--- /dev/null
+From 56364c910691f6d10ba88c964c9041b9ab777bd6 Mon Sep 17 00:00:00 2001
+From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Date: Mon, 25 Mar 2024 08:40:28 +0100
+Subject: [PATCH 1/4] net: Remove conditional threaded-NAPI wakeup based on
+ task state.
+
+A NAPI thread is scheduled by first setting NAPI_STATE_SCHED bit. If
+successful (the bit was not yet set) then the NAPI_STATE_SCHED_THREADED
+is set but only if thread's state is not TASK_INTERRUPTIBLE (is
+TASK_RUNNING) followed by task wakeup.
+
+If the task is idle (TASK_INTERRUPTIBLE) then the
+NAPI_STATE_SCHED_THREADED bit is not set. The thread is no relying on
+the bit but always leaving the wait-loop after returning from schedule()
+because there must have been a wakeup.
+
+The smpboot-threads implementation for per-CPU threads requires an
+explicit condition and does not support "if we get out of schedule()
+then there must be something to do".
+
+Removing this optimisation simplifies the following integration.
+
+Set NAPI_STATE_SCHED_THREADED unconditionally on wakeup and rely on it
+in the wait path by removing the `woken' condition.
+
+Acked-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+---
+ net/core/dev.c | 14 ++------------
+ 1 file changed, 2 insertions(+), 12 deletions(-)
+
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -4473,13 +4473,7 @@ static inline void ____napi_schedule(str
+ */
+ thread = READ_ONCE(napi->thread);
+ if (thread) {
+- /* Avoid doing set_bit() if the thread is in
+- * INTERRUPTIBLE state, cause napi_thread_wait()
+- * makes sure to proceed with napi polling
+- * if the thread is explicitly woken from here.
+- */
+- if (READ_ONCE(thread->__state) != TASK_INTERRUPTIBLE)
+- set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
++ set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
+ wake_up_process(thread);
+ return;
+ }
+@@ -6635,8 +6629,6 @@ static int napi_poll(struct napi_struct
+
+ static int napi_thread_wait(struct napi_struct *napi)
+ {
+- bool woken = false;
+-
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ while (!kthread_should_stop()) {
+@@ -6645,15 +6637,13 @@ static int napi_thread_wait(struct napi_
+ * Testing SCHED bit is not enough because SCHED bit might be
+ * set by some other busy poll thread or by napi_disable().
+ */
+- if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) {
++ if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) {
+ WARN_ON(!list_empty(&napi->poll_list));
+ __set_current_state(TASK_RUNNING);
+ return 0;
+ }
+
+ schedule();
+- /* woken being true indicates this thread owns this napi. */
+- woken = true;
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+ __set_current_state(TASK_RUNNING);
--- /dev/null
+From dad6b97702639fba27a2bd3e986982ad6f0db3a7 Mon Sep 17 00:00:00 2001
+From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Date: Mon, 25 Mar 2024 08:40:29 +0100
+Subject: [PATCH 2/4] net: Allow to use SMP threads for backlog NAPI.
+
+Backlog NAPI is a per-CPU NAPI struct only (with no device behind it)
+used by drivers which don't do NAPI them self, RPS and parts of the
+stack which need to avoid recursive deadlocks while processing a packet.
+
+The non-NAPI driver use the CPU local backlog NAPI. If RPS is enabled
+then a flow for the skb is computed and based on the flow the skb can be
+enqueued on a remote CPU. Scheduling/ raising the softirq (for backlog's
+NAPI) on the remote CPU isn't trivial because the softirq is only
+scheduled on the local CPU and performed after the hardirq is done.
+In order to schedule a softirq on the remote CPU, an IPI is sent to the
+remote CPU which schedules the backlog-NAPI on the then local CPU.
+
+On PREEMPT_RT interrupts are force-threaded. The soft interrupts are
+raised within the interrupt thread and processed after the interrupt
+handler completed still within the context of the interrupt thread. The
+softirq is handled in the context where it originated.
+
+With force-threaded interrupts enabled, ksoftirqd is woken up if a
+softirq is raised from hardirq context. This is the case if it is raised
+from an IPI. Additionally there is a warning on PREEMPT_RT if the
+softirq is raised from the idle thread.
