sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state

Currently ptrace_stop() / do_signal_stop() rely on the special states
TASK_TRACED and TASK_STOPPED resp. to keep unique state. That is, this
state exists only in task->__state and nowhere else.

There's two spots of bother with this:

 - PREEMPT_RT has task->saved_state which complicates matters,
   meaning task_is_{traced,stopped}() needs to check an additional
   variable.

 - An alternative freezer implementation that itself relies on a
   special TASK state would loose TASK_TRACED/TASK_STOPPED and will
   result in misbehaviour.

As such, add additional state to task->jobctl to track this state
outside of task->__state.

NOTE: this doesn't actually fix anything yet, just adds extra state.

--EWB
  * didn't add a unnecessary newline in signal.h
  * Update t->jobctl in signal_wake_up and ptrace_signal_wake_up
    instead of in signal_wake_up_state.  This prevents the clearing
    of TASK_STOPPED and TASK_TRACED from getting lost.
  * Added warnings if JOBCTL_STOPPED or JOBCTL_TRACED are not cleared

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220421150654.757693825@infradead.org
Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-12-ebiederm@xmission.com
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>

3 files changed, 24 insertions, 9 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 610f2fdb1e2c..cbe5c899599c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -118,11 +118,9 @@ struct task_group;
 
 #define task_is_running(task)		(READ_ONCE((task)->__state) == TASK_RUNNING)
 
-#define task_is_traced(task)		((READ_ONCE(task->__state) & __TASK_TRACED) != 0)
-
-#define task_is_stopped(task)		((READ_ONCE(task->__state) & __TASK_STOPPED) != 0)
-
-#define task_is_stopped_or_traced(task)	((READ_ONCE(task->__state) & (__TASK_STOPPED | __TASK_TRACED)) != 0)
+#define task_is_traced(task)		((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0)
+#define task_is_stopped(task)		((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0)
+#define task_is_stopped_or_traced(task)	((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0)
 
 /*
  * Special states are those that do not use the normal wait-loop pattern. See
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index d556c3425963..68876d0a7ef9 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -21,6 +21,9 @@ struct task_struct;
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
 #define JOBCTL_PTRACE_FROZEN_BIT	24	/* frozen for ptrace */
 
+#define JOBCTL_STOPPED_BIT	26	/* do_signal_stop() */
+#define JOBCTL_TRACED_BIT	27	/* ptrace_stop() */
+
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
 #define JOBCTL_STOP_CONSUME	(1UL << JOBCTL_STOP_CONSUME_BIT)
@@ -31,6 +34,9 @@ struct task_struct;
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
 #define JOBCTL_PTRACE_FROZEN	(1UL << JOBCTL_PTRACE_FROZEN_BIT)
 
+#define JOBCTL_STOPPED		(1UL << JOBCTL_STOPPED_BIT)
+#define JOBCTL_TRACED		(1UL << JOBCTL_TRACED_BIT)
+
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index e66948abbee4..07ba3404fcde 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -294,8 +294,10 @@ static inline int kernel_dequeue_signal(void)
 static inline void kernel_signal_stop(void)
 {
 	spin_lock_irq(&current->sighand->siglock);
-	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+	if (current->jobctl & JOBCTL_STOP_DEQUEUED) {
+		current->jobctl |= JOBCTL_STOPPED;
 		set_special_state(TASK_STOPPED);
+	}
 	spin_unlock_irq(&current->sighand->siglock);
 
 	schedule();
@@ -437,12 +439,21 @@ extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
 
 static inline void signal_wake_up(struct task_struct *t, bool fatal)
 {
-	fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN);
-	signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0);
+	unsigned int state = 0;
+	if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) {
+		t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED);
+		state = TASK_WAKEKILL | __TASK_TRACED;
+	}
+	signal_wake_up_state(t, state);
 }
 static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
 {
-	signal_wake_up_state(t, resume ? __TASK_TRACED : 0);
+	unsigned int state = 0;
+	if (resume) {
+		t->jobctl &= ~JOBCTL_TRACED;
+		state = __TASK_TRACED;
+	}
+	signal_wake_up_state(t, state);
 }
 
 void task_join_group_stop(struct task_struct *task);