ptrace: Don't change __state

Stop playing with tsk->__state to remove TASK_WAKEKILL while a ptrace
command is executing.

Instead remove TASK_WAKEKILL from the definition of TASK_TRACED, and
implement a new jobctl flag TASK_PTRACE_FROZEN.  This new flag is set
in jobctl_freeze_task and cleared when ptrace_stop is awoken or in
jobctl_unfreeze_task (when ptrace_stop remains asleep).

In signal_wake_up add __TASK_TRACED to state along with TASK_WAKEKILL
when the wake up is for a fatal signal.  Skip adding __TASK_TRACED
when TASK_PTRACE_FROZEN is not set.  This has the same effect as
changing TASK_TRACED to __TASK_TRACED as all of the wake_ups that use
TASK_KILLABLE go through signal_wake_up.

Handle a ptrace_stop being called with a pending fatal signal.
Previously it would have been handled by schedule simply failing to
sleep.  As TASK_WAKEKILL is no longer part of TASK_TRACED schedule
will sleep with a fatal_signal_pending.   The code in signal_wake_up
guarantees that the code will be awaked by any fatal signal that
codes after TASK_TRACED is set.

Previously the __state value of __TASK_TRACED was changed to
TASK_RUNNING when woken up or back to TASK_TRACED when the code was
left in ptrace_stop.  Now when woken up ptrace_stop now clears
JOBCTL_PTRACE_FROZEN and when left sleeping ptrace_unfreezed_traced
clears JOBCTL_PTRACE_FROZEN.

Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-10-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

3 files changed, 6 insertions, 3 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d5e3c00b74e1..610f2fdb1e2c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -103,7 +103,7 @@ struct task_group;
 /* Convenience macros for the sake of set_current_state: */
 #define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
 #define TASK_STOPPED			(TASK_WAKEKILL | __TASK_STOPPED)
-#define TASK_TRACED			(TASK_WAKEKILL | __TASK_TRACED)
+#define TASK_TRACED			__TASK_TRACED
 
 #define TASK_IDLE			(TASK_UNINTERRUPTIBLE | TASK_NOLOAD)
 
diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h
index fa067de9f1a9..d556c3425963 100644
--- a/include/linux/sched/jobctl.h
+++ b/include/linux/sched/jobctl.h
@@ -19,6 +19,7 @@ struct task_struct;
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 #define JOBCTL_LISTENING_BIT	22	/* ptracer is listening for events */
 #define JOBCTL_TRAP_FREEZE_BIT	23	/* trap for cgroup freezer */
+#define JOBCTL_PTRACE_FROZEN_BIT	24	/* frozen for ptrace */
 
 #define JOBCTL_STOP_DEQUEUED	(1UL << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1UL << JOBCTL_STOP_PENDING_BIT)
@@ -28,6 +29,7 @@ struct task_struct;
 #define JOBCTL_TRAPPING		(1UL << JOBCTL_TRAPPING_BIT)
 #define JOBCTL_LISTENING	(1UL << JOBCTL_LISTENING_BIT)
 #define JOBCTL_TRAP_FREEZE	(1UL << JOBCTL_TRAP_FREEZE_BIT)
+#define JOBCTL_PTRACE_FROZEN	(1UL << JOBCTL_PTRACE_FROZEN_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 3c8b34876744..e66948abbee4 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -435,9 +435,10 @@ extern void calculate_sigpending(void);
 
 extern void signal_wake_up_state(struct task_struct *t, unsigned int state);
 
-static inline void signal_wake_up(struct task_struct *t, bool resume)
+static inline void signal_wake_up(struct task_struct *t, bool fatal)
 {
-	signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0);
+	fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN);
+	signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0);
 }
 static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume)
 {