+This was done for two reasons:
+- With threaded interrupts the processing should happen in thread
+ context (where it originated) and ksoftirqd is the only thread for
+ this context if raised from hardirq. Using the currently running task
+ instead would "punish" a random task.
+- Once ksoftirqd is active it consumes all further softirqs until it
+ stops running. This changed recently and is no longer the case.
+
+Instead of keeping the backlog NAPI in ksoftirqd (in force-threaded/
+PREEMPT_RT setups) I am proposing NAPI-threads for backlog.
+The "proper" setup with threaded-NAPI is not doable because the threads
+are not pinned to an individual CPU and can be modified by the user.
+Additionally a dummy network device would have to be assigned. Also
+CPU-hotplug has to be considered if additional CPUs show up.
+All this can be probably done/ solved but the smpboot-threads already
+provide this infrastructure.
+
+Sending UDP packets over loopback expects that the packet is processed
+within the call. Delaying it by handing it over to the thread hurts
+performance. It is not beneficial to the outcome if the context switch
+happens immediately after enqueue or after a while to process a few
+packets in a batch.
+There is no need to always use the thread if the backlog NAPI is
+requested on the local CPU. This restores the loopback throuput. The
+performance drops mostly to the same value after enabling RPS on the
+loopback comparing the IPI and the tread result.
+
+Create NAPI-threads for backlog if request during boot. The thread runs
+the inner loop from napi_threaded_poll(), the wait part is different. It
+checks for NAPI_STATE_SCHED (the backlog NAPI can not be disabled).
+
+The NAPI threads for backlog are optional, it has to be enabled via the boot
+argument "thread_backlog_napi". It is mandatory for PREEMPT_RT to avoid the
+wakeup of ksoftirqd from the IPI.
+
+Acked-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+---
+ net/core/dev.c | 148 +++++++++++++++++++++++++++++++++++++------------
+ 1 file changed, 113 insertions(+), 35 deletions(-)
+
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -78,6 +78,7 @@
+ #include <linux/slab.h>
+ #include <linux/sched.h>
+ #include <linux/sched/mm.h>
++#include <linux/smpboot.h>
+ #include <linux/mutex.h>
+ #include <linux/rwsem.h>
+ #include <linux/string.h>
+@@ -217,6 +218,31 @@ static inline struct hlist_head *dev_ind
+ return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
+ }
+
++#ifndef CONFIG_PREEMPT_RT
++
++static DEFINE_STATIC_KEY_FALSE(use_backlog_threads_key);
++
++static int __init setup_backlog_napi_threads(char *arg)
++{
++ static_branch_enable(&use_backlog_threads_key);
++ return 0;
++}
++early_param("thread_backlog_napi", setup_backlog_napi_threads);
++
++static bool use_backlog_threads(void)
++{
++ return static_branch_unlikely(&use_backlog_threads_key);
++}
++
++#else
++
++static bool use_backlog_threads(void)
++{
++ return true;
++}
++
++#endif
++
+ static inline void rps_lock_irqsave(struct softnet_data *sd,
+ unsigned long *flags)
+ {
+@@ -4441,6 +4467,7 @@ EXPORT_SYMBOL(__dev_direct_xmit);
+ /*************************************************************************
+ * Receiver routines
+ *************************************************************************/
++static DEFINE_PER_CPU(struct task_struct *, backlog_napi);
+
+ int netdev_max_backlog __read_mostly = 1000;
+ EXPORT_SYMBOL(netdev_max_backlog);
+@@ -4473,12 +4500,16 @@ static inline void ____napi_schedule(str
