* Copyright (C) 2002 Red Hat, Inc.
*/
-#include <linux/smp_lock.h>
+#include <linux/moduleparam.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/string.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <asm/unaligned.h>
+#include <trace/events/napi.h>
/*
* We maintain a small pool of fully-sized skbs, to make sure the
static void zap_completion_queue(void);
static void arp_reply(struct sk_buff *skb);
+static unsigned int carrier_timeout = 4;
+module_param(carrier_timeout, uint, 0644);
+
static void queue_process(struct work_struct *work)
{
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;
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct netdev_queue *txq;
if (!netif_device_present(dev) || !netif_running(dev)) {
__kfree_skb(skb);
continue;
}
- netif_tx_lock_bh(dev);
- if (netif_queue_stopped(dev) ||
- dev->hard_start_xmit(skb, dev) != NETDEV_TX_OK) {
+ txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+
+ local_irq_save(flags);
+ __netif_tx_lock(txq, smp_processor_id());
+ if (netif_tx_queue_stopped(txq) ||
+ netif_tx_queue_frozen(txq) ||
+ ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {
skb_queue_head(&npinfo->txq, skb);
- netif_tx_unlock_bh(dev);
+ __netif_tx_unlock(txq);
+ local_irq_restore(flags);
schedule_delayed_work(&npinfo->tx_work, HZ/10);
return;
}
+ __netif_tx_unlock(txq);
+ local_irq_restore(flags);
}
}
{
__wsum psum;
- if (uh->check == 0 || skb->ip_summed == CHECKSUM_UNNECESSARY)
+ if (uh->check == 0 || skb_csum_unnecessary(skb))
return 0;
psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
* 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 netpoll_info *npinfo,
+ 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);
+ npinfo->rx_flags |= NETPOLL_RX_DROP;
+ atomic_inc(&trapped);
+ 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);
+ trace_napi_poll(napi);
+
+ clear_bit(NAPI_STATE_NPSVC, &napi->state);
+ atomic_dec(&trapped);
+ npinfo->rx_flags &= ~NETPOLL_RX_DROP;
+
+ return budget - work;
}
-static void service_arp_queue(struct netpoll_info *npi)
+static void poll_napi(struct net_device *dev)
{
- struct sk_buff *skb;
+ struct napi_struct *napi;
+ int budget = 16;
- if (unlikely(!npi))
- return;
+ 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(dev->npinfo, napi, budget);
+ spin_unlock(&napi->poll_lock);
+
+ if (!budget)
+ break;
+ }
+ }
+}
- skb = skb_dequeue(&npi->arp_tx);
+static void service_arp_queue(struct netpoll_info *npi)
+{
+ if (npi) {
+ struct sk_buff *skb;
- while (skb != NULL) {
- arp_reply(skb);
- skb = skb_dequeue(&npi->arp_tx);
+ while ((skb = skb_dequeue(&npi->arp_tx)))
+ arp_reply(skb);
}
}
void netpoll_poll(struct netpoll *np)
{
- if (!np->dev || !netif_running(np->dev) || !np->dev->poll_controller)
+ struct net_device *dev = np->dev;
+ const struct net_device_ops *ops;
+
+ if (!dev || !netif_running(dev))
+ return;
+
+ ops = dev->netdev_ops;
+ if (!ops->ndo_poll_controller)
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);
- service_arp_queue(np->dev->npinfo);
+ service_arp_queue(dev->npinfo);
zap_completion_queue();
}
while (clist != NULL) {
struct sk_buff *skb = clist;
clist = clist->next;
- if (skb->destructor)
+ if (skb->destructor) {
+ atomic_inc(&skb->users);
dev_kfree_skb_any(skb); /* put this one back */
- else
+ } else {
__kfree_skb(skb);
+ }
}
}
return skb;
}
+static int netpoll_owner_active(struct net_device *dev)
+{
+ struct napi_struct *napi;
+
+ list_for_each_entry(napi, &dev->napi_list, dev_list) {
+ if (napi->poll_owner == smp_processor_id())
+ return 1;
+ }
+ return 0;
+}
+
static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
{
int status = NETDEV_TX_BUSY;
unsigned long tries;
- struct net_device *dev = np->dev;
- struct netpoll_info *npinfo = np->dev->npinfo;
+ struct net_device *dev = np->dev;
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct netpoll_info *npinfo = np->dev->npinfo;
- if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
- __kfree_skb(skb);
- return;
- }
+ if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
