The patch titled Subject: pidns: add reboot_pid_ns() to handle the reboot syscall has been added to the -mm tree. Its filename is pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Daniel Lezcano <daniel.lezcano@xxxxxxx> Subject: 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; } Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxx> Acked-by: Serge Hallyn <serge.hallyn@xxxxxxxxxxxxx> Tested-by: Serge Hallyn <serge.hallyn@xxxxxxxxxxxxx> Reviewed-by: Oleg Nesterov <oleg@xxxxxxxxxx> Cc: Michael Kerrisk <mtk.manpages@xxxxxxxxx> Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx> Cc: Tejun Heo <tj@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/pid_namespace.h | 8 ++++++- kernel/pid_namespace.c | 33 ++++++++++++++++++++++++++++++++ kernel/sys.c | 8 +++++++ 3 files changed, 48 insertions(+), 1 deletion(-) diff -puN include/linux/pid_namespace.h~pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall include/linux/pid_namespace.h --- a/include/linux/pid_namespace.h~pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall +++ a/include/linux/pid_namespace.h @@ -32,6 +32,7 @@ struct pid_namespace { #endif gid_t pid_gid; int hide_pid; + int reboot; }; extern struct pid_namespace init_pid_ns; @@ -47,6 +48,7 @@ static inline struct pid_namespace *get_ extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns); extern void free_pid_ns(struct kref *kref); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); +extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); static inline void put_pid_ns(struct pid_namespace *ns) { @@ -74,11 +76,15 @@ static inline void put_pid_ns(struct pid { } - static inline void zap_pid_ns_processes(struct pid_namespace *ns) { BUG(); } + +static inline int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) +{ + return 0; +} #endif /* CONFIG_PID_NS */ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); diff -puN kernel/pid_namespace.c~pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall kernel/pid_namespace.c --- a/kernel/pid_namespace.c~pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall +++ a/kernel/pid_namespace.c @@ -15,6 +15,7 @@ #include <linux/acct.h> #include <linux/slab.h> #include <linux/proc_fs.h> +#include <linux/reboot.h> #define BITS_PER_PAGE (PAGE_SIZE*8) @@ -187,6 +188,9 @@ void zap_pid_ns_processes(struct pid_nam rc = sys_wait4(-1, NULL, __WALL, NULL); } while (rc != -ECHILD); + if (pid_ns->reboot) + current->signal->group_exit_code = pid_ns->reboot; + acct_exit_ns(pid_ns); return; } @@ -221,6 +225,35 @@ static struct ctl_table pid_ns_ctl_table static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } }; +int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd) +{ + if (pid_ns == &init_pid_ns) + return 0; + + switch(cmd) { + case LINUX_REBOOT_CMD_RESTART2: + case LINUX_REBOOT_CMD_RESTART: + pid_ns->reboot = SIGHUP; + break; + + case LINUX_REBOOT_CMD_POWER_OFF: + case LINUX_REBOOT_CMD_HALT: + pid_ns->reboot = SIGINT; + break; + default: + return -EINVAL; + } + + read_lock(&tasklist_lock); + force_sig(SIGKILL, pid_ns->child_reaper); + read_unlock(&tasklist_lock); + + do_exit(0); + + /* Not reached */ + return 0; +} + static __init int pid_namespaces_init(void) { pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC); diff -puN kernel/sys.c~pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall kernel/sys.c --- a/kernel/sys.c~pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall +++ a/kernel/sys.c @@ -444,6 +444,14 @@ SYSCALL_DEFINE4(reboot, int, magic1, int magic2 != LINUX_REBOOT_MAGIC2C)) return -EINVAL; + /* In case the pid namespaces are enabled, the current task is in a + * child pid_namespace and the command is handled by 'reboot_pid_ns', + * this one will invoke 'do_exit'. + */ + ret = reboot_pid_ns(task_active_pid_ns(current), cmd); + if (ret) + return ret; + /* Instead of trying to make the power_off code look like * halt when pm_power_off is not set do it the easy way. */ _ Subject: Subject: pidns: add reboot_pid_ns() to handle the reboot syscall Patches currently in -mm which might be from daniel.lezcano@xxxxxxx are pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall.patch pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall-fix.patch pidns-add-reboot_pid_ns-to-handle-the-reboot-syscall-checkpatch-fixes.patch fs-proc-namespacesc-prevent-crash-when-ns_entries-is-empty.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html