+ */
+ thread = READ_ONCE(napi->thread);
+ if (thread) {
++ if (use_backlog_threads() && thread == raw_cpu_read(backlog_napi))
++ goto use_local_napi;
++
+ set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
+ wake_up_process(thread);
+ return;
+ }
+ }
+
++use_local_napi:
+ list_add_tail(&napi->poll_list, &sd->poll_list);
+ WRITE_ONCE(napi->list_owner, smp_processor_id());
+ /* If not called from net_rx_action()
+@@ -4724,6 +4755,11 @@ static void napi_schedule_rps(struct sof
+
+ #ifdef CONFIG_RPS
+ if (sd != mysd) {
++ if (use_backlog_threads()) {
++ __napi_schedule_irqoff(&sd->backlog);
++ return;
++ }
++
+ sd->rps_ipi_next = mysd->rps_ipi_list;
+ mysd->rps_ipi_list = sd;
+
+@@ -5947,7 +5983,7 @@ static void net_rps_action_and_irq_enabl
+ #ifdef CONFIG_RPS
+ struct softnet_data *remsd = sd->rps_ipi_list;
+
+- if (remsd) {
++ if (!use_backlog_threads() && remsd) {
+ sd->rps_ipi_list = NULL;
+
+ local_irq_enable();
+@@ -5962,7 +5998,7 @@ static void net_rps_action_and_irq_enabl
+ static bool sd_has_rps_ipi_waiting(struct softnet_data *sd)
+ {
+ #ifdef CONFIG_RPS
+- return sd->rps_ipi_list != NULL;
++ return !use_backlog_threads() && sd->rps_ipi_list;
+ #else
+ return false;
+ #endif
+@@ -6006,7 +6042,7 @@ static int process_backlog(struct napi_s
+ * We can use a plain write instead of clear_bit(),
+ * and we dont need an smp_mb() memory barrier.
+ */
+- napi->state = 0;
++ napi->state &= NAPIF_STATE_THREADED;
+ again = false;
+ } else {
+ skb_queue_splice_tail_init(&sd->input_pkt_queue,
+@@ -6672,43 +6708,48 @@ static void skb_defer_free_flush(struct
+ }
+ }
+
+-static int napi_threaded_poll(void *data)
++static void napi_threaded_poll_loop(struct napi_struct *napi)
+ {
+- struct napi_struct *napi = data;
+ struct softnet_data *sd;
+- void *have;
++ unsigned long last_qs = jiffies;
+
+- while (!napi_thread_wait(napi)) {
+- unsigned long last_qs = jiffies;
++ for (;;) {
++ bool repoll = false;
++ void *have;
+
+- for (;;) {
+- bool repoll = false;
++ local_bh_disable();
++ sd = this_cpu_ptr(&softnet_data);
++ sd->in_napi_threaded_poll = true;
+
+- local_bh_disable();
+- sd = this_cpu_ptr(&softnet_data);
+- sd->in_napi_threaded_poll = true;
+-
+- have = netpoll_poll_lock(napi);
+- __napi_poll(napi, &repoll);
+- netpoll_poll_unlock(have);
+-
+- sd->in_napi_threaded_poll = false;
+- barrier();
+-
+- if (sd_has_rps_ipi_waiting(sd)) {
+- local_irq_disable();
+- net_rps_action_and_irq_enable(sd);
+- }
+- skb_defer_free_flush(sd);
+- local_bh_enable();
++ have = netpoll_poll_lock(napi);
++ __napi_poll(napi, &repoll);
++ netpoll_poll_unlock(have);
++
++ sd->in_napi_threaded_poll = false;
++ barrier();
++
++ if (sd_has_rps_ipi_waiting(sd)) {
++ local_irq_disable();
++ net_rps_action_and_irq_enable(sd);
++ }
++ skb_defer_free_flush(sd);
++ local_bh_enable();
+
+- if (!repoll)
+- break;
++ if (!repoll)
++ break;
+
+- rcu_softirq_qs_periodic(last_qs);
+- cond_resched();
+- }
++ rcu_softirq_qs_periodic(last_qs);
++ cond_resched();
+ }
++}
++
++static int napi_threaded_poll(void *data)
++{
++ struct napi_struct *napi = data;
++
++ while (!napi_thread_wait(napi))
++ napi_threaded_poll_loop(napi);
++
+ return 0;
+ }
+
+@@ -11288,7 +11329,7 @@ static int dev_cpu_dead(unsigned int old
+
+ list_del_init(&napi->poll_list);
+ if (napi->poll == process_backlog)
+- napi->state = 0;
++ napi->state &= NAPIF_STATE_THREADED;
+ else
+ ____napi_schedule(sd, napi);
+ }
+@@ -11296,12 +11337,14 @@ static int dev_cpu_dead(unsigned int old
