From 755e276b3326f300585435d2f3876e66e248c476 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 2 Jun 2011 11:13:59 +0200
Subject: ptrace: ptrace_check_attach(): rename @kill to @ignore_state and add
 comments

PTRACE_INTERRUPT is going to be added which should also skip
task_is_traced() check in ptrace_check_attach().  Rename @kill to
@ignore_state and make it bool.  Add function comment while at it.

This patch doesn't introduce any behavior difference.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/ptrace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 9178d5cc0b0..e93ef1a54fc 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -105,7 +105,7 @@ extern long arch_ptrace(struct task_struct *child, long request,
 extern int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len);
 extern int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long dst, int len);
 extern void ptrace_disable(struct task_struct *);
-extern int ptrace_check_attach(struct task_struct *task, int kill);
+extern int ptrace_check_attach(struct task_struct *task, bool ignore_state);
 extern int ptrace_request(struct task_struct *child, long request,
 			  unsigned long addr, unsigned long data);
 extern void ptrace_notify(int exit_code);
-- 
cgit v1.2.3-70-g09d2


From 3544d72a0e10d0aa1c1bd59ed77a53a59cdc12f7 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 14 Jun 2011 11:20:15 +0200
Subject: 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>
---
 include/linux/ptrace.h |  7 +++++++
 kernel/ptrace.c        | 35 +++++++++++++++++++++++++++++------
 kernel/signal.c        | 39 ++++++++++++++++++++++++++++++---------
 3 files changed, 66 insertions(+), 15 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index e93ef1a54fc..67ad3f15232 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -47,6 +47,11 @@
 #define PTRACE_GETREGSET	0x4204
 #define PTRACE_SETREGSET	0x4205
 
+#define PTRACE_SEIZE		0x4206
+
+/* flags in @data for PTRACE_SEIZE */
+#define PTRACE_SEIZE_DEVEL	0x80000000 /* temp flag for development */
+
 /* options set using PTRACE_SETOPTIONS */
 #define PTRACE_O_TRACESYSGOOD	0x00000001
 #define PTRACE_O_TRACEFORK	0x00000002
@@ -65,6 +70,7 @@
 #define PTRACE_EVENT_EXEC	4
 #define PTRACE_EVENT_VFORK_DONE	5
 #define PTRACE_EVENT_EXIT	6
+#define PTRACE_EVENT_STOP	7
 
 #include <asm/ptrace.h>
 
@@ -77,6 +83,7 @@
  * flags.  When the a task is stopped the ptracer owns task->ptrace.
  */
 
+#define PT_SEIZED	0x00010000	/* SEIZE used, enable new behavior */
 #define PT_PTRACED	0x00000001
 #define PT_DTRACE	0x00000002	/* delayed trace (used on m68k, i386) */
 #define PT_TRACESYSGOOD	0x00000004
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 45a8a4c5d8b..dcf9f974198 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 b5f55ca1f43..589292f3853 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,
-- 
cgit v1.2.3-70-g09d2


From fca26f260c528ee51a2e451b5b200aeb528f3e09 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 14 Jun 2011 11:20:16 +0200
Subject: ptrace: implement PTRACE_INTERRUPT

Currently, there's no way to trap a running ptracee short of sending a
signal which has various side effects.  This patch implements
PTRACE_INTERRUPT which traps ptracee without any signal or job control
related side effect.

The implementation is almost trivial.  It uses the group stop trap -
SIGTRAP | PTRACE_EVENT_STOP << 8.  A new trap flag
JOBCTL_TRAP_INTERRUPT is added, which is set on PTRACE_INTERRUPT and
cleared when any trap happens.  As INTERRUPT should be useable
regardless of the current state of tracee, task_is_traced() test in
ptrace_check_attach() is skipped for INTERRUPT.

PTRACE_INTERRUPT is available iff tracee is attached with
PTRACE_SEIZE.

Test program follows.

  #define PTRACE_SEIZE		0x4206
  #define PTRACE_INTERRUPT	0x4207

  #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 pid=%d\n", getpid());
			  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: INTERRUPT and DETACH\n");
	  ptrace(PTRACE_INTERRUPT, tracee, NULL, NULL);
	  waitid(P_PID, tracee, NULL, WSTOPPED);
	  ptrace(PTRACE_DETACH, tracee, NULL, NULL);
	  nanosleep(&ts3s, NULL);

	  printf("tracer: exiting\n");
	  kill(tracee, SIGKILL);
	  return 0;
  }

When called without argument, tracee is seized from running state,
interrupted and then detached back to running state.

  # ./test-interrupt
  tracee: alive pid=4546
  tracee: alive pid=4546
  tracee: alive pid=4546
  tracer: INTERRUPT and DETACH
  tracee: alive pid=4546
  tracee: alive pid=4546
  tracee: alive pid=4546
  tracer: exiting

When called with argument, tracee is seized from stopped state,
continued, interrupted and then detached back to stopped state.

  # ./test-interrupt  1
  tracee: alive pid=4548
  tracee: alive pid=4548
  tracee: alive pid=4548
  tracer: INTERRUPT and DETACH
  tracer: exiting

Before PTRACE_INTERRUPT, once the tracee was running, there was no way
to trap tracee and do PTRACE_DETACH without causing side effect.

