From cf3f89214ef6a33fad60856bc5ffd7bb2fc4709b Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 28 Mar 2012 14:42:51 -0700 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 #include #include #include #include #include #include #include #include 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 Acked-by: Serge Hallyn Tested-by: Serge Hallyn Reviewed-by: Oleg Nesterov Cc: Michael Kerrisk Cc: "Eric W. Biederman" Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/pid_namespace.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'kernel/pid_namespace.c') diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 17b232869a04..57bc1fd35b3c 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -15,6 +15,7 @@ #include #include #include +#include #define BITS_PER_PAGE (PAGE_SIZE*8) @@ -183,6 +184,9 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) 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; } @@ -217,6 +221,35 @@ 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); -- cgit v1.2.3-58-ga151