ptrace: Clean transitions between TASK_STOPPED and TRACED

Currently, if the task is STOPPED on ptrace attach, it's left alone
and the state is silently changed to TRACED on the next ptrace call.
The behavior breaks the assumption that arch_ptrace_stop() is called
before any task is poked by ptrace and is ugly in that a task
manipulates the state of another task directly.

With GROUP_STOP_PENDING, the transitions between TASK_STOPPED and
TRACED can be made clean.  The tracer can use the flag to tell the
tracee to retry stop on attach and detach.  On retry, the tracee will
enter the desired state in the correct way.  The lower 16bits of
task->group_stop is used to remember the signal number which caused
the last group stop.  This is used while retrying for ptrace attach as
the original group_exit_code could have been consumed with wait(2) by
then.

As the real parent may wait(2) and consume the group_exit_code
anytime, the group_exit_code needs to be saved separately so that it
can be used when switching from regular sleep to ptrace_stop().  This
is recorded in the lower 16bits of task->group_stop.

If a task is already stopped and there's no intervening SIGCONT, a
ptrace request immediately following a successful PTRACE_ATTACH should
always succeed even if the tracer doesn't wait(2) for attach
completion; however, with this change, the tracee might still be
TASK_RUNNING trying to enter TASK_TRACED which would cause the
following request to fail with -ESRCH.

This intermediate state is hidden from the ptracer by setting
GROUP_STOP_TRAPPING on attach and making ptrace_check_attach() wait
for it to clear on its signal->wait_chldexit.  Completing the
transition or getting killed clears TRAPPING and wakes up the tracer.

Note that the STOPPED -> RUNNING -> TRACED transition is still visible
to other threads which are in the same group as the ptracer and the
reverse transition is visible to all.  Please read the comments for
details.

Oleg:

* Spotted a race condition where a task may retry group stop without
  proper bookkeeping.  Fixed by redoing bookkeeping on retry.

* Spotted that the transition is visible to userland in several
  different ways.  Most are fixed with GROUP_STOP_TRAPPING.  Unhandled
  corner case is documented.

* Pointed out not setting GROUP_STOP_SIGMASK on an already stopped
  task would result in more consistent behavior.

* Pointed out that calling ptrace_stop() from do_signal_stop() in
  TASK_STOPPED can race with group stop start logic and then confuse
  the TRAPPING wait in ptrace_check_attach().  ptrace_stop() is now
  called with TASK_RUNNING.

* Suggested using signal->wait_chldexit instead of bit wait.

* Spotted a race condition between TRACED transition and clearing of
  TRAPPING.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>

1 files changed, 66 insertions, 13 deletions

diff --git a/kernel/signal.c b/kernel/signal.c
index 418776c41d2..1e199919ae0 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -224,6 +224,26 @@ static inline void print_dropped_signal(int sig)
 }
 
 /**
+ * task_clear_group_stop_trapping - clear group stop trapping bit
+ * @task: target task
+ *
+ * If GROUP_STOP_TRAPPING is set, a ptracer is waiting for us.  Clear it
+ * and wake up the ptracer.  Note that we don't need any further locking.
+ * @task->siglock guarantees that @task->parent points to the ptracer.
+ *
+ * CONTEXT:
+ * Must be called with @task->sighand->siglock held.
+ */
+static void task_clear_group_stop_trapping(struct task_struct *task)
+{
+	if (unlikely(task->group_stop & GROUP_STOP_TRAPPING)) {
+		task->group_stop &= ~GROUP_STOP_TRAPPING;
+		__wake_up_sync(&task->parent->signal->wait_chldexit,
+			       TASK_UNINTERRUPTIBLE, 1);
+	}
+}
+
+/**
  * task_clear_group_stop_pending - clear pending group stop
  * @task: target task
  *
@@ -1706,8 +1726,20 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 	current->last_siginfo = info;
 	current->exit_code = exit_code;
 
