1 files changed, 574 insertions, 504 deletions

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 802fe11efad..e33937fb32a 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -9,10 +9,14 @@
  * Copyright (C) 2002  Red Hat, Inc.
  */
 
-#include <linux/smp_lock.h>
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/string.h>
+#include <linux/if_arp.h>
 #include <linux/inetdevice.h>
 #include <linux/inet.h>
 #include <linux/interrupt.h>
@@ -21,9 +25,16 @@
 #include <linux/delay.h>
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/if_vlan.h>
 #include <net/tcp.h>
 #include <net/udp.h>
+#include <net/addrconf.h>
+#include <net/ndisc.h>
+#include <net/ip6_checksum.h>
 #include <asm/unaligned.h>
+#include <trace/events/napi.h>
 
 /*
  * We maintain a small pool of fully-sized skbs, to make sure the
@@ -32,85 +43,95 @@
 
 #define MAX_UDP_CHUNK 1460
 #define MAX_SKBS 32
-#define MAX_QUEUE_DEPTH (MAX_SKBS / 2)
-#define MAX_RETRIES 20000
-
-static DEFINE_SPINLOCK(skb_list_lock);
-static int nr_skbs;
-static struct sk_buff *skbs;
 
-static DEFINE_SPINLOCK(queue_lock);
-static int queue_depth;
-static struct sk_buff *queue_head, *queue_tail;
+static struct sk_buff_head skb_pool;
 
-static atomic_t trapped;
+DEFINE_STATIC_SRCU(netpoll_srcu);
 
-#define NETPOLL_RX_ENABLED  1
-#define NETPOLL_RX_DROP     2
+#define USEC_PER_POLL	50
 
-#define MAX_SKB_SIZE \
-		(MAX_UDP_CHUNK + sizeof(struct udphdr) + \
-				sizeof(struct iphdr) + sizeof(struct ethhdr))
+#define MAX_SKB_SIZE							\
+	(sizeof(struct ethhdr) +					\
+	 sizeof(struct iphdr) +						\
+	 sizeof(struct udphdr) +					\
+	 MAX_UDP_CHUNK)
 
 static void zap_completion_queue(void);
+static void netpoll_async_cleanup(struct work_struct *work);
 
-static void queue_process(void *p)
-{
-	unsigned long flags;
-	struct sk_buff *skb;
-
-	while (queue_head) {
-		spin_lock_irqsave(&queue_lock, flags);
-
-		skb = queue_head;
-		queue_head = skb->next;
-		if (skb == queue_tail)
-			queue_head = NULL;
-
-		queue_depth--;
+static unsigned int carrier_timeout = 4;
+module_param(carrier_timeout, uint, 0644);
 
-		spin_unlock_irqrestore(&queue_lock, flags);
+#define np_info(np, fmt, ...)				\
+	pr_info("%s: " fmt, np->name, ##__VA_ARGS__)
+#define np_err(np, fmt, ...)				\
+	pr_err("%s: " fmt, np->name, ##__VA_ARGS__)
+#define np_notice(np, fmt, ...)				\
+	pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
 
-		dev_queue_xmit(skb);
-	}
-}
-
-static DECLARE_WORK(send_queue, queue_process, NULL);
-
-void netpoll_queue(struct sk_buff *skb)
+static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
+			      struct netdev_queue *txq)
 {
-	unsigned long flags;
-
-	if (queue_depth == MAX_QUEUE_DEPTH) {
-		__kfree_skb(skb);
-		return;
+	const struct net_device_ops *ops = dev->netdev_ops;
+	int status = NETDEV_TX_OK;
+	netdev_features_t features;
+
+	features = netif_skb_features(skb);
+
+	if (vlan_tx_tag_present(skb) &&
+	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+		skb = __vlan_put_tag(skb, skb->vlan_proto,
+				     vlan_tx_tag_get(skb));
+		if (unlikely(!skb)) {
+			/* This is actually a packet drop, but we
+			 * don't want the code that calls this
+			 * function to try and operate on a NULL skb.
+			 */
+			goto out;
+		}
+		skb->vlan_tci = 0;
 	}
 
-	spin_lock_irqsave(&queue_lock, flags);
-	if (!queue_head)
-		queue_head = skb;
-	else
-		queue_tail->next = skb;
-	queue_tail = skb;
-	queue_depth++;
-	spin_unlock_irqrestore(&queue_lock, flags);
+	status = ops->ndo_start_xmit(skb, dev);
+	if (status == NETDEV_TX_OK)
+		txq_trans_update(txq);
 
-	schedule_work(&send_queue);
+out:
+	return status;
 }
 
-static int checksum_udp(struct sk_buff *skb, struct udphdr *uh,
-			     unsigned short ulen, u32 saddr, u32 daddr)
+static void queue_process(struct work_struct *work)
 {
-	if (uh->check == 0)
-		return 0;
+	struct netpoll_info *npinfo =
+		container_of(work, struct netpoll_info, tx_work.work);
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	while ((skb = skb_dequeue(&npinfo->txq))) {
+		struct net_device *dev = skb->dev;
+		struct netdev_queue *txq;
 
-	if (skb->ip_summed == CHECKSUM_HW)
-		return csum_tcpudp_magic(
-			saddr, daddr, ulen, IPPROTO_UDP, skb->csum);
+		if (!netif_device_present(dev) || !netif_running(dev)) {
+			kfree_skb(skb);
+			continue;
+		}
 
-	skb->csum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
+		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
 
