ptrace: implement PTRACE_SEIZE

PTRACE_ATTACH implicitly issues SIGSTOP on attach which has side
effects on tracee signal and job control states.  This patch
implements a new ptrace request PTRACE_SEIZE which attaches a tracee
without trapping it or affecting its signal and job control states.

The usage is the same with PTRACE_ATTACH but it takes PTRACE_SEIZE_*
flags in @data.  Currently, the only defined flag is
PTRACE_SEIZE_DEVEL which is a temporary flag to enable PTRACE_SEIZE.
PTRACE_SEIZE will change ptrace behaviors outside of attach itself.
The changes will be implemented gradually and the DEVEL flag is to
prevent programs which expect full SEIZE behavior from using it before
all the behavior modifications are complete while allowing unit
testing.  The flag will be removed once SEIZE behaviors are completely
implemented.

* PTRACE_SEIZE, unlike ATTACH, doesn't force tracee to trap.  After
  attaching tracee continues to run unless a trap condition occurs.

* PTRACE_SEIZE doesn't affect signal or group stop state.

* If PTRACE_SEIZE'd, group stop uses PTRACE_EVENT_STOP trap which uses
  exit_code of (signr | PTRACE_EVENT_STOP << 8) where signr is one of
  the stopping signals if group stop is in effect or SIGTRAP
  otherwise, and returns usual trap siginfo on PTRACE_GETSIGINFO
  instead of NULL.

Seizing sets PT_SEIZED in ->ptrace of the tracee.  This flag will be
used to determine whether new SEIZE behaviors should be enabled.

Test program follows.

  #define PTRACE_SEIZE		0x4206
  #define PTRACE_SEIZE_DEVEL	0x80000000

  static const struct timespec ts100ms = { .tv_nsec = 100000000 };
  static const struct timespec ts1s = { .tv_sec = 1 };
  static const struct timespec ts3s = { .tv_sec = 3 };

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

	  tracee = fork();
	  if (tracee == 0) {
		  nanosleep(&ts100ms, NULL);
		  while (1) {
			  printf("tracee: alive\n");
			  nanosleep(&ts1s, NULL);
		  }
	  }

	  if (argc > 1)
		  kill(tracee, SIGSTOP);

	  nanosleep(&ts100ms, NULL);

	  ptrace(PTRACE_SEIZE, tracee, NULL,
		 (void *)(unsigned long)PTRACE_SEIZE_DEVEL);
	  if (argc > 1) {
		  waitid(P_PID, tracee, NULL, WSTOPPED);
		  ptrace(PTRACE_CONT, tracee, NULL, NULL);
	  }
	  nanosleep(&ts3s, NULL);
	  printf("tracer: exiting\n");
	  return 0;
  }

When the above program is called w/o argument, tracee is seized while
running and remains running.  When tracer exits, tracee continues to
run and print out messages.

  # ./test-seize-simple
  tracee: alive
  tracee: alive
  tracee: alive
  tracer: exiting
  tracee: alive
  tracee: alive

When called with an argument, tracee is seized from stopped state and
continued, and returns to stopped state when tracer exits.

  # ./test-seize
  tracee: alive
  tracee: alive
  tracee: alive
  tracer: exiting
  # ps -el|grep test-seize
  1 T     0  4720     1  0  80   0 -   941 signal ttyS0    00:00:00 test-seize

-v2: SEIZE doesn't schedule TRAP_STOP and leaves tracee running as Jan
     suggested.

-v3: PTRACE_EVENT_STOP traps now report group stop state by signr.  If
     group stop is in effect the stop signal number is returned as
     part of exit_code; otherwise, SIGTRAP.  This was suggested by
     Denys and Oleg.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Cc: Denys Vlasenko <vda.linux@googlemail.com>
Cc: Oleg Nesterov <oleg@redhat.com>

2 files changed, 59 insertions, 15 deletions

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 45a8a4c5d8b2..dcf9f974198c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -209,10 +209,28 @@ bool ptrace_may_access(struct task_struct *task, unsigned int mode)
 	return !err;
 }
 
-static int ptrace_attach(struct task_struct *task)
+static int ptrace_attach(struct task_struct *task, long request,
+			 unsigned long flags)
 {
+	bool seize = (request == PTRACE_SEIZE);
 	int retval;
 