+ __kfree_skb(skb);
+ return;
+ }
/* don't get messages out of order, and no recursion */
- if (skb_queue_len(&npinfo->txq) == 0 &&
- npinfo->poll_owner != smp_processor_id()) {
+ if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
+ struct netdev_queue *txq;
unsigned long flags;
+ txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+
local_irq_save(flags);
- if (netif_tx_trylock(dev)) {
- /* try until next clock tick */
- for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
- tries > 0; --tries) {
- if (!netif_queue_stopped(dev))
- status = dev->hard_start_xmit(skb, dev);
+ /* try until next clock tick */
+ for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
+ tries > 0; --tries) {
+ if (__netif_tx_trylock(txq)) {
+ if (!netif_tx_queue_stopped(txq)) {
+ status = ops->ndo_start_xmit(skb, dev);
+ if (status == NETDEV_TX_OK)
+ txq_trans_update(txq);
+ }
+ __netif_tx_unlock(txq);
if (status == NETDEV_TX_OK)
break;
- /* tickle device maybe there is some cleanup */
- netpoll_poll(np);
-
- udelay(USEC_PER_POLL);
}
- netif_tx_unlock(dev);
+
+ /* tickle device maybe there is some cleanup */
+ netpoll_poll(np);
+
+ udelay(USEC_PER_POLL);
}
+
+ WARN_ONCE(!irqs_disabled(),
+ "netpoll_send_skb(): %s enabled interrupts in poll (%pF)\n",
+ dev->name, ops->ndo_start_xmit);
+
local_irq_restore(flags);
}
if (!skb)
return;
- memcpy(skb->data, msg, len);
+ skb_copy_to_linear_data(skb, msg, len);
skb->len += len;
- skb->h.uh = 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;
- udph->check = csum_tcpudp_magic(htonl(np->local_ip),
- htonl(np->remote_ip),
+ udph->check = csum_tcpudp_magic(np->local_ip,
+ np->remote_ip,
udp_len, IPPROTO_UDP,
- csum_partial((unsigned char *)udph, udp_len, 0));
+ csum_partial(udph, udp_len, 0));
if (udph->check == 0)
udph->check = CSUM_MANGLED_0;
- skb->nh.iph = iph = (struct iphdr *)skb_push(skb, sizeof(*iph));
+ 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->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));
+ put_unaligned(np->local_ip, &(iph->saddr));
+ put_unaligned(np->remote_ip, &(iph->daddr));
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
- skb->mac.raw = skb->data;
+ skb_reset_mac_header(skb);
skb->protocol = eth->h_proto = htons(ETH_P_IP);
- memcpy(eth->h_source, np->local_mac, 6);
- memcpy(eth->h_dest, np->remote_mac, 6);
+ memcpy(eth->h_source, np->dev->dev_addr, ETH_ALEN);
+ memcpy(eth->h_dest, np->remote_mac, ETH_ALEN);
skb->dev = np->dev;
if (skb->dev->flags & IFF_NOARP)
return;
- if (!pskb_may_pull(skb, (sizeof(struct arphdr) +
- (2 * skb->dev->addr_len) +
- (2 * sizeof(u32)))))
+ if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
return;
- skb->h.raw = skb->nh.raw = skb->data;
- arp = skb->nh.arph;
+ skb_reset_network_header(skb);
+ skb_reset_transport_header(skb);
+ arp = arp_hdr(skb);
if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
memcpy(&tip, arp_ptr, 4);
/* Should we ignore arp? */
- if (tip != htonl(np->local_ip) || LOOPBACK(tip) || MULTICAST(tip))
+ if (tip != np->local_ip ||
+ ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
return;
- size = sizeof(struct arphdr) + 2 * (skb->dev->addr_len + 4);
- send_skb = find_skb(np, size + LL_RESERVED_SPACE(np->dev),
+ size = arp_hdr_len(skb->dev);
+ send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev),
LL_RESERVED_SPACE(np->dev));
if (!send_skb)
return;
- send_skb->nh.raw = send_skb->data;
+ skb_reset_network_header(send_skb);
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,
- sha, np->local_mac,
- send_skb->len) < 0) {
+ if (dev_hard_header(send_skb, skb->dev, ptype,
+ sha, np->dev->dev_addr,
+ send_skb->len) < 0) {
kfree_skb(send_skb);
return;
}
goto out;
/* check if netpoll clients need ARP */
- if (skb->protocol == __constant_htons(ETH_P_ARP) &&
+ if (skb->protocol == htons(ETH_P_ARP) &&
atomic_read(&trapped)) {
skb_queue_tail(&npi->arp_tx, skb);
return 1;
if (skb->len < len || len < iph->ihl*4)
goto out;
+ /*
+ * Our transport medium may have padded the buffer out.
+ * Now We trim to the true length of the frame.