-	return csum_fold(skb_checksum(skb, 0, skb->len, skb->csum));
+		local_irq_save(flags);
+		HARD_TX_LOCK(dev, txq, smp_processor_id());
+		if (netif_xmit_frozen_or_stopped(txq) ||
+		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
+			skb_queue_head(&npinfo->txq, skb);
+			HARD_TX_UNLOCK(dev, txq);
+			local_irq_restore(flags);
+
+			schedule_delayed_work(&npinfo->tx_work, HZ/10);
+			return;
+		}
+		HARD_TX_UNLOCK(dev, txq);
+		local_irq_restore(flags);
+	}
 }
 
 /*
@@ -123,60 +144,114 @@ static int checksum_udp(struct sk_buff *skb, struct udphdr *uh,
  * trylock here and interrupts are already disabled in the softirq
  * case. Further, we test the poll_owner to avoid recursion on UP
  * systems where the lock doesn't exist.
- *
- * In cases where there is bi-directional communications, reading only
- * one message at a time can lead to packets being dropped by the
- * network adapter, forcing superfluous retries and possibly timeouts.
- * Thus, we set our budget to greater than 1.
  */
-static void poll_napi(struct netpoll *np)
+static int poll_one_napi(struct napi_struct *napi, int budget)
 {
-	struct netpoll_info *npinfo = np->dev->npinfo;
-	int budget = 16;
+	int work;
 
-	if (test_bit(__LINK_STATE_RX_SCHED, &np->dev->state) &&
-	    npinfo->poll_owner != smp_processor_id() &&
-	    spin_trylock(&npinfo->poll_lock)) {
-		npinfo->rx_flags |= NETPOLL_RX_DROP;
-		atomic_inc(&trapped);
+	/* net_rx_action's ->poll() invocations and our's are
+	 * synchronized by this test which is only made while
+	 * holding the napi->poll_lock.
+	 */
+	if (!test_bit(NAPI_STATE_SCHED, &napi->state))
+		return budget;
 
-		np->dev->poll(np->dev, &budget);
+	set_bit(NAPI_STATE_NPSVC, &napi->state);
 
-		atomic_dec(&trapped);
-		npinfo->rx_flags &= ~NETPOLL_RX_DROP;
-		spin_unlock(&npinfo->poll_lock);
+	work = napi->poll(napi, budget);
+	WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
+	trace_napi_poll(napi);
+
+	clear_bit(NAPI_STATE_NPSVC, &napi->state);
+
+	return budget - work;
+}
+
+static void poll_napi(struct net_device *dev, int budget)
+{
+	struct napi_struct *napi;
+
+	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+		if (napi->poll_owner != smp_processor_id() &&
+		    spin_trylock(&napi->poll_lock)) {
+			budget = poll_one_napi(napi, budget);
+			spin_unlock(&napi->poll_lock);
+		}
 	}
 }
 
-void netpoll_poll(struct netpoll *np)
+static void netpoll_poll_dev(struct net_device *dev)
 {
-	if(!np->dev || !netif_running(np->dev) || !np->dev->poll_controller)
+	const struct net_device_ops *ops;
+	struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
+	int budget = 0;
+
+	/* Don't do any rx activity if the dev_lock mutex is held
+	 * the dev_open/close paths use this to block netpoll activity
+	 * while changing device state
+	 */
+	if (down_trylock(&ni->dev_lock))
+		return;
+
+	if (!netif_running(dev)) {
+		up(&ni->dev_lock);
 		return;
+	}
+
+	ops = dev->netdev_ops;
+	if (!ops->ndo_poll_controller) {
+		up(&ni->dev_lock);
+		return;
+	}
 
 	/* Process pending work on NIC */
-	np->dev->poll_controller(np->dev);
-	if (np->dev->poll)
-		poll_napi(np);
+	ops->ndo_poll_controller(dev);
+
+	poll_napi(dev, budget);
+
+	up(&ni->dev_lock);
 
 	zap_completion_queue();
 }
 
+void netpoll_poll_disable(struct net_device *dev)
+{
+	struct netpoll_info *ni;
+	int idx;
+	might_sleep();
+	idx = srcu_read_lock(&netpoll_srcu);
+	ni = srcu_dereference(dev->npinfo, &netpoll_srcu);
+	if (ni)
+		down(&ni->dev_lock);
+	srcu_read_unlock(&netpoll_srcu, idx);
+}
+EXPORT_SYMBOL(netpoll_poll_disable);
+
+void netpoll_poll_enable(struct net_device *dev)
+{
+	struct netpoll_info *ni;
+	rcu_read_lock();
+	ni = rcu_dereference(dev->npinfo);
+	if (ni)
+		up(&ni->dev_lock);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(netpoll_poll_enable);
+
 static void refill_skbs(void)
 {
 	struct sk_buff *skb;
 	unsigned long flags;
 
-	spin_lock_irqsave(&skb_list_lock, flags);
-	while (nr_skbs < MAX_SKBS) {
+	spin_lock_irqsave(&skb_pool.lock, flags);
+	while (skb_pool.qlen < MAX_SKBS) {
 		skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC);
 		if (!skb)
 			break;
 
-		skb->next = skbs;
-		skbs = skb;
-		nr_skbs++;
+		__skb_queue_tail(&skb_pool, skb);
 	}
-	spin_unlock_irqrestore(&skb_list_lock, flags);
+	spin_unlock_irqrestore(&skb_pool.lock, flags);
 }
 
 static void zap_completion_queue(void)
@@ -195,48 +270,37 @@ static void zap_completion_queue(void)
 		while (clist != NULL) {
 			struct sk_buff *skb = clist;
 			clist = clist->next;
-			if(skb->destructor)
+			if (!skb_irq_freeable(skb)) {
+				atomic_inc(&skb->users);
 				dev_kfree_skb_any(skb); /* put this one back */
-			else
+			} else {
 				__kfree_skb(skb);
+			}
 		}
 	}
 
 	put_cpu_var(softnet_data);
 }
 
-static struct sk_buff * find_skb(struct netpoll *np, int len, int reserve)
+static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve)
 {
-	int once = 1, count = 0;
-	unsigned long flags;
-	struct sk_buff *skb = NULL;
+	int count = 0;
+	struct sk_buff *skb;
 
 	zap_completion_queue();
+	refill_skbs();
 repeat:
-	if (nr_skbs < MAX_SKBS)
-		refill_skbs();
 
 	skb = alloc_skb(len, GFP_ATOMIC);
+	if (!skb)
+		skb = skb_dequeue(&skb_pool);
 
 	if (!skb) {
-		spin_lock_irqsave(&skb_list_lock, flags);
-		skb = skbs;
-		if (skb) {
-			skbs = skb->next;
-			skb->next = NULL;
-			nr_skbs--;
+		if (++count < 10) {
+			netpoll_poll_dev(np->dev);
+			goto repeat;
 		}
-		spin_unlock_irqrestore(&skb_list_lock, flags);
-	}
-
-	if(!skb) {
-		count++;
-		if (once && (count == 1000000)) {
-			printk("out of netpoll skbs!\n");
-			once = 0;
-		}
-		netpoll_poll(np);
-		goto repeat;
+		return NULL;
 	}
 
 	atomic_set(&skb->users, 1);
@@ -244,445 +308,394 @@ repeat:
 	return skb;
 }
 
-static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
+static int netpoll_owner_active(struct net_device *dev)
 {
-	int status;
-	struct netpoll_info *npinfo;
+	struct napi_struct *napi;
 
-	if (!np || !np->dev || !netif_running(np->dev)) {
-		__kfree_skb(skb);
-		return;
+	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+		if (napi->poll_owner == smp_processor_id())
+			return 1;
 	}
+	return 0;
+}
 
-	npinfo = np->dev->npinfo;
+/* call with IRQ disabled */
+void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
+			     struct net_device *dev)
+{
+	int status = NETDEV_TX_BUSY;
+	unsigned long tries;
+	/* It is up to the caller to keep npinfo alive. */
+	struct netpoll_info *npinfo;
 
-	/* avoid recursion */
-	if (npinfo->poll_owner == smp_processor_id() ||
-	    np->dev->xmit_lock_owner == smp_processor_id()) {
-		if (np->drop)
-			np->drop(skb);
-		else
-			__kfree_skb(skb);
+	WARN_ON_ONCE(!irqs_disabled());
+
+	npinfo = rcu_dereference_bh(np->dev->npinfo);
+	if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
+		dev_kfree_skb_irq(skb);
 		return;
 	}
 
-	do {
-		npinfo->tries--;
-		spin_lock(&np->dev->xmit_lock);
-		np->dev->xmit_lock_owner = smp_processor_id();
+	/* don't get messages out of order, and no recursion */
+	if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
+		struct netdev_queue *txq;
 
-		/*
-		 * network drivers do not expect to be called if the queue is
-		 * stopped.
-		 */
-		if (netif_queue_stopped(np->dev)) {
-			np->dev->xmit_lock_owner = -1;
-			spin_unlock(&np->dev->xmit_lock);
-			netpoll_poll(np);
-			udelay(50);
-			continue;
-		}
+		txq = netdev_pick_tx(dev, skb, NULL);
 
-		status = np->dev->hard_start_xmit(skb, np->dev);
-		np->dev->xmit_lock_owner = -1;
-		spin_unlock(&np->dev->xmit_lock);
+		/* try until next clock tick */
+		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
+		     tries > 0; --tries) {
+			if (HARD_TX_TRYLOCK(dev, txq)) {
+				if (!netif_xmit_stopped(txq))
+					status = netpoll_start_xmit(skb, dev, txq);
 
-		/* success */
-		if(!status) {
-			npinfo->tries = MAX_RETRIES; /* reset */
-			return;
+				HARD_TX_UNLOCK(dev, txq);
+
+				if (status == NETDEV_TX_OK)
+					break;
+
+			}
+
+			/* tickle device maybe there is some cleanup */
+			netpoll_poll_dev(np->dev);
+
+			udelay(USEC_PER_POLL);
 		}
 
-		/* transmit busy */
-		netpoll_poll(np);
-		udelay(50);
-	} while (npinfo->tries > 0);
+		WARN_ONCE(!irqs_disabled(),
+			"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
+			dev->name, dev->netdev_ops->ndo_start_xmit);
+
+	}
+
+	if (status != NETDEV_TX_OK) {
+		skb_queue_tail(&npinfo->txq, skb);
+		schedule_delayed_work(&npinfo->tx_work,0);
+	}
 }
+EXPORT_SYMBOL(netpoll_send_skb_on_dev);
 
 void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 {
-	int total_len, eth_len, ip_len, udp_len;
+	int total_len, ip_len, udp_len;
 	struct sk_buff *skb;
 	struct udphdr *udph;
 	struct iphdr *iph;
 	struct ethhdr *eth;
+	static atomic_t ip_ident;
+	struct ipv6hdr *ip6h;
 
 	udp_len = len + sizeof(*udph);
-	ip_len = eth_len = udp_len + sizeof(*iph);
-	total_len = eth_len + ETH_HLEN + NET_IP_ALIGN;
+	if (np->ipv6)
+		ip_len = udp_len + sizeof(*ip6h);
+	else
+		ip_len = udp_len + sizeof(*iph);
 