+	/*
+	 * SEIZE will enable new ptrace behaviors which will be implemented
+	 * gradually.  SEIZE_DEVEL is used to prevent applications
+	 * expecting full SEIZE behaviors trapping on kernel commits which
+	 * are still in the process of implementing them.
+	 *
+	 * Only test programs for new ptrace behaviors being implemented
+	 * should set SEIZE_DEVEL.  If unset, SEIZE will fail with -EIO.
+	 *
+	 * Once SEIZE behaviors are completely implemented, this flag and
+	 * the following test will be removed.
+	 */
+	retval = -EIO;
+	if (seize && !(flags & PTRACE_SEIZE_DEVEL))
+		goto out;
+
 	audit_ptrace(task);
 
 	retval = -EPERM;
@@ -244,11 +262,16 @@ static int ptrace_attach(struct task_struct *task)
 		goto unlock_tasklist;
 
 	task->ptrace = PT_PTRACED;
+	if (seize)
+		task->ptrace |= PT_SEIZED;
 	if (task_ns_capable(task, CAP_SYS_PTRACE))
 		task->ptrace |= PT_PTRACE_CAP;
 
 	__ptrace_link(task, current);
-	send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
+
+	/* SEIZE doesn't trap tracee on attach */
+	if (!seize)
+		send_sig_info(SIGSTOP, SEND_SIG_FORCED, task);
 
 	spin_lock(&task->sighand->siglock);
 
@@ -785,8 +808,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
 		goto out;
 	}
 
-	if (request == PTRACE_ATTACH) {
-		ret = ptrace_attach(child);
+	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
+		ret = ptrace_attach(child, request, data);
 		/*
 		 * Some architectures need to do book-keeping after
 		 * a ptrace attach.
@@ -927,8 +950,8 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 		goto out;
 	}
 
-	if (request == PTRACE_ATTACH) {
-		ret = ptrace_attach(child);
+	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
+		ret = ptrace_attach(child, request, data);
 		/*
 		 * Some architectures need to do book-keeping after
 		 * a ptrace attach.
diff --git a/kernel/signal.c b/kernel/signal.c
index b5f55ca1f43f..589292f38530 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1873,21 +1873,26 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 	recalc_sigpending_tsk(current);
 }
 
-void ptrace_notify(int exit_code)
+static void ptrace_do_notify(int signr, int exit_code, int why)
 {
 	siginfo_t info;
 
-	BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);
-
 	memset(&info, 0, sizeof info);
-	info.si_signo = SIGTRAP;
+	info.si_signo = signr;
 	info.si_code = exit_code;
 	info.si_pid = task_pid_vnr(current);
 	info.si_uid = current_uid();
 
 	/* Let the debugger run.  */
+	ptrace_stop(exit_code, why, 1, &info);
+}
+
+void ptrace_notify(int exit_code)
+{
+	BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP);
+
 	spin_lock_irq(&current->sighand->siglock);
-	ptrace_stop(exit_code, CLD_TRAPPED, 1, &info);
+	ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED);
 	spin_unlock_irq(&current->sighand->siglock);
 }
 
@@ -2017,7 +2022,13 @@ static bool do_signal_stop(int signr)
 /**
  * do_jobctl_trap - take care of ptrace jobctl traps
  *
- * It is currently used only to trap for group stop while ptraced.
+ * When PT_SEIZED, it's used for both group stop and explicit
+ * SEIZE/INTERRUPT traps.  Both generate PTRACE_EVENT_STOP trap with
+ * accompanying siginfo.  If stopped, lower eight bits of exit_code contain
+ * the stop signal; otherwise, %SIGTRAP.
+ *
+ * When !PT_SEIZED, it's used only for group stop trap with stop signal
+ * number as exit_code and no siginfo.
  *
  * CONTEXT:
  * Must be called with @current->sighand->siglock held, which may be
@@ -2025,11 +2036,21 @@ static bool do_signal_stop(int signr)
  */
 static void do_jobctl_trap(void)
 {
+	struct signal_struct *signal = current->signal;
 	int signr = current->jobctl & JOBCTL_STOP_SIGMASK;
 
-	WARN_ON_ONCE(!signr);
-	ptrace_stop(signr, CLD_STOPPED, 0, NULL);
-	current->exit_code = 0;
+	if (current->ptrace & PT_SEIZED) {
+		if (!signal->group_stop_count &&
+		    !(signal->flags & SIGNAL_STOP_STOPPED))
+			signr = SIGTRAP;
+		WARN_ON_ONCE(!signr);
+		ptrace_do_notify(signr, signr | (PTRACE_EVENT_STOP << 8),
+				 CLD_STOPPED);
+	} else {
+		WARN_ON_ONCE(!signr);
+		ptrace_stop(signr, CLD_STOPPED, 0, NULL);
+		current->exit_code = 0;
+	}
 }
 
 static int ptrace_signal(int signr, siginfo_t *info,