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_enable();
+
++ if (!use_backlog_threads()) {
+ #ifdef CONFIG_RPS
+- remsd = oldsd->rps_ipi_list;
+- oldsd->rps_ipi_list = NULL;
++ remsd = oldsd->rps_ipi_list;
++ oldsd->rps_ipi_list = NULL;
+ #endif
+- /* send out pending IPI's on offline CPU */
+- net_rps_send_ipi(remsd);
++ /* send out pending IPI's on offline CPU */
++ net_rps_send_ipi(remsd);
++ }
+
+ /* Process offline CPU's input_pkt_queue */
+ while ((skb = __skb_dequeue(&oldsd->process_queue))) {
+@@ -11564,6 +11607,38 @@ static struct pernet_operations __net_in
+ *
+ */
+
++static int backlog_napi_should_run(unsigned int cpu)
++{
++ struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
++ struct napi_struct *napi = &sd->backlog;
++
++ return test_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
++}
++
++static void run_backlog_napi(unsigned int cpu)
++{
++ struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
++
++ napi_threaded_poll_loop(&sd->backlog);
++}
++
++static void backlog_napi_setup(unsigned int cpu)
++{
++ struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
++ struct napi_struct *napi = &sd->backlog;
++
++ napi->thread = this_cpu_read(backlog_napi);
++ set_bit(NAPI_STATE_THREADED, &napi->state);
++}
++
++static struct smp_hotplug_thread backlog_threads = {
++ .store = &backlog_napi,
++ .thread_should_run = backlog_napi_should_run,
++ .thread_fn = run_backlog_napi,
++ .thread_comm = "backlog_napi/%u",
++ .setup = backlog_napi_setup,
++};
++
+ /*
+ * This is called single threaded during boot, so no need
+ * to take the rtnl semaphore.
+@@ -11614,7 +11689,10 @@ static int __init net_dev_init(void)
+ init_gro_hash(&sd->backlog);
+ sd->backlog.poll = process_backlog;
+ sd->backlog.weight = weight_p;
++ INIT_LIST_HEAD(&sd->backlog.poll_list);
+ }
++ if (use_backlog_threads())
++ smpboot_register_percpu_thread(&backlog_threads);
+
+ dev_boot_phase = 0;
+
--- /dev/null
+From 80d2eefcb4c84aa9018b2a997ab3a4c567bc821a Mon Sep 17 00:00:00 2001
+From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Date: Mon, 25 Mar 2024 08:40:30 +0100
+Subject: [PATCH 3/4] 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>
+---
+ include/linux/netdevice.h | 1 +
+ net/core/dev.c | 25 +++++++++++++++++++++----
+ net/core/skbuff.c | 4 ++--
+ 3 files changed, 24 insertions(+), 6 deletions(-)
+
+--- a/include/linux/netdevice.h
++++ b/include/linux/netdevice.h
+@@ -3300,6 +3300,7 @@ static inline void dev_xmit_recursion_de
+ __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);
+
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -246,7 +246,7 @@ 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);
+@@ -254,7 +254,7 @@ static inline void rps_lock_irqsave(stru
+
+ 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();
+@@ -263,7 +263,7 @@ static inline void rps_lock_irq_disable(
+ 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);
+@@ -271,7 +271,7 @@ static inline void rps_unlock_irq_restor
+
+ 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();
+@@ -4774,6 +4774,23 @@ static void napi_schedule_rps(struct sof
+ __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
+--- a/net/core/skbuff.c
++++ b/net/core/skbuff.c
+@@ -6863,8 +6863,8 @@ 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,
--- /dev/null
+From 765b11f8f4e20b7433e4ba4a3e9106a0d59501ed Mon Sep 17 00:00:00 2001
+From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Date: Mon, 25 Mar 2024 08:40:31 +0100
+Subject: [PATCH 4/4] net: Rename rps_lock to backlog_lock.
