[path][rfc] add PR_DETACH prctl command

[Stas Sergeev]

Hi.

The attched patch adds the PR_DETACH prctl command.
It is needed for those rare but unfortunate cases, where
you can't daemonize your process before creating a thread.
The effect of this command is similar to the fork() and then
exit() on parent, except that:
1. PID does not change
2. Threads are not destroyed

It would be nice to know what people think about such an
approach.

Signed-off-by: stsp@xxxxxxxx
CC: Oleg Nesterov <oleg@xxxxxxxxxx>
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 7c99c1c..ccccfa8 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -462,7 +462,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	/* convert nsec -> ticks */
 	start_time = nsec_to_clock_t(start_time);
 
-	seq_printf(m, "%d (%s) %c %d %d %d %d %d %u %lu \
+	seq_printf(m, "%d (%s) %c %d %d %d %d %d %llu %lu \
 %lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
 %lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
 		pid_nr_ns(pid, ns),
diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h
index 942d30b..1da9c20 100644
--- a/include/asm-generic/siginfo.h
+++ b/include/asm-generic/siginfo.h
@@ -218,7 +218,8 @@ typedef struct siginfo {
 #define CLD_TRAPPED	(__SI_CHLD|4)	/* traced child has trapped */
 #define CLD_STOPPED	(__SI_CHLD|5)	/* child has stopped */
 #define CLD_CONTINUED	(__SI_CHLD|6)	/* stopped child has continued */
-#define NSIGCHLD	6
+#define CLD_DETACHED	(__SI_CHLD|7)	/* child has detached */
+#define NSIGCHLD	7
 
 /*
  * SIGPOLL si_codes
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index a3baeb2..fbd2451 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -102,4 +102,6 @@
 
 #define PR_MCE_KILL_GET 34
 
+#define PR_DETACH 35
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 777d8a5..75c977e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1194,7 +1194,7 @@ struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
 	atomic_t usage;
-	unsigned int flags;	/* per process flags, defined below */
+	u64 flags;	/* per process flags, defined below */
 	unsigned int ptrace;
 
 	int lock_depth;		/* BKL lock depth */
@@ -1746,6 +1746,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
 #define PF_FREEZER_NOSIG 0x80000000	/* Freezer won't send signals to it */
+#define PF_DETACH	 0x100000000ULL	/* Detach from parent */
 
 /*
  * Only the _current_ task can read/write to tsk->flags, but other
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 156cc55..f11c1ca 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -181,7 +181,7 @@ static inline void check_for_tasks(int cpu)
 		    (!cputime_eq(p->utime, cputime_zero) ||
 		     !cputime_eq(p->stime, cputime_zero)))
 			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "
-				"(state = %ld, flags = %x)\n",
+				"(state = %ld, flags = %llx)\n",
 				p->comm, task_pid_nr(p), cpu,
 				p->state, p->flags);
 	}
diff --git a/kernel/exit.c b/kernel/exit.c
index f9a45eb..2c8f050 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1507,6 +1507,38 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 	return retval;
 }
 
+static int wait_task_detached(struct wait_opts *wo, struct task_struct *p)
+{
+	int retval = 0;
+	pid_t pid = task_pid_vnr(p);
+	uid_t uid = __task_cred(p)->uid;
+
+	get_task_struct(p);
+	if (unlikely(wo->wo_flags & WNOWAIT)) {
+		read_unlock(&tasklist_lock);
+		return wait_noreap_copyout(wo, p, pid, uid, CLD_DETACHED,
+			p->exit_code >> 8);
+	}
+
+	p->flags &= ~PF_DETACH;
+	if (!ptrace_reparented(p))
+		p->parent = init_pid_ns.child_reaper;
+	p->real_parent = init_pid_ns.child_reaper;
+	p->exit_signal = SIGCHLD;
+	list_move_tail(&p->sibling, &p->real_parent->children);
+
+	read_unlock(&tasklist_lock);
+	if (wo->wo_stat)
+		retval = put_user(p->exit_code, wo->wo_stat);
+
+	if (!retval)
+		retval = wait_noreap_copyout(wo, p, pid, uid, CLD_DETACHED,
+			p->exit_code >> 8);
+	else
+		put_task_struct(p);
+	return retval;
+}
+
 /*
  * Consider @p for a wait by @parent.
  *
@@ -1549,6 +1581,9 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 	if (p->exit_state == EXIT_DEAD)
 		return 0;
 
+	if (p->flags & PF_DETACH)
+		return wait_task_detached(wo, p);
+
 	/*
 	 * We don't reap group leaders with subthreads.
 	 */
diff --git a/kernel/signal.c b/kernel/signal.c
index 4e3cff1..2cd495a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1450,10 +1450,10 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 
 	BUG_ON(sig == -1);
 
- 	/* do_notify_parent_cldstop should have been called instead.  */
- 	BUG_ON(task_is_stopped_or_traced(tsk));
+	/* do_notify_parent_cldstop should have been called instead.  */
+	BUG_ON(task_is_stopped_or_traced(tsk));
 
-	BUG_ON(!task_ptrace(tsk) &&
+	BUG_ON(!task_ptrace(tsk) && (tsk->flags & PF_EXITING) &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
 
 	info.si_signo = sig;
diff --git a/kernel/sys.c b/kernel/sys.c
index 18da702..c09205f 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1736,6 +1736,22 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			else
 				error = PR_MCE_KILL_DEFAULT;
 			break;
+		case PR_DETACH:
+			error = -EPERM;
+			/* if parent is init, or not a group leader - bail */
+			if (me->real_parent == init_pid_ns.child_reaper)
+				break;
+			if (me->group_leader != me)
+				break;
+			if (arg2 & ~0xff)
+				break;
+			write_lock_irq(&tasklist_lock);
+			me->exit_code = arg2 << 8;
+			me->flags |= PF_DETACH;
+			do_notify_parent(me, me->exit_signal);
+			write_unlock_irq(&tasklist_lock);
+			error = 0;
+			break;
 		default:
 			error = -EINVAL;
 			break;