+ */
+ if (pskb_trim_rcsum(skb, len))
+ goto out;
+
if (iph->protocol != IPPROTO_UDP)
goto out;
goto out;
if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
goto out;
- if (np->local_ip && np->local_ip != ntohl(iph->daddr))
+ if (np->local_ip && np->local_ip != iph->daddr)
goto out;
- if (np->remote_ip && np->remote_ip != ntohl(iph->saddr))
+ if (np->remote_ip && np->remote_ip != iph->saddr)
goto out;
if (np->local_port && np->local_port != ntohs(uh->dest))
goto out;
return 0;
}
+void netpoll_print_options(struct netpoll *np)
+{
+ printk(KERN_INFO "%s: local port %d\n",
+ np->name, np->local_port);
+ printk(KERN_INFO "%s: local IP %pI4\n",
+ np->name, &np->local_ip);
+ printk(KERN_INFO "%s: interface %s\n",
+ np->name, np->dev_name);
+ printk(KERN_INFO "%s: remote port %d\n",
+ np->name, np->remote_port);
+ printk(KERN_INFO "%s: remote IP %pI4\n",
+ np->name, &np->remote_ip);
+ printk(KERN_INFO "%s: remote ethernet address %pM\n",
+ np->name, np->remote_mac);
+}
+
int netpoll_parse_options(struct netpoll *np, char *opt)
{
char *cur=opt, *delim;
cur = delim;
}
cur++;
- printk(KERN_INFO "%s: local port %d\n", np->name, np->local_port);
if (*cur != '/') {
if ((delim = strchr(cur, '/')) == NULL)
goto parse_failed;
*delim = 0;
- np->local_ip = ntohl(in_aton(cur));
+ np->local_ip = in_aton(cur);
cur = delim;
-
- printk(KERN_INFO "%s: local IP %d.%d.%d.%d\n",
- np->name, HIPQUAD(np->local_ip));
}
cur++;
}
cur++;
- printk(KERN_INFO "%s: interface %s\n", np->name, np->dev_name);
-
if (*cur != '@') {
/* dst port */
if ((delim = strchr(cur, '@')) == NULL)
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));
+ np->remote_ip = in_aton(cur);
cur = delim + 1;
- printk(KERN_INFO "%s: remote IP %d.%d.%d.%d\n",
- np->name, HIPQUAD(np->remote_ip));
-
if (*cur != 0) {
/* MAC address */
if ((delim = strchr(cur, ':')) == NULL)
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;
int err;
if (np->dev_name)
- ndev = dev_get_by_name(np->dev_name);
+ ndev = dev_get_by_name(&init_net, np->dev_name);
if (!ndev) {
printk(KERN_ERR "%s: %s doesn't exist, aborting.\n",
np->name, np->dev_name);
npinfo->rx_flags = 0;
npinfo->rx_np = NULL;
- spin_lock_init(&npinfo->poll_lock);
- npinfo->poll_owner = -1;
spin_lock_init(&npinfo->rx_lock);
skb_queue_head_init(&npinfo->arp_tx);
atomic_inc(&npinfo->refcnt);
}
- if (!ndev->poll_controller) {
+ if (!ndev->netdev_ops->ndo_poll_controller) {
printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n",
np->name, np->dev_name);
err = -ENOTSUPP;
}
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
np->name);
break;
}
- cond_resched();
+ msleep(1);
}
/* If carrier appears to come up instantly, we don't
}
}
- if (is_zero_ether_addr(np->local_mac) && ndev->dev_addr)
- memcpy(np->local_mac, ndev->dev_addr, 6);
-
if (!np->local_ip) {
rcu_read_lock();
in_dev = __in_dev_get_rcu(ndev);
goto release;
}
- np->local_ip = ntohl(in_dev->ifa_list->ifa_local);
+ np->local_ip = 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));
+ printk(KERN_INFO "%s: local IP %pI4\n", np->name, &np->local_ip);
}
if (np->rx_hook) {
spin_unlock_irqrestore(&npinfo->rx_lock, flags);
}
- np->dev->npinfo = NULL;
if (atomic_dec_and_test(&npinfo->refcnt)) {
skb_queue_purge(&npinfo->arp_tx);
- skb_queue_purge(&npinfo->txq);
+ skb_queue_purge(&npinfo->txq);
cancel_rearming_delayed_work(&npinfo->tx_work);
- flush_scheduled_work();
+ /* clean after last, unfinished work */
+ __skb_queue_purge(&npinfo->txq);
kfree(npinfo);
+ np->dev->npinfo = NULL;
}
}
EXPORT_SYMBOL(netpoll_set_trap);
EXPORT_SYMBOL(netpoll_trap);
+EXPORT_SYMBOL(netpoll_print_options);
EXPORT_SYMBOL(netpoll_parse_options);
EXPORT_SYMBOL(netpoll_setup);
EXPORT_SYMBOL(netpoll_cleanup);