+
+The rps_lock.*() functions use the inner lock of a sk_buff_head for
+locking. This lock is used if RPS is enabled, otherwise the list is
+accessed lockless and disabling interrupts is enough for the
+synchronisation because it is only accessed CPU local. Not only the list
+is protected but also the NAPI state protected.
+With the addition of backlog threads, the lock is also needed because of
+the cross CPU access even without RPS. The clean up of the defer_list
+list is also done via backlog threads (if enabled).
+
+It has been suggested to rename the locking function since it is no
+longer just RPS.
+
+Rename the rps_lock*() functions to backlog_lock*().
+
+Suggested-by: Jakub Kicinski <kuba@kernel.org>
+Acked-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+---
+ net/core/dev.c | 34 +++++++++++++++++-----------------
+ 1 file changed, 17 insertions(+), 17 deletions(-)
+
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -243,8 +243,8 @@ static bool use_backlog_threads(void)
+
+ #endif
+
+-static inline void rps_lock_irqsave(struct softnet_data *sd,
+- unsigned long *flags)
++static inline void backlog_lock_irq_save(struct softnet_data *sd,
++ unsigned long *flags)
+ {
+ if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
+ spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags);
+@@ -252,7 +252,7 @@ static inline void rps_lock_irqsave(stru
+ local_irq_save(*flags);
+ }
+
+-static inline void rps_lock_irq_disable(struct softnet_data *sd)
++static inline void backlog_lock_irq_disable(struct softnet_data *sd)
+ {
+ if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
+ spin_lock_irq(&sd->input_pkt_queue.lock);
+@@ -260,8 +260,8 @@ static inline void rps_lock_irq_disable(
+ local_irq_disable();
+ }
+
+-static inline void rps_unlock_irq_restore(struct softnet_data *sd,
+- unsigned long *flags)
++static inline void backlog_unlock_irq_restore(struct softnet_data *sd,
++ unsigned long *flags)
+ {
+ if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
+ spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags);
+@@ -269,7 +269,7 @@ static inline void rps_unlock_irq_restor
+ local_irq_restore(*flags);
+ }
+
+-static inline void rps_unlock_irq_enable(struct softnet_data *sd)
++static inline void backlog_unlock_irq_enable(struct softnet_data *sd)
+ {
+ if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
+ spin_unlock_irq(&sd->input_pkt_queue.lock);
+@@ -4779,12 +4779,12 @@ void kick_defer_list_purge(struct softne
+ unsigned long flags;
+
+ if (use_backlog_threads()) {
+- rps_lock_irqsave(sd, &flags);
++ backlog_lock_irq_save(sd, &flags);
+
+ if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state))
+ __napi_schedule_irqoff(&sd->backlog);
+
+- rps_unlock_irq_restore(sd, &flags);
++ backlog_unlock_irq_restore(sd, &flags);
+
+ } else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) {
+ smp_call_function_single_async(cpu, &sd->defer_csd);
+@@ -4846,7 +4846,7 @@ static int enqueue_to_backlog(struct sk_
+ reason = SKB_DROP_REASON_NOT_SPECIFIED;
+ sd = &per_cpu(softnet_data, cpu);
+
+- rps_lock_irqsave(sd, &flags);
++ backlog_lock_irq_save(sd, &flags);
+ if (!netif_running(skb->dev))
+ goto drop;
+ qlen = skb_queue_len(&sd->input_pkt_queue);
+@@ -4855,7 +4855,7 @@ static int enqueue_to_backlog(struct sk_
+ enqueue:
+ __skb_queue_tail(&sd->input_pkt_queue, skb);
+ input_queue_tail_incr_save(sd, qtail);
+- rps_unlock_irq_restore(sd, &flags);
++ backlog_unlock_irq_restore(sd, &flags);
+ return NET_RX_SUCCESS;
+ }
+
+@@ -4870,7 +4870,7 @@ enqueue:
+
+ drop:
+ sd->dropped++;
+- rps_unlock_irq_restore(sd, &flags);
++ backlog_unlock_irq_restore(sd, &flags);
+