-v2: Updated to use task_set_jobctl_pending() so that it doesn't end
     up scheduling TRAP_STOP if child is dying which may make the
     child unkillable.  Spotted by Oleg.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/ptrace.h |  1 +
 kernel/ptrace.c        | 29 +++++++++++++++++++++++++++--
 2 files changed, 28 insertions(+), 2 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 67ad3f15232..ad754d1e0b1 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -48,6 +48,7 @@
 #define PTRACE_SETREGSET	0x4205
 
 #define PTRACE_SEIZE		0x4206
+#define PTRACE_INTERRUPT	0x4207
 
 /* flags in @data for PTRACE_SEIZE */
 #define PTRACE_SEIZE_DEVEL	0x80000000 /* temp flag for development */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index dcf9f974198..6852c0f4a91 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -658,10 +658,12 @@ static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
 int ptrace_request(struct task_struct *child, long request,
 		   unsigned long addr, unsigned long data)
 {
+	bool seized = child->ptrace & PT_SEIZED;
 	int ret = -EIO;
 	siginfo_t siginfo;
 	void __user *datavp = (void __user *) data;
 	unsigned long __user *datalp = datavp;
+	unsigned long flags;
 
 	switch (request) {
 	case PTRACE_PEEKTEXT:
@@ -694,6 +696,27 @@ int ptrace_request(struct task_struct *child, long request,
 			ret = ptrace_setsiginfo(child, &siginfo);
 		break;
 
+	case PTRACE_INTERRUPT:
+		/*
+		 * Stop tracee without any side-effect on signal or job
+		 * control.  At least one trap is guaranteed to happen
+		 * after this request.  If @child is already trapped, the
+		 * current trap is not disturbed and another trap will
+		 * happen after the current trap is ended with PTRACE_CONT.
+		 *
+		 * The actual trap might not be PTRACE_EVENT_STOP trap but
+		 * the pending condition is cleared regardless.
+		 */
+		if (unlikely(!seized || !lock_task_sighand(child, &flags)))
+			break;
+
+		if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP)))
+			signal_wake_up(child, 0);
+
+		unlock_task_sighand(child, &flags);
+		ret = 0;
+		break;
+
 	case PTRACE_DETACH:	 /* detach a process that was attached. */
 		ret = ptrace_detach(child, data);
 		break;
@@ -819,7 +842,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
 		goto out_put_task_struct;
 	}
 
-	ret = ptrace_check_attach(child, request == PTRACE_KILL);
+	ret = ptrace_check_attach(child, request == PTRACE_KILL ||
+				  request == PTRACE_INTERRUPT);
 	if (ret < 0)
 		goto out_put_task_struct;
 
@@ -961,7 +985,8 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 		goto out_put_task_struct;
 	}
 
-	ret = ptrace_check_attach(child, request == PTRACE_KILL);
+	ret = ptrace_check_attach(child, request == PTRACE_KILL ||
+				  request == PTRACE_INTERRUPT);
 	if (!ret)
 		ret = compat_arch_ptrace(child, request, addr, data);
 
-- 
cgit v1.2.3-70-g09d2


From 544b2c91a9f14f9565af1972203438b7f49afd48 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 14 Jun 2011 11:20:18 +0200
Subject: ptrace: implement PTRACE_LISTEN

The previous patch implemented async notification for ptrace but it
only worked while trace is running.  This patch introduces
PTRACE_LISTEN which is suggested by Oleg Nestrov.

It's allowed iff tracee is in STOP trap and puts tracee into
quasi-running state - tracee never really runs but wait(2) and
ptrace(2) consider it to be running.  While ptracer is listening,
tracee is allowed to re-enter STOP to notify an async event.
Listening state is cleared on the first notification.  Ptracer can
also clear it by issuing INTERRUPT - tracee will re-trap into STOP
with listening state cleared.

This allows ptracer to monitor group stop state without running tracee
- use INTERRUPT to put tracee into STOP trap, issue LISTEN and then
wait(2) to wait for the next group stop event.  When it happens,
PTRACE_GETSIGINFO provides information to determine the current state.

Test program follows.

  #define PTRACE_SEIZE		0x4206
  #define PTRACE_INTERRUPT	0x4207
  #define PTRACE_LISTEN		0x4208

  #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);
		  if (si.si_signo != SIGTRAP)
			  ptrace(PTRACE_LISTEN, tracee, NULL, NULL);
		  else
			  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;
  }

This is identical to the program to test TRAP_NOTIFY except that
tracee is PTRACE_LISTEN'd instead of PTRACE_CONT'd when group stopped.
This allows ptracer to monitor when group stop ends without running
tracee.

  # ./test-listen
  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

-v2: Moved JOBCTL_LISTENING check in wait_task_stopped() into
     task_stopped_code() as suggested by Oleg.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/ptrace.h |  1 +
 include/linux/sched.h  |  2 ++
 kernel/exit.c          |  3 ++-
 kernel/ptrace.c        | 42 +++++++++++++++++++++++++++++++++++++++---
 kernel/signal.c        | 13 +++++++++----
 5 files changed, 53 insertions(+), 8 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index ad754d1e0b1..4f224f16952 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -49,6 +49,7 @@
 
 #define PTRACE_SEIZE		0x4206
 #define PTRACE_INTERRUPT	0x4207
+#define PTRACE_LISTEN		0x4208
 
 /* flags in @data for PTRACE_SEIZE */
 #define PTRACE_SEIZE_DEVEL	0x80000000 /* temp flag for development */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1854def284f..87f7ca7ed6f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1813,6 +1813,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #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_LISTENING_BIT	22	/* ptracer is listening for events */
 
 #define JOBCTL_STOP_DEQUEUED	(1 << JOBCTL_STOP_DEQUEUED_BIT)
 #define JOBCTL_STOP_PENDING	(1 << JOBCTL_STOP_PENDING_BIT)
@@ -1820,6 +1821,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #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_LISTENING	(1 << JOBCTL_LISTENING_BIT)
 
 #define JOBCTL_TRAP_MASK	(JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY)
 #define JOBCTL_PENDING_MASK	(JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK)
diff --git a/kernel/exit.c b/kernel/exit.c
index 20a40647152..289f59d686b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1368,7 +1368,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 static int *task_stopped_code(struct task_struct *p, bool ptrace)
 {
 	if (ptrace) {
-		if (task_is_stopped_or_traced(p))
+		if (task_is_stopped_or_traced(p) &&
+		    !(p->jobctl & JOBCTL_LISTENING))
 			return &p->exit_code;
 	} else {
 		if (p->signal->flags & SIGNAL_STOP_STOPPED)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 6852c0f4a91..e18966c1c0d 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -146,7 +146,8 @@ int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 		 */
 		spin_lock_irq(&child->sighand->siglock);
 		WARN_ON_ONCE(task_is_stopped(child));
-		if (task_is_traced(child) || ignore_state)
+		if (ignore_state || (task_is_traced(child) &&
+				     !(child->jobctl & JOBCTL_LISTENING)))
 			ret = 0;
 		spin_unlock_irq(&child->sighand->siglock);
 	}
@@ -660,7 +661,7 @@ int ptrace_request(struct task_struct *child, long request,
 {
 	bool seized = child->ptrace & PT_SEIZED;
 	int ret = -EIO;
-	siginfo_t siginfo;
+	siginfo_t siginfo, *si;
 	void __user *datavp = (void __user *) data;
 	unsigned long __user *datalp = datavp;
 	unsigned long flags;
@@ -710,8 +711,43 @@ int ptrace_request(struct task_struct *child, long request,
 		if (unlikely(!seized || !lock_task_sighand(child, &flags)))
 			break;
 
