History

pidns: add reboot_pid_ns() to handle the reboot syscall

In the case of a child pid namespace, rebooting the system does not really makes sense. When the pid namespace is used in conjunction with the other namespaces in order to create a linux container, the reboot syscall leads to some problems. A container can reboot the host. That can be fixed by dropping the sys_reboot capability but we are unable to correctly to poweroff/ halt/reboot a container and the container stays stuck at the shutdown time with the container's init process waiting indefinitively. After several attempts, no solution from userspace was found to reliabily handle the shutdown from a container. This patch propose to make the init process of the child pid namespace to exit with a signal status set to : SIGINT if the child pid namespace called "halt/poweroff" and SIGHUP if the child pid namespace called "reboot". When the reboot syscall is called and we are not in the initial pid namespace, we kill the pid namespace for "HALT", "POWEROFF", "RESTART", and "RESTART2". Otherwise we return EINVAL. Returning EINVAL is also an easy way to check if this feature is supported by the kernel when invoking another 'reboot' option like CAD. By this way the parent process of the child pid namespace knows if it rebooted or not and can take the right decision. Test case: ========== #include <alloca.h> #include <stdio.h> #include <sched.h> #include <unistd.h> #include <signal.h> #include <sys/reboot.h> #include <sys/types.h> #include <sys/wait.h> #include <linux/reboot.h> static int do_reboot(void *arg) { int *cmd = arg; if (reboot(*cmd)) printf("failed to reboot(%d): %m\n", *cmd); } int test_reboot(int cmd, int sig) { long stack_size = 4096; void *stack = alloca(stack_size) + stack_size; int status; pid_t ret; ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd); if (ret < 0) { printf("failed to clone: %m\n"); return -1; } if (wait(&status) < 0) { printf("unexpected wait error: %m\n"); return -1; } if (!WIFSIGNALED(status)) { printf("child process exited but was not signaled\n"); return -1; } if (WTERMSIG(status) != sig) { printf("signal termination is not the one expected\n"); return -1; } return 0; } int main(int argc, char *argv[]) { int status; status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1); if (status >= 0) { printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n"); return 1; } printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n"); return 0; } [akpm@linux-foundation.org: tweak and add comments] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Tested-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Daniel Lezcano committed 14 years ago

Commit cf3f8921 parent 5a04cca3 files · +49 −1Browse files

Unified · Split

3 files
  1. include/linux/pid_namespace.h +7 −1
  2. kernel/pid_namespace.c +33 −0
  3. kernel/sys.c +9 −0
include/linux/pid_namespace.h+7−1
@@ -33,6 +33,7 @@ struct pid_namespace { · 32 unmodified lines
3333 #endif
3434 gid_t pid_gid;
3535 int hide_pid;
36+ int reboot; /* group exit code if this pidns was rebooted */
3637 };
3738
3839 extern struct pid_namespace init_pid_ns;
@@ -48,6 +49,7 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) · 9 unmodified lines
4849 extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns);
4950 extern void free_pid_ns(struct kref *kref);
5051 extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
52+extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd);
5153
5254 static inline void put_pid_ns(struct pid_namespace *ns)
5355 {
@@ -75,11 +77,15 @@ static inline void put_pid_ns(struct pid_namespace *ns) · 21 unmodified lines
7577 {
7678 }
7779
78−
7980 static inline void zap_pid_ns_processes(struct pid_namespace *ns)
8081 {
8182 BUG();
8283 }
84+
85+static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
86+{
87+ return 0;
88+}
8389 #endif /* CONFIG_PID_NS */
8490
8591 extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk);
kernel/pid_namespace.c+33−0
@@ -15,6 +15,7 @@ · 14 unmodified lines
1515 #include <linux/acct.h>
1616 #include <linux/slab.h>
1717 #include <linux/proc_fs.h>
18+#include <linux/reboot.h>
1819
1920 #define BITS_PER_PAGE (PAGE_SIZE*8)
2021
@@ -183,6 +184,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) · 162 unmodified lines
183184 rc = sys_wait4(-1, NULL, __WALL, NULL);
184185 } while (rc != -ECHILD);
185186
187+ if (pid_ns->reboot)
188+ current->signal->group_exit_code = pid_ns->reboot;
189+
186190 acct_exit_ns(pid_ns);
187191 return;
188192 }
@@ -217,6 +221,35 @@ static struct ctl_table pid_ns_ctl_table[] = { · 28 unmodified lines
217221
218222 static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
219223
224+int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
225+{
226+ if (pid_ns == &init_pid_ns)
227+ return 0;
228+
229+ switch (cmd) {
230+ case LINUX_REBOOT_CMD_RESTART2:
231+ case LINUX_REBOOT_CMD_RESTART:
232+ pid_ns->reboot = SIGHUP;
233+ break;
234+
235+ case LINUX_REBOOT_CMD_POWER_OFF:
236+ case LINUX_REBOOT_CMD_HALT:
237+ pid_ns->reboot = SIGINT;
238+ break;
239+ default:
240+ return -EINVAL;
241+ }
242+
243+ read_lock(&tasklist_lock);
244+ force_sig(SIGKILL, pid_ns->child_reaper);
245+ read_unlock(&tasklist_lock);
246+
247+ do_exit(0);
248+
249+ /* Not reached */
250+ return 0;
251+}
252+
220253 static __init int pid_namespaces_init(void)
221254 {
222255 pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
kernel/sys.c+9−0
@@ -444,6 +444,15 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, · 443 unmodified lines
444444 magic2 != LINUX_REBOOT_MAGIC2C))
445445 return -EINVAL;
446446
447+ /*
448+ * If pid namespaces are enabled and the current task is in a child
449+ * pid_namespace, the command is handled by reboot_pid_ns() which will
450+ * call do_exit().
451+ */
452+ ret = reboot_pid_ns(task_active_pid_ns(current), cmd);
453+ if (ret)
454+ return ret;
455+
447456 /* Instead of trying to make the power_off code look like
448457 * halt when pm_power_off is not set do it the easy way.
449458 */

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t