-	skb = find_skb(np, total_len, total_len - len);
+	total_len = ip_len + LL_RESERVED_SPACE(np->dev);
+
+	skb = find_skb(np, total_len + np->dev->needed_tailroom,
+		       total_len - len);
 	if (!skb)
 		return;
 
-	memcpy(skb->data, msg, len);
-	skb->len += len;
+	skb_copy_to_linear_data(skb, msg, len);
+	skb_put(skb, len);
 
-	udph = (struct udphdr *) skb_push(skb, sizeof(*udph));
+	skb_push(skb, sizeof(*udph));
+	skb_reset_transport_header(skb);
+	udph = udp_hdr(skb);
 	udph->source = htons(np->local_port);
 	udph->dest = htons(np->remote_port);
 	udph->len = htons(udp_len);
-	udph->check = 0;
-
-	iph = (struct iphdr *)skb_push(skb, sizeof(*iph));
 
-	/* iph->version = 4; iph->ihl = 5; */
-	put_unaligned(0x45, (unsigned char *)iph);
-	iph->tos      = 0;
-	put_unaligned(htons(ip_len), &(iph->tot_len));
-	iph->id       = 0;
-	iph->frag_off = 0;
-	iph->ttl      = 64;
-	iph->protocol = IPPROTO_UDP;
-	iph->check    = 0;
-	put_unaligned(htonl(np->local_ip), &(iph->saddr));
-	put_unaligned(htonl(np->remote_ip), &(iph->daddr));
-	iph->check    = ip_fast_csum((unsigned char *)iph, iph->ihl);
-
-	eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
+	if (np->ipv6) {
+		udph->check = 0;
+		udph->check = csum_ipv6_magic(&np->local_ip.in6,
+					      &np->remote_ip.in6,
+					      udp_len, IPPROTO_UDP,
+					      csum_partial(udph, udp_len, 0));
+		if (udph->check == 0)
+			udph->check = CSUM_MANGLED_0;
+
+		skb_push(skb, sizeof(*ip6h));
+		skb_reset_network_header(skb);
+		ip6h = ipv6_hdr(skb);
+
+		/* ip6h->version = 6; ip6h->priority = 0; */
+		put_unaligned(0x60, (unsigned char *)ip6h);
+		ip6h->flow_lbl[0] = 0;
+		ip6h->flow_lbl[1] = 0;
+		ip6h->flow_lbl[2] = 0;
+
+		ip6h->payload_len = htons(sizeof(struct udphdr) + len);
+		ip6h->nexthdr = IPPROTO_UDP;
+		ip6h->hop_limit = 32;
+		ip6h->saddr = np->local_ip.in6;
+		ip6h->daddr = np->remote_ip.in6;
+
+		eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
+		skb_reset_mac_header(skb);
+		skb->protocol = eth->h_proto = htons(ETH_P_IPV6);
+	} else {
+		udph->check = 0;
+		udph->check = csum_tcpudp_magic(np->local_ip.ip,
+						np->remote_ip.ip,
+						udp_len, IPPROTO_UDP,
+						csum_partial(udph, udp_len, 0));
+		if (udph->check == 0)
+			udph->check = CSUM_MANGLED_0;
+
+		skb_push(skb, sizeof(*iph));
+		skb_reset_network_header(skb);
+		iph = ip_hdr(skb);
+
+		/* iph->version = 4; iph->ihl = 5; */
+		put_unaligned(0x45, (unsigned char *)iph);
+		iph->tos      = 0;
+		put_unaligned(htons(ip_len), &(iph->tot_len));
+		iph->id       = htons(atomic_inc_return(&ip_ident));
+		iph->frag_off = 0;
+		iph->ttl      = 64;
+		iph->protocol = IPPROTO_UDP;
+		iph->check    = 0;
+		put_unaligned(np->local_ip.ip, &(iph->saddr));
+		put_unaligned(np->remote_ip.ip, &(iph->daddr));
+		iph->check    = ip_fast_csum((unsigned char *)iph, iph->ihl);
+
+		eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
+		skb_reset_mac_header(skb);
+		skb->protocol = eth->h_proto = htons(ETH_P_IP);
+	}
 
-	eth->h_proto = htons(ETH_P_IP);
-	memcpy(eth->h_source, np->local_mac, 6);
-	memcpy(eth->h_dest, np->remote_mac, 6);
+	ether_addr_copy(eth->h_source, np->dev->dev_addr);
+	ether_addr_copy(eth->h_dest, np->remote_mac);
 
 	skb->dev = np->dev;
 
 	netpoll_send_skb(np, skb);
 }
+EXPORT_SYMBOL(netpoll_send_udp);
 
-static void arp_reply(struct sk_buff *skb)
+void netpoll_print_options(struct netpoll *np)
 {
-	struct netpoll_info *npinfo = skb->dev->npinfo;
-	struct arphdr *arp;
-	unsigned char *arp_ptr;
-	int size, type = ARPOP_REPLY, ptype = ETH_P_ARP;
-	u32 sip, tip;
-	struct sk_buff *send_skb;
-	struct netpoll *np = NULL;
-
-	if (npinfo->rx_np && npinfo->rx_np->dev == skb->dev)
-		np = npinfo->rx_np;
-	if (!np)
-		return;
-
-	/* No arp on this interface */
-	if (skb->dev->flags & IFF_NOARP)
-		return;
-
-	if (!pskb_may_pull(skb, (sizeof(struct arphdr) +
-				 (2 * skb->dev->addr_len) +
-				 (2 * sizeof(u32)))))
-		return;
-
-	skb->h.raw = skb->nh.raw = skb->data;
-	arp = skb->nh.arph;
-
-	if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
-	     arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
-	    arp->ar_pro != htons(ETH_P_IP) ||
-	    arp->ar_op != htons(ARPOP_REQUEST))
-		return;
-
-	arp_ptr = (unsigned char *)(arp+1) + skb->dev->addr_len;
-	memcpy(&sip, arp_ptr, 4);
-	arp_ptr += 4 + skb->dev->addr_len;
-	memcpy(&tip, arp_ptr, 4);
-
-	/* Should we ignore arp? */
-	if (tip != htonl(np->local_ip) || LOOPBACK(tip) || MULTICAST(tip))
-		return;
-
-	size = sizeof(struct arphdr) + 2 * (skb->dev->addr_len + 4);
-	send_skb = find_skb(np, size + LL_RESERVED_SPACE(np->dev),
-			    LL_RESERVED_SPACE(np->dev));
-
-	if (!send_skb)
-		return;
-
-	send_skb->nh.raw = send_skb->data;
-	arp = (struct arphdr *) skb_put(send_skb, size);
-	send_skb->dev = skb->dev;
-	send_skb->protocol = htons(ETH_P_ARP);
-
-	/* Fill the device header for the ARP frame */
-
-	if (np->dev->hard_header &&
-	    np->dev->hard_header(send_skb, skb->dev, ptype,
-				       np->remote_mac, np->local_mac,
-				       send_skb->len) < 0) {
-		kfree_skb(send_skb);
-		return;
-	}
-
-	/*
-	 * Fill out the arp protocol part.
-	 *
-	 * we only support ethernet device type,
-	 * which (according to RFC 1390) should always equal 1 (Ethernet).
-	 */
-
-	arp->ar_hrd = htons(np->dev->type);
-	arp->ar_pro = htons(ETH_P_IP);
-	arp->ar_hln = np->dev->addr_len;
-	arp->ar_pln = 4;
-	arp->ar_op = htons(type);
-
-	arp_ptr=(unsigned char *)(arp + 1);
-	memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
-	arp_ptr += np->dev->addr_len;
-	memcpy(arp_ptr, &tip, 4);
-	arp_ptr += 4;
-	memcpy(arp_ptr, np->remote_mac, np->dev->addr_len);
-	arp_ptr += np->dev->addr_len;
-	memcpy(arp_ptr, &sip, 4);
-
-	netpoll_send_skb(np, send_skb);
+	np_info(np, "local port %d\n", np->local_port);
+	if (np->ipv6)
+		np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
+	else
+		np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
+	np_info(np, "interface '%s'\n", np->dev_name);
+	np_info(np, "remote port %d\n", np->remote_port);
+	if (np->ipv6)
+		np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
+	else
+		np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip);
+	np_info(np, "remote ethernet address %pM\n", np->remote_mac);
 }
+EXPORT_SYMBOL(netpoll_print_options);
 
-int __netpoll_rx(struct sk_buff *skb)
+static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr)
 {
-	int proto, len, ulen;
-	struct iphdr *iph;
-	struct udphdr *uh;
-	struct netpoll *np = skb->dev->npinfo->rx_np;
+	const char *end;
 
-	if (!np)
-		goto out;
-	if (skb->dev->type != ARPHRD_ETHER)
-		goto out;
-
-	/* check if netpoll clients need ARP */
-	if (skb->protocol == __constant_htons(ETH_P_ARP) &&
-	    atomic_read(&trapped)) {
-		arp_reply(skb);
-		return 1;
+	if (!strchr(str, ':') &&
+	    in4_pton(str, -1, (void *)addr, -1, &end) > 0) {
+		if (!*end)
+			return 0;
 	}
-
-	proto = ntohs(eth_hdr(skb)->h_proto);
-	if (proto != ETH_P_IP)
-		goto out;
-	if (skb->pkt_type == PACKET_OTHERHOST)
-		goto out;
-	if (skb_shared(skb))
-		goto out;
-
-	iph = (struct iphdr *)skb->data;
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		goto out;
-	if (iph->ihl < 5 || iph->version != 4)
-		goto out;
-	if (!pskb_may_pull(skb, iph->ihl*4))
-		goto out;
-	if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
-		goto out;
-
-	len = ntohs(iph->tot_len);
-	if (skb->len < len || len < iph->ihl*4)
-		goto out;
-
-	if (iph->protocol != IPPROTO_UDP)
-		goto out;
-
-	len -= iph->ihl*4;
-	uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
-	ulen = ntohs(uh->len);
-
-	if (ulen != len)
-		goto out;
-	if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr) < 0)
-		goto out;
-	if (np->local_ip && np->local_ip != ntohl(iph->daddr))
-		goto out;
-	if (np->remote_ip && np->remote_ip != ntohl(iph->saddr))
-		goto out;
-	if (np->local_port && np->local_port != ntohs(uh->dest))
-		goto out;
-
-	np->rx_hook(np, ntohs(uh->source),
-		    (char *)(uh+1),
-		    ulen - sizeof(struct udphdr));
-
-	kfree_skb(skb);
-	return 1;
-
-out:
-	if (atomic_read(&trapped)) {
-		kfree_skb(skb);
-		return 1;
+	if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) {
+#if IS_ENABLED(CONFIG_IPV6)
+		if (!*end)
+			return 1;
+#else
+		return -1;
+#endif
 	}
-
-	return 0;
+	return -1;
 }
 
 int netpoll_parse_options(struct netpoll *np, char *opt)
 {
 	char *cur=opt, *delim;
+	int ipv6;
+	bool ipversion_set = false;
 
-	if(*cur != '@') {
+	if (*cur != '@') {
 		if ((delim = strchr(cur, '@')) == NULL)
 			goto parse_failed;
-		*delim=0;
-		np->local_port=simple_strtol(cur, NULL, 10);
-		cur=delim;
+		*delim = 0;
+		if (kstrtou16(cur, 10, &np->local_port))
+			goto parse_failed;
+		cur = delim;
 	}
 	cur++;
-	printk(KERN_INFO "%s: local port %d\n", np->name, np->local_port);
 
-	if(*cur != '/') {
+	if (*cur != '/') {
+		ipversion_set = true;
 		if ((delim = strchr(cur, '/')) == NULL)
 			goto parse_failed;
-		*delim=0;
-		np->local_ip=ntohl(in_aton(cur));
-		cur=delim;
-
-		printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n",
-		       np->name, HIPQUAD(np->local_ip));
+		*delim = 0;
+		ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip);
+		if (ipv6 < 0)
+			goto parse_failed;
+		else
+			np->ipv6 = (bool)ipv6;
+		cur = delim;
 	}
 	cur++;
 
-	if ( *cur != ',') {
+	if (*cur != ',') {
 		/* parse out dev name */
 		if ((delim = strchr(cur, ',')) == NULL)
 			goto parse_failed;
-		*delim=0;
+		*delim = 0;
 		strlcpy(np->dev_name, cur, sizeof(np->dev_name));
-		cur=delim;
+		cur = delim;
 	}
 	cur++;
 
-	printk(KERN_INFO "%s: interface %s\n", np->name, np->dev_name);
-
-	if ( *cur != '@' ) {
+	if (*cur != '@') {
 		/* dst port */
 		if ((delim = strchr(cur, '@')) == NULL)
 			goto parse_failed;
-		*delim=0;
-		np->remote_port=simple_strtol(cur, NULL, 10);
-		cur=delim;
+		*delim = 0;
+		if (*cur == ' ' || *cur == '\t')
+			np_info(np, "warning: whitespace is not allowed\n");
+		if (kstrtou16(cur, 10, &np->remote_port))
+			goto parse_failed;
+		cur = delim;
 	}
 	cur++;
-	printk(KERN_INFO "%s: remote port %d\n", np->name, np->remote_port);
 
 	/* dst ip */
 	if ((delim = strchr(cur, '/')) == NULL)
 		goto parse_failed;
-	*delim=0;
-	np->remote_ip=ntohl(in_aton(cur));
-	cur=delim+1;
-
-	printk(KERN_INFO "%s: remote IP %d.%d.%d.%d\n",
-		       np->name, HIPQUAD(np->remote_ip));
+	*delim = 0;
+	ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
+	if (ipv6 < 0)
+		goto parse_failed;
+	else if (ipversion_set && np->ipv6 != (bool)ipv6)
+		goto parse_failed;
+	else
+		np->ipv6 = (bool)ipv6;
+	cur = delim + 1;
 
-	if( *cur != 0 )
-	{
+	if (*cur != 0) {
 		/* MAC address */
-		if ((delim = strchr(cur, ':')) == NULL)
+		if (!mac_pton(cur, np->remote_mac))
 			goto parse_failed;
-		*delim=0;
-		np->remote_mac[0]=simple_strtol(cur, NULL, 16);
-		cur=delim+1;
-		if ((delim = strchr(cur, ':')) == NULL)
-			goto parse_failed;
-		*delim=0;
-		np->remote_mac[1]=simple_strtol(cur, NULL, 16);
-		cur=delim+1;
-		if ((delim = strchr(cur, ':')) == NULL)
-			goto parse_failed;
-		*delim=0;
-		np->remote_mac[2]=simple_strtol(cur, NULL, 16);
-		cur=delim+1;
-		if ((delim = strchr(cur, ':')) == NULL)
-			goto parse_failed;
-		*delim=0;
-		np->remote_mac[3]=simple_strtol(cur, NULL, 16);
-		cur=delim+1;
-		if ((delim = strchr(cur, ':')) == NULL)
-			goto parse_failed;
-		*delim=0;
-		np->remote_mac[4]=simple_strtol(cur, NULL, 16);
-		cur=delim+1;
-		np->remote_mac[5]=simple_strtol(cur, NULL, 16);
 	}
 
-	printk(KERN_INFO "%s: remote ethernet address "
-	       "%02x:%02x:%02x:%02x:%02x:%02x\n",
-	       np->name,
-	       np->remote_mac[0],
-	       np->remote_mac[1],
-	       np->remote_mac[2],
-	       np->remote_mac[3],
-	       np->remote_mac[4],
-	       np->remote_mac[5]);
+	netpoll_print_options(np);
 
 	return 0;
 
  parse_failed:
-	printk(KERN_INFO "%s: couldn't parse config at %s!\n",
-	       np->name, cur);
+	np_info(np, "couldn't parse config at '%s'!\n", cur);
 	return -1;
 }
+EXPORT_SYMBOL(netpoll_parse_options);
+
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
+{
+	struct netpoll_info *npinfo;
+	const struct net_device_ops *ops;
+	int err;
+
+	np->dev = ndev;
+	strlcpy(np->dev_name, ndev->name, IFNAMSIZ);
+	INIT_WORK(&np->cleanup_work, netpoll_async_cleanup);
+
+	if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) ||
+	    !ndev->netdev_ops->ndo_poll_controller) {
+		np_err(np, "%s doesn't support polling, aborting\n",
+		       np->dev_name);
+		err = -ENOTSUPP;
+		goto out;
+	}
+
+	if (!ndev->npinfo) {
+		npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
+		if (!npinfo) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		sema_init(&npinfo->dev_lock, 1);
+		skb_queue_head_init(&npinfo->txq);
+		INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
+
+		atomic_set(&npinfo->refcnt, 1);
+
+		ops = np->dev->netdev_ops;
+		if (ops->ndo_netpoll_setup) {
+			err = ops->ndo_netpoll_setup(ndev, npinfo);
+			if (err)
+				goto free_npinfo;
+		}
+	} else {
+		npinfo = rtnl_dereference(ndev->npinfo);
+		atomic_inc(&npinfo->refcnt);
+	}
+
+	npinfo->netpoll = np;
+
+	/* last thing to do is link it to the net device structure */
+	rcu_assign_pointer(ndev->npinfo, npinfo);
+
+	return 0;
+
+free_npinfo:
+	kfree(npinfo);
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(__netpoll_setup);
 
 int netpoll_setup(struct netpoll *np)
 {
 	struct net_device *ndev = NULL;
 	struct in_device *in_dev;
-	struct netpoll_info *npinfo;
-	unsigned long flags;
+	int err;
 
-	if (np->dev_name)
-		ndev = dev_get_by_name(np->dev_name);
+	rtnl_lock();
+	if (np->dev_name) {
+		struct net *net = current->nsproxy->net_ns;
+		ndev = __dev_get_by_name(net, np->dev_name);
+	}
 	if (!ndev) {
-		printk(KERN_ERR "%s: %s doesn't exist, aborting.\n",
-		       np->name, np->dev_name);
-		return -1;
+		np_err(np, "%s doesn't exist, aborting\n", np->dev_name);
+		err = -ENODEV;
+		goto unlock;
 	}
+	dev_hold(ndev);
 
-	np->dev = ndev;
-	if (!ndev->npinfo) {
-		npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
-		if (!npinfo)
-			goto release;
-
-		npinfo->rx_flags = 0;
-		npinfo->rx_np = NULL;
-		spin_lock_init(&npinfo->poll_lock);
-		npinfo->poll_owner = -1;
-		npinfo->tries = MAX_RETRIES;
-		spin_lock_init(&npinfo->rx_lock);
-	} else
-		npinfo = ndev->npinfo;
-
-	if (!ndev->poll_controller) {
-		printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n",
-		       np->name, np->dev_name);
-		goto release;
+	if (netdev_master_upper_dev_get(ndev)) {
+		np_err(np, "%s is a slave device, aborting\n", np->dev_name);
+		err = -EBUSY;
+		goto put;
 	}
 
 	if (!netif_running(ndev)) {
 		unsigned long atmost, atleast;
 
-		printk(KERN_INFO "%s: device %s not up yet, forcing it\n",
-		       np->name, np->dev_name);
+		np_info(np, "device %s not up yet, forcing it\n", np->dev_name);
 
-		rtnl_shlock();
-		if (dev_change_flags(ndev, ndev->flags | IFF_UP) < 0) {
-			printk(KERN_ERR "%s: failed to open %s\n",
-			       np->name, np->dev_name);
-			rtnl_shunlock();
-			goto release;
+		err = dev_open(ndev);
+
+		if (err) {
+			np_err(np, "failed to open %s\n", ndev->name);
+			goto put;
 		}
-		rtnl_shunlock();
 
+		rtnl_unlock();
 		atleast = jiffies + HZ/10;
- 		atmost = jiffies + 4*HZ;
+		atmost = jiffies + carrier_timeout * HZ;
 		while (!netif_carrier_ok(ndev)) {
 			if (time_after(jiffies, atmost)) {
-				printk(KERN_NOTICE
-				       "%s: timeout waiting for carrier\n",
-				       np->name);
+				np_notice(np, "timeout waiting for carrier\n");
 				break;
 			}
-			cond_resched();
+			msleep(1);
 		}
 
 		/* If carrier appears to come up instantly, we don't
@@ -691,96 +704,153 @@ int netpoll_setup(struct netpoll *np)
 		 */
 
 		if (time_before(jiffies, atleast)) {
-			printk(KERN_NOTICE "%s: carrier detect appears"
-			       " untrustworthy, waiting 4 seconds\n",
-			       np->name);
+			np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n");
 			msleep(4000);
 		}
+		rtnl_lock();
 	}
 
-	if (!memcmp(np->local_mac, "\0\0\0\0\0\0", 6) && ndev->dev_addr)
-		memcpy(np->local_mac, ndev->dev_addr, 6);
+	if (!np->local_ip.ip) {
+		if (!np->ipv6) {
+			in_dev = __in_dev_get_rtnl(ndev);
 
-	if (!np->local_ip) {
-		rcu_read_lock();
-		in_dev = __in_dev_get_rcu(ndev);
+			if (!in_dev || !in_dev->ifa_list) {
+				np_err(np, "no IP address for %s, aborting\n",
+				       np->dev_name);
+				err = -EDESTADDRREQ;
+				goto put;
+			}
 
-		if (!in_dev || !in_dev->ifa_list) {
-			rcu_read_unlock();
-			printk(KERN_ERR "%s: no IP address for %s, aborting\n",
-			       np->name, np->dev_name);
-			goto release;
+			np->local_ip.ip = in_dev->ifa_list->ifa_local;
+			np_info(np, "local IP %pI4\n", &np->local_ip.ip);
+		} else {
+#if IS_ENABLED(CONFIG_IPV6)
+			struct inet6_dev *idev;
+
+			err = -EDESTADDRREQ;
+			idev = __in6_dev_get(ndev);
+			if (idev) {
+				struct inet6_ifaddr *ifp;
+
+				read_lock_bh(&idev->lock);
+				list_for_each_entry(ifp, &idev->addr_list, if_list) {
+					if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)
+						continue;
+					np->local_ip.in6 = ifp->addr;
+					err = 0;
+					break;
+				}
+				read_unlock_bh(&idev->lock);
+			}
+			if (err) {
+				np_err(np, "no IPv6 address for %s, aborting\n",
+				       np->dev_name);
+				goto put;
+			} else
+				np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6);
+#else
+			np_err(np, "IPv6 is not supported %s, aborting\n",
+			       np->dev_name);
+			err = -EINVAL;
+			goto put;
+#endif
 		}
-
-		np->local_ip = ntohl(in_dev->ifa_list->ifa_local);
-		rcu_read_unlock();
-		printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n",
-		       np->name, HIPQUAD(np->local_ip));
-	}
-
-	if (np->rx_hook) {
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		npinfo->rx_flags |= NETPOLL_RX_ENABLED;
-		npinfo->rx_np = np;
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
 	}
 
 	/* fill up the skb queue */
 	refill_skbs();
 
-	/* last thing to do is link it to the net device structure */
-	ndev->npinfo = npinfo;
-
-	/* avoid racing with NAPI reading npinfo */
-	synchronize_rcu();
+	err = __netpoll_setup(np, ndev);
+	if (err)
+		goto put;
 
+	rtnl_unlock();
 	return 0;
 
- release:
-	if (!ndev->npinfo)
-		kfree(npinfo);
-	np->dev = NULL;
+put:
 	dev_put(ndev);
-	return -1;
+unlock:
+	rtnl_unlock();
+	return err;
 }
+EXPORT_SYMBOL(netpoll_setup);
 
-void netpoll_cleanup(struct netpoll *np)
+static int __init netpoll_init(void)
+{
+	skb_queue_head_init(&skb_pool);
+	return 0;
+}
+core_initcall(netpoll_init);
+
+static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
+{
+	struct netpoll_info *npinfo =
+			container_of(rcu_head, struct netpoll_info, rcu);
+
+	skb_queue_purge(&npinfo->txq);
+
+	/* we can't call cancel_delayed_work_sync here, as we are in softirq */
+	cancel_delayed_work(&npinfo->tx_work);
+
+	/* clean after last, unfinished work */
+	__skb_queue_purge(&npinfo->txq);
+	/* now cancel it again */
+	cancel_delayed_work(&npinfo->tx_work);
+	kfree(npinfo);
+}
+
+void __netpoll_cleanup(struct netpoll *np)
 {
 	struct netpoll_info *npinfo;
-	unsigned long flags;
 
-	if (np->dev) {
-		npinfo = np->dev->npinfo;
-		if (npinfo && npinfo->rx_np == np) {
-			spin_lock_irqsave(&npinfo->rx_lock, flags);
-			npinfo->rx_np = NULL;
-			npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
-			spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-		}
-		dev_put(np->dev);
-	}
+	/* rtnl_dereference would be preferable here but
+	 * rcu_cleanup_netpoll path can put us in here safely without
+	 * holding the rtnl, so plain rcu_dereference it is
+	 */
+	npinfo = rtnl_dereference(np->dev->npinfo);
+	if (!npinfo)
+		return;
 
-	np->dev = NULL;
+	synchronize_srcu(&netpoll_srcu);
+
+	if (atomic_dec_and_test(&npinfo->refcnt)) {
+		const struct net_device_ops *ops;
+
+		ops = np->dev->netdev_ops;
+		if (ops->ndo_netpoll_cleanup)
+			ops->ndo_netpoll_cleanup(np->dev);
+
+		RCU_INIT_POINTER(np->dev->npinfo, NULL);
+		call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
+	}
 }
+EXPORT_SYMBOL_GPL(__netpoll_cleanup);
 
-int netpoll_trap(void)
+static void netpoll_async_cleanup(struct work_struct *work)
 {
-	return atomic_read(&trapped);
+	struct netpoll *np = container_of(work, struct netpoll, cleanup_work);
+
+	rtnl_lock();
+	__netpoll_cleanup(np);
+	rtnl_unlock();
+	kfree(np);
 }
 
-void netpoll_set_trap(int trap)
+void __netpoll_free_async(struct netpoll *np)
 {
-	if (trap)
-		atomic_inc(&trapped);
-	else
-		atomic_dec(&trapped);
+	schedule_work(&np->cleanup_work);
 }
+EXPORT_SYMBOL_GPL(__netpoll_free_async);
 
-EXPORT_SYMBOL(netpoll_set_trap);
-EXPORT_SYMBOL(netpoll_trap);
-EXPORT_SYMBOL(netpoll_parse_options);
-EXPORT_SYMBOL(netpoll_setup);
+void netpoll_cleanup(struct netpoll *np)
+{
+	rtnl_lock();
+	if (!np->dev)
+		goto out;
+	__netpoll_cleanup(np);
+	dev_put(np->dev);
+	np->dev = NULL;
+out:
+	rtnl_unlock();
+}
 EXPORT_SYMBOL(netpoll_cleanup);
-EXPORT_SYMBOL(netpoll_send_udp);
-EXPORT_SYMBOL(netpoll_poll);
-EXPORT_SYMBOL(netpoll_queue);