Merge branch 'per_signal_struct_coredumps-for-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull per signal_struct coredumps from Eric Biederman:
 "Current coredumps are mixed up with the exit code, the signal handling
  code, and the ptrace code making coredumps much more complicated than
  necessary and difficult to follow.

  This series of changes starts with ptrace_stop and cleans it up,
  making it easier to follow what is happening in ptrace_stop. Then
  cleans up the exec interactions with coredumps. Then cleans up the
  coredump interactions with exit. Finally the coredump interactions
  with the signal handling code is cleaned up.

  The first and last changes are bug fixes for minor bugs.

  I believe the fact that vfork followed by execve can kill the process
  the called vfork if exec fails is sufficient justification to change
  the userspace visible behavior.

  In previous discussions some of these changes were organized
  differently and individually appeared to make the code base worse. As
  currently written I believe they all stand on their own as cleanups
  and bug fixes.

  Which means that even if the worst should happen and the last change
  needs to be reverted for some unimaginable reason, the code base will
  still be improved.

  If the worst does not happen there are a more cleanups that can be
  made. Signals that generate coredumps can easily become eligible for
  short circuit delivery in complete_signal. The entire rendezvous for
  generating a coredump can move into get_signal. The function
  force_sig_info_to_task be written in a way that does not modify the
  signal handling state of the target task (because coredumps are
  eligible for short circuit delivery). Many of these future cleanups
  can be done another way but nothing so cleanly as if coredumps become
  per signal_struct"

* 'per_signal_struct_coredumps-for-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  coredump: Limit coredumps to a single thread group
  coredump:  Don't perform any cleanups before dumping core
  exit: Factor coredump_exit_mm out of exit_mm
  exec: Check for a pending fatal signal instead of core_state
  ptrace: Remove the unnecessary arguments from arch_ptrace_stop
  signal: Remove the bogus sigkill_pending in ptrace_stop

1 files changed, 41 insertions, 35 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 50f1692c732d..f702a6a63686 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -340,6 +340,46 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
 	}
 }
 
+static void coredump_task_exit(struct task_struct *tsk)
+{
+	struct core_state *core_state;
+
+	/*
+	 * Serialize with any possible pending coredump.
+	 * We must hold siglock around checking core_state
+	 * and setting PF_POSTCOREDUMP.  The core-inducing thread
+	 * will increment ->nr_threads for each thread in the
+	 * group without PF_POSTCOREDUMP set.
+	 */
+	spin_lock_irq(&tsk->sighand->siglock);
+	tsk->flags |= PF_POSTCOREDUMP;
+	core_state = tsk->signal->core_state;
+	spin_unlock_irq(&tsk->sighand->siglock);
+	if (core_state) {
+		struct core_thread self;
+
+		self.task = current;
+		if (self.task->flags & PF_SIGNALED)
+			self.next = xchg(&core_state->dumper.next, &self);
+		else
+			self.task = NULL;
+		/*
+		 * Implies mb(), the result of xchg() must be visible
+		 * to core_state->dumper.
+		 */
+		if (atomic_dec_and_test(&core_state->nr_threads))
+			complete(&core_state->startup);
+
+		for (;;) {
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			if (!self.task) /* see coredump_finish() */
+				break;
+			freezable_schedule();
+		}
+		__set_current_state(TASK_RUNNING);
+	}
+}
+
 #ifdef CONFIG_MEMCG
 /*
  * A task is exiting.   If it owned this mm, find a new owner for the mm.
@@ -435,47 +475,12 @@ assign_new_owner:
 static void exit_mm(void)
 {
 	struct mm_struct *mm = current->mm;
-	struct core_state *core_state;
 
 	exit_mm_release(current, mm);
 	if (!mm)
 		return;
 	sync_mm_rss(mm);
-	/*
-	 * Serialize with any possible pending coredump.
-	 * We must hold mmap_lock around checking core_state
-	 * and clearing tsk->mm.  The core-inducing thread
-	 * will increment ->nr_threads for each thread in the
-	 * group with ->mm != NULL.
-	 */
 	mmap_read_lock(mm);
-	core_state = mm->core_state;
-	if (core_state) {
-		struct core_thread self;
-
-		mmap_read_unlock(mm);
-
-		self.task = current;
-		if (self.task->flags & PF_SIGNALED)
-			self.next = xchg(&core_state->dumper.next, &self);
-		else
-			self.task = NULL;
-		/*
-		 * Implies mb(), the result of xchg() must be visible
-		 * to core_state->dumper.
-		 */
-		if (atomic_dec_and_test(&core_state->nr_threads))
-			complete(&core_state->startup);
-
-		for (;;) {
-			set_current_state(TASK_UNINTERRUPTIBLE);
-			if (!self.task) /* see coredump_finish() */
-				break;
-			freezable_schedule();
-		}
-		__set_current_state(TASK_RUNNING);
-		mmap_read_lock(mm);
-	}
 	mmgrab(mm);
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
@@ -763,6 +768,7 @@ void __noreturn do_exit(long code)
 	profile_task_exit(tsk);
 	kcov_task_exit(tsk);
 
+	coredump_task_exit(tsk);
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 
 	validate_creds_for_do_exit(tsk);