+		/*
+		 * INTERRUPT doesn't disturb existing trap sans one
+		 * exception.  If ptracer issued LISTEN for the current
+		 * STOP, this INTERRUPT should clear LISTEN and re-trap
+		 * tracee into STOP.
+		 */
 		if (likely(task_set_jobctl_pending(child, JOBCTL_TRAP_STOP)))
-			signal_wake_up(child, 0);
+			signal_wake_up(child, child->jobctl & JOBCTL_LISTENING);
+
+		unlock_task_sighand(child, &flags);
+		ret = 0;
+		break;
+
+	case PTRACE_LISTEN:
+		/*
+		 * Listen for events.  Tracee must be in STOP.  It's not
+		 * resumed per-se but is not considered to be in TRACED by
+		 * wait(2) or ptrace(2).  If an async event (e.g. group
+		 * stop state change) happens, tracee will enter STOP trap
+		 * again.  Alternatively, ptracer can issue INTERRUPT to
+		 * finish listening and re-trap tracee into STOP.
+		 */
+		if (unlikely(!seized || !lock_task_sighand(child, &flags)))
+			break;
+
+		si = child->last_siginfo;
+		if (unlikely(!si || si->si_code >> 8 != PTRACE_EVENT_STOP))
+			break;
+
+		child->jobctl |= JOBCTL_LISTENING;
+
+		/*
+		 * If NOTIFY is set, it means event happened between start
+		 * of this trap and now.  Trigger re-trap immediately.
+		 */
+		if (child->jobctl & JOBCTL_TRAP_NOTIFY)
+			signal_wake_up(child, true);
 
 		unlock_task_sighand(child, &flags);
 		ret = 0;
diff --git a/kernel/signal.c b/kernel/signal.c
index 06177e2b391..97e575a3387 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -825,9 +825,11 @@ static int check_kill_permission(int sig, struct siginfo *info,
  * TRAP_STOP to notify ptracer of an event.  @t must have been seized by
  * ptracer.
  *
- * If @t is running, STOP trap will be taken.  If already trapped, STOP
- * trap will be eventually taken without returning to userland after the
- * existing traps are finished by PTRACE_CONT.
+ * If @t is running, STOP trap will be taken.  If trapped for STOP and
+ * ptracer is listening for events, tracee is woken up so that it can
+ * re-trap for the new event.  If trapped otherwise, STOP trap will be
+ * eventually taken without returning to userland after the existing traps
+ * are finished by PTRACE_CONT.
  *
  * CONTEXT:
  * Must be called with @task->sighand->siglock held.
@@ -838,7 +840,7 @@ static void ptrace_trap_notify(struct task_struct *t)
 	assert_spin_locked(&t->sighand->siglock);
 
 	task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY);
-	signal_wake_up(t, 0);
+	signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
 }
 
 /*
@@ -1894,6 +1896,9 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info)
 	spin_lock_irq(&current->sighand->siglock);
 	current->last_siginfo = NULL;
 
+	/* LISTENING can be set only during STOP traps, clear it */
+	current->jobctl &= ~JOBCTL_LISTENING;
+
 	/*
 	 * Queued signals ignored us while we were stopped for tracing.
 	 * So check for any that we should take before resuming user mode.
-- 
cgit v1.2.3-70-g09d2


From d21142ece414ce1088cfcae760689aa60d6fee80 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 17 Jun 2011 16:50:34 +0200
Subject: ptrace: kill task_ptrace()

task_ptrace(task) simply dereferences task->ptrace and isn't even used
consistently only adding confusion.  Kill it and directly access
->ptrace instead.

This doesn't introduce any behavior change.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/ptrace.h    | 11 -----------
 include/linux/tracehook.h | 16 ++++++++--------
 kernel/exit.c             |  8 ++++----
 kernel/signal.c           | 14 +++++++-------
 mm/oom_kill.c             |  3 +--
 5 files changed, 20 insertions(+), 32 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 4f224f16952..3ff20b32259 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -145,17 +145,6 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
 int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
 			    unsigned long data);
 
-/**
- * task_ptrace - return %PT_* flags that apply to a task
- * @task:	pointer to &task_struct in question
- *
- * Returns the %PT_* flags that apply to @task.
- */
-static inline int task_ptrace(struct task_struct *task)
-{
-	return task->ptrace;
-}
-
 /**
  * ptrace_event - possibly stop for a ptrace event notification
  * @mask:	%PT_* bit to check in @current->ptrace
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 15745cdd32c..a3e838784f4 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -63,7 +63,7 @@ struct linux_binprm;
  */
 static inline int tracehook_expect_breakpoints(struct task_struct *task)
 {
-	return (task_ptrace(task) & PT_PTRACED) != 0;
+	return (task->ptrace & PT_PTRACED) != 0;
 }
 
