Received-SPF: pass (google.com: domain of linux-kernel+bounces-158704-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: Frederic Weisbecker <frederic@kernel.org>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>,
	"Paul E. McKenney" <paulmck@kernel.org>,
	Boqun Feng <boqun.feng@gmail.com>,
	Joel Fernandes <joel@joelfernandes.org>,
	Neeraj Upadhyay <neeraj.upadhyay@amd.com>,
	Uladzislau Rezki <urezki@gmail.com>,
	Zqiang <qiang.zhang1211@gmail.com>,
	rcu <rcu@vger.kernel.org>,
	Oleg Nesterov <oleg@redhat.com>,
	"Eric W . Biederman" <ebiederm@xmission.com>,
	Lai Jiangshan <jiangshanlai@gmail.com>
Subject: [PATCH] Revert "rcu-tasks: Fix synchronize_rcu_tasks() VS zap_pid_ns_processes()"
Date: Thu, 25 Apr 2024 16:24:04 +0200
Message-ID: <20240425142404.19927-1-frederic@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

This reverts commit 28319d6dc5e2ffefa452c2377dd0f71621b5bff0. The race
it fixed was subject to conditions that don't exist anymore since:

	1612160b9127 ("rcu-tasks: Eliminate deadlocks involving do_exit() and RCU tasks")

This latter commit removes the use of SRCU that used to cover the
RCU-tasks blind spot on exit between the tasklist's removal and the
final preemption disabling. The task is now placed instead into a
temporary list inside which voluntary sleeps are accounted as RCU-tasks
quiescent states. This would disarm the deadlock initially reported
against PID namespace exit.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 include/linux/rcupdate.h |  2 --
 kernel/pid_namespace.c   | 17 -----------------
 kernel/rcu/tasks.h       | 16 +++-------------
 3 files changed, 3 insertions(+), 32 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 8470a85f6563..be450a3477be 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -209,7 +209,6 @@ void synchronize_rcu_tasks_rude(void);
 
 #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false)
 void exit_tasks_rcu_start(void);
-void exit_tasks_rcu_stop(void);
 void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
 #define rcu_tasks_classic_qs(t, preempt) do { } while (0)
@@ -218,7 +217,6 @@ void exit_tasks_rcu_finish(void);
 #define call_rcu_tasks call_rcu
 #define synchronize_rcu_tasks synchronize_rcu
 static inline void exit_tasks_rcu_start(void) { }
-static inline void exit_tasks_rcu_stop(void) { }
 static inline void exit_tasks_rcu_finish(void) { }
 #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 7ade20e95232..20a0b3ceb064 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -248,24 +248,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (pid_ns->pid_allocated == init_pids)
 			break;
-		/*
-		 * Release tasks_rcu_exit_srcu to avoid following deadlock:
-		 *
-		 * 1) TASK A unshare(CLONE_NEWPID)
-		 * 2) TASK A fork() twice -> TASK B (child reaper for new ns)
-		 *    and TASK C
-		 * 3) TASK B exits, kills TASK C, waits for TASK A to reap it
-		 * 4) TASK A calls synchronize_rcu_tasks()
-		 *                   -> synchronize_srcu(tasks_rcu_exit_srcu)
-		 * 5) *DEADLOCK*
-		 *
-		 * It is considered safe to release tasks_rcu_exit_srcu here
-		 * because we assume the current task can not be concurrently
-		 * reaped at this point.
-		 */
-		exit_tasks_rcu_stop();
 		schedule();
-		exit_tasks_rcu_start();
 	}
 	__set_current_state(TASK_RUNNING);
 
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 445561ee4d22..8c9538b555e3 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -858,7 +858,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 //	not know to synchronize with this RCU Tasks grace period) have
 //	completed exiting.  The synchronize_rcu() in rcu_tasks_postgp()
 //	will take care of any tasks stuck in the non-preemptible region
-//	of do_exit() following its call to exit_tasks_rcu_stop().
+//	of do_exit() following its call to exit_tasks_rcu_finish().
 // check_all_holdout_tasks(), repeatedly until holdout list is empty:
 //	Scans the holdout list, attempting to identify a quiescent state
 //	for each task on the list.  If there is a quiescent state, the
@@ -1220,7 +1220,7 @@ void exit_tasks_rcu_start(void)
  * Remove the task from the "yet another list" because do_exit() is now
  * non-preemptible, allowing synchronize_rcu() to wait beyond this point.
  */
-void exit_tasks_rcu_stop(void)
+void exit_tasks_rcu_finish(void)
 {
 	unsigned long flags;
 	struct rcu_tasks_percpu *rtpcp;
@@ -1231,22 +1231,12 @@ void exit_tasks_rcu_stop(void)
 	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
 	list_del_init(&t->rcu_tasks_exit_list);
 	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
-}
 
-/*
- * Contribute to protect against tasklist scan blind spot while the
- * task is exiting and may be removed from the tasklist. See
- * corresponding synchronize_srcu() for further details.
- */
-void exit_tasks_rcu_finish(void)
-{
-	exit_tasks_rcu_stop();
-	exit_tasks_rcu_finish_trace(current);
+	exit_tasks_rcu_finish_trace(t);
 }
 
 #else /* #ifdef CONFIG_TASKS_RCU */
 void exit_tasks_rcu_start(void) { }
-void exit_tasks_rcu_stop(void) { }
 void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
-- 
2.44.0