coredump: Don't perform any cleanups before dumping core

Rename coredump_exit_mm to coredump_task_exit and call it from do_exit
before PTRACE_EVENT_EXIT, and before any cleanup work for a task
happens.  This ensures that an accurate copy of the process can be
captured in the coredump as no cleanup for the process happens before
the coredump completes.  This also ensures that PTRACE_EVENT_EXIT
will not be visited by any thread until the coredump is complete.

Add a new flag PF_POSTCOREDUMP so that tasks that have passed through
coredump_task_exit can be recognized and ignored in zap_process.

Now that all of the coredumping happens before exit_mm remove code to
test for a coredump in progress from mm_release.

Replace "may_ptrace_stop()" with a simple test of "current->ptrace".
The other tests in may_ptrace_stop all concern avoiding stopping
during a coredump.  These tests are no longer necessary as it is now
guaranteed that fatal_signal_pending will be set if the code enters
ptrace_stop during a coredump.  The code in ptrace_stop is guaranteed
not to stop if fatal_signal_pending returns true.

Until this change "ptrace_event(PTRACE_EVENT_EXIT)" could call
ptrace_stop without fatal_signal_pending being true, as signals are
dequeued in get_signal before calling do_exit.  This is no longer
an issue as "ptrace_event(PTRACE_EVENT_EXIT)" is no longer reached
until after the coredump completes.

Link: https://lkml.kernel.org/r/874kaax26c.fsf@disp2133
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

1 files changed, 12 insertions, 7 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index cb1619d8fd64..774e6b5061b8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -339,23 +339,29 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
 	}
 }
 
-static void coredump_exit_mm(struct mm_struct *mm)
+static void coredump_task_exit(struct task_struct *tsk)
 {
 	struct core_state *core_state;
+	struct mm_struct *mm;
+
+	mm = tsk->mm;
+	if (!mm)
+		return;
 
 	/*
 	 * Serialize with any possible pending coredump.
 	 * We must hold mmap_lock around checking core_state
-	 * and clearing tsk->mm.  The core-inducing thread
+	 * and setting PF_POSTCOREDUMP.  The core-inducing thread
 	 * will increment ->nr_threads for each thread in the
-	 * group with ->mm != NULL.
+	 * group without PF_POSTCOREDUMP set.
 	 */
+	mmap_read_lock(mm);
+	tsk->flags |= PF_POSTCOREDUMP;
 	core_state = mm->core_state;
+	mmap_read_unlock(mm);
 	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);
@@ -375,7 +381,6 @@ static void coredump_exit_mm(struct mm_struct *mm)
 			freezable_schedule();
 		}
 		__set_current_state(TASK_RUNNING);
-		mmap_read_lock(mm);
 	}
 }
 
@@ -480,7 +485,6 @@ static void exit_mm(void)
 		return;
 	sync_mm_rss(mm);
 	mmap_read_lock(mm);
-	coredump_exit_mm(mm);
 	mmgrab(mm);
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
@@ -768,6 +772,7 @@ 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);