Merge tag 'ptrace_stop-cleanup-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull ptrace_stop cleanups from Eric Biederman:
 "While looking at the ptrace problems with PREEMPT_RT and the problems
  Peter Zijlstra was encountering with ptrace in his freezer rewrite I
  identified some cleanups to ptrace_stop that make sense on their own
  and move make resolving the other problems much simpler.

  The biggest issue is the habit of the ptrace code to change
  task->__state from the tracer to suppress TASK_WAKEKILL from waking up
  the tracee. No other code in the kernel does that and it is straight
  forward to update signal_wake_up and friends to make that unnecessary.

  Peter's task freezer sets frozen tasks to a new state TASK_FROZEN and
  then it stores them by calling "wake_up_state(t, TASK_FROZEN)" relying
  on the fact that all stopped states except the special stop states can
  tolerate spurious wake up and recover their state.

  The state of stopped and traced tasked is changed to be stored in
  task->jobctl as well as in task->__state. This makes it possible for
  the freezer to recover tasks in these special states, as well as
  serving as a general cleanup. With a little more work in that
  direction I believe TASK_STOPPED can learn to tolerate spurious wake
  ups and become an ordinary stop state.

  The TASK_TRACED state has to remain a special state as the registers
  for a process are only reliably available when the process is stopped
  in the scheduler. Fundamentally ptrace needs acess to the saved
  register values of a task.

  There are bunch of semi-random ptrace related cleanups that were found
  while looking at these issues.

  One cleanup that deserves to be called out is from commit 57b6de08b5f6
  ("ptrace: Admit ptrace_stop can generate spuriuos SIGTRAPs"). This
  makes a change that is technically user space visible, in the handling
  of what happens to a tracee when a tracer dies unexpectedly. According
  to our testing and our understanding of userspace nothing cares that
  spurious SIGTRAPs can be generated in that case"

* tag 'ptrace_stop-cleanup-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state
  ptrace: Always take siglock in ptrace_resume
  ptrace: Don't change __state
  ptrace: Admit ptrace_stop can generate spuriuos SIGTRAPs
  ptrace: Document that wait_task_inactive can't fail
  ptrace: Reimplement PTRACE_KILL by always sending SIGKILL
  signal: Use lockdep_assert_held instead of assert_spin_locked
  ptrace: Remove arch_ptrace_attach
  ptrace/xtensa: Replace PT_SINGLESTEP with TIF_SINGLESTEP
  ptrace/um: Replace PT_DTRACE with TIF_SINGLESTEP
  signal: Replace __group_send_sig_info with send_signal_locked
  signal: Rename send_signal send_signal_locked

1 files changed, 61 insertions, 79 deletions

diff --git a/kernel/signal.c b/kernel/signal.c
index e43bc2a692f5..edb1dc9b00dc 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -762,7 +762,10 @@ still_pending:
  */
 void signal_wake_up_state(struct task_struct *t, unsigned int state)
 {
+	lockdep_assert_held(&t->sighand->siglock);
+
 	set_tsk_thread_flag(t, TIF_SIGPENDING);
+
 	/*
 	 * TASK_WAKEKILL also means wake it up in the stopped/traced/killable
 	 * case. We don't check t->state here because there is a race with it
@@ -884,7 +887,7 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info,
 static void ptrace_trap_notify(struct task_struct *t)
 {
 	WARN_ON_ONCE(!(t->ptrace & PT_SEIZED));
-	assert_spin_locked(&t->sighand->siglock);
+	lockdep_assert_held(&t->sighand->siglock);
 
 	task_set_jobctl_pending(t, JOBCTL_TRAP_NOTIFY);
 	ptrace_signal_wake_up(t, t->jobctl & JOBCTL_LISTENING);
@@ -930,9 +933,10 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force)
 		for_each_thread(p, t) {
 			flush_sigqueue_mask(&flush, &t->pending);
 			task_clear_jobctl_pending(t, JOBCTL_STOP_PENDING);
-			if (likely(!(t->ptrace & PT_SEIZED)))
+			if (likely(!(t->ptrace & PT_SEIZED))) {
+				t->jobctl &= ~JOBCTL_STOPPED;
 				wake_up_state(t, __TASK_STOPPED);
-			else
+			} else
 				ptrace_trap_notify(t);
 		}
 
