This patch allows running each napi poll loop inside its own kernel thread. The rx mode can be enabled per napi instance via the newly addded napi_set_threaded() api; the requested kthread will be created on demand and shut down on device stop.
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. Signed-off-by: Paolo Abeni <pab...@redhat.com> Signed-off-by: Hannes Frederic Sowa <han...@stressinduktion.org> --- include/linux/netdevice.h | 4 ++ net/core/dev.c | 113 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 117 insertions(+) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 63580e6..0722ed5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -323,6 +323,7 @@ struct napi_struct { struct list_head dev_list; struct hlist_node napi_hash_node; unsigned int napi_id; + struct task_struct *thread; }; enum { @@ -331,6 +332,7 @@ enum { NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ 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_THREADED, /* The poll is performed inside its own thread*/ }; enum gro_result { @@ -475,6 +477,8 @@ static inline void napi_complete(struct napi_struct *n) */ void napi_hash_add(struct napi_struct *napi); +int napi_set_threaded(struct napi_struct *n, bool threded); + /** * napi_hash_del - remove a NAPI from global table * @napi: NAPI context diff --git a/net/core/dev.c b/net/core/dev.c index c749033..0de286b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -94,6 +94,7 @@ #include <linux/ethtool.h> #include <linux/notifier.h> #include <linux/skbuff.h> +#include <linux/kthread.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/busy_poll.h> @@ -1305,9 +1306,19 @@ void netdev_notify_peers(struct net_device *dev) } EXPORT_SYMBOL(netdev_notify_peers); +static int napi_threaded_poll(void *data); + +static inline void napi_thread_start(struct napi_struct *n) +{ + if (test_bit(NAPI_STATE_THREADED, &n->state) && !n->thread) + n->thread = kthread_create(napi_threaded_poll, n, "%s-%d", + n->dev->name, n->napi_id); +} + static int __dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; + struct napi_struct *n; int ret; ASSERT_RTNL(); @@ -1334,6 +1345,9 @@ static int __dev_open(struct net_device *dev) if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); + list_for_each_entry(n, &dev->napi_list, dev_list) + napi_thread_start(n); + netpoll_poll_enable(dev); if (ret) @@ -1378,6 +1392,14 @@ int dev_open(struct net_device *dev) } EXPORT_SYMBOL(dev_open); +static inline void napi_thread_stop(struct napi_struct *n) +{ + if (!n->thread) + return; + kthread_stop(n->thread); + n->thread = NULL; +} + static int __dev_close_many(struct list_head *head) { struct net_device *dev; @@ -1406,6 +1428,7 @@ static int __dev_close_many(struct list_head *head) list_for_each_entry(dev, head, close_list) { const struct net_device_ops *ops = dev->netdev_ops; + struct napi_struct *n; /* * Call the device specific close. This cannot fail. @@ -1417,6 +1440,9 @@ static int __dev_close_many(struct list_head *head) if (ops->ndo_stop) ops->ndo_stop(dev); + list_for_each_entry(n, &dev->napi_list, dev_list) + napi_thread_stop(n); + dev->flags &= ~IFF_UP; netpoll_poll_enable(dev); } @@ -3456,6 +3482,11 @@ int weight_p __read_mostly = 64; /* old backlog weight */ static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { + if (napi->thread) { + wake_up_process(napi->thread); + return; + } + list_add_tail(&napi->poll_list, &sd->poll_list); __raise_softirq_irqoff(NET_RX_SOFTIRQ); } @@ -5174,6 +5205,88 @@ out_unlock: 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)) { + __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; + + while (!napi_thread_wait(napi)) { + struct list_head dummy_repoll; + int budget = netdev_budget; + unsigned long time_limit; + bool again = true; + + INIT_LIST_HEAD(&dummy_repoll); + local_bh_disable(); + time_limit = jiffies + 2; + do { + /* ensure that the poll list is not empty */ + if (list_empty(&dummy_repoll)) + list_add(&napi->poll_list, &dummy_repoll); + + budget -= napi_poll(napi, &dummy_repoll); + if (unlikely(budget <= 0 || + time_after_eq(jiffies, time_limit))) { + cond_resched_softirq(); + + /* refresh the budget */ + budget = netdev_budget; + __kfree_skb_flush(); + time_limit = jiffies + 2; + } + + if (napi_disable_pending(napi)) + again = false; + else if (!test_bit(NAPI_STATE_SCHED, &napi->state)) + again = false; + } while (again); + + __kfree_skb_flush(); + local_bh_enable(); + } + return 0; +} + +int napi_set_threaded(struct napi_struct *n, bool threaded) +{ + ASSERT_RTNL(); + + if (n->dev->flags & IFF_UP) + return -EBUSY; + + if (threaded == !!test_bit(NAPI_STATE_THREADED, &n->state)) + return 0; + if (threaded) + set_bit(NAPI_STATE_THREADED, &n->state); + else + clear_bit(NAPI_STATE_THREADED, &n->state); + + /* if the device is initializing, nothing todo */ + if (test_bit(__LINK_STATE_START, &n->dev->state)) + return 0; + + napi_thread_stop(n); + napi_thread_start(n); + return 0; +} +EXPORT_SYMBOL(napi_set_threaded); + static void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); -- 1.8.3.1