 /*
@@ -71,7 +71,7 @@ static inline int tracehook_expect_breakpoints(struct task_struct *task)
  */
 static inline void ptrace_report_syscall(struct pt_regs *regs)
 {
-	int ptrace = task_ptrace(current);
+	int ptrace = current->ptrace;
 
 	if (!(ptrace & PT_PTRACED))
 		return;
@@ -155,7 +155,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step)
 static inline int tracehook_unsafe_exec(struct task_struct *task)
 {
 	int unsafe = 0;
-	int ptrace = task_ptrace(task);
+	int ptrace = task->ptrace;
 	if (ptrace & PT_PTRACED) {
 		if (ptrace & PT_PTRACE_CAP)
 			unsafe |= LSM_UNSAFE_PTRACE_CAP;
@@ -178,7 +178,7 @@ static inline int tracehook_unsafe_exec(struct task_struct *task)
  */
 static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk)
 {
-	if (task_ptrace(tsk) & PT_PTRACED)
+	if (tsk->ptrace & PT_PTRACED)
 		return rcu_dereference(tsk->parent);
 	return NULL;
 }
@@ -202,7 +202,7 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt,
 					 struct pt_regs *regs)
 {
 	if (!ptrace_event(PT_TRACE_EXEC, PTRACE_EVENT_EXEC, 0) &&
-	    unlikely(task_ptrace(current) & PT_PTRACED))
+	    unlikely(current->ptrace & PT_PTRACED))
 		send_sig(SIGTRAP, current, 0);
 }
 
@@ -285,7 +285,7 @@ static inline void tracehook_report_clone(struct pt_regs *regs,
 					  unsigned long clone_flags,
 					  pid_t pid, struct task_struct *child)
 {
-	if (unlikely(task_ptrace(child))) {
+	if (unlikely(child->ptrace)) {
 		/*
 		 * It doesn't matter who attached/attaching to this
 		 * task, the pending SIGSTOP is right in any case.
@@ -403,7 +403,7 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info,
 static inline int tracehook_consider_ignored_signal(struct task_struct *task,
 						    int sig)
 {
-	return (task_ptrace(task) & PT_PTRACED) != 0;
+	return (task->ptrace & PT_PTRACED) != 0;
 }
 
 /**
@@ -422,7 +422,7 @@ static inline int tracehook_consider_ignored_signal(struct task_struct *task,
 static inline int tracehook_consider_fatal_signal(struct task_struct *task,
 						  int sig)
 {
-	return (task_ptrace(task) & PT_PTRACED) != 0;
+	return (task->ptrace & PT_PTRACED) != 0;
 }
 
 #define DEATH_REAP			-1
diff --git a/kernel/exit.c b/kernel/exit.c
index 289f59d686b..e5cc0564460 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -765,7 +765,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	p->exit_signal = SIGCHLD;
 
 	/* If it has exited notify the new parent about this child's death. */
-	if (!task_ptrace(p) &&
+	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
 		do_notify_parent(p, p->exit_signal);
 		if (task_detached(p)) {
@@ -795,7 +795,7 @@ static void forget_original_parent(struct task_struct *father)
 		do {
 			t->real_parent = reaper;
 			if (t->parent == father) {
-				BUG_ON(task_ptrace(t));
+				BUG_ON(t->ptrace);
 				t->parent = t->real_parent;
 			}
 			if (t->pdeath_signal)
@@ -1565,7 +1565,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		 * Notification and reaping will be cascaded to the real
 		 * parent when the ptracer detaches.
 		 */
-		if (likely(!ptrace) && unlikely(task_ptrace(p))) {
+		if (likely(!ptrace) && unlikely(p->ptrace)) {
 			/* it will become visible, clear notask_error */
 			wo->notask_error = 0;
 			return 0;
@@ -1608,7 +1608,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		 * own children, it should create a separate process which
 		 * takes the role of real parent.
 		 */
-		if (likely(!ptrace) && task_ptrace(p) &&
+		if (likely(!ptrace) && p->ptrace &&
 		    same_thread_group(p->parent, p->real_parent))
 			return 0;
 
diff --git a/kernel/signal.c b/kernel/signal.c
index 97e575a3387..0f337087250 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1592,7 +1592,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
  	/* do_notify_parent_cldstop should have been called instead.  */
  	BUG_ON(task_is_stopped_or_traced(tsk));
 
-	BUG_ON(!task_ptrace(tsk) &&
+	BUG_ON(!tsk->ptrace &&
 	       (tsk->group_leader != tsk || !thread_group_empty(tsk)));
 
 	info.si_signo = sig;
@@ -1631,7 +1631,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 
 	psig = tsk->parent->sighand;
 	spin_lock_irqsave(&psig->siglock, flags);
-	if (!task_ptrace(tsk) && sig == SIGCHLD &&
+	if (!tsk->ptrace && sig == SIGCHLD &&
 	    (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
 	     (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT))) {
 		/*
@@ -1731,7 +1731,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 
 static inline int may_ptrace_stop(void)
 {
-	if (!likely(task_ptrace(current)))
+	if (!likely(current->ptrace))
 		return 0;
 	/*
 	 * Are we in the middle of do_coredump?
@@ -1989,7 +1989,7 @@ static bool do_signal_stop(int signr)
 		if (!(sig->flags & SIGNAL_STOP_STOPPED))
 			sig->group_exit_code = signr;
 		else
-			WARN_ON_ONCE(!task_ptrace(current));
+			WARN_ON_ONCE(!current->ptrace);
 
 		sig->group_stop_count = 0;
 
@@ -2014,7 +2014,7 @@ static bool do_signal_stop(int signr)
 		}
 	}
 
-	if (likely(!task_ptrace(current))) {
+	if (likely(!current->ptrace)) {
 		int notify = 0;
 
 		/*
@@ -2093,7 +2093,7 @@ static void do_jobctl_trap(void)
 static int ptrace_signal(int signr, siginfo_t *info,
 			 struct pt_regs *regs, void *cookie)
 {
-	if (!task_ptrace(current))
+	if (!current->ptrace)
 		return signr;
 
 	ptrace_signal_deliver(regs, cookie);
@@ -2179,7 +2179,7 @@ relock:
 		do_notify_parent_cldstop(current, false, why);
 
 		leader = current->group_leader;
-		if (task_ptrace(leader) && !real_parent_is_ptracer(leader))
+		if (leader->ptrace && !real_parent_is_ptracer(leader))
 			do_notify_parent_cldstop(leader, true, why);
 
 		read_unlock(&tasklist_lock);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index e4b0991ca35..b0be989d436 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -339,8 +339,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 				 * then wait for it to finish before killing
 				 * some other task unnecessarily.
 				 */
-				if (!(task_ptrace(p->group_leader) &
-							PT_TRACE_EXIT))
+				if (!(p->group_leader->ptrace & PT_TRACE_EXIT))
 					return ERR_PTR(-1UL);
 			}
 		}
-- 
cgit v1.2.3-70-g09d2


From 643ad8388e189dfd14ef76972cf7dc394b3cbebd Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 17 Jun 2011 16:50:35 +0200
Subject: ptrace: introduce ptrace_event_enabled() and simplify ptrace_event()
 and tracehook_prepare_clone()

This patch implements ptrace_event_enabled() which tests whether a
given PTRACE_EVENT_* is enabled and use it to simplify ptrace_event()
and tracehook_prepare_clone().

