep.3, sockatmark.3, sqrt.3, statvfs.3, stdarg.3, stdin.3, stdio.3, stdio_ext.3, stpcpy.3, stpncpy.3, strcasecmp.3, strcat.3, strchr.3, strcmp.3, strcoll.3, strcpy.3, strdup.3, strerror.3, strfmon.3, strfry.3, strftime.3, string.3, strlen.3, strnlen.3, strpbrk.3, strptime.3, strsep.3, strsignal.3, strspn.3, strstr.3, strtod.3, strtoimax.3, strtok.3, strtol.3, strtoul.3, strverscmp.3, strxfrm.3, swab.3, sysconf.3, syslog.3, system.3, sysv_signal.3, tan.3, tanh.3, tcgetpgrp.3, tcgetsid.3, telldir.3, tempnam.3, termios.3, tgamma.3, timegm.3, timeradd.3, tmpfile.3, tmpnam.3, toascii.3, toupper.3, towctrans.3, towlower.3, towupper.3, trunc.3, tsearch.3, ttyname.3, ttyslot.3, tzset.3, ualarm.3, ulimit.3, ungetwc.3, unlocked_stdio.3, unlockpt.3, updwtmp.3, usleep.3, wcpcpy.3, wcpncpy.3, wcrtomb.3, wcscasecmp.3, wcscat.3, wcschr.3, wcscmp.3, wcscpy.3, wcscspn.3, wcsdup.3, wcslen.3, wcsncasecmp.3, wcsncat.3, wcsncmp.3, wcsncpy.3, wcsnlen.3, wcsnrtombs.3, wcspbrk.3, wcsrchr.3, wcsrtombs.3, wcsspn.3, wcsstr.3, wcstoimax.3, wcstok.3, wcstombs.3, wcswidth.3, wctob.3, wctomb.3, wctrans.3, wctype.3, wcwidth.3, wmemchr.3, wmemcmp.3, wmemcpy.3, wmemmove.3, wmemset.3, wordexp.3, wprintf.3, xcrypt.3, xdr.3, y0.3, cciss.4, console.4, console_codes.4, console_ioctl.4, dsp56k.4, fd.4, full.4, hd.4, hpsa.4, initrd.4, intro.4, lp.4, mem.4, mouse.4, null.4, pts.4, ram.4, random.4, rtc.4, sk98lin.4, st.4, tty.4, ttyS.4, tty_ioctl.4, vcs.4, wavelan.4, acct.5, charmap.5, dir_colors.5, filesystems.5, ftpusers.5, group.5, host.conf.5, hosts.5, hosts.equiv.5, intro.5, issue.5, locale.5, motd.5, networks.5, nologin.5, nscd.conf.5, passwd.5, proc.5, protocols.5, resolv.conf.5, rpc.5, securetty.5, services.5, shells.5, termcap.5, ttytype.5, utmp.5, armscii-8.7, arp.7, ascii.7, bootparam.7, capabilities.7, charsets.7, complex.7, cp1251.7, credentials.7, ddp.7, environ.7, epoll.7, fifo.7, futex.7, glob.7, hier.7, icmp.7, inotify.7, intro.7, ip.7, ipv6.7, iso_8859-1.7, iso_8859-10.7, iso_8859-11.7, iso_8859-13.7, iso_8859-14.7, iso_8859-15.7, iso_8859-16.7, iso_8859-2.7, iso_8859-3.7, iso_8859-4.7, iso_8859-5.7, iso_8859-6.7, iso_8859-7.7, iso_8859-8.7, iso_8859-9.7, koi8-r.7, koi8-u.7, locale.7, mailaddr.7, man.7, mq_overview.7, netdevice.7, netlink.7, numa.7, packet.7, path_resolution.7, pipe.7, posixoptions.7, pthreads.7, pty.7, raw.7, regex.7, rtld-audit.7, rtnetlink.7, sem_overview.7, shm_overview.7, sigevent.7, signal.7, socket.7, standards.7, suffixes.7, svipc.7, tcp.7, termio.7, time.7, udp.7, udplite.7, unicode.7, unix.7, uri.7, utf-8.7, x25.7, nscd.8, sync.8, tzselect.8, zdump.8, zic.8: Global fix: remove unneeded double quotes in .SH headings
Signed-off-by: Michael Kerrisk <mtk.manpages@gmail.com>
2013-02-24 18:01:36 +00:00
|
|
|
.SH SEE ALSO
|
2004-11-03 13:51:07 +00:00
|
|
|
.BR chdir (2),
|
|
|
|
|
.BR chroot (2),
|
2019-07-26 15:10:58 +00:00
|
|
|
.BR mount (2),
|
2004-11-03 13:51:07 +00:00
|
|
|
.BR stat (2),
|
|
|
|
|
.BR initrd (4),
|
2019-07-27 05:40:16 +00:00
|
|
|
.BR mount_namespaces (7),
|
2017-09-25 08:46:39 +00:00
|
|
|
.BR pivot_root (8),
|
|
|
|
|
.BR switch_root (8)
|