net: Use backlog-NAPI to clean up the defer_list.

The defer_list is a per-CPU list which is used to free skbs outside of
the socket lock and on the CPU on which they have been allocated.
The list is processed during NAPI callbacks so ideally the list is
cleaned up.
Should the amount of skbs on the list exceed a certain water mark then
the softirq is triggered remotely on the target CPU by invoking a remote
function call. The raise of the softirqs via a remote function call
leads to waking the ksoftirqd on PREEMPT_RT which is undesired.
The backlog-NAPI threads already provide the infrastructure which can be
utilized to perform the cleanup of the defer_list.

The NAPI state is updated with the input_pkt_queue.lock acquired. It
order not to break the state, it is needed to also wake the backlog-NAPI
thread with the lock held. This requires to acquire the use the lock in
rps_lock_irq*() if the backlog-NAPI threads are used even with RPS
disabled.

Move the logic of remotely starting softirqs to clean up the defer_list
into kick_defer_list_purge(). Make sure a lock is held in
rps_lock_irq*() if backlog-NAPI threads are used. Schedule backlog-NAPI
for defer_list cleanup if backlog-NAPI is available.

Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cb37817d6382c29117afd8ce54db6dba94f8c930..e41d30ebaca61e48a2ceb43edf777fa8b9859ef2 100644 (file)
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3287,6 +3287,7 @@ static inline void dev_xmit_recursion_dec(void)
        __this_cpu_dec(softnet_data.xmit.recursion);
 }
 
+void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu);
 void __netif_schedule(struct Qdisc *q);
 void netif_schedule_queue(struct netdev_queue *txq);
 

diff --git a/net/core/dev.c b/net/core/dev.c
index ea574df49640736633c3b81f06d1e9f63ef2635b..85e11dabab48c3d980320b6797f3cd827676e5d3 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -226,7 +226,7 @@ static bool use_backlog_threads(void)
 static inline void rps_lock_irqsave(struct softnet_data *sd,
                                    unsigned long *flags)
 {
-       if (IS_ENABLED(CONFIG_RPS))
+       if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
                spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags);
        else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
                local_irq_save(*flags);
@@ -234,7 +234,7 @@ static inline void rps_lock_irqsave(struct softnet_data *sd,
 
 static inline void rps_lock_irq_disable(struct softnet_data *sd)
 {
-       if (IS_ENABLED(CONFIG_RPS))
+       if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
                spin_lock_irq(&sd->input_pkt_queue.lock);
        else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
                local_irq_disable();
@@ -243,7 +243,7 @@ static inline void rps_lock_irq_disable(struct softnet_data *sd)
 static inline void rps_unlock_irq_restore(struct softnet_data *sd,
                                          unsigned long *flags)
 {
-       if (IS_ENABLED(CONFIG_RPS))
+       if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
                spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags);
        else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
                local_irq_restore(*flags);
@@ -251,7 +251,7 @@ static inline void rps_unlock_irq_restore(struct softnet_data *sd,
 
 static inline void rps_unlock_irq_enable(struct softnet_data *sd)
 {
-       if (IS_ENABLED(CONFIG_RPS))
+       if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
                spin_unlock_irq(&sd->input_pkt_queue.lock);
        else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
                local_irq_enable();
@@ -4722,6 +4722,23 @@ static void napi_schedule_rps(struct softnet_data *sd)
        __napi_schedule_irqoff(&mysd->backlog);
 }
 
+void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu)
+{
+       unsigned long flags;
+
+       if (use_backlog_threads()) {
+               rps_lock_irqsave(sd, &flags);
+
+               if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state))
+                       __napi_schedule_irqoff(&sd->backlog);
+
+               rps_unlock_irq_restore(sd, &flags);
+
+       } else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) {
+               smp_call_function_single_async(cpu, &sd->defer_csd);
+       }
+}
+
 #ifdef CONFIG_NET_FLOW_LIMIT
 int netdev_flow_limit_table_len __read_mostly = (1 << 12);
 #endif

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b99127712e6704dda41636014db46096da171bfd..17617c29be2df53058163e63b15a71dabf280db3 100644 (file)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -7039,8 +7039,8 @@ 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))
-               smp_call_function_single_async(cpu, &sd->defer_csd);
+       if (unlikely(kick))
+               kick_defer_list_purge(sd, cpu);
 }
 
 static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,