PT_EVENT_FLAG() macro is added which calculates PT_TRACE_* flag from
PTRACE_EVENT_*.  This is used to define PT_TRACE_* flags and by
ptrace_event_enabled() to find the matching flag.

This is used to make ptrace_event() and tracehook_prepare_clone()
simpler.

* ptrace_event() callers were responsible for providing mask to test
  whether the event was enabled.  This patch implements
  ptrace_event_enabled() and make ptrace_event() drop @mask and
  determine whether the event is enabled from @event.  Note that
  @event is constant and this conversion doesn't add runtime overhead.

  All conversions except tracehook_report_clone_complete() are
  trivial.  tracehook_report_clone_complete() used to use 0 for @mask
  (always enabled) but now tests whether the specified event is
  enabled.  This doesn't cause any behavior difference as it's
  guaranteed that the event specified by @trace is enabled.

* tracehook_prepare_clone() now only determines which event is
  applicable and use ptrace_event_enabled() for enable test.

This doesn't introduce any behavior change.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/ptrace.h    | 46 ++++++++++++++++++++++++++++++++--------------
 include/linux/tracehook.h | 26 +++++++++++++-------------
 2 files changed, 45 insertions(+), 27 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 3ff20b32259..18feac6f441 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -90,12 +90,17 @@
 #define PT_DTRACE	0x00000002	/* delayed trace (used on m68k, i386) */
 #define PT_TRACESYSGOOD	0x00000004
 #define PT_PTRACE_CAP	0x00000008	/* ptracer can follow suid-exec */
-#define PT_TRACE_FORK	0x00000010
-#define PT_TRACE_VFORK	0x00000020
-#define PT_TRACE_CLONE	0x00000040
-#define PT_TRACE_EXEC	0x00000080
-#define PT_TRACE_VFORK_DONE	0x00000100
-#define PT_TRACE_EXIT	0x00000200
+
+/* PT_TRACE_* event enable flags */
+#define PT_EVENT_FLAG_SHIFT	4
+#define PT_EVENT_FLAG(event)	(1 << (PT_EVENT_FLAG_SHIFT + (event) - 1))
+
+#define PT_TRACE_FORK		PT_EVENT_FLAG(PTRACE_EVENT_FORK)
+#define PT_TRACE_VFORK		PT_EVENT_FLAG(PTRACE_EVENT_VFORK)
+#define PT_TRACE_CLONE		PT_EVENT_FLAG(PTRACE_EVENT_CLONE)
+#define PT_TRACE_EXEC		PT_EVENT_FLAG(PTRACE_EVENT_EXEC)
+#define PT_TRACE_VFORK_DONE	PT_EVENT_FLAG(PTRACE_EVENT_VFORK_DONE)
+#define PT_TRACE_EXIT		PT_EVENT_FLAG(PTRACE_EVENT_EXIT)
 
 #define PT_TRACE_MASK	0x000003f4
 
@@ -145,26 +150,39 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
 int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
 			    unsigned long data);
 
+/**
+ * ptrace_event_enabled - test whether a ptrace event is enabled
+ * @task: ptracee of interest
+ * @event: %PTRACE_EVENT_* to test
+ *
+ * Test whether @event is enabled for ptracee @task.
+ *
+ * Returns %true if @event is enabled, %false otherwise.
+ */
+static inline bool ptrace_event_enabled(struct task_struct *task, int event)
+{
+	return task->ptrace & PT_EVENT_FLAG(event);
+}
+
 /**
  * ptrace_event - possibly stop for a ptrace event notification
- * @mask:	%PT_* bit to check in @current->ptrace
- * @event:	%PTRACE_EVENT_* value to report if @mask is set
+ * @event:	%PTRACE_EVENT_* value to report
  * @message:	value for %PTRACE_GETEVENTMSG to return
  *
- * This checks the @mask bit to see if ptrace wants stops for this event.
- * If so we stop, reporting @event and @message to the ptrace parent.
+ * Check whether @event is enabled and, if so, report @event and @message
+ * to the ptrace parent.
  *
  * Returns nonzero if we did a ptrace notification, zero if not.
  *
  * Called without locks.
  */
-static inline int ptrace_event(int mask, int event, unsigned long message)
+static inline int ptrace_event(int event, unsigned long message)
 {
-	if (mask && likely(!(current->ptrace & mask)))
-		return 0;
+	if (likely(!ptrace_event_enabled(current, event)))
+		return false;
 	current->ptrace_message = message;
 	ptrace_notify((event << 8) | SIGTRAP);
-	return 1;
+	return true;
 }
 
 /**
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index a3e838784f4..7d38571b0c0 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -201,7 +201,7 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt,
 					 struct linux_binprm *bprm,
 					 struct pt_regs *regs)
 {
-	if (!ptrace_event(PT_TRACE_EXEC, PTRACE_EVENT_EXEC, 0) &&
+	if (!ptrace_event(PTRACE_EVENT_EXEC, 0) &&
 	    unlikely(current->ptrace & PT_PTRACED))
 		send_sig(SIGTRAP, current, 0);
 }
@@ -218,7 +218,7 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt,
  */
 static inline void tracehook_report_exit(long *exit_code)
 {
-	ptrace_event(PT_TRACE_EXIT, PTRACE_EVENT_EXIT, *exit_code);
+	ptrace_event(PTRACE_EVENT_EXIT, *exit_code);
 }
 