+ dev_core_stats_rx_dropped_inc(skb->dev);
+ kfree_skb_reason(skb, reason);
+@@ -5901,7 +5901,7 @@ static void flush_backlog(struct work_st
+ local_bh_disable();
+ sd = this_cpu_ptr(&softnet_data);
+
+- rps_lock_irq_disable(sd);
++ backlog_lock_irq_disable(sd);
+ skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
+ if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+ __skb_unlink(skb, &sd->input_pkt_queue);
+@@ -5909,7 +5909,7 @@ static void flush_backlog(struct work_st
+ input_queue_head_incr(sd);
+ }
+ }
+- rps_unlock_irq_enable(sd);
++ backlog_unlock_irq_enable(sd);
+
+ skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
+ if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+@@ -5927,14 +5927,14 @@ static bool flush_required(int cpu)
+ struct softnet_data *sd = &per_cpu(softnet_data, cpu);
+ bool do_flush;
+
+- rps_lock_irq_disable(sd);
++ backlog_lock_irq_disable(sd);
+
+ /* as insertion into process_queue happens with the rps lock held,
+ * process_queue access may race only with dequeue
+ */
+ do_flush = !skb_queue_empty(&sd->input_pkt_queue) ||
+ !skb_queue_empty_lockless(&sd->process_queue);
+- rps_unlock_irq_enable(sd);
++ backlog_unlock_irq_enable(sd);
+
+ return do_flush;
+ #endif
+@@ -6049,7 +6049,7 @@ static int process_backlog(struct napi_s
+
+ }
+
+- rps_lock_irq_disable(sd);
++ backlog_lock_irq_disable(sd);
+ if (skb_queue_empty(&sd->input_pkt_queue)) {
+ /*
+ * Inline a custom version of __napi_complete().
+@@ -6065,7 +6065,7 @@ static int process_backlog(struct napi_s
+ skb_queue_splice_tail_init(&sd->input_pkt_queue,
+ &sd->process_queue);
+ }
+- rps_unlock_irq_enable(sd);
++ backlog_unlock_irq_enable(sd);
+ }
+
+ return work;
/**
--- a/net/core/dev.c
+++ b/net/core/dev.c
-@@ -6555,7 +6555,7 @@ static int __napi_poll(struct napi_struc
+@@ -6602,7 +6602,7 @@ static int __napi_poll(struct napi_struc
* accidentally calling ->poll() when NAPI is not scheduled.
*/
work = 0;
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
-@@ -1759,6 +1759,7 @@ enum netdev_priv_flags {
+@@ -1758,6 +1758,7 @@ enum netdev_priv_flags {
IFF_TX_SKB_NO_LINEAR = BIT_ULL(31),
IFF_CHANGE_PROTO_DOWN = BIT_ULL(32),
IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33),
};
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
-@@ -1792,6 +1793,7 @@ enum netdev_priv_flags {
+@@ -1791,6 +1792,7 @@ enum netdev_priv_flags {
#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE
#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER
#define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR
/* Specifies the type of the struct net_device::ml_priv pointer */
enum netdev_ml_priv_type {
-@@ -2184,6 +2186,11 @@ struct net_device {
+@@ -2183,6 +2185,11 @@ struct net_device {
const struct tlsdev_ops *tlsdev_ops;
#endif
const struct header_ops *header_ops;
unsigned char operstate;
-@@ -2257,6 +2264,10 @@ struct net_device {
+@@ -2256,6 +2263,10 @@ struct net_device {
struct mctp_dev __rcu *mctp_ptr;
#endif
help
--- a/net/core/dev.c
+++ b/net/core/dev.c
-@@ -3571,6 +3571,11 @@ static int xmit_one(struct sk_buff *skb,
+@@ -3597,6 +3597,11 @@ static int xmit_one(struct sk_buff *skb,
if (dev_nit_active(dev))
dev_queue_xmit_nit(skb, dev);
+++ /dev/null
-From: Felix Fietkau <nbd@nbd.name>
-Date: Thu, 16 Feb 2023 18:39:04 +0100
-Subject: [PATCH] net/core: add optional threading for backlog processing
-
-When dealing with few flows or an imbalance on CPU utilization, static RPS
-CPU assignment can be too inflexible. Add support for enabling threaded NAPI
-for backlog processing in order to allow the scheduler to better balance
-processing. This helps better spread the load across idle CPUs.
