From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 15 Aug 2022 17:29:50 +0200
Subject: [PATCH] net: Avoid the IPI to free the

skb_attempt_defer_free() collects a skbs, which was allocated on a
remote CPU, on a per-CPU list. These skbs are either freed on that
remote CPU once the CPU enters NET_RX or an remote IPI function is
invoked in to raise the NET_RX softirq if a threshold of pending skb has
been exceeded.
This remote IPI can cause the wakeup of ksoftirqd on PREEMPT_RT if the
remote CPU idle was idle. This is undesired because once the ksoftirqd
is running it will acquire all pending softirqs and they will not be
executed as part of the threaded interrupt until ksoftird goes idle
again.

To void all this, schedule the deferred clean up from a worker.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 include/linux/netdevice.h |    4 ++++
 net/core/dev.c            |   37 ++++++++++++++++++++++++++++---------
 net/core/skbuff.c         |    7 ++++++-
 3 files changed, 38 insertions(+), 10 deletions(-)

--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3156,7 +3156,11 @@ struct softnet_data {
 	int			defer_count;
 	int			defer_ipi_scheduled;
 	struct sk_buff		*defer_list;
+#ifndef CONFIG_PREEMPT_RT
 	call_single_data_t	defer_csd;
+#else
+	struct work_struct	defer_work;
+#endif
 };
 
 static inline void input_queue_head_incr(struct softnet_data *sd)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4582,15 +4582,6 @@ static void rps_trigger_softirq(void *da
 
 #endif /* CONFIG_RPS */
 
-/* Called from hardirq (IPI) context */
-static void trigger_rx_softirq(void *data)
-{
-	struct softnet_data *sd = data;
-
-	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
-	smp_store_release(&sd->defer_ipi_scheduled, 0);
-}
-
 /*
  * Check if this softnet_data structure is another cpu one
  * If yes, queue it to our IPI list and return 1
@@ -6661,6 +6652,30 @@ static void skb_defer_free_flush(struct
 	}
 }
 
+#ifndef CONFIG_PREEMPT_RT
+/* Called from hardirq (IPI) context */
+static void trigger_rx_softirq(void *data)
+{
+	struct softnet_data *sd = data;
+
+	__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+	smp_store_release(&sd->defer_ipi_scheduled, 0);
+}
+
+#else
+
+static void trigger_rx_softirq(struct work_struct *defer_work)
+{
+	struct softnet_data *sd;
+
+	sd = container_of(defer_work, struct softnet_data, defer_work);
+	smp_store_release(&sd->defer_ipi_scheduled, 0);
+	local_bh_disable();
+	skb_defer_free_flush(sd);
+	local_bh_enable();
+}
+#endif
+
 static __latent_entropy void net_rx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -11412,7 +11427,11 @@ static int __init net_dev_init(void)
 		INIT_CSD(&sd->csd, rps_trigger_softirq, sd);
 		sd->cpu = i;
 #endif
+#ifndef CONFIG_PREEMPT_RT
 		INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd);
+#else
+		INIT_WORK(&sd->defer_work, trigger_rx_softirq);
+#endif
 		spin_lock_init(&sd->defer_lock);
 
 		init_gro_hash(&sd->backlog);
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6555,6 +6555,11 @@ nodefer:	__kfree_skb(skb);
 	/* Make sure to trigger NET_RX_SOFTIRQ on the remote CPU
 	 * if we are unlucky enough (this seems very unlikely).
 	 */
-	if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1))
+	if (unlikely(kick) && !cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) {
+#ifndef CONFIG_PREEMPT_RT
 		smp_call_function_single_async(cpu, &sd->defer_csd);
+#else
+		schedule_work_on(cpu, &sd->defer_work);
+#endif
+	}
 }