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, 28 insertions, 59 deletions

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 49c29baf9907..156a99283b11 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -185,7 +185,12 @@ static bool looks_like_a_spurious_pid(struct task_struct *task)
 	return true;
 }
 
-/* Ensure that nothing can wake it up, even SIGKILL */
+/*
+ * Ensure that nothing can wake it up, even SIGKILL
+ *
+ * A task is switched to this state while a ptrace operation is in progress;
+ * such that the ptrace operation is uninterruptible.
+ */
 static bool ptrace_freeze_traced(struct task_struct *task)
 {
 	bool ret = false;
@@ -197,7 +202,7 @@ static bool ptrace_freeze_traced(struct task_struct *task)
 	spin_lock_irq(&task->sighand->siglock);
 	if (task_is_traced(task) && !looks_like_a_spurious_pid(task) &&
 	    !__fatal_signal_pending(task)) {
-		WRITE_ONCE(task->__state, __TASK_TRACED);
+		task->jobctl |= JOBCTL_PTRACE_FROZEN;
 		ret = true;
 	}
 	spin_unlock_irq(&task->sighand->siglock);
@@ -207,23 +212,21 @@ static bool ptrace_freeze_traced(struct task_struct *task)
 
 static void ptrace_unfreeze_traced(struct task_struct *task)
 {
-	if (READ_ONCE(task->__state) != __TASK_TRACED)
-		return;
-
-	WARN_ON(!task->ptrace || task->parent != current);
+	unsigned long flags;
 
 	/*
-	 * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
-	 * Recheck state under the lock to close this race.
+	 * The child may be awake and may have cleared
+	 * JOBCTL_PTRACE_FROZEN (see ptrace_resume).  The child will
+	 * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew.
 	 */
-	spin_lock_irq(&task->sighand->siglock);
-	if (READ_ONCE(task->__state) == __TASK_TRACED) {
-		if (__fatal_signal_pending(task))
+	if (lock_task_sighand(task, &flags)) {
+		task->jobctl &= ~JOBCTL_PTRACE_FROZEN;
+		if (__fatal_signal_pending(task)) {
+			task->jobctl &= ~TASK_TRACED;
 			wake_up_state(task, __TASK_TRACED);
-		else
-			WRITE_ONCE(task->__state, TASK_TRACED);
+		}
+		unlock_task_sighand(task, &flags);
 	}
-	spin_unlock_irq(&task->sighand->siglock);
 }
 
 /**
@@ -256,7 +259,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	 */
 	read_lock(&tasklist_lock);
 	if (child->ptrace && child->parent == current) {
-		WARN_ON(READ_ONCE(child->__state) == __TASK_TRACED);
 		/*
 		 * child->sighand can't be NULL, release_task()
 		 * does ptrace_unlink() before __exit_signal().
@@ -266,17 +268,9 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
 	}
 	read_unlock(&tasklist_lock);
 
-	if (!ret && !ignore_state) {
-		if (!wait_task_inactive(child, __TASK_TRACED)) {
-			/*
-			 * This can only happen if may_ptrace_stop() fails and
-			 * ptrace_stop() changes ->state back to TASK_RUNNING,
-			 * so we should not worry about leaking __TASK_TRACED.
-			 */
-			WARN_ON(READ_ONCE(child->__state) == __TASK_TRACED);
-			ret = -ESRCH;
-		}
-	}
+	if (!ret && !ignore_state &&
+	    WARN_ON_ONCE(!wait_task_inactive(child, __TASK_TRACED)))
+		ret = -ESRCH;
 
 	return ret;
 }
@@ -475,8 +469,10 @@ static int ptrace_attach(struct task_struct *task, long request,
 	 * in and out of STOPPED are protected by siglock.
 	 */
 	if (task_is_stopped(task) &&
-	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING))
+	    task_set_jobctl_pending(task, JOBCTL_TRAP_STOP | JOBCTL_TRAPPING)) {
+		task->jobctl &= ~JOBCTL_STOPPED;
 		signal_wake_up_state(task, __TASK_STOPPED);
+	}
 
 	spin_unlock(&task->sighand->siglock);
 
@@ -846,8 +842,6 @@ static long ptrace_get_rseq_configuration(struct task_struct *task,
 static int ptrace_resume(struct task_struct *child, long request,
 			 unsigned long data)
 {
-	bool need_siglock;
-
 	if (!valid_signal(data))
 		return -EIO;
 
@@ -883,18 +877,12 @@ static int ptrace_resume(struct task_struct *child, long request,
 	 * Note that we need siglock even if ->exit_code == data and/or this
 	 * status was not reported yet, the new status must not be cleared by
 	 * wait_task_stopped() after resume.
-	 *
-	 * If data == 0 we do not care if wait_task_stopped() reports the old
-	 * status and clears the code too; this can't race with the tracee, it
-	 * takes siglock after resume.
 	 */
-	need_siglock = data && !thread_group_empty(current);
-	if (need_siglock)
-		spin_lock_irq(&child->sighand->siglock);
+	spin_lock_irq(&child->sighand->siglock);
 	child->exit_code = data;
+	child->jobctl &= ~JOBCTL_TRACED;
 	wake_up_state(child, __TASK_TRACED);
-	if (need_siglock)
-		spin_unlock_irq(&child->sighand->siglock);
+	spin_unlock_irq(&child->sighand->siglock);
 
 	return 0;
 }
@@ -1230,9 +1218,8 @@ int ptrace_request(struct task_struct *child, long request,
 		return ptrace_resume(child, request, data);
 
 	case PTRACE_KILL:
-		if (child->exit_state)	/* already dead */
-			return 0;
-		return ptrace_resume(child, request, SIGKILL);
+		send_sig_info(SIGKILL, SEND_SIG_NOINFO, child);
+		return 0;
 
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK
 	case PTRACE_GETREGSET:
@@ -1279,10 +1266,6 @@ int ptrace_request(struct task_struct *child, long request,
 	return ret;
 }
 
-#ifndef arch_ptrace_attach
-#define arch_ptrace_attach(child)	do { } while (0)
-#endif
-
 SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
 		unsigned long, data)
 {
@@ -1291,8 +1274,6 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
 
 	if (request == PTRACE_TRACEME) {
 		ret = ptrace_traceme();
-		if (!ret)
-			arch_ptrace_attach(current);
 		goto out;
 	}
 
@@ -1304,12 +1285,6 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr,
 
 	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
 		ret = ptrace_attach(child, request, addr, data);
-		/*
-		 * Some architectures need to do book-keeping after
-		 * a ptrace attach.
-		 */
-		if (!ret)
-			arch_ptrace_attach(child);
 		goto out_put_task_struct;
 	}
 
@@ -1449,12 +1424,6 @@ COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid,
 
 	if (request == PTRACE_ATTACH || request == PTRACE_SEIZE) {
 		ret = ptrace_attach(child, request, addr, data);
-		/*
-		 * Some architectures need to do book-keeping after
-		 * a ptrace attach.
-		 */
-		if (!ret)
-			arch_ptrace_attach(child);
 		goto out_put_task_struct;
 	}