 /**
@@ -232,19 +232,19 @@ static inline void tracehook_report_exit(long *exit_code)
  */
 static inline int tracehook_prepare_clone(unsigned clone_flags)
 {
+	int event = 0;
+
 	if (clone_flags & CLONE_UNTRACED)
 		return 0;
 
-	if (clone_flags & CLONE_VFORK) {
-		if (current->ptrace & PT_TRACE_VFORK)
-			return PTRACE_EVENT_VFORK;
-	} else if ((clone_flags & CSIGNAL) != SIGCHLD) {
-		if (current->ptrace & PT_TRACE_CLONE)
-			return PTRACE_EVENT_CLONE;
-	} else if (current->ptrace & PT_TRACE_FORK)
-		return PTRACE_EVENT_FORK;
+	if (clone_flags & CLONE_VFORK)
+		event = PTRACE_EVENT_VFORK;
+	else if ((clone_flags & CSIGNAL) != SIGCHLD)
+		event = PTRACE_EVENT_CLONE;
+	else
+		event = PTRACE_EVENT_FORK;
 
-	return 0;
+	return ptrace_event_enabled(current, event) ? event : 0;
 }
 
 /**
@@ -318,7 +318,7 @@ static inline void tracehook_report_clone_complete(int trace,
 						   struct task_struct *child)
 {
 	if (unlikely(trace))
-		ptrace_event(0, trace, pid);
+		ptrace_event(trace, pid);
 }
 
 /**
@@ -336,7 +336,7 @@ static inline void tracehook_report_clone_complete(int trace,
 static inline void tracehook_report_vfork_done(struct task_struct *child,
 					       pid_t pid)
 {
-	ptrace_event(PT_TRACE_VFORK_DONE, PTRACE_EVENT_VFORK_DONE, pid);
+	ptrace_event(PTRACE_EVENT_VFORK_DONE, pid);
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From f3c04b934d429b1ace21866f011b66de328c0dc9 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 17 Jun 2011 16:50:36 +0200
Subject: ptrace: move SIGTRAP on exec(2) logic to ptrace_event()

Move SIGTRAP on exec(2) logic from tracehook_report_exec() to
ptrace_event().  This is part of changes to make ptrace_event()
smarter and handle ptrace event related details in one place.

This doesn't introduce any behavior change.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/ptrace.h    | 16 ++++++++--------
 include/linux/tracehook.h |  4 +---
 2 files changed, 9 insertions(+), 11 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 18feac6f441..b546fd6c350 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -172,17 +172,17 @@ static inline bool ptrace_event_enabled(struct task_struct *task, int event)
  * Check whether @event is enabled and, if so, report @event and @message
  * to the ptrace parent.
  *
- * Returns nonzero if we did a ptrace notification, zero if not.
- *
  * Called without locks.
  */
-static inline int ptrace_event(int event, unsigned long message)
+static inline void ptrace_event(int event, unsigned long message)
 {
-	if (likely(!ptrace_event_enabled(current, event)))
-		return false;
-	current->ptrace_message = message;
-	ptrace_notify((event << 8) | SIGTRAP);
-	return true;
+	if (unlikely(ptrace_event_enabled(current, event))) {
+		current->ptrace_message = message;
+		ptrace_notify((event << 8) | SIGTRAP);
+	} else if (event == PTRACE_EVENT_EXEC && unlikely(current->ptrace)) {
+		/* legacy EXEC report via SIGTRAP */
+		send_sig(SIGTRAP, current, 0);
+	}
 }
 
 /**
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 7d38571b0c0..3b68aa842a9 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -201,9 +201,7 @@ static inline void tracehook_report_exec(struct linux_binfmt *fmt,
 					 struct linux_binprm *bprm,
 					 struct pt_regs *regs)
 {
-	if (!ptrace_event(PTRACE_EVENT_EXEC, 0) &&
-	    unlikely(current->ptrace & PT_PTRACED))
-		send_sig(SIGTRAP, current, 0);
+	ptrace_event(PTRACE_EVENT_EXEC, 0);
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From 06d984737bac0545fe20bb5447ee488b95adb531 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 17 Jun 2011 16:50:40 +0200
Subject: ptrace: s/tracehook_tracer_task()/ptrace_parent()/

tracehook.h is on the way out.  Rename tracehook_tracer_task() to
ptrace_parent() and move it from tracehook.h to ptrace.h.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: John Johansen <john.johansen@canonical.com>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 fs/proc/array.c            |  2 +-
 fs/proc/base.c             |  2 +-
 include/linux/ptrace.h     | 18 ++++++++++++++++++
 include/linux/tracehook.h  | 18 ------------------
 security/apparmor/domain.c |  2 +-
 security/selinux/hooks.c   |  4 ++--
 6 files changed, 23 insertions(+), 23 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 9b45ee84fbc..3a1dafd228d 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -172,7 +172,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
 	tpid = 0;
 	if (pid_alive(p)) {
-		struct task_struct *tracer = tracehook_tracer_task(p);
+		struct task_struct *tracer = ptrace_parent(p);
 		if (tracer)
 			tpid = task_pid_nr_ns(tracer, ns);
 	}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 14def991d9d..c883dad74b9 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -216,7 +216,7 @@ static struct mm_struct *__check_mem_permission(struct task_struct *task)
 	if (task_is_stopped_or_traced(task)) {
 		int match;
 		rcu_read_lock();
-		match = (tracehook_tracer_task(task) == current);
+		match = (ptrace_parent(task) == current);
 		rcu_read_unlock();
 		if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
 			return mm;
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index b546fd6c350..bb157bdd0c5 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -150,6 +150,24 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr,
 int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr,
 			    unsigned long data);
 
