mirror of
https://github.com/opencontainers/runc.git
synced 2026-07-11 06:03:57 +08:00
fdb100d247
We need to make sure the container is destroyed before closing the stdio for the container. This becomes a big issues when running in the host's pid namespace because the other processes could have inherited the stdio of the initial process. The call to close will just block as they still have the io open. Calling destroy before closing io, especially in the host pid namespace will cause all additional processes to be killed in the container's cgroup. This will allow the io to be closed successfuly. This change makes sure the order for destroy and close is correct as well as ensuring that if any errors encoutered during start or exec will be handled by terminating the process and destroying the container. We cannot use defers here because we need to enforce the correct ordering on destroy. This also sets the subreaper setting for runc so that when running in pid host, runc can wait on the addiontal processes launched by the container, useful on destroy, but also good for reaping the additional processes that were launched. Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
141 lines
3.2 KiB
Go
141 lines
3.2 KiB
Go
// +build linux
|
|
|
|
package system
|
|
|
|
import (
|
|
"bufio"
|
|
"fmt"
|
|
"os"
|
|
"os/exec"
|
|
"syscall"
|
|
"unsafe"
|
|
)
|
|
|
|
// If arg2 is nonzero, set the "child subreaper" attribute of the
|
|
// calling process; if arg2 is zero, unset the attribute. When a
|
|
// process is marked as a child subreaper, all of the children
|
|
// that it creates, and their descendants, will be marked as
|
|
// having a subreaper. In effect, a subreaper fulfills the role
|
|
// of init(1) for its descendant processes. Upon termination of
|
|
// a process that is orphaned (i.e., its immediate parent has
|
|
// already terminated) and marked as having a subreaper, the
|
|
// nearest still living ancestor subreaper will receive a SIGCHLD
|
|
// signal and be able to wait(2) on the process to discover its
|
|
// termination status.
|
|
const PR_SET_CHILD_SUBREAPER = 36
|
|
|
|
type ParentDeathSignal int
|
|
|
|
func (p ParentDeathSignal) Restore() error {
|
|
if p == 0 {
|
|
return nil
|
|
}
|
|
current, err := GetParentDeathSignal()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if p == current {
|
|
return nil
|
|
}
|
|
return p.Set()
|
|
}
|
|
|
|
func (p ParentDeathSignal) Set() error {
|
|
return SetParentDeathSignal(uintptr(p))
|
|
}
|
|
|
|
func Execv(cmd string, args []string, env []string) error {
|
|
name, err := exec.LookPath(cmd)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
return syscall.Exec(name, args, env)
|
|
}
|
|
|
|
func SetParentDeathSignal(sig uintptr) error {
|
|
if _, _, err := syscall.RawSyscall(syscall.SYS_PRCTL, syscall.PR_SET_PDEATHSIG, sig, 0); err != 0 {
|
|
return err
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func GetParentDeathSignal() (ParentDeathSignal, error) {
|
|
var sig int
|
|
_, _, err := syscall.RawSyscall(syscall.SYS_PRCTL, syscall.PR_GET_PDEATHSIG, uintptr(unsafe.Pointer(&sig)), 0)
|
|
if err != 0 {
|
|
return -1, err
|
|
}
|
|
return ParentDeathSignal(sig), nil
|
|
}
|
|
|
|
func SetKeepCaps() error {
|
|
if _, _, err := syscall.RawSyscall(syscall.SYS_PRCTL, syscall.PR_SET_KEEPCAPS, 1, 0); err != 0 {
|
|
return err
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func ClearKeepCaps() error {
|
|
if _, _, err := syscall.RawSyscall(syscall.SYS_PRCTL, syscall.PR_SET_KEEPCAPS, 0, 0); err != 0 {
|
|
return err
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func Setctty() error {
|
|
if _, _, err := syscall.RawSyscall(syscall.SYS_IOCTL, 0, uintptr(syscall.TIOCSCTTY), 0); err != 0 {
|
|
return err
|
|
}
|
|
return nil
|
|
}
|
|
|
|
/*
|
|
* Detect whether we are currently running in a user namespace.
|
|
* Copied from github.com/lxc/lxd/shared/util.go
|
|
*/
|
|
func RunningInUserNS() bool {
|
|
file, err := os.Open("/proc/self/uid_map")
|
|
if err != nil {
|
|
/*
|
|
* This kernel-provided file only exists if user namespaces are
|
|
* supported
|
|
*/
|
|
return false
|
|
}
|
|
defer file.Close()
|
|
|
|
buf := bufio.NewReader(file)
|
|
l, _, err := buf.ReadLine()
|
|
if err != nil {
|
|
return false
|
|
}
|
|
|
|
line := string(l)
|
|
var a, b, c int64
|
|
fmt.Sscanf(line, "%d %d %d", &a, &b, &c)
|
|
/*
|
|
* We assume we are in the initial user namespace if we have a full
|
|
* range - 4294967295 uids starting at uid 0.
|
|
*/
|
|
if a == 0 && b == 0 && c == 4294967295 {
|
|
return false
|
|
}
|
|
return true
|
|
}
|
|
|
|
// SetSubreaper sets the value i as the subreaper setting for the calling process
|
|
func SetSubreaper(i int) error {
|
|
return Prctl(PR_SET_CHILD_SUBREAPER, uintptr(i), 0, 0, 0)
|
|
}
|
|
|
|
func Prctl(option int, arg2, arg3, arg4, arg5 uintptr) (err error) {
|
|
_, _, e1 := syscall.Syscall6(syscall.SYS_PRCTL, uintptr(option), arg2, arg3, arg4, arg5, 0)
|
|
if e1 != 0 {
|
|
err = e1
|
|
}
|
|
return
|
|
}
|