netdevsim: call napi_schedule from a timer context

The netdevsim driver was experiencing NOHZ tick-stop errors during packet
transmission due to pending softirq work when calling napi_schedule().
This issue was observed when running the netconsole selftest, which
triggered the following error message:

  NOHZ tick-stop error: local softirq work is pending, handler #08!!!

To fix this issue, introduce a timer that schedules napi_schedule()
from a timer context instead of calling it directly from the TX path.

Create an hrtimer for each queue and kick it from the TX path,
which then schedules napi_schedule() from the timer context.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250219-netdevsim-v3-1-811e2b8abc4c@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 9b394ddc5206a7a5ca5440341551aac50c43e20c..a41dc79e9c2e082367af156b10b61f04be8c41fb 100644 (file)
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -87,7 +87,8 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
        if (unlikely(nsim_forward_skb(peer_dev, skb, rq) == NET_RX_DROP))
                goto out_drop_cnt;
 
-       napi_schedule(&rq->napi);
+       if (!hrtimer_active(&rq->napi_timer))
+               hrtimer_start(&rq->napi_timer, us_to_ktime(5), HRTIMER_MODE_REL);
 
        rcu_read_unlock();
        u64_stats_update_begin(&ns->syncp);
@@ -426,6 +427,22 @@ err_pp_destroy:
        return err;
 }
 
+static enum hrtimer_restart nsim_napi_schedule(struct hrtimer *timer)
+{
+       struct nsim_rq *rq;
+
+       rq = container_of(timer, struct nsim_rq, napi_timer);
+       napi_schedule(&rq->napi);
+
+       return HRTIMER_NORESTART;
+}
+
+static void nsim_rq_timer_init(struct nsim_rq *rq)
+{
+       hrtimer_init(&rq->napi_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+       rq->napi_timer.function = nsim_napi_schedule;
+}
+
 static void nsim_enable_napi(struct netdevsim *ns)
 {
        struct net_device *dev = ns->netdev;
@@ -615,11 +632,13 @@ static struct nsim_rq *nsim_queue_alloc(void)
                return NULL;
 
        skb_queue_head_init(&rq->skb_queue);
+       nsim_rq_timer_init(rq);
        return rq;
 }
 
 static void nsim_queue_free(struct nsim_rq *rq)
 {
+       hrtimer_cancel(&rq->napi_timer);
        skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE);
        kfree(rq);
 }

diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 96d54c08043d3a62b0731efd43bc6a313998bf01..e757f85ed8617bb13ed0bf0e367803e4ddbd8e95 100644 (file)
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -97,6 +97,7 @@ struct nsim_rq {
        struct napi_struct napi;
        struct sk_buff_head skb_queue;
        struct page_pool *page_pool;
+       struct hrtimer napi_timer;
 };
 
 struct netdevsim {