[PATCH 6.10 618/634] lockdep: fix deadlock issue between lockdep and rcu

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



6.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Zhiguo Niu <zhiguo.niu@xxxxxxxxxx>

commit a6f88ac32c6e63e69c595bfae220d8641704c9b7 upstream.

There is a deadlock scenario between lockdep and rcu when
rcu nocb feature is enabled, just as following call stack:

     rcuop/x
-000|queued_spin_lock_slowpath(lock = 0xFFFFFF817F2A8A80, val = ?)
-001|queued_spin_lock(inline) // try to hold nocb_gp_lock
-001|do_raw_spin_lock(lock = 0xFFFFFF817F2A8A80)
-002|__raw_spin_lock_irqsave(inline)
-002|_raw_spin_lock_irqsave(lock = 0xFFFFFF817F2A8A80)
-003|wake_nocb_gp_defer(inline)
-003|__call_rcu_nocb_wake(rdp = 0xFFFFFF817F30B680)
-004|__call_rcu_common(inline)
-004|call_rcu(head = 0xFFFFFFC082EECC28, func = ?)
-005|call_rcu_zapped(inline)
-005|free_zapped_rcu(ch = ?)// hold graph lock
-006|rcu_do_batch(rdp = 0xFFFFFF817F245680)
-007|nocb_cb_wait(inline)
-007|rcu_nocb_cb_kthread(arg = 0xFFFFFF817F245680)
-008|kthread(_create = 0xFFFFFF80803122C0)
-009|ret_from_fork(asm)

     rcuop/y
-000|queued_spin_lock_slowpath(lock = 0xFFFFFFC08291BBC8, val = 0)
-001|queued_spin_lock()
-001|lockdep_lock()
-001|graph_lock() // try to hold graph lock
-002|lookup_chain_cache_add()
-002|validate_chain()
-003|lock_acquire
-004|_raw_spin_lock_irqsave(lock = 0xFFFFFF817F211D80)
-005|lock_timer_base(inline)
-006|mod_timer(inline)
-006|wake_nocb_gp_defer(inline)// hold nocb_gp_lock
-006|__call_rcu_nocb_wake(rdp = 0xFFFFFF817F2A8680)
-007|__call_rcu_common(inline)
-007|call_rcu(head = 0xFFFFFFC0822E0B58, func = ?)
-008|call_rcu_hurry(inline)
-008|rcu_sync_call(inline)
-008|rcu_sync_func(rhp = 0xFFFFFFC0822E0B58)
-009|rcu_do_batch(rdp = 0xFFFFFF817F266680)
-010|nocb_cb_wait(inline)
-010|rcu_nocb_cb_kthread(arg = 0xFFFFFF817F266680)
-011|kthread(_create = 0xFFFFFF8080363740)
-012|ret_from_fork(asm)

rcuop/x and rcuop/y are rcu nocb threads with the same nocb gp thread.
This patch release the graph lock before lockdep call_rcu.

Fixes: a0b0fd53e1e6 ("locking/lockdep: Free lock classes that are no longer in use")
Cc: stable@xxxxxxxxxxxxxxx
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Carlos Llamas <cmllamas@xxxxxxxxxx>
Cc: Bart Van Assche <bvanassche@xxxxxxx>
Signed-off-by: Zhiguo Niu <zhiguo.niu@xxxxxxxxxx>
Signed-off-by: Xuewen Yan <xuewen.yan@xxxxxxxxxx>
Reviewed-by: Waiman Long <longman@xxxxxxxxxx>
Reviewed-by: Carlos Llamas <cmllamas@xxxxxxxxxx>
Reviewed-by: Bart Van Assche <bvanassche@xxxxxxx>
Signed-off-by: Carlos Llamas <cmllamas@xxxxxxxxxx>
Acked-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Signed-off-by: Boqun Feng <boqun.feng@xxxxxxxxx>
Link: https://lore.kernel.org/r/20240620225436.3127927-1-cmllamas@xxxxxxxxxx
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 kernel/locking/lockdep.c |   48 +++++++++++++++++++++++++++++++----------------
 1 file changed, 32 insertions(+), 16 deletions(-)

--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -6184,25 +6184,27 @@ static struct pending_free *get_pending_
 static void free_zapped_rcu(struct rcu_head *cb);
 
