ptrace: implement TRAP_NOTIFY and use it for group stop events

Currently there's no way for ptracer to find out whether group stop
finished other than polling with INTERRUPT - GETSIGINFO - CONT
sequence.  This patch implements group stop notification for ptracer
using STOP traps.

When group stop state of a seized tracee changes, JOBCTL_TRAP_NOTIFY
is set, which schedules a STOP trap which is sticky - it isn't cleared
by other traps and at least one STOP trap will happen eventually.
STOP trap is synchronization point for event notification and the
tracer can determine the current group stop state by looking at the
signal number portion of exit code (si_status from waitid(2) or
si_code from PTRACE_GETSIGINFO).

Notifications are generated both on start and end of group stops but,
because group stop participation always happens before STOP trap, this
doesn't cause an extra trap while tracee is participating in group
stop.  The symmetry will be useful later.

Note that this notification works iff tracee is not trapped.
Currently there is no way to be notified of group stop state changes
while tracee is trapped.  This will be addressed by a later patch.

An example program follows.

  #define PTRACE_SEIZE		0x4206
  #define PTRACE_INTERRUPT	0x4207

  #define PTRACE_SEIZE_DEVEL	0x80000000

  static const struct timespec ts1s = { .tv_sec = 1 };

  int main(int argc, char **argv)
  {
	  pid_t tracee, tracer;
	  int i;

	  tracee = fork();
	  if (!tracee)
		  while (1)
			  pause();

	  tracer = fork();
	  if (!tracer) {
		  siginfo_t si;

		  ptrace(PTRACE_SEIZE, tracee, NULL,
			 (void *)(unsigned long)PTRACE_SEIZE_DEVEL);
		  ptrace(PTRACE_INTERRUPT, tracee, NULL, NULL);
	  repeat:
		  waitid(P_PID, tracee, NULL, WSTOPPED);

		  ptrace(PTRACE_GETSIGINFO, tracee, NULL, &si);
		  if (!si.si_code) {
			  printf("tracer: SIG %d\n", si.si_signo);
			  ptrace(PTRACE_CONT, tracee, NULL,
				 (void *)(unsigned long)si.si_signo);
			  goto repeat;
		  }
		  printf("tracer: stopped=%d signo=%d\n",
			 si.si_signo != SIGTRAP, si.si_signo);
		  ptrace(PTRACE_CONT, tracee, NULL, NULL);
		  goto repeat;
	  }

	  for (i = 0; i < 3; i++) {
		  nanosleep(&ts1s, NULL);
		  printf("mother: SIGSTOP\n");
		  kill(tracee, SIGSTOP);
		  nanosleep(&ts1s, NULL);
		  printf("mother: SIGCONT\n");
		  kill(tracee, SIGCONT);
	  }
	  nanosleep(&ts1s, NULL);

	  kill(tracer, SIGKILL);
	  kill(tracee, SIGKILL);
	  return 0;
  }

In the above program, tracer keeps tracee running and gets
notification of each group stop state changes.

  # ./test-notify
  tracer: stopped=0 signo=5
  mother: SIGSTOP
  tracer: SIG 19
  tracer: stopped=1 signo=19
  mother: SIGCONT
  tracer: stopped=0 signo=5
  tracer: SIG 18
  mother: SIGSTOP
  tracer: SIG 19
  tracer: stopped=1 signo=19
  mother: SIGCONT
  tracer: stopped=0 signo=5
  tracer: SIG 18
  mother: SIGSTOP
  tracer: SIG 19
  tracer: stopped=1 signo=19
  mother: SIGCONT
  tracer: stopped=0 signo=5
  tracer: SIG 18

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>

1 files changed, 3 insertions, 1 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8bd84b83a35b..1854def284f5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1811,15 +1811,17 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define JOBCTL_STOP_PENDING_BIT	17	/* task should stop for group stop */
 #define JOBCTL_STOP_CONSUME_BIT	18	/* consume group stop count */
 #define JOBCTL_TRAP_STOP_BIT	19	/* trap for STOP */
+#define JOBCTL_TRAP_NOTIFY_BIT	20	/* trap for NOTIFY */
 #define JOBCTL_TRAPPING_BIT	21	/* switching to TRACED */
 
 #define JOBCTL_STOP_DEQUEUED	(1 << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1 << JOBCTL_STOP_PENDING_BIT)
 #define JOBCTL_STOP_CONSUME	(1 << JOBCTL_STOP_CONSUME_BIT)
 #define JOBCTL_TRAP_STOP	(1 << JOBCTL_TRAP_STOP_BIT)
+#define JOBCTL_TRAP_NOTIFY	(1 << JOBCTL_TRAP_NOTIFY_BIT)
 #define JOBCTL_TRAPPING		(1 << JOBCTL_TRAPPING_BIT)
 
-#define JOBCTL_TRAP_MASK	JOBCTL_TRAP_STOP
+#define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
 
 extern bool task_set_jobctl_pending(struct task_struct *task,