+/**
+ * ptrace_parent - return the task that is tracing the given task
+ * @task: task to consider
+ *
+ * Returns %NULL if no one is tracing @task, or the &struct task_struct
+ * pointer to its tracer.
+ *
+ * Must called under rcu_read_lock().  The pointer returned might be kept
+ * live only by RCU.  During exec, this may be called with task_lock() held
+ * on @task, still held from when check_unsafe_exec() was called.
+ */
+static inline struct task_struct *ptrace_parent(struct task_struct *task)
+{
+	if (unlikely(task->ptrace))
+		return rcu_dereference(task->parent);
+	return NULL;
+}
+
 /**
  * ptrace_event_enabled - test whether a ptrace event is enabled
  * @task: ptracee of interest
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index bcc4ca762ae..7a1bd12aeff 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -129,24 +129,6 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step)
 	ptrace_report_syscall(regs);
 }
 
-/**
- * tracehook_tracer_task - return the task that is tracing the given task
- * @tsk:		task to consider
- *
- * Returns NULL if no one is tracing @task, or the &struct task_struct
- * pointer to its tracer.
- *
- * Must called under rcu_read_lock().  The pointer returned might be kept
- * live only by RCU.  During exec, this may be called with task_lock()
- * held on @task, still held from when tracehook_unsafe_exec() was called.
- */
-static inline struct task_struct *tracehook_tracer_task(struct task_struct *tsk)
-{
-	if (tsk->ptrace & PT_PTRACED)
-		return rcu_dereference(tsk->parent);
-	return NULL;
-}
-
 /**
  * tracehook_signal_handler - signal handler setup is complete
  * @sig:		number of signal being delivered
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
index c825c6e0b63..7312bf9f7af 100644
--- a/security/apparmor/domain.c
+++ b/security/apparmor/domain.c
@@ -67,7 +67,7 @@ static int may_change_ptraced_domain(struct task_struct *task,
 	int error = 0;
 
 	rcu_read_lock();
-	tracer = tracehook_tracer_task(task);
+	tracer = ptrace_parent(task);
 	if (tracer) {
 		/* released below */
 		cred = get_task_cred(tracer);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index a0d38459d65..fc07d18ed6f 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2048,7 +2048,7 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 			u32 ptsid = 0;
 
 			rcu_read_lock();
-			tracer = tracehook_tracer_task(current);
+			tracer = ptrace_parent(current);
 			if (likely(tracer != NULL)) {
 				sec = __task_cred(tracer)->security;
 				ptsid = sec->sid;
@@ -5314,7 +5314,7 @@ static int selinux_setprocattr(struct task_struct *p,
 		   Otherwise, leave SID unchanged and fail. */
 		ptsid = 0;
 		task_lock(p);
-		tracer = tracehook_tracer_task(p);
+		tracer = ptrace_parent(p);
 		if (tracer)
 			ptsid = task_sid(tracer);
 		task_unlock(p);
-- 
cgit v1.2.3-70-g09d2


From 0347e17739095c58c0194fed6a61aced3536d258 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 24 Jun 2011 17:34:06 +0200
Subject: ptrace: ptrace_reparented() should check same_thread_group()

ptrace_reparented() naively does parent != real_parent, this means
it returns true even if the tracer _is_ the real parent. This is per
process thing, not per-thread. The only reason ->real_parent can
point to the non-leader thread is that we have __WNOTHREAD.

Change it to check !same_thread_group(parent, real_parent).

It has two callers, and in both cases the current check does not
look right.

exit_notify: we should respect ->exit_signal if the exiting leader
is traced by any thread from the parent thread group. It is the
child of the whole group, and we are going to send the signal to
the whole group.

wait_task_zombie: without __WNOTHREAD do_wait() should do the same
for any thread, only sys_ptrace() is "bound" to the single thread.
However do_wait(WEXITED) succeeds but does not release a traced
natural child unless the caller is the tracer.

Test-case:

	void *tfunc(void *arg)
	{
		assert(ptrace(PTRACE_ATTACH, (long)arg, 0,0) == 0);
		pause();
		return NULL;
	}

	int main(void)
	{
		pthread_t thr;
		pid_t pid, stat, ret;

		pid = fork();
		if (!pid) {
			pause();
			assert(0);
		}

		assert(pthread_create(&thr, NULL, tfunc, (void*)(long)pid) == 0);

		assert(waitpid(-1, &stat, 0) == pid);
		assert(WIFSTOPPED(stat));

		kill(pid, SIGKILL);

		assert(waitpid(-1, &stat, 0) == pid);
		assert(WIFSIGNALED(stat) && WTERMSIG(stat) == SIGKILL);

		ret = waitpid(pid, &stat, 0);
		if (ret < 0)
			return 0;

		printf("WTF? %d is dead, but: wait=%d stat=%x\n",
				pid, ret, stat);

		return 1;
	}

Note that the main thread simply does

	pid = fork();
	kill(pid, SIGKILL);

and then without the patch wait4(WEXITED) succeeds twice and reports
WTERMSIG(stat) == SIGKILL.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
---
 include/linux/ptrace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index bb157bdd0c5..eae381d584f 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -136,7 +136,7 @@ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode);
 
 static inline int ptrace_reparented(struct task_struct *child)
 {
-	return child->real_parent != child->parent;
+	return !same_thread_group(child->real_parent, child->parent);
 }
 
 static inline void ptrace_unlink(struct task_struct *child)
-- 
cgit v1.2.3-70-g09d2


From 6634ae1033ceaeca5877dd75723210f8c2648c17 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 8 Jul 2011 19:13:39 +0200
Subject: ptrace_init_task: initialize child->jobctl explicitly

new_child->jobctl is not initialized during the fork, it is copied
from parent->jobctl. Currently this is harmless, the forking task
is running and copy_process() can't succeed if signal_pending() is
true, so only JOBCTL_STOP_DEQUEUED can be copied. Still this is a
bit fragile, it would be more clean to set ->jobctl = 0 explicitly.