 /*
- * Schedule an RCU callback if no RCU callback is pending. Must be called with
- * the graph lock held.
- */
-static void call_rcu_zapped(struct pending_free *pf)
+* See if we need to queue an RCU callback, must called with
+* the lockdep lock held, returns false if either we don't have
+* any pending free or the callback is already scheduled.
+* Otherwise, a call_rcu() must follow this function call.
+*/
+static bool prepare_call_rcu_zapped(struct pending_free *pf)
 {
 	WARN_ON_ONCE(inside_selftest());
 
 	if (list_empty(&pf->zapped))
-		return;
+		return false;
 
 	if (delayed_free.scheduled)
-		return;
+		return false;
 
 	delayed_free.scheduled = true;
 
 	WARN_ON_ONCE(delayed_free.pf + delayed_free.index != pf);
 	delayed_free.index ^= 1;
 
-	call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+	return true;
 }
 
 /* The caller must hold the graph lock. May be called from RCU context. */
@@ -6228,6 +6230,7 @@ static void free_zapped_rcu(struct rcu_h
 {
 	struct pending_free *pf;
 	unsigned long flags;
+	bool need_callback;
 
 	if (WARN_ON_ONCE(ch != &delayed_free.rcu_head))
 		return;
@@ -6239,14 +6242,18 @@ static void free_zapped_rcu(struct rcu_h
 	pf = delayed_free.pf + (delayed_free.index ^ 1);
 	__free_zapped_classes(pf);
 	delayed_free.scheduled = false;
+	need_callback =
+		prepare_call_rcu_zapped(delayed_free.pf + delayed_free.index);
+	lockdep_unlock();
+	raw_local_irq_restore(flags);
 
 	/*
-	 * If there's anything on the open list, close and start a new callback.
-	 */
-	call_rcu_zapped(delayed_free.pf + delayed_free.index);
+	* If there's pending free and its callback has not been scheduled,
+	* queue an RCU callback.
+	*/
+	if (need_callback)
+		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
 
-	lockdep_unlock();
-	raw_local_irq_restore(flags);
 }
 
 /*
@@ -6286,6 +6293,7 @@ static void lockdep_free_key_range_reg(v
 {
 	struct pending_free *pf;
 	unsigned long flags;
+	bool need_callback;
 
 	init_data_structures_once();
 
@@ -6293,10 +6301,11 @@ static void lockdep_free_key_range_reg(v
 	lockdep_lock();
 	pf = get_pending_free();
 	__lockdep_free_key_range(pf, start, size);
-	call_rcu_zapped(pf);
+	need_callback = prepare_call_rcu_zapped(pf);
 	lockdep_unlock();
 	raw_local_irq_restore(flags);
-
+	if (need_callback)
+		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
 	/*
 	 * Wait for any possible iterators from look_up_lock_class() to pass
 	 * before continuing to free the memory they refer to.
@@ -6390,6 +6399,7 @@ static void lockdep_reset_lock_reg(struc
 	struct pending_free *pf;
 	unsigned long flags;
 	int locked;
+	bool need_callback = false;
 
 	raw_local_irq_save(flags);
 	locked = graph_lock();
@@ -6398,11 +6408,13 @@ static void lockdep_reset_lock_reg(struc
 
 	pf = get_pending_free();
 	__lockdep_reset_lock(pf, lock);
-	call_rcu_zapped(pf);
+	need_callback = prepare_call_rcu_zapped(pf);
 
 	graph_unlock();
 out_irq:
 	raw_local_irq_restore(flags);
+	if (need_callback)
+		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
 }
 
 /*
@@ -6446,6 +6458,7 @@ void lockdep_unregister_key(struct lock_
 	struct pending_free *pf;
 	unsigned long flags;
 	bool found = false;
+	bool need_callback = false;
 
 	might_sleep();
 
@@ -6466,11 +6479,14 @@ void lockdep_unregister_key(struct lock_
 	if (found) {
 		pf = get_pending_free();
 		__lockdep_free_key_range(pf, key, 1);
-		call_rcu_zapped(pf);
+		need_callback = prepare_call_rcu_zapped(pf);
 	}
 	lockdep_unlock();
 	raw_local_irq_restore(flags);
 
+	if (need_callback)
+		call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+
 	/* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
 	synchronize_rcu();
 }






[Index of Archives]     [Linux Kernel]     [Kernel Development Newbies]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite Hiking]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux