[PATCH 5.15.y 2/2] fork: release the files of a failed fork after sched_cancel_fork()

[Sasha Levin <sashal@kernel.org>]

From: Christian Brauner <brauner@kernel.org>

[ Upstream commit 296a98c1fa50778c3b31eebed1a3f903f9684349 ]

Reorder copy_process() cleanup so sched_fork() taking scx_fork_rwsem
scx_pre_fork() is safe and isn't held around exiting files. Right now, a
fork that fails while another thread closed the bpf link fd will
deadlock against its own read side. It also blocks every fork on the
system:

    copy_process()                  holds scx_fork_rwsem for read
      exit_files()
        close_files()
          filp_close_sync()
            bpf_scx_unreg()
              kthread_flush_work()  waits for the disable work
                scx_root_disable()
                  percpu_down_write(&scx_fork_rwsem)

Simply release the child's files after sched_cancel_fork() dropped the
lock. The task starts out as a copy of its parent so p->files points to
the parent's table until copy_files() replaces it. exit_files() must not
run for a fork that failed before that. Clear p->files up front so
exit_files() is a no-op for those and make copy_files() set it
explicitly for CLONE_FILES.

Reported-by: Chris Mason <mason@kernel.org>
Link: https://patch.msgid.link/20260921-work-coredump-fixes-v3-7-8e4adb1619e6@kernel.org
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/fork.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 8f925267e9c2d..032b969e32b18 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1567,6 +1567,7 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
 
 	if (clone_flags & CLONE_FILES) {
 		atomic_inc(&oldf->count);
+		tsk->files = oldf;
 		return 0;
 	}
 
@@ -2199,6 +2200,8 @@ static __latent_entropy struct task_struct *copy_process(
 	INIT_LIST_HEAD(&p->sibling);
 	rcu_copy_process(p);
 	p->vfork_done = NULL;
+	/* Set by copy_files(), exit_files() on the error path skips NULL. */
+	p->files = NULL;
 	spin_lock_init(&p->alloc_lock);
 
 	init_sigpending(&p->pending);
@@ -2297,7 +2300,7 @@ static __latent_entropy struct task_struct *copy_process(
 		goto bad_fork_cleanup_semundo;
 	retval = copy_fs(clone_flags, p);
 	if (retval)
-		goto bad_fork_cleanup_files;
+		goto bad_fork_cleanup_semundo;
 	retval = copy_sighand(clone_flags, p);
 	if (retval)
 		goto bad_fork_cleanup_fs;
@@ -2571,8 +2574,6 @@ static __latent_entropy struct task_struct *copy_process(
 	__cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:
 	exit_fs(p); /* blocking */
-bad_fork_cleanup_files:
-	exit_files(p); /* blocking */
 bad_fork_cleanup_semundo:
 	exit_sem(p);
 bad_fork_cleanup_security:
@@ -2583,6 +2584,8 @@ static __latent_entropy struct task_struct *copy_process(
 	perf_event_free_task(p);
 bad_fork_sched_cancel_fork:
 	sched_cancel_fork(p);
+	/* ->release() of a file may need scx_fork_rwsem for write. */
+	exit_files(p); /* blocking */
 bad_fork_cleanup_policy:
 	lockdep_free_task(p);
 #ifdef CONFIG_NUMA
-- 
2.53.0