Also, check ->ptrace != 0 instead of PT_PTRACED, move the
CONFIG_HAVE_HW_BREAKPOINT code up.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
---
 include/linux/ptrace.h | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index eae381d584f..fd8669fc339 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -217,16 +217,17 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 {
 	INIT_LIST_HEAD(&child->ptrace_entry);
 	INIT_LIST_HEAD(&child->ptraced);
-	child->parent = child->real_parent;
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
+	atomic_set(&child->ptrace_bp_refcnt, 1);
+#endif
+	child->jobctl = 0;
 	child->ptrace = 0;
-	if (unlikely(ptrace) && (current->ptrace & PT_PTRACED)) {
+	child->parent = child->real_parent;
+
+	if (unlikely(ptrace) && current->ptrace) {
 		child->ptrace = current->ptrace;
 		__ptrace_link(child, current->parent);
 	}
-
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-	atomic_set(&child->ptrace_bp_refcnt, 1);
-#endif
 }
 
 /**
-- 
cgit v1.2.3-70-g09d2


From dcace06cc29df927a74a6bc0e57b9bef87704377 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 8 Jul 2011 19:13:54 +0200
Subject: ptrace: mv send-SIGSTOP from do_fork() to ptrace_init_task()

If the new child is traced, do_fork() adds the pending SIGSTOP.
It assumes that either it is traced because of auto-attach or the
tracer attached later, in both cases sigaddset/set_thread_flag is
correct even if SIGSTOP is already pending.

Now that we have PTRACE_SEIZE this is no longer right in the latter
case. If the tracer does PTRACE_SEIZE after copy_process() makes the
child visible the queued SIGSTOP is wrong.

We could check PT_SEIZED bit and change ptrace_attach() to set both
PT_PTRACED and PT_SEIZED bits simultaneously but see the next patch,
we need to know whether this child was auto-attached or not anyway.

So this patch simply moves this code to ptrace_init_task(), this
way we can never race with ptrace_attach().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
---
 include/linux/ptrace.h |  3 +++
 kernel/fork.c          | 12 ------------
 2 files changed, 3 insertions(+), 12 deletions(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index fd8669fc339..9b5d2c901d0 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -227,6 +227,9 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 	if (unlikely(ptrace) && current->ptrace) {
 		child->ptrace = current->ptrace;
 		__ptrace_link(child, current->parent);
+
+		sigaddset(&child->pending.signal, SIGSTOP);
+		set_tsk_thread_flag(child, TIF_SIGPENDING);
 	}
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 3c72a5b321a..4d4117e0150 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -37,7 +37,6 @@
 #include <linux/swap.h>
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
-#include <linux/tracehook.h>
 #include <linux/futex.h>
 #include <linux/compat.h>
 #include <linux/kthread.h>
@@ -1521,17 +1520,6 @@ long do_fork(unsigned long clone_flags,
 
 		audit_finish_fork(p);
 
-		/*
-		 * Child is ready but hasn't started running yet.  Queue
-		 * SIGSTOP if it's gonna be ptraced - it doesn't matter who
-		 * attached/attaching to this task, the pending SIGSTOP is
-		 * right in any case.
-		 */
-		if (unlikely(p->ptrace)) {
-			sigaddset(&p->pending.signal, SIGSTOP);
-			set_tsk_thread_flag(p, TIF_SIGPENDING);
-		}
-
 		/*
 		 * We set PF_STARTING at creation in case tracing wants to
 		 * use this to distinguish a fully live task from one that
-- 
cgit v1.2.3-70-g09d2


From d184d6eb1dc3c9869e25a8e422be5c55ab0db4ac Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 8 Jul 2011 19:14:17 +0200
Subject: ptrace: dont send SIGSTOP on auto-attach if PT_SEIZED

The fake SIGSTOP during attach has numerous problems. PTRACE_SEIZE
is already fine, but we have basically the same problems is SIGSTOP
is sent on auto-attach, the tracer can't know if this signal signal
should be cancelled or not.

Change ptrace_event() to set JOBCTL_TRAP_STOP if the new child is
PT_SEIZED, this triggers the PTRACE_EVENT_STOP report.

Thereafter a PT_SEIZED task can never report the bogus SIGSTOP.

Test-case:

	#define PTRACE_SEIZE		0x4206
	#define PTRACE_SEIZE_DEVEL	0x80000000
	#define PTRACE_EVENT_STOP	7
	#define WEVENT(s)		((s & 0xFF0000) >> 16)

	int main(void)
	{
		int child, grand_child, status;
		long message;

		child = fork();
		if (!child) {
			kill(getpid(), SIGSTOP);
			fork();
			assert(0);
			return 0x23;
		}

		assert(ptrace(PTRACE_SEIZE, child, 0,PTRACE_SEIZE_DEVEL) == 0);
		assert(wait(&status) == child);
		assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGSTOP);

		assert(ptrace(PTRACE_SETOPTIONS, child, 0, PTRACE_O_TRACEFORK) == 0);

		assert(ptrace(PTRACE_CONT, child, 0,0) == 0);
		assert(waitpid(child, &status, 0) == child);
		assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP);
		assert(WEVENT(status) == PTRACE_EVENT_FORK);

		assert(ptrace(PTRACE_GETEVENTMSG, child, 0, &message) == 0);
		grand_child = message;

		assert(waitpid(grand_child, &status, 0) == grand_child);
		assert(WIFSTOPPED(status) && WSTOPSIG(status) == SIGTRAP);
		assert(WEVENT(status) == PTRACE_EVENT_STOP);

		kill(child, SIGKILL);
		kill(grand_child, SIGKILL);
		return 0;
	}

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
---
 include/linux/ptrace.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux/ptrace.h')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 9b5d2c901d0..800f113bea6 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -228,7 +228,11 @@ static inline void ptrace_init_task(struct task_struct *child, bool ptrace)
 		child->ptrace = current->ptrace;
 		__ptrace_link(child, current->parent);
 
-		sigaddset(&child->pending.signal, SIGSTOP);
+		if (child->ptrace & PT_SEIZED)
+			task_set_jobctl_pending(child, JOBCTL_TRAP_STOP);
+		else
+			sigaddset(&child->pending.signal, SIGSTOP);
+
 		set_tsk_thread_flag(child, TIF_SIGPENDING);
 	}
 }
-- 
cgit v1.2.3-70-g09d2