--- /dev/null
+From: Felix Fietkau <nbd@nbd.name>
+Date: Mon, 8 Feb 2021 11:34:08 -0800
+Subject: [PATCH] net: extract napi poll functionality to __napi_poll()
+
+This commit introduces a new function __napi_poll() which does the main
+logic of the existing napi_poll() function, and will be called by other
+functions in later commits.
+This idea and implementation is done by Felix Fietkau <nbd@nbd.name> and
+is proposed as part of the patch to move napi work to work_queue
+context.
+This commit by itself is a code restructure.
+
+Signed-off-by: Felix Fietkau <nbd@nbd.name>
+Signed-off-by: Wei Wang <weiwan@google.com>
+Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -6322,15 +6322,10 @@ void netif_napi_del(struct napi_struct *
+ }
+ EXPORT_SYMBOL(netif_napi_del);
+
+-static int napi_poll(struct napi_struct *n, struct list_head *repoll)
++static int __napi_poll(struct napi_struct *n, bool *repoll)
+ {
+- void *have;
+ int work, weight;
+
+- list_del_init(&n->poll_list);
+-
+- have = netpoll_poll_lock(n);
+-
+ weight = n->weight;
+
+ /* This NAPI_STATE_SCHED test is for avoiding a race
+@@ -6348,7 +6343,7 @@ static int napi_poll(struct napi_struct
+ WARN_ON_ONCE(work > weight);
+
+ if (likely(work < weight))
+- goto out_unlock;
++ return work;
+
+ /* Drivers must not modify the NAPI state if they
+ * consume the entire weight. In such cases this code
+@@ -6357,7 +6352,7 @@ static int napi_poll(struct napi_struct
+ */
+ if (unlikely(napi_disable_pending(n))) {
+ napi_complete(n);
+- goto out_unlock;
++ return work;
+ }
+
+ if (n->gro_bitmask) {
+@@ -6375,12 +6370,29 @@ static int napi_poll(struct napi_struct
+ if (unlikely(!list_empty(&n->poll_list))) {
+ pr_warn_once("%s: Budget exhausted after napi rescheduled\n",
+ n->dev ? n->dev->name : "backlog");
+- goto out_unlock;
++ return work;
+ }
+
+- list_add_tail(&n->poll_list, repoll);
++ *repoll = true;
++
++ return work;
++}
++
++static int napi_poll(struct napi_struct *n, struct list_head *repoll)
++{
++ bool do_repoll = false;
++ void *have;
++ int work;
++
++ list_del_init(&n->poll_list);
++
++ have = netpoll_poll_lock(n);
++
++ work = __napi_poll(n, &do_repoll);
++
++ if (do_repoll)
++ list_add_tail(&n->poll_list, repoll);
+
+-out_unlock:
+ netpoll_poll_unlock(have);
+
+ return work;
--- /dev/null
+From: Wei Wang <weiwan@google.com>
+Date: Mon, 8 Feb 2021 11:34:09 -0800
+Subject: [PATCH] net: implement threaded-able napi poll loop support
+
+This patch allows running each napi poll loop inside its own
+kernel thread.
+The kthread is created during netif_napi_add() if dev->threaded
+is set. And threaded mode is enabled in napi_enable(). We will
+provide a way to set dev->threaded and enable threaded mode
+without a device up/down in the following patch.
+
+Once that threaded mode is enabled and the kthread is
+started, napi_schedule() will wake-up such thread instead
+of scheduling the softirq.
+
+The threaded poll loop behaves quite likely the net_rx_action,
+but it does not have to manipulate local irqs and uses
+an explicit scheduling point based on netdev_budget.
+
+Co-developed-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Co-developed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Co-developed-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Wei Wang <weiwan@google.com>
+Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/include/linux/netdevice.h
++++ b/include/linux/netdevice.h
+@@ -340,6 +340,7 @@ struct napi_struct {
+ struct list_head dev_list;
+ struct hlist_node napi_hash_node;
+ unsigned int napi_id;
++ struct task_struct *thread;
+ };
+
+ enum {
+@@ -350,6 +351,7 @@ enum {
+ NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */
+ NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
+ NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
++ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/
+ };
+
+ enum {
+@@ -360,6 +362,7 @@ enum {
+ NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED),
+ NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
+ NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
++ NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED),
+ };
+
+ enum gro_result {
+@@ -504,20 +507,7 @@ bool napi_hash_del(struct napi_struct *n
+ */
+ void napi_disable(struct napi_struct *n);
+
+-/**
+- * napi_enable - enable NAPI scheduling
+- * @n: NAPI context
+- *
+- * Resume NAPI from being scheduled on this context.
+- * Must be paired with napi_disable.
+- */
+-static inline void napi_enable(struct napi_struct *n)
+-{
+- BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
+- smp_mb__before_atomic();
+- clear_bit(NAPI_STATE_SCHED, &n->state);
+- clear_bit(NAPI_STATE_NPSVC, &n->state);
+-}
++void napi_enable(struct napi_struct *n);
+
+ /**
+ * napi_synchronize - wait until NAPI is not running
+@@ -1783,6 +1773,8 @@ enum netdev_ml_priv_type {
+ *
+ * @wol_enabled: Wake-on-LAN is enabled
+ *
++ * @threaded: napi threaded mode is enabled
++ *
+ * FIXME: cleanup struct net_device such that network protocol info
+ * moves out.
+ */
+@@ -2075,6 +2067,7 @@ struct net_device {
+ struct lock_class_key addr_list_lock_key;
+ bool proto_down;
+ unsigned wol_enabled:1;
++ unsigned threaded:1;
+ };
+ #define to_net_dev(d) container_of(d, struct net_device, dev)
+
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -91,6 +91,7 @@
+ #include <linux/etherdevice.h>
+ #include <linux/ethtool.h>
+ #include <linux/skbuff.h>
++#include <linux/kthread.h>
+ #include <linux/bpf.h>
+ #include <linux/bpf_trace.h>
+ #include <net/net_namespace.h>
+@@ -1289,6 +1290,27 @@ void netdev_notify_peers(struct net_devi
+ }
+ EXPORT_SYMBOL(netdev_notify_peers);
+
++static int napi_threaded_poll(void *data);
++
++static int napi_kthread_create(struct napi_struct *n)
++{
++ int err = 0;
++
++ /* Create and wake up the kthread once to put it in
++ * TASK_INTERRUPTIBLE mode to avoid the blocked task
++ * warning and work with loadavg.
++ */
++ n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d",
++ n->dev->name, n->napi_id);
++ if (IS_ERR(n->thread)) {
++ err = PTR_ERR(n->thread);
++ pr_err("kthread_run failed with err %d\n", err);
++ n->thread = NULL;
++ }
++
++ return err;
++}
++
+ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
+ {
+ const struct net_device_ops *ops = dev->netdev_ops;
+@@ -3885,6 +3907,21 @@ int gro_normal_batch __read_mostly = 8;
+ static inline void ____napi_schedule(struct softnet_data *sd,
+ struct napi_struct *napi)
+ {
++ struct task_struct *thread;
++
++ if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
++ /* Paired with smp_mb__before_atomic() in
++ * napi_enable(). Use READ_ONCE() to guarantee
++ * a complete read on napi->thread. Only call
++ * wake_up_process() when it's not NULL.
++ */
++ thread = READ_ONCE(napi->thread);
++ if (thread) {
++ wake_up_process(thread);
++ return;
++ }
++ }
++
+ list_add_tail(&napi->poll_list, &sd->poll_list);
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ }
+@@ -6276,6 +6313,12 @@ void netif_napi_add(struct net_device *d
+ set_bit(NAPI_STATE_NPSVC, &napi->state);
+ list_add_rcu(&napi->dev_list, &dev->napi_list);
+ napi_hash_add(napi);
++ /* Create kthread for this napi if dev->threaded is set.
++ * Clear dev->threaded if kthread creation failed so that
++ * threaded mode will not be enabled in napi_enable().
++ */
++ if (dev->threaded && napi_kthread_create(napi))
++ dev->threaded = 0;
+ }
+ EXPORT_SYMBOL(netif_napi_add);
+
+@@ -6292,9 +6335,28 @@ void napi_disable(struct napi_struct *n)
+ hrtimer_cancel(&n->timer);
+
+ clear_bit(NAPI_STATE_DISABLE, &n->state);
++ clear_bit(NAPI_STATE_THREADED, &n->state);
+ }
+ EXPORT_SYMBOL(napi_disable);
+
++/**
++ * napi_enable - enable NAPI scheduling
++ * @n: NAPI context
++ *
++ * Resume NAPI from being scheduled on this context.
++ * Must be paired with napi_disable.
++ */
++void napi_enable(struct napi_struct *n)
++{
++ BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
++ smp_mb__before_atomic();
++ clear_bit(NAPI_STATE_SCHED, &n->state);
++ clear_bit(NAPI_STATE_NPSVC, &n->state);
++ if (n->dev->threaded && n->thread)
++ set_bit(NAPI_STATE_THREADED, &n->state);
++}
++EXPORT_SYMBOL(napi_enable);
++
+ static void flush_gro_hash(struct napi_struct *napi)
+ {
+ int i;
+@@ -6319,6 +6381,11 @@ void netif_napi_del(struct napi_struct *
+
+ flush_gro_hash(napi);
+ napi->gro_bitmask = 0;
++
++ if (napi->thread) {
++ kthread_stop(napi->thread);
++ napi->thread = NULL;
++ }
+ }
+ EXPORT_SYMBOL(netif_napi_del);
+
+@@ -6398,6 +6465,51 @@ static int napi_poll(struct napi_struct
+ return work;
+ }
+
++static int napi_thread_wait(struct napi_struct *napi)
++{
++ set_current_state(TASK_INTERRUPTIBLE);
++
++ while (!kthread_should_stop() && !napi_disable_pending(napi)) {
++ if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
++ WARN_ON(!list_empty(&napi->poll_list));
++ __set_current_state(TASK_RUNNING);
++ return 0;
++ }
++
++ schedule();
++ set_current_state(TASK_INTERRUPTIBLE);
++ }
++ __set_current_state(TASK_RUNNING);
++ return -1;
++}
++
++static int napi_threaded_poll(void *data)
++{
++ struct napi_struct *napi = data;
++ void *have;
++
++ while (!napi_thread_wait(napi)) {
++ for (;;) {
++ bool repoll = false;
++
++ local_bh_disable();
++
++ have = netpoll_poll_lock(napi);
++ __napi_poll(napi, &repoll);
++ netpoll_poll_unlock(have);
++
++ __kfree_skb_flush();
++ local_bh_enable();
++
++ if (!repoll)
++ break;
++
++ cond_resched();
++ }
++ }
++ return 0;
++}
++
+ static __latent_entropy void net_rx_action(struct softirq_action *h)
+ {
+ struct softnet_data *sd = this_cpu_ptr(&softnet_data);
--- /dev/null
+From: Wei Wang <weiwan@google.com>
+Date: Mon, 8 Feb 2021 11:34:10 -0800
+Subject: [PATCH] net: add sysfs attribute to control napi threaded mode
+
+This patch adds a new sysfs attribute to the network device class.
+Said attribute provides a per-device control to enable/disable the
+threaded mode for all the napi instances of the given network device,
+without the need for a device up/down.
+User sets it to 1 or 0 to enable or disable threaded mode.
+Note: when switching between threaded and the current softirq based mode
+for a napi instance, it will not immediately take effect if the napi is
+currently being polled. The mode switch will happen for the next time
+napi_schedule() is called.
+
+Co-developed-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Co-developed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Co-developed-by: Felix Fietkau <nbd@nbd.name>
+Signed-off-by: Felix Fietkau <nbd@nbd.name>
+Signed-off-by: Wei Wang <weiwan@google.com>
+Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/Documentation/ABI/testing/sysfs-class-net
++++ b/Documentation/ABI/testing/sysfs-class-net
+@@ -301,3 +301,18 @@ Contact: netdev@vger.kernel.org
+ Description:
+ 32-bit unsigned integer counting the number of times the link has
+ been down
++
++What: /sys/class/net/<iface>/threaded
++Date: Jan 2021
++KernelVersion: 5.12
++Contact: netdev@vger.kernel.org
++Description:
++ Boolean value to control the threaded mode per device. User could
++ set this value to enable/disable threaded mode for all napi
++ belonging to this device, without the need to do device up/down.
++
++ Possible values:
++ == ==================================
++ 0 threaded mode disabled for this dev
++ 1 threaded mode enabled for this dev
++ == ==================================
+--- a/include/linux/netdevice.h
++++ b/include/linux/netdevice.h
+@@ -498,6 +498,8 @@ static inline bool napi_complete(struct
+ */
+ bool napi_hash_del(struct napi_struct *napi);
+
++int dev_set_threaded(struct net_device *dev, bool threaded);
++
+ /**
+ * napi_disable - prevent NAPI from scheduling
+ * @n: NAPI context
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -3911,8 +3911,9 @@ static inline void ____napi_schedule(str
+
+ if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
+ /* Paired with smp_mb__before_atomic() in
+- * napi_enable(). Use READ_ONCE() to guarantee
+- * a complete read on napi->thread. Only call
++ * napi_enable()/dev_set_threaded().
++ * Use READ_ONCE() to guarantee a complete
++ * read on napi->thread. Only call
+ * wake_up_process() when it's not NULL.
+ */
+ thread = READ_ONCE(napi->thread);
+@@ -6290,6 +6291,49 @@ static void init_gro_hash(struct napi_st
+ napi->gro_bitmask = 0;
+ }
+
++int dev_set_threaded(struct net_device *dev, bool threaded)
++{
++ struct napi_struct *napi;
++ int err = 0;
++
++ if (dev->threaded == threaded)
++ return 0;
++
++ if (threaded) {
++ list_for_each_entry(napi, &dev->napi_list, dev_list) {
++ if (!napi->thread) {
++ err = napi_kthread_create(napi);
++ if (err) {
++ threaded = false;
++ break;
++ }
++ }
++ }
++ }
++
++ dev->threaded = threaded;
++
++ /* Make sure kthread is created before THREADED bit
++ * is set.
++ */
++ smp_mb__before_atomic();
++
++ /* Setting/unsetting threaded mode on a napi might not immediately
++ * take effect, if the current napi instance is actively being
++ * polled. In this case, the switch between threaded mode and
++ * softirq mode will happen in the next round of napi_schedule().
++ * This should not cause hiccups/stalls to the live traffic.
++ */
++ list_for_each_entry(napi, &dev->napi_list, dev_list) {
++ if (threaded)
++ set_bit(NAPI_STATE_THREADED, &napi->state);
++ else
++ clear_bit(NAPI_STATE_THREADED, &napi->state);
++ }
++
++ return err;
++}
++
+ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int), int weight)
+ {
+--- a/net/core/net-sysfs.c
++++ b/net/core/net-sysfs.c
+@@ -557,6 +557,45 @@ static ssize_t phys_switch_id_show(struc
+ }
+ static DEVICE_ATTR_RO(phys_switch_id);
+
++static ssize_t threaded_show(struct device *dev,
++ struct device_attribute *attr, char *buf)
++{
++ struct net_device *netdev = to_net_dev(dev);
++ ssize_t ret = -EINVAL;
++
++ if (!rtnl_trylock())
++ return restart_syscall();
++
++ if (dev_isalive(netdev))
++ ret = sprintf(buf, fmt_dec, netdev->threaded);
++
++ rtnl_unlock();
++ return ret;
++}
++
++static int modify_napi_threaded(struct net_device *dev, unsigned long val)
++{
++ int ret;
++
++ if (list_empty(&dev->napi_list))
++ return -EOPNOTSUPP;
++
++ if (val != 0 && val != 1)
++ return -EOPNOTSUPP;
++
++ ret = dev_set_threaded(dev, val);
++
++ return ret;
++}
++
++static ssize_t threaded_store(struct device *dev,
++ struct device_attribute *attr,
++ const char *buf, size_t len)
++{
++ return netdev_store(dev, attr, buf, len, modify_napi_threaded);
++}
++static DEVICE_ATTR_RW(threaded);
++
+ static struct attribute *net_class_attrs[] __ro_after_init = {
+ &dev_attr_netdev_group.attr,
+ &dev_attr_type.attr,
+@@ -587,6 +626,7 @@ static struct attribute *net_class_attrs
+ &dev_attr_proto_down.attr,
+ &dev_attr_carrier_up_count.attr,
+ &dev_attr_carrier_down_count.attr,
++ &dev_attr_threaded.attr,
+ NULL,
+ };
+ ATTRIBUTE_GROUPS(net_class);
--- /dev/null
+From: Wei Wang <weiwan@google.com>
+Date: Mon, 1 Mar 2021 17:21:13 -0800
+Subject: [PATCH] net: fix race between napi kthread mode and busy poll
+
+Currently, napi_thread_wait() checks for NAPI_STATE_SCHED bit to
+determine if the kthread owns this napi and could call napi->poll() on
+it. However, if socket busy poll is enabled, it is possible that the
+busy poll thread grabs this SCHED bit (after the previous napi->poll()
+invokes napi_complete_done() and clears SCHED bit) and tries to poll
+on the same napi. napi_disable() could grab the SCHED bit as well.
+This patch tries to fix this race by adding a new bit
+NAPI_STATE_SCHED_THREADED in napi->state. This bit gets set in
+____napi_schedule() if the threaded mode is enabled, and gets cleared
+in napi_complete_done(), and we only poll the napi in kthread if this
+bit is set. This helps distinguish the ownership of the napi between
+kthread and other scenarios and fixes the race issue.
+
+Fixes: 29863d41bb6e ("net: implement threaded-able napi poll loop support")
+Reported-by: Martin Zaharinov <micron10@gmail.com>
+Suggested-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Wei Wang <weiwan@google.com>
+Cc: Alexander Duyck <alexanderduyck@fb.com>
+Cc: Eric Dumazet <edumazet@google.com>
+Cc: Paolo Abeni <pabeni@redhat.com>
+Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
+---
+
+--- a/include/linux/netdevice.h
++++ b/include/linux/netdevice.h
+@@ -352,6 +352,7 @@ enum {
+ NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
+ NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
+ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/
++ NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */
+ };
+
+ enum {
+@@ -363,6 +364,7 @@ enum {
+ NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
+ NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
+ NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED),
++ NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED),
+ };
+
+ enum gro_result {
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -3918,6 +3918,8 @@ static inline void ____napi_schedule(str
+ */
+ thread = READ_ONCE(napi->thread);
+ if (thread) {
++ if (thread->state != TASK_INTERRUPTIBLE)
++ set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
+ wake_up_process(thread);
+ return;
+ }
+@@ -6078,7 +6080,8 @@ bool napi_complete_done(struct napi_stru
+
+ WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
+
+- new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
++ new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
++ NAPIF_STATE_SCHED_THREADED);
+
+ /* If STATE_MISSED was set, leave STATE_SCHED set,
+ * because we will call napi->poll() one more time.
+@@ -6511,16 +6514,25 @@ 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() && !napi_disable_pending(napi)) {
+- if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
++ /* Testing SCHED_THREADED bit here to make sure the current
++ * kthread owns this napi and could poll on this 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) {
+ 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: Paolo Abeni <pabeni@redhat.com>
+Date: Fri, 9 Apr 2021 17:24:17 +0200
+Subject: [PATCH] net: fix hangup on napi_disable for threaded napi
+
+napi_disable() is subject to an hangup, when the threaded
+mode is enabled and the napi is under heavy traffic.
+
+If the relevant napi has been scheduled and the napi_disable()
+kicks in before the next napi_threaded_wait() completes - so
+that the latter quits due to the napi_disable_pending() condition,
+the existing code leaves the NAPI_STATE_SCHED bit set and the
+napi_disable() loop waiting for such bit will hang.
+
+This patch addresses the issue by dropping the NAPI_STATE_DISABLE
+bit test in napi_thread_wait(). The later napi_threaded_poll()
+iteration will take care of clearing the NAPI_STATE_SCHED.
+
+This also addresses a related problem reported by Jakub:
+before this patch a napi_disable()/napi_enable() pair killed
+the napi thread, effectively disabling the threaded mode.
+On the patched kernel napi_disable() simply stops scheduling
+the relevant thread.
+
+v1 -> v2:
+ - let the main napi_thread_poll() loop clear the SCHED bit
+
+Reported-by: Jakub Kicinski <kuba@kernel.org>
+Fixes: 29863d41bb6e ("net: implement threaded-able napi poll loop support")
+Signed-off-by: Paolo Abeni <pabeni@redhat.com>
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Link: https://lore.kernel.org/r/883923fa22745a9589e8610962b7dc59df09fb1f.1617981844.git.pabeni@redhat.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+---
+
+--- a/net/core/dev.c
++++ b/net/core/dev.c
+@@ -6518,7 +6518,7 @@ static int napi_thread_wait(struct napi_
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+- while (!kthread_should_stop() && !napi_disable_pending(napi)) {
++ while (!kthread_should_stop()) {
+ /* Testing SCHED_THREADED bit here to make sure the current
+ * kthread owns this napi and could poll on this napi.
+ * Testing SCHED bit is not enough because SCHED bit might be
+@@ -6536,6 +6536,7 @@ static int napi_thread_wait(struct napi_
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+ __set_current_state(TASK_RUNNING);
++
+ return -1;
+ }
+
--- a/net/core/dev.c
+++ b/net/core/dev.c
-@@ -5432,8 +5432,7 @@ static inline void skb_gro_reset_offset(
+@@ -5472,8 +5472,7 @@ static inline void skb_gro_reset_offset(
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
-@@ -1549,6 +1549,7 @@ enum netdev_priv_flags {
+@@ -1540,6 +1540,7 @@ enum netdev_priv_flags {
IFF_FAILOVER_SLAVE = 1<<28,
IFF_L3MDEV_RX_HANDLER = 1<<29,
IFF_LIVE_RENAME_OK = 1<<30,
};
#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN
-@@ -1581,6 +1582,7 @@ enum netdev_priv_flags {
+@@ -1572,6 +1573,7 @@ enum netdev_priv_flags {
#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE
#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER
#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK
/* Specifies the type of the struct net_device::ml_priv pointer */
enum netdev_ml_priv_type {
-@@ -1889,6 +1891,11 @@ struct net_device {
+@@ -1882,6 +1884,11 @@ struct net_device {
const struct tlsdev_ops *tlsdev_ops;
#endif
const struct header_ops *header_ops;
unsigned int flags;
-@@ -1971,6 +1978,10 @@ struct net_device {
+@@ -1964,6 +1971,10 @@ struct net_device {
struct mpls_dev __rcu *mpls_ptr;
#endif
help
--- a/net/core/dev.c
+++ b/net/core/dev.c
-@@ -3200,10 +3200,20 @@ static int xmit_one(struct sk_buff *skb,
+@@ -3221,10 +3221,20 @@ static int xmit_one(struct sk_buff *skb,
if (dev_nit_active(dev))
dev_queue_xmit_nit(skb, dev);
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
-@@ -928,6 +928,13 @@ struct devlink;
+@@ -922,6 +922,13 @@ struct devlink;
struct tlsdev_ops;
/*
* This structure defines the management hooks for network devices.
* The following hooks can be defined; unless noted otherwise, they are
-@@ -1160,6 +1167,10 @@ struct tlsdev_ops;
+@@ -1154,6 +1161,10 @@ struct tlsdev_ops;
* int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh,
* u16 flags);
*
* int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier);
* Called to change device carrier. Soft-devices (like dummy, team, etc)
* which do not represent real hardware may define this to allow their
-@@ -1407,6 +1418,8 @@ struct net_device_ops {
+@@ -1401,6 +1412,8 @@ struct net_device_ops {
int (*ndo_bridge_dellink)(struct net_device *dev,
struct nlmsghdr *nlh,
u16 flags);
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
-@@ -929,6 +929,7 @@ struct tlsdev_ops;
+@@ -923,6 +923,7 @@ struct tlsdev_ops;
struct flow_offload;
enum flow_offload_type {
FLOW_OFFLOAD_ADD = 0,
-@@ -1167,8 +1168,15 @@ enum flow_offload_type {
+@@ -1161,8 +1162,15 @@ enum flow_offload_type {
* int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh,
* u16 flags);
*
* Adds/deletes flow entry to/from net device flowtable.
*
* int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier);
-@@ -1418,8 +1426,11 @@ struct net_device_ops {
+@@ -1412,8 +1420,11 @@ struct net_device_ops {
int (*ndo_bridge_dellink)(struct net_device *dev,
struct nlmsghdr *nlh,
u16 flags);
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
-@@ -1931,6 +1931,8 @@ struct net_device {
+@@ -1927,6 +1927,8 @@ struct net_device {
struct netdev_hw_addr_list mc;
struct netdev_hw_addr_list dev_addrs;
__u16 tc_index; /* traffic control index */
--- a/net/core/dev.c
+++ b/net/core/dev.c
-@@ -5498,6 +5498,9 @@ static enum gro_result dev_gro_receive(s
+@@ -5538,6 +5538,9 @@ static enum gro_result dev_gro_receive(s
int same_flow;
int grow;
if (netif_elide_gro(skb->dev))
goto normal;
-@@ -7300,6 +7303,48 @@ static void __netdev_adjacent_dev_unlink
+@@ -7481,6 +7484,48 @@ static void __netdev_adjacent_dev_unlink
&upper_dev->adj_list.lower);
}
static int __netdev_upper_dev_link(struct net_device *dev,
struct net_device *upper_dev, bool master,
void *upper_priv, void *upper_info,
-@@ -7350,6 +7395,7 @@ static int __netdev_upper_dev_link(struc
+@@ -7531,6 +7576,7 @@ static int __netdev_upper_dev_link(struc
if (ret)
return ret;
ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
ret = notifier_to_errno(ret);
-@@ -7443,6 +7489,7 @@ void netdev_upper_dev_unlink(struct net_
+@@ -7624,6 +7670,7 @@ void netdev_upper_dev_unlink(struct net_
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
&changeupper_info.info);
-@@ -8173,6 +8220,7 @@ int dev_set_mac_address(struct net_devic
+@@ -8354,6 +8401,7 @@ int dev_set_mac_address(struct net_devic
if (err)
return err;
dev->addr_assign_type = NET_ADDR_SET;
+++ /dev/null
-From: Felix Fietkau <nbd@nbd.name>
-Date: Sun, 26 Jul 2020 14:03:21 +0200
-Subject: [PATCH] net: add support for threaded NAPI polling
-
-For some drivers (especially 802.11 drivers), doing a lot of work in the NAPI
-poll function does not perform well. Since NAPI poll is bound to the CPU it
-was scheduled from, we can easily end up with a few very busy CPUs spending
-most of their time in softirq/ksoftirqd and some idle ones.
-
-Introduce threaded NAPI for such drivers based on a workqueue. The API is the
-same except for using netif_threaded_napi_add instead of netif_napi_add.
-
-In my tests with mt76 on MT7621 using threaded NAPI + a thread for tx scheduling
-improves LAN->WLAN bridging throughput by 10-50%. Throughput without threaded
-NAPI is wildly inconsistent, depending on the CPU that runs the tx scheduling
-thread.
-
-With threaded NAPI it seems stable and consistent (and higher than the best
-results I got without it).
-
-Based on a patch by Hillf Danton
-
-Cc: Hillf Danton <hdanton@sina.com>
-Signed-off-by: Felix Fietkau <nbd@nbd.name>
----
-
---- a/include/linux/netdevice.h
-+++ b/include/linux/netdevice.h
-@@ -340,6 +340,7 @@ struct napi_struct {
- struct list_head dev_list;
- struct hlist_node napi_hash_node;
- unsigned int napi_id;
-+ struct work_struct work;
- };
-
- enum {
-@@ -350,6 +351,7 @@ enum {
- NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */
- NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */
- NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */
-+ NAPI_STATE_THREADED, /* Use threaded NAPI */
- };
-
- enum {
-@@ -360,6 +362,7 @@ enum {
- NAPIF_STATE_HASHED = BIT(NAPI_STATE_HASHED),
- NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL),
- NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
-+ NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED),
- };
-
- enum gro_result {
-@@ -2101,6 +2104,7 @@ struct net_device {
- struct lock_class_key addr_list_lock_key;
- bool proto_down;
- unsigned wol_enabled:1;
-+ unsigned threaded:1;
- };
- #define to_net_dev(d) container_of(d, struct net_device, dev)
-
-@@ -2281,6 +2285,26 @@ void netif_napi_add(struct net_device *d
- int (*poll)(struct napi_struct *, int), int weight);
-
- /**
-+ * netif_threaded_napi_add - initialize a NAPI context
-+ * @dev: network device
-+ * @napi: NAPI context
-+ * @poll: polling function
-+ * @weight: default weight
-+ *
-+ * This variant of netif_napi_add() should be used from drivers using NAPI
-+ * with CPU intensive poll functions.
-+ * This will schedule polling from a high priority workqueue
-+ */
-+static inline void netif_threaded_napi_add(struct net_device *dev,
-+ struct napi_struct *napi,
-+ int (*poll)(struct napi_struct *, int),
-+ int weight)
-+{
-+ set_bit(NAPI_STATE_THREADED, &napi->state);
-+ netif_napi_add(dev, napi, poll, weight);
-+}
-+
-+/**
- * netif_tx_napi_add - initialize a NAPI context
- * @dev: network device
- * @napi: NAPI context
---- a/net/core/dev.c
-+++ b/net/core/dev.c
-@@ -156,6 +156,7 @@ static DEFINE_SPINLOCK(offload_lock);
- struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
- struct list_head ptype_all __read_mostly; /* Taps */
- static struct list_head offload_base __read_mostly;
-+static struct workqueue_struct *napi_workq __read_mostly;
-
- static int netif_rx_internal(struct sk_buff *skb);
- static int call_netdevice_notifiers_info(unsigned long val,
-@@ -5940,6 +5941,11 @@ void __napi_schedule(struct napi_struct
- {
- unsigned long flags;
-
-+ if (test_bit(NAPI_STATE_THREADED, &n->state)) {
-+ queue_work(napi_workq, &n->work);
-+ return;
-+ }
-+
- local_irq_save(flags);
- ____napi_schedule(this_cpu_ptr(&softnet_data), n);
- local_irq_restore(flags);
-@@ -5991,6 +5997,11 @@ EXPORT_SYMBOL(napi_schedule_prep);
- */
- void __napi_schedule_irqoff(struct napi_struct *n)
- {
-+ if (test_bit(NAPI_STATE_THREADED, &n->state)) {
-+ queue_work(napi_workq, &n->work);
-+ return;
-+ }
-+
- if (!IS_ENABLED(CONFIG_PREEMPT_RT))
- ____napi_schedule(this_cpu_ptr(&softnet_data), n);
- else
-@@ -6255,9 +6266,89 @@ static void init_gro_hash(struct napi_st
- napi->gro_bitmask = 0;
- }
-
-+static int __napi_poll(struct napi_struct *n, bool *repoll)
-+{
-+ int work, weight;
-+
-+ weight = n->weight;
-+
-+ /* This NAPI_STATE_SCHED test is for avoiding a race
-+ * with netpoll's poll_napi(). Only the entity which
-+ * obtains the lock and sees NAPI_STATE_SCHED set will
-+ * actually make the ->poll() call. Therefore we avoid
-+ * accidentally calling ->poll() when NAPI is not scheduled.
-+ */
-+ work = 0;
-+ if (test_bit(NAPI_STATE_SCHED, &n->state)) {
-+ work = n->poll(n, weight);
-+ trace_napi_poll(n, work, weight);
-+ }
-+
-+ WARN_ON_ONCE(work > weight);
-+
-+ if (likely(work < weight))
-+ return work;
-+
-+ /* Drivers must not modify the NAPI state if they
-+ * consume the entire weight. In such cases this code
-+ * still "owns" the NAPI instance and therefore can
-+ * move the instance around on the list at-will.
-+ */
-+ if (unlikely(napi_disable_pending(n))) {
-+ napi_complete(n);
-+ return work;
-+ }
-+
-+ if (n->gro_bitmask) {
-+ /* flush too old packets
-+ * If HZ < 1000, flush all packets.
-+ */
-+ napi_gro_flush(n, HZ >= 1000);
-+ }
-+
-+ gro_normal_list(n);
-+
-+ *repoll = true;
-+
-+ return work;
-+}
-+
-+static void napi_workfn(struct work_struct *work)
-+{
-+ struct napi_struct *n = container_of(work, struct napi_struct, work);
-+ void *have;
-+
-+ for (;;) {
-+ bool repoll = false;
-+
-+ local_bh_disable();
-+
-+ have = netpoll_poll_lock(n);
-+ __napi_poll(n, &repoll);
-+ netpoll_poll_unlock(have);
-+
-+ local_bh_enable();
-+
-+ if (!repoll)
-+ return;
-+
-+ if (!need_resched())
-+ continue;
-+
-+ /*
-+ * have to pay for the latency of task switch even if
-+ * napi is scheduled
-+ */
-+ queue_work(napi_workq, work);
-+ return;
-+ }
-+}
-+
- void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
- int (*poll)(struct napi_struct *, int), int weight)
- {
-+ if (dev->threaded)
-+ set_bit(NAPI_STATE_THREADED, &napi->state);
- INIT_LIST_HEAD(&napi->poll_list);
- hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
- napi->timer.function = napi_watchdog;
-@@ -6274,6 +6365,7 @@ void netif_napi_add(struct net_device *d
- #ifdef CONFIG_NETPOLL
- napi->poll_owner = -1;
- #endif
-+ INIT_WORK(&napi->work, napi_workfn);
- set_bit(NAPI_STATE_SCHED, &napi->state);
- set_bit(NAPI_STATE_NPSVC, &napi->state);
- list_add_rcu(&napi->dev_list, &dev->napi_list);
-@@ -6314,6 +6406,7 @@ static void flush_gro_hash(struct napi_s
- void netif_napi_del(struct napi_struct *napi)
- {
- might_sleep();
-+ cancel_work_sync(&napi->work);
- if (napi_hash_del(napi))
- synchronize_net();
- list_del_init(&napi->dev_list);
-@@ -6326,50 +6419,18 @@ EXPORT_SYMBOL(netif_napi_del);
-
- static int napi_poll(struct napi_struct *n, struct list_head *repoll)
- {
-+ bool do_repoll = false;
- void *have;
-- int work, weight;
-+ int work;
-
- list_del_init(&n->poll_list);
-
- have = netpoll_poll_lock(n);
-
-- weight = n->weight;
-+ work = __napi_poll(n, &do_repoll);
-
-- /* This NAPI_STATE_SCHED test is for avoiding a race
-- * with netpoll's poll_napi(). Only the entity which
-- * obtains the lock and sees NAPI_STATE_SCHED set will
-- * actually make the ->poll() call. Therefore we avoid
-- * accidentally calling ->poll() when NAPI is not scheduled.
-- */
-- work = 0;
-- if (test_bit(NAPI_STATE_SCHED, &n->state)) {
-- work = n->poll(n, weight);
-- trace_napi_poll(n, work, weight);
-- }
--
-- WARN_ON_ONCE(work > weight);
--
-- if (likely(work < weight))
-- goto out_unlock;
--
-- /* Drivers must not modify the NAPI state if they
-- * consume the entire weight. In such cases this code
-- * still "owns" the NAPI instance and therefore can
-- * move the instance around on the list at-will.
-- */
-- if (unlikely(napi_disable_pending(n))) {
-- napi_complete(n);
-+ if (!do_repoll)
- goto out_unlock;
-- }
--
-- if (n->gro_bitmask) {
-- /* flush too old packets
-- * If HZ < 1000, flush all packets.
-- */
-- napi_gro_flush(n, HZ >= 1000);
-- }
--
-- gro_normal_list(n);
-
- /* Some drivers may have called napi_schedule
- * prior to exhausting their budget.
-@@ -10349,6 +10410,10 @@ static int __init net_dev_init(void)
- sd->backlog.weight = weight_p;
- }
-
-+ napi_workq = alloc_workqueue("napi_workq", WQ_UNBOUND | WQ_HIGHPRI,
-+ WQ_UNBOUND_MAX_ACTIVE | WQ_SYSFS);
-+ BUG_ON(!napi_workq);
-+
- dev_boot_phase = 0;
-
- /* The loopback device is special if any other network devices
---- a/net/core/net-sysfs.c
-+++ b/net/core/net-sysfs.c
-@@ -470,6 +470,52 @@ static ssize_t proto_down_store(struct d
- }
- NETDEVICE_SHOW_RW(proto_down, fmt_dec);
-
-+static int change_napi_threaded(struct net_device *dev, unsigned long val)
-+{
-+ struct napi_struct *napi;
-+
-+ if (list_empty(&dev->napi_list))
-+ return -EOPNOTSUPP;
-+
-+ list_for_each_entry(napi, &dev->napi_list, dev_list) {
-+ if (val)
-+ set_bit(NAPI_STATE_THREADED, &napi->state);
-+ else
-+ clear_bit(NAPI_STATE_THREADED, &napi->state);
-+ }
-+
-+ return 0;
-+}
-+
-+static ssize_t napi_threaded_store(struct device *dev,
-+ struct device_attribute *attr,
-+ const char *buf, size_t len)
-+{
-+ return netdev_store(dev, attr, buf, len, change_napi_threaded);
-+}
-+
-+static ssize_t napi_threaded_show(struct device *dev,
-+ struct device_attribute *attr,
-+ char *buf)
-+{
-+ struct net_device *netdev = to_net_dev(dev);
-+ struct napi_struct *napi;
-+ bool enabled = false;
-+
-+ if (!rtnl_trylock())
-+ return restart_syscall();
-+
-+ list_for_each_entry(napi, &netdev->napi_list, dev_list) {
-+ if (test_bit(NAPI_STATE_THREADED, &napi->state))
-+ enabled = true;
-+ }
-+
-+ rtnl_unlock();
-+
-+ return sprintf(buf, fmt_dec, enabled);
-+}
-+static DEVICE_ATTR_RW(napi_threaded);
-+
- static ssize_t phys_port_id_show(struct device *dev,
- struct device_attribute *attr, char *buf)
- {
-@@ -581,6 +627,7 @@ static struct attribute *net_class_attrs
- &dev_attr_flags.attr,
- &dev_attr_tx_queue_len.attr,
- &dev_attr_gro_flush_timeout.attr,
-+ &dev_attr_napi_threaded.attr,
- &dev_attr_phys_port_id.attr,
- &dev_attr_phys_port_name.attr,
- &dev_attr_phys_switch_id.attr,
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
-@@ -776,6 +776,16 @@ struct xps_map {
+@@ -767,6 +767,16 @@ struct xps_map {
#define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \
- sizeof(struct xps_map)) / sizeof(u16))
/*
* This structure holds all XPS maps for device. Maps are indexed by CPU.
*/
-@@ -1379,6 +1389,9 @@ struct net_device_ops {
+@@ -1370,6 +1380,9 @@ struct net_device_ops {
const struct sk_buff *skb,
u16 rxq_index,
u32 flow_id);
projects / openwrt / staging / rmilecki.git / commitdiff