dev: Use nested-BH locking for softnet_data.process_queue.

softnet_data::process_queue is a per-CPU variable and relies on disabled
BH for its locking. Without per-CPU locking in local_bh_disable() on
PREEMPT_RT this data structure requires explicit locking.

softnet_data::input_queue_head can be updated lockless. This is fine
because this value is only update CPU local by the local backlog_napi
thread.

Add a local_lock_t to softnet_data and use local_lock_nested_bh() for locking
of process_queue. This change adds only lockdep coverage and does not
alter the functional behaviour for !PREEMPT_RT.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20240620132727.660738-11-bigeasy@linutronix.deSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/netdevice.h

@@ -3202,6 +3202,7 @@ static inline bool dev_has_header(const struct net_device *dev)
 struct softnet_data {
 	struct list_head	poll_list;
 	struct sk_buff_head	process_queue;
+	local_lock_t		process_queue_bh_lock;
 
 	/* stats */
 	unsigned int		processed;

net/core/dev.c

@@ -449,7 +449,9 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
  *	queue in the local softnet handler.
  */
 
-DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
+DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = {
+	.process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock),
+};
 EXPORT_PER_CPU_SYMBOL(softnet_data);
 
 /* Page_pool has a lockless array/stack to alloc/recycle pages.
@@ -5949,6 +5951,7 @@ static void flush_backlog(struct work_struct *work)
 	}
 	backlog_unlock_irq_enable(sd);
 
+	local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->process_queue);
@@ -5956,6 +5959,7 @@ static void flush_backlog(struct work_struct *work)
 			rps_input_queue_head_incr(sd);
 		}
 	}
+	local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 	local_bh_enable();
 }
 
@@ -6077,7 +6081,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
 	while (again) {
 		struct sk_buff *skb;
 
+		local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 			rcu_read_lock();
 			__netif_receive_skb(skb);
 			rcu_read_unlock();
@@ -6086,7 +6092,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
 				return work;
 			}
 
+			local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 		}
+		local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 
 		backlog_lock_irq_disable(sd);
 		if (skb_queue_empty(&sd->input_pkt_queue)) {
@@ -6101,8 +6109,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
 			napi->state &= NAPIF_STATE_THREADED;
 			again = false;
 		} else {
+			local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 			skb_queue_splice_tail_init(&sd->input_pkt_queue,
 						   &sd->process_queue);
+			local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 		}
 		backlog_unlock_irq_enable(sd);
 	}