@@ -1071,15 +1075,15 @@ static inline bool legacy_queue(struct sigpending *signals, int sig)
 	return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
 }
 
-static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t,
-			enum pid_type type, bool force)
+static int __send_signal_locked(int sig, struct kernel_siginfo *info,
+				struct task_struct *t, enum pid_type type, bool force)
 {
 	struct sigpending *pending;
 	struct sigqueue *q;
 	int override_rlimit;
 	int ret = 0, result;
 
-	assert_spin_locked(&t->sighand->siglock);
+	lockdep_assert_held(&t->sighand->siglock);
 
 	result = TRACE_SIGNAL_IGNORED;
 	if (!prepare_signal(sig, t, force))
@@ -1212,8 +1216,8 @@ static inline bool has_si_pid_and_uid(struct kernel_siginfo *info)
 	return ret;
 }
 
-static int send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t,
-			enum pid_type type)
+int send_signal_locked(int sig, struct kernel_siginfo *info,
+		       struct task_struct *t, enum pid_type type)
 {
 	/* Should SIGKILL or SIGSTOP be received by a pid namespace init? */
 	bool force = false;
@@ -1245,7 +1249,7 @@ static int send_signal(int sig, struct kernel_siginfo *info, struct task_struct
 			force = true;
 		}
 	}
-	return __send_signal(sig, info, t, type, force);
+	return __send_signal_locked(sig, info, t, type, force);
 }
 
 static void print_fatal_signal(int signr)
@@ -1281,12 +1285,6 @@ static int __init setup_print_fatal_signals(char *str)
 
 __setup("print-fatal-signals=", setup_print_fatal_signals);
 
-int
-__group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p)
-{
-	return send_signal(sig, info, p, PIDTYPE_TGID);
-}
-
 int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p,
 			enum pid_type type)
 {
@@ -1294,7 +1292,7 @@ int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p
 	int ret = -ESRCH;
 
 	if (lock_task_sighand(p, &flags)) {
-		ret = send_signal(sig, info, p, type);
+		ret = send_signal_locked(sig, info, p, type);
 		unlock_task_sighand(p, &flags);
 	}
 
@@ -1347,7 +1345,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
 	if (action->sa.sa_handler == SIG_DFL &&
 	    (!t->ptrace || (handler == HANDLER_EXIT)))
 		t->signal->flags &= ~SIGNAL_UNKILLABLE;
-	ret = send_signal(sig, info, t, PIDTYPE_PID);
+	ret = send_signal_locked(sig, info, t, PIDTYPE_PID);
 	spin_unlock_irqrestore(&t->sighand->siglock, flags);
 
 	return ret;
@@ -1567,7 +1565,7 @@ int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr,
 
 	if (sig) {
 		if (lock_task_sighand(p, &flags)) {
-			ret = __send_signal(sig, &info, p, PIDTYPE_TGID, false);
+			ret = __send_signal_locked(sig, &info, p, PIDTYPE_TGID, false);
 			unlock_task_sighand(p, &flags);
 		} else
 			ret = -ESRCH;
@@ -2114,7 +2112,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 	 * parent's namespaces.
 	 */
 	if (valid_signal(sig) && sig)
-		__send_signal(sig, &info, tsk->parent, PIDTYPE_TGID, false);
+		__send_signal_locked(sig, &info, tsk->parent, PIDTYPE_TGID, false);
 	__wake_up_parent(tsk, tsk->parent);
 	spin_unlock_irqrestore(&psig->siglock, flags);
 
@@ -2184,7 +2182,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 	spin_lock_irqsave(&sighand->siglock, flags);
 	if (sighand->action[SIGCHLD-1].sa.sa_handler != SIG_IGN &&
 	    !(sighand->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
-		__group_send_sig_info(SIGCHLD, &info, parent);
+		send_signal_locked(SIGCHLD, &info, parent, PIDTYPE_TGID);
 	/*
 	 * Even if SIGCHLD is not generated, we must wake up wait4 calls.
 	 */
@@ -2204,13 +2202,12 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
  * with.  If the code did not stop because the tracer is gone,
  * the stop signal remains unchanged unless clear_code.
  */
-static int ptrace_stop(int exit_code, int why, int clear_code,
-			unsigned long message, kernel_siginfo_t *info)
+static int ptrace_stop(int exit_code, int why, unsigned long message,
+		       kernel_siginfo_t *info)
 	__releases(&current->sighand->siglock)
 	__acquires(&current->sighand->siglock)
 {
 	bool gstop_done = false;
-	bool read_code = true;
 
 	if (arch_ptrace_stop_needed()) {
 		/*
@@ -2227,10 +2224,16 @@ static int ptrace_stop(int exit_code, int why, int clear_code,
 	}
 
 	/*
-	 * schedule() will not sleep if there is a pending signal that
-	 * can awaken the task.
+	 * After this point ptrace_signal_wake_up or signal_wake_up
+	 * will clear TASK_TRACED if ptrace_unlink happens or a fatal
+	 * signal comes in.  Handle previous ptrace_unlinks and fatal
+	 * signals here to prevent ptrace_stop sleeping in schedule.
 	 */
+	if (!current->ptrace || __fatal_signal_pending(current))
+		return exit_code;
+
 	set_special_state(TASK_TRACED);
+	current->jobctl |= JOBCTL_TRACED;
 
 	/*
 	 * We're committing to trapping.  TRACED should be visible before
@@ -2276,54 +2279,33 @@ static int ptrace_stop(int exit_code, int why, int clear_code,
 
 	spin_unlock_irq(&current->sighand->siglock);
 	read_lock(&tasklist_lock);
-	if (likely(current->ptrace)) {
-		/*
-		 * Notify parents of the stop.
-		 *
-		 * While ptraced, there are two parents - the ptracer and
-		 * the real_parent of the group_leader.  The ptracer should
-		 * know about every stop while the real parent is only
-		 * interested in the completion of group stop.  The states
-		 * for the two don't interact with each other.  Notify
-		 * separately unless they're gonna be duplicates.
-		 */
+	/*
+	 * Notify parents of the stop.
+	 *
+	 * While ptraced, there are two parents - the ptracer and
+	 * the real_parent of the group_leader.  The ptracer should
+	 * know about every stop while the real parent is only
+	 * interested in the completion of group stop.  The states
+	 * for the two don't interact with each other.  Notify
+	 * separately unless they're gonna be duplicates.
+	 */
+	if (current->ptrace)
 		do_notify_parent_cldstop(current, true, why);
-		if (gstop_done && ptrace_reparented(current))
-			do_notify_parent_cldstop(current, false, why);
+	if (gstop_done && (!current->ptrace || ptrace_reparented(current)))
+		do_notify_parent_cldstop(current, false, why);
 
-		/*
-		 * Don't want to allow preemption here, because
-		 * sys_ptrace() needs this task to be inactive.
-		 *
-		 * XXX: implement read_unlock_no_resched().
-		 */
-		preempt_disable();
-		read_unlock(&tasklist_lock);
-		cgroup_enter_frozen();
-		preempt_enable_no_resched();
-		freezable_schedule();
-		cgroup_leave_frozen(true);
-	} else {
-		/*
-		 * By the time we got the lock, our tracer went away.
-		 * Don't drop the lock yet, another tracer may come.
-		 *
-		 * If @gstop_done, the ptracer went away between group stop
-		 * completion and here.  During detach, it would have set
-		 * JOBCTL_STOP_PENDING on us and we'll re-enter
-		 * TASK_STOPPED in do_signal_stop() on return, so notifying
-		 * the real parent of the group stop completion is enough.
-		 */
-		if (gstop_done)
-			do_notify_parent_cldstop(current, false, why);
-
-		/* tasklist protects us from ptrace_freeze_traced() */
-		__set_current_state(TASK_RUNNING);
-		read_code = false;
-		if (clear_code)
-			exit_code = 0;
-		read_unlock(&tasklist_lock);
-	}
+	/*
+	 * Don't want to allow preemption here, because
+	 * sys_ptrace() needs this task to be inactive.
+	 *
+	 * XXX: implement read_unlock_no_resched().
+	 */
+	preempt_disable();
+	read_unlock(&tasklist_lock);
+	cgroup_enter_frozen();
+	preempt_enable_no_resched();
+	freezable_schedule();
+	cgroup_leave_frozen(true);
 
 	/*
 	 * We are back.  Now reacquire the siglock before touching
@@ -2331,14 +2313,13 @@ static int ptrace_stop(int exit_code, int why, int clear_code,
 	 * any signal-sending on another CPU that wants to examine it.
 	 */
 	spin_lock_irq(&current->sighand->siglock);
-	if (read_code)
-		exit_code = current->exit_code;
+	exit_code = current->exit_code;
 	current->last_siginfo = NULL;
 	current->ptrace_message = 0;
 	current->exit_code = 0;
 
 	/* LISTENING can be set only during STOP traps, clear it */
-	current->jobctl &= ~JOBCTL_LISTENING;
+	current->jobctl &= ~(JOBCTL_LISTENING | JOBCTL_PTRACE_FROZEN);
 
 	/*
 	 * Queued signals ignored us while we were stopped for tracing.
@@ -2360,7 +2341,7 @@ static int ptrace_do_notify(int signr, int exit_code, int why, unsigned long mes
 	info.si_uid = from_kuid_munged(current_user_ns(), current_uid());
 
 	/* Let the debugger run.  */
-	return ptrace_stop(exit_code, why, 1, message, &info);
+	return ptrace_stop(exit_code, why, message, &info);
 }
 
 int ptrace_notify(int exit_code, unsigned long message)
@@ -2471,6 +2452,7 @@ static bool do_signal_stop(int signr)
 		if (task_participate_group_stop(current))
 			notify = CLD_STOPPED;
 
+		current->jobctl |= JOBCTL_STOPPED;
 		set_special_state(TASK_STOPPED);
 		spin_unlock_irq(&current->sighand->siglock);
 
@@ -2532,7 +2514,7 @@ static void do_jobctl_trap(void)
 				 CLD_STOPPED, 0);
 	} else {
 		WARN_ON_ONCE(!signr);
-		ptrace_stop(signr, CLD_STOPPED, 0, 0, NULL);
+		ptrace_stop(signr, CLD_STOPPED, 0, NULL);
 	}
 }
 
@@ -2585,7 +2567,7 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type)
 	 * comment in dequeue_signal().
 	 */
 	current->jobctl |= JOBCTL_STOP_DEQUEUED;
-	signr = ptrace_stop(signr, CLD_TRAPPED, 0, 0, info);
+	signr = ptrace_stop(signr, CLD_TRAPPED, 0, info);
 
 	/* We're back.  Did the debugger cancel the sig?  */
 	if (signr == 0)
@@ -2612,7 +2594,7 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type)
 	/* If the (new) signal is now blocked, requeue it.  */
 	if (sigismember(&current->blocked, signr) ||
 	    fatal_signal_pending(current)) {
-		send_signal(signr, info, current, type);
+		send_signal_locked(signr, info, current, type);
 		signr = 0;
 	}
 
@@ -4807,7 +4789,7 @@ void kdb_send_sig(struct task_struct *t, int sig)
 			   "the deadlock.\n");
 		return;
 	}
-	ret = send_signal(sig, SEND_SIG_PRIV, t, PIDTYPE_PID);
+	ret = send_signal_locked(sig, SEND_SIG_PRIV, t, PIDTYPE_PID);
 	spin_unlock(&t->sighand->siglock);
 	if (ret)
 		kdb_printf("Fail to deliver Signal %d to process %d.\n",