-	/* Let the debugger run.  */
-	__set_current_state(TASK_TRACED);
+	/*
+	 * TRACED should be visible before TRAPPING is cleared; otherwise,
+	 * the tracer might fail do_wait().
+	 */
+	set_current_state(TASK_TRACED);
+
+	/*
+	 * We're committing to trapping.  Clearing GROUP_STOP_TRAPPING and
+	 * transition to TASK_TRACED should be atomic with respect to
+	 * siglock.  This hsould be done after the arch hook as siglock is
+	 * released and regrabbed across it.
+	 */
+	task_clear_group_stop_trapping(current);
+
 	spin_unlock_irq(&current->sighand->siglock);
 	read_lock(&tasklist_lock);
 	if (may_ptrace_stop()) {
@@ -1788,6 +1820,9 @@ static int do_signal_stop(int signr)
 		unsigned int gstop = GROUP_STOP_PENDING | GROUP_STOP_CONSUME;
 		struct task_struct *t;
 
+		/* signr will be recorded in task->group_stop for retries */
+		WARN_ON_ONCE(signr & ~GROUP_STOP_SIGMASK);
+
 		if (!likely(sig->flags & SIGNAL_STOP_DEQUEUED) ||
 		    unlikely(signal_group_exit(sig)))
 			return 0;
@@ -1797,25 +1832,27 @@ static int do_signal_stop(int signr)
 		 */
 		sig->group_exit_code = signr;
 
-		current->group_stop = gstop;
+		current->group_stop &= ~GROUP_STOP_SIGMASK;
+		current->group_stop |= signr | gstop;
 		sig->group_stop_count = 1;
-		for (t = next_thread(current); t != current; t = next_thread(t))
+		for (t = next_thread(current); t != current;
+		     t = next_thread(t)) {
+			t->group_stop &= ~GROUP_STOP_SIGMASK;
 			/*
 			 * Setting state to TASK_STOPPED for a group
 			 * stop is always done with the siglock held,
 			 * so this check has no races.
 			 */
 			if (!(t->flags & PF_EXITING) && !task_is_stopped(t)) {
-				t->group_stop = gstop;
+				t->group_stop |= signr | gstop;
 				sig->group_stop_count++;
 				signal_wake_up(t, 0);
-			} else
+			} else {
 				task_clear_group_stop_pending(t);
+			}
+		}
 	}
-
-	current->exit_code = sig->group_exit_code;
-	__set_current_state(TASK_STOPPED);
-
+retry:
 	if (likely(!task_ptrace(current))) {
 		int notify = 0;
 
@@ -1827,6 +1864,7 @@ static int do_signal_stop(int signr)
 		if (task_participate_group_stop(current))
 			notify = CLD_STOPPED;
 
+		__set_current_state(TASK_STOPPED);
 		spin_unlock_irq(&current->sighand->siglock);
 
 		if (notify) {
@@ -1839,13 +1877,28 @@ static int do_signal_stop(int signr)
 		schedule();
 
 		spin_lock_irq(&current->sighand->siglock);
-	} else
-		ptrace_stop(current->exit_code, CLD_STOPPED, 0, NULL);
+	} else {
+		ptrace_stop(current->group_stop & GROUP_STOP_SIGMASK,
+			    CLD_STOPPED, 0, NULL);
+		current->exit_code = 0;
+	}
+
+	/*
+	 * GROUP_STOP_PENDING could be set if another group stop has
+	 * started since being woken up or ptrace wants us to transit
+	 * between TASK_STOPPED and TRACED.  Retry group stop.
+	 */
+	if (current->group_stop & GROUP_STOP_PENDING) {
+		WARN_ON_ONCE(!(current->group_stop & GROUP_STOP_SIGMASK));
+		goto retry;
+	}
+
+	/* PTRACE_ATTACH might have raced with task killing, clear trapping */
+	task_clear_group_stop_trapping(current);
 
 	spin_unlock_irq(&current->sighand->siglock);
 
 	tracehook_finish_jctl();
-	current->exit_code = 0;
 
 	return 1;
 }