-
-Signed-off-by: Felix Fietkau <nbd@nbd.name>
----
-
---- a/include/linux/netdevice.h
-+++ b/include/linux/netdevice.h
-@@ -558,6 +558,7 @@ static inline bool napi_complete(struct
- }
-
- int dev_set_threaded(struct net_device *dev, bool threaded);
-+int backlog_set_threaded(bool threaded);
-
- /**
- * napi_disable - prevent NAPI from scheduling
-@@ -3236,6 +3237,7 @@ struct softnet_data {
- /* stats */
- unsigned int processed;
- unsigned int time_squeeze;
-+ unsigned int process_queue_empty;
- #ifdef CONFIG_RPS
- struct softnet_data *rps_ipi_list;
- #endif
---- a/net/core/dev.c
-+++ b/net/core/dev.c
-@@ -4729,7 +4729,7 @@ static void napi_schedule_rps(struct sof
- struct softnet_data *mysd = this_cpu_ptr(&softnet_data);
-
- #ifdef CONFIG_RPS
-- if (sd != mysd) {
-+ if (sd != mysd && !test_bit(NAPI_STATE_THREADED, &sd->backlog.state)) {
- sd->rps_ipi_next = mysd->rps_ipi_list;
- mysd->rps_ipi_list = sd;
-
-@@ -5848,6 +5848,8 @@ static DEFINE_PER_CPU(struct work_struct
- /* Network device is going away, flush any packets still pending */
- static void flush_backlog(struct work_struct *work)
- {
-+ unsigned int process_queue_empty;
-+ bool threaded, flush_processq;
- struct sk_buff *skb, *tmp;
- struct softnet_data *sd;
-
-@@ -5862,8 +5864,17 @@ static void flush_backlog(struct work_st
- input_queue_head_incr(sd);
- }
- }
-+
-+ threaded = test_bit(NAPI_STATE_THREADED, &sd->backlog.state);
-+ flush_processq = threaded &&
-+ !skb_queue_empty_lockless(&sd->process_queue);
-+ if (flush_processq)
-+ process_queue_empty = sd->process_queue_empty;
- rps_unlock_irq_enable(sd);
-
-+ if (threaded)
-+ goto out;
-+
- skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
- if (skb->dev->reg_state == NETREG_UNREGISTERING) {
- __skb_unlink(skb, &sd->process_queue);
-@@ -5871,7 +5882,16 @@ static void flush_backlog(struct work_st
- input_queue_head_incr(sd);
- }
- }
-+
-+out:
- local_bh_enable();
-+
-+ while (flush_processq) {
-+ msleep(1);
-+ rps_lock_irq_disable(sd);
-+ flush_processq = process_queue_empty == sd->process_queue_empty;
-+ rps_unlock_irq_enable(sd);
-+ }
- }
-
- static bool flush_required(int cpu)
-@@ -6003,6 +6023,7 @@ static int process_backlog(struct napi_s
- }
-
- rps_lock_irq_disable(sd);
-+ sd->process_queue_empty++;
- if (skb_queue_empty(&sd->input_pkt_queue)) {
- /*
- * Inline a custom version of __napi_complete().
-@@ -6012,7 +6033,8 @@ static int process_backlog(struct napi_s
- * We can use a plain write instead of clear_bit(),
- * and we dont need an smp_mb() memory barrier.
- */
-- napi->state = 0;
-+ napi->state &= ~(NAPIF_STATE_SCHED |
-+ NAPIF_STATE_SCHED_THREADED);
- again = false;
- } else {
- skb_queue_splice_tail_init(&sd->input_pkt_queue,
-@@ -6426,6 +6448,55 @@ int dev_set_threaded(struct net_device *
- }
- EXPORT_SYMBOL(dev_set_threaded);
-
-+int backlog_set_threaded(bool threaded)
-+{
-+ static bool backlog_threaded;
-+ int err = 0;
-+ int i;
-+
-+ if (backlog_threaded == threaded)
-+ return 0;
-+
-+ for_each_possible_cpu(i) {
-+ struct softnet_data *sd = &per_cpu(softnet_data, i);
-+ struct napi_struct *n = &sd->backlog;
-+
-+ if (n->thread)
-+ continue;
-+ n->thread = kthread_run(napi_threaded_poll, n, "napi/backlog-%d", i);
-+ if (IS_ERR(n->thread)) {
-+ err = PTR_ERR(n->thread);
-+ pr_err("kthread_run failed with err %d\n", err);
-+ n->thread = NULL;
-+ threaded = false;
-+ break;
-+ }
-+
-+ }
-+
-+ backlog_threaded = threaded;
-+
-+ /* Make sure kthread is created before THREADED bit
-+ * is set.
-+ */
-+ smp_mb__before_atomic();
-+
-+ for_each_possible_cpu(i) {
-+ struct softnet_data *sd = &per_cpu(softnet_data, i);
-+ struct napi_struct *n = &sd->backlog;
-+ unsigned long flags;
-+
-+ rps_lock_irqsave(sd, &flags);
-+ if (threaded)
-+ n->state |= NAPIF_STATE_THREADED;
-+ else
-+ n->state &= ~NAPIF_STATE_THREADED;
-+ rps_unlock_irq_restore(sd, &flags);
-+ }
-+
-+ return err;
-+}
-+
- void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
- int (*poll)(struct napi_struct *, int), int weight)
- {
-@@ -11307,6 +11378,9 @@ static int dev_cpu_dead(unsigned int old
- raise_softirq_irqoff(NET_TX_SOFTIRQ);
- local_irq_enable();
-
-+ if (test_bit(NAPI_STATE_THREADED, &oldsd->backlog.state))
-+ return 0;
-+
- #ifdef CONFIG_RPS
- remsd = oldsd->rps_ipi_list;
- oldsd->rps_ipi_list = NULL;
-@@ -11622,6 +11696,7 @@ static int __init net_dev_init(void)
- INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd);
- spin_lock_init(&sd->defer_lock);
-
-+ INIT_LIST_HEAD(&sd->backlog.poll_list);
- init_gro_hash(&sd->backlog);
- sd->backlog.poll = process_backlog;
- sd->backlog.weight = weight_p;
---- a/net/core/sysctl_net_core.c
-+++ b/net/core/sysctl_net_core.c
-@@ -30,6 +30,7 @@ static int int_3600 = 3600;
- static int min_sndbuf = SOCK_MIN_SNDBUF;
- static int min_rcvbuf = SOCK_MIN_RCVBUF;
- static int max_skb_frags = MAX_SKB_FRAGS;
-+static int backlog_threaded;
- static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE;
-
- static int net_msg_warn; /* Unused, but still a sysctl */
-@@ -189,6 +190,23 @@ static int rps_sock_flow_sysctl(struct c
- }
- #endif /* CONFIG_RPS */
-
-+static int backlog_threaded_sysctl(struct ctl_table *table, int write,
-+ void *buffer, size_t *lenp, loff_t *ppos)
-+{
-+ static DEFINE_MUTEX(backlog_threaded_mutex);
-+ int ret;
-+
-+ mutex_lock(&backlog_threaded_mutex);
-+
-+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-+ if (write && !ret)
-+ ret = backlog_set_threaded(backlog_threaded);
-+
-+ mutex_unlock(&backlog_threaded_mutex);
-+
-+ return ret;
-+}
-+
- #ifdef CONFIG_NET_FLOW_LIMIT
- static DEFINE_MUTEX(flow_limit_update_mutex);
-
-@@ -541,6 +559,15 @@ static struct ctl_table net_core_table[]
- .proc_handler = rps_sock_flow_sysctl
- },
- #endif
-+ {
-+ .procname = "backlog_threaded",
-+ .data = &backlog_threaded,
-+ .maxlen = sizeof(unsigned int),
-+ .mode = 0644,
-+ .proc_handler = backlog_threaded_sysctl,
-+ .extra1 = SYSCTL_ZERO,
-+ .extra2 = SYSCTL_ONE
-+ },
- #ifdef CONFIG_NET_FLOW_LIMIT
- {
- .procname = "flow_limit_cpu_bitmap",