[PATCH 1/2] introduce for_each_process_thread_break() and for_each_process_thread_continue()

[Oleg Nesterov]

Usage:

	rcu_read_lock();
	for_each_process_thread(p, t) {
		do_something_slow(p, t);

		if (SPENT_TOO_MUCH_TIME) {
			for_each_process_thread_break(p, t);
			rcu_read_unlock();
			schedule();
			rcu_read_lock();
			for_each_process_thread_continue(&p, &t);
		}
	}
	rcu_read_unlock();

This looks similar to rcu_lock_break(), but much better and the next patch
changes check_hung_uninterruptible_tasks() to use these new helpers. But my
real target is show_state_filter() which can trivially lead to lockup.

Compared to rcu_lock_break(), for_each_process_thread_continue() never gives
up, it relies on fact that both process and thread lists are sorted by the
task->start_time key. So, for example, even if both leader/thread are already
dead we can find the next alive process and continue.

Strictly speaking, the for_each_process/for_each_thread loops in _continue()
could be "SPEND_TOO_MUCH_TIME" by themselves, so perhaps we will add another
"max_scan" argument later or do something else. But at least they can not
livelock under heavy fork/exit loads, they are bounded by PID_MAX_DEFAULT in
the worst case.

NOTE: it seems that, contrary to the comment, task_struct->start_time is not
really monotonic, and this should be probably fixed. Until then  _continue()
might skip more threads with the same ->start_time than necessary.

Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
---
 include/linux/sched/signal.h | 10 ++++++++++
 kernel/exit.c                | 42 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 1be3572..1c957d4 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -565,6 +565,16 @@ extern bool current_is_single_threaded(void);
 #define for_each_process_thread(p, t)	\
 	for_each_process(p) for_each_thread(p, t)
 
+static inline void
+for_each_process_thread_break(struct task_struct *p, struct task_struct *t)
+{
+	get_task_struct(p);
+	get_task_struct(t);
+}
+
+extern void
+for_each_process_thread_continue(struct task_struct **, struct task_struct **);
+
 typedef int (*proc_visitor)(struct task_struct *p, void *data);
 void walk_process_tree(struct task_struct *top, proc_visitor, void *);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 0e21e6d..71380c7 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -319,6 +319,48 @@ void rcuwait_wake_up(struct rcuwait *w)
 	rcu_read_unlock();
 }
 
+void for_each_process_thread_continue(struct task_struct **p_leader,
+				      struct task_struct **p_thread)
+{
+	struct task_struct *leader = *p_leader, *thread = *p_thread;
+	struct task_struct *prev, *next;
+	u64 start_time;
+
+	if (pid_alive(thread)) {
+		/* mt exec could change the leader */
+		*p_leader = thread->group_leader;
+	} else if (pid_alive(leader)) {
+		start_time = thread->start_time;
+		prev = leader;
+
+		for_each_thread(leader, next) {
+			if (next->start_time > start_time)
+				break;
+			prev = next;
+		}
+
+		*p_thread = prev;
+	} else {
+		start_time = leader->start_time;
+		prev = &init_task;
+
+		for_each_process(next) {
+			if (next->start_time > start_time)
+				break;
+			prev = next;
+		}
+
+		*p_leader = prev;
+		/* a new thread can come after that, but this is fine */
+		*p_thread = list_last_entry(&prev->signal->thread_head,
+						struct task_struct,
+						thread_node);
+	}
+
+	put_task_struct(leader);
+	put_task_struct(thread);
+}
+
 /*
  * Determine if a process group is "orphaned", according to the POSIX
  * definition in 2.2.2.52.  Orphaned process groups are not to be affected
-- 
2.5.0