[PATCH net-next v4 2/3] net: implement threaded-able napi poll loop support
From: Wei Wang <hidden>
Date: 2020-12-09 00:55:46
Subsystem:
networking drivers, networking [general], the rest · Maintainers:
Andrew Lunn, "David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Linus Torvalds
This patch allows running each napi poll loop inside its own kernel thread. The threaded mode could be enabled through napi_set_threaded() api, and does not require a device up/down. The kthread gets created on demand when napi_set_threaded() is called, and gets shut down eventually in napi_disable(). 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 <redacted> Signed-off-by: Hannes Frederic Sowa <redacted> Co-developed-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Wei Wang <redacted> Reviewed-by: Eric Dumazet <edumazet@google.com> --- include/linux/netdevice.h | 5 ++ net/core/dev.c | 105 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 110 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7bf167993c05..abd3b52b7da6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h@@ -347,6 +347,7 @@ struct napi_struct { struct list_head dev_list; struct hlist_node napi_hash_node; unsigned int napi_id; + struct task_struct *thread; }; enum {
@@ -358,6 +359,7 @@ 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_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ + NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ }; enum {
@@ -369,6 +371,7 @@ 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_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), + NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), }; enum gro_result {
@@ -495,6 +498,8 @@ static inline bool napi_complete(struct napi_struct *n) return napi_complete_done(n, 0); } +int napi_set_threaded(struct napi_struct *n, bool threaded); + /** * napi_disable - prevent NAPI from scheduling * @n: NAPI context
diff --git a/net/core/dev.c b/net/core/dev.c
index 8064af1dd03c..cb6c4e2363a4 100644
--- 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>
@@ -1475,6 +1476,36 @@ void netdev_notify_peers(struct net_device *dev) } 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 void napi_kthread_stop(struct napi_struct *n) +{ + if (!n->thread) + return; + kthread_stop(n->thread); + clear_bit(NAPI_STATE_THREADED, &n->state); + n->thread = NULL; +} + static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops;
@@ -4234,6 +4265,11 @@ int gro_normal_batch __read_mostly = 8; static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { + if (test_bit(NAPI_STATE_THREADED, &napi->state)) { + wake_up_process(napi->thread); + return; + } + list_add_tail(&napi->poll_list, &sd->poll_list); __raise_softirq_irqoff(NET_RX_SOFTIRQ); }
@@ -6690,6 +6726,29 @@ static void init_gro_hash(struct napi_struct *napi) napi->gro_bitmask = 0; } +int napi_set_threaded(struct napi_struct *n, bool threaded) +{ + int err = 0; + + ASSERT_RTNL(); + + if (threaded == !!test_bit(NAPI_STATE_THREADED, &n->state)) + return 0; + if (threaded) { + if (!n->thread) { + err = napi_kthread_create(n); + if (err) + goto out; + } + set_bit(NAPI_STATE_THREADED, &n->state); + } else { + clear_bit(NAPI_STATE_THREADED, &n->state); + } + +out: + return err; +} + void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) {
@@ -6731,6 +6790,7 @@ void napi_disable(struct napi_struct *n) msleep(1); hrtimer_cancel(&n->timer); + napi_kthread_stop(n); clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); clear_bit(NAPI_STATE_DISABLE, &n->state);
@@ -6859,6 +6919,51 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) 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);
--
2.29.